diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-11-01 18:47:59 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-11-01 18:47:59 +0300 |
commit | 49f8275c7d9247cf1dd4440fc8162f784252c849 (patch) | |
tree | 7caefaa8b68d3162f60ecef7bafacbed0e1056d8 /mm/filemap.c | |
parent | 8bb7eca972ad531c9b149c0a51ab43a417385813 (diff) | |
parent | 121703c1c817b3c77f61002466d0bfca7e39f25d (diff) | |
download | linux-49f8275c7d9247cf1dd4440fc8162f784252c849.tar.xz |
Merge tag 'folio-5.16' of git://git.infradead.org/users/willy/pagecache
Pull memory folios from Matthew Wilcox:
"Add memory folios, a new type to represent either order-0 pages or the
head page of a compound page. This should be enough infrastructure to
support filesystems converting from pages to folios.
The point of all this churn is to allow filesystems and the page cache
to manage memory in larger chunks than PAGE_SIZE. The original plan
was to use compound pages like THP does, but I ran into problems with
some functions expecting only a head page while others expect the
precise page containing a particular byte.
The folio type allows a function to declare that it's expecting only a
head page. Almost incidentally, this allows us to remove various calls
to VM_BUG_ON(PageTail(page)) and compound_head().
This converts just parts of the core MM and the page cache. For 5.17,
we intend to convert various filesystems (XFS and AFS are ready; other
filesystems may make it) and also convert more of the MM and page
cache to folios. For 5.18, multi-page folios should be ready.
The multi-page folios offer some improvement to some workloads. The
80% win is real, but appears to be an artificial benchmark (postgres
startup, which isn't a serious workload). Real workloads (eg building
the kernel, running postgres in a steady state, etc) seem to benefit
between 0-10%. I haven't heard of any performance losses as a result
of this series. Nobody has done any serious performance tuning; I
imagine that tweaking the readahead algorithm could provide some more
interesting wins. There are also other places where we could choose to
create large folios and currently do not, such as writes that are
larger than PAGE_SIZE.
I'd like to thank all my reviewers who've offered review/ack tags:
Christoph Hellwig, David Howells, Jan Kara, Jeff Layton, Johannes
Weiner, Kirill A. Shutemov, Michal Hocko, Mike Rapoport, Vlastimil
Babka, William Kucharski, Yu Zhao and Zi Yan.
I'd also like to thank those who gave feedback I incorporated but
haven't offered up review tags for this part of the series: Nick
Piggin, Mel Gorman, Ming Lei, Darrick Wong, Ted Ts'o, John Hubbard,
Hugh Dickins, and probably a few others who I forget"
* tag 'folio-5.16' of git://git.infradead.org/users/willy/pagecache: (90 commits)
mm/writeback: Add folio_write_one
mm/filemap: Add FGP_STABLE
mm/filemap: Add filemap_get_folio
mm/filemap: Convert mapping_get_entry to return a folio
mm/filemap: Add filemap_add_folio()
mm/filemap: Add filemap_alloc_folio
mm/page_alloc: Add folio allocation functions
mm/lru: Add folio_add_lru()
mm/lru: Convert __pagevec_lru_add_fn to take a folio
mm: Add folio_evictable()
mm/workingset: Convert workingset_refault() to take a folio
mm/filemap: Add readahead_folio()
mm/filemap: Add folio_mkwrite_check_truncate()
mm/filemap: Add i_blocks_per_folio()
mm/writeback: Add folio_redirty_for_writepage()
mm/writeback: Add folio_account_redirty()
mm/writeback: Add folio_clear_dirty_for_io()
mm/writeback: Add folio_cancel_dirty()
mm/writeback: Add folio_account_cleaned()
mm/writeback: Add filemap_dirty_folio()
...
Diffstat (limited to 'mm/filemap.c')
-rw-r--r-- | mm/filemap.c | 567 |
1 files changed, 272 insertions, 295 deletions
diff --git a/mm/filemap.c b/mm/filemap.c index dae481293b5d..3e9feb5cc570 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -835,6 +835,8 @@ EXPORT_SYMBOL(file_write_and_wait_range); */ void replace_page_cache_page(struct page *old, struct page *new) { + struct folio *fold = page_folio(old); + struct folio *fnew = page_folio(new); struct address_space *mapping = old->mapping; void (*freepage)(struct page *) = mapping->a_ops->freepage; pgoff_t offset = old->index; @@ -848,7 +850,7 @@ void replace_page_cache_page(struct page *old, struct page *new) new->mapping = mapping; new->index = offset; - mem_cgroup_migrate(old, new); + mem_cgroup_migrate(fold, fnew); xas_lock_irq(&xas); xas_store(&xas, new); @@ -870,26 +872,25 @@ void replace_page_cache_page(struct page *old, struct page *new) } EXPORT_SYMBOL_GPL(replace_page_cache_page); -noinline int __add_to_page_cache_locked(struct page *page, - struct address_space *mapping, - pgoff_t offset, gfp_t gfp, - void **shadowp) +noinline int __filemap_add_folio(struct address_space *mapping, + struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp) { - XA_STATE(xas, &mapping->i_pages, offset); - int huge = PageHuge(page); + XA_STATE(xas, &mapping->i_pages, index); + int huge = folio_test_hugetlb(folio); int error; bool charged = false; - VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(PageSwapBacked(page), page); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio); mapping_set_update(&xas, mapping); - get_page(page); - page->mapping = mapping; - page->index = offset; + folio_get(folio); + folio->mapping = mapping; + folio->index = index; if (!huge) { - error = mem_cgroup_charge(page, NULL, gfp); + error = mem_cgroup_charge(folio, NULL, gfp); + VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio); if (error) goto error; charged = true; @@ -901,7 +902,7 @@ noinline int __add_to_page_cache_locked(struct page *page, unsigned int order = xa_get_order(xas.xa, xas.xa_index); void *entry, *old = NULL; - if (order > thp_order(page)) + if (order > folio_order(folio)) xas_split_alloc(&xas, xa_load(xas.xa, xas.xa_index), order, gfp); xas_lock_irq(&xas); @@ -918,13 +919,13 @@ noinline int __add_to_page_cache_locked(struct page *page, *shadowp = old; /* entry may have been split before we acquired lock */ order = xa_get_order(xas.xa, xas.xa_index); - if (order > thp_order(page)) { + if (order > folio_order(folio)) { xas_split(&xas, old, order); xas_reset(&xas); } } - xas_store(&xas, page); + xas_store(&xas, folio); if (xas_error(&xas)) goto unlock; @@ -932,7 +933,7 @@ noinline int __add_to_page_cache_locked(struct page *page, /* hugetlb pages do not participate in page cache accounting */ if (!huge) - __inc_lruvec_page_state(page, NR_FILE_PAGES); + __lruvec_stat_add_folio(folio, NR_FILE_PAGES); unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp)); @@ -940,19 +941,19 @@ unlock: if (xas_error(&xas)) { error = xas_error(&xas); if (charged) - mem_cgroup_uncharge(page); + mem_cgroup_uncharge(folio); goto error; } - trace_mm_filemap_add_to_page_cache(page); + trace_mm_filemap_add_to_page_cache(&folio->page); return 0; error: - page->mapping = NULL; + folio->mapping = NULL; /* Leave page->index set: truncation relies upon it */ - put_page(page); + folio_put(folio); return error; } -ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO); +ALLOW_ERROR_INJECTION(__filemap_add_folio, ERRNO); /** * add_to_page_cache_locked - add a locked page to the pagecache @@ -969,59 +970,58 @@ ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO); int add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { - return __add_to_page_cache_locked(page, mapping, offset, + return __filemap_add_folio(mapping, page_folio(page), offset, gfp_mask, NULL); } EXPORT_SYMBOL(add_to_page_cache_locked); -int add_to_page_cache_lru(struct page *page, struct address_space *mapping, - pgoff_t offset, gfp_t gfp_mask) +int filemap_add_folio(struct address_space *mapping, struct folio *folio, + pgoff_t index, gfp_t gfp) { void *shadow = NULL; int ret; - __SetPageLocked(page); - ret = __add_to_page_cache_locked(page, mapping, offset, - gfp_mask, &shadow); + __folio_set_locked(folio); + ret = __filemap_add_folio(mapping, folio, index, gfp, &shadow); if (unlikely(ret)) - __ClearPageLocked(page); + __folio_clear_locked(folio); else { /* - * The page might have been evicted from cache only + * The folio might have been evicted from cache only * recently, in which case it should be activated like - * any other repeatedly accessed page. - * The exception is pages getting rewritten; evicting other + * any other repeatedly accessed folio. + * The exception is folios getting rewritten; evicting other * data from the working set, only to cache data that will * get overwritten with something else, is a waste of memory. */ - WARN_ON_ONCE(PageActive(page)); - if (!(gfp_mask & __GFP_WRITE) && shadow) - workingset_refault(page, shadow); - lru_cache_add(page); + WARN_ON_ONCE(folio_test_active(folio)); + if (!(gfp & __GFP_WRITE) && shadow) + workingset_refault(folio, shadow); + folio_add_lru(folio); } return ret; } -EXPORT_SYMBOL_GPL(add_to_page_cache_lru); +EXPORT_SYMBOL_GPL(filemap_add_folio); #ifdef CONFIG_NUMA -struct page *__page_cache_alloc(gfp_t gfp) +struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order) { int n; - struct page *page; + struct folio *folio; if (cpuset_do_page_mem_spread()) { unsigned int cpuset_mems_cookie; do { cpuset_mems_cookie = read_mems_allowed_begin(); n = cpuset_mem_spread_node(); - page = __alloc_pages_node(n, gfp, 0); - } while (!page && read_mems_allowed_retry(cpuset_mems_cookie)); + folio = __folio_alloc_node(gfp, order, n); + } while (!folio && read_mems_allowed_retry(cpuset_mems_cookie)); - return page; + return folio; } - return alloc_pages(gfp, 0); + return folio_alloc(gfp, order); } -EXPORT_SYMBOL(__page_cache_alloc); +EXPORT_SYMBOL(filemap_alloc_folio); #endif /* @@ -1074,11 +1074,11 @@ EXPORT_SYMBOL(filemap_invalidate_unlock_two); */ #define PAGE_WAIT_TABLE_BITS 8 #define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS) -static wait_queue_head_t page_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned; +static wait_queue_head_t folio_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned; -static wait_queue_head_t *page_waitqueue(struct page *page) +static wait_queue_head_t *folio_waitqueue(struct folio *folio) { - return &page_wait_table[hash_ptr(page, PAGE_WAIT_TABLE_BITS)]; + return &folio_wait_table[hash_ptr(folio, PAGE_WAIT_TABLE_BITS)]; } void __init pagecache_init(void) @@ -1086,7 +1086,7 @@ void __init pagecache_init(void) int i; for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++) - init_waitqueue_head(&page_wait_table[i]); + init_waitqueue_head(&folio_wait_table[i]); page_writeback_init(); } @@ -1141,10 +1141,10 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, */ flags = wait->flags; if (flags & WQ_FLAG_EXCLUSIVE) { - if (test_bit(key->bit_nr, &key->page->flags)) + if (test_bit(key->bit_nr, &key->folio->flags)) return -1; if (flags & WQ_FLAG_CUSTOM) { - if (test_and_set_bit(key->bit_nr, &key->page->flags)) + if (test_and_set_bit(key->bit_nr, &key->folio->flags)) return -1; flags |= WQ_FLAG_DONE; } @@ -1157,7 +1157,7 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, * * So update the flags atomically, and wake up the waiter * afterwards to avoid any races. This store-release pairs - * with the load-acquire in wait_on_page_bit_common(). + * with the load-acquire in folio_wait_bit_common(). */ smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN); wake_up_state(wait->private, mode); @@ -1176,14 +1176,14 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, return (flags & WQ_FLAG_EXCLUSIVE) != 0; } -static void wake_up_page_bit(struct page *page, int bit_nr) +static void folio_wake_bit(struct folio *folio, int bit_nr) { - wait_queue_head_t *q = page_waitqueue(page); + wait_queue_head_t *q = folio_waitqueue(folio); struct wait_page_key key; unsigned long flags; wait_queue_entry_t bookmark; - key.page = page; + key.folio = folio; key.bit_nr = bit_nr; key.page_match = 0; @@ -1218,7 +1218,7 @@ static void wake_up_page_bit(struct page *page, int bit_nr) * page waiters. */ if (!waitqueue_active(q) || !key.page_match) { - ClearPageWaiters(page); + folio_clear_waiters(folio); /* * It's possible to miss clearing Waiters here, when we woke * our page waiters, but the hashed waitqueue has waiters for @@ -1230,19 +1230,19 @@ static void wake_up_page_bit(struct page *page, int bit_nr) spin_unlock_irqrestore(&q->lock, flags); } -static void wake_up_page(struct page *page, int bit) +static void folio_wake(struct folio *folio, int bit) { - if (!PageWaiters(page)) + if (!folio_test_waiters(folio)) return; - wake_up_page_bit(page, bit); + folio_wake_bit(folio, bit); } /* - * A choice of three behaviors for wait_on_page_bit_common(): + * A choice of three behaviors for folio_wait_bit_common(): */ enum behavior { EXCLUSIVE, /* Hold ref to page and take the bit when woken, like - * __lock_page() waiting on then setting PG_locked. + * __folio_lock() waiting on then setting PG_locked. */ SHARED, /* Hold ref to page and check the bit when woken, like * wait_on_page_writeback() waiting on PG_writeback. @@ -1253,16 +1253,16 @@ enum behavior { }; /* - * Attempt to check (or get) the page bit, and mark us done + * Attempt to check (or get) the folio flag, and mark us done * if successful. */ -static inline bool trylock_page_bit_common(struct page *page, int bit_nr, +static inline bool folio_trylock_flag(struct folio *folio, int bit_nr, struct wait_queue_entry *wait) { if (wait->flags & WQ_FLAG_EXCLUSIVE) { - if (test_and_set_bit(bit_nr, &page->flags)) + if (test_and_set_bit(bit_nr, &folio->flags)) return false; - } else if (test_bit(bit_nr, &page->flags)) + } else if (test_bit(bit_nr, &folio->flags)) return false; wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE; @@ -1272,9 +1272,10 @@ static inline bool trylock_page_bit_common(struct page *page, int bit_nr, /* How many times do we accept lock stealing from under a waiter? */ int sysctl_page_lock_unfairness = 5; -static inline int wait_on_page_bit_common(wait_queue_head_t *q, - struct page *page, int bit_nr, int state, enum behavior behavior) +static inline int folio_wait_bit_common(struct folio *folio, int bit_nr, + int state, enum behavior behavior) { + wait_queue_head_t *q = folio_waitqueue(folio); int unfairness = sysctl_page_lock_unfairness; struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; @@ -1283,8 +1284,8 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, unsigned long pflags; if (bit_nr == PG_locked && - !PageUptodate(page) && PageWorkingset(page)) { - if (!PageSwapBacked(page)) { + !folio_test_uptodate(folio) && folio_test_workingset(folio)) { + if (!folio_test_swapbacked(folio)) { delayacct_thrashing_start(); delayacct = true; } @@ -1294,7 +1295,7 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, init_wait(wait); wait->func = wake_page_function; - wait_page.page = page; + wait_page.folio = folio; wait_page.bit_nr = bit_nr; repeat: @@ -1309,7 +1310,7 @@ repeat: * Do one last check whether we can get the * page bit synchronously. * - * Do the SetPageWaiters() marking before that + * Do the folio_set_waiters() marking before that * to let any waker we _just_ missed know they * need to wake us up (otherwise they'll never * even go to the slow case that looks at the @@ -1320,8 +1321,8 @@ repeat: * lock to avoid races. */ spin_lock_irq(&q->lock); - SetPageWaiters(page); - if (!trylock_page_bit_common(page, bit_nr, wait)) + folio_set_waiters(folio); + if (!folio_trylock_flag(folio, bit_nr, wait)) __add_wait_queue_entry_tail(q, wait); spin_unlock_irq(&q->lock); @@ -1331,10 +1332,10 @@ repeat: * see whether the page bit testing has already * been done by the wake function. * - * We can drop our reference to the page. + * We can drop our reference to the folio. */ if (behavior == DROP) - put_page(page); + folio_put(folio); /* * Note that until the "finish_wait()", or until @@ -1371,7 +1372,7 @@ repeat: * * And if that fails, we'll have to retry this all. */ - if (unlikely(test_and_set_bit(bit_nr, &page->flags))) + if (unlikely(test_and_set_bit(bit_nr, folio_flags(folio, 0)))) goto repeat; wait->flags |= WQ_FLAG_DONE; @@ -1380,7 +1381,7 @@ repeat: /* * If a signal happened, this 'finish_wait()' may remove the last - * waiter from the wait-queues, but the PageWaiters bit will remain + * waiter from the wait-queues, but the folio waiters bit will remain * set. That's ok. The next wakeup will take care of it, and trying * to do it here would be difficult and prone to races. */ @@ -1411,19 +1412,17 @@ repeat: return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR; } -void wait_on_page_bit(struct page *page, int bit_nr) +void folio_wait_bit(struct folio *folio, int bit_nr) { - wait_queue_head_t *q = page_waitqueue(page); - wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, SHARED); + folio_wait_bit_common(folio, bit_nr, TASK_UNINTERRUPTIBLE, SHARED); } -EXPORT_SYMBOL(wait_on_page_bit); +EXPORT_SYMBOL(folio_wait_bit); -int wait_on_page_bit_killable(struct page *page, int bit_nr) +int folio_wait_bit_killable(struct folio *folio, int bit_nr) { - wait_queue_head_t *q = page_waitqueue(page); - return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, SHARED); + return folio_wait_bit_common(folio, bit_nr, TASK_KILLABLE, SHARED); } -EXPORT_SYMBOL(wait_on_page_bit_killable); +EXPORT_SYMBOL(folio_wait_bit_killable); /** * put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked @@ -1440,31 +1439,28 @@ EXPORT_SYMBOL(wait_on_page_bit_killable); */ int put_and_wait_on_page_locked(struct page *page, int state) { - wait_queue_head_t *q; - - page = compound_head(page); - q = page_waitqueue(page); - return wait_on_page_bit_common(q, page, PG_locked, state, DROP); + return folio_wait_bit_common(page_folio(page), PG_locked, state, + DROP); } /** - * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue - * @page: Page defining the wait queue of interest + * folio_add_wait_queue - Add an arbitrary waiter to a folio's wait queue + * @folio: Folio defining the wait queue of interest * @waiter: Waiter to add to the queue * - * Add an arbitrary @waiter to the wait queue for the nominated @page. + * Add an arbitrary @waiter to the wait queue for the nominated @folio. */ -void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter) +void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter) { - wait_queue_head_t *q = page_waitqueue(page); + wait_queue_head_t *q = folio_waitqueue(folio); unsigned long flags; spin_lock_irqsave(&q->lock, flags); __add_wait_queue_entry_tail(q, waiter); - SetPageWaiters(page); + folio_set_waiters(folio); spin_unlock_irqrestore(&q->lock, flags); } -EXPORT_SYMBOL_GPL(add_page_wait_queue); +EXPORT_SYMBOL_GPL(folio_add_wait_queue); #ifndef clear_bit_unlock_is_negative_byte @@ -1490,124 +1486,116 @@ static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem #endif /** - * unlock_page - unlock a locked page - * @page: the page + * folio_unlock - Unlock a locked folio. + * @folio: The folio. * - * Unlocks the page and wakes up sleepers in wait_on_page_locked(). - * Also wakes sleepers in wait_on_page_writeback() because the wakeup - * mechanism between PageLocked pages and PageWriteback pages is shared. - * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep. + * Unlocks the folio and wakes up any thread sleeping on the page lock. * - * Note that this depends on PG_waiters being the sign bit in the byte - * that contains PG_locked - thus the BUILD_BUG_ON(). That allows us to - * clear the PG_locked bit and test PG_waiters at the same time fairly - * portably (architectures that do LL/SC can test any bit, while x86 can - * test the sign bit). + * Context: May be called from interrupt or process context. May not be + * called from NMI context. */ -void unlock_page(struct page *page) +void folio_unlock(struct folio *folio) { + /* Bit 7 allows x86 to check the byte's sign bit */ BUILD_BUG_ON(PG_waiters != 7); - page = compound_head(page); - VM_BUG_ON_PAGE(!PageLocked(page), page); - if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags)) - wake_up_page_bit(page, PG_locked); + BUILD_BUG_ON(PG_locked > 7); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + if (clear_bit_unlock_is_negative_byte(PG_locked, folio_flags(folio, 0))) + folio_wake_bit(folio, PG_locked); } -EXPORT_SYMBOL(unlock_page); +EXPORT_SYMBOL(folio_unlock); /** - * end_page_private_2 - Clear PG_private_2 and release any waiters - * @page: The page + * folio_end_private_2 - Clear PG_private_2 and wake any waiters. + * @folio: The folio. * - * Clear the PG_private_2 bit on a page and wake up any sleepers waiting for - * this. The page ref held for PG_private_2 being set is released. + * Clear the PG_private_2 bit on a folio and wake up any sleepers waiting for + * it. The folio reference held for PG_private_2 being set is released. * - * This is, for example, used when a netfs page is being written to a local - * disk cache, thereby allowing writes to the cache for the same page to be + * This is, for example, used when a netfs folio is being written to a local + * disk cache, thereby allowing writes to the cache for the same folio to be * serialised. */ -void end_page_private_2(struct page *page) +void folio_end_private_2(struct folio *folio) { - page = compound_head(page); - VM_BUG_ON_PAGE(!PagePrivate2(page), page); - clear_bit_unlock(PG_private_2, &page->flags); - wake_up_page_bit(page, PG_private_2); - put_page(page); + VM_BUG_ON_FOLIO(!folio_test_private_2(folio), folio); + clear_bit_unlock(PG_private_2, folio_flags(folio, 0)); + folio_wake_bit(folio, PG_private_2); + folio_put(folio); } -EXPORT_SYMBOL(end_page_private_2); +EXPORT_SYMBOL(folio_end_private_2); /** - * wait_on_page_private_2 - Wait for PG_private_2 to be cleared on a page - * @page: The page to wait on + * folio_wait_private_2 - Wait for PG_private_2 to be cleared on a folio. + * @folio: The folio to wait on. * - * Wait for PG_private_2 (aka PG_fscache) to be cleared on a page. + * Wait for PG_private_2 (aka PG_fscache) to be cleared on a folio. */ -void wait_on_page_private_2(struct page *page) +void folio_wait_private_2(struct folio *folio) { - page = compound_head(page); - while (PagePrivate2(page)) - wait_on_page_bit(page, PG_private_2); + while (folio_test_private_2(folio)) + folio_wait_bit(folio, PG_private_2); } -EXPORT_SYMBOL(wait_on_page_private_2); +EXPORT_SYMBOL(folio_wait_private_2); /** - * wait_on_page_private_2_killable - Wait for PG_private_2 to be cleared on a page - * @page: The page to wait on + * folio_wait_private_2_killable - Wait for PG_private_2 to be cleared on a folio. + * @folio: The folio to wait on. * - * Wait for PG_private_2 (aka PG_fscache) to be cleared on a page or until a + * Wait for PG_private_2 (aka PG_fscache) to be cleared on a folio or until a * fatal signal is received by the calling task. * * Return: * - 0 if successful. * - -EINTR if a fatal signal was encountered. */ -int wait_on_page_private_2_killable(struct page *page) +int folio_wait_private_2_killable(struct folio *folio) { int ret = 0; - page = compound_head(page); - while (PagePrivate2(page)) { - ret = wait_on_page_bit_killable(page, PG_private_2); + while (folio_test_private_2(folio)) { + ret = folio_wait_bit_killable(folio, PG_private_2); if (ret < 0) break; } return ret; } -EXPORT_SYMBOL(wait_on_page_private_2_killable); +EXPORT_SYMBOL(folio_wait_private_2_killable); /** - * end_page_writeback - end writeback against a page - * @page: the page + * folio_end_writeback - End writeback against a folio. + * @folio: The folio. */ -void end_page_writeback(struct page *page) +void folio_end_writeback(struct folio *folio) { /* - * TestClearPageReclaim could be used here but it is an atomic - * operation and overkill in this particular case. Failing to - * shuffle a page marked for immediate reclaim is too mild to - * justify taking an atomic operation penalty at the end of - * ever page writeback. + * folio_test_clear_reclaim() could be used here but it is an + * atomic operation and overkill in this particular case. Failing + * to shuffle a folio marked for immediate reclaim is too mild + * a gain to justify taking an atomic operation penalty at the + * end of every folio writeback. */ - if (PageReclaim(page)) { - ClearPageReclaim(page); - rotate_reclaimable_page(page); + if (folio_test_reclaim(folio)) { + folio_clear_reclaim(folio); + folio_rotate_reclaimable(folio); } /* - * Writeback does not hold a page reference of its own, relying + * Writeback does not hold a folio reference of its own, relying * on truncation to wait for the clearing of PG_writeback. - * But here we must make sure that the page is not freed and - * reused before the wake_up_page(). + * But here we must make sure that the folio is not freed and + * reused before the folio_wake(). */ - get_page(page); - if (!test_clear_page_writeback(page)) + folio_get(folio); + if (!__folio_end_writeback(folio)) BUG(); smp_mb__after_atomic(); - wake_up_page(page, PG_writeback); - put_page(page); + folio_wake(folio, PG_writeback); + folio_put(folio); } -EXPORT_SYMBOL(end_page_writeback); +EXPORT_SYMBOL(folio_end_writeback); /* * After completing I/O on a page, call this routine to update the page @@ -1638,39 +1626,35 @@ void page_endio(struct page *page, bool is_write, int err) EXPORT_SYMBOL_GPL(page_endio); /** - * __lock_page - get a lock on the page, assuming we need to sleep to get it - * @__page: the page to lock + * __folio_lock - Get a lock on the folio, assuming we need to sleep to get it. + * @folio: The folio to lock */ -void __lock_page(struct page *__page) +void __folio_lock(struct folio *folio) { - struct page *page = compound_head(__page); - wait_queue_head_t *q = page_waitqueue(page); - wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, + folio_wait_bit_common(folio, PG_locked, TASK_UNINTERRUPTIBLE, EXCLUSIVE); } -EXPORT_SYMBOL(__lock_page); +EXPORT_SYMBOL(__folio_lock); -int __lock_page_killable(struct page *__page) +int __folio_lock_killable(struct folio *folio) { - struct page *page = compound_head(__page); - wait_queue_head_t *q = page_waitqueue(page); - return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE, + return folio_wait_bit_common(folio, PG_locked, TASK_KILLABLE, EXCLUSIVE); } -EXPORT_SYMBOL_GPL(__lock_page_killable); +EXPORT_SYMBOL_GPL(__folio_lock_killable); -int __lock_page_async(struct page *page, struct wait_page_queue *wait) +static int __folio_lock_async(struct folio *folio, struct wait_page_queue *wait) { - struct wait_queue_head *q = page_waitqueue(page); + struct wait_queue_head *q = folio_waitqueue(folio); int ret = 0; - wait->page = page; + wait->folio = folio; wait->bit_nr = PG_locked; spin_lock_irq(&q->lock); __add_wait_queue_entry_tail(q, &wait->wait); - SetPageWaiters(page); - ret = !trylock_page(page); + folio_set_waiters(folio); + ret = !folio_trylock(folio); /* * If we were successful now, we know we're still on the * waitqueue as we're still under the lock. This means it's @@ -1687,16 +1671,16 @@ int __lock_page_async(struct page *page, struct wait_page_queue *wait) /* * Return values: - * 1 - page is locked; mmap_lock is still held. - * 0 - page is not locked. + * true - folio is locked; mmap_lock is still held. + * false - folio is not locked. * mmap_lock has been released (mmap_read_unlock(), unless flags had both * FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_RETRY_NOWAIT set, in * which case mmap_lock is still held. * - * If neither ALLOW_RETRY nor KILLABLE are set, will always return 1 - * with the page locked and the mmap_lock unperturbed. + * If neither ALLOW_RETRY nor KILLABLE are set, will always return true + * with the folio locked and the mmap_lock unperturbed. */ -int __lock_page_or_retry(struct page *page, struct mm_struct *mm, +bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm, unsigned int flags) { if (fault_flag_allow_retry_first(flags)) { @@ -1705,28 +1689,28 @@ int __lock_page_or_retry(struct page *page, struct mm_struct *mm, * even though return 0. */ if (flags & FAULT_FLAG_RETRY_NOWAIT) - return 0; + return false; mmap_read_unlock(mm); if (flags & FAULT_FLAG_KILLABLE) - wait_on_page_locked_killable(page); + folio_wait_locked_killable(folio); else - wait_on_page_locked(page); - return 0; + folio_wait_locked(folio); + return false; } if (flags & FAULT_FLAG_KILLABLE) { - int ret; + bool ret; - ret = __lock_page_killable(page); + ret = __folio_lock_killable(folio); if (ret) { mmap_read_unlock(mm); - return 0; + return false; } } else { - __lock_page(page); + __folio_lock(folio); } - return 1; + return true; } /** @@ -1802,143 +1786,155 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, EXPORT_SYMBOL(page_cache_prev_miss); /* + * Lockless page cache protocol: + * On the lookup side: + * 1. Load the folio from i_pages + * 2. Increment the refcount if it's not zero + * 3. If the folio is not found by xas_reload(), put the refcount and retry + * + * On the removal side: + * A. Freeze the page (by zeroing the refcount if nobody else has a reference) + * B. Remove the page from i_pages + * C. Return the page to the page allocator + * + * This means that any page may have its reference count temporarily + * increased by a speculative page cache (or fast GUP) lookup as it can + * be allocated by another user before the RCU grace period expires. + * Because the refcount temporarily acquired here may end up being the + * last refcount on the page, any page allocation must be freeable by + * folio_put(). + */ + +/* * mapping_get_entry - Get a page cache entry. * @mapping: the address_space to search * @index: The page cache index. * - * Looks up the page cache slot at @mapping & @index. If there is a - * page cache page, the head page is returned with an increased refcount. + * Looks up the page cache entry at @mapping & @index. If it is a folio, + * it is returned with an increased refcount. If it is a shadow entry + * of a previously evicted folio, or a swap entry from shmem/tmpfs, + * it is returned without further action. * - * If the slot holds a shadow entry of a previously evicted page, or a - * swap entry from shmem/tmpfs, it is returned. - * - * Return: The head page or shadow entry, %NULL if nothing is found. + * Return: The folio, swap or shadow entry, %NULL if nothing is found. */ -static struct page *mapping_get_entry(struct address_space *mapping, - pgoff_t index) +static void *mapping_get_entry(struct address_space *mapping, pgoff_t index) { XA_STATE(xas, &mapping->i_pages, index); - struct page *page; + struct folio *folio; rcu_read_lock(); repeat: xas_reset(&xas); - page = xas_load(&xas); - if (xas_retry(&xas, page)) + folio = xas_load(&xas); + if (xas_retry(&xas, folio)) goto repeat; /* * A shadow entry of a recently evicted page, or a swap entry from * shmem/tmpfs. Return it without attempting to raise page count. */ - if (!page || xa_is_value(page)) + if (!folio || xa_is_value(folio)) goto out; - if (!page_cache_get_speculative(page)) + if (!folio_try_get_rcu(folio)) goto repeat; - /* - * Has the page moved or been split? - * This is part of the lockless pagecache protocol. See - * include/linux/pagemap.h for details. - */ - if (unlikely(page != xas_reload(&xas))) { - put_page(page); + if (unlikely(folio != xas_reload(&xas))) { + folio_put(folio); goto repeat; } out: rcu_read_unlock(); - return page; + return folio; } /** - * pagecache_get_page - Find and get a reference to a page. + * __filemap_get_folio - Find and get a reference to a folio. * @mapping: The address_space to search. * @index: The page index. - * @fgp_flags: %FGP flags modify how the page is returned. - * @gfp_mask: Memory allocation flags to use if %FGP_CREAT is specified. + * @fgp_flags: %FGP flags modify how the folio is returned. + * @gfp: Memory allocation flags to use if %FGP_CREAT is specified. * * Looks up the page cache entry at @mapping & @index. * * @fgp_flags can be zero or more of these flags: * - * * %FGP_ACCESSED - The page will be marked accessed. - * * %FGP_LOCK - The page is returned locked. - * * %FGP_HEAD - If the page is present and a THP, return the head page - * rather than the exact page specified by the index. + * * %FGP_ACCESSED - The folio will be marked accessed. + * * %FGP_LOCK - The folio is returned locked. * * %FGP_ENTRY - If there is a shadow / swap / DAX entry, return it - * instead of allocating a new page to replace it. + * instead of allocating a new folio to replace it. * * %FGP_CREAT - If no page is present then a new page is allocated using - * @gfp_mask and added to the page cache and the VM's LRU list. + * @gfp and added to the page cache and the VM's LRU list. * The page is returned locked and with an increased refcount. * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the * page is already in cache. If the page was allocated, unlock it before * returning so the caller can do the same dance. - * * %FGP_WRITE - The page will be written - * * %FGP_NOFS - __GFP_FS will get cleared in gfp mask - * * %FGP_NOWAIT - Don't get blocked by page lock + * * %FGP_WRITE - The page will be written to by the caller. + * * %FGP_NOFS - __GFP_FS will get cleared in gfp. + * * %FGP_NOWAIT - Don't get blocked by page lock. + * * %FGP_STABLE - Wait for the folio to be stable (finished writeback) * * If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even * if the %GFP flags specified for %FGP_CREAT are atomic. * * If there is a page cache page, it is returned with an increased refcount. * - * Return: The found page or %NULL otherwise. + * Return: The found folio or %NULL otherwise. */ -struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, - int fgp_flags, gfp_t gfp_mask) +struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, + int fgp_flags, gfp_t gfp) { - struct page *page; + struct folio *folio; repeat: - page = mapping_get_entry(mapping, index); - if (xa_is_value(page)) { + folio = mapping_get_entry(mapping, index); + if (xa_is_value(folio)) { if (fgp_flags & FGP_ENTRY) - return page; - page = NULL; + return folio; + folio = NULL; } - if (!page) + if (!folio) goto no_page; if (fgp_flags & FGP_LOCK) { if (fgp_flags & FGP_NOWAIT) { - if (!trylock_page(page)) { - put_page(page); + if (!folio_trylock(folio)) { + folio_put(folio); return NULL; } } else { - lock_page(page); + folio_lock(folio); } /* Has the page been truncated? */ - if (unlikely(page->mapping != mapping)) { - unlock_page(page); - put_page(page); + if (unlikely(folio->mapping != mapping)) { + folio_unlock(folio); + folio_put(folio); goto repeat; } - VM_BUG_ON_PAGE(!thp_contains(page, index), page); + VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); } if (fgp_flags & FGP_ACCESSED) - mark_page_accessed(page); + folio_mark_accessed(folio); else if (fgp_flags & FGP_WRITE) { /* Clear idle flag for buffer write */ - if (page_is_idle(page)) - clear_page_idle(page); + if (folio_test_idle(folio)) + folio_clear_idle(folio); } - if (!(fgp_flags & FGP_HEAD)) - page = find_subpage(page, index); + if (fgp_flags & FGP_STABLE) + folio_wait_stable(folio); no_page: - if (!page && (fgp_flags & FGP_CREAT)) { + if (!folio && (fgp_flags & FGP_CREAT)) { int err; if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping)) - gfp_mask |= __GFP_WRITE; + gfp |= __GFP_WRITE; if (fgp_flags & FGP_NOFS) - gfp_mask &= ~__GFP_FS; + gfp &= ~__GFP_FS; - page = __page_cache_alloc(gfp_mask); - if (!page) + folio = filemap_alloc_folio(gfp, 0); + if (!folio) return NULL; if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP)))) @@ -1946,27 +1942,27 @@ no_page: /* Init accessed so avoid atomic mark_page_accessed later */ if (fgp_flags & FGP_ACCESSED) - __SetPageReferenced(page); + __folio_set_referenced(folio); - err = add_to_page_cache_lru(page, mapping, index, gfp_mask); + err = filemap_add_folio(mapping, folio, index, gfp); if (unlikely(err)) { - put_page(page); - page = NULL; + folio_put(folio); + folio = NULL; if (err == -EEXIST) goto repeat; } /* - * add_to_page_cache_lru locks the page, and for mmap we expect - * an unlocked page. + * filemap_add_folio locks the page, and for mmap + * we expect an unlocked page. */ - if (page && (fgp_flags & FGP_FOR_MMAP)) - unlock_page(page); + if (folio && (fgp_flags & FGP_FOR_MMAP)) + folio_unlock(folio); } - return page; + return folio; } -EXPORT_SYMBOL(pagecache_get_page); +EXPORT_SYMBOL(__filemap_get_folio); static inline struct page *find_get_entry(struct xa_state *xas, pgoff_t max, xa_mark_t mark) @@ -2421,6 +2417,7 @@ static int filemap_update_page(struct kiocb *iocb, struct address_space *mapping, struct iov_iter *iter, struct page *page) { + struct folio *folio = page_folio(page); int error; if (iocb->ki_flags & IOCB_NOWAIT) { @@ -2430,40 +2427,40 @@ static int filemap_update_page(struct kiocb *iocb, filemap_invalidate_lock_shared(mapping); } - if (!trylock_page(page)) { + if (!folio_trylock(folio)) { error = -EAGAIN; if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO)) goto unlock_mapping; if (!(iocb->ki_flags & IOCB_WAITQ)) { filemap_invalidate_unlock_shared(mapping); - put_and_wait_on_page_locked(page, TASK_KILLABLE); + put_and_wait_on_page_locked(&folio->page, TASK_KILLABLE); return AOP_TRUNCATED_PAGE; } - error = __lock_page_async(page, iocb->ki_waitq); + error = __folio_lock_async(folio, iocb->ki_waitq); if (error) goto unlock_mapping; } error = AOP_TRUNCATED_PAGE; - if (!page->mapping) + if (!folio->mapping) goto unlock; error = 0; - if (filemap_range_uptodate(mapping, iocb->ki_pos, iter, page)) + if (filemap_range_uptodate(mapping, iocb->ki_pos, iter, &folio->page)) goto unlock; error = -EAGAIN; if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT | IOCB_WAITQ)) goto unlock; - error = filemap_read_page(iocb->ki_filp, mapping, page); + error = filemap_read_page(iocb->ki_filp, mapping, &folio->page); goto unlock_mapping; unlock: - unlock_page(page); + folio_unlock(folio); unlock_mapping: filemap_invalidate_unlock_shared(mapping); if (error == AOP_TRUNCATED_PAGE) - put_page(page); + folio_put(folio); return error; } @@ -2900,7 +2897,9 @@ unlock: static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page, struct file **fpin) { - if (trylock_page(page)) + struct folio *folio = page_folio(page); + + if (folio_trylock(folio)) return 1; /* @@ -2913,7 +2912,7 @@ static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page, *fpin = maybe_unlock_mmap_for_io(vmf, *fpin); if (vmf->flags & FAULT_FLAG_KILLABLE) { - if (__lock_page_killable(page)) { + if (__folio_lock_killable(folio)) { /* * We didn't have the right flags to drop the mmap_lock, * but all fault_handlers only check for fatal signals @@ -2925,11 +2924,11 @@ static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page, return 0; } } else - __lock_page(page); + __folio_lock(folio); + return 1; } - /* * Synchronous readahead happens when we don't even find a page in the page * cache at all. We don't want to perform IO under the mmap sem, so if we have @@ -3708,28 +3707,6 @@ out: } EXPORT_SYMBOL(generic_file_direct_write); -/* - * Find or create a page at the given pagecache position. Return the locked - * page. This function is specifically for buffered writes. - */ -struct page *grab_cache_page_write_begin(struct address_space *mapping, - pgoff_t index, unsigned flags) -{ - struct page *page; - int fgp_flags = FGP_LOCK|FGP_WRITE|FGP_CREAT; - - if (flags & AOP_FLAG_NOFS) - fgp_flags |= FGP_NOFS; - - page = pagecache_get_page(mapping, index, fgp_flags, - mapping_gfp_mask(mapping)); - if (page) - wait_for_stable_page(page); - - return page; -} -EXPORT_SYMBOL(grab_cache_page_write_begin); - ssize_t generic_perform_write(struct file *file, struct iov_iter *i, loff_t pos) { |