The patch titled Subject: linux-next-rejects has been added to the -mm tree. Its filename is linux-next-rejects.patch This patch should soon appear at https://ozlabs.org/~akpm/mmots/broken-out/linux-next-rejects.patch and later at https://ozlabs.org/~akpm/mmotm/broken-out/linux-next-rejects.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next and is updated there every 3-4 working days ------------------------------------------------------ From: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> Subject: linux-next-rejects Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/memcontrol.h | 17 +--- mm/memcontrol.c | 89 ++++++++++----------- mm/page-writeback.c | 145 ++++++++++++++++++++--------------- 3 files changed, 135 insertions(+), 116 deletions(-) --- a/include/linux/memcontrol.h~linux-next-rejects +++ a/include/linux/memcontrol.h @@ -704,26 +704,25 @@ static inline bool mem_cgroup_below_min( page_counter_read(&memcg->memory); } -int __mem_cgroup_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask); -static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask) +int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp); +static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, + gfp_t gfp) { if (mem_cgroup_disabled()) return 0; - return __mem_cgroup_charge(page, mm, gfp_mask); + return __mem_cgroup_charge(folio, mm, gfp); } int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry); void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry); -void __mem_cgroup_uncharge(struct page *page); -static inline void mem_cgroup_uncharge(struct page *page) +void __mem_cgroup_uncharge(struct folio *folio); +static inline void mem_cgroup_uncharge(struct folio *folio) { if (mem_cgroup_disabled()) return; - __mem_cgroup_uncharge(page); + __mem_cgroup_uncharge(folio); } void __mem_cgroup_uncharge_list(struct list_head *page_list); @@ -734,7 +733,7 @@ static inline void mem_cgroup_uncharge_l __mem_cgroup_uncharge_list(page_list); } -void mem_cgroup_migrate(struct page *oldpage, struct page *newpage); +void mem_cgroup_migrate(struct folio *old, struct folio *new); /** * mem_cgroup_lruvec - get the lru list vector for a memcg & node --- a/mm/memcontrol.c~linux-next-rejects +++ a/mm/memcontrol.c @@ -6675,9 +6675,10 @@ void mem_cgroup_calculate_protection(str atomic_long_read(&parent->memory.children_low_usage))); } -static int charge_memcg(struct page *page, struct mem_cgroup *memcg, gfp_t gfp) +static int charge_memcg(struct folio *folio, struct mem_cgroup *memcg, + gfp_t gfp) { - unsigned int nr_pages = thp_nr_pages(page); + unsigned int nr_pages = folio_nr_pages(folio); int ret; ret = try_charge(memcg, gfp, nr_pages); @@ -6685,38 +6686,37 @@ static int charge_memcg(struct page *pag goto out; css_get(&memcg->css); - commit_charge(page, memcg); + commit_charge(folio, memcg); local_irq_disable(); - mem_cgroup_charge_statistics(memcg, page, nr_pages); - memcg_check_events(memcg, page); + mem_cgroup_charge_statistics(memcg, nr_pages); + memcg_check_events(memcg, folio_nid(folio)); local_irq_enable(); out: return ret; } /** - * __mem_cgroup_charge - charge a newly allocated page to a cgroup - * @page: page to charge - * @mm: mm context of the victim - * @gfp_mask: reclaim mode + * __mem_cgroup_charge - Charge a newly allocated folio to a cgroup. + * @folio: Folio to charge. + * @mm: mm context of the allocating task. + * @gfp: Reclaim mode. * - * Try to charge @page to the memcg that @mm belongs to, reclaiming - * pages according to @gfp_mask if necessary. if @mm is NULL, try to + * Try to charge @folio to the memcg that @mm belongs to, reclaiming + * pages according to @gfp if necessary. If @mm is NULL, try to * charge to the active memcg. * - * Do not use this for pages allocated for swapin. + * Do not use this for folios allocated for swapin. * - * Returns 0 on success. Otherwise, an error code is returned. + * Return: 0 on success. Otherwise, an error code is returned. */ -int __mem_cgroup_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask) +int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp) { struct mem_cgroup *memcg; int ret; memcg = get_mem_cgroup_from_mm(mm); - ret = charge_memcg(page, memcg, gfp_mask); + ret = charge_memcg(folio, memcg, gfp); css_put(&memcg->css); return ret; @@ -6752,7 +6752,7 @@ int mem_cgroup_swapin_charge_page(struct memcg = get_mem_cgroup_from_mm(mm); rcu_read_unlock(); - ret = charge_memcg(page, memcg, gfp); + ret = charge_memcg(folio, memcg, gfp); css_put(&memcg->css); return ret; @@ -6881,28 +6881,28 @@ static void uncharge_folio(struct folio ug->nr_memory += nr_pages; ug->pgpgout++; - page->memcg_data = 0; + folio->memcg_data = 0; } css_put(&memcg->css); } /** - * __mem_cgroup_uncharge - uncharge a page - * @page: page to uncharge + * __mem_cgroup_uncharge - Uncharge a folio. + * @folio: Folio to uncharge. * - * Uncharge a page previously charged with __mem_cgroup_charge(). + * Uncharge a folio previously charged with mem_cgroup_charge(). */ -void __mem_cgroup_uncharge(struct page *page) +void __mem_cgroup_uncharge(struct folio *folio) { struct uncharge_gather ug; - /* Don't touch page->lru of any random page, pre-check: */ - if (!page_memcg(page)) + /* Don't touch folio->lru of any random page, pre-check: */ + if (!folio_memcg(folio)) return; uncharge_gather_clear(&ug); - uncharge_page(page, &ug); + uncharge_folio(folio, &ug); uncharge_batch(&ug); } @@ -6916,52 +6916,49 @@ void __mem_cgroup_uncharge(struct page * void __mem_cgroup_uncharge_list(struct list_head *page_list) { struct uncharge_gather ug; - struct page *page; + struct folio *folio; uncharge_gather_clear(&ug); - list_for_each_entry(page, page_list, lru) - uncharge_page(page, &ug); + list_for_each_entry(folio, page_list, lru) + uncharge_folio(folio, &ug); if (ug.memcg) uncharge_batch(&ug); } /** - * mem_cgroup_migrate - charge a page's replacement - * @oldpage: currently circulating page - * @newpage: replacement page + * mem_cgroup_migrate - Charge a folio's replacement. + * @old: Currently circulating folio. + * @new: Replacement folio. * - * Charge @newpage as a replacement page for @oldpage. @oldpage will + * Charge @new as a replacement folio for @old. @old will * be uncharged upon free. * - * Both pages must be locked, @newpage->mapping must be set up. + * Both folios must be locked, @new->mapping must be set up. */ -void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) +void mem_cgroup_migrate(struct folio *old, struct folio *new) { struct mem_cgroup *memcg; - unsigned int nr_pages; + unsigned int nr_pages = folio_nr_pages(new); unsigned long flags; - VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage); - VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); - VM_BUG_ON_PAGE(PageAnon(oldpage) != PageAnon(newpage), newpage); - VM_BUG_ON_PAGE(PageTransHuge(oldpage) != PageTransHuge(newpage), - newpage); + VM_BUG_ON_FOLIO(!folio_test_locked(old), old); + VM_BUG_ON_FOLIO(!folio_test_locked(new), new); + VM_BUG_ON_FOLIO(folio_test_anon(old) != folio_test_anon(new), new); + VM_BUG_ON_FOLIO(folio_nr_pages(old) != nr_pages, new); if (mem_cgroup_disabled()) return; - /* Page cache replacement: new page already charged? */ - if (page_memcg(newpage)) + /* Page cache replacement: new folio already charged? */ + if (folio_memcg(new)) return; - memcg = page_memcg(oldpage); - VM_WARN_ON_ONCE_PAGE(!memcg, oldpage); + memcg = folio_memcg(old); + VM_WARN_ON_ONCE_FOLIO(!memcg, old); if (!memcg) return; /* Force-charge the new page. The old one will be freed soon */ - nr_pages = thp_nr_pages(newpage); - if (!mem_cgroup_is_root(memcg)) { page_counter_charge(&memcg->memory, nr_pages); if (do_memsw_account()) --- a/mm/page-writeback.c~linux-next-rejects +++ a/mm/page-writeback.c @@ -2723,48 +2723,49 @@ bool folio_clear_dirty_for_io(struct fol * We use this sequence to make sure that * (a) we account for dirty stats properly * (b) we tell the low-level filesystem to - * mark the whole page dirty if it was + * mark the whole folio dirty if it was * dirty in a pagetable. Only to then - * (c) clean the page again and return 1 to + * (c) clean the folio again and return 1 to * cause the writeback. * * This way we avoid all nasty races with the * dirty bit in multiple places and clearing * them concurrently from different threads. * - * Note! Normally the "set_page_dirty(page)" + * Note! Normally the "folio_mark_dirty(folio)" * has no effect on the actual dirty bit - since * that will already usually be set. But we * need the side effects, and it can help us * avoid races. * - * We basically use the page "master dirty bit" + * We basically use the folio "master dirty bit" * as a serialization point for all the different * threads doing their things. */ - if (page_mkclean(page)) - set_page_dirty(page); + if (folio_mkclean(folio)) + folio_mark_dirty(folio); /* * We carefully synchronise fault handlers against - * installing a dirty pte and marking the page dirty + * installing a dirty pte and marking the folio dirty * at this point. We do this by having them hold the - * page lock while dirtying the page, and pages are + * page lock while dirtying the folio, and folios are * always locked coming in here, so we get the desired * exclusion. */ wb = unlocked_inode_to_wb_begin(inode, &cookie); - if (TestClearPageDirty(page)) { - dec_lruvec_page_state(page, NR_FILE_DIRTY); - dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); - dec_wb_stat(wb, WB_RECLAIMABLE); - ret = 1; + if (folio_test_clear_dirty(folio)) { + long nr = folio_nr_pages(folio); + lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr); + zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); + wb_stat_mod(wb, WB_RECLAIMABLE, -nr); + ret = true; } unlocked_inode_to_wb_end(inode, &cookie); return ret; } - return TestClearPageDirty(page); + return folio_test_clear_dirty(folio); } -EXPORT_SYMBOL(clear_page_dirty_for_io); +EXPORT_SYMBOL(folio_clear_dirty_for_io); static void wb_inode_writeback_start(struct bdi_writeback *wb) { @@ -2784,27 +2785,28 @@ static void wb_inode_writeback_end(struc queue_delayed_work(bdi_wq, &wb->bw_dwork, BANDWIDTH_INTERVAL); } -int test_clear_page_writeback(struct page *page) +bool __folio_end_writeback(struct folio *folio) { - struct address_space *mapping = page_mapping(page); - int ret; + long nr = folio_nr_pages(folio); + struct address_space *mapping = folio_mapping(folio); + bool ret; - lock_page_memcg(page); + folio_memcg_lock(folio); if (mapping && mapping_use_writeback_tags(mapping)) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); - ret = TestClearPageWriteback(page); + ret = folio_test_clear_writeback(folio); if (ret) { - __xa_clear_mark(&mapping->i_pages, page_index(page), + __xa_clear_mark(&mapping->i_pages, folio_index(folio), PAGECACHE_TAG_WRITEBACK); if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { struct bdi_writeback *wb = inode_to_wb(inode); - dec_wb_stat(wb, WB_WRITEBACK); - __wb_writeout_inc(wb); + wb_stat_mod(wb, WB_WRITEBACK, -nr); + __wb_writeout_add(wb, nr); if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) wb_inode_writeback_end(wb); @@ -2855,84 +2857,105 @@ bool __folio_start_writeback(struct foli if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { struct bdi_writeback *wb = inode_to_wb(inode); - inc_wb_stat(wb, WB_WRITEBACK); + wb_stat_mod(wb, WB_WRITEBACK, nr); if (!on_wblist) wb_inode_writeback_start(wb); } /* - * We can come through here when swapping anonymous - * pages, so we don't necessarily have an inode to track - * for sync. + * We can come through here when swapping + * anonymous folios, so we don't necessarily + * have an inode to track for sync. */ if (mapping->host && !on_wblist) sb_mark_inode_writeback(mapping->host); } - if (!PageDirty(page)) + if (!folio_test_dirty(folio)) xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); if (!keep_write) xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); xas_unlock_irqrestore(&xas, flags); } else { - ret = TestSetPageWriteback(page); + ret = folio_test_set_writeback(folio); } if (!ret) { - inc_lruvec_page_state(page, NR_WRITEBACK); - inc_zone_page_state(page, NR_ZONE_WRITE_PENDING); + lruvec_stat_mod_folio(folio, NR_WRITEBACK, nr); + zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr); } - unlock_page_memcg(page); - access_ret = arch_make_page_accessible(page); + folio_memcg_unlock(folio); + access_ret = arch_make_folio_accessible(folio); /* * If writeback has been triggered on a page that cannot be made * accessible, it is too late to recover here. */ - VM_BUG_ON_PAGE(access_ret != 0, page); + VM_BUG_ON_FOLIO(access_ret != 0, folio); return ret; - } -EXPORT_SYMBOL(__test_set_page_writeback); +EXPORT_SYMBOL(__folio_start_writeback); -/* - * Wait for a page to complete writeback +/** + * folio_wait_writeback - Wait for a folio to finish writeback. + * @folio: The folio to wait for. + * + * If the folio is currently being written back to storage, wait for the + * I/O to complete. + * + * Context: Sleeps. Must be called in process context and with + * no spinlocks held. Caller should hold a reference on the folio. + * If the folio is not locked, writeback may start again after writeback + * has finished. */ -void wait_on_page_writeback(struct page *page) +void folio_wait_writeback(struct folio *folio) { - while (PageWriteback(page)) { - trace_wait_on_page_writeback(page, page_mapping(page)); - wait_on_page_bit(page, PG_writeback); + while (folio_test_writeback(folio)) { + trace_folio_wait_writeback(folio, folio_mapping(folio)); + folio_wait_bit(folio, PG_writeback); } } -EXPORT_SYMBOL_GPL(wait_on_page_writeback); +EXPORT_SYMBOL_GPL(folio_wait_writeback); -/* - * Wait for a page to complete writeback. Returns -EINTR if we get a - * fatal signal while waiting. +/** + * folio_wait_writeback_killable - Wait for a folio to finish writeback. + * @folio: The folio to wait for. + * + * If the folio is currently being written back to storage, wait for the + * I/O to complete or a fatal signal to arrive. + * + * Context: Sleeps. Must be called in process context and with + * no spinlocks held. Caller should hold a reference on the folio. + * If the folio is not locked, writeback may start again after writeback + * has finished. + * Return: 0 on success, -EINTR if we get a fatal signal while waiting. */ -int wait_on_page_writeback_killable(struct page *page) +int folio_wait_writeback_killable(struct folio *folio) { - while (PageWriteback(page)) { - trace_wait_on_page_writeback(page, page_mapping(page)); - if (wait_on_page_bit_killable(page, PG_writeback)) + while (folio_test_writeback(folio)) { + trace_folio_wait_writeback(folio, folio_mapping(folio)); + if (folio_wait_bit_killable(folio, PG_writeback)) return -EINTR; } return 0; } -EXPORT_SYMBOL_GPL(wait_on_page_writeback_killable); +EXPORT_SYMBOL_GPL(folio_wait_writeback_killable); /** - * wait_for_stable_page() - wait for writeback to finish, if necessary. - * @page: The page to wait on. + * folio_wait_stable() - wait for writeback to finish, if necessary. + * @folio: The folio to wait on. + * + * This function determines if the given folio is related to a backing + * device that requires folio contents to be held stable during writeback. + * If so, then it will wait for any pending writeback to complete. * - * This function determines if the given page is related to a backing device - * that requires page contents to be held stable during writeback. If so, then - * it will wait for any pending writeback to complete. + * Context: Sleeps. Must be called in process context and with + * no spinlocks held. Caller should hold a reference on the folio. + * If the folio is not locked, writeback may start again after writeback + * has finished. */ -void wait_for_stable_page(struct page *page) +void folio_wait_stable(struct folio *folio) { - page = thp_head(page); - if (page->mapping->host->i_sb->s_iflags & SB_I_STABLE_WRITES) - wait_on_page_writeback(page); + if (folio->mapping->host->i_sb->s_iflags & SB_I_STABLE_WRITES) + folio_wait_writeback(folio); } -EXPORT_SYMBOL_GPL(wait_for_stable_page); +EXPORT_SYMBOL_GPL(folio_wait_stable); _ Patches currently in -mm which might be from akpm@xxxxxxxxxxxxxxxxxxxx are mm.patch lazy-tlb-allow-lazy-tlb-mm-refcounting-to-be-configurable-fix.patch mm-compaction-optimize-proactive-compaction-deferrals-fix.patch mm-hugetlb-add-support-for-mempolicy-mpol_preferred_many-fix.patch mm-mempolicy-convert-from-atomic_t-to-refcount_t-on-mempolicy-refcnt-fix.patch linux-next-rejects.patch kernel-forkc-export-kernel_thread-to-modules.patch