diff options
Diffstat (limited to 'mm/readahead.c')
-rw-r--r-- | mm/readahead.c | 514 |
1 files changed, 357 insertions, 157 deletions
diff --git a/mm/readahead.c b/mm/readahead.c index c5b0457415be..2648ec4f0494 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -8,15 +8,120 @@ * Initial version. */ +/** + * DOC: Readahead Overview + * + * Readahead is used to read content into the page cache before it is + * explicitly requested by the application. Readahead only ever + * attempts to read folios that are not yet in the page cache. If a + * folio is present but not up-to-date, readahead will not try to read + * it. In that case a simple ->read_folio() will be requested. + * + * Readahead is triggered when an application read request (whether a + * system call or a page fault) finds that the requested folio is not in + * the page cache, or that it is in the page cache and has the + * readahead flag set. This flag indicates that the folio was read + * as part of a previous readahead request and now that it has been + * accessed, it is time for the next readahead. + * + * Each readahead request is partly synchronous read, and partly async + * readahead. This is reflected in the struct file_ra_state which + * contains ->size being the total number of pages, and ->async_size + * which is the number of pages in the async section. The readahead + * flag will be set on the first folio in this async section to trigger + * a subsequent readahead. Once a series of sequential reads has been + * established, there should be no need for a synchronous component and + * all readahead request will be fully asynchronous. + * + * When either of the triggers causes a readahead, three numbers need + * to be determined: the start of the region to read, the size of the + * region, and the size of the async tail. + * + * The start of the region is simply the first page address at or after + * the accessed address, which is not currently populated in the page + * cache. This is found with a simple search in the page cache. + * + * The size of the async tail is determined by subtracting the size that + * was explicitly requested from the determined request size, unless + * this would be less than zero - then zero is used. NOTE THIS + * CALCULATION IS WRONG WHEN THE START OF THE REGION IS NOT THE ACCESSED + * PAGE. ALSO THIS CALCULATION IS NOT USED CONSISTENTLY. + * + * The size of the region is normally determined from the size of the + * previous readahead which loaded the preceding pages. This may be + * discovered from the struct file_ra_state for simple sequential reads, + * or from examining the state of the page cache when multiple + * sequential reads are interleaved. Specifically: where the readahead + * was triggered by the readahead flag, the size of the previous + * readahead is assumed to be the number of pages from the triggering + * page to the start of the new readahead. In these cases, the size of + * the previous readahead is scaled, often doubled, for the new + * readahead, though see get_next_ra_size() for details. + * + * If the size of the previous read cannot be determined, the number of + * preceding pages in the page cache is used to estimate the size of + * a previous read. This estimate could easily be misled by random + * reads being coincidentally adjacent, so it is ignored unless it is + * larger than the current request, and it is not scaled up, unless it + * is at the start of file. + * + * In general readahead is accelerated at the start of the file, as + * reads from there are often sequential. There are other minor + * adjustments to the readahead size in various special cases and these + * are best discovered by reading the code. + * + * The above calculation, based on the previous readahead size, + * determines the size of the readahead, to which any requested read + * size may be added. + * + * Readahead requests are sent to the filesystem using the ->readahead() + * address space operation, for which mpage_readahead() is a canonical + * implementation. ->readahead() should normally initiate reads on all + * folios, but may fail to read any or all folios without causing an I/O + * error. The page cache reading code will issue a ->read_folio() request + * for any folio which ->readahead() did not read, and only an error + * from this will be final. + * + * ->readahead() will generally call readahead_folio() repeatedly to get + * each folio from those prepared for readahead. It may fail to read a + * folio by: + * + * * not calling readahead_folio() sufficiently many times, effectively + * ignoring some folios, as might be appropriate if the path to + * storage is congested. + * + * * failing to actually submit a read request for a given folio, + * possibly due to insufficient resources, or + * + * * getting an error during subsequent processing of a request. + * + * In the last two cases, the folio should be unlocked by the filesystem + * to indicate that the read attempt has failed. In the first case the + * folio will be unlocked by the VFS. + * + * Those folios not in the final ``async_size`` of the request should be + * considered to be important and ->readahead() should not fail them due + * to congestion or temporary resource unavailability, but should wait + * for necessary resources (e.g. memory or indexing information) to + * become available. Folios in the final ``async_size`` may be + * considered less urgent and failure to read them is more acceptable. + * In this case it is best to use filemap_remove_folio() to remove the + * folios from the page cache as is automatically done for folios that + * were not fetched with readahead_folio(). This will allow a + * subsequent synchronous readahead request to try them again. If they + * are left in the page cache, then they will be read individually using + * ->read_folio() which may be less efficient. + */ + +#include <linux/blkdev.h> #include <linux/kernel.h> #include <linux/dax.h> #include <linux/gfp.h> #include <linux/export.h> -#include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/task_io_accounting_ops.h> -#include <linux/pagevec.h> #include <linux/pagemap.h> +#include <linux/psi.h> #include <linux/syscalls.h> #include <linux/file.h> #include <linux/mm_inline.h> @@ -38,123 +143,49 @@ file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping) } EXPORT_SYMBOL_GPL(file_ra_state_init); -/* - * see if a page needs releasing upon read_cache_pages() failure - * - the caller of read_cache_pages() may have set PG_private or PG_fscache - * before calling, such as the NFS fs marking pages that are cached locally - * on disk, thus we need to give the fs a chance to clean up in the event of - * an error - */ -static void read_cache_pages_invalidate_page(struct address_space *mapping, - struct page *page) -{ - if (page_has_private(page)) { - if (!trylock_page(page)) - BUG(); - page->mapping = mapping; - do_invalidatepage(page, 0, PAGE_SIZE); - page->mapping = NULL; - unlock_page(page); - } - put_page(page); -} - -/* - * release a list of pages, invalidating them first if need be - */ -static void read_cache_pages_invalidate_pages(struct address_space *mapping, - struct list_head *pages) -{ - struct page *victim; - - while (!list_empty(pages)) { - victim = lru_to_page(pages); - list_del(&victim->lru); - read_cache_pages_invalidate_page(mapping, victim); - } -} - -/** - * read_cache_pages - populate an address space with some pages & start reads against them - * @mapping: the address_space - * @pages: The address of a list_head which contains the target pages. These - * pages have their ->index populated and are otherwise uninitialised. - * @filler: callback routine for filling a single page. - * @data: private data for the callback routine. - * - * Hides the details of the LRU cache etc from the filesystems. - * - * Returns: %0 on success, error return by @filler otherwise - */ -int read_cache_pages(struct address_space *mapping, struct list_head *pages, - int (*filler)(void *, struct page *), void *data) -{ - struct page *page; - int ret = 0; - - while (!list_empty(pages)) { - page = lru_to_page(pages); - list_del(&page->lru); - if (add_to_page_cache_lru(page, mapping, page->index, - readahead_gfp_mask(mapping))) { - read_cache_pages_invalidate_page(mapping, page); - continue; - } - put_page(page); - - ret = filler(data, page); - if (unlikely(ret)) { - read_cache_pages_invalidate_pages(mapping, pages); - break; - } - task_io_account_read(PAGE_SIZE); - } - return ret; -} - -EXPORT_SYMBOL(read_cache_pages); - -static void read_pages(struct readahead_control *rac, struct list_head *pages, - bool skip_page) +static void read_pages(struct readahead_control *rac) { const struct address_space_operations *aops = rac->mapping->a_ops; - struct page *page; + struct folio *folio; struct blk_plug plug; if (!readahead_count(rac)) - goto out; + return; + if (unlikely(rac->_workingset)) + psi_memstall_enter(&rac->_pflags); blk_start_plug(&plug); if (aops->readahead) { aops->readahead(rac); - /* Clean up the remaining pages */ - while ((page = readahead_page(rac))) { - unlock_page(page); - put_page(page); + /* + * Clean up the remaining folios. The sizes in ->ra + * may be used to size the next readahead, so make sure + * they accurately reflect what happened. + */ + while ((folio = readahead_folio(rac)) != NULL) { + unsigned long nr = folio_nr_pages(folio); + + folio_get(folio); + rac->ra->size -= nr; + if (rac->ra->async_size >= nr) { + rac->ra->async_size -= nr; + filemap_remove_folio(folio); + } + folio_unlock(folio); + folio_put(folio); } - } else if (aops->readpages) { - aops->readpages(rac->file, rac->mapping, pages, - readahead_count(rac)); - /* Clean up the remaining pages */ - put_pages_list(pages); - rac->_index += rac->_nr_pages; - rac->_nr_pages = 0; } else { - while ((page = readahead_page(rac))) { - aops->readpage(rac->file, page); - put_page(page); - } + while ((folio = readahead_folio(rac)) != NULL) + aops->read_folio(rac->file, folio); } blk_finish_plug(&plug); + if (unlikely(rac->_workingset)) + psi_memstall_leave(&rac->_pflags); + rac->_workingset = false; - BUG_ON(!list_empty(pages)); BUG_ON(readahead_count(rac)); - -out: - if (skip_page) - rac->_index++; } /** @@ -176,7 +207,6 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, { struct address_space *mapping = ractl->mapping; unsigned long index = readahead_index(ractl); - LIST_HEAD(page_pool); gfp_t gfp_mask = readahead_gfp_mask(mapping); unsigned long i; @@ -192,15 +222,14 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, */ unsigned int nofs = memalloc_nofs_save(); + filemap_invalidate_lock_shared(mapping); /* * Preallocate as many pages as we will need. */ for (i = 0; i < nr_to_read; i++) { - struct page *page = xa_load(&mapping->i_pages, index + i); + struct folio *folio = xa_load(&mapping->i_pages, index + i); - BUG_ON(index + i != ractl->_index + ractl->_nr_pages); - - if (page && !xa_is_value(page)) { + if (folio && !xa_is_value(folio)) { /* * Page already present? Kick off the current batch * of contiguous pages before continuing with the @@ -209,33 +238,36 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, * have a stable reference to this page, and it's * not worth getting one just for that. */ - read_pages(ractl, &page_pool, true); + read_pages(ractl); + ractl->_index++; + i = ractl->_index + ractl->_nr_pages - index - 1; continue; } - page = __page_cache_alloc(gfp_mask); - if (!page) + folio = filemap_alloc_folio(gfp_mask, 0); + if (!folio) break; - if (mapping->a_ops->readpages) { - page->index = index + i; - list_add(&page->lru, &page_pool); - } else if (add_to_page_cache_lru(page, mapping, index + i, + if (filemap_add_folio(mapping, folio, index + i, gfp_mask) < 0) { - put_page(page); - read_pages(ractl, &page_pool, true); + folio_put(folio); + read_pages(ractl); + ractl->_index++; + i = ractl->_index + ractl->_nr_pages - index - 1; continue; } if (i == nr_to_read - lookahead_size) - SetPageReadahead(page); + folio_set_readahead(folio); + ractl->_workingset |= folio_test_workingset(folio); ractl->_nr_pages++; } /* - * Now start the IO. We ignore I/O errors - if the page is not - * uptodate then the caller will launch readpage again, and + * Now start the IO. We ignore I/O errors - if the folio is not + * uptodate then the caller will launch read_folio again, and * will then handle the error. */ - read_pages(ractl, &page_pool, false); + read_pages(ractl); + filemap_invalidate_unlock_shared(mapping); memalloc_nofs_restore(nofs); } EXPORT_SYMBOL_GPL(page_cache_ra_unbounded); @@ -246,7 +278,7 @@ EXPORT_SYMBOL_GPL(page_cache_ra_unbounded); * behaviour which would occur if page allocations are causing VM writeback. * We really don't want to intermingle reads and writes like that. */ -void do_page_cache_ra(struct readahead_control *ractl, +static void do_page_cache_ra(struct readahead_control *ractl, unsigned long nr_to_read, unsigned long lookahead_size) { struct inode *inode = ractl->mapping->host; @@ -272,14 +304,14 @@ void do_page_cache_ra(struct readahead_control *ractl, * memory at once. */ void force_page_cache_ra(struct readahead_control *ractl, - struct file_ra_state *ra, unsigned long nr_to_read) + unsigned long nr_to_read) { struct address_space *mapping = ractl->mapping; + struct file_ra_state *ra = ractl->ra; struct backing_dev_info *bdi = inode_to_bdi(mapping->host); unsigned long max_pages, index; - if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages && - !mapping->a_ops->readahead)) + if (unlikely(!mapping->a_ops->read_folio && !mapping->a_ops->readahead)) return; /* @@ -306,7 +338,7 @@ void force_page_cache_ra(struct readahead_control *ractl, * Set the initial window size, round to next power of 2 and square * for small size, x 4 for medium, and x 2 for large * for 128k (32 page) max ra - * 1-8 page = 32k initial, > 8 page = 128k initial + * 1-2 page = 16k, 3-4 page 32k, 5-8 page = 64k, > 8 page = 128k initial */ static unsigned long get_init_ra_size(unsigned long size, unsigned long max) { @@ -396,7 +428,7 @@ static pgoff_t count_history_pages(struct address_space *mapping, } /* - * page cache context based read-ahead + * page cache context based readahead */ static int try_context_readahead(struct address_space *mapping, struct file_ra_state *ra, @@ -429,18 +461,102 @@ static int try_context_readahead(struct address_space *mapping, return 1; } +static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index, + pgoff_t mark, unsigned int order, gfp_t gfp) +{ + int err; + struct folio *folio = filemap_alloc_folio(gfp, order); + + if (!folio) + return -ENOMEM; + mark = round_down(mark, 1UL << order); + if (index == mark) + folio_set_readahead(folio); + err = filemap_add_folio(ractl->mapping, folio, index, gfp); + if (err) { + folio_put(folio); + return err; + } + + ractl->_nr_pages += 1UL << order; + ractl->_workingset |= folio_test_workingset(folio); + return 0; +} + +void page_cache_ra_order(struct readahead_control *ractl, + struct file_ra_state *ra, unsigned int new_order) +{ + struct address_space *mapping = ractl->mapping; + pgoff_t index = readahead_index(ractl); + pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT; + pgoff_t mark = index + ra->size - ra->async_size; + int err = 0; + gfp_t gfp = readahead_gfp_mask(mapping); + + if (!mapping_large_folio_support(mapping) || ra->size < 4) + goto fallback; + + limit = min(limit, index + ra->size - 1); + + if (new_order < MAX_PAGECACHE_ORDER) { + new_order += 2; + if (new_order > MAX_PAGECACHE_ORDER) + new_order = MAX_PAGECACHE_ORDER; + while ((1 << new_order) > ra->size) + new_order--; + } + + filemap_invalidate_lock_shared(mapping); + while (index <= limit) { + unsigned int order = new_order; + + /* Align with smaller pages if needed */ + if (index & ((1UL << order) - 1)) + order = __ffs(index); + /* Don't allocate pages past EOF */ + while (index + (1UL << order) - 1 > limit) + order--; + /* THP machinery does not support order-1 */ + if (order == 1) + order = 0; + err = ra_alloc_folio(ractl, index, mark, order, gfp); + if (err) + break; + index += 1UL << order; + } + + if (index > limit) { + ra->size += index - limit - 1; + ra->async_size += index - limit - 1; + } + + read_pages(ractl); + filemap_invalidate_unlock_shared(mapping); + + /* + * If there were already pages in the page cache, then we may have + * left some gaps. Let the regular readahead code take care of this + * situation. + */ + if (!err) + return; +fallback: + do_page_cache_ra(ractl, ra->size, ra->async_size); +} + /* * A minimal readahead algorithm for trivial sequential/random reads. */ static void ondemand_readahead(struct readahead_control *ractl, - struct file_ra_state *ra, bool hit_readahead_marker, - unsigned long req_size) + struct folio *folio, unsigned long req_size) { struct backing_dev_info *bdi = inode_to_bdi(ractl->mapping->host); + struct file_ra_state *ra = ractl->ra; unsigned long max_pages = ra->ra_pages; unsigned long add_pages; - unsigned long index = readahead_index(ractl); - pgoff_t prev_index; + pgoff_t index = readahead_index(ractl); + pgoff_t expected, prev_index; + unsigned int order = folio ? folio_order(folio) : 0; /* * If the request exceeds the readahead window, allow the read to @@ -459,8 +575,9 @@ static void ondemand_readahead(struct readahead_control *ractl, * It's the expected callback index, assume sequential access. * Ramp up sizes, and push forward the readahead window. */ - if ((index == (ra->start + ra->size - ra->async_size) || - index == (ra->start + ra->size))) { + expected = round_down(ra->start + ra->size - ra->async_size, + 1UL << order); + if (index == expected || index == (ra->start + ra->size)) { ra->start += ra->size; ra->size = get_next_ra_size(ra, max_pages); ra->async_size = ra->size; @@ -468,12 +585,12 @@ static void ondemand_readahead(struct readahead_control *ractl, } /* - * Hit a marked page without valid readahead state. + * Hit a marked folio without valid readahead state. * E.g. interleaved reads. * Query the pagecache for async_size, which normally equals to * readahead size. Ramp it up and use it as the new readahead size. */ - if (hit_readahead_marker) { + if (folio) { pgoff_t start; rcu_read_lock(); @@ -546,21 +663,21 @@ readit: } ractl->_index = ra->start; - do_page_cache_ra(ractl, ra->size, ra->async_size); + page_cache_ra_order(ractl, ra, order); } void page_cache_sync_ra(struct readahead_control *ractl, - struct file_ra_state *ra, unsigned long req_count) + unsigned long req_count) { bool do_forced_ra = ractl->file && (ractl->file->f_mode & FMODE_RANDOM); /* - * Even if read-ahead is disabled, issue this request as read-ahead + * Even if readahead is disabled, issue this request as readahead * as we'll need it to satisfy the requested range. The forced - * read-ahead will do the right thing and limit the read to just the + * readahead will do the right thing and limit the read to just the * requested range, which we'll set to 1 page for this case. */ - if (!ra->ra_pages || blk_cgroup_congested()) { + if (!ractl->ra->ra_pages || blk_cgroup_congested()) { if (!ractl->file) return; req_count = 1; @@ -569,42 +686,33 @@ void page_cache_sync_ra(struct readahead_control *ractl, /* be dumb */ if (do_forced_ra) { - force_page_cache_ra(ractl, ra, req_count); + force_page_cache_ra(ractl, req_count); return; } - /* do read-ahead */ - ondemand_readahead(ractl, ra, false, req_count); + ondemand_readahead(ractl, NULL, req_count); } EXPORT_SYMBOL_GPL(page_cache_sync_ra); void page_cache_async_ra(struct readahead_control *ractl, - struct file_ra_state *ra, struct page *page, - unsigned long req_count) + struct folio *folio, unsigned long req_count) { - /* no read-ahead */ - if (!ra->ra_pages) + /* no readahead */ + if (!ractl->ra->ra_pages) return; /* * Same bit is used for PG_readahead and PG_reclaim. */ - if (PageWriteback(page)) + if (folio_test_writeback(folio)) return; - ClearPageReadahead(page); - - /* - * Defer asynchronous read-ahead on IO congestion. - */ - if (inode_read_congested(ractl->mapping->host)) - return; + folio_clear_readahead(folio); if (blk_cgroup_congested()) return; - /* do read-ahead */ - ondemand_readahead(ractl, ra, true, req_count); + ondemand_readahead(ractl, folio, req_count); } EXPORT_SYMBOL_GPL(page_cache_async_ra); @@ -625,7 +733,8 @@ ssize_t ksys_readahead(int fd, loff_t offset, size_t count) */ ret = -EINVAL; if (!f.file->f_mapping || !f.file->f_mapping->a_ops || - !S_ISREG(file_inode(f.file)->i_mode)) + (!S_ISREG(file_inode(f.file)->i_mode) && + !S_ISBLK(file_inode(f.file)->i_mode))) goto out; ret = vfs_fadvise(f.file, offset, count, POSIX_FADV_WILLNEED); @@ -638,3 +747,94 @@ SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count) { return ksys_readahead(fd, offset, count); } + +#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_READAHEAD) +COMPAT_SYSCALL_DEFINE4(readahead, int, fd, compat_arg_u64_dual(offset), size_t, count) +{ + return ksys_readahead(fd, compat_arg_u64_glue(offset), count); +} +#endif + +/** + * readahead_expand - Expand a readahead request + * @ractl: The request to be expanded + * @new_start: The revised start + * @new_len: The revised size of the request + * + * Attempt to expand a readahead request outwards from the current size to the + * specified size by inserting locked pages before and after the current window + * to increase the size to the new window. This may involve the insertion of + * THPs, in which case the window may get expanded even beyond what was + * requested. + * + * The algorithm will stop if it encounters a conflicting page already in the + * pagecache and leave a smaller expansion than requested. + * + * The caller must check for this by examining the revised @ractl object for a + * different expansion than was requested. + */ +void readahead_expand(struct readahead_control *ractl, + loff_t new_start, size_t new_len) +{ + struct address_space *mapping = ractl->mapping; + struct file_ra_state *ra = ractl->ra; + pgoff_t new_index, new_nr_pages; + gfp_t gfp_mask = readahead_gfp_mask(mapping); + + new_index = new_start / PAGE_SIZE; + + /* Expand the leading edge downwards */ + while (ractl->_index > new_index) { + unsigned long index = ractl->_index - 1; + struct folio *folio = xa_load(&mapping->i_pages, index); + + if (folio && !xa_is_value(folio)) + return; /* Folio apparently present */ + + folio = filemap_alloc_folio(gfp_mask, 0); + if (!folio) + return; + if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) { + folio_put(folio); + return; + } + if (unlikely(folio_test_workingset(folio)) && + !ractl->_workingset) { + ractl->_workingset = true; + psi_memstall_enter(&ractl->_pflags); + } + ractl->_nr_pages++; + ractl->_index = folio->index; + } + + new_len += new_start - readahead_pos(ractl); + new_nr_pages = DIV_ROUND_UP(new_len, PAGE_SIZE); + + /* Expand the trailing edge upwards */ + while (ractl->_nr_pages < new_nr_pages) { + unsigned long index = ractl->_index + ractl->_nr_pages; + struct folio *folio = xa_load(&mapping->i_pages, index); + + if (folio && !xa_is_value(folio)) + return; /* Folio apparently present */ + + folio = filemap_alloc_folio(gfp_mask, 0); + if (!folio) + return; + if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) { + folio_put(folio); + return; + } + if (unlikely(folio_test_workingset(folio)) && + !ractl->_workingset) { + ractl->_workingset = true; + psi_memstall_enter(&ractl->_pflags); + } + ractl->_nr_pages++; + if (ra) { + ra->size++; + ra->async_size++; + } + } +} +EXPORT_SYMBOL(readahead_expand); |