From 2e85abf053b99a6488f1b529d7aa3b8d7478adae Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 22 May 2020 08:59:42 -0600 Subject: mm: allow read-ahead with IOCB_NOWAIT set The read-ahead shouldn't block, so allow it to be done even if IOCB_NOWAIT is set in the kiocb. Acked-by: Johannes Weiner Signed-off-by: Jens Axboe --- mm/filemap.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index f0ae9a6308cb..3378d4fca883 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2028,8 +2028,6 @@ find_page: page = find_get_page(mapping, index); if (!page) { - if (iocb->ki_flags & IOCB_NOWAIT) - goto would_block; page_cache_sync_readahead(mapping, ra, filp, index, last_index - index); -- cgit v1.2.3 From c7510ab2cf5ccd997fe7f194edfe09cc511abf99 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 23 May 2020 08:22:14 -0600 Subject: mm: abstract out wake_page_match() from wake_page_function() No functional changes in this patch, just in preparation for allowing more callers. Acked-by: Johannes Weiner Signed-off-by: Jens Axboe --- include/linux/pagemap.h | 37 +++++++++++++++++++++++++++++++++++++ mm/filemap.c | 35 ++++------------------------------- 2 files changed, 41 insertions(+), 31 deletions(-) (limited to 'mm/filemap.c') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index cf2468da68e9..2f18221bb5c8 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -496,6 +496,43 @@ static inline pgoff_t linear_page_index(struct vm_area_struct *vma, return pgoff; } +/* This has the same layout as wait_bit_key - see fs/cachefiles/rdwr.c */ +struct wait_page_key { + struct page *page; + int bit_nr; + int page_match; +}; + +struct wait_page_queue { + struct page *page; + int bit_nr; + wait_queue_entry_t wait; +}; + +static inline int wake_page_match(struct wait_page_queue *wait_page, + struct wait_page_key *key) +{ + if (wait_page->page != key->page) + return 0; + key->page_match = 1; + + if (wait_page->bit_nr != key->bit_nr) + return 0; + + /* + * Stop walking if it's locked. + * Is this safe if put_and_wait_on_page_locked() is in use? + * Yes: the waker must hold a reference to this page, and if PG_locked + * has now already been set by another task, that task must also hold + * a reference to the *same usage* of this page; so there is no need + * to walk on to wake even the put_and_wait_on_page_locked() callers. + */ + if (test_bit(key->bit_nr, &key->page->flags)) + return -1; + + return 1; +} + extern void __lock_page(struct page *page); extern int __lock_page_killable(struct page *page); extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm, diff --git a/mm/filemap.c b/mm/filemap.c index 3378d4fca883..c3175dbd8fba 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -987,43 +987,16 @@ void __init pagecache_init(void) page_writeback_init(); } -/* This has the same layout as wait_bit_key - see fs/cachefiles/rdwr.c */ -struct wait_page_key { - struct page *page; - int bit_nr; - int page_match; -}; - -struct wait_page_queue { - struct page *page; - int bit_nr; - wait_queue_entry_t wait; -}; - static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg) { struct wait_page_key *key = arg; struct wait_page_queue *wait_page = container_of(wait, struct wait_page_queue, wait); + int ret; - if (wait_page->page != key->page) - return 0; - key->page_match = 1; - - if (wait_page->bit_nr != key->bit_nr) - return 0; - - /* - * Stop walking if it's locked. - * Is this safe if put_and_wait_on_page_locked() is in use? - * Yes: the waker must hold a reference to this page, and if PG_locked - * has now already been set by another task, that task must also hold - * a reference to the *same usage* of this page; so there is no need - * to walk on to wake even the put_and_wait_on_page_locked() callers. - */ - if (test_bit(key->bit_nr, &key->page->flags)) - return -1; - + ret = wake_page_match(wait_page, key); + if (ret != 1) + return ret; return autoremove_wake_function(wait, mode, sync, key); } -- cgit v1.2.3 From dd3e6d5039de1cbff4e20e2b34390ff44cdb182f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 22 May 2020 09:12:09 -0600 Subject: mm: add support for async page locking Normally waiting for a page to become unlocked, or locking the page, requires waiting for IO to complete. Add support for lock_page_async() and wait_on_page_locked_async(), which are callback based instead. This allows a caller to get notified when a page becomes unlocked, rather than wait for it. We add a new iocb field, ki_waitq, to pass in the necessary data for this to happen. We can unionize this with ki_cookie, since that is only used for polled IO. Polled IO can never co-exist with async callbacks, as it is (by definition) polled completions. struct wait_page_key is made public, and we define struct wait_page_async as the interface between the caller and the core. Acked-by: Johannes Weiner Signed-off-by: Jens Axboe --- include/linux/fs.h | 7 ++++++- include/linux/pagemap.h | 17 +++++++++++++++++ mm/filemap.c | 45 ++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 67 insertions(+), 2 deletions(-) (limited to 'mm/filemap.c') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3f881a892ea7..2a5cf6080e68 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -315,6 +315,8 @@ enum rw_hint { #define IOCB_SYNC (1 << 5) #define IOCB_WRITE (1 << 6) #define IOCB_NOWAIT (1 << 7) +/* iocb->ki_waitq is valid */ +#define IOCB_WAITQ (1 << 8) struct kiocb { struct file *ki_filp; @@ -328,7 +330,10 @@ struct kiocb { int ki_flags; u16 ki_hint; u16 ki_ioprio; /* See linux/ioprio.h */ - unsigned int ki_cookie; /* for ->iopoll */ + union { + unsigned int ki_cookie; /* for ->iopoll */ + struct wait_page_queue *ki_waitq; /* for async buffered IO */ + }; randomized_struct_fields_end }; diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 2f18221bb5c8..e053e1d9a4d7 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -535,6 +535,7 @@ static inline int wake_page_match(struct wait_page_queue *wait_page, extern void __lock_page(struct page *page); extern int __lock_page_killable(struct page *page); +extern int __lock_page_async(struct page *page, struct wait_page_queue *wait); extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags); extern void unlock_page(struct page *page); @@ -571,6 +572,22 @@ static inline int lock_page_killable(struct page *page) return 0; } +/* + * lock_page_async - Lock the page, unless this would block. If the page + * is already locked, then queue a callback when the page becomes unlocked. + * This callback can then retry the operation. + * + * Returns 0 if the page is locked successfully, or -EIOCBQUEUED if the page + * was already locked and the callback defined in 'wait' was queued. + */ +static inline int lock_page_async(struct page *page, + struct wait_page_queue *wait) +{ + if (!trylock_page(page)) + return __lock_page_async(page, wait); + return 0; +} + /* * lock_page_or_retry - Lock the page, unless this would block and the * caller indicated that it can handle a retry. diff --git a/mm/filemap.c b/mm/filemap.c index c3175dbd8fba..e8aaf43bee9f 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1180,6 +1180,36 @@ int wait_on_page_bit_killable(struct page *page, int bit_nr) } EXPORT_SYMBOL(wait_on_page_bit_killable); +static int __wait_on_page_locked_async(struct page *page, + struct wait_page_queue *wait, bool set) +{ + struct wait_queue_head *q = page_waitqueue(page); + int ret = 0; + + wait->page = page; + wait->bit_nr = PG_locked; + + spin_lock_irq(&q->lock); + __add_wait_queue_entry_tail(q, &wait->wait); + SetPageWaiters(page); + if (set) + ret = !trylock_page(page); + else + ret = PageLocked(page); + /* + * If we were succesful now, we know we're still on the + * waitqueue as we're still under the lock. This means it's + * safe to remove and return success, we know the callback + * isn't going to trigger. + */ + if (!ret) + __remove_wait_queue(q, &wait->wait); + else + ret = -EIOCBQUEUED; + spin_unlock_irq(&q->lock); + return ret; +} + /** * put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked * @page: The page to wait for. @@ -1342,6 +1372,11 @@ int __lock_page_killable(struct page *__page) } EXPORT_SYMBOL_GPL(__lock_page_killable); +int __lock_page_async(struct page *page, struct wait_page_queue *wait) +{ + return __wait_on_page_locked_async(page, wait, true); +} + /* * Return values: * 1 - page is locked; mmap_lock is still held. @@ -2131,6 +2166,11 @@ page_not_up_to_date_locked: } readpage: + if (iocb->ki_flags & IOCB_NOWAIT) { + unlock_page(page); + put_page(page); + goto would_block; + } /* * A previous I/O error may have been due to temporary * failures, eg. multipath errors. @@ -2150,7 +2190,10 @@ readpage: } if (!PageUptodate(page)) { - error = lock_page_killable(page); + if (iocb->ki_flags & IOCB_WAITQ) + error = lock_page_async(page, iocb->ki_waitq); + else + error = lock_page_killable(page); if (unlikely(error)) goto readpage_error; if (!PageUptodate(page)) { -- cgit v1.2.3 From 1a0a7853b901c35a742b3bf176cf4701a5c5817c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 22 May 2020 09:18:38 -0600 Subject: mm: support async buffered reads in generic_file_buffered_read() Use the async page locking infrastructure, if IOCB_WAITQ is set in the passed in iocb. The caller must expect an -EIOCBQUEUED return value, which means that IO is started but not done yet. This is similar to how O_DIRECT signals the same operation. Once the callback is received by the caller for IO completion, the caller must retry the operation. Acked-by: Johannes Weiner Signed-off-by: Jens Axboe --- mm/filemap.c | 38 +++++++++++++++++++++++++++----------- 1 file changed, 27 insertions(+), 11 deletions(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index e8aaf43bee9f..a5b1fa8f7ce4 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1210,6 +1210,14 @@ static int __wait_on_page_locked_async(struct page *page, return ret; } +static int wait_on_page_locked_async(struct page *page, + struct wait_page_queue *wait) +{ + if (!PageLocked(page)) + return 0; + return __wait_on_page_locked_async(compound_head(page), wait, false); +} + /** * put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked * @page: The page to wait for. @@ -2049,17 +2057,25 @@ find_page: index, last_index - index); } if (!PageUptodate(page)) { - if (iocb->ki_flags & IOCB_NOWAIT) { - put_page(page); - goto would_block; - } - /* * See comment in do_read_cache_page on why * wait_on_page_locked is used to avoid unnecessarily * serialisations and why it's safe. */ - error = wait_on_page_locked_killable(page); + if (iocb->ki_flags & IOCB_WAITQ) { + if (written) { + put_page(page); + goto out; + } + error = wait_on_page_locked_async(page, + iocb->ki_waitq); + } else { + if (iocb->ki_flags & IOCB_NOWAIT) { + put_page(page); + goto would_block; + } + error = wait_on_page_locked_killable(page); + } if (unlikely(error)) goto readpage_error; if (PageUptodate(page)) @@ -2147,7 +2163,10 @@ page_ok: page_not_up_to_date: /* Get exclusive access to the page ... */ - error = lock_page_killable(page); + if (iocb->ki_flags & IOCB_WAITQ) + error = lock_page_async(page, iocb->ki_waitq); + else + error = lock_page_killable(page); if (unlikely(error)) goto readpage_error; @@ -2190,10 +2209,7 @@ readpage: } if (!PageUptodate(page)) { - if (iocb->ki_flags & IOCB_WAITQ) - error = lock_page_async(page, iocb->ki_waitq); - else - error = lock_page_killable(page); + error = lock_page_killable(page); if (unlikely(error)) goto readpage_error; if (!PageUptodate(page)) { -- cgit v1.2.3