diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 15 | ||||
| -rw-r--r-- | mm/backing-dev.c | 11 | ||||
| -rw-r--r-- | mm/bootmem.c | 8 | ||||
| -rw-r--r-- | mm/bounce.c | 48 | ||||
| -rw-r--r-- | mm/filemap.c | 5 | ||||
| -rw-r--r-- | mm/huge_memory.c | 4 | ||||
| -rw-r--r-- | mm/hugetlb.c | 1 | ||||
| -rw-r--r-- | mm/memblock.c | 17 | ||||
| -rw-r--r-- | mm/memcontrol.c | 4 | ||||
| -rw-r--r-- | mm/migrate.c | 4 | ||||
| -rw-r--r-- | mm/mlock.c | 6 | ||||
| -rw-r--r-- | mm/mmap.c | 3 | ||||
| -rw-r--r-- | mm/mremap.c | 1 | ||||
| -rw-r--r-- | mm/nobootmem.c | 23 | ||||
| -rw-r--r-- | mm/nommu.c | 1 | ||||
| -rw-r--r-- | mm/page-writeback.c | 25 | ||||
| -rw-r--r-- | mm/page_alloc.c | 20 | ||||
| -rw-r--r-- | mm/rmap.c | 24 |
18 files changed, 162 insertions, 58 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 278e3ab1f169..0b23db9a8791 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -1,6 +1,6 @@ config SELECT_MEMORY_MODEL def_bool y - depends on EXPERIMENTAL || ARCH_SELECT_MEMORY_MODEL + depends on ARCH_SELECT_MEMORY_MODEL choice prompt "Memory model" @@ -258,6 +258,19 @@ config BOUNCE def_bool y depends on BLOCK && MMU && (ZONE_DMA || HIGHMEM) +# On the 'tile' arch, USB OHCI needs the bounce pool since tilegx will often +# have more than 4GB of memory, but we don't currently use the IOTLB to present +# a 32-bit address to OHCI. So we need to use a bounce pool instead. +# +# We also use the bounce pool to provide stable page writes for jbd. jbd +# initiates buffer writeback without locking the page or setting PG_writeback, +# and fixing that behavior (a second time; jbd2 doesn't have this problem) is +# a major rework effort. Instead, use the bounce buffer to snapshot pages +# (until jbd goes away). The only jbd user is ext3. +config NEED_BOUNCE_POOL + bool + default y if (TILE && USB_OHCI_HCD) || (BLK_DEV_INTEGRITY && JBD) + config NR_QUICK int depends on QUICKLIST diff --git a/mm/backing-dev.c b/mm/backing-dev.c index d3ca2b3ee176..41733c5dc820 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -221,12 +221,23 @@ static ssize_t max_ratio_store(struct device *dev, } BDI_SHOW(max_ratio, bdi->max_ratio) +static ssize_t stable_pages_required_show(struct device *dev, + struct device_attribute *attr, + char *page) +{ + struct backing_dev_info *bdi = dev_get_drvdata(dev); + + return snprintf(page, PAGE_SIZE-1, "%d\n", + bdi_cap_stable_pages_required(bdi) ? 1 : 0); +} + #define __ATTR_RW(attr) __ATTR(attr, 0644, attr##_show, attr##_store) static struct device_attribute bdi_dev_attrs[] = { __ATTR_RW(read_ahead_kb), __ATTR_RW(min_ratio), __ATTR_RW(max_ratio), + __ATTR_RO(stable_pages_required), __ATTR_NULL, }; diff --git a/mm/bootmem.c b/mm/bootmem.c index b93376c39b61..2b0bcb019ec2 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -833,6 +833,14 @@ void * __init __alloc_bootmem_low(unsigned long size, unsigned long align, return ___alloc_bootmem(size, align, goal, ARCH_LOW_ADDRESS_LIMIT); } +void * __init __alloc_bootmem_low_nopanic(unsigned long size, + unsigned long align, + unsigned long goal) +{ + return ___alloc_bootmem_nopanic(size, align, goal, + ARCH_LOW_ADDRESS_LIMIT); +} + /** * __alloc_bootmem_low_node - allocate low boot memory from a specific node * @pgdat: node to allocate from diff --git a/mm/bounce.c b/mm/bounce.c index 042086775561..5f8901768602 100644 --- a/mm/bounce.c +++ b/mm/bounce.c @@ -178,8 +178,45 @@ static void bounce_end_io_read_isa(struct bio *bio, int err) __bounce_end_io_read(bio, isa_page_pool, err); } +#ifdef CONFIG_NEED_BOUNCE_POOL +static int must_snapshot_stable_pages(struct request_queue *q, struct bio *bio) +{ + struct page *page; + struct backing_dev_info *bdi; + struct address_space *mapping; + struct bio_vec *from; + int i; + + if (bio_data_dir(bio) != WRITE) + return 0; + + if (!bdi_cap_stable_pages_required(&q->backing_dev_info)) + return 0; + + /* + * Based on the first page that has a valid mapping, decide whether or + * not we have to employ bounce buffering to guarantee stable pages. + */ + bio_for_each_segment(from, bio, i) { + page = from->bv_page; + mapping = page_mapping(page); + if (!mapping) + continue; + bdi = mapping->backing_dev_info; + return mapping->host->i_sb->s_flags & MS_SNAP_STABLE; + } + + return 0; +} +#else +static int must_snapshot_stable_pages(struct request_queue *q, struct bio *bio) +{ + return 0; +} +#endif /* CONFIG_NEED_BOUNCE_POOL */ + static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, - mempool_t *pool) + mempool_t *pool, int force) { struct page *page; struct bio *bio = NULL; @@ -192,7 +229,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, /* * is destination page below bounce pfn? */ - if (page_to_pfn(page) <= queue_bounce_pfn(q)) + if (page_to_pfn(page) <= queue_bounce_pfn(q) && !force) continue; /* @@ -270,6 +307,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig) { + int must_bounce; mempool_t *pool; /* @@ -278,13 +316,15 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig) if (!bio_has_data(*bio_orig)) return; + must_bounce = must_snapshot_stable_pages(q, *bio_orig); + /* * for non-isa bounce case, just check if the bounce pfn is equal * to or bigger than the highest pfn in the system -- in that case, * don't waste time iterating over bio segments */ if (!(q->bounce_gfp & GFP_DMA)) { - if (queue_bounce_pfn(q) >= blk_max_pfn) + if (queue_bounce_pfn(q) >= blk_max_pfn && !must_bounce) return; pool = page_pool; } else { @@ -295,7 +335,7 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig) /* * slow path */ - __blk_queue_bounce(q, bio_orig, pool); + __blk_queue_bounce(q, bio_orig, pool, must_bounce); } EXPORT_SYMBOL(blk_queue_bounce); diff --git a/mm/filemap.c b/mm/filemap.c index 83efee76a5c0..c610076c30e1 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1728,6 +1728,7 @@ int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) * see the dirty page and writeprotect it again. */ set_page_dirty(page); + wait_for_stable_page(page); out: sb_end_pagefault(inode->i_sb); return ret; @@ -2056,7 +2057,7 @@ EXPORT_SYMBOL(iov_iter_fault_in_readable); /* * Return the count of just the current iov_iter segment. */ -size_t iov_iter_single_seg_count(struct iov_iter *i) +size_t iov_iter_single_seg_count(const struct iov_iter *i) { const struct iovec *iov = i->iov; if (i->nr_segs == 1) @@ -2274,7 +2275,7 @@ repeat: return NULL; } found: - wait_on_page_writeback(page); + wait_for_stable_page(page); return page; } EXPORT_SYMBOL(grab_cache_page_write_begin); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 6001ee6347a9..b5783d81eda9 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1257,6 +1257,10 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, if (flags & FOLL_WRITE && !pmd_write(*pmd)) goto out; + /* Avoid dumping huge zero page */ + if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd)) + return ERR_PTR(-EFAULT); + page = pmd_page(*pmd); VM_BUG_ON(!PageHead(page)); if (flags & FOLL_TOUCH) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 4f3ea0b1e57c..546db81820e4 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3033,6 +3033,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, if (!huge_pte_none(huge_ptep_get(ptep))) { pte = huge_ptep_get_and_clear(mm, address, ptep); pte = pte_mkhuge(pte_modify(pte, newprot)); + pte = arch_make_huge_pte(pte, vma, NULL, 0); set_huge_pte_at(mm, address, ptep, pte); pages++; } diff --git a/mm/memblock.c b/mm/memblock.c index 88adc8afb610..b8d9147e5c08 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -828,6 +828,23 @@ phys_addr_t __init memblock_phys_mem_size(void) return memblock.memory.total_size; } +phys_addr_t __init memblock_mem_size(unsigned long limit_pfn) +{ + unsigned long pages = 0; + struct memblock_region *r; + unsigned long start_pfn, end_pfn; + + for_each_memblock(memory, r) { + start_pfn = memblock_region_memory_base_pfn(r); + end_pfn = memblock_region_memory_end_pfn(r); + start_pfn = min_t(unsigned long, start_pfn, limit_pfn); + end_pfn = min_t(unsigned long, end_pfn, limit_pfn); + pages += end_pfn - start_pfn; + } + + return (phys_addr_t)pages << PAGE_SHIFT; +} + /* lowest address */ phys_addr_t __init_memblock memblock_start_of_DRAM(void) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 09255ec8159c..fbb60b103e64 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3030,7 +3030,9 @@ int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s, if (memcg) { s->memcg_params->memcg = memcg; s->memcg_params->root_cache = root_cache; - } + } else + s->memcg_params->is_root_cache = true; + return 0; } diff --git a/mm/migrate.c b/mm/migrate.c index c38778610aa8..2fd8b4af4744 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -160,8 +160,10 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, if (is_write_migration_entry(entry)) pte = pte_mkwrite(pte); #ifdef CONFIG_HUGETLB_PAGE - if (PageHuge(new)) + if (PageHuge(new)) { pte = pte_mkhuge(pte); + pte = arch_make_huge_pte(pte, vma, new, 0); + } #endif flush_cache_page(vma, addr, pte_pfn(pte)); set_pte_at(mm, addr, ptep, pte); diff --git a/mm/mlock.c b/mm/mlock.c index f0b9ce572fc7..c9bd528b01d2 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -517,11 +517,11 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) static int do_mlockall(int flags) { struct vm_area_struct * vma, * prev = NULL; - unsigned int def_flags = 0; if (flags & MCL_FUTURE) - def_flags = VM_LOCKED; - current->mm->def_flags = def_flags; + current->mm->def_flags |= VM_LOCKED; + else + current->mm->def_flags &= ~VM_LOCKED; if (flags == MCL_FUTURE) goto out; diff --git a/mm/mmap.c b/mm/mmap.c index 35730ee9d515..09da0b264982 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -32,6 +32,7 @@ #include <linux/khugepaged.h> #include <linux/uprobes.h> #include <linux/rbtree_augmented.h> +#include <linux/sched/sysctl.h> #include <asm/uaccess.h> #include <asm/cacheflush.h> @@ -2943,7 +2944,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) * vma in this mm is backed by the same anon_vma or address_space. * * We can take all the locks in random order because the VM code - * taking i_mmap_mutex or anon_vma->mutex outside the mmap_sem never + * taking i_mmap_mutex or anon_vma->rwsem outside the mmap_sem never * takes more than one of them in a row. Secondly we're protected * against a concurrent mm_take_all_locks() by the mm_all_locks_mutex. * diff --git a/mm/mremap.c b/mm/mremap.c index e1031e1f6a61..f9766f460299 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -19,6 +19,7 @@ #include <linux/security.h> #include <linux/syscalls.h> #include <linux/mmu_notifier.h> +#include <linux/sched/sysctl.h> #include <asm/uaccess.h> #include <asm/cacheflush.h> diff --git a/mm/nobootmem.c b/mm/nobootmem.c index b8294fc03df8..5e07d36e381e 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -154,21 +154,6 @@ static void reset_node_lowmem_managed_pages(pg_data_t *pgdat) } /** - * free_all_bootmem_node - release a node's free pages to the buddy allocator - * @pgdat: node to be released - * - * Returns the number of pages actually released. - */ -unsigned long __init free_all_bootmem_node(pg_data_t *pgdat) -{ - register_page_bootmem_info_node(pgdat); - reset_node_lowmem_managed_pages(pgdat); - - /* free_low_memory_core_early(MAX_NUMNODES) will be called later */ - return 0; -} - -/** * free_all_bootmem - release free pages to the buddy allocator * * Returns the number of pages actually released. @@ -406,6 +391,14 @@ void * __init __alloc_bootmem_low(unsigned long size, unsigned long align, return ___alloc_bootmem(size, align, goal, ARCH_LOW_ADDRESS_LIMIT); } +void * __init __alloc_bootmem_low_nopanic(unsigned long size, + unsigned long align, + unsigned long goal) +{ + return ___alloc_bootmem_nopanic(size, align, goal, + ARCH_LOW_ADDRESS_LIMIT); +} + /** * __alloc_bootmem_low_node - allocate low boot memory from a specific node * @pgdat: node to allocate from diff --git a/mm/nommu.c b/mm/nommu.c index 79c3cac87afa..b20db4e22263 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -29,6 +29,7 @@ #include <linux/security.h> #include <linux/syscalls.h> #include <linux/audit.h> +#include <linux/sched/sysctl.h> #include <asm/uaccess.h> #include <asm/tlb.h> diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 0713bfbf0954..7300c9d5e1d9 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -35,6 +35,7 @@ #include <linux/buffer_head.h> /* __set_page_dirty_buffers */ #include <linux/pagevec.h> #include <linux/timer.h> +#include <linux/sched/rt.h> #include <trace/events/writeback.h> /* @@ -2289,3 +2290,27 @@ int mapping_tagged(struct address_space *mapping, int tag) return radix_tree_tagged(&mapping->page_tree, tag); } EXPORT_SYMBOL(mapping_tagged); + +/** + * wait_for_stable_page() - wait for writeback to finish, if necessary. + * @page: The page to wait on. + * + * 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. + */ +void wait_for_stable_page(struct page *page) +{ + struct address_space *mapping = page_mapping(page); + struct backing_dev_info *bdi = mapping->backing_dev_info; + + if (!bdi_cap_stable_pages_required(bdi)) + return; +#ifdef CONFIG_NEED_BOUNCE_POOL + if (mapping->host->i_sb->s_flags & MS_SNAP_STABLE) + return; +#endif /* CONFIG_NEED_BOUNCE_POOL */ + + wait_on_page_writeback(page); +} +EXPORT_SYMBOL_GPL(wait_for_stable_page); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index df2022ff0c8a..d1107adf174a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -58,6 +58,7 @@ #include <linux/prefetch.h> #include <linux/migrate.h> #include <linux/page-debug-flags.h> +#include <linux/sched/rt.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -773,6 +774,10 @@ void __init init_cma_reserved_pageblock(struct page *page) set_pageblock_migratetype(page, MIGRATE_CMA); __free_pages(page, pageblock_order); totalram_pages += pageblock_nr_pages; +#ifdef CONFIG_HIGHMEM + if (PageHighMem(page)) + totalhigh_pages += pageblock_nr_pages; +#endif } #endif @@ -4416,10 +4421,11 @@ static void __meminit calculate_node_totalpages(struct pglist_data *pgdat, * round what is now in bits to nearest long in bits, then return it in * bytes. */ -static unsigned long __init usemap_size(unsigned long zonesize) +static unsigned long __init usemap_size(unsigned long zone_start_pfn, unsigned long zonesize) { unsigned long usemapsize; + zonesize += zone_start_pfn & (pageblock_nr_pages-1); usemapsize = roundup(zonesize, pageblock_nr_pages); usemapsize = usemapsize >> pageblock_order; usemapsize *= NR_PAGEBLOCK_BITS; @@ -4429,17 +4435,19 @@ static unsigned long __init usemap_size(unsigned long zonesize) } static void __init setup_usemap(struct pglist_data *pgdat, - struct zone *zone, unsigned long zonesize) + struct zone *zone, + unsigned long zone_start_pfn, + unsigned long zonesize) { - unsigned long usemapsize = usemap_size(zonesize); + unsigned long usemapsize = usemap_size(zone_start_pfn, zonesize); zone->pageblock_flags = NULL; if (usemapsize) zone->pageblock_flags = alloc_bootmem_node_nopanic(pgdat, usemapsize); } #else -static inline void setup_usemap(struct pglist_data *pgdat, - struct zone *zone, unsigned long zonesize) {} +static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone, + unsigned long zone_start_pfn, unsigned long zonesize) {} #endif /* CONFIG_SPARSEMEM */ #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE @@ -4590,7 +4598,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, continue; set_pageblock_order(); - setup_usemap(pgdat, zone, size); + setup_usemap(pgdat, zone, zone_start_pfn, size); ret = init_currently_empty_zone(zone, zone_start_pfn, size, MEMMAP_EARLY); BUG_ON(ret); diff --git a/mm/rmap.c b/mm/rmap.c index 2c78f8cadc95..3d38edffda41 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1126,7 +1126,6 @@ void page_add_file_rmap(struct page *page) */ void page_remove_rmap(struct page *page) { - struct address_space *mapping = page_mapping(page); bool anon = PageAnon(page); bool locked; unsigned long flags; @@ -1144,29 +1143,6 @@ void page_remove_rmap(struct page *page) goto out; /* - * Now that the last pte has gone, s390 must transfer dirty - * flag from storage key to struct page. We can usually skip - * this if the page is anon, so about to be freed; but perhaps - * not if it's in swapcache - there might be another pte slot - * containing the swap entry, but page not yet written to swap. - * - * And we can skip it on file pages, so long as the filesystem - * participates in dirty tracking (note that this is not only an - * optimization but also solves problems caused by dirty flag in - * storage key getting set by a write from inside kernel); but need to - * catch shm and tmpfs and ramfs pages which have been modified since - * creation by read fault. - * - * Note that mapping must be decided above, before decrementing - * mapcount (which luckily provides a barrier): once page is unmapped, - * it could be truncated and page->mapping reset to NULL at any moment. - * Note also that we are relying on page_mapping(page) to set mapping - * to &swapper_space when PageSwapCache(page). - */ - if (mapping && !mapping_cap_account_dirty(mapping) && - page_test_and_clear_dirty(page_to_pfn(page), 1)) - set_page_dirty(page); - /* * Hugepages are not counted in NR_ANON_PAGES nor NR_FILE_MAPPED * and not charged by memcg for now. */ |