diff --git a/fs/Kconfig b/fs/Kconfig index a55bda4233bbea..97e7b77c93094f 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -125,6 +125,7 @@ source "fs/overlayfs/Kconfig" menu "Caches" +source "fs/netfs/Kconfig" source "fs/fscache/Kconfig" source "fs/cachefiles/Kconfig" diff --git a/fs/Makefile b/fs/Makefile index 3215fe205256dd..9c708e1fbe8fb3 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -67,6 +67,7 @@ obj-y += devpts/ obj-$(CONFIG_DLM) += dlm/ # Do not add any filesystems before this line +obj-$(CONFIG_NETFS_SUPPORT) += netfs/ obj-$(CONFIG_FSCACHE) += fscache/ obj-$(CONFIG_REISERFS_FS) += reiserfs/ obj-$(CONFIG_EXT4_FS) += ext4/ diff --git a/fs/netfs/Makefile b/fs/netfs/Makefile new file mode 100644 index 00000000000000..4b4eff2ba369df --- /dev/null +++ b/fs/netfs/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 + +netfs-y := \ + read_helper.o + +obj-$(CONFIG_NETFS_SUPPORT) := netfs.o diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h new file mode 100644 index 00000000000000..ee665c0e7dc80f --- /dev/null +++ b/fs/netfs/internal.h @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Internal definitions for network filesystem support + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#ifdef pr_fmt +#undef pr_fmt +#endif + +#define pr_fmt(fmt) "netfs: " fmt + +/* + * read_helper.c + */ +extern unsigned int netfs_debug; + +#define netfs_stat(x) do {} while(0) +#define netfs_stat_d(x) do {} while(0) + +/*****************************************************************************/ +/* + * debug tracing + */ +#define dbgprintk(FMT, ...) \ + printk("[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__) + +#define kenter(FMT, ...) dbgprintk("==> %s("FMT")", __func__, ##__VA_ARGS__) +#define kleave(FMT, ...) dbgprintk("<== %s()"FMT"", __func__, ##__VA_ARGS__) +#define kdebug(FMT, ...) dbgprintk(FMT, ##__VA_ARGS__) + +#ifdef __KDEBUG +#define _enter(FMT, ...) kenter(FMT, ##__VA_ARGS__) +#define _leave(FMT, ...) kleave(FMT, ##__VA_ARGS__) +#define _debug(FMT, ...) kdebug(FMT, ##__VA_ARGS__) + +#elif defined(CONFIG_NETFS_DEBUG) +#define _enter(FMT, ...) \ +do { \ + if (netfs_debug) \ + kenter(FMT, ##__VA_ARGS__); \ +} while (0) + +#define _leave(FMT, ...) \ +do { \ + if (netfs_debug) \ + kleave(FMT, ##__VA_ARGS__); \ +} while (0) + +#define _debug(FMT, ...) \ +do { \ + if (netfs_debug) \ + kdebug(FMT, ##__VA_ARGS__); \ +} while (0) + +#else +#define _enter(FMT, ...) no_printk("==> %s("FMT")", __func__, ##__VA_ARGS__) +#define _leave(FMT, ...) no_printk("<== %s()"FMT"", __func__, ##__VA_ARGS__) +#define _debug(FMT, ...) no_printk(FMT, ##__VA_ARGS__) +#endif diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c new file mode 100644 index 00000000000000..30d4bf6bf28aa9 --- /dev/null +++ b/fs/netfs/read_helper.c @@ -0,0 +1,725 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Network filesystem high-level read support. + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "internal.h" + +MODULE_DESCRIPTION("Network fs support"); +MODULE_AUTHOR("Red Hat, Inc."); +MODULE_LICENSE("GPL"); + +unsigned netfs_debug; +module_param_named(debug, netfs_debug, uint, S_IWUSR | S_IRUGO); +MODULE_PARM_DESC(netfs_debug, "Netfs support debugging mask"); + +static void netfs_rreq_work(struct work_struct *); +static void __netfs_put_subrequest(struct netfs_read_subrequest *, bool); + +static void netfs_put_subrequest(struct netfs_read_subrequest *subreq, + bool was_async) +{ + if (refcount_dec_and_test(&subreq->usage)) + __netfs_put_subrequest(subreq, was_async); +} + +static struct netfs_read_request *netfs_alloc_read_request( + const struct netfs_read_request_ops *ops, void *netfs_priv, + struct file *file) +{ + static atomic_t debug_ids; + struct netfs_read_request *rreq; + + rreq = kzalloc(sizeof(struct netfs_read_request), GFP_KERNEL); + if (rreq) { + rreq->netfs_ops = ops; + rreq->netfs_priv = netfs_priv; + rreq->inode = file_inode(file); + rreq->i_size = i_size_read(rreq->inode); + rreq->debug_id = atomic_inc_return(&debug_ids); + INIT_LIST_HEAD(&rreq->subrequests); + INIT_WORK(&rreq->work, netfs_rreq_work); + refcount_set(&rreq->usage, 1); + __set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags); + ops->init_rreq(rreq, file); + } + + return rreq; +} + +static void netfs_get_read_request(struct netfs_read_request *rreq) +{ + refcount_inc(&rreq->usage); +} + +static void netfs_rreq_clear_subreqs(struct netfs_read_request *rreq, + bool was_async) +{ + struct netfs_read_subrequest *subreq; + + while (!list_empty(&rreq->subrequests)) { + subreq = list_first_entry(&rreq->subrequests, + struct netfs_read_subrequest, rreq_link); + list_del(&subreq->rreq_link); + netfs_put_subrequest(subreq, was_async); + } +} + +static void netfs_free_read_request(struct work_struct *work) +{ + struct netfs_read_request *rreq = + container_of(work, struct netfs_read_request, work); + netfs_rreq_clear_subreqs(rreq, false); + if (rreq->netfs_priv) + rreq->netfs_ops->cleanup(rreq->mapping, rreq->netfs_priv); + kfree(rreq); +} + +static void netfs_put_read_request(struct netfs_read_request *rreq, bool was_async) +{ + if (refcount_dec_and_test(&rreq->usage)) { + if (was_async) { + rreq->work.func = netfs_free_read_request; + if (!queue_work(system_unbound_wq, &rreq->work)) + BUG(); + } else { + netfs_free_read_request(&rreq->work); + } + } +} + +/* + * Allocate and partially initialise an I/O request structure. + */ +static struct netfs_read_subrequest *netfs_alloc_subrequest( + struct netfs_read_request *rreq) +{ + struct netfs_read_subrequest *subreq; + + subreq = kzalloc(sizeof(struct netfs_read_subrequest), GFP_KERNEL); + if (subreq) { + INIT_LIST_HEAD(&subreq->rreq_link); + refcount_set(&subreq->usage, 2); + subreq->rreq = rreq; + netfs_get_read_request(rreq); + } + + return subreq; +} + +static void netfs_get_read_subrequest(struct netfs_read_subrequest *subreq) +{ + refcount_inc(&subreq->usage); +} + +static void __netfs_put_subrequest(struct netfs_read_subrequest *subreq, + bool was_async) +{ + struct netfs_read_request *rreq = subreq->rreq; + + kfree(subreq); + netfs_put_read_request(rreq, was_async); +} + +/* + * Clear the unread part of an I/O request. + */ +static void netfs_clear_unread(struct netfs_read_subrequest *subreq) +{ + struct iov_iter iter; + + iov_iter_xarray(&iter, WRITE, &subreq->rreq->mapping->i_pages, + subreq->start + subreq->transferred, + subreq->len - subreq->transferred); + iov_iter_zero(iov_iter_count(&iter), &iter); +} + +/* + * Fill a subrequest region with zeroes. + */ +static void netfs_fill_with_zeroes(struct netfs_read_request *rreq, + struct netfs_read_subrequest *subreq) +{ + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + netfs_subreq_terminated(subreq, 0, false); +} + +/* + * Ask the netfs to issue a read request to the server for us. + * + * The netfs is expected to read from subreq->pos + subreq->transferred to + * subreq->pos + subreq->len - 1. It may not backtrack and write data into the + * buffer prior to the transferred point as it might clobber dirty data + * obtained from the cache. + * + * Alternatively, the netfs is allowed to indicate one of two things: + * + * - NETFS_SREQ_SHORT_READ: A short read - it will get called again to try and + * make progress. + * + * - NETFS_SREQ_CLEAR_TAIL: A short read - the rest of the buffer will be + * cleared. + */ +static void netfs_read_from_server(struct netfs_read_request *rreq, + struct netfs_read_subrequest *subreq) +{ + rreq->netfs_ops->issue_op(subreq); +} + +/* + * Release those waiting. + */ +static void netfs_rreq_completed(struct netfs_read_request *rreq, bool was_async) +{ + netfs_rreq_clear_subreqs(rreq, was_async); + netfs_put_read_request(rreq, was_async); +} + +/* + * Unlock the pages in a read operation. We need to set PG_fscache on any + * pages we're going to write back before we unlock them. + */ +static void netfs_rreq_unlock(struct netfs_read_request *rreq) +{ + struct netfs_read_subrequest *subreq; + struct page *page; + unsigned int iopos, account = 0; + pgoff_t start_page = rreq->start / PAGE_SIZE; + pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1; + bool subreq_failed = false; + int i; + + XA_STATE(xas, &rreq->mapping->i_pages, start_page); + + if (test_bit(NETFS_RREQ_FAILED, &rreq->flags)) { + __clear_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags); + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + __clear_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags); + } + } + + /* Walk through the pagecache and the I/O request lists simultaneously. + * We may have a mixture of cached and uncached sections and we only + * really want to write out the uncached sections. This is slightly + * complicated by the possibility that we might have huge pages with a + * mixture inside. + */ + subreq = list_first_entry(&rreq->subrequests, + struct netfs_read_subrequest, rreq_link); + iopos = 0; + subreq_failed = (subreq->error < 0); + + rcu_read_lock(); + xas_for_each(&xas, page, last_page) { + unsigned int pgpos = (page->index - start_page) * PAGE_SIZE; + unsigned int pgend = pgpos + thp_size(page); + bool pg_failed = false; + + for (;;) { + if (!subreq) { + pg_failed = true; + break; + } + if (test_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags)) + set_page_fscache(page); + pg_failed |= subreq_failed; + if (pgend < iopos + subreq->len) + break; + + account += subreq->transferred; + iopos += subreq->len; + if (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { + subreq = list_next_entry(subreq, rreq_link); + subreq_failed = (subreq->error < 0); + } else { + subreq = NULL; + subreq_failed = false; + } + if (pgend == iopos) + break; + } + + if (!pg_failed) { + for (i = 0; i < thp_nr_pages(page); i++) + flush_dcache_page(page); + SetPageUptodate(page); + } + + if (!test_bit(NETFS_RREQ_DONT_UNLOCK_PAGES, &rreq->flags)) { + if (page->index == rreq->no_unlock_page && + test_bit(NETFS_RREQ_NO_UNLOCK_PAGE, &rreq->flags)) + _debug("no unlock"); + else + unlock_page(page); + } + } + rcu_read_unlock(); + + task_io_account_read(account); + if (rreq->netfs_ops->done) + rreq->netfs_ops->done(rreq); +} + +/* + * Handle a short read. + */ +static void netfs_rreq_short_read(struct netfs_read_request *rreq, + struct netfs_read_subrequest *subreq) +{ + __clear_bit(NETFS_SREQ_SHORT_READ, &subreq->flags); + __set_bit(NETFS_SREQ_SEEK_DATA_READ, &subreq->flags); + + netfs_get_read_subrequest(subreq); + atomic_inc(&rreq->nr_rd_ops); + netfs_read_from_server(rreq, subreq); +} + +/* + * Resubmit any short or failed operations. Returns true if we got the rreq + * ref back. + */ +static bool netfs_rreq_perform_resubmissions(struct netfs_read_request *rreq) +{ + struct netfs_read_subrequest *subreq; + + WARN_ON(in_interrupt()); + + /* We don't want terminating submissions trying to wake us up whilst + * we're still going through the list. + */ + atomic_inc(&rreq->nr_rd_ops); + + __clear_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + if (subreq->error) { + if (subreq->source != NETFS_READ_FROM_CACHE) + break; + subreq->source = NETFS_DOWNLOAD_FROM_SERVER; + subreq->error = 0; + netfs_get_read_subrequest(subreq); + atomic_inc(&rreq->nr_rd_ops); + netfs_read_from_server(rreq, subreq); + } else if (test_bit(NETFS_SREQ_SHORT_READ, &subreq->flags)) { + netfs_rreq_short_read(rreq, subreq); + } + } + + /* If we decrement nr_rd_ops to 0, the usage ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_rd_ops)) + return true; + + wake_up_var(&rreq->nr_rd_ops); + return false; +} + +/* + * Assess the state of a read request and decide what to do next. + * + * Note that we could be in an ordinary kernel thread, on a workqueue or in + * softirq context at this point. We inherit a ref from the caller. + */ +static void netfs_rreq_assess(struct netfs_read_request *rreq, bool was_async) +{ +again: + if (!test_bit(NETFS_RREQ_FAILED, &rreq->flags) && + test_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags)) { + if (netfs_rreq_perform_resubmissions(rreq)) + goto again; + return; + } + + netfs_rreq_unlock(rreq); + + clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags); + wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS); + + netfs_rreq_completed(rreq, was_async); +} + +static void netfs_rreq_work(struct work_struct *work) +{ + struct netfs_read_request *rreq = + container_of(work, struct netfs_read_request, work); + netfs_rreq_assess(rreq, false); +} + +/* + * Handle the completion of all outstanding I/O operations on a read request. + * We inherit a ref from the caller. + */ +static void netfs_rreq_terminated(struct netfs_read_request *rreq, + bool was_async) +{ + if (test_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags) && + was_async) { + if (!queue_work(system_unbound_wq, &rreq->work)) + BUG(); + } else { + netfs_rreq_assess(rreq, was_async); + } +} + +/** + * netfs_subreq_terminated - Note the termination of an I/O operation. + * @subreq: The I/O request that has terminated. + * @transferred_or_error: The amount of data transferred or an error code. + * @was_async: The termination was asynchronous + * + * This tells the read helper that a contributory I/O operation has terminated, + * one way or another, and that it should integrate the results. + * + * The caller indicates in @transferred_or_error the outcome of the operation, + * supplying a positive value to indicate the number of bytes transferred, 0 to + * indicate a failure to transfer anything that should be retried or a negative + * error code. The helper will look after reissuing I/O operations as + * appropriate and writing downloaded data to the cache. + * + * If @was_async is true, the caller might be running in softirq or interrupt + * context and we can't sleep. + */ +void netfs_subreq_terminated(struct netfs_read_subrequest *subreq, + ssize_t transferred_or_error, + bool was_async) +{ + struct netfs_read_request *rreq = subreq->rreq; + int u; + + _enter("[%u]{%llx,%lx},%zd", + subreq->debug_index, subreq->start, subreq->flags, + transferred_or_error); + + if (IS_ERR_VALUE(transferred_or_error)) { + subreq->error = transferred_or_error; + goto failed; + } + + if (WARN(transferred_or_error > subreq->len - subreq->transferred, + "Subreq overread: R%x[%x] %zd > %zu - %zu", + rreq->debug_id, subreq->debug_index, + transferred_or_error, subreq->len, subreq->transferred)) + transferred_or_error = subreq->len - subreq->transferred; + + subreq->error = 0; + subreq->transferred += transferred_or_error; + if (subreq->transferred < subreq->len) + goto incomplete; + +complete: + __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); + if (test_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags)) + set_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags); + +out: + /* If we decrement nr_rd_ops to 0, the ref belongs to us. */ + u = atomic_dec_return(&rreq->nr_rd_ops); + if (u == 0) + netfs_rreq_terminated(rreq, was_async); + else if (u == 1) + wake_up_var(&rreq->nr_rd_ops); + + netfs_put_subrequest(subreq, was_async); + return; + +incomplete: + if (test_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags)) { + netfs_clear_unread(subreq); + subreq->transferred = subreq->len; + goto complete; + } + + if (transferred_or_error == 0) { + if (__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) { + subreq->error = -ENODATA; + goto failed; + } + } else { + __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); + } + + __set_bit(NETFS_SREQ_SHORT_READ, &subreq->flags); + set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); + goto out; + +failed: + if (subreq->source == NETFS_READ_FROM_CACHE) { + set_bit(NETFS_RREQ_INCOMPLETE_IO, &rreq->flags); + } else { + set_bit(NETFS_RREQ_FAILED, &rreq->flags); + rreq->error = subreq->error; + } + goto out; +} +EXPORT_SYMBOL(netfs_subreq_terminated); + +static enum netfs_read_source netfs_cache_prepare_read(struct netfs_read_subrequest *subreq, + loff_t i_size) +{ + struct netfs_read_request *rreq = subreq->rreq; + + if (subreq->start >= rreq->i_size) + return NETFS_FILL_WITH_ZEROES; + return NETFS_DOWNLOAD_FROM_SERVER; +} + +/* + * Work out what sort of subrequest the next one will be. + */ +static enum netfs_read_source +netfs_rreq_prepare_read(struct netfs_read_request *rreq, + struct netfs_read_subrequest *subreq) +{ + enum netfs_read_source source; + + _enter("%llx-%llx,%llx", subreq->start, subreq->start + subreq->len, rreq->i_size); + + source = netfs_cache_prepare_read(subreq, rreq->i_size); + if (source == NETFS_INVALID_READ) + goto out; + + if (source == NETFS_DOWNLOAD_FROM_SERVER) { + /* Call out to the netfs to let it shrink the request to fit + * its own I/O sizes and boundaries. If it shinks it here, it + * will be called again to make simultaneous calls; if it wants + * to make serial calls, it can indicate a short read and then + * we will call it again. + */ + if (subreq->len > rreq->i_size - subreq->start) + subreq->len = rreq->i_size - subreq->start; + + if (rreq->netfs_ops->clamp_length && + !rreq->netfs_ops->clamp_length(subreq)) { + source = NETFS_INVALID_READ; + goto out; + } + } + + if (WARN_ON(subreq->len == 0)) + source = NETFS_INVALID_READ; + +out: + subreq->source = source; + return source; +} + +/* + * Slice off a piece of a read request and submit an I/O request for it. + */ +static bool netfs_rreq_submit_slice(struct netfs_read_request *rreq, + unsigned int *_debug_index) +{ + struct netfs_read_subrequest *subreq; + enum netfs_read_source source; + + subreq = netfs_alloc_subrequest(rreq); + if (!subreq) + return false; + + subreq->debug_index = (*_debug_index)++; + subreq->start = rreq->start + rreq->submitted; + subreq->len = rreq->len - rreq->submitted; + + _debug("slice %llx,%zx,%zx", subreq->start, subreq->len, rreq->submitted); + list_add_tail(&subreq->rreq_link, &rreq->subrequests); + + /* Call out to the cache to find out what it can do with the remaining + * subset. It tells us in subreq->flags what it decided should be done + * and adjusts subreq->len down if the subset crosses a cache boundary. + * + * Then when we hand the subset, it can choose to take a subset of that + * (the starts must coincide), in which case, we go around the loop + * again and ask it to download the next piece. + */ + source = netfs_rreq_prepare_read(rreq, subreq); + if (source == NETFS_INVALID_READ) + goto subreq_failed; + + atomic_inc(&rreq->nr_rd_ops); + + rreq->submitted += subreq->len; + + switch (source) { + case NETFS_FILL_WITH_ZEROES: + netfs_fill_with_zeroes(rreq, subreq); + break; + case NETFS_DOWNLOAD_FROM_SERVER: + netfs_read_from_server(rreq, subreq); + break; + default: + BUG(); + } + + return true; + +subreq_failed: + rreq->error = subreq->error; + netfs_put_subrequest(subreq, false); + return false; +} + +static void netfs_rreq_expand(struct netfs_read_request *rreq, + struct readahead_control *ractl) +{ + /* Give the netfs a chance to change the request parameters. The + * resultant request must contain the original region. + */ + if (rreq->netfs_ops->expand_readahead) + rreq->netfs_ops->expand_readahead(rreq); + + /* Expand the request if the cache wants it to start earlier. Note + * that the expansion may get further extended if the VM wishes to + * insert THPs and the preferred start and/or end wind up in the middle + * of THPs. + * + * If this is the case, however, the THP size should be an integer + * multiple of the cache granule size, so we get a whole number of + * granules to deal with. + */ + if (rreq->start != readahead_pos(ractl) || + rreq->len != readahead_length(ractl)) { + readahead_expand(ractl, rreq->start, rreq->len); + rreq->start = readahead_pos(ractl); + rreq->len = readahead_length(ractl); + } +} + +/** + * netfs_readahead - Helper to manage a read request + * @ractl: The description of the readahead request + * @ops: The network filesystem's operations for the helper to use + * @netfs_priv: Private netfs data to be retained in the request + * + * Fulfil a readahead request by drawing data from the cache if possible, or + * the netfs if not. Space beyond the EOF is zero-filled. Multiple I/O + * requests from different sources will get munged together. If necessary, the + * readahead window can be expanded in either direction to a more convenient + * alighment for RPC efficiency or to make storage in the cache feasible. + * + * The calling netfs must provide a table of operations, only one of which, + * issue_op, is mandatory. It may also be passed a private token, which will + * be retained in rreq->netfs_priv and will be cleaned up by ops->cleanup(). + * + * This is usable whether or not caching is enabled. + */ +void netfs_readahead(struct readahead_control *ractl, + const struct netfs_read_request_ops *ops, + void *netfs_priv) +{ + struct netfs_read_request *rreq; + struct page *page; + unsigned int debug_index = 0; + + _enter("%lx,%x", readahead_index(ractl), readahead_count(ractl)); + + if (readahead_count(ractl) == 0) + goto cleanup; + + rreq = netfs_alloc_read_request(ops, netfs_priv, ractl->file); + if (!rreq) + goto cleanup; + rreq->mapping = ractl->mapping; + rreq->start = readahead_pos(ractl); + rreq->len = readahead_length(ractl); + + netfs_rreq_expand(rreq, ractl); + + atomic_set(&rreq->nr_rd_ops, 1); + do { + if (!netfs_rreq_submit_slice(rreq, &debug_index)) + break; + + } while (rreq->submitted < rreq->len); + + /* Drop the refs on the pages here rather than in the cache or + * filesystem. The locks will be dropped in netfs_rreq_unlock(). + */ + while ((page = readahead_page(ractl))) + put_page(page); + + /* If we decrement nr_rd_ops to 0, the ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_rd_ops)) + netfs_rreq_assess(rreq, false); + return; + +cleanup: + if (netfs_priv) + ops->cleanup(ractl->mapping, netfs_priv); + return; +} +EXPORT_SYMBOL(netfs_readahead); + +/** + * netfs_page - Helper to manage a readpage request + * @file: The file to read from + * @page: The page to read + * @ops: The network filesystem's operations for the helper to use + * @netfs_priv: Private netfs data to be retained in the request + * + * Fulfil a readpage request by drawing data from the cache if possible, or the + * netfs if not. Space beyond the EOF is zero-filled. Multiple I/O requests + * from different sources will get munged together. + * + * The calling netfs must provide a table of operations, only one of which, + * issue_op, is mandatory. It may also be passed a private token, which will + * be retained in rreq->netfs_priv and will be cleaned up by ops->cleanup(). + * + * This is usable whether or not caching is enabled. + */ +int netfs_readpage(struct file *file, + struct page *page, + const struct netfs_read_request_ops *ops, + void *netfs_priv) +{ + struct netfs_read_request *rreq; + unsigned int debug_index = 0; + int ret; + + _enter("%lx", page_index(page)); + + rreq = netfs_alloc_read_request(ops, netfs_priv, file); + if (!rreq) { + if (netfs_priv) + ops->cleanup(netfs_priv, page_file_mapping(page)); + unlock_page(page); + return -ENOMEM; + } + rreq->mapping = page_file_mapping(page); + rreq->start = page_index(page) * PAGE_SIZE; + rreq->len = thp_size(page); + + netfs_get_read_request(rreq); + + atomic_set(&rreq->nr_rd_ops, 1); + do { + if (!netfs_rreq_submit_slice(rreq, &debug_index)) + break; + + } while (rreq->submitted < rreq->len); + + /* Keep nr_rd_ops incremented so that the ref always belongs to us, and + * the service code isn't punted off to a random thread pool to + * process. + */ + do { + wait_var_event(&rreq->nr_rd_ops, atomic_read(&rreq->nr_rd_ops) == 1); + netfs_rreq_assess(rreq, false); + } while (test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)); + + ret = rreq->error; + if (ret == 0 && rreq->submitted < rreq->len) + ret = -EIO; + netfs_put_read_request(rreq, false); + return ret; +} +EXPORT_SYMBOL(netfs_readpage); diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 8479d63406f7b7..59e926e62d2ef8 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -14,6 +14,8 @@ #ifndef _LINUX_NETFS_H #define _LINUX_NETFS_H +#include +#include #include /* @@ -83,4 +85,85 @@ static inline int wait_on_page_fscache_killable(struct page *page) return wait_on_page_private_2_killable(page); } +enum netfs_read_source { + NETFS_FILL_WITH_ZEROES, + NETFS_DOWNLOAD_FROM_SERVER, + NETFS_READ_FROM_CACHE, + NETFS_INVALID_READ, +} __mode(byte); + +/* + * Descriptor for a single component subrequest. + */ +struct netfs_read_subrequest { + struct netfs_read_request *rreq; /* Supervising read request */ + struct list_head rreq_link; /* Link in rreq->subrequests */ + loff_t start; /* Where to start the I/O */ + size_t len; /* Size of the I/O */ + size_t transferred; /* Amount of data transferred */ + refcount_t usage; + short error; /* 0 or error that occurred */ + unsigned short debug_index; /* Index in list (for debugging output) */ + enum netfs_read_source source; /* Where to read from */ + unsigned long flags; +#define NETFS_SREQ_WRITE_TO_CACHE 0 /* Set if should write to cache */ +#define NETFS_SREQ_CLEAR_TAIL 1 /* Set if the rest of the read should be cleared */ +#define NETFS_SREQ_SHORT_READ 2 /* Set if there was a short read from the cache */ +#define NETFS_SREQ_SEEK_DATA_READ 3 /* Set if ->read() should SEEK_DATA first */ +#define NETFS_SREQ_NO_PROGRESS 4 /* Set if we didn't manage to read any data */ +}; + +/* + * Descriptor for a read helper request. This is used to make multiple I/O + * requests on a variety of sources and then stitch the result together. + */ +struct netfs_read_request { + struct work_struct work; + struct inode *inode; /* The file being accessed */ + struct address_space *mapping; /* The mapping being accessed */ + struct list_head subrequests; /* Requests to fetch I/O from disk or net */ + void *netfs_priv; /* Private data for the netfs */ + unsigned int debug_id; + atomic_t nr_rd_ops; /* Number of read ops in progress */ + size_t submitted; /* Amount submitted for I/O so far */ + size_t len; /* Length of the request */ + short error; /* 0 or error that occurred */ + loff_t i_size; /* Size of the file */ + loff_t start; /* Start position */ + pgoff_t no_unlock_page; /* Don't unlock this page after read */ + refcount_t usage; + unsigned long flags; +#define NETFS_RREQ_INCOMPLETE_IO 0 /* Some ioreqs terminated short or with error */ +#define NETFS_RREQ_WRITE_TO_CACHE 1 /* Need to write to the cache */ +#define NETFS_RREQ_NO_UNLOCK_PAGE 2 /* Don't unlock no_unlock_page on completion */ +#define NETFS_RREQ_DONT_UNLOCK_PAGES 3 /* Don't unlock the pages on completion */ +#define NETFS_RREQ_FAILED 4 /* The request failed */ +#define NETFS_RREQ_IN_PROGRESS 5 /* Unlocked when the request completes */ + const struct netfs_read_request_ops *netfs_ops; +}; + +/* + * Operations the network filesystem can/must provide to the helpers. + */ +struct netfs_read_request_ops { + void (*init_rreq)(struct netfs_read_request *rreq, struct file *file); + void (*expand_readahead)(struct netfs_read_request *rreq); + bool (*clamp_length)(struct netfs_read_subrequest *subreq); + void (*issue_op)(struct netfs_read_subrequest *subreq); + bool (*is_still_valid)(struct netfs_read_request *rreq); + void (*done)(struct netfs_read_request *rreq); + void (*cleanup)(struct address_space *mapping, void *netfs_priv); +}; + +struct readahead_control; +extern void netfs_readahead(struct readahead_control *, + const struct netfs_read_request_ops *, + void *); +extern int netfs_readpage(struct file *, + struct page *, + const struct netfs_read_request_ops *, + void *); + +extern void netfs_subreq_terminated(struct netfs_read_subrequest *, ssize_t, bool); + #endif /* _LINUX_NETFS_H */