diff options
Diffstat (limited to 'fs')
97 files changed, 1565 insertions, 960 deletions
diff --git a/fs/afs/callback.c b/fs/afs/callback.c index 1c7955f5cdaf..128f2dbe256a 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -203,8 +203,7 @@ void afs_put_cb_interest(struct afs_net *net, struct afs_cb_interest *cbi) */ void afs_init_callback_state(struct afs_server *server) { - if (!test_and_clear_bit(AFS_SERVER_FL_NEW, &server->flags)) - server->cb_s_break++; + server->cb_s_break++; } /* diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index 8ee5972893ed..2f8acb4c556d 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -34,7 +34,7 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *); static int afs_deliver_yfs_cb_callback(struct afs_call *); #define CM_NAME(name) \ - const char afs_SRXCB##name##_name[] __tracepoint_string = \ + char afs_SRXCB##name##_name[] __tracepoint_string = \ "CB." #name /* diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index ca08c83168f5..0b37867b5c20 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -1515,8 +1515,8 @@ static int afs_fs_setattr_size64(struct afs_fs_cursor *fc, struct iattr *attr) xdr_encode_AFS_StoreStatus(&bp, attr); - *bp++ = 0; /* position of start of write */ - *bp++ = 0; + *bp++ = htonl(attr->ia_size >> 32); /* position of start of write */ + *bp++ = htonl((u32) attr->ia_size); *bp++ = 0; /* size of write */ *bp++ = 0; *bp++ = htonl(attr->ia_size >> 32); /* new file length */ @@ -1564,7 +1564,7 @@ static int afs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) xdr_encode_AFS_StoreStatus(&bp, attr); - *bp++ = 0; /* position of start of write */ + *bp++ = htonl(attr->ia_size); /* position of start of write */ *bp++ = 0; /* size of write */ *bp++ = htonl(attr->ia_size); /* new file length */ diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 1a4ce07fb406..9cedc3fc1b77 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -216,9 +216,7 @@ struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root) set_nlink(inode, 2); inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; - inode->i_ctime.tv_sec = get_seconds(); - inode->i_ctime.tv_nsec = 0; - inode->i_atime = inode->i_mtime = inode->i_ctime; + inode->i_ctime = inode->i_atime = inode->i_mtime = current_time(inode); inode->i_blocks = 0; inode_set_iversion_raw(inode, 0); inode->i_generation = 0; diff --git a/fs/afs/internal.h b/fs/afs/internal.h index bb1f244b2b3a..3904ab0b9563 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -474,7 +474,6 @@ struct afs_server { time64_t put_time; /* Time at which last put */ time64_t update_at; /* Time at which to next update the record */ unsigned long flags; -#define AFS_SERVER_FL_NEW 0 /* New server, don't inc cb_s_break */ #define AFS_SERVER_FL_NOT_READY 1 /* The record is not ready for use */ #define AFS_SERVER_FL_NOT_FOUND 2 /* VL server says no such server */ #define AFS_SERVER_FL_VL_FAIL 3 /* Failed to access VL server */ @@ -827,7 +826,7 @@ static inline struct afs_cb_interest *afs_get_cb_interest(struct afs_cb_interest static inline unsigned int afs_calc_vnode_cb_break(struct afs_vnode *vnode) { - return vnode->cb_break + vnode->cb_s_break + vnode->cb_v_break; + return vnode->cb_break + vnode->cb_v_break; } static inline bool afs_cb_is_broken(unsigned int cb_break, @@ -835,7 +834,6 @@ static inline bool afs_cb_is_broken(unsigned int cb_break, const struct afs_cb_interest *cbi) { return !cbi || cb_break != (vnode->cb_break + - cbi->server->cb_s_break + vnode->volume->cb_v_break); } diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 2c588f9bbbda..15c7e82d80cb 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -572,13 +572,17 @@ static void afs_deliver_to_call(struct afs_call *call) case -ENODATA: case -EBADMSG: case -EMSGSIZE: - default: abort_code = RXGEN_CC_UNMARSHAL; if (state != AFS_CALL_CL_AWAIT_REPLY) abort_code = RXGEN_SS_UNMARSHAL; rxrpc_kernel_abort_call(call->net->socket, call->rxcall, abort_code, ret, "KUM"); goto local_abort; + default: + abort_code = RX_USER_ABORT; + rxrpc_kernel_abort_call(call->net->socket, call->rxcall, + abort_code, ret, "KER"); + goto local_abort; } } @@ -610,6 +614,7 @@ static long afs_wait_for_call_to_complete(struct afs_call *call, bool stalled = false; u64 rtt; u32 life, last_life; + bool rxrpc_complete = false; DECLARE_WAITQUEUE(myself, current); @@ -621,7 +626,7 @@ static long afs_wait_for_call_to_complete(struct afs_call *call, rtt2 = 2; timeout = rtt2; - last_life = rxrpc_kernel_check_life(call->net->socket, call->rxcall); + rxrpc_kernel_check_life(call->net->socket, call->rxcall, &last_life); add_wait_queue(&call->waitq, &myself); for (;;) { @@ -639,7 +644,12 @@ static long afs_wait_for_call_to_complete(struct afs_call *call, if (afs_check_call_state(call, AFS_CALL_COMPLETE)) break; - life = rxrpc_kernel_check_life(call->net->socket, call->rxcall); + if (!rxrpc_kernel_check_life(call->net->socket, call->rxcall, &life)) { + /* rxrpc terminated the call. */ + rxrpc_complete = true; + break; + } + if (timeout == 0 && life == last_life && signal_pending(current)) { if (stalled) @@ -663,12 +673,16 @@ static long afs_wait_for_call_to_complete(struct afs_call *call, remove_wait_queue(&call->waitq, &myself); __set_current_state(TASK_RUNNING); - /* Kill off the call if it's still live. */ if (!afs_check_call_state(call, AFS_CALL_COMPLETE)) { - _debug("call interrupted"); - if (rxrpc_kernel_abort_call(call->net->socket, call->rxcall, - RX_USER_ABORT, -EINTR, "KWI")) - afs_set_call_complete(call, -EINTR, 0); + if (rxrpc_complete) { + afs_set_call_complete(call, call->error, call->abort_code); + } else { + /* Kill off the call if it's still live. */ + _debug("call interrupted"); + if (rxrpc_kernel_abort_call(call->net->socket, call->rxcall, + RX_USER_ABORT, -EINTR, "KWI")) + afs_set_call_complete(call, -EINTR, 0); + } } spin_lock_bh(&call->state_lock); diff --git a/fs/afs/server.c b/fs/afs/server.c index 642afa2e9783..65b33b6da48b 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -226,7 +226,6 @@ static struct afs_server *afs_alloc_server(struct afs_net *net, RCU_INIT_POINTER(server->addresses, alist); server->addr_version = alist->version; server->uuid = *uuid; - server->flags = (1UL << AFS_SERVER_FL_NEW); server->update_at = ktime_get_real_seconds() + afs_server_update_delay; rwlock_init(&server->fs_lock); INIT_HLIST_HEAD(&server->cb_volumes); diff --git a/fs/afs/write.c b/fs/afs/write.c index 72efcfcf9f95..0122d7445fba 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -264,6 +264,7 @@ static void afs_kill_pages(struct address_space *mapping, first = page->index + 1; lock_page(page); generic_error_remove_page(mapping, page); + unlock_page(page); } __pagevec_release(&pv); diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index 5aa57929e8c2..6e97a42d24d1 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -1514,7 +1514,7 @@ static int yfs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) bp = xdr_encode_u32(bp, 0); /* RPC flags */ bp = xdr_encode_YFSFid(bp, &vnode->fid); bp = xdr_encode_YFS_StoreStatus(bp, attr); - bp = xdr_encode_u64(bp, 0); /* position of start of write */ + bp = xdr_encode_u64(bp, attr->ia_size); /* position of start of write */ bp = xdr_encode_u64(bp, 0); /* size of write */ bp = xdr_encode_u64(bp, attr->ia_size); /* new file length */ yfs_check_req(call, bp); @@ -181,7 +181,7 @@ struct poll_iocb { struct file *file; struct wait_queue_head *head; __poll_t events; - bool woken; + bool done; bool cancelled; struct wait_queue_entry wait; struct work_struct work; @@ -204,8 +204,7 @@ struct aio_kiocb { struct kioctx *ki_ctx; kiocb_cancel_fn *ki_cancel; - struct iocb __user *ki_user_iocb; /* user's aiocb */ - __u64 ki_user_data; /* user's data for completion */ + struct io_event ki_res; struct list_head ki_list; /* the aio core uses this * for cancellation */ @@ -1022,6 +1021,9 @@ static bool get_reqs_available(struct kioctx *ctx) /* aio_get_req * Allocate a slot for an aio request. * Returns NULL if no requests are free. + * + * The refcount is initialized to 2 - one for the async op completion, + * one for the synchronous code that does this. */ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx) { @@ -1031,10 +1033,15 @@ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx) if (unlikely(!req)) return NULL; + if (unlikely(!get_reqs_available(ctx))) { + kmem_cache_free(kiocb_cachep, req); + return NULL; + } + percpu_ref_get(&ctx->reqs); req->ki_ctx = ctx; INIT_LIST_HEAD(&req->ki_list); - refcount_set(&req->ki_refcnt, 0); + refcount_set(&req->ki_refcnt, 2); req->ki_eventfd = NULL; return req; } @@ -1067,30 +1074,20 @@ out: return ret; } -static inline void iocb_put(struct aio_kiocb *iocb) -{ - if (refcount_read(&iocb->ki_refcnt) == 0 || - refcount_dec_and_test(&iocb->ki_refcnt)) { - if (iocb->ki_filp) - fput(iocb->ki_filp); - percpu_ref_put(&iocb->ki_ctx->reqs); - kmem_cache_free(kiocb_cachep, iocb); - } -} - -static void aio_fill_event(struct io_event *ev, struct aio_kiocb *iocb, - long res, long res2) +static inline void iocb_destroy(struct aio_kiocb *iocb) { - ev->obj = (u64)(unsigned long)iocb->ki_user_iocb; - ev->data = iocb->ki_user_data; - ev->res = res; - ev->res2 = res2; + if (iocb->ki_eventfd) + eventfd_ctx_put(iocb->ki_eventfd); + if (iocb->ki_filp) + fput(iocb->ki_filp); + percpu_ref_put(&iocb->ki_ctx->reqs); + kmem_cache_free(kiocb_cachep, iocb); } /* aio_complete * Called when the io request on the given iocb is complete. */ -static void aio_complete(struct aio_kiocb *iocb, long res, long res2) +static void aio_complete(struct aio_kiocb *iocb) { struct kioctx *ctx = iocb->ki_ctx; struct aio_ring *ring; @@ -1114,14 +1111,14 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2) ev_page = kmap_atomic(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]); event = ev_page + pos % AIO_EVENTS_PER_PAGE; - aio_fill_event(event, iocb, res, res2); + *event = iocb->ki_res; kunmap_atomic(ev_page); flush_dcache_page(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]); - pr_debug("%p[%u]: %p: %p %Lx %lx %lx\n", - ctx, tail, iocb, iocb->ki_user_iocb, iocb->ki_user_data, - res, res2); + pr_debug("%p[%u]: %p: %p %Lx %Lx %Lx\n", ctx, tail, iocb, + (void __user *)(unsigned long)iocb->ki_res.obj, + iocb->ki_res.data, iocb->ki_res.res, iocb->ki_res.res2); /* after flagging the request as done, we * must never even look at it again @@ -1148,10 +1145,8 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2) * eventfd. The eventfd_signal() function is safe to be called * from IRQ context. */ - if (iocb->ki_eventfd) { + if (iocb->ki_eventfd) eventfd_signal(iocb->ki_eventfd, 1); - eventfd_ctx_put(iocb->ki_eventfd); - } /* * We have to order our ring_info tail store above and test @@ -1163,7 +1158,14 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2) if (waitqueue_active(&ctx->wait)) wake_up(&ctx->wait); - iocb_put(iocb); +} + +static inline void iocb_put(struct aio_kiocb *iocb) +{ + if (refcount_dec_and_test(&iocb->ki_refcnt)) { + aio_complete(iocb); + iocb_destroy(iocb); + } } /* aio_read_events_ring @@ -1437,7 +1439,9 @@ static void aio_complete_rw(struct kiocb *kiocb, long res, long res2) file_end_write(kiocb->ki_filp); } - aio_complete(iocb, res, res2); + iocb->ki_res.res = res; + iocb->ki_res.res2 = res2; + iocb_put(iocb); } static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) @@ -1514,13 +1518,13 @@ static inline void aio_rw_done(struct kiocb *req, ssize_t ret) } } -static ssize_t aio_read(struct kiocb *req, const struct iocb *iocb, +static int aio_read(struct kiocb *req, const struct iocb *iocb, bool vectored, bool compat) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct iov_iter iter; struct file *file; - ssize_t ret; + int ret; ret = aio_prep_rw(req, iocb); if (ret) @@ -1542,13 +1546,13 @@ static ssize_t aio_read(struct kiocb *req, const struct iocb *iocb, return ret; } -static ssize_t aio_write(struct kiocb *req, const struct iocb *iocb, +static int aio_write(struct kiocb *req, const struct iocb *iocb, bool vectored, bool compat) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct iov_iter iter; struct file *file; - ssize_t ret; + int ret; ret = aio_prep_rw(req, iocb); if (ret) @@ -1585,11 +1589,10 @@ static ssize_t aio_write(struct kiocb *req, const struct iocb *iocb, static void aio_fsync_work(struct work_struct *work) { - struct fsync_iocb *req = container_of(work, struct fsync_iocb, work); - int ret; + struct aio_kiocb *iocb = container_of(work, struct aio_kiocb, fsync.work); - ret = vfs_fsync(req->file, req->datasync); - aio_complete(container_of(req, struct aio_kiocb, fsync), ret, 0); + iocb->ki_res.res = vfs_fsync(iocb->fsync.file, iocb->fsync.datasync); + iocb_put(iocb); } static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb, @@ -1608,11 +1611,6 @@ static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb, return 0; } -static inline void aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask) -{ - aio_complete(iocb, mangle_poll(mask), 0); -} - static void aio_poll_complete_work(struct work_struct *work) { struct poll_iocb *req = container_of(work, struct poll_iocb, work); @@ -1638,9 +1636,11 @@ static void aio_poll_complete_work(struct work_struct *work) return; } list_del_init(&iocb->ki_list); + iocb->ki_res.res = mangle_poll(mask); + req->done = true; spin_unlock_irq(&ctx->ctx_lock); - aio_poll_complete(iocb, mask); + iocb_put(iocb); } /* assumes we are called with irqs disabled */ @@ -1668,31 +1668,27 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, __poll_t mask = key_to_poll(key); unsigned long flags; - req->woken = true; - /* for instances that support it check for an event match first: */ - if (mask) { - if (!(mask & req->events)) - return 0; + if (mask && !(mask & req->events)) + return 0; + + list_del_init(&req->wait.entry); + if (mask && spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { /* * Try to complete the iocb inline if we can. Use * irqsave/irqrestore because not all filesystems (e.g. fuse) * call this function with IRQs disabled and because IRQs * have to be disabled before ctx_lock is obtained. */ - if (spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { - list_del(&iocb->ki_list); - spin_unlock_irqrestore(&iocb->ki_ctx->ctx_lock, flags); - - list_del_init(&req->wait.entry); - aio_poll_complete(iocb, mask); - return 1; - } + list_del(&iocb->ki_list); + iocb->ki_res.res = mangle_poll(mask); + req->done = true; + spin_unlock_irqrestore(&iocb->ki_ctx->ctx_lock, flags); + iocb_put(iocb); + } else { + schedule_work(&req->work); } - - list_del_init(&req->wait.entry); - schedule_work(&req->work); return 1; } @@ -1719,11 +1715,12 @@ aio_poll_queue_proc(struct file *file, struct wait_queue_head *head, add_wait_queue(head, &pt->iocb->poll.wait); } -static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) +static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) { struct kioctx *ctx = aiocb->ki_ctx; struct poll_iocb *req = &aiocb->poll; struct aio_poll_table apt; + bool cancel = false; __poll_t mask; /* reject any unknown events outside the normal event mask. */ @@ -1737,7 +1734,7 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP; req->head = NULL; - req->woken = false; + req->done = false; req->cancelled = false; apt.pt._qproc = aio_poll_queue_proc; @@ -1749,156 +1746,135 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) INIT_LIST_HEAD(&req->wait.entry); init_waitqueue_func_entry(&req->wait, aio_poll_wake); - /* one for removal from waitqueue, one for this function */ - refcount_set(&aiocb->ki_refcnt, 2); - mask = vfs_poll(req->file, &apt.pt) & req->events; - if (unlikely(!req->head)) { - /* we did not manage to set up a waitqueue, done */ - goto out; - } - spin_lock_irq(&ctx->ctx_lock); - spin_lock(&req->head->lock); - if (req->woken) { - /* wake_up context handles the rest */ - mask = 0; + if (likely(req->head)) { + spin_lock(&req->head->lock); + if (unlikely(list_empty(&req->wait.entry))) { + if (apt.error) + cancel = true; + apt.error = 0; + mask = 0; + } + if (mask || apt.error) { + list_del_init(&req->wait.entry); + } else if (cancel) { + WRITE_ONCE(req->cancelled, true); + } else if (!req->done) { /* actually waiting for an event */ + list_add_tail(&aiocb->ki_list, &ctx->active_reqs); + aiocb->ki_cancel = aio_poll_cancel; + } + spin_unlock(&req->head->lock); + } + if (mask) { /* no async, we'd stolen it */ + aiocb->ki_res.res = mangle_poll(mask); apt.error = 0; - } else if (mask || apt.error) { - /* if we get an error or a mask we are done */ - WARN_ON_ONCE(list_empty(&req->wait.entry)); - list_del_init(&req->wait.entry); - } else { - /* actually waiting for an event */ - list_add_tail(&aiocb->ki_list, &ctx->active_reqs); - aiocb->ki_cancel = aio_poll_cancel; } - spin_unlock(&req->head->lock); spin_unlock_irq(&ctx->ctx_lock); - -out: - if (unlikely(apt.error)) - return apt.error; - if (mask) - aio_poll_complete(aiocb, mask); - iocb_put(aiocb); - return 0; + iocb_put(aiocb); + return apt.error; } static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb, - struct iocb __user *user_iocb, bool compat) + struct iocb __user *user_iocb, struct aio_kiocb *req, + bool compat) { - struct aio_kiocb *req; - ssize_t ret; - - /* enforce forwards compatibility on users */ - if (unlikely(iocb->aio_reserved2)) { - pr_debug("EINVAL: reserve field set\n"); - return -EINVAL; - } - - /* prevent overflows */ - if (unlikely( - (iocb->aio_buf != (unsigned long)iocb->aio_buf) || - (iocb->aio_nbytes != (size_t)iocb->aio_nbytes) || - ((ssize_t)iocb->aio_nbytes < 0) - )) { - pr_debug("EINVAL: overflow check\n"); - return -EINVAL; - } - - if (!get_reqs_available(ctx)) - return -EAGAIN; - - ret = -EAGAIN; - req = aio_get_req(ctx); - if (unlikely(!req)) - goto out_put_reqs_available; - req->ki_filp = fget(iocb->aio_fildes); - ret = -EBADF; if (unlikely(!req->ki_filp)) - goto out_put_req; + return -EBADF; if (iocb->aio_flags & IOCB_FLAG_RESFD) { + struct eventfd_ctx *eventfd; /* * If the IOCB_FLAG_RESFD flag of aio_flags is set, get an * instance of the file* now. The file descriptor must be * an eventfd() fd, and will be signaled for each completed * event using the eventfd_signal() function. */ - req->ki_eventfd = eventfd_ctx_fdget((int) iocb->aio_resfd); - if (IS_ERR(req->ki_eventfd)) { - ret = PTR_ERR(req->ki_eventfd); - req->ki_eventfd = NULL; - goto out_put_req; - } + eventfd = eventfd_ctx_fdget(iocb->aio_resfd); + if (IS_ERR(eventfd)) + return PTR_ERR(eventfd); + + req->ki_eventfd = eventfd; } - ret = put_user(KIOCB_KEY, &user_iocb->aio_key); - if (unlikely(ret)) { + if (unlikely(put_user(KIOCB_KEY, &user_iocb->aio_key))) { pr_debug("EFAULT: aio_key\n"); - goto out_put_req; + return -EFAULT; } - req->ki_user_iocb = user_iocb; - req->ki_user_data = iocb->aio_data; + req->ki_res.obj = (u64)(unsigned long)user_iocb; + req->ki_res.data = iocb->aio_data; + req->ki_res.res = 0; + req->ki_res.res2 = 0; switch (iocb->aio_lio_opcode) { case IOCB_CMD_PREAD: - ret = aio_read(&req->rw, iocb, false, compat); - break; + return aio_read(&req->rw, iocb, false, compat); case IOCB_CMD_PWRITE: - ret = aio_write(&req->rw, iocb, false, compat); - break; + return aio_write(&req->rw, iocb, false, compat); case IOCB_CMD_PREADV: - ret = aio_read(&req->rw, iocb, true, compat); - break; + return aio_read(&req->rw, iocb, true, compat); case IOCB_CMD_PWRITEV: - ret = aio_write(&req->rw, iocb, true, compat); - break; + return aio_write(&req->rw, iocb, true, compat); case IOCB_CMD_FSYNC: - ret = aio_fsync(&req->fsync, iocb, false); - break; + return aio_fsync(&req->fsync, iocb, false); case IOCB_CMD_FDSYNC: - ret = aio_fsync(&req->fsync, iocb, true); - break; + return aio_fsync(&req->fsync, iocb, true); case IOCB_CMD_POLL: - ret = aio_poll(req, iocb); - break; + return aio_poll(req, iocb); default: pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode); - ret = -EINVAL; - break; + return -EINVAL; } - - /* - * If ret is 0, we'd either done aio_complete() ourselves or have - * arranged for that to be done asynchronously. Anything non-zero - * means that we need to destroy req ourselves. - */ - if (ret) - goto out_put_req; - return 0; -out_put_req: - if (req->ki_eventfd) - eventfd_ctx_put(req->ki_eventfd); - iocb_put(req); -out_put_reqs_available: - put_reqs_available(ctx, 1); - return ret; } static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, bool compat) { + struct aio_kiocb *req; struct iocb iocb; + int err; if (unlikely(copy_from_user(&iocb, user_iocb, sizeof(iocb)))) return -EFAULT; - return __io_submit_one(ctx, &iocb, user_iocb, compat); + /* enforce forwards compatibility on users */ + if (unlikely(iocb.aio_reserved2)) { + pr_debug("EINVAL: reserve field set\n"); + return -EINVAL; + } + + /* prevent overflows */ + if (unlikely( + (iocb.aio_buf != (unsigned long)iocb.aio_buf) || + (iocb.aio_nbytes != (size_t)iocb.aio_nbytes) || + ((ssize_t)iocb.aio_nbytes < 0) + )) { + pr_debug("EINVAL: overflow check\n"); + return -EINVAL; + } + + req = aio_get_req(ctx); + if (unlikely(!req)) + return -EAGAIN; + + err = __io_submit_one(ctx, &iocb, user_iocb, req, compat); + + /* Done with the synchronous reference */ + iocb_put(req); + + /* + * If err is 0, we'd either done aio_complete() ourselves or have + * arranged for that to be done asynchronously. Anything non-zero + * means that we need to destroy req ourselves. + */ + if (unlikely(err)) { + iocb_destroy(req); + put_reqs_available(ctx, 1); + } + return err; } /* sys_io_submit: @@ -1997,24 +1973,6 @@ COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id, } #endif -/* lookup_kiocb - * Finds a given iocb for cancellation. - */ -static struct aio_kiocb * -lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb) -{ - struct aio_kiocb *kiocb; - - assert_spin_locked(&ctx->ctx_lock); - - /* TODO: use a hash or array, this sucks. */ - list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) { - if (kiocb->ki_user_iocb == iocb) - return kiocb; - } - return NULL; -} - /* sys_io_cancel: * Attempts to cancel an iocb previously passed to io_submit. If * the operation is successfully cancelled, the resulting event is @@ -2032,6 +1990,7 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, struct aio_kiocb *kiocb; int ret = -EINVAL; u32 key; + u64 obj = (u64)(unsigned long)iocb; if (unlikely(get_user(key, &iocb->aio_key))) return -EFAULT; @@ -2043,10 +2002,13 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, return -EINVAL; spin_lock_irq(&ctx->ctx_lock); - kiocb = lookup_kiocb(ctx, iocb); - if (kiocb) { - ret = kiocb->ki_cancel(&kiocb->rw); - list_del_init(&kiocb->ki_list); + /* TODO: use a hash or array, this sucks. */ + list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) { + if (kiocb->ki_res.obj == obj) { + ret = kiocb->ki_cancel(&kiocb->rw); + list_del_init(&kiocb->ki_list); + break; + } } spin_unlock_irq(&ctx->ctx_lock); diff --git a/fs/block_dev.c b/fs/block_dev.c index e9faa52bb489..bb28e2ead679 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -264,7 +264,8 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, bio_for_each_segment_all(bvec, &bio, i, iter_all) { if (should_dirty && !PageCompound(bvec->bv_page)) set_page_dirty_lock(bvec->bv_page); - put_page(bvec->bv_page); + if (!bio_flagged(&bio, BIO_NO_PAGE_REF)) + put_page(bvec->bv_page); } if (unlikely(bio.bi_status)) @@ -307,10 +308,10 @@ static void blkdev_bio_end_io(struct bio *bio) struct blkdev_dio *dio = bio->bi_private; bool should_dirty = dio->should_dirty; - if (dio->multi_bio && !atomic_dec_and_test(&dio->ref)) { - if (bio->bi_status && !dio->bio.bi_status) - dio->bio.bi_status = bio->bi_status; - } else { + if (bio->bi_status && !dio->bio.bi_status) + dio->bio.bi_status = bio->bi_status; + + if (!dio->multi_bio || atomic_dec_and_test(&dio->ref)) { if (!dio->is_sync) { struct kiocb *iocb = dio->iocb; ssize_t ret; @@ -336,12 +337,14 @@ static void blkdev_bio_end_io(struct bio *bio) if (should_dirty) { bio_check_pages_dirty(bio); } else { - struct bio_vec *bvec; - int i; - struct bvec_iter_all iter_all; + if (!bio_flagged(bio, BIO_NO_PAGE_REF)) { + struct bvec_iter_all iter_all; + struct bio_vec *bvec; + int i; - bio_for_each_segment_all(bvec, bio, i, iter_all) - put_page(bvec->bv_page); + bio_for_each_segment_all(bvec, bio, i, iter_all) + put_page(bvec->bv_page); + } bio_put(bio); } } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 1d49694e6ae3..c5880329ae37 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -6174,7 +6174,7 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info, * * This is overestimating in most cases. */ - qgroup_rsv_size = outstanding_extents * fs_info->nodesize; + qgroup_rsv_size = (u64)outstanding_extents * fs_info->nodesize; spin_lock(&block_rsv->lock); block_rsv->size = reserve_size; diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 920bf3b4b0ef..cccc75d15970 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -7,6 +7,7 @@ #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/highmem.h> +#include <linux/sched/mm.h> #include "ctree.h" #include "disk-io.h" #include "transaction.h" @@ -427,9 +428,13 @@ blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio, unsigned long this_sum_bytes = 0; int i; u64 offset; + unsigned nofs_flag; + + nofs_flag = memalloc_nofs_save(); + sums = kvzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size), + GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); - sums = kzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size), - GFP_NOFS); if (!sums) return BLK_STS_RESOURCE; @@ -472,8 +477,10 @@ blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio, bytes_left = bio->bi_iter.bi_size - total_bytes; - sums = kzalloc(btrfs_ordered_sum_size(fs_info, bytes_left), - GFP_NOFS); + nofs_flag = memalloc_nofs_save(); + sums = kvzalloc(btrfs_ordered_sum_size(fs_info, + bytes_left), GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); BUG_ON(!sums); /* -ENOMEM */ sums->len = bytes_left; ordered = btrfs_lookup_ordered_extent(inode, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 82fdda8ff5ab..2973608824ec 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6783,7 +6783,7 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, u64 extent_start = 0; u64 extent_end = 0; u64 objectid = btrfs_ino(inode); - u8 extent_type; + int extent_type = -1; struct btrfs_path *path = NULL; struct btrfs_root *root = inode->root; struct btrfs_file_extent_item *item; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index ec2d8919e7fb..cd4e693406a0 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -501,6 +501,16 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; + /* + * If the fs is mounted with nologreplay, which requires it to be + * mounted in RO mode as well, we can not allow discard on free space + * inside block groups, because log trees refer to extents that are not + * pinned in a block group's free space cache (pinning the extents is + * precisely the first phase of replaying a log tree). + */ + if (btrfs_test_opt(fs_info, NOLOGREPLAY)) + return -EROFS; + rcu_read_lock(); list_for_each_entry_rcu(device, &fs_info->fs_devices->devices, dev_list) { diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 6fde2b2741ef..45e3cfd1198b 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -6,6 +6,7 @@ #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/writeback.h> +#include <linux/sched/mm.h> #include "ctree.h" #include "transaction.h" #include "btrfs_inode.h" @@ -442,7 +443,7 @@ void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry) cur = entry->list.next; sum = list_entry(cur, struct btrfs_ordered_sum, list); list_del(&sum->list); - kfree(sum); + kvfree(sum); } kmem_cache_free(btrfs_ordered_extent_cache, entry); } diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c index dc6140013ae8..61d22a56c0ba 100644 --- a/fs/btrfs/props.c +++ b/fs/btrfs/props.c @@ -366,11 +366,11 @@ int btrfs_subvol_inherit_props(struct btrfs_trans_handle *trans, static int prop_compression_validate(const char *value, size_t len) { - if (!strncmp("lzo", value, len)) + if (!strncmp("lzo", value, 3)) return 0; - else if (!strncmp("zlib", value, len)) + else if (!strncmp("zlib", value, 4)) return 0; - else if (!strncmp("zstd", value, len)) + else if (!strncmp("zstd", value, 4)) return 0; return -EINVAL; @@ -396,7 +396,7 @@ static int prop_compression_apply(struct inode *inode, btrfs_set_fs_incompat(fs_info, COMPRESS_LZO); } else if (!strncmp("zlib", value, 4)) { type = BTRFS_COMPRESS_ZLIB; - } else if (!strncmp("zstd", value, len)) { + } else if (!strncmp("zstd", value, 4)) { type = BTRFS_COMPRESS_ZSTD; btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD); } else { diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index eb680b715dd6..e659d9d61107 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1922,8 +1922,8 @@ static int qgroup_trace_new_subtree_blocks(struct btrfs_trans_handle* trans, int i; /* Level sanity check */ - if (cur_level < 0 || cur_level >= BTRFS_MAX_LEVEL || - root_level < 0 || root_level >= BTRFS_MAX_LEVEL || + if (cur_level < 0 || cur_level >= BTRFS_MAX_LEVEL - 1 || + root_level < 0 || root_level >= BTRFS_MAX_LEVEL - 1 || root_level < cur_level) { btrfs_err_rl(fs_info, "%s: bad levels, cur_level=%d root_level=%d", diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 1869ba8e5981..67a6f7d47402 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -2430,8 +2430,9 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, bitmap_clear(rbio->dbitmap, pagenr, 1); kunmap(p); - for (stripe = 0; stripe < rbio->real_stripes; stripe++) + for (stripe = 0; stripe < nr_data; stripe++) kunmap(page_in_rbio(rbio, stripe, pagenr, 0)); + kunmap(p_page); } __free_page(p_page); diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index d09b6cdb785a..b283d3a6e837 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -205,28 +205,17 @@ static struct root_entry *lookup_root_entry(struct rb_root *root, u64 objectid) #ifdef CONFIG_STACKTRACE static void __save_stack_trace(struct ref_action *ra) { - struct stack_trace stack_trace; - - stack_trace.max_entries = MAX_TRACE; - stack_trace.nr_entries = 0; - stack_trace.entries = ra->trace; - stack_trace.skip = 2; - save_stack_trace(&stack_trace); - ra->trace_len = stack_trace.nr_entries; + ra->trace_len = stack_trace_save(ra->trace, MAX_TRACE, 2); } static void __print_stack_trace(struct btrfs_fs_info *fs_info, struct ref_action *ra) { - struct stack_trace trace; - if (ra->trace_len == 0) { btrfs_err(fs_info, " ref-verify: no stacktrace"); return; } - trace.nr_entries = ra->trace_len; - trace.entries = ra->trace; - print_stack_trace(&trace, 2); + stack_trace_print(ra->trace, ra->trace_len, 2); } #else static void inline __save_stack_trace(struct ref_action *ra) diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index acdad6d658f5..e4e665f422fc 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1886,8 +1886,10 @@ static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans) } } -static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info) +static inline int btrfs_start_delalloc_flush(struct btrfs_trans_handle *trans) { + struct btrfs_fs_info *fs_info = trans->fs_info; + /* * We use writeback_inodes_sb here because if we used * btrfs_start_delalloc_roots we would deadlock with fs freeze. @@ -1897,15 +1899,50 @@ static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info) * from already being in a transaction and our join_transaction doesn't * have to re-take the fs freeze lock. */ - if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) + if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) { writeback_inodes_sb(fs_info->sb, WB_REASON_SYNC); + } else { + struct btrfs_pending_snapshot *pending; + struct list_head *head = &trans->transaction->pending_snapshots; + + /* + * Flush dellaloc for any root that is going to be snapshotted. + * This is done to avoid a corrupted version of files, in the + * snapshots, that had both buffered and direct IO writes (even + * if they were done sequentially) due to an unordered update of + * the inode's size on disk. + */ + list_for_each_entry(pending, head, list) { + int ret; + + ret = btrfs_start_delalloc_snapshot(pending->root); + if (ret) + return ret; + } + } return 0; } -static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info) +static inline void btrfs_wait_delalloc_flush(struct btrfs_trans_handle *trans) { - if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) + struct btrfs_fs_info *fs_info = trans->fs_info; + + if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) { btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); + } else { + struct btrfs_pending_snapshot *pending; + struct list_head *head = &trans->transaction->pending_snapshots; + + /* + * Wait for any dellaloc that we started previously for the roots + * that are going to be snapshotted. This is to avoid a corrupted + * version of files in the snapshots that had both buffered and + * direct IO writes (even if they were done sequentially). + */ + list_for_each_entry(pending, head, list) + btrfs_wait_ordered_extents(pending->root, + U64_MAX, 0, U64_MAX); + } } int btrfs_commit_transaction(struct btrfs_trans_handle *trans) @@ -2023,7 +2060,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) extwriter_counter_dec(cur_trans, trans->type); - ret = btrfs_start_delalloc_flush(fs_info); + ret = btrfs_start_delalloc_flush(trans); if (ret) goto cleanup_transaction; @@ -2039,7 +2076,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) if (ret) goto cleanup_transaction; - btrfs_wait_delalloc_flush(fs_info); + btrfs_wait_delalloc_flush(trans); btrfs_scrub_pause(fs_info); /* diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index f06454a55e00..561884f60d35 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3578,9 +3578,16 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans, } btrfs_release_path(path); - /* find the first key from this transaction again */ + /* + * Find the first key from this transaction again. See the note for + * log_new_dir_dentries, if we're logging a directory recursively we + * won't be holding its i_mutex, which means we can modify the directory + * while we're logging it. If we remove an entry between our first + * search and this search we'll not find the key again and can just + * bail. + */ ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0); - if (WARN_ON(ret != 0)) + if (ret != 0) goto done; /* @@ -4544,6 +4551,19 @@ static int logged_inode_size(struct btrfs_root *log, struct btrfs_inode *inode, item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_item); *size_ret = btrfs_inode_size(path->nodes[0], item); + /* + * If the in-memory inode's i_size is smaller then the inode + * size stored in the btree, return the inode's i_size, so + * that we get a correct inode size after replaying the log + * when before a power failure we had a shrinking truncate + * followed by addition of a new name (rename / new hard link). + * Otherwise return the inode size from the btree, to avoid + * data loss when replaying a log due to previously doing a + * write that expands the inode's size and logging a new name + * immediately after. + */ + if (*size_ret > inode->vfs_inode.i_size) + *size_ret = inode->vfs_inode.i_size; } btrfs_release_path(path); @@ -4705,15 +4725,8 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans, struct btrfs_file_extent_item); if (btrfs_file_extent_type(leaf, extent) == - BTRFS_FILE_EXTENT_INLINE) { - len = btrfs_file_extent_ram_bytes(leaf, extent); - ASSERT(len == i_size || - (len == fs_info->sectorsize && - btrfs_file_extent_compression(leaf, extent) != - BTRFS_COMPRESS_NONE) || - (len < i_size && i_size < fs_info->sectorsize)); + BTRFS_FILE_EXTENT_INLINE) return 0; - } len = btrfs_file_extent_num_bytes(leaf, extent); /* Last extent goes beyond i_size, no need to log a hole. */ diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 9024eee889b9..db934ceae9c1 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -6407,7 +6407,7 @@ static void btrfs_end_bio(struct bio *bio) if (bio_op(bio) == REQ_OP_WRITE) btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS); - else + else if (!(bio->bi_opf & REQ_RAHEAD)) btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_READ_ERRS); if (bio->bi_opf & REQ_PREFLUSH) diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index a8f429882249..0637149fb9f9 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1766,6 +1766,7 @@ static ssize_t ceph_read_dir(struct file *file, char __user *buf, size_t size, unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn) { struct ceph_inode_info *dci = ceph_inode(dir); + unsigned hash; switch (dci->i_dir_layout.dl_dir_hash) { case 0: /* for backward compat */ @@ -1773,8 +1774,11 @@ unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn) return dn->d_name.hash; default: - return ceph_str_hash(dci->i_dir_layout.dl_dir_hash, + spin_lock(&dn->d_lock); + hash = ceph_str_hash(dci->i_dir_layout.dl_dir_hash, dn->d_name.name, dn->d_name.len); + spin_unlock(&dn->d_lock); + return hash; } } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index e3346628efe2..c2feb310ac1e 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -524,6 +524,7 @@ static void ceph_i_callback(struct rcu_head *head) struct inode *inode = container_of(head, struct inode, i_rcu); struct ceph_inode_info *ci = ceph_inode(inode); + kfree(ci->i_symlink); kmem_cache_free(ceph_inode_cachep, ci); } @@ -566,7 +567,6 @@ void ceph_destroy_inode(struct inode *inode) } } - kfree(ci->i_symlink); while ((n = rb_first(&ci->i_fragtree)) != NULL) { frag = rb_entry(n, struct ceph_inode_frag, node); rb_erase(n, &ci->i_fragtree); @@ -1163,6 +1163,19 @@ static int splice_dentry(struct dentry **pdn, struct inode *in) return 0; } +static int d_name_cmp(struct dentry *dentry, const char *name, size_t len) +{ + int ret; + + /* take d_lock to ensure dentry->d_name stability */ + spin_lock(&dentry->d_lock); + ret = dentry->d_name.len - len; + if (!ret) + ret = memcmp(dentry->d_name.name, name, len); + spin_unlock(&dentry->d_lock); + return ret; +} + /* * Incorporate results into the local cache. This is either just * one inode, or a directory, dentry, and possibly linked-to inode (e.g., @@ -1412,7 +1425,8 @@ retry_lookup: err = splice_dentry(&req->r_dentry, in); if (err < 0) goto done; - } else if (rinfo->head->is_dentry) { + } else if (rinfo->head->is_dentry && + !d_name_cmp(req->r_dentry, rinfo->dname, rinfo->dname_len)) { struct ceph_vino *ptvino = NULL; if ((le32_to_cpu(rinfo->diri.in->cap.caps) & CEPH_CAP_FILE_SHARED) || diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 21c33ed048ed..9049c2a3e972 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1414,6 +1414,15 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap, list_add(&ci->i_prealloc_cap_flush->i_list, &to_remove); ci->i_prealloc_cap_flush = NULL; } + + if (drop && + ci->i_wrbuffer_ref_head == 0 && + ci->i_wr_ref == 0 && + ci->i_dirty_caps == 0 && + ci->i_flushing_caps == 0) { + ceph_put_snap_context(ci->i_head_snapc); + ci->i_head_snapc = NULL; + } } spin_unlock(&ci->i_ceph_lock); while (!list_empty(&to_remove)) { @@ -2161,10 +2170,39 @@ retry: return path; } +/* Duplicate the dentry->d_name.name safely */ +static int clone_dentry_name(struct dentry *dentry, const char **ppath, + int *ppathlen) +{ + u32 len; + char *name; + +retry: + len = READ_ONCE(dentry->d_name.len); + name = kmalloc(len + 1, GFP_NOFS); + if (!name) + return -ENOMEM; + + spin_lock(&dentry->d_lock); + if (dentry->d_name.len != len) { + spin_unlock(&dentry->d_lock); + kfree(name); + goto retry; + } + memcpy(name, dentry->d_name.name, len); + spin_unlock(&dentry->d_lock); + + name[len] = '\0'; + *ppath = name; + *ppathlen = len; + return 0; +} + static int build_dentry_path(struct dentry *dentry, struct inode *dir, const char **ppath, int *ppathlen, u64 *pino, - int *pfreepath) + bool *pfreepath, bool parent_locked) { + int ret; char *path; rcu_read_lock(); @@ -2173,8 +2211,15 @@ static int build_dentry_path(struct dentry *dentry, struct inode *dir, if (dir && ceph_snap(dir) == CEPH_NOSNAP) { *pino = ceph_ino(dir); rcu_read_unlock(); - *ppath = dentry->d_name.name; - *ppathlen = dentry->d_name.len; + if (parent_locked) { + *ppath = dentry->d_name.name; + *ppathlen = dentry->d_name.len; + } else { + ret = clone_dentry_name(dentry, ppath, ppathlen); + if (ret) + return ret; + *pfreepath = true; + } return 0; } rcu_read_unlock(); @@ -2182,13 +2227,13 @@ static int build_dentry_path(struct dentry *dentry, struct inode *dir, if (IS_ERR(path)) return PTR_ERR(path); *ppath = path; - *pfreepath = 1; + *pfreepath = true; return 0; } static int build_inode_path(struct inode *inode, const char **ppath, int *ppathlen, u64 *pino, - int *pfreepath) + bool *pfreepath) { struct dentry *dentry; char *path; @@ -2204,7 +2249,7 @@ static int build_inode_path(struct inode *inode, if (IS_ERR(path)) return PTR_ERR(path); *ppath = path; - *pfreepath = 1; + *pfreepath = true; return 0; } @@ -2215,7 +2260,7 @@ static int build_inode_path(struct inode *inode, static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry, struct inode *rdiri, const char *rpath, u64 rino, const char **ppath, int *pathlen, - u64 *ino, int *freepath) + u64 *ino, bool *freepath, bool parent_locked) { int r = 0; @@ -2225,7 +2270,7 @@ static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry, ceph_snap(rinode)); } else if (rdentry) { r = build_dentry_path(rdentry, rdiri, ppath, pathlen, ino, - freepath); + freepath, parent_locked); dout(" dentry %p %llx/%.*s\n", rdentry, *ino, *pathlen, *ppath); } else if (rpath || rino) { @@ -2251,7 +2296,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, const char *path2 = NULL; u64 ino1 = 0, ino2 = 0; int pathlen1 = 0, pathlen2 = 0; - int freepath1 = 0, freepath2 = 0; + bool freepath1 = false, freepath2 = false; int len; u16 releases; void *p, *end; @@ -2259,16 +2304,19 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, ret = set_request_path_attr(req->r_inode, req->r_dentry, req->r_parent, req->r_path1, req->r_ino1.ino, - &path1, &pathlen1, &ino1, &freepath1); + &path1, &pathlen1, &ino1, &freepath1, + test_bit(CEPH_MDS_R_PARENT_LOCKED, + &req->r_req_flags)); if (ret < 0) { msg = ERR_PTR(ret); goto out; } + /* If r_old_dentry is set, then assume that its parent is locked */ ret = set_request_path_attr(NULL, req->r_old_dentry, req->r_old_dentry_dir, req->r_path2, req->r_ino2.ino, - &path2, &pathlen2, &ino2, &freepath2); + &path2, &pathlen2, &ino2, &freepath2, true); if (ret < 0) { msg = ERR_PTR(ret); goto out_free1; diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 89aa37fa0f84..b26e12cd8ec3 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -572,7 +572,12 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci) old_snapc = NULL; update_snapc: - if (ci->i_head_snapc) { + if (ci->i_wrbuffer_ref_head == 0 && + ci->i_wr_ref == 0 && + ci->i_dirty_caps == 0 && + ci->i_flushing_caps == 0) { + ci->i_head_snapc = NULL; + } else { ci->i_head_snapc = ceph_get_snap_context(new_snapc); dout(" new snapc is %p\n", new_snapc); } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 217276b8b942..a05bf1d6e1d0 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -559,6 +559,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root) tcon->ses->server->echo_interval / HZ); if (tcon->snapshot_time) seq_printf(s, ",snapshot=%llu", tcon->snapshot_time); + if (tcon->handle_timeout) + seq_printf(s, ",handletimeout=%u", tcon->handle_timeout); /* convert actimeo and display it in seconds */ seq_printf(s, ",actimeo=%lu", cifs_sb->actimeo / HZ); @@ -1008,7 +1010,7 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, unsigned int xid; int rc; - if (remap_flags & ~REMAP_FILE_ADVISORY) + if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) return -EINVAL; cifs_dbg(FYI, "clone range\n"); diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 142164ef1f05..5c0298b9998f 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -150,5 +150,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "2.18" +#define CIFS_VERSION "2.19" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 38feae812b47..585ad3207cb1 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -60,6 +60,12 @@ #define CIFS_MAX_ACTIMEO (1 << 30) /* + * Max persistent and resilient handle timeout (milliseconds). + * Windows durable max was 960000 (16 minutes) + */ +#define SMB3_MAX_HANDLE_TIMEOUT 960000 + +/* * MAX_REQ is the maximum number of requests that WE will send * on one socket concurrently. */ @@ -586,6 +592,7 @@ struct smb_vol { struct nls_table *local_nls; unsigned int echo_interval; /* echo interval in secs */ __u64 snapshot_time; /* needed for timewarp tokens */ + __u32 handle_timeout; /* persistent and durable handle timeout in ms */ unsigned int max_credits; /* smb3 max_credits 10 < credits < 60000 */ }; @@ -1058,6 +1065,7 @@ struct cifs_tcon { __u32 vol_serial_number; __le64 vol_create_time; __u64 snapshot_time; /* for timewarp tokens - timestamp of snapshot */ + __u32 handle_timeout; /* persistent and durable handle timeout in ms */ __u32 ss_flags; /* sector size flags */ __u32 perf_sector_size; /* best sector size for perf */ __u32 max_chunks; @@ -1325,6 +1333,7 @@ cifsFileInfo_get_locked(struct cifsFileInfo *cifs_file) } struct cifsFileInfo *cifsFileInfo_get(struct cifsFileInfo *cifs_file); +void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_hdlr); void cifsFileInfo_put(struct cifsFileInfo *cifs_file); #define CIFS_CACHE_READ_FLG 1 @@ -1847,6 +1856,7 @@ GLOBAL_EXTERN spinlock_t gidsidlock; #endif /* CONFIG_CIFS_ACL */ void cifs_oplock_break(struct work_struct *work); +void cifs_queue_oplock_break(struct cifsFileInfo *cfile); extern const struct slow_work_ops cifs_oplock_break_ops; extern struct workqueue_struct *cifsiod_wq; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index a8e9738db691..4c0e44489f21 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -103,7 +103,7 @@ enum { Opt_cruid, Opt_gid, Opt_file_mode, Opt_dirmode, Opt_port, Opt_blocksize, Opt_rsize, Opt_wsize, Opt_actimeo, - Opt_echo_interval, Opt_max_credits, + Opt_echo_interval, Opt_max_credits, Opt_handletimeout, Opt_snapshot, /* Mount options which take string value */ @@ -208,6 +208,7 @@ static const match_table_t cifs_mount_option_tokens = { { Opt_rsize, "rsize=%s" }, { Opt_wsize, "wsize=%s" }, { Opt_actimeo, "actimeo=%s" }, + { Opt_handletimeout, "handletimeout=%s" }, { Opt_echo_interval, "echo_interval=%s" }, { Opt_max_credits, "max_credits=%s" }, { Opt_snapshot, "snapshot=%s" }, @@ -1619,6 +1620,9 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, vol->actimeo = CIFS_DEF_ACTIMEO; + /* Most clients set timeout to 0, allows server to use its default */ + vol->handle_timeout = 0; /* See MS-SMB2 spec section 2.2.14.2.12 */ + /* offer SMB2.1 and later (SMB3 etc). Secure and widely accepted */ vol->ops = &smb30_operations; vol->vals = &smbdefault_values; @@ -2017,6 +2021,18 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, goto cifs_parse_mount_err; } break; + case Opt_handletimeout: + if (get_option_ul(args, &option)) { + cifs_dbg(VFS, "%s: Invalid handletimeout value\n", + __func__); + goto cifs_parse_mount_err; + } + vol->handle_timeout = option; + if (vol->handle_timeout > SMB3_MAX_HANDLE_TIMEOUT) { + cifs_dbg(VFS, "Invalid handle cache timeout, longer than 16 minutes\n"); + goto cifs_parse_mount_err; + } + break; case Opt_echo_interval: if (get_option_ul(args, &option)) { cifs_dbg(VFS, "%s: Invalid echo interval value\n", @@ -3183,6 +3199,8 @@ static int match_tcon(struct cifs_tcon *tcon, struct smb_vol *volume_info) return 0; if (tcon->snapshot_time != volume_info->snapshot_time) return 0; + if (tcon->handle_timeout != volume_info->handle_timeout) + return 0; return 1; } @@ -3297,6 +3315,16 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info) tcon->snapshot_time = volume_info->snapshot_time; } + if (volume_info->handle_timeout) { + if (ses->server->vals->protocol_id == 0) { + cifs_dbg(VFS, + "Use SMB2.1 or later for handle timeout option\n"); + rc = -EOPNOTSUPP; + goto out_fail; + } else + tcon->handle_timeout = volume_info->handle_timeout; + } + tcon->ses = ses; if (volume_info->password) { tcon->password = kstrdup(volume_info->password, GFP_KERNEL); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 2a6d20c0ce02..7037a137fa53 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -360,13 +360,31 @@ cifsFileInfo_get(struct cifsFileInfo *cifs_file) return cifs_file; } -/* - * Release a reference on the file private data. This may involve closing - * the filehandle out on the server. Must be called without holding - * tcon->open_file_lock and cifs_file->file_info_lock. +/** + * cifsFileInfo_put - release a reference of file priv data + * + * Always potentially wait for oplock handler. See _cifsFileInfo_put(). */ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) { + _cifsFileInfo_put(cifs_file, true); +} + +/** + * _cifsFileInfo_put - release a reference of file priv data + * + * This may involve closing the filehandle @cifs_file out on the + * server. Must be called without holding tcon->open_file_lock and + * cifs_file->file_info_lock. + * + * If @wait_for_oplock_handler is true and we are releasing the last + * reference, wait for any running oplock break handler of the file + * and cancel any pending one. If calling this function from the + * oplock break handler, you need to pass false. + * + */ +void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler) +{ struct inode *inode = d_inode(cifs_file->dentry); struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink); struct TCP_Server_Info *server = tcon->ses->server; @@ -414,7 +432,8 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) spin_unlock(&tcon->open_file_lock); - oplock_break_cancelled = cancel_work_sync(&cifs_file->oplock_break); + oplock_break_cancelled = wait_oplock_handler ? + cancel_work_sync(&cifs_file->oplock_break) : false; if (!tcon->need_reconnect && !cifs_file->invalidHandle) { struct TCP_Server_Info *server = tcon->ses->server; @@ -2632,43 +2651,56 @@ cifs_resend_wdata(struct cifs_writedata *wdata, struct list_head *wdata_list, struct TCP_Server_Info *server = tlink_tcon(wdata->cfile->tlink)->ses->server; - /* - * Wait for credits to resend this wdata. - * Note: we are attempting to resend the whole wdata not in segments - */ do { - rc = server->ops->wait_mtu_credits(server, wdata->bytes, &wsize, - &credits); + if (wdata->cfile->invalidHandle) { + rc = cifs_reopen_file(wdata->cfile, false); + if (rc == -EAGAIN) + continue; + else if (rc) + break; + } - if (rc) - goto out; - if (wsize < wdata->bytes) { - add_credits_and_wake_if(server, &credits, 0); - msleep(1000); - } - } while (wsize < wdata->bytes); + /* + * Wait for credits to resend this wdata. + * Note: we are attempting to resend the whole wdata not in + * segments + */ + do { + rc = server->ops->wait_mtu_credits(server, wdata->bytes, + &wsize, &credits); + if (rc) + goto fail; + + if (wsize < wdata->bytes) { + add_credits_and_wake_if(server, &credits, 0); + msleep(1000); + } + } while (wsize < wdata->bytes); + wdata->credits = credits; - wdata->credits = credits; - rc = -EAGAIN; - while (rc == -EAGAIN) { - rc = 0; - if (wdata->cfile->invalidHandle) - rc = cifs_reopen_file(wdata->cfile, false); - if (!rc) - rc = server->ops->async_writev(wdata, + rc = adjust_credits(server, &wdata->credits, wdata->bytes); + + if (!rc) { + if (wdata->cfile->invalidHandle) + rc = -EAGAIN; + else + rc = server->ops->async_writev(wdata, cifs_uncached_writedata_release); - } + } - if (!rc) { - list_add_tail(&wdata->list, wdata_list); - return 0; - } + /* If the write was successfully sent, we are done */ + if (!rc) { + list_add_tail(&wdata->list, wdata_list); + return 0; + } - add_credits_and_wake_if(server, &wdata->credits, 0); -out: - kref_put(&wdata->refcount, cifs_uncached_writedata_release); + /* Roll back credits and retry if needed */ + add_credits_and_wake_if(server, &wdata->credits, 0); + } while (rc == -EAGAIN); +fail: + kref_put(&wdata->refcount, cifs_uncached_writedata_release); return rc; } @@ -2845,7 +2877,6 @@ static void collect_uncached_write_data(struct cifs_aio_ctx *ctx) struct cifs_tcon *tcon; struct cifs_sb_info *cifs_sb; struct dentry *dentry = ctx->cfile->dentry; - unsigned int i; int rc; tcon = tlink_tcon(ctx->cfile->tlink); @@ -2896,12 +2927,12 @@ restart_loop: wdata->bytes, &tmp_from, ctx->cfile, cifs_sb, &tmp_list, ctx); + + kref_put(&wdata->refcount, + cifs_uncached_writedata_release); } list_splice(&tmp_list, &ctx->list); - - kref_put(&wdata->refcount, - cifs_uncached_writedata_release); goto restart_loop; } } @@ -2909,10 +2940,6 @@ restart_loop: kref_put(&wdata->refcount, cifs_uncached_writedata_release); } - if (!ctx->direct_io) - for (i = 0; i < ctx->npages; i++) - put_page(ctx->bv[i].bv_page); - cifs_stats_bytes_written(tcon, ctx->total_len); set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(dentry->d_inode)->flags); @@ -3348,44 +3375,55 @@ static int cifs_resend_rdata(struct cifs_readdata *rdata, struct TCP_Server_Info *server = tlink_tcon(rdata->cfile->tlink)->ses->server; - /* - * Wait for credits to resend this rdata. - * Note: we are attempting to resend the whole rdata not in segments - */ do { - rc = server->ops->wait_mtu_credits(server, rdata->bytes, + if (rdata->cfile->invalidHandle) { + rc = cifs_reopen_file(rdata->cfile, true); + if (rc == -EAGAIN) + continue; + else if (rc) + break; + } + + /* + * Wait for credits to resend this rdata. + * Note: we are attempting to resend the whole rdata not in + * segments + */ + do { + rc = server->ops->wait_mtu_credits(server, rdata->bytes, &rsize, &credits); - if (rc) - goto out; + if (rc) + goto fail; - if (rsize < rdata->bytes) { - add_credits_and_wake_if(server, &credits, 0); - msleep(1000); - } - } while (rsize < rdata->bytes); + if (rsize < rdata->bytes) { + add_credits_and_wake_if(server, &credits, 0); + msleep(1000); + } + } while (rsize < rdata->bytes); + rdata->credits = credits; - rdata->credits = credits; - rc = -EAGAIN; - while (rc == -EAGAIN) { - rc = 0; - if (rdata->cfile->invalidHandle) - rc = cifs_reopen_file(rdata->cfile, true); - if (!rc) - rc = server->ops->async_readv(rdata); - } + rc = adjust_credits(server, &rdata->credits, rdata->bytes); + if (!rc) { + if (rdata->cfile->invalidHandle) + rc = -EAGAIN; + else + rc = server->ops->async_readv(rdata); + } - if (!rc) { - /* Add to aio pending list */ - list_add_tail(&rdata->list, rdata_list); - return 0; - } + /* If the read was successfully sent, we are done */ + if (!rc) { + /* Add to aio pending list */ + list_add_tail(&rdata->list, rdata_list); + return 0; + } - add_credits_and_wake_if(server, &rdata->credits, 0); -out: - kref_put(&rdata->refcount, - cifs_uncached_readdata_release); + /* Roll back credits and retry if needed */ + add_credits_and_wake_if(server, &rdata->credits, 0); + } while (rc == -EAGAIN); +fail: + kref_put(&rdata->refcount, cifs_uncached_readdata_release); return rc; } @@ -3539,7 +3577,6 @@ collect_uncached_read_data(struct cifs_aio_ctx *ctx) struct iov_iter *to = &ctx->iter; struct cifs_sb_info *cifs_sb; struct cifs_tcon *tcon; - unsigned int i; int rc; tcon = tlink_tcon(ctx->cfile->tlink); @@ -3623,15 +3660,8 @@ again: kref_put(&rdata->refcount, cifs_uncached_readdata_release); } - if (!ctx->direct_io) { - for (i = 0; i < ctx->npages; i++) { - if (ctx->should_dirty) - set_page_dirty(ctx->bv[i].bv_page); - put_page(ctx->bv[i].bv_page); - } - + if (!ctx->direct_io) ctx->total_len = ctx->len - iov_iter_count(to); - } /* mask nodata case */ if (rc == -ENODATA) @@ -4579,6 +4609,7 @@ void cifs_oplock_break(struct work_struct *work) cinode); cifs_dbg(FYI, "Oplock release rc = %d\n", rc); } + _cifsFileInfo_put(cfile, false /* do not wait for ourself */); cifs_done_oplock_break(cinode); } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 53fdb5df0d2e..538fd7d807e4 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1735,6 +1735,10 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry, if (rc == 0 || rc != -EBUSY) goto do_rename_exit; + /* Don't fall back to using SMB on SMB 2+ mount */ + if (server->vals->protocol_id != 0) + goto do_rename_exit; + /* open-file renames don't work across directories */ if (to_dentry->d_parent != from_dentry->d_parent) goto do_rename_exit; diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 1a6040998227..b1a696a73f7c 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -501,8 +501,7 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &pCifsInode->flags); - queue_work(cifsoplockd_wq, - &netfile->oplock_break); + cifs_queue_oplock_break(netfile); netfile->oplock_break_cancelled = false; spin_unlock(&tcon->open_file_lock); @@ -607,6 +606,28 @@ void cifs_put_writer(struct cifsInodeInfo *cinode) spin_unlock(&cinode->writers_lock); } +/** + * cifs_queue_oplock_break - queue the oplock break handler for cfile + * + * This function is called from the demultiplex thread when it + * receives an oplock break for @cfile. + * + * Assumes the tcon->open_file_lock is held. + * Assumes cfile->file_info_lock is NOT held. + */ +void cifs_queue_oplock_break(struct cifsFileInfo *cfile) +{ + /* + * Bump the handle refcount now while we hold the + * open_file_lock to enforce the validity of it for the oplock + * break handler. The matching put is done at the end of the + * handler. + */ + cifsFileInfo_get(cfile); + + queue_work(cifsoplockd_wq, &cfile->oplock_break); +} + void cifs_done_oplock_break(struct cifsInodeInfo *cinode) { clear_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags); @@ -768,6 +789,11 @@ cifs_aio_ctx_alloc(void) { struct cifs_aio_ctx *ctx; + /* + * Must use kzalloc to initialize ctx->bv to NULL and ctx->direct_io + * to false so that we know when we have to unreference pages within + * cifs_aio_ctx_release() + */ ctx = kzalloc(sizeof(struct cifs_aio_ctx), GFP_KERNEL); if (!ctx) return NULL; @@ -786,7 +812,23 @@ cifs_aio_ctx_release(struct kref *refcount) struct cifs_aio_ctx, refcount); cifsFileInfo_put(ctx->cfile); - kvfree(ctx->bv); + + /* + * ctx->bv is only set if setup_aio_ctx_iter() was call successfuly + * which means that iov_iter_get_pages() was a success and thus that + * we have taken reference on pages. + */ + if (ctx->bv) { + unsigned i; + + for (i = 0; i < ctx->npages; i++) { + if (ctx->should_dirty) + set_page_dirty(ctx->bv[i].bv_page); + put_page(ctx->bv[i].bv_page); + } + kvfree(ctx->bv); + } + kfree(ctx); } diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index b204e84b87fb..54bffb2a1786 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -68,13 +68,15 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, if (oparms->tcon->use_resilient) { - nr_ioctl_req.Timeout = 0; /* use server default (120 seconds) */ + /* default timeout is 0, servers pick default (120 seconds) */ + nr_ioctl_req.Timeout = + cpu_to_le32(oparms->tcon->handle_timeout); nr_ioctl_req.Reserved = 0; rc = SMB2_ioctl(xid, oparms->tcon, fid->persistent_fid, fid->volatile_fid, FSCTL_LMR_REQUEST_RESILIENCY, true /* is_fsctl */, (char *)&nr_ioctl_req, sizeof(nr_ioctl_req), - NULL, NULL /* no return info */); + CIFSMaxBufSize, NULL, NULL /* no return info */); if (rc == -EOPNOTSUPP) { cifs_dbg(VFS, "resiliency not supported by server, disabling\n"); diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c index 924269cec135..e32c264e3adb 100644 --- a/fs/cifs/smb2maperror.c +++ b/fs/cifs/smb2maperror.c @@ -1036,7 +1036,8 @@ static const struct status_to_posix_error smb2_error_map_table[] = { {STATUS_UNFINISHED_CONTEXT_DELETED, -EIO, "STATUS_UNFINISHED_CONTEXT_DELETED"}, {STATUS_NO_TGT_REPLY, -EIO, "STATUS_NO_TGT_REPLY"}, - {STATUS_OBJECTID_NOT_FOUND, -EIO, "STATUS_OBJECTID_NOT_FOUND"}, + /* Note that ENOATTTR and ENODATA are the same errno */ + {STATUS_OBJECTID_NOT_FOUND, -ENODATA, "STATUS_OBJECTID_NOT_FOUND"}, {STATUS_NO_IP_ADDRESSES, -EIO, "STATUS_NO_IP_ADDRESSES"}, {STATUS_WRONG_CREDENTIAL_HANDLE, -EIO, "STATUS_WRONG_CREDENTIAL_HANDLE"}, diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 0e3570e40ff8..e311f58dc1c8 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -555,7 +555,7 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp, clear_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags); - queue_work(cifsoplockd_wq, &cfile->oplock_break); + cifs_queue_oplock_break(cfile); kfree(lw); return true; } @@ -712,8 +712,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags); spin_unlock(&cfile->file_info_lock); - queue_work(cifsoplockd_wq, - &cfile->oplock_break); + + cifs_queue_oplock_break(cfile); spin_unlock(&tcon->open_file_lock); spin_unlock(&cifs_tcp_ses_lock); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 1022a3771e14..c36ff0d1fe2a 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -581,7 +581,7 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon) rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, FSCTL_QUERY_NETWORK_INTERFACE_INFO, true /* is_fsctl */, NULL /* no data input */, 0 /* no data input */, - (char **)&out_buf, &ret_data_len); + CIFSMaxBufSize, (char **)&out_buf, &ret_data_len); if (rc == -EOPNOTSUPP) { cifs_dbg(FYI, "server does not support query network interfaces\n"); @@ -717,32 +717,28 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid) oparms.fid->mid = le64_to_cpu(o_rsp->sync_hdr.MessageId); #endif /* CIFS_DEBUG2 */ - if (o_rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) - oplock = smb2_parse_lease_state(server, o_rsp, - &oparms.fid->epoch, - oparms.fid->lease_key); - else - goto oshr_exit; - - memcpy(tcon->crfid.fid, pfid, sizeof(struct cifs_fid)); tcon->crfid.tcon = tcon; tcon->crfid.is_valid = true; kref_init(&tcon->crfid.refcount); - kref_get(&tcon->crfid.refcount); + if (o_rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) { + kref_get(&tcon->crfid.refcount); + oplock = smb2_parse_lease_state(server, o_rsp, + &oparms.fid->epoch, + oparms.fid->lease_key); + } else + goto oshr_exit; qi_rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base; if (le32_to_cpu(qi_rsp->OutputBufferLength) < sizeof(struct smb2_file_all_info)) goto oshr_exit; - rc = smb2_validate_and_copy_iov( + if (!smb2_validate_and_copy_iov( le16_to_cpu(qi_rsp->OutputBufferOffset), sizeof(struct smb2_file_all_info), &rsp_iov[1], sizeof(struct smb2_file_all_info), - (char *)&tcon->crfid.file_all_info); - if (rc) - goto oshr_exit; - tcon->crfid.file_all_info_is_valid = 1; + (char *)&tcon->crfid.file_all_info)) + tcon->crfid.file_all_info_is_valid = 1; oshr_exit: mutex_unlock(&tcon->crfid.fid_mutex); @@ -1299,7 +1295,7 @@ SMB2_request_res_key(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid, FSCTL_SRV_REQUEST_RESUME_KEY, true /* is_fsctl */, - NULL, 0 /* no input */, + NULL, 0 /* no input */, CIFSMaxBufSize, (char **)&res_key, &ret_data_len); if (rc) { @@ -1404,7 +1400,7 @@ smb2_ioctl_query_info(const unsigned int xid, rc = SMB2_ioctl_init(tcon, &rqst[1], COMPOUND_FID, COMPOUND_FID, qi.info_type, true, NULL, - 0); + 0, CIFSMaxBufSize); } } else if (qi.flags == PASSTHRU_QUERY_INFO) { memset(&qi_iov, 0, sizeof(qi_iov)); @@ -1532,8 +1528,8 @@ smb2_copychunk_range(const unsigned int xid, rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid, trgtfile->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE, true /* is_fsctl */, (char *)pcchunk, - sizeof(struct copychunk_ioctl), (char **)&retbuf, - &ret_data_len); + sizeof(struct copychunk_ioctl), CIFSMaxBufSize, + (char **)&retbuf, &ret_data_len); if (rc == 0) { if (ret_data_len != sizeof(struct copychunk_ioctl_rsp)) { @@ -1693,7 +1689,7 @@ static bool smb2_set_sparse(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SET_SPARSE, true /* is_fctl */, - &setsparse, 1, NULL, NULL); + &setsparse, 1, CIFSMaxBufSize, NULL, NULL); if (rc) { tcon->broken_sparse_sup = true; cifs_dbg(FYI, "set sparse rc = %d\n", rc); @@ -1766,7 +1762,7 @@ smb2_duplicate_extents(const unsigned int xid, true /* is_fsctl */, (char *)&dup_ext_buf, sizeof(struct duplicate_extents_to_file), - NULL, + CIFSMaxBufSize, NULL, &ret_data_len); if (ret_data_len > 0) @@ -1801,7 +1797,7 @@ smb3_set_integrity(const unsigned int xid, struct cifs_tcon *tcon, true /* is_fsctl */, (char *)&integr_info, sizeof(struct fsctl_set_integrity_information_req), - NULL, + CIFSMaxBufSize, NULL, &ret_data_len); } @@ -1809,6 +1805,8 @@ smb3_set_integrity(const unsigned int xid, struct cifs_tcon *tcon, /* GMT Token is @GMT-YYYY.MM.DD-HH.MM.SS Unicode which is 48 bytes + null */ #define GMT_TOKEN_SIZE 50 +#define MIN_SNAPSHOT_ARRAY_SIZE 16 /* See MS-SMB2 section 3.3.5.15.1 */ + /* * Input buffer contains (empty) struct smb_snapshot array with size filled in * For output see struct SRV_SNAPSHOT_ARRAY in MS-SMB2 section 2.2.32.2 @@ -1820,13 +1818,29 @@ smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon, char *retbuf = NULL; unsigned int ret_data_len = 0; int rc; + u32 max_response_size; struct smb_snapshot_array snapshot_in; + if (get_user(ret_data_len, (unsigned int __user *)ioc_buf)) + return -EFAULT; + + /* + * Note that for snapshot queries that servers like Azure expect that + * the first query be minimal size (and just used to get the number/size + * of previous versions) so response size must be specified as EXACTLY + * sizeof(struct snapshot_array) which is 16 when rounded up to multiple + * of eight bytes. + */ + if (ret_data_len == 0) + max_response_size = MIN_SNAPSHOT_ARRAY_SIZE; + else + max_response_size = CIFSMaxBufSize; + rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SRV_ENUMERATE_SNAPSHOTS, true /* is_fsctl */, - NULL, 0 /* no input data */, + NULL, 0 /* no input data */, max_response_size, (char **)&retbuf, &ret_data_len); cifs_dbg(FYI, "enum snaphots ioctl returned %d and ret buflen is %d\n", @@ -2304,7 +2318,7 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, FSCTL_DFS_GET_REFERRALS, true /* is_fsctl */, - (char *)dfs_req, dfs_req_size, + (char *)dfs_req, dfs_req_size, CIFSMaxBufSize, (char **)&dfs_rsp, &dfs_rsp_size); } while (rc == -EAGAIN); @@ -2375,6 +2389,8 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, &err_iov, &resp_buftype); + if (!rc) + SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); if (!rc || !err_iov.iov_base) { rc = -ENOENT; goto free_path; @@ -2658,7 +2674,8 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, rc = SMB2_ioctl_init(tcon, &rqst[num++], cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA, true /* is_fctl */, (char *)&fsctl_buf, - sizeof(struct file_zero_data_information)); + sizeof(struct file_zero_data_information), + CIFSMaxBufSize); if (rc) goto zero_range_exit; @@ -2735,7 +2752,8 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA, true /* is_fctl */, (char *)&fsctl_buf, - sizeof(struct file_zero_data_information), NULL, NULL); + sizeof(struct file_zero_data_information), + CIFSMaxBufSize, NULL, NULL); free_xid(xid); return rc; } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index c399e09b76e6..a37774a55f3a 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -832,8 +832,11 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) } else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) { /* ops set to 3.0 by default for default so update */ ses->server->ops = &smb21_operations; - } else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) + ses->server->vals = &smb21_values; + } else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) { ses->server->ops = &smb311_operations; + ses->server->vals = &smb311_values; + } } else if (le16_to_cpu(rsp->DialectRevision) != ses->server->vals->protocol_id) { /* if requested single dialect ensure returned dialect matched */ @@ -1002,7 +1005,8 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon) rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, FSCTL_VALIDATE_NEGOTIATE_INFO, true /* is_fsctl */, - (char *)pneg_inbuf, inbuflen, (char **)&pneg_rsp, &rsplen); + (char *)pneg_inbuf, inbuflen, CIFSMaxBufSize, + (char **)&pneg_rsp, &rsplen); if (rc == -EOPNOTSUPP) { /* * Old Windows versions or Netapp SMB server can return @@ -1628,9 +1632,16 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, iov[1].iov_base = unc_path; iov[1].iov_len = unc_path_len; - /* 3.11 tcon req must be signed if not encrypted. See MS-SMB2 3.2.4.1.1 */ + /* + * 3.11 tcon req must be signed if not encrypted. See MS-SMB2 3.2.4.1.1 + * unless it is guest or anonymous user. See MS-SMB2 3.2.5.3.1 + * (Samba servers don't always set the flag so also check if null user) + */ if ((ses->server->dialect == SMB311_PROT_ID) && - !smb3_encryption_required(tcon)) + !smb3_encryption_required(tcon) && + !(ses->session_flags & + (SMB2_SESSION_FLAG_IS_GUEST|SMB2_SESSION_FLAG_IS_NULL)) && + ((ses->user_name != NULL) || (ses->sectype == Kerberos))) req->sync_hdr.Flags |= SMB2_FLAGS_SIGNED; memset(&rqst, 0, sizeof(struct smb_rqst)); @@ -1851,8 +1862,9 @@ add_lease_context(struct TCP_Server_Info *server, struct kvec *iov, } static struct create_durable_v2 * -create_durable_v2_buf(struct cifs_fid *pfid) +create_durable_v2_buf(struct cifs_open_parms *oparms) { + struct cifs_fid *pfid = oparms->fid; struct create_durable_v2 *buf; buf = kzalloc(sizeof(struct create_durable_v2), GFP_KERNEL); @@ -1866,7 +1878,14 @@ create_durable_v2_buf(struct cifs_fid *pfid) (struct create_durable_v2, Name)); buf->ccontext.NameLength = cpu_to_le16(4); - buf->dcontext.Timeout = 0; /* Should this be configurable by workload */ + /* + * NB: Handle timeout defaults to 0, which allows server to choose + * (most servers default to 120 seconds) and most clients default to 0. + * This can be overridden at mount ("handletimeout=") if the user wants + * a different persistent (or resilient) handle timeout for all opens + * opens on a particular SMB3 mount. + */ + buf->dcontext.Timeout = cpu_to_le32(oparms->tcon->handle_timeout); buf->dcontext.Flags = cpu_to_le32(SMB2_DHANDLE_FLAG_PERSISTENT); generate_random_uuid(buf->dcontext.CreateGuid); memcpy(pfid->create_guid, buf->dcontext.CreateGuid, 16); @@ -1919,7 +1938,7 @@ add_durable_v2_context(struct kvec *iov, unsigned int *num_iovec, struct smb2_create_req *req = iov[0].iov_base; unsigned int num = *num_iovec; - iov[num].iov_base = create_durable_v2_buf(oparms->fid); + iov[num].iov_base = create_durable_v2_buf(oparms); if (iov[num].iov_base == NULL) return -ENOMEM; iov[num].iov_len = sizeof(struct create_durable_v2); @@ -2471,7 +2490,8 @@ creat_exit: int SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, u64 persistent_fid, u64 volatile_fid, u32 opcode, - bool is_fsctl, char *in_data, u32 indatalen) + bool is_fsctl, char *in_data, u32 indatalen, + __u32 max_response_size) { struct smb2_ioctl_req *req; struct kvec *iov = rqst->rq_iov; @@ -2513,16 +2533,21 @@ SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, req->OutputCount = 0; /* MBZ */ /* - * Could increase MaxOutputResponse, but that would require more - * than one credit. Windows typically sets this smaller, but for some + * In most cases max_response_size is set to 16K (CIFSMaxBufSize) + * We Could increase default MaxOutputResponse, but that could require + * more credits. Windows typically sets this smaller, but for some * ioctls it may be useful to allow server to send more. No point * limiting what the server can send as long as fits in one credit - * Unfortunately - we can not handle more than CIFS_MAX_MSG_SIZE - * (by default, note that it can be overridden to make max larger) - * in responses (except for read responses which can be bigger. - * We may want to bump this limit up + * We can not handle more than CIFS_MAX_BUF_SIZE yet but may want + * to increase this limit up in the future. + * Note that for snapshot queries that servers like Azure expect that + * the first query be minimal size (and just used to get the number/size + * of previous versions) so response size must be specified as EXACTLY + * sizeof(struct snapshot_array) which is 16 when rounded up to multiple + * of eight bytes. Currently that is the only case where we set max + * response size smaller. */ - req->MaxOutputResponse = cpu_to_le32(CIFSMaxBufSize); + req->MaxOutputResponse = cpu_to_le32(max_response_size); if (is_fsctl) req->Flags = cpu_to_le32(SMB2_0_IOCTL_IS_FSCTL); @@ -2543,13 +2568,14 @@ SMB2_ioctl_free(struct smb_rqst *rqst) cifs_small_buf_release(rqst->rq_iov[0].iov_base); /* request */ } + /* * SMB2 IOCTL is used for both IOCTLs and FSCTLs */ int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, u32 opcode, bool is_fsctl, - char *in_data, u32 indatalen, + char *in_data, u32 indatalen, u32 max_out_data_len, char **out_data, u32 *plen /* returned data len */) { struct smb_rqst rqst; @@ -2586,8 +2612,8 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, rqst.rq_iov = iov; rqst.rq_nvec = SMB2_IOCTL_IOV_SIZE; - rc = SMB2_ioctl_init(tcon, &rqst, persistent_fid, volatile_fid, - opcode, is_fsctl, in_data, indatalen); + rc = SMB2_ioctl_init(tcon, &rqst, persistent_fid, volatile_fid, opcode, + is_fsctl, in_data, indatalen, max_out_data_len); if (rc) goto ioctl_exit; @@ -2665,7 +2691,8 @@ SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid, FSCTL_SET_COMPRESSION, true /* is_fsctl */, (char *)&fsctl_input /* data input */, - 2 /* in data len */, &ret_data /* out data */, NULL); + 2 /* in data len */, CIFSMaxBufSize /* max out data */, + &ret_data /* out data */, NULL); cifs_dbg(FYI, "set compression rc %d\n", rc); @@ -3424,8 +3451,6 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, rqst.rq_nvec = 1; rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); - cifs_small_buf_release(req); - rsp = (struct smb2_read_rsp *)rsp_iov.iov_base; if (rc) { @@ -3441,12 +3466,15 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, io_parms->tcon->tid, ses->Suid, io_parms->offset, 0); free_rsp_buf(resp_buftype, rsp_iov.iov_base); + cifs_small_buf_release(req); return rc == -ENODATA ? 0 : rc; } else trace_smb3_read_done(xid, req->PersistentFileId, io_parms->tcon->tid, ses->Suid, io_parms->offset, io_parms->length); + cifs_small_buf_release(req); + *nbytes = le32_to_cpu(rsp->DataLength); if ((*nbytes > CIFS_MAX_MSGSIZE) || (*nbytes > io_parms->length)) { @@ -3745,7 +3773,6 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms, rc = cifs_send_recv(xid, io_parms->tcon->ses, &rqst, &resp_buftype, flags, &rsp_iov); - cifs_small_buf_release(req); rsp = (struct smb2_write_rsp *)rsp_iov.iov_base; if (rc) { @@ -3763,6 +3790,7 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms, io_parms->offset, *nbytes); } + cifs_small_buf_release(req); free_rsp_buf(resp_buftype, rsp); return rc; } diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 3c32d0cfea69..52df125e9189 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -142,11 +142,12 @@ extern int SMB2_open_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, extern void SMB2_open_free(struct smb_rqst *rqst); extern int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, u32 opcode, - bool is_fsctl, char *in_data, u32 indatalen, + bool is_fsctl, char *in_data, u32 indatalen, u32 maxoutlen, char **out_data, u32 *plen /* returned data len */); extern int SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, u64 persistent_fid, u64 volatile_fid, u32 opcode, - bool is_fsctl, char *in_data, u32 indatalen); + bool is_fsctl, char *in_data, u32 indatalen, + __u32 max_response_size); extern void SMB2_ioctl_free(struct smb_rqst *rqst); extern int SMB2_close(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_file_id, u64 volatile_file_id); diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h index fa226de48ef3..99c4d799c24b 100644 --- a/fs/cifs/trace.h +++ b/fs/cifs/trace.h @@ -549,19 +549,19 @@ DECLARE_EVENT_CLASS(smb3_tcon_class, __field(unsigned int, xid) __field(__u32, tid) __field(__u64, sesid) - __field(const char *, unc_name) + __string(name, unc_name) __field(int, rc) ), TP_fast_assign( __entry->xid = xid; __entry->tid = tid; __entry->sesid = sesid; - __entry->unc_name = unc_name; + __assign_str(name, unc_name); __entry->rc = rc; ), TP_printk("xid=%u sid=0x%llx tid=0x%x unc_name=%s rc=%d", __entry->xid, __entry->sesid, __entry->tid, - __entry->unc_name, __entry->rc) + __get_str(name), __entry->rc) ) #define DEFINE_SMB3_TCON_EVENT(name) \ @@ -33,6 +33,7 @@ #include <linux/sizes.h> #include <linux/mmu_notifier.h> #include <linux/iomap.h> +#include <asm/pgalloc.h> #include "internal.h" #define CREATE_TRACE_POINTS @@ -1407,7 +1408,9 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, { struct address_space *mapping = vmf->vma->vm_file->f_mapping; unsigned long pmd_addr = vmf->address & PMD_MASK; + struct vm_area_struct *vma = vmf->vma; struct inode *inode = mapping->host; + pgtable_t pgtable = NULL; struct page *zero_page; spinlock_t *ptl; pmd_t pmd_entry; @@ -1422,12 +1425,22 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, *entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn, DAX_PMD | DAX_ZERO_PAGE, false); + if (arch_needs_pgtable_deposit()) { + pgtable = pte_alloc_one(vma->vm_mm); + if (!pgtable) + return VM_FAULT_OOM; + } + ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); if (!pmd_none(*(vmf->pmd))) { spin_unlock(ptl); goto fallback; } + if (pgtable) { + pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); + mm_inc_nr_ptes(vma->vm_mm); + } pmd_entry = mk_pmd(zero_page, vmf->vma->vm_page_prot); pmd_entry = pmd_mkhuge(pmd_entry); set_pmd_at(vmf->vma->vm_mm, pmd_addr, vmf->pmd, pmd_entry); @@ -1436,6 +1449,8 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, return VM_FAULT_NOPAGE; fallback: + if (pgtable) + pte_free(vma->vm_mm, pgtable); trace_dax_pmd_load_hole_fallback(inode, vmf, zero_page, *entry); return VM_FAULT_FALLBACK; } diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 95b5e78c22b1..f25daa207421 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -163,19 +163,24 @@ static int debugfs_show_options(struct seq_file *m, struct dentry *root) return 0; } -static void debugfs_evict_inode(struct inode *inode) +static void debugfs_i_callback(struct rcu_head *head) { - truncate_inode_pages_final(&inode->i_data); - clear_inode(inode); + struct inode *inode = container_of(head, struct inode, i_rcu); if (S_ISLNK(inode->i_mode)) kfree(inode->i_link); + free_inode_nonrcu(inode); +} + +static void debugfs_destroy_inode(struct inode *inode) +{ + call_rcu(&inode->i_rcu, debugfs_i_callback); } static const struct super_operations debugfs_super_operations = { .statfs = simple_statfs, .remount_fs = debugfs_remount, .show_options = debugfs_show_options, - .evict_inode = debugfs_evict_inode, + .destroy_inode = debugfs_destroy_inode, }; static void debugfs_release_dentry(struct dentry *dentry) diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index a1ac7e9245ec..75a5309f2231 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -384,7 +384,7 @@ static inline void ext4_update_inode_fsync_trans(handle_t *handle, { struct ext4_inode_info *ei = EXT4_I(inode); - if (ext4_handle_valid(handle)) { + if (ext4_handle_valid(handle) && !is_handle_aborted(handle)) { ei->i_sync_tid = handle->h_transaction->t_tid; if (datasync) ei->i_datasync_tid = handle->h_transaction->t_tid; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 69d65d49837b..98ec11f69cd4 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -125,7 +125,7 @@ ext4_unaligned_aio(struct inode *inode, struct iov_iter *from, loff_t pos) struct super_block *sb = inode->i_sb; int blockmask = sb->s_blocksize - 1; - if (pos >= i_size_read(inode)) + if (pos >= ALIGN(i_size_read(inode), sb->s_blocksize)) return 0; if ((pos | iov_iter_alignment(from)) & blockmask) diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index c2225f0d31b5..2024d3fa5504 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -1222,6 +1222,7 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode, ext4_lblk_t offsets[4], offsets2[4]; Indirect chain[4], chain2[4]; Indirect *partial, *partial2; + Indirect *p = NULL, *p2 = NULL; ext4_lblk_t max_block; __le32 nr = 0, nr2 = 0; int n = 0, n2 = 0; @@ -1263,7 +1264,7 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode, } - partial = ext4_find_shared(inode, n, offsets, chain, &nr); + partial = p = ext4_find_shared(inode, n, offsets, chain, &nr); if (nr) { if (partial == chain) { /* Shared branch grows from the inode */ @@ -1288,13 +1289,11 @@ int ext4_ind_remove_space(handle_t *handle, struct inode *inode, partial->p + 1, (__le32 *)partial->bh->b_data+addr_per_block, (chain+n-1) - partial); - BUFFER_TRACE(partial->bh, "call brelse"); - brelse(partial->bh); partial--; } end_range: - partial2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2); + partial2 = p2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2); if (nr2) { if (partial2 == chain2) { /* @@ -1324,16 +1323,14 @@ end_range: (__le32 *)partial2->bh->b_data, partial2->p, (chain2+n2-1) - partial2); - BUFFER_TRACE(partial2->bh, "call brelse"); - brelse(partial2->bh); partial2--; } goto do_indirects; } /* Punch happened within the same level (n == n2) */ - partial = ext4_find_shared(inode, n, offsets, chain, &nr); - partial2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2); + partial = p = ext4_find_shared(inode, n, offsets, chain, &nr); + partial2 = p2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2); /* Free top, but only if partial2 isn't its subtree. */ if (nr) { @@ -1390,11 +1387,7 @@ end_range: partial->p + 1, partial2->p, (chain+n-1) - partial); - BUFFER_TRACE(partial->bh, "call brelse"); - brelse(partial->bh); - BUFFER_TRACE(partial2->bh, "call brelse"); - brelse(partial2->bh); - return 0; + goto cleanup; } /* @@ -1409,8 +1402,6 @@ end_range: partial->p + 1, (__le32 *)partial->bh->b_data+addr_per_block, (chain+n-1) - partial); - BUFFER_TRACE(partial->bh, "call brelse"); - brelse(partial->bh); partial--; } if (partial2 > chain2 && depth2 <= depth) { @@ -1418,11 +1409,21 @@ end_range: (__le32 *)partial2->bh->b_data, partial2->p, (chain2+n2-1) - partial2); - BUFFER_TRACE(partial2->bh, "call brelse"); - brelse(partial2->bh); partial2--; } } + +cleanup: + while (p && p > chain) { + BUFFER_TRACE(p->bh, "call brelse"); + brelse(p->bh); + p--; + } + while (p2 && p2 > chain2) { + BUFFER_TRACE(p2->bh, "call brelse"); + brelse(p2->bh); + p2--; + } return 0; do_indirects: @@ -1430,7 +1431,7 @@ do_indirects: switch (offsets[0]) { default: if (++n >= n2) - return 0; + break; nr = i_data[EXT4_IND_BLOCK]; if (nr) { ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1); @@ -1439,7 +1440,7 @@ do_indirects: /* fall through */ case EXT4_IND_BLOCK: if (++n >= n2) - return 0; + break; nr = i_data[EXT4_DIND_BLOCK]; if (nr) { ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2); @@ -1448,7 +1449,7 @@ do_indirects: /* fall through */ case EXT4_DIND_BLOCK: if (++n >= n2) - return 0; + break; nr = i_data[EXT4_TIND_BLOCK]; if (nr) { ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3); @@ -1458,5 +1459,5 @@ do_indirects: case EXT4_TIND_BLOCK: ; } - return 0; + goto cleanup; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index b54b261ded36..b32a57bc5d5d 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -6080,36 +6080,6 @@ out: return; } -#if 0 -/* - * Bind an inode's backing buffer_head into this transaction, to prevent - * it from being flushed to disk early. Unlike - * ext4_reserve_inode_write, this leaves behind no bh reference and - * returns no iloc structure, so the caller needs to repeat the iloc - * lookup to mark the inode dirty later. - */ -static int ext4_pin_inode(handle_t *handle, struct inode *inode) -{ - struct ext4_iloc iloc; - - int err = 0; - if (handle) { - err = ext4_get_inode_loc(inode, &iloc); - if (!err) { - BUFFER_TRACE(iloc.bh, "get_write_access"); - err = jbd2_journal_get_write_access(handle, iloc.bh); - if (!err) - err = ext4_handle_dirty_metadata(handle, - NULL, - iloc.bh); - brelse(iloc.bh); - } - } - ext4_std_error(inode->i_sb, err); - return err; -} -#endif - int ext4_change_inode_journal_flag(struct inode *inode, int val) { journal_t *journal; diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 3c4f8bb59f8a..bab3da4f1e0d 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -1000,6 +1000,13 @@ resizefs_out: if (!blk_queue_discard(q)) return -EOPNOTSUPP; + /* + * We haven't replayed the journal, so we cannot use our + * block-bitmap-guided storage zapping commands. + */ + if (test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) + return -EROFS; + if (copy_from_user(&range, (struct fstrim_range __user *)arg, sizeof(range))) return -EFAULT; diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 3d9b18505c0c..e7ae26e36c9c 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -932,11 +932,18 @@ static int add_new_gdb_meta_bg(struct super_block *sb, memcpy(n_group_desc, o_group_desc, EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *)); n_group_desc[gdb_num] = gdb_bh; + + BUFFER_TRACE(gdb_bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, gdb_bh); + if (err) { + kvfree(n_group_desc); + brelse(gdb_bh); + return err; + } + EXT4_SB(sb)->s_group_desc = n_group_desc; EXT4_SB(sb)->s_gdb_count++; kvfree(o_group_desc); - BUFFER_TRACE(gdb_bh, "get_write_access"); - err = ext4_journal_get_write_access(handle, gdb_bh); return err; } @@ -2073,6 +2080,10 @@ out: free_flex_gd(flex_gd); if (resize_inode != NULL) iput(resize_inode); - ext4_msg(sb, KERN_INFO, "resized filesystem to %llu", n_blocks_count); + if (err) + ext4_warning(sb, "error (%d) occurred during " + "file system resize", err); + ext4_msg(sb, KERN_INFO, "resized filesystem to %llu", + ext4_blocks_count(es)); return err; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index f5b828bf1299..6ed4eb81e674 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -430,6 +430,12 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn) spin_unlock(&sbi->s_md_lock); } +static bool system_going_down(void) +{ + return system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF + || system_state == SYSTEM_RESTART; +} + /* Deal with the reporting of failure conditions on a filesystem such as * inconsistencies detected or read IO failures. * @@ -460,7 +466,12 @@ static void ext4_handle_error(struct super_block *sb) if (journal) jbd2_journal_abort(journal, -EIO); } - if (test_opt(sb, ERRORS_RO)) { + /* + * We force ERRORS_RO behavior when system is rebooting. Otherwise we + * could panic during 'reboot -f' as the underlying device got already + * disabled. + */ + if (test_opt(sb, ERRORS_RO) || system_going_down()) { ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); /* * Make sure updated value of ->s_mount_flags will be visible @@ -468,8 +479,7 @@ static void ext4_handle_error(struct super_block *sb) */ smp_wmb(); sb->s_flags |= SB_RDONLY; - } - if (test_opt(sb, ERRORS_PANIC)) { + } else if (test_opt(sb, ERRORS_PANIC)) { if (EXT4_SB(sb)->s_journal && !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR)) return; diff --git a/fs/fs_parser.c b/fs/fs_parser.c index 842e8f749db6..570d71043acf 100644 --- a/fs/fs_parser.c +++ b/fs/fs_parser.c @@ -410,7 +410,7 @@ bool fs_validate_description(const struct fs_parameter_description *desc) for (param = desc->specs; param->name; param++) { if (param->opt == e->opt && param->type != fs_param_is_enum) { - pr_err("VALIDATE %s: e[%lu] enum val for %s\n", + pr_err("VALIDATE %s: e[%tu] enum val for %s\n", name, e - desc->enums, param->name); good = false; } diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 8a63e52785e9..9971a35cf1ef 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -2056,10 +2056,8 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, rem += pipe->bufs[(pipe->curbuf + idx) & (pipe->buffers - 1)].len; ret = -EINVAL; - if (rem < len) { - pipe_unlock(pipe); - goto out; - } + if (rem < len) + goto out_free; rem = len; while (rem) { @@ -2077,7 +2075,9 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1); pipe->nrbufs--; } else { - pipe_buf_get(pipe, ibuf); + if (!pipe_buf_get(pipe, ibuf)) + goto out_free; + *obuf = *ibuf; obuf->flags &= ~PIPE_BUF_FLAG_GIFT; obuf->len = rem; @@ -2100,11 +2100,11 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, ret = fuse_dev_do_write(fud, &cs, len); pipe_lock(pipe); +out_free: for (idx = 0; idx < nbuf; idx++) pipe_buf_release(pipe, &bufs[idx]); pipe_unlock(pipe); -out: kvfree(bufs); return ret; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index ec32fece5e1e..9285dd4f4b1c 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -755,11 +755,17 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, umode_t mode, dev_t dev) { struct inode *inode; - struct resv_map *resv_map; + struct resv_map *resv_map = NULL; - resv_map = resv_map_alloc(); - if (!resv_map) - return NULL; + /* + * Reserve maps are only needed for inodes that can have associated + * page allocations. + */ + if (S_ISREG(mode) || S_ISLNK(mode)) { + resv_map = resv_map_alloc(); + if (!resv_map) + return NULL; + } inode = new_inode(sb); if (inode) { @@ -794,8 +800,10 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, break; } lockdep_annotate_inode_mutex_key(inode); - } else - kref_put(&resv_map->refs, resv_map_release); + } else { + if (resv_map) + kref_put(&resv_map->refs, resv_map_release); + } return inode; } diff --git a/fs/inode.c b/fs/inode.c index e9d97add2b36..9a453f3637f8 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1817,8 +1817,13 @@ int file_remove_privs(struct file *file) int kill; int error = 0; - /* Fast path for nothing security related */ - if (IS_NOSEC(inode)) + /* + * Fast path for nothing security related. + * As well for non-regular files, e.g. blkdev inodes. + * For example, blkdev_write_iter() might get here + * trying to remove privs which it is not allowed to. + */ + if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode)) return 0; kill = dentry_needs_remove_privs(dentry); diff --git a/fs/io_uring.c b/fs/io_uring.c index c88088d92613..84efb8956734 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -4,15 +4,28 @@ * supporting fast/efficient IO. * * A note on the read/write ordering memory barriers that are matched between - * the application and kernel side. When the application reads the CQ ring - * tail, it must use an appropriate smp_rmb() to order with the smp_wmb() - * the kernel uses after writing the tail. Failure to do so could cause a - * delay in when the application notices that completion events available. - * This isn't a fatal condition. Likewise, the application must use an - * appropriate smp_wmb() both before writing the SQ tail, and after writing - * the SQ tail. The first one orders the sqe writes with the tail write, and - * the latter is paired with the smp_rmb() the kernel will issue before - * reading the SQ tail on submission. + * the application and kernel side. + * + * After the application reads the CQ ring tail, it must use an + * appropriate smp_rmb() to pair with the smp_wmb() the kernel uses + * before writing the tail (using smp_load_acquire to read the tail will + * do). It also needs a smp_mb() before updating CQ head (ordering the + * entry load(s) with the head store), pairing with an implicit barrier + * through a control-dependency in io_get_cqring (smp_store_release to + * store head will do). Failure to do so could lead to reading invalid + * CQ entries. + * + * Likewise, the application must use an appropriate smp_wmb() before + * writing the SQ tail (ordering SQ entry stores with the tail store), + * which pairs with smp_load_acquire in io_get_sqring (smp_store_release + * to store the tail will do). And it needs a barrier ordering the SQ + * head load before writing new SQ entries (smp_load_acquire to read + * head will do). + * + * When using the SQ poll thread (IORING_SETUP_SQPOLL), the application + * needs to check the SQ flags for IORING_SQ_NEED_WAKEUP *after* + * updating the SQ tail; a full memory barrier smp_mb() is needed + * between. * * Also see the examples in the liburing library: * @@ -70,20 +83,108 @@ struct io_uring { u32 tail ____cacheline_aligned_in_smp; }; +/* + * This data is shared with the application through the mmap at offset + * IORING_OFF_SQ_RING. + * + * The offsets to the member fields are published through struct + * io_sqring_offsets when calling io_uring_setup. + */ struct io_sq_ring { + /* + * Head and tail offsets into the ring; the offsets need to be + * masked to get valid indices. + * + * The kernel controls head and the application controls tail. + */ struct io_uring r; + /* + * Bitmask to apply to head and tail offsets (constant, equals + * ring_entries - 1) + */ u32 ring_mask; + /* Ring size (constant, power of 2) */ u32 ring_entries; + /* + * Number of invalid entries dropped by the kernel due to + * invalid index stored in array + * + * Written by the kernel, shouldn't be modified by the + * application (i.e. get number of "new events" by comparing to + * cached value). + * + * After a new SQ head value was read by the application this + * counter includes all submissions that were dropped reaching + * the new SQ head (and possibly more). + */ u32 dropped; + /* + * Runtime flags + * + * Written by the kernel, shouldn't be modified by the + * application. + * + * The application needs a full memory barrier before checking + * for IORING_SQ_NEED_WAKEUP after updating the sq tail. + */ u32 flags; + /* + * Ring buffer of indices into array of io_uring_sqe, which is + * mmapped by the application using the IORING_OFF_SQES offset. + * + * This indirection could e.g. be used to assign fixed + * io_uring_sqe entries to operations and only submit them to + * the queue when needed. + * + * The kernel modifies neither the indices array nor the entries + * array. + */ u32 array[]; }; +/* + * This data is shared with the application through the mmap at offset + * IORING_OFF_CQ_RING. + * + * The offsets to the member fields are published through struct + * io_cqring_offsets when calling io_uring_setup. + */ struct io_cq_ring { + /* + * Head and tail offsets into the ring; the offsets need to be + * masked to get valid indices. + * + * The application controls head and the kernel tail. + */ struct io_uring r; + /* + * Bitmask to apply to head and tail offsets (constant, equals + * ring_entries - 1) + */ u32 ring_mask; + /* Ring size (constant, power of 2) */ u32 ring_entries; + /* + * Number of completion events lost because the queue was full; + * this should be avoided by the application by making sure + * there are not more requests pending thatn there is space in + * the completion queue. + * + * Written by the kernel, shouldn't be modified by the + * application (i.e. get number of "new events" by comparing to + * cached value). + * + * As completion events come in out of order this counter is not + * ordered with any other data. + */ u32 overflow; + /* + * Ring buffer of completion events. + * + * The kernel writes completion events fresh every time they are + * produced, so the application is allowed to modify pending + * entries. + */ struct io_uring_cqe cqes[]; }; @@ -189,17 +290,28 @@ struct sqe_submit { bool needs_fixed_file; }; +/* + * First field must be the file pointer in all the + * iocb unions! See also 'struct kiocb' in <linux/fs.h> + */ struct io_poll_iocb { struct file *file; struct wait_queue_head *head; __poll_t events; - bool woken; + bool done; bool canceled; struct wait_queue_entry wait; }; +/* + * NOTE! Each of the iocb union members has the file pointer + * as the first entry in their struct definition. So you can + * access the file pointer through any of the sub-structs, + * or directly as just 'ki_filp' in this struct. + */ struct io_kiocb { union { + struct file *file; struct kiocb rw; struct io_poll_iocb poll; }; @@ -210,10 +322,11 @@ struct io_kiocb { struct list_head list; unsigned int flags; refcount_t refs; -#define REQ_F_FORCE_NONBLOCK 1 /* inline submission attempt */ +#define REQ_F_NOWAIT 1 /* must not punt to workers */ #define REQ_F_IOPOLL_COMPLETED 2 /* polled IO has completed */ #define REQ_F_FIXED_FILE 4 /* ctx owns file */ #define REQ_F_SEQ_PREV 8 /* sequential with previous */ +#define REQ_F_PREPPED 16 /* prep already done */ u64 user_data; u64 error; @@ -305,12 +418,6 @@ static void io_commit_cqring(struct io_ring_ctx *ctx) /* order cqe stores with ring update */ smp_store_release(&ring->r.tail, ctx->cached_cq_tail); - /* - * Write sider barrier of tail update, app has read side. See - * comment at the top of this file. - */ - smp_wmb(); - if (wq_has_sleeper(&ctx->cq_wait)) { wake_up_interruptible(&ctx->cq_wait); kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN); @@ -324,9 +431,12 @@ static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx) unsigned tail; tail = ctx->cached_cq_tail; - /* See comment at the top of the file */ - smp_rmb(); - if (tail + 1 == READ_ONCE(ring->r.head)) + /* + * writes to the cq entry need to come after reading head; the + * control dependency is enough as we're using WRITE_ONCE to + * fill the cq entry + */ + if (tail - READ_ONCE(ring->r.head) == ring->ring_entries) return NULL; ctx->cached_cq_tail++; @@ -355,20 +465,25 @@ static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data, } } -static void io_cqring_add_event(struct io_ring_ctx *ctx, u64 ki_user_data, +static void io_cqring_ev_posted(struct io_ring_ctx *ctx) +{ + if (waitqueue_active(&ctx->wait)) + wake_up(&ctx->wait); + if (waitqueue_active(&ctx->sqo_wait)) + wake_up(&ctx->sqo_wait); +} + +static void io_cqring_add_event(struct io_ring_ctx *ctx, u64 user_data, long res, unsigned ev_flags) { unsigned long flags; spin_lock_irqsave(&ctx->completion_lock, flags); - io_cqring_fill_event(ctx, ki_user_data, res, ev_flags); + io_cqring_fill_event(ctx, user_data, res, ev_flags); io_commit_cqring(ctx); spin_unlock_irqrestore(&ctx->completion_lock, flags); - if (waitqueue_active(&ctx->wait)) - wake_up(&ctx->wait); - if (waitqueue_active(&ctx->sqo_wait)) - wake_up(&ctx->sqo_wait); + io_cqring_ev_posted(ctx); } static void io_ring_drop_ctx_refs(struct io_ring_ctx *ctx, unsigned refs) @@ -382,13 +497,14 @@ static void io_ring_drop_ctx_refs(struct io_ring_ctx *ctx, unsigned refs) static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx, struct io_submit_state *state) { + gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; struct io_kiocb *req; if (!percpu_ref_tryget(&ctx->refs)) return NULL; if (!state) { - req = kmem_cache_alloc(req_cachep, __GFP_NOWARN); + req = kmem_cache_alloc(req_cachep, gfp); if (unlikely(!req)) goto out; } else if (!state->free_reqs) { @@ -396,10 +512,18 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx, int ret; sz = min_t(size_t, state->ios_left, ARRAY_SIZE(state->reqs)); - ret = kmem_cache_alloc_bulk(req_cachep, __GFP_NOWARN, sz, - state->reqs); - if (unlikely(ret <= 0)) - goto out; + ret = kmem_cache_alloc_bulk(req_cachep, gfp, sz, state->reqs); + + /* + * Bulk alloc is all-or-nothing. If we fail to get a batch, + * retry single alloc to be on the safe side. + */ + if (unlikely(ret <= 0)) { + state->reqs[0] = kmem_cache_alloc(req_cachep, gfp); + if (!state->reqs[0]) + goto out; + ret = 1; + } state->free_reqs = ret - 1; state->cur_req = 1; req = state->reqs[0]; @@ -411,7 +535,8 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx, req->ctx = ctx; req->flags = 0; - refcount_set(&req->refs, 0); + /* one is dropped after submission, the other at completion */ + refcount_set(&req->refs, 2); return req; out: io_ring_drop_ctx_refs(ctx, 1); @@ -429,10 +554,16 @@ static void io_free_req_many(struct io_ring_ctx *ctx, void **reqs, int *nr) static void io_free_req(struct io_kiocb *req) { - if (!refcount_read(&req->refs) || refcount_dec_and_test(&req->refs)) { - io_ring_drop_ctx_refs(req->ctx, 1); - kmem_cache_free(req_cachep, req); - } + if (req->file && !(req->flags & REQ_F_FIXED_FILE)) + fput(req->file); + io_ring_drop_ctx_refs(req->ctx, 1); + kmem_cache_free(req_cachep, req); +} + +static void io_put_req(struct io_kiocb *req) +{ + if (refcount_dec_and_test(&req->refs)) + io_free_req(req); } /* @@ -442,44 +573,34 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, struct list_head *done) { void *reqs[IO_IOPOLL_BATCH]; - int file_count, to_free; - struct file *file = NULL; struct io_kiocb *req; + int to_free; - file_count = to_free = 0; + to_free = 0; while (!list_empty(done)) { req = list_first_entry(done, struct io_kiocb, list); list_del(&req->list); io_cqring_fill_event(ctx, req->user_data, req->error, 0); - - reqs[to_free++] = req; (*nr_events)++; - /* - * Batched puts of the same file, to avoid dirtying the - * file usage count multiple times, if avoidable. - */ - if (!(req->flags & REQ_F_FIXED_FILE)) { - if (!file) { - file = req->rw.ki_filp; - file_count = 1; - } else if (file == req->rw.ki_filp) { - file_count++; + if (refcount_dec_and_test(&req->refs)) { + /* If we're not using fixed files, we have to pair the + * completion part with the file put. Use regular + * completions for those, only batch free for fixed + * file. + */ + if (req->flags & REQ_F_FIXED_FILE) { + reqs[to_free++] = req; + if (to_free == ARRAY_SIZE(reqs)) + io_free_req_many(ctx, reqs, &to_free); } else { - fput_many(file, file_count); - file = req->rw.ki_filp; - file_count = 1; + io_free_req(req); } } - - if (to_free == ARRAY_SIZE(reqs)) - io_free_req_many(ctx, reqs, &to_free); } - io_commit_cqring(ctx); - if (file) - fput_many(file, file_count); + io_commit_cqring(ctx); io_free_req_many(ctx, reqs, &to_free); } @@ -602,21 +723,14 @@ static void kiocb_end_write(struct kiocb *kiocb) } } -static void io_fput(struct io_kiocb *req) -{ - if (!(req->flags & REQ_F_FIXED_FILE)) - fput(req->rw.ki_filp); -} - static void io_complete_rw(struct kiocb *kiocb, long res, long res2) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw); kiocb_end_write(kiocb); - io_fput(req); io_cqring_add_event(req->ctx, req->user_data, res, 0); - io_free_req(req); + io_put_req(req); } static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) @@ -666,11 +780,9 @@ static void io_iopoll_req_issued(struct io_kiocb *req) list_add_tail(&req->list, &ctx->poll_list); } -static void io_file_put(struct io_submit_state *state, struct file *file) +static void io_file_put(struct io_submit_state *state) { - if (!state) { - fput(file); - } else if (state->file) { + if (state->file) { int diff = state->has_refs - state->used_refs; if (diff) @@ -695,7 +807,7 @@ static struct file *io_file_get(struct io_submit_state *state, int fd) state->ios_left--; return state->file; } - io_file_put(state, NULL); + io_file_put(state); } state->file = fget_many(fd, state->ios_left); if (!state->file) @@ -726,36 +838,23 @@ static bool io_file_supports_async(struct file *file) } static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s, - bool force_nonblock, struct io_submit_state *state) + bool force_nonblock) { const struct io_uring_sqe *sqe = s->sqe; struct io_ring_ctx *ctx = req->ctx; struct kiocb *kiocb = &req->rw; - unsigned ioprio, flags; - int fd, ret; + unsigned ioprio; + int ret; + if (!req->file) + return -EBADF; /* For -EAGAIN retry, everything is already prepped */ - if (kiocb->ki_filp) + if (req->flags & REQ_F_PREPPED) return 0; - flags = READ_ONCE(sqe->flags); - fd = READ_ONCE(sqe->fd); + if (force_nonblock && !io_file_supports_async(req->file)) + force_nonblock = false; - if (flags & IOSQE_FIXED_FILE) { - if (unlikely(!ctx->user_files || - (unsigned) fd >= ctx->nr_user_files)) - return -EBADF; - kiocb->ki_filp = ctx->user_files[fd]; - req->flags |= REQ_F_FIXED_FILE; - } else { - if (s->needs_fixed_file) - return -EBADF; - kiocb->ki_filp = io_file_get(state, fd); - if (unlikely(!kiocb->ki_filp)) - return -EBADF; - if (force_nonblock && !io_file_supports_async(kiocb->ki_filp)) - force_nonblock = false; - } kiocb->ki_pos = READ_ONCE(sqe->off); kiocb->ki_flags = iocb_flags(kiocb->ki_filp); kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp)); @@ -764,7 +863,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s, if (ioprio) { ret = ioprio_check_cap(ioprio); if (ret) - goto out_fput; + return ret; kiocb->ki_ioprio = ioprio; } else @@ -772,38 +871,30 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s, ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags)); if (unlikely(ret)) - goto out_fput; - if (force_nonblock) { + return ret; + + /* don't allow async punt if RWF_NOWAIT was requested */ + if (kiocb->ki_flags & IOCB_NOWAIT) + req->flags |= REQ_F_NOWAIT; + + if (force_nonblock) kiocb->ki_flags |= IOCB_NOWAIT; - req->flags |= REQ_F_FORCE_NONBLOCK; - } + if (ctx->flags & IORING_SETUP_IOPOLL) { - ret = -EOPNOTSUPP; if (!(kiocb->ki_flags & IOCB_DIRECT) || !kiocb->ki_filp->f_op->iopoll) - goto out_fput; + return -EOPNOTSUPP; req->error = 0; kiocb->ki_flags |= IOCB_HIPRI; kiocb->ki_complete = io_complete_rw_iopoll; } else { - if (kiocb->ki_flags & IOCB_HIPRI) { - ret = -EINVAL; - goto out_fput; - } + if (kiocb->ki_flags & IOCB_HIPRI) + return -EINVAL; kiocb->ki_complete = io_complete_rw; } + req->flags |= REQ_F_PREPPED; return 0; -out_fput: - if (!(flags & IOSQE_FIXED_FILE)) { - /* - * in case of error, we didn't use this file reference. drop it. - */ - if (state) - state->used_refs--; - io_file_put(state, kiocb->ki_filp); - } - return ret; } static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) @@ -864,6 +955,9 @@ static int io_import_fixed(struct io_ring_ctx *ctx, int rw, iov_iter_bvec(iter, rw, imu->bvec, imu->nr_bvecs, offset + len); if (offset) iov_iter_advance(iter, offset); + + /* don't drop a reference to these pages */ + iter->type |= ITER_BVEC_FLAG_NO_REF; return 0; } @@ -887,7 +981,7 @@ static int io_import_iovec(struct io_ring_ctx *ctx, int rw, opcode = READ_ONCE(sqe->opcode); if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { - ssize_t ret = io_import_fixed(ctx, rw, sqe, iter); + int ret = io_import_fixed(ctx, rw, sqe, iter); *iovec = NULL; return ret; } @@ -945,31 +1039,29 @@ static void io_async_list_note(int rw, struct io_kiocb *req, size_t len) async_list->io_end = io_end; } -static ssize_t io_read(struct io_kiocb *req, const struct sqe_submit *s, - bool force_nonblock, struct io_submit_state *state) +static int io_read(struct io_kiocb *req, const struct sqe_submit *s, + bool force_nonblock) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct kiocb *kiocb = &req->rw; struct iov_iter iter; struct file *file; size_t iov_count; - ssize_t ret; + int ret; - ret = io_prep_rw(req, s, force_nonblock, state); + ret = io_prep_rw(req, s, force_nonblock); if (ret) return ret; file = kiocb->ki_filp; - ret = -EBADF; if (unlikely(!(file->f_mode & FMODE_READ))) - goto out_fput; - ret = -EINVAL; + return -EBADF; if (unlikely(!file->f_op->read_iter)) - goto out_fput; + return -EINVAL; ret = io_import_iovec(req->ctx, READ, s, &iovec, &iter); if (ret) - goto out_fput; + return ret; iov_count = iov_iter_count(&iter); ret = rw_verify_area(READ, file, &kiocb->ki_pos, iov_count); @@ -991,38 +1083,32 @@ static ssize_t io_read(struct io_kiocb *req, const struct sqe_submit *s, } } kfree(iovec); -out_fput: - /* Hold on to the file for -EAGAIN */ - if (unlikely(ret && ret != -EAGAIN)) - io_fput(req); return ret; } -static ssize_t io_write(struct io_kiocb *req, const struct sqe_submit *s, - bool force_nonblock, struct io_submit_state *state) +static int io_write(struct io_kiocb *req, const struct sqe_submit *s, + bool force_nonblock) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct kiocb *kiocb = &req->rw; struct iov_iter iter; struct file *file; size_t iov_count; - ssize_t ret; + int ret; - ret = io_prep_rw(req, s, force_nonblock, state); + ret = io_prep_rw(req, s, force_nonblock); if (ret) return ret; - ret = -EBADF; file = kiocb->ki_filp; if (unlikely(!(file->f_mode & FMODE_WRITE))) - goto out_fput; - ret = -EINVAL; + return -EBADF; if (unlikely(!file->f_op->write_iter)) - goto out_fput; + return -EINVAL; ret = io_import_iovec(req->ctx, WRITE, s, &iovec, &iter); if (ret) - goto out_fput; + return ret; iov_count = iov_iter_count(&iter); @@ -1036,6 +1122,8 @@ static ssize_t io_write(struct io_kiocb *req, const struct sqe_submit *s, ret = rw_verify_area(WRITE, file, &kiocb->ki_pos, iov_count); if (!ret) { + ssize_t ret2; + /* * Open-code file_start_write here to grab freeze protection, * which will be released by another thread in @@ -1050,14 +1138,22 @@ static ssize_t io_write(struct io_kiocb *req, const struct sqe_submit *s, SB_FREEZE_WRITE); } kiocb->ki_flags |= IOCB_WRITE; - io_rw_done(kiocb, call_write_iter(file, kiocb, &iter)); + + ret2 = call_write_iter(file, kiocb, &iter); + if (!force_nonblock || ret2 != -EAGAIN) { + io_rw_done(kiocb, ret2); + } else { + /* + * If ->needs_lock is true, we're already in async + * context. + */ + if (!s->needs_lock) + io_async_list_note(WRITE, req, iov_count); + ret = -EAGAIN; + } } out_free: kfree(iovec); -out_fput: - /* Hold on to the file for -EAGAIN */ - if (unlikely(ret && ret != -EAGAIN)) - io_fput(req); return ret; } @@ -1072,29 +1168,19 @@ static int io_nop(struct io_kiocb *req, u64 user_data) if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - /* - * Twilight zone - it's possible that someone issued an opcode that - * has a file attached, then got -EAGAIN on submission, and changed - * the sqe before we retried it from async context. Avoid dropping - * a file reference for this malicious case, and flag the error. - */ - if (req->rw.ki_filp) { - err = -EBADF; - io_fput(req); - } io_cqring_add_event(ctx, user_data, err, 0); - io_free_req(req); + io_put_req(req); return 0; } static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_ring_ctx *ctx = req->ctx; - unsigned flags; - int fd; - /* Prep already done */ - if (req->rw.ki_filp) + if (!req->file) + return -EBADF; + /* Prep already done (EAGAIN retry) */ + if (req->flags & REQ_F_PREPPED) return 0; if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) @@ -1102,20 +1188,7 @@ static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index)) return -EINVAL; - fd = READ_ONCE(sqe->fd); - flags = READ_ONCE(sqe->flags); - - if (flags & IOSQE_FIXED_FILE) { - if (unlikely(!ctx->user_files || fd >= ctx->nr_user_files)) - return -EBADF; - req->rw.ki_filp = ctx->user_files[fd]; - req->flags |= REQ_F_FIXED_FILE; - } else { - req->rw.ki_filp = fget(fd); - if (unlikely(!req->rw.ki_filp)) - return -EBADF; - } - + req->flags |= REQ_F_PREPPED; return 0; } @@ -1144,9 +1217,8 @@ static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe, end > 0 ? end : LLONG_MAX, fsync_flags & IORING_FSYNC_DATASYNC); - io_fput(req); io_cqring_add_event(req->ctx, sqe->user_data, ret, 0); - io_free_req(req); + io_put_req(req); return 0; } @@ -1204,15 +1276,16 @@ static int io_poll_remove(struct io_kiocb *req, const struct io_uring_sqe *sqe) spin_unlock_irq(&ctx->completion_lock); io_cqring_add_event(req->ctx, sqe->user_data, ret, 0); - io_free_req(req); + io_put_req(req); return 0; } -static void io_poll_complete(struct io_kiocb *req, __poll_t mask) +static void io_poll_complete(struct io_ring_ctx *ctx, struct io_kiocb *req, + __poll_t mask) { - io_cqring_add_event(req->ctx, req->user_data, mangle_poll(mask), 0); - io_fput(req); - io_free_req(req); + req->poll.done = true; + io_cqring_fill_event(ctx, req->user_data, mangle_poll(mask), 0); + io_commit_cqring(ctx); } static void io_poll_complete_work(struct work_struct *work) @@ -1240,9 +1313,11 @@ static void io_poll_complete_work(struct work_struct *work) return; } list_del_init(&req->list); + io_poll_complete(ctx, req, mask); spin_unlock_irq(&ctx->completion_lock); - io_poll_complete(req, mask); + io_cqring_ev_posted(ctx); + io_put_req(req); } static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, @@ -1253,29 +1328,25 @@ static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, struct io_kiocb *req = container_of(poll, struct io_kiocb, poll); struct io_ring_ctx *ctx = req->ctx; __poll_t mask = key_to_poll(key); - - poll->woken = true; + unsigned long flags; /* for instances that support it check for an event match first: */ - if (mask) { - unsigned long flags; + if (mask && !(mask & poll->events)) + return 0; - if (!(mask & poll->events)) - return 0; + list_del_init(&poll->wait.entry); - /* try to complete the iocb inline if we can: */ - if (spin_trylock_irqsave(&ctx->completion_lock, flags)) { - list_del(&req->list); - spin_unlock_irqrestore(&ctx->completion_lock, flags); + if (mask && spin_trylock_irqsave(&ctx->completion_lock, flags)) { + list_del(&req->list); + io_poll_complete(ctx, req, mask); + spin_unlock_irqrestore(&ctx->completion_lock, flags); - list_del_init(&poll->wait.entry); - io_poll_complete(req, mask); - return 1; - } + io_cqring_ev_posted(ctx); + io_put_req(req); + } else { + queue_work(ctx->sqo_wq, &req->work); } - list_del_init(&poll->wait.entry); - queue_work(ctx->sqo_wq, &req->work); return 1; } @@ -1305,36 +1376,23 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe) struct io_poll_iocb *poll = &req->poll; struct io_ring_ctx *ctx = req->ctx; struct io_poll_table ipt; - unsigned flags; + bool cancel = false; __poll_t mask; u16 events; - int fd; if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (sqe->addr || sqe->ioprio || sqe->off || sqe->len || sqe->buf_index) return -EINVAL; + if (!poll->file) + return -EBADF; INIT_WORK(&req->work, io_poll_complete_work); events = READ_ONCE(sqe->poll_events); poll->events = demangle_poll(events) | EPOLLERR | EPOLLHUP; - flags = READ_ONCE(sqe->flags); - fd = READ_ONCE(sqe->fd); - - if (flags & IOSQE_FIXED_FILE) { - if (unlikely(!ctx->user_files || fd >= ctx->nr_user_files)) - return -EBADF; - poll->file = ctx->user_files[fd]; - req->flags |= REQ_F_FIXED_FILE; - } else { - poll->file = fget(fd); - } - if (unlikely(!poll->file)) - return -EBADF; - poll->head = NULL; - poll->woken = false; + poll->done = false; poll->canceled = false; ipt.pt._qproc = io_poll_queue_proc; @@ -1346,56 +1404,43 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe) INIT_LIST_HEAD(&poll->wait.entry); init_waitqueue_func_entry(&poll->wait, io_poll_wake); - /* one for removal from waitqueue, one for this function */ - refcount_set(&req->refs, 2); - mask = vfs_poll(poll->file, &ipt.pt) & poll->events; - if (unlikely(!poll->head)) { - /* we did not manage to set up a waitqueue, done */ - goto out; - } spin_lock_irq(&ctx->completion_lock); - spin_lock(&poll->head->lock); - if (poll->woken) { - /* wake_up context handles the rest */ - mask = 0; + if (likely(poll->head)) { + spin_lock(&poll->head->lock); + if (unlikely(list_empty(&poll->wait.entry))) { + if (ipt.error) + cancel = true; + ipt.error = 0; + mask = 0; + } + if (mask || ipt.error) + list_del_init(&poll->wait.entry); + else if (cancel) + WRITE_ONCE(poll->canceled, true); + else if (!poll->done) /* actually waiting for an event */ + list_add_tail(&req->list, &ctx->cancel_list); + spin_unlock(&poll->head->lock); + } + if (mask) { /* no async, we'd stolen it */ + req->error = mangle_poll(mask); ipt.error = 0; - } else if (mask || ipt.error) { - /* if we get an error or a mask we are done */ - WARN_ON_ONCE(list_empty(&poll->wait.entry)); - list_del_init(&poll->wait.entry); - } else { - /* actually waiting for an event */ - list_add_tail(&req->list, &ctx->cancel_list); + io_poll_complete(ctx, req, mask); } - spin_unlock(&poll->head->lock); spin_unlock_irq(&ctx->completion_lock); -out: - if (unlikely(ipt.error)) { - if (!(flags & IOSQE_FIXED_FILE)) - fput(poll->file); - /* - * Drop one of our refs to this req, __io_submit_sqe() will - * drop the other one since we're returning an error. - */ - io_free_req(req); - return ipt.error; + if (mask) { + io_cqring_ev_posted(ctx); + io_put_req(req); } - - if (mask) - io_poll_complete(req, mask); - io_free_req(req); - return 0; + return ipt.error; } static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, - const struct sqe_submit *s, bool force_nonblock, - struct io_submit_state *state) + const struct sqe_submit *s, bool force_nonblock) { - ssize_t ret; - int opcode; + int ret, opcode; if (unlikely(s->index >= ctx->sq_entries)) return -EINVAL; @@ -1409,18 +1454,18 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, case IORING_OP_READV: if (unlikely(s->sqe->buf_index)) return -EINVAL; - ret = io_read(req, s, force_nonblock, state); + ret = io_read(req, s, force_nonblock); break; case IORING_OP_WRITEV: if (unlikely(s->sqe->buf_index)) return -EINVAL; - ret = io_write(req, s, force_nonblock, state); + ret = io_write(req, s, force_nonblock); break; case IORING_OP_READ_FIXED: - ret = io_read(req, s, force_nonblock, state); + ret = io_read(req, s, force_nonblock); break; case IORING_OP_WRITE_FIXED: - ret = io_write(req, s, force_nonblock, state); + ret = io_write(req, s, force_nonblock); break; case IORING_OP_FSYNC: ret = io_fsync(req, s->sqe, force_nonblock); @@ -1493,8 +1538,7 @@ restart: struct sqe_submit *s = &req->submit; const struct io_uring_sqe *sqe = s->sqe; - /* Ensure we clear previously set forced non-block flag */ - req->flags &= ~REQ_F_FORCE_NONBLOCK; + /* Ensure we clear previously set non-block flag */ req->rw.ki_flags &= ~IOCB_NOWAIT; ret = 0; @@ -1513,7 +1557,7 @@ restart: s->has_user = cur_mm != NULL; s->needs_lock = true; do { - ret = __io_submit_sqe(ctx, req, s, false, NULL); + ret = __io_submit_sqe(ctx, req, s, false); /* * We can get EAGAIN for polled IO even though * we're forcing a sync submission from here, @@ -1525,9 +1569,13 @@ restart: cond_resched(); } while (1); } + + /* drop submission reference */ + io_put_req(req); + if (ret) { io_cqring_add_event(ctx, sqe->user_data, ret, 0); - io_free_req(req); + io_put_req(req); } /* async context always use a copy of the sqe */ @@ -1614,11 +1662,55 @@ static bool io_add_to_prev_work(struct async_list *list, struct io_kiocb *req) return ret; } +static bool io_op_needs_file(const struct io_uring_sqe *sqe) +{ + int op = READ_ONCE(sqe->opcode); + + switch (op) { + case IORING_OP_NOP: + case IORING_OP_POLL_REMOVE: + return false; + default: + return true; + } +} + +static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s, + struct io_submit_state *state, struct io_kiocb *req) +{ + unsigned flags; + int fd; + + flags = READ_ONCE(s->sqe->flags); + fd = READ_ONCE(s->sqe->fd); + + if (!io_op_needs_file(s->sqe)) { + req->file = NULL; + return 0; + } + + if (flags & IOSQE_FIXED_FILE) { + if (unlikely(!ctx->user_files || + (unsigned) fd >= ctx->nr_user_files)) + return -EBADF; + req->file = ctx->user_files[fd]; + req->flags |= REQ_F_FIXED_FILE; + } else { + if (s->needs_fixed_file) + return -EBADF; + req->file = io_file_get(state, fd); + if (unlikely(!req->file)) + return -EBADF; + } + + return 0; +} + static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s, struct io_submit_state *state) { struct io_kiocb *req; - ssize_t ret; + int ret; /* enforce forwards compatibility on users */ if (unlikely(s->sqe->flags & ~IOSQE_FIXED_FILE)) @@ -1628,10 +1720,12 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s, if (unlikely(!req)) return -EAGAIN; - req->rw.ki_filp = NULL; + ret = io_req_set_file(ctx, s, state, req); + if (unlikely(ret)) + goto out; - ret = __io_submit_sqe(ctx, req, s, true, state); - if (ret == -EAGAIN) { + ret = __io_submit_sqe(ctx, req, s, true); + if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) { struct io_uring_sqe *sqe_copy; sqe_copy = kmalloc(sizeof(*sqe_copy), GFP_KERNEL); @@ -1649,11 +1743,23 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s, INIT_WORK(&req->work, io_sq_wq_submit_work); queue_work(ctx->sqo_wq, &req->work); } - ret = 0; + + /* + * Queued up for async execution, worker will release + * submit reference when the iocb is actually + * submitted. + */ + return 0; } } + +out: + /* drop submission reference */ + io_put_req(req); + + /* and drop final reference, if we failed */ if (ret) - io_free_req(req); + io_put_req(req); return ret; } @@ -1664,7 +1770,7 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s, static void io_submit_state_end(struct io_submit_state *state) { blk_finish_plug(&state->plug); - io_file_put(state, NULL); + io_file_put(state); if (state->free_reqs) kmem_cache_free_bulk(req_cachep, state->free_reqs, &state->reqs[state->cur_req]); @@ -1693,24 +1799,10 @@ static void io_commit_sqring(struct io_ring_ctx *ctx) * write new data to them. */ smp_store_release(&ring->r.head, ctx->cached_sq_head); - - /* - * write side barrier of head update, app has read side. See - * comment at the top of this file - */ - smp_wmb(); } } /* - * Undo last io_get_sqring() - */ -static void io_drop_sqring(struct io_ring_ctx *ctx) -{ - ctx->cached_sq_head--; -} - -/* * Fetch an sqe, if one is available. Note that s->sqe will point to memory * that is mapped by userspace. This means that care needs to be taken to * ensure that reads are stable, as we cannot rely on userspace always @@ -1732,9 +1824,8 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s) * though the application is the one updating it. */ head = ctx->cached_sq_head; - /* See comment at the top of this file */ - smp_rmb(); - if (head == READ_ONCE(ring->r.tail)) + /* make sure SQ entry isn't read before tail */ + if (head == smp_load_acquire(&ring->r.tail)) return false; head = READ_ONCE(ring->array[head & ctx->sq_mask]); @@ -1748,8 +1839,6 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s) /* drop invalid entries */ ctx->cached_sq_head++; ring->dropped++; - /* See comment at the top of this file */ - smp_wmb(); return false; } @@ -1859,7 +1948,8 @@ static int io_sq_thread(void *data) /* Tell userspace we may need a wakeup call */ ctx->sq_ring->flags |= IORING_SQ_NEED_WAKEUP; - smp_wmb(); + /* make sure to read SQ tail after writing flags */ + smp_mb(); if (!io_get_sqring(ctx, &sqes[0])) { if (kthread_should_stop()) { @@ -1872,13 +1962,11 @@ static int io_sq_thread(void *data) finish_wait(&ctx->sqo_wait, &wait); ctx->sq_ring->flags &= ~IORING_SQ_NEED_WAKEUP; - smp_wmb(); continue; } finish_wait(&ctx->sqo_wait, &wait); ctx->sq_ring->flags &= ~IORING_SQ_NEED_WAKEUP; - smp_wmb(); } i = 0; @@ -1913,13 +2001,17 @@ static int io_sq_thread(void *data) unuse_mm(cur_mm); mmput(cur_mm); } + + if (kthread_should_park()) + kthread_parkme(); + return 0; } static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit) { struct io_submit_state state, *statep = NULL; - int i, ret = 0, submit = 0; + int i, submit = 0; if (to_submit > IO_PLUG_THRESHOLD) { io_submit_state_start(&state, ctx, to_submit); @@ -1928,6 +2020,7 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit) for (i = 0; i < to_submit; i++) { struct sqe_submit s; + int ret; if (!io_get_sqring(ctx, &s)) break; @@ -1935,21 +2028,18 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit) s.has_user = true; s.needs_lock = false; s.needs_fixed_file = false; + submit++; ret = io_submit_sqe(ctx, &s, statep); - if (ret) { - io_drop_sqring(ctx); - break; - } - - submit++; + if (ret) + io_cqring_add_event(ctx, s.sqe->user_data, ret, 0); } io_commit_sqring(ctx); if (statep) io_submit_state_end(statep); - return submit ? submit : ret; + return submit; } static unsigned io_cqring_events(struct io_cq_ring *ring) @@ -1975,7 +2065,15 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, return 0; if (sig) { - ret = set_user_sigmask(sig, &ksigmask, &sigsaved, sigsz); +#ifdef CONFIG_COMPAT + if (in_compat_syscall()) + ret = set_compat_user_sigmask((const compat_sigset_t __user *)sig, + &ksigmask, &sigsaved, sigsz); + else +#endif + ret = set_user_sigmask(sig, &ksigmask, + &sigsaved, sigsz); + if (ret) return ret; } @@ -2039,6 +2137,7 @@ static void io_sq_thread_stop(struct io_ring_ctx *ctx) if (ctx->sqo_thread) { ctx->sqo_stop = 1; mb(); + kthread_park(ctx->sqo_thread); kthread_stop(ctx->sqo_thread); ctx->sqo_thread = NULL; } @@ -2200,6 +2299,7 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, fput(ctx->user_files[i]); kfree(ctx->user_files); + ctx->user_files = NULL; ctx->nr_user_files = 0; return ret; } @@ -2220,19 +2320,23 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx, mmgrab(current->mm); ctx->sqo_mm = current->mm; - ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle); - if (!ctx->sq_thread_idle) - ctx->sq_thread_idle = HZ; + if (ctx->flags & IORING_SETUP_SQPOLL) { + ret = -EPERM; + if (!capable(CAP_SYS_ADMIN)) + goto err; - ret = -EINVAL; - if (!cpu_possible(p->sq_thread_cpu)) - goto err; + ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle); + if (!ctx->sq_thread_idle) + ctx->sq_thread_idle = HZ; - if (ctx->flags & IORING_SETUP_SQPOLL) { if (p->flags & IORING_SETUP_SQ_AFF) { - int cpu; + int cpu = array_index_nospec(p->sq_thread_cpu, + nr_cpu_ids); + + ret = -EINVAL; + if (!cpu_possible(cpu)) + goto err; - cpu = array_index_nospec(p->sq_thread_cpu, NR_CPUS); ctx->sqo_thread = kthread_create_on_cpu(io_sq_thread, ctx, cpu, "io_uring-sq"); @@ -2293,8 +2397,12 @@ static int io_account_mem(struct user_struct *user, unsigned long nr_pages) static void io_mem_free(void *ptr) { - struct page *page = virt_to_head_page(ptr); + struct page *page; + + if (!ptr) + return; + page = virt_to_head_page(ptr); if (put_page_testzero(page)) free_compound_page(page); } @@ -2335,7 +2443,7 @@ static int io_sqe_buffer_unregister(struct io_ring_ctx *ctx) if (ctx->account_mem) io_unaccount_mem(ctx->user, imu->nr_bvecs); - kfree(imu->bvec); + kvfree(imu->bvec); imu->nr_bvecs = 0; } @@ -2427,9 +2535,9 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, if (!pages || nr_pages > got_pages) { kfree(vmas); kfree(pages); - pages = kmalloc_array(nr_pages, sizeof(struct page *), + pages = kvmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL); - vmas = kmalloc_array(nr_pages, + vmas = kvmalloc_array(nr_pages, sizeof(struct vm_area_struct *), GFP_KERNEL); if (!pages || !vmas) { @@ -2441,7 +2549,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, got_pages = nr_pages; } - imu->bvec = kmalloc_array(nr_pages, sizeof(struct bio_vec), + imu->bvec = kvmalloc_array(nr_pages, sizeof(struct bio_vec), GFP_KERNEL); ret = -ENOMEM; if (!imu->bvec) { @@ -2480,6 +2588,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, } if (ctx->account_mem) io_unaccount_mem(ctx->user, nr_pages); + kvfree(imu->bvec); goto err; } @@ -2502,12 +2611,12 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, ctx->nr_user_bufs++; } - kfree(pages); - kfree(vmas); + kvfree(pages); + kvfree(vmas); return 0; err: - kfree(pages); - kfree(vmas); + kvfree(pages); + kvfree(vmas); io_sqe_buffer_unregister(ctx); return ret; } @@ -2545,9 +2654,13 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait) __poll_t mask = 0; poll_wait(file, &ctx->cq_wait, wait); - /* See comment at the top of this file */ + /* + * synchronizes with barrier from wq_has_sleeper call in + * io_commit_cqring + */ smp_rmb(); - if (READ_ONCE(ctx->sq_ring->r.tail) + 1 != ctx->cached_sq_head) + if (READ_ONCE(ctx->sq_ring->r.tail) - ctx->cached_sq_head != + ctx->sq_ring->ring_entries) mask |= EPOLLOUT | EPOLLWRNORM; if (READ_ONCE(ctx->cq_ring->r.head) != ctx->cached_cq_tail) mask |= EPOLLIN | EPOLLRDNORM; @@ -2658,24 +2771,12 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit, mutex_lock(&ctx->uring_lock); submitted = io_ring_submit(ctx, to_submit); mutex_unlock(&ctx->uring_lock); - - if (submitted < 0) - goto out_ctx; } if (flags & IORING_ENTER_GETEVENTS) { unsigned nr_events = 0; min_complete = min(min_complete, ctx->cq_entries); - /* - * The application could have included the 'to_submit' count - * in how many events it wanted to wait for. If we failed to - * submit the desired count, we may need to adjust the number - * of events to poll/wait for. - */ - if (submitted < to_submit) - min_complete = min_t(unsigned, submitted, min_complete); - if (ctx->flags & IORING_SETUP_IOPOLL) { mutex_lock(&ctx->uring_lock); ret = io_iopoll_check(ctx, &nr_events, min_complete); @@ -2721,17 +2822,12 @@ static int io_allocate_scq_urings(struct io_ring_ctx *ctx, return -EOVERFLOW; ctx->sq_sqes = io_mem_alloc(size); - if (!ctx->sq_sqes) { - io_mem_free(ctx->sq_ring); + if (!ctx->sq_sqes) return -ENOMEM; - } cq_ring = io_mem_alloc(struct_size(cq_ring, cqes, p->cq_entries)); - if (!cq_ring) { - io_mem_free(ctx->sq_ring); - io_mem_free(ctx->sq_sqes); + if (!cq_ring) return -ENOMEM; - } ctx->cq_ring = cq_ring; cq_ring->ring_mask = p->cq_entries - 1; @@ -2902,11 +2998,31 @@ SYSCALL_DEFINE2(io_uring_setup, u32, entries, static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode, void __user *arg, unsigned nr_args) + __releases(ctx->uring_lock) + __acquires(ctx->uring_lock) { int ret; + /* + * We're inside the ring mutex, if the ref is already dying, then + * someone else killed the ctx or is already going through + * io_uring_register(). + */ + if (percpu_ref_is_dying(&ctx->refs)) + return -ENXIO; + percpu_ref_kill(&ctx->refs); + + /* + * Drop uring mutex before waiting for references to exit. If another + * thread is currently inside io_uring_enter() it might need to grab + * the uring_lock to make progress. If we hold it here across the drain + * wait, then we can deadlock. It's safe to drop the mutex here, since + * no new references will come in after we've killed the percpu ref. + */ + mutex_unlock(&ctx->uring_lock); wait_for_completion(&ctx->ctx_done); + mutex_lock(&ctx->uring_lock); switch (opcode) { case IORING_REGISTER_BUFFERS: diff --git a/fs/iomap.c b/fs/iomap.c index 97cb9d486a7d..abdd18e404f8 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -1589,12 +1589,14 @@ static void iomap_dio_bio_end_io(struct bio *bio) if (should_dirty) { bio_check_pages_dirty(bio); } else { - struct bio_vec *bvec; - int i; - struct bvec_iter_all iter_all; + if (!bio_flagged(bio, BIO_NO_PAGE_REF)) { + struct bvec_iter_all iter_all; + struct bio_vec *bvec; + int i; - bio_for_each_segment_all(bvec, bio, i, iter_all) - put_page(bvec->bv_page); + bio_for_each_segment_all(bvec, bio, i, iter_all) + put_page(bvec->bv_page); + } bio_put(bio); } } diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c index 389ea53ea487..bccfc40b3a74 100644 --- a/fs/jffs2/readinode.c +++ b/fs/jffs2/readinode.c @@ -1414,11 +1414,6 @@ void jffs2_do_clear_inode(struct jffs2_sb_info *c, struct jffs2_inode_info *f) jffs2_kill_fragtree(&f->fragtree, deleted?c:NULL); - if (f->target) { - kfree(f->target); - f->target = NULL; - } - fds = f->dents; while(fds) { fd = fds; diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index bb6ae387469f..05d892c79339 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -47,7 +47,10 @@ static struct inode *jffs2_alloc_inode(struct super_block *sb) static void jffs2_i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); - kmem_cache_free(jffs2_inode_cachep, JFFS2_INODE_INFO(inode)); + struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); + + kfree(f->target); + kmem_cache_free(jffs2_inode_cachep, f); } static void jffs2_destroy_inode(struct inode *inode) diff --git a/fs/lockd/host.c b/fs/lockd/host.c index 93fb7cf0b92b..f0b5c987d6ae 100644 --- a/fs/lockd/host.c +++ b/fs/lockd/host.c @@ -290,12 +290,11 @@ void nlmclnt_release_host(struct nlm_host *host) WARN_ON_ONCE(host->h_server); - if (refcount_dec_and_test(&host->h_count)) { + if (refcount_dec_and_mutex_lock(&host->h_count, &nlm_host_mutex)) { WARN_ON_ONCE(!list_empty(&host->h_lockowners)); WARN_ON_ONCE(!list_empty(&host->h_granted)); WARN_ON_ONCE(!list_empty(&host->h_reclaim)); - mutex_lock(&nlm_host_mutex); nlm_destroy_host_locked(host); mutex_unlock(&nlm_host_mutex); } diff --git a/fs/locks.c b/fs/locks.c index eaa1cfaf73b0..71d0c6c2aac5 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1160,6 +1160,11 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, */ error = -EDEADLK; spin_lock(&blocked_lock_lock); + /* + * Ensure that we don't find any locks blocked on this + * request during deadlock detection. + */ + __locks_wake_up_blocks(request); if (likely(!posix_locks_deadlock(request, fl))) { error = FILE_LOCK_DEFERRED; __locks_insert_block(fl, request, diff --git a/fs/nfs/client.c b/fs/nfs/client.c index fb1cf1a4bda2..90d71fda65ce 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -453,7 +453,7 @@ void nfs_init_timeout_values(struct rpc_timeout *to, int proto, case XPRT_TRANSPORT_RDMA: if (retrans == NFS_UNSPEC_RETRANS) to->to_retries = NFS_DEF_TCP_RETRANS; - if (timeo == NFS_UNSPEC_TIMEO || to->to_retries == 0) + if (timeo == NFS_UNSPEC_TIMEO || to->to_initval == 0) to->to_initval = NFS_DEF_TCP_TIMEO * HZ / 10; if (to->to_initval > NFS_MAX_TCP_TIMEOUT) to->to_initval = NFS_MAX_TCP_TIMEOUT; diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index f9264e1922a2..6673d4ff5a2a 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1289,6 +1289,7 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, static int ff_layout_read_done_cb(struct rpc_task *task, struct nfs_pgio_header *hdr) { + int new_idx = hdr->pgio_mirror_idx; int err; trace_nfs4_pnfs_read(hdr, task->tk_status); @@ -1307,7 +1308,7 @@ static int ff_layout_read_done_cb(struct rpc_task *task, case -NFS4ERR_RESET_TO_PNFS: if (ff_layout_choose_best_ds_for_read(hdr->lseg, hdr->pgio_mirror_idx + 1, - &hdr->pgio_mirror_idx)) + &new_idx)) goto out_layouterror; set_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags); return task->tk_status; @@ -1320,7 +1321,9 @@ static int ff_layout_read_done_cb(struct rpc_task *task, return 0; out_layouterror: + ff_layout_read_record_layoutstats_done(task, hdr); ff_layout_send_layouterror(hdr->lseg); + hdr->pgio_mirror_idx = new_idx; out_eagain: rpc_restart_call_prepare(task); return -EAGAIN; diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index ff6f85fb676b..5196bfa7894d 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -329,9 +329,6 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src, }; ssize_t err, err2; - if (!nfs_server_capable(file_inode(dst), NFS_CAP_COPY)) - return -EOPNOTSUPP; - src_lock = nfs_get_lock_context(nfs_file_open_context(src)); if (IS_ERR(src_lock)) return PTR_ERR(src_lock); diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 45b2322e092d..00d17198ee12 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -133,8 +133,10 @@ static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t count, unsigned int flags) { + if (!nfs_server_capable(file_inode(file_out), NFS_CAP_COPY)) + return -EOPNOTSUPP; if (file_inode(file_in) == file_inode(file_out)) - return -EINVAL; + return -EOPNOTSUPP; return nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count); } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 4dbb0ee23432..741ff8c9c6ed 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2933,7 +2933,8 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, } out: - nfs4_sequence_free_slot(&opendata->o_res.seq_res); + if (!opendata->cancelled) + nfs4_sequence_free_slot(&opendata->o_res.seq_res); return ret; } @@ -6301,7 +6302,6 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl, p->arg.seqid = seqid; p->res.seqid = seqid; p->lsp = lsp; - refcount_inc(&lsp->ls_count); /* Ensure we don't close file until we're done freeing locks! */ p->ctx = get_nfs_open_context(ctx); p->l_ctx = nfs_get_lock_context(ctx); @@ -6526,7 +6526,6 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl, p->res.lock_seqid = p->arg.lock_seqid; p->lsp = lsp; p->server = server; - refcount_inc(&lsp->ls_count); p->ctx = get_nfs_open_context(ctx); locks_init_lock(&p->fl); locks_copy_lock(&p->fl, fl); diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index cfcabc33e24d..602446158bfb 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -2589,7 +2589,7 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr, ARRAY_SIZE(nfs4_acl_bitmap), &hdr); rpc_prepare_reply_pages(req, args->acl_pages, 0, - args->acl_len, replen); + args->acl_len, replen + 1); encode_nops(&hdr); } @@ -2811,7 +2811,7 @@ static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req, } rpc_prepare_reply_pages(req, (struct page **)&args->page, 0, - PAGE_SIZE, replen); + PAGE_SIZE, replen + 1); encode_nops(&hdr); } diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 23790c7b2289..c27ac96a95bd 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2041,7 +2041,8 @@ static int nfs23_validate_mount_data(void *options, memcpy(sap, &data->addr, sizeof(data->addr)); args->nfs_server.addrlen = sizeof(data->addr); args->nfs_server.port = ntohs(data->addr.sin_port); - if (!nfs_verify_server_address(sap)) + if (sap->sa_family != AF_INET || + !nfs_verify_server_address(sap)) goto out_no_address; if (!(data->flags & NFS_MOUNT_TCP)) diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 8f933e84cec1..9bc32af4e2da 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -442,7 +442,9 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp) struct nfsd3_readdirargs *argp = rqstp->rq_argp; struct nfsd3_readdirres *resp = rqstp->rq_resp; __be32 nfserr; - int count; + int count = 0; + struct page **p; + caddr_t page_addr = NULL; dprintk("nfsd: READDIR(3) %s %d bytes at %d\n", SVCFH_fmt(&argp->fh), @@ -462,7 +464,18 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp) nfserr = nfsd_readdir(rqstp, &resp->fh, (loff_t*) &argp->cookie, &resp->common, nfs3svc_encode_entry); memcpy(resp->verf, argp->verf, 8); - resp->count = resp->buffer - argp->buffer; + count = 0; + for (p = rqstp->rq_respages + 1; p < rqstp->rq_next_page; p++) { + page_addr = page_address(*p); + + if (((caddr_t)resp->buffer >= page_addr) && + ((caddr_t)resp->buffer < page_addr + PAGE_SIZE)) { + count += (caddr_t)resp->buffer - page_addr; + break; + } + count += PAGE_SIZE; + } + resp->count = count >> 2; if (resp->offset) { loff_t offset = argp->cookie; diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 93fea246f676..8d789124ed3c 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -573,6 +573,7 @@ int nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) { struct nfsd3_readdirargs *args = rqstp->rq_argp; + int len; u32 max_blocksize = svc_max_payload(rqstp); p = decode_fh(p, &args->fh); @@ -582,8 +583,14 @@ nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) args->verf = p; p += 2; args->dircount = ~0; args->count = ntohl(*p++); - args->count = min_t(u32, args->count, max_blocksize); - args->buffer = page_address(*(rqstp->rq_next_page++)); + len = args->count = min_t(u32, args->count, max_blocksize); + + while (len > 0) { + struct page *p = *(rqstp->rq_next_page++); + if (!args->buffer) + args->buffer = page_address(p); + len -= PAGE_SIZE; + } return xdr_argsize_check(rqstp, p); } diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index d219159b98af..7caa3801ce72 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -1010,8 +1010,9 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata) cb->cb_seq_status = 1; cb->cb_status = 0; if (minorversion) { - if (!nfsd41_cb_get_slot(clp, task)) + if (!cb->cb_holds_slot && !nfsd41_cb_get_slot(clp, task)) return; + cb->cb_holds_slot = true; } rpc_call_start(task); } @@ -1038,6 +1039,9 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback return true; } + if (!cb->cb_holds_slot) + goto need_restart; + switch (cb->cb_seq_status) { case 0: /* @@ -1076,6 +1080,7 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback cb->cb_seq_status); } + cb->cb_holds_slot = false; clear_bit(0, &clp->cl_cb_slot_busy); rpc_wake_up_next(&clp->cl_cb_waitq); dprintk("%s: freed slot, new seqid=%d\n", __func__, @@ -1283,6 +1288,7 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp, cb->cb_seq_status = 1; cb->cb_status = 0; cb->cb_need_restart = false; + cb->cb_holds_slot = false; } void nfsd4_run_cb(struct nfsd4_callback *cb) diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 6a45fb00c5fc..f056b1d3fecd 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -265,6 +265,7 @@ find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh, static void free_blocked_lock(struct nfsd4_blocked_lock *nbl) { + locks_delete_block(&nbl->nbl_lock); locks_release_private(&nbl->nbl_lock); kfree(nbl); } @@ -293,11 +294,18 @@ remove_blocked_locks(struct nfs4_lockowner *lo) nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock, nbl_lru); list_del_init(&nbl->nbl_lru); - locks_delete_block(&nbl->nbl_lock); free_blocked_lock(nbl); } } +static void +nfsd4_cb_notify_lock_prepare(struct nfsd4_callback *cb) +{ + struct nfsd4_blocked_lock *nbl = container_of(cb, + struct nfsd4_blocked_lock, nbl_cb); + locks_delete_block(&nbl->nbl_lock); +} + static int nfsd4_cb_notify_lock_done(struct nfsd4_callback *cb, struct rpc_task *task) { @@ -325,6 +333,7 @@ nfsd4_cb_notify_lock_release(struct nfsd4_callback *cb) } static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = { + .prepare = nfsd4_cb_notify_lock_prepare, .done = nfsd4_cb_notify_lock_done, .release = nfsd4_cb_notify_lock_release, }; @@ -4863,7 +4872,6 @@ nfs4_laundromat(struct nfsd_net *nn) nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock, nbl_lru); list_del_init(&nbl->nbl_lru); - locks_delete_block(&nbl->nbl_lock); free_blocked_lock(nbl); } out: diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 396c76755b03..9d6cb246c6c5 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -70,6 +70,7 @@ struct nfsd4_callback { int cb_seq_status; int cb_status; bool cb_need_restart; + bool cb_holds_slot; }; struct nfsd4_callback_ops { diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 6b9c27548997..63c6bb1f8c4d 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -346,10 +346,16 @@ static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info) __kernel_fsid_t fsid = {}; fsnotify_foreach_obj_type(type) { + struct fsnotify_mark_connector *conn; + if (!fsnotify_iter_should_report_type(iter_info, type)) continue; - fsid = iter_info->marks[type]->connector->fsid; + conn = READ_ONCE(iter_info->marks[type]->connector); + /* Mark is just getting destroyed or created? */ + if (!conn) + continue; + fsid = conn->fsid; if (WARN_ON_ONCE(!fsid.val[0] && !fsid.val[1])) continue; return fsid; @@ -408,8 +414,12 @@ static int fanotify_handle_event(struct fsnotify_group *group, return 0; } - if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) + if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) { fsid = fanotify_get_fsid(iter_info); + /* Racing with mark destruction or creation? */ + if (!fsid.val[0] && !fsid.val[1]) + return 0; + } event = fanotify_alloc_event(group, inode, mask, data, data_type, &fsid); diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 56992b32c6bb..a90bb19dcfa2 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -208,6 +208,7 @@ static int copy_fid_to_user(struct fanotify_event *event, char __user *buf) { struct fanotify_event_info_fid info = { }; struct file_handle handle = { }; + unsigned char bounce[FANOTIFY_INLINE_FH_LEN], *fh; size_t fh_len = event->fh_len; size_t len = fanotify_event_info_len(event); @@ -233,7 +234,16 @@ static int copy_fid_to_user(struct fanotify_event *event, char __user *buf) buf += sizeof(handle); len -= sizeof(handle); - if (copy_to_user(buf, fanotify_event_fh(event), fh_len)) + /* + * For an inline fh, copy through stack to exclude the copy from + * usercopy hardening protections. + */ + fh = fanotify_event_fh(event); + if (fh_len <= FANOTIFY_INLINE_FH_LEN) { + memcpy(bounce, fh, fh_len); + fh = bounce; + } + if (copy_to_user(buf, fh, fh_len)) return -EFAULT; /* Pad with 0's */ diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index e2901fbb9f76..7b53598c8804 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -519,8 +519,10 @@ static int inotify_update_existing_watch(struct fsnotify_group *group, fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, group); if (!fsn_mark) return -ENOENT; - else if (create) - return -EEXIST; + else if (create) { + ret = -EEXIST; + goto out; + } i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark); @@ -548,6 +550,7 @@ static int inotify_update_existing_watch(struct fsnotify_group *group, /* return the wd */ ret = i_mark->wd; +out: /* match the get from fsnotify_find_mark() */ fsnotify_put_mark(fsn_mark); diff --git a/fs/notify/mark.c b/fs/notify/mark.c index d593d4269561..22acb0a79b53 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -239,13 +239,13 @@ static void fsnotify_drop_object(unsigned int type, void *objp) void fsnotify_put_mark(struct fsnotify_mark *mark) { - struct fsnotify_mark_connector *conn; + struct fsnotify_mark_connector *conn = READ_ONCE(mark->connector); void *objp = NULL; unsigned int type = FSNOTIFY_OBJ_TYPE_DETACHED; bool free_conn = false; /* Catch marks that were actually never attached to object */ - if (!mark->connector) { + if (!conn) { if (refcount_dec_and_test(&mark->refcnt)) fsnotify_final_mark_destroy(mark); return; @@ -255,10 +255,9 @@ void fsnotify_put_mark(struct fsnotify_mark *mark) * We have to be careful so that traversals of obj_list under lock can * safely grab mark reference. */ - if (!refcount_dec_and_lock(&mark->refcnt, &mark->connector->lock)) + if (!refcount_dec_and_lock(&mark->refcnt, &conn->lock)) return; - conn = mark->connector; hlist_del_init_rcu(&mark->obj_list); if (hlist_empty(&conn->list)) { objp = fsnotify_detach_connector_from_object(conn, &type); @@ -266,7 +265,7 @@ void fsnotify_put_mark(struct fsnotify_mark *mark) } else { __fsnotify_recalc_mask(conn); } - mark->connector = NULL; + WRITE_ONCE(mark->connector, NULL); spin_unlock(&conn->lock); fsnotify_drop_object(type, objp); @@ -620,7 +619,7 @@ restart: /* mark should be the last entry. last is the current last entry */ hlist_add_behind_rcu(&mark->obj_list, &last->obj_list); added: - mark->connector = conn; + WRITE_ONCE(mark->connector, conn); out_err: spin_unlock(&conn->lock); spin_unlock(&mark->lock); @@ -808,6 +807,7 @@ void fsnotify_init_mark(struct fsnotify_mark *mark, refcount_set(&mark->refcnt, 1); fsnotify_get_group(group); mark->group = group; + WRITE_ONCE(mark->connector, NULL); } /* diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index a35259eebc56..1dc9a08e8bdc 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -4719,22 +4719,23 @@ out: /* Lock an inode and grab a bh pointing to the inode. */ int ocfs2_reflink_inodes_lock(struct inode *s_inode, - struct buffer_head **bh1, + struct buffer_head **bh_s, struct inode *t_inode, - struct buffer_head **bh2) + struct buffer_head **bh_t) { - struct inode *inode1; - struct inode *inode2; + struct inode *inode1 = s_inode; + struct inode *inode2 = t_inode; struct ocfs2_inode_info *oi1; struct ocfs2_inode_info *oi2; + struct buffer_head *bh1 = NULL; + struct buffer_head *bh2 = NULL; bool same_inode = (s_inode == t_inode); + bool need_swap = (inode1->i_ino > inode2->i_ino); int status; /* First grab the VFS and rw locks. */ lock_two_nondirectories(s_inode, t_inode); - inode1 = s_inode; - inode2 = t_inode; - if (inode1->i_ino > inode2->i_ino) + if (need_swap) swap(inode1, inode2); status = ocfs2_rw_lock(inode1, 1); @@ -4757,17 +4758,13 @@ int ocfs2_reflink_inodes_lock(struct inode *s_inode, trace_ocfs2_double_lock((unsigned long long)oi1->ip_blkno, (unsigned long long)oi2->ip_blkno); - if (*bh1) - *bh1 = NULL; - if (*bh2) - *bh2 = NULL; - /* We always want to lock the one with the lower lockid first. */ if (oi1->ip_blkno > oi2->ip_blkno) mlog_errno(-ENOLCK); /* lock id1 */ - status = ocfs2_inode_lock_nested(inode1, bh1, 1, OI_LS_REFLINK_TARGET); + status = ocfs2_inode_lock_nested(inode1, &bh1, 1, + OI_LS_REFLINK_TARGET); if (status < 0) { if (status != -ENOENT) mlog_errno(status); @@ -4776,15 +4773,25 @@ int ocfs2_reflink_inodes_lock(struct inode *s_inode, /* lock id2 */ if (!same_inode) { - status = ocfs2_inode_lock_nested(inode2, bh2, 1, + status = ocfs2_inode_lock_nested(inode2, &bh2, 1, OI_LS_REFLINK_TARGET); if (status < 0) { if (status != -ENOENT) mlog_errno(status); goto out_cl1; } - } else - *bh2 = *bh1; + } else { + bh2 = bh1; + } + + /* + * If we swapped inode order above, we have to swap the buffer heads + * before passing them back to the caller. + */ + if (need_swap) + swap(bh1, bh2); + *bh_s = bh1; + *bh_t = bh2; trace_ocfs2_double_lock_end( (unsigned long long)oi1->ip_blkno, @@ -4794,8 +4801,7 @@ int ocfs2_reflink_inodes_lock(struct inode *s_inode, out_cl1: ocfs2_inode_unlock(inode1, 1); - brelse(*bh1); - *bh1 = NULL; + brelse(bh1); out_rw2: ocfs2_rw_unlock(inode2, 1); out_i2: diff --git a/fs/open.c b/fs/open.c index 0285ce7dbd51..a00350018a47 100644 --- a/fs/open.c +++ b/fs/open.c @@ -733,6 +733,12 @@ static int do_dentry_open(struct file *f, return 0; } + /* Any file opened for execve()/uselib() has to be a regular file. */ + if (unlikely(f->f_flags & FMODE_EXEC && !S_ISREG(inode->i_mode))) { + error = -EACCES; + goto cleanup_file; + } + if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) { error = get_write_access(inode); if (unlikely(error)) @@ -1209,3 +1215,21 @@ int nonseekable_open(struct inode *inode, struct file *filp) } EXPORT_SYMBOL(nonseekable_open); + +/* + * stream_open is used by subsystems that want stream-like file descriptors. + * Such file descriptors are not seekable and don't have notion of position + * (file.f_pos is always 0). Contrary to file descriptors of other regular + * files, .read() and .write() can run simultaneously. + * + * stream_open never fails and is marked to return int so that it could be + * directly used as file_operations.open . + */ +int stream_open(struct inode *inode, struct file *filp) +{ + filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS); + filp->f_mode |= FMODE_STREAM; + return 0; +} + +EXPORT_SYMBOL(stream_open); diff --git a/fs/pipe.c b/fs/pipe.c index 070aad543382..41065901106b 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -188,9 +188,9 @@ EXPORT_SYMBOL(generic_pipe_buf_steal); * in the tee() system call, when we duplicate the buffers in one * pipe into another. */ -void generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) +bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { - get_page(buf->page); + return try_get_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_get); diff --git a/fs/proc/base.c b/fs/proc/base.c index ddef482f1334..f179568b4c76 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -407,7 +407,6 @@ static void unlock_trace(struct task_struct *task) static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { - struct stack_trace trace; unsigned long *entries; int err; @@ -430,20 +429,17 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, if (!entries) return -ENOMEM; - trace.nr_entries = 0; - trace.max_entries = MAX_STACK_TRACE_DEPTH; - trace.entries = entries; - trace.skip = 0; - err = lock_trace(task); if (!err) { - unsigned int i; + unsigned int i, nr_entries; - save_stack_trace_tsk(task, &trace); + nr_entries = stack_trace_save_tsk(task, entries, + MAX_STACK_TRACE_DEPTH, 0); - for (i = 0; i < trace.nr_entries; i++) { + for (i = 0; i < nr_entries; i++) { seq_printf(m, "[<0>] %pB\n", (void *)entries[i]); } + unlock_trace(task); } kfree(entries); @@ -489,10 +485,9 @@ static int lstats_show_proc(struct seq_file *m, void *v) lr->count, lr->time, lr->max); for (q = 0; q < LT_BACKTRACEDEPTH; q++) { unsigned long bt = lr->backtrace[q]; + if (!bt) break; - if (bt == ULONG_MAX) - break; seq_printf(m, " %ps", (void *)bt); } seq_putc(m, '\n'); @@ -616,24 +611,25 @@ static int proc_pid_limits(struct seq_file *m, struct pid_namespace *ns, static int proc_pid_syscall(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { - long nr; - unsigned long args[6], sp, pc; + struct syscall_info info; + u64 *args = &info.data.args[0]; int res; res = lock_trace(task); if (res) return res; - if (task_current_syscall(task, &nr, args, 6, &sp, &pc)) + if (task_current_syscall(task, &info)) seq_puts(m, "running\n"); - else if (nr < 0) - seq_printf(m, "%ld 0x%lx 0x%lx\n", nr, sp, pc); + else if (info.data.nr < 0) + seq_printf(m, "%d 0x%llx 0x%llx\n", + info.data.nr, info.sp, info.data.instruction_pointer); else seq_printf(m, - "%ld 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx\n", - nr, + "%d 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx\n", + info.data.nr, args[0], args[1], args[2], args[3], args[4], args[5], - sp, pc); + info.sp, info.data.instruction_pointer); unlock_trace(task); return 0; diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index bbcc185062bb..f5834488b67d 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -54,6 +54,28 @@ static LIST_HEAD(kclist_head); static DECLARE_RWSEM(kclist_lock); static int kcore_need_update = 1; +/* + * Returns > 0 for RAM pages, 0 for non-RAM pages, < 0 on error + * Same as oldmem_pfn_is_ram in vmcore + */ +static int (*mem_pfn_is_ram)(unsigned long pfn); + +int __init register_mem_pfn_is_ram(int (*fn)(unsigned long pfn)) +{ + if (mem_pfn_is_ram) + return -EBUSY; + mem_pfn_is_ram = fn; + return 0; +} + +static int pfn_is_ram(unsigned long pfn) +{ + if (mem_pfn_is_ram) + return mem_pfn_is_ram(pfn); + else + return 1; +} + /* This doesn't grab kclist_lock, so it should only be used at init time. */ void __init kclist_add(struct kcore_list *new, void *addr, size_t size, int type) @@ -465,6 +487,11 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) goto out; } m = NULL; /* skip the list anchor */ + } else if (!pfn_is_ram(__pa(start) >> PAGE_SHIFT)) { + if (clear_user(buffer, tsz)) { + ret = -EFAULT; + goto out; + } } else if (m->type == KCORE_VMALLOC) { vread(buf, (char *)start, tsz); /* we have to zero-fill user buffer even if no read */ @@ -588,7 +615,7 @@ static void __init proc_kcore_text_init(void) /* * MODULES_VADDR has no intersection with VMALLOC_ADDR. */ -struct kcore_list kcore_modules; +static struct kcore_list kcore_modules; static void __init add_modules_range(void) { if (MODULES_VADDR != VMALLOC_START && MODULES_END != VMALLOC_END) { diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 4d598a399bbf..7325baa8f9d4 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1626,8 +1626,11 @@ static void drop_sysctl_table(struct ctl_table_header *header) if (--header->nreg) return; - put_links(header); - start_unregistering(header); + if (parent) { + put_links(header); + start_unregistering(header); + } + if (!--header->count) kfree_rcu(header, rcu); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 92a91e7816d8..95ca1fe7283c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1143,6 +1143,24 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, count = -EINTR; goto out_mm; } + /* + * Avoid to modify vma->vm_flags + * without locked ops while the + * coredump reads the vm_flags. + */ + if (!mmget_still_valid(mm)) { + /* + * Silently return "count" + * like if get_task_mm() + * failed. FIXME: should this + * function have returned + * -ESRCH if get_task_mm() + * failed like if + * get_proc_task() fails? + */ + up_write(&mm->mmap_sem); + goto out_mm; + } for (vma = mm->mmap; vma; vma = vma->vm_next) { vma->vm_flags &= ~VM_SOFTDIRTY; vma_set_page_prot(vma); diff --git a/fs/read_write.c b/fs/read_write.c index 177ccc3d405a..61b43ad7608e 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -560,12 +560,13 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_ static inline loff_t file_pos_read(struct file *file) { - return file->f_pos; + return file->f_mode & FMODE_STREAM ? 0 : file->f_pos; } static inline void file_pos_write(struct file *file, loff_t pos) { - file->f_pos = pos; + if ((file->f_mode & FMODE_STREAM) == 0) + file->f_pos = pos; } ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count) diff --git a/fs/splice.c b/fs/splice.c index 3ee7e82df48f..25212dcca2df 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -330,8 +330,8 @@ const struct pipe_buf_operations default_pipe_buf_ops = { .get = generic_pipe_buf_get, }; -static int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe, - struct pipe_buffer *buf) +int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) { return 1; } @@ -1593,7 +1593,11 @@ retry: * Get a reference to this pipe buffer, * so we can copy the contents over. */ - pipe_buf_get(ipipe, ibuf); + if (!pipe_buf_get(ipipe, ibuf)) { + if (ret == 0) + ret = -EFAULT; + break; + } *obuf = *ibuf; /* @@ -1667,7 +1671,11 @@ static int link_pipe(struct pipe_inode_info *ipipe, * Get a reference to this pipe buffer, * so we can copy the contents over. */ - pipe_buf_get(ipipe, ibuf); + if (!pipe_buf_get(ipipe, ibuf)) { + if (ret == 0) + ret = -EFAULT; + break; + } obuf = opipe->bufs + nbuf; *obuf = *ibuf; diff --git a/fs/super.c b/fs/super.c index 583a0124bc39..2739f57515f8 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1467,11 +1467,6 @@ int vfs_get_tree(struct fs_context *fc) struct super_block *sb; int error; - if (fc->fs_type->fs_flags & FS_REQUIRES_DEV && !fc->source) { - errorf(fc, "Filesystem requires source device"); - return -ENOENT; - } - if (fc->root) return -EBUSY; diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 8dc2818fdd84..12628184772c 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -276,14 +276,12 @@ static void ubifs_i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); struct ubifs_inode *ui = ubifs_inode(inode); + kfree(ui->data); kmem_cache_free(ubifs_inode_slab, ui); } static void ubifs_destroy_inode(struct inode *inode) { - struct ubifs_inode *ui = ubifs_inode(inode); - - kfree(ui->data); call_rcu(&inode->i_rcu, ubifs_i_callback); } diff --git a/fs/udf/inode.c b/fs/udf/inode.c index ae796e10f68b..e7276932e433 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1242,8 +1242,10 @@ set_size: truncate_setsize(inode, newsize); down_write(&iinfo->i_data_sem); udf_clear_extent_cache(inode); - udf_truncate_extents(inode); + err = udf_truncate_extents(inode); up_write(&iinfo->i_data_sem); + if (err) + return err; } update_time: inode->i_mtime = inode->i_ctime = current_time(inode); diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c index b647f0bd150c..63a47f1e1d52 100644 --- a/fs/udf/truncate.c +++ b/fs/udf/truncate.c @@ -199,7 +199,7 @@ static void udf_update_alloc_ext_desc(struct inode *inode, * for making file shorter. For making file longer, udf_extend_file() has to * be used. */ -void udf_truncate_extents(struct inode *inode) +int udf_truncate_extents(struct inode *inode) { struct extent_position epos; struct kernel_lb_addr eloc, neloc = {}; @@ -224,7 +224,7 @@ void udf_truncate_extents(struct inode *inode) if (etype == -1) { /* We should extend the file? */ WARN_ON(byte_offset); - return; + return 0; } epos.offset -= adsize; extent_trunc(inode, &epos, &eloc, etype, elen, byte_offset); @@ -260,6 +260,9 @@ void udf_truncate_extents(struct inode *inode) epos.block = eloc; epos.bh = udf_tread(sb, udf_get_lb_pblock(sb, &eloc, 0)); + /* Error reading indirect block? */ + if (!epos.bh) + return -EIO; if (elen) indirect_ext_len = (elen + sb->s_blocksize - 1) >> @@ -283,4 +286,5 @@ void udf_truncate_extents(struct inode *inode) iinfo->i_lenExtents = inode->i_size; brelse(epos.bh); + return 0; } diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h index ee246769dee4..d89ef71887fc 100644 --- a/fs/udf/udfdecl.h +++ b/fs/udf/udfdecl.h @@ -235,7 +235,7 @@ extern struct inode *udf_new_inode(struct inode *, umode_t); /* truncate.c */ extern void udf_truncate_tail_extent(struct inode *); extern void udf_discard_prealloc(struct inode *); -extern void udf_truncate_extents(struct inode *); +extern int udf_truncate_extents(struct inode *); /* balloc.c */ extern void udf_free_blocks(struct super_block *, struct inode *, diff --git a/fs/ufs/util.h b/fs/ufs/util.h index 1fd3011ea623..7fd4802222b8 100644 --- a/fs/ufs/util.h +++ b/fs/ufs/util.h @@ -229,7 +229,7 @@ ufs_get_inode_gid(struct super_block *sb, struct ufs_inode *inode) case UFS_UID_44BSD: return fs32_to_cpu(sb, inode->ui_u3.ui_44.ui_gid); case UFS_UID_EFT: - if (inode->ui_u1.oldids.ui_suid == 0xFFFF) + if (inode->ui_u1.oldids.ui_sgid == 0xFFFF) return fs32_to_cpu(sb, inode->ui_u3.ui_sun.ui_gid); /* Fall through */ default: diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 89800fc7dc9d..f5de1e726356 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -629,6 +629,8 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, /* the various vma->vm_userfaultfd_ctx still points to it */ down_write(&mm->mmap_sem); + /* no task can run (and in turn coredump) yet */ + VM_WARN_ON(!mmget_still_valid(mm)); for (vma = mm->mmap; vma; vma = vma->vm_next) if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; @@ -883,6 +885,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file) * taking the mmap_sem for writing. */ down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto skip_mm; prev = NULL; for (vma = mm->mmap; vma; vma = vma->vm_next) { cond_resched(); @@ -905,6 +909,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) vma->vm_flags = new_flags; vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; } +skip_mm: up_write(&mm->mmap_sem); mmput(mm); wakeup: @@ -1333,6 +1338,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, goto out; down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; @@ -1520,6 +1527,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, goto out; down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 48502cb9990f..4637ae1ae91c 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -1191,7 +1191,10 @@ xfs_iread_extents( * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out. */ level = be16_to_cpu(block->bb_level); - ASSERT(level > 0); + if (unlikely(level == 0)) { + XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp); + return -EFSCORRUPTED; + } pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes); bno = be64_to_cpu(*pp); @@ -4249,9 +4252,13 @@ xfs_bmapi_write( struct xfs_bmbt_irec *mval, /* output: map values */ int *nmap) /* i/o: mval size/count */ { + struct xfs_bmalloca bma = { + .tp = tp, + .ip = ip, + .total = total, + }; struct xfs_mount *mp = ip->i_mount; struct xfs_ifork *ifp; - struct xfs_bmalloca bma = { NULL }; /* args for xfs_bmap_alloc */ xfs_fileoff_t end; /* end of mapped file region */ bool eof = false; /* after the end of extents */ int error; /* error return */ @@ -4319,10 +4326,6 @@ xfs_bmapi_write( eof = true; if (!xfs_iext_peek_prev_extent(ifp, &bma.icur, &bma.prev)) bma.prev.br_startoff = NULLFILEOFF; - bma.tp = tp; - bma.ip = ip; - bma.total = total; - bma.datatype = 0; bma.minleft = xfs_bmapi_minleft(tp, ip, whichfork); n = 0; diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c index 6f94d1f7322d..117910db51b8 100644 --- a/fs/xfs/scrub/btree.c +++ b/fs/xfs/scrub/btree.c @@ -415,8 +415,17 @@ xchk_btree_check_owner( struct xfs_btree_cur *cur = bs->cur; struct check_owner *co; - if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) && bp == NULL) + /* + * In theory, xfs_btree_get_block should only give us a null buffer + * pointer for the root of a root-in-inode btree type, but we need + * to check defensively here in case the cursor state is also screwed + * up. + */ + if (bp == NULL) { + if (!(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)) + xchk_btree_set_corrupt(bs->sc, bs->cur, level); return 0; + } /* * We want to cross-reference each btree block with the bnobt diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c index f1260b4bfdee..90527b094878 100644 --- a/fs/xfs/scrub/dabtree.c +++ b/fs/xfs/scrub/dabtree.c @@ -574,6 +574,11 @@ xchk_da_btree( /* Drill another level deeper. */ blkno = be32_to_cpu(key->before); level++; + if (level >= XFS_DA_NODE_MAXDEPTH) { + /* Too deep! */ + xchk_da_set_corrupt(&ds, level - 1); + break; + } ds.tree_level--; error = xchk_da_btree_block(&ds, level, blkno); if (error) diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index 93f07edafd81..9ee2a7d02e70 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -161,6 +161,14 @@ xfs_ioc_trim( return -EPERM; if (!blk_queue_discard(q)) return -EOPNOTSUPP; + + /* + * We haven't recovered the log, so we cannot use our bnobt-guided + * storage zapping commands. + */ + if (mp->m_flags & XFS_MOUNT_NORECOVERY) + return -EROFS; + if (copy_from_user(&range, urange, sizeof(range))) return -EFAULT; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 1f2e2845eb76..a7ceae90110e 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -529,18 +529,17 @@ xfs_file_dio_aio_write( count = iov_iter_count(from); /* - * If we are doing unaligned IO, wait for all other IO to drain, - * otherwise demote the lock if we had to take the exclusive lock - * for other reasons in xfs_file_aio_write_checks. + * If we are doing unaligned IO, we can't allow any other overlapping IO + * in-flight at the same time or we risk data corruption. Wait for all + * other IO to drain before we submit. If the IO is aligned, demote the + * iolock if we had to take the exclusive lock in + * xfs_file_aio_write_checks() for other reasons. */ if (unaligned_io) { - /* If we are going to wait for other DIO to finish, bail */ - if (iocb->ki_flags & IOCB_NOWAIT) { - if (atomic_read(&inode->i_dio_count)) - return -EAGAIN; - } else { - inode_dio_wait(inode); - } + /* unaligned dio always waits, bail */ + if (iocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + inode_dio_wait(inode); } else if (iolock == XFS_IOLOCK_EXCL) { xfs_ilock_demote(ip, XFS_IOLOCK_EXCL); iolock = XFS_IOLOCK_SHARED; @@ -548,6 +547,14 @@ xfs_file_dio_aio_write( trace_xfs_file_direct_write(ip, count, iocb->ki_pos); ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, xfs_dio_write_end_io); + + /* + * If unaligned, this is the only IO in-flight. If it has not yet + * completed, wait on it before we release the iolock to prevent + * subsequent overlapping IO. + */ + if (ret == -EIOCBQUEUED && unaligned_io) + inode_dio_wait(inode); out: xfs_iunlock(ip, iolock); |