diff --git a/fs/afs/symlink.c b/fs/afs/symlink.c index ed5868369f37..16b4823cb7b7 100644 --- a/fs/afs/symlink.c +++ b/fs/afs/symlink.c @@ -255,11 +255,11 @@ int afs_symlink_writepages(struct address_space *mapping, } if (ret == 0) { - mutex_lock(&vnode->netfs.wb_lock); + netfs_wb_begin(&vnode->netfs, false); netfs_free_folioq_buffer(vnode->directory); vnode->directory = NULL; vnode->directory_size = 0; - mutex_unlock(&vnode->netfs.wb_lock); + netfs_wb_end(&vnode->netfs); } else if (ret == 1) { ret = 0; /* Skipped write due to lock conflict. */ } diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index 2c46f0decb02..8a9f6be15828 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -374,7 +374,7 @@ int cachefiles_bury_object(struct cachefiles_cache *cache, "Rename failed with error %d", ret); } - __cachefiles_unmark_inode_in_use(object, d_inode(rep)); + cachefiles_do_unmark_inode_in_use(object, d_inode(rep)); end_renaming(&rd); _leave(" = 0"); return 0; @@ -466,7 +466,6 @@ struct file *cachefiles_create_tmpfile(struct cachefiles_object *object) ret = -EINVAL; if (unlikely(!file->f_op->read_iter) || unlikely(!file->f_op->write_iter)) { - fput(file); pr_notice("Cache does not support read_iter and write_iter\n"); goto err_unuse; } diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 76d0f6a29aba..24a8a5418e31 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -659,7 +659,7 @@ int netfs_write_begin(struct netfs_inode *ctx, * within the cache granule containing the EOF, in which case we need * to preload the granule. */ - if (!netfs_is_cache_enabled(ctx) && + if (!netfs_is_cache_maybe_enabled(ctx) && netfs_skip_folio_read(folio, pos, len, false)) { netfs_stat(&netfs_n_rh_write_zskip); goto have_folio_no_wait; diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c index 6bde3320bcec..2cdb68e6b16f 100644 --- a/fs/netfs/buffered_write.c +++ b/fs/netfs/buffered_write.c @@ -277,7 +277,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, * caching service temporarily because the backing store got * culled. */ - if (netfs_is_cache_enabled(ctx)) { + if (netfs_is_cache_maybe_enabled(ctx)) { if (finfo) { netfs_stat(&netfs_n_wh_wstream_conflict); goto flush_content; diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index 25f8ceb15fad..c16fbad286a1 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -166,13 +166,16 @@ static int netfs_unbuffered_write(struct netfs_io_request *wreq) */ subreq->error = -EAGAIN; trace_netfs_sreq(subreq, netfs_sreq_trace_retry); - if (subreq->transferred > 0) + if (subreq->transferred > 0) { iov_iter_advance(&wreq->buffer.iter, subreq->transferred); + wreq->transferred += subreq->transferred; + } if (stream->source == NETFS_UPLOAD_TO_SERVER && wreq->netfs_ops->retry_request) wreq->netfs_ops->retry_request(wreq, stream); + __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); __clear_bit(NETFS_SREQ_BOUNDARY, &subreq->flags); __clear_bit(NETFS_SREQ_FAILED, &subreq->flags); @@ -186,17 +189,10 @@ static int netfs_unbuffered_write(struct netfs_io_request *wreq) netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); - if (stream->prepare_write) { + if (stream->prepare_write) stream->prepare_write(subreq); - __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); - netfs_stat(&netfs_n_wh_retry_write_subreq); - } else { - struct iov_iter source; - - netfs_reset_iter(subreq); - source = subreq->io_iter; - netfs_reissue_write(stream, subreq, &source); - } + __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); + netfs_stat(&netfs_n_wh_retry_write_subreq); } netfs_unbuffered_write_done(wreq); diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index 645996ecfc80..d889caa401dc 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -239,6 +239,18 @@ static inline bool netfs_is_cache_enabled(struct netfs_inode *ctx) #endif } +static inline bool netfs_is_cache_maybe_enabled(struct netfs_inode *ctx) +{ +#if IS_ENABLED(CONFIG_FSCACHE) + struct fscache_cookie *cookie = ctx->cache; + + return fscache_cookie_valid(cookie) && + test_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags); +#else + return false; +#endif +} + /* * Get a ref on a netfs group attached to a dirty page (e.g. a ceph snap). */ diff --git a/fs/netfs/locking.c b/fs/netfs/locking.c index 2249ecd09d0a..4e3be2b81504 100644 --- a/fs/netfs/locking.c +++ b/fs/netfs/locking.c @@ -9,6 +9,11 @@ #include #include "internal.h" +struct netfs_wb_waiter { + struct list_head link; /* Link in ictx->wb_queue */ + struct task_struct *waiter; /* Waiter task; cleared when lock granted */ +}; + /* * inode_dio_wait_interruptible - wait for outstanding DIO requests to finish * @inode: inode to wait for @@ -203,3 +208,93 @@ void netfs_end_io_direct(struct inode *inode) up_read(&inode->i_rwsem); } EXPORT_SYMBOL(netfs_end_io_direct); + +/* + * Wait to have exclusive access to writeback. + */ +static bool netfs_wb_begin_wait(struct netfs_inode *ictx) +{ + struct netfs_wb_waiter waiter = {}; + struct task_struct *tsk = current; + bool got = false; + + spin_lock(&ictx->lock); + + if (test_and_set_bit_lock(NETFS_ICTX_WB_LOCK, &ictx->flags)) { + get_task_struct(tsk); + waiter.waiter = tsk; + list_add_tail(&waiter.link, &ictx->wb_queue); + } else { + got = true; + } + spin_unlock(&ictx->lock); + + if (!got) { + for (;;) { + set_current_state(TASK_UNINTERRUPTIBLE); + /* Read waiter before accessing inode state. */ + if (smp_load_acquire(&waiter.waiter) == NULL) + break; + schedule(); + } + } + __set_current_state(TASK_RUNNING); + return true; +} + +/** + * netfs_wb_begin - Begin writeback, waiting if need be + * @ictx: The inode to get writeback access on + * @nowait: Return failure immediately rather than waiting if true + * + * Begin writeback to an inode, waiting for exclusive access if @nowait is + * false. This prevents collection from being done out of order with respect + * to the issuance of write subrequests. + * + * Note that writeback may be ended in a different process (e.g. the collection + * function on a workqueue) than started it. + * + * Return: True if can proceed, false if denied. + */ +bool netfs_wb_begin(struct netfs_inode *ictx, bool nowait) +{ + if (!test_and_set_bit_lock(NETFS_ICTX_WB_LOCK, &ictx->flags)) + return true; + if (nowait) { + netfs_stat(&netfs_n_wb_lock_skip); + return false; + } + netfs_stat(&netfs_n_wb_lock_wait); + return netfs_wb_begin_wait(ictx); +} +EXPORT_SYMBOL(netfs_wb_begin); + +/* netfs_wb_end - End writeback + * @ictx: The inode we have writeback access to + * + * End writeback access on an inode, waking up the next writeback request. + */ +void netfs_wb_end(struct netfs_inode *ictx) +{ + struct netfs_wb_waiter *waiter; + struct task_struct *tsk; + + WARN_ON_ONCE(!test_bit(NETFS_ICTX_WB_LOCK, &ictx->flags)); + + spin_lock(&ictx->lock); + + waiter = list_first_entry_or_null(&ictx->wb_queue, struct netfs_wb_waiter, link); + if (waiter) { + list_del(&waiter->link); + tsk = waiter->waiter; + /* Write inode state before clearing waiter. */ + smp_store_release(&waiter->waiter, NULL); + wake_up_process(tsk); + put_task_struct(tsk); + } else { + clear_bit_unlock(NETFS_ICTX_WB_LOCK, &ictx->flags); + } + + spin_unlock(&ictx->lock); +} +EXPORT_SYMBOL(netfs_wb_end); diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index 24fc2bb2f8a4..210eb8f3958d 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -408,6 +408,16 @@ bool netfs_write_collection(struct netfs_io_request *wreq) netfs_wake_rreq_flag(wreq, NETFS_RREQ_IN_PROGRESS, netfs_rreq_trace_wake_ip); /* As we cleared NETFS_RREQ_IN_PROGRESS, we acquired its ref. */ + switch (wreq->origin) { + case NETFS_WRITEBACK: + case NETFS_WRITEBACK_SINGLE: + case NETFS_WRITETHROUGH: + netfs_wb_end(ictx); + break; + default: + break; + } + if (wreq->iocb) { size_t written = min(wreq->transferred, wreq->len); wreq->iocb->ki_pos += written; diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index c03c7cc45e47..f2761c99795a 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -106,7 +106,7 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, _enter("R=%x", wreq->debug_id); ictx = netfs_inode(wreq->inode); - if (is_cacheable && netfs_is_cache_enabled(ictx)) + if (is_cacheable) fscache_begin_write_operation(&wreq->cache_resources, netfs_i_cookie(ictx)); if (rolling_buffer_init(&wreq->buffer, wreq->debug_id, ITER_SOURCE) < 0) goto nomem; @@ -551,14 +551,8 @@ int netfs_writepages(struct address_space *mapping, struct folio *folio; int error = 0; - if (!mutex_trylock(&ictx->wb_lock)) { - if (wbc->sync_mode == WB_SYNC_NONE) { - netfs_stat(&netfs_n_wb_lock_skip); - return 0; - } - netfs_stat(&netfs_n_wb_lock_wait); - mutex_lock(&ictx->wb_lock); - } + if (!netfs_wb_begin(ictx, wbc->sync_mode == WB_SYNC_NONE)) + return 0; /* Need the first folio to be able to set up the op. */ folio = writeback_iter(mapping, wbc, NULL, &error); @@ -588,13 +582,13 @@ int netfs_writepages(struct address_space *mapping, } error = netfs_write_folio(wreq, wbc, folio); - if (error < 0) - break; + if (error == -ENOMEM) { + folio_redirty_for_writepage(wbc, folio); + folio_unlock(folio); + } } while ((folio = writeback_iter(mapping, wbc, folio, &error))); netfs_end_issue_write(wreq); - - mutex_unlock(&ictx->wb_lock); netfs_wake_collector(wreq); netfs_put_request(wreq, netfs_rreq_trace_put_return); @@ -602,9 +596,16 @@ int netfs_writepages(struct address_space *mapping, return error; couldnt_start: - netfs_kill_dirty_pages(mapping, wbc, folio); + if (error == -ENOMEM) { + folio_redirty_for_writepage(wbc, folio); + folio_unlock(folio); + folio = writeback_iter(mapping, wbc, folio, &error); + WARN_ON_ONCE(folio != NULL); + } else { + netfs_kill_dirty_pages(mapping, wbc, folio); + } out: - mutex_unlock(&ictx->wb_lock); + netfs_wb_end(ictx); _leave(" = %d", error); return error; } @@ -618,16 +619,17 @@ struct netfs_io_request *netfs_begin_writethrough(struct kiocb *iocb, size_t len struct netfs_io_request *wreq = NULL; struct netfs_inode *ictx = netfs_inode(file_inode(iocb->ki_filp)); - mutex_lock(&ictx->wb_lock); + netfs_wb_begin(ictx, false); wreq = netfs_create_write_req(iocb->ki_filp->f_mapping, iocb->ki_filp, iocb->ki_pos, NETFS_WRITETHROUGH); if (IS_ERR(wreq)) { - mutex_unlock(&ictx->wb_lock); + netfs_wb_end(ictx); return wreq; } wreq->io_streams[0].avail = true; + __set_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &wreq->flags); trace_netfs_write(wreq, netfs_write_trace_writethrough); return wreq; } @@ -685,7 +687,6 @@ int netfs_advance_writethrough(struct netfs_io_request *wreq, struct writeback_c ssize_t netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_control *wbc, struct folio *writethrough_cache) { - struct netfs_inode *ictx = netfs_inode(wreq->inode); ssize_t ret; _enter("R=%x", wreq->debug_id); @@ -699,8 +700,6 @@ ssize_t netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_c netfs_end_issue_write(wreq); - mutex_unlock(&ictx->wb_lock); - if (wreq->iocb) ret = -EIOCBQUEUED; else @@ -847,15 +846,10 @@ int netfs_writeback_single(struct address_space *mapping, if (WARN_ON_ONCE(!iov_iter_is_folioq(iter))) return -EIO; - if (!mutex_trylock(&ictx->wb_lock)) { - if (wbc->sync_mode == WB_SYNC_NONE) { - /* The VFS will have undirtied the inode. */ - netfs_single_mark_inode_dirty(&ictx->inode); - netfs_stat(&netfs_n_wb_lock_skip); - return 1; - } - netfs_stat(&netfs_n_wb_lock_wait); - mutex_lock(&ictx->wb_lock); + if (!netfs_wb_begin(ictx, wbc->sync_mode == WB_SYNC_NONE)) { + /* The VFS will have undirtied the inode. */ + netfs_single_mark_inode_dirty(&ictx->inode); + return 1; } wreq = netfs_create_write_req(mapping, NULL, 0, NETFS_WRITEBACK_SINGLE); @@ -893,7 +887,6 @@ int netfs_writeback_single(struct address_space *mapping, smp_wmb(); /* Write lists before ALL_QUEUED. */ set_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags); - mutex_unlock(&ictx->wb_lock); netfs_wake_collector(wreq); netfs_put_request(wreq, netfs_rreq_trace_put_return); @@ -901,7 +894,7 @@ int netfs_writeback_single(struct address_space *mapping, return ret; couldnt_start: - mutex_unlock(&ictx->wb_lock); + netfs_wb_end(ictx); _leave(" = %d", ret); return ret; } diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 243c0f737938..1bc120d61c5b 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -61,14 +61,16 @@ struct netfs_inode { #if IS_ENABLED(CONFIG_FSCACHE) struct fscache_cookie *cache; #endif - struct mutex wb_lock; /* Writeback serialisation */ + struct list_head wb_queue; /* Queue of processes wanting to do writeback */ loff_t _remote_i_size; /* Size of the remote file */ loff_t _zero_point; /* Size after which we assume there's no data * on the server */ + spinlock_t lock; /* Lock covering wb_queue */ atomic_t io_count; /* Number of outstanding reqs */ unsigned long flags; #define NETFS_ICTX_ODIRECT 0 /* The file has DIO in progress */ #define NETFS_ICTX_UNBUFFERED 1 /* I/O should not use the pagecache */ +#define NETFS_ICTX_WB_LOCK 2 /* Writeback serialisation lock */ #define NETFS_ICTX_MODIFIED_ATTR 3 /* Indicate change in mtime/ctime */ #define NETFS_ICTX_SINGLE_NO_UPLOAD 4 /* Monolithic payload, cache but no upload */ }; @@ -462,6 +464,10 @@ int netfs_alloc_folioq_buffer(struct address_space *mapping, size_t *_cur_size, ssize_t size, gfp_t gfp); void netfs_free_folioq_buffer(struct folio_queue *fq); +/* Writeback exclusion API. */ +bool netfs_wb_begin(struct netfs_inode *ictx, bool nowait); +void netfs_wb_end(struct netfs_inode *ictx); + /** * netfs_inode - Get the netfs inode context from the inode * @inode: The inode to query @@ -743,7 +749,8 @@ static inline void netfs_inode_init(struct netfs_inode *ctx, #if IS_ENABLED(CONFIG_FSCACHE) ctx->cache = NULL; #endif - mutex_init(&ctx->wb_lock); + INIT_LIST_HEAD(&ctx->wb_queue); + spin_lock_init(&ctx->lock); /* ->releasepage() drives zero_point */ if (use_zero_point) { ctx->_zero_point = ctx->_remote_i_size; @@ -753,7 +760,7 @@ static inline void netfs_inode_init(struct netfs_inode *ctx, /** * netfs_resize_file - Note that a file got resized - * @ctx: The netfs inode being resized + * @ictx: The netfs inode being resized * @new_i_size: The new file size * @changed_on_server: The change was applied to the server * diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 273919b16161..c2484551a4e8 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1568,6 +1568,7 @@ static ssize_t iov_iter_extract_xarray_pages(struct iov_iter *i, struct folio *folio; unsigned int nr = 0, offset; loff_t pos = i->xarray_start + i->iov_offset; + bool will_alloc = !*pages; XA_STATE(xas, i->xarray, pos >> PAGE_SHIFT); offset = pos & ~PAGE_MASK; @@ -1595,6 +1596,14 @@ static ssize_t iov_iter_extract_xarray_pages(struct iov_iter *i, } rcu_read_unlock(); + if (!nr) { + if (will_alloc) { + kvfree(*pages); + *pages = NULL; + } + return 0; + } + maxsize = min_t(size_t, nr * PAGE_SIZE - offset, maxsize); iov_iter_advance(i, maxsize); return maxsize; @@ -1628,6 +1637,8 @@ static ssize_t iov_iter_extract_bvec_pages(struct iov_iter *i, bi.bi_bvec_done = skip; maxpages = want_pages_array(pages, maxsize, skip, maxpages); + if (!maxpages) + return -ENOMEM; while (bi.bi_size && bi.bi_idx < i->nr_segs) { struct bio_vec bv = bvec_iter_bvec(i->bvec, bi); @@ -1745,6 +1756,7 @@ static ssize_t iov_iter_extract_user_pages(struct iov_iter *i, unsigned long addr; unsigned int gup_flags = 0; size_t offset; + bool will_alloc = !*pages; int res; if (i->data_source == ITER_DEST) @@ -1761,8 +1773,14 @@ static ssize_t iov_iter_extract_user_pages(struct iov_iter *i, if (!maxpages) return -ENOMEM; res = pin_user_pages_fast(addr, maxpages, gup_flags, *pages); - if (unlikely(res <= 0)) + if (unlikely(res <= 0)) { + if (will_alloc) { + kvfree(*pages); + *pages = NULL; + } return res; + } + maxsize = min_t(size_t, maxsize, res * PAGE_SIZE - offset); iov_iter_advance(i, maxsize); return maxsize; diff --git a/lib/scatterlist.c b/lib/scatterlist.c index b7fe91ef35b8..6ea40d2e6247 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -1366,6 +1366,7 @@ static ssize_t extract_xarray_to_sg(struct iov_iter *iter, sg_max--; maxsize -= len; + start += len; ret += len; if (maxsize <= 0 || sg_max == 0) break; diff --git a/lib/tests/kunit_iov_iter.c b/lib/tests/kunit_iov_iter.c index 1e6fce9cb255..d9690ba1db88 100644 --- a/lib/tests/kunit_iov_iter.c +++ b/lib/tests/kunit_iov_iter.c @@ -283,7 +283,7 @@ static void __init iov_kunit_copy_to_bvec(struct kunit *test) struct page **spages, **bpages; u8 *scratch, *buffer; size_t bufsize, npages, size, copied; - int i, b, patt; + int i, patt; bufsize = 0x100000; npages = bufsize / PAGE_SIZE; @@ -306,10 +306,9 @@ static void __init iov_kunit_copy_to_bvec(struct kunit *test) KUNIT_EXPECT_EQ(test, iter.nr_segs, 0); /* Build the expected image in the scratch buffer. */ - b = 0; patt = 0; memset(scratch, 0, bufsize); - for (pr = bvec_test_ranges; pr->from >= 0; pr++, b++) { + for (pr = bvec_test_ranges; pr->from >= 0; pr++) { u8 *p = scratch + pr->page * PAGE_SIZE; for (i = pr->from; i < pr->to; i++)