diff --git a/MAINTAINERS b/MAINTAINERS index cba1095..2a427d1 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10519,8 +10519,12 @@ F: mm/memblock.c F: Documentation/core-api/boot-time-mm.rst MEMORY MANAGEMENT +M: Andrew Morton L: linux-mm@kvack.org W: http://www.linux-mm.org +T: quilt https://ozlabs.org/~akpm/mmotm/ +T: quilt https://ozlabs.org/~akpm/mmots/ +T: git git://github.com/hnaz/linux-mm.git S: Maintained F: include/linux/mm.h F: include/linux/gfp.h @@ -18034,6 +18038,7 @@ F: Documentation/vm/zsmalloc.rst ZSWAP COMPRESSED SWAP CACHING M: Seth Jennings M: Dan Streetman +M: Vitaly Wool L: linux-mm@kvack.org S: Maintained F: mm/zswap.c diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 53939bf..9876db5 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2098,53 +2098,89 @@ static int ocfs2_is_io_unaligned(struct inode *inode, size_t count, loff_t pos) return 0; } -static int ocfs2_prepare_inode_for_refcount(struct inode *inode, - struct file *file, - loff_t pos, size_t count, - int *meta_level) +static int ocfs2_inode_lock_for_extent_tree(struct inode *inode, + struct buffer_head **di_bh, + int meta_level, + int overwrite_io, + int write_sem, + int wait) { - int ret; - struct buffer_head *di_bh = NULL; - u32 cpos = pos >> OCFS2_SB(inode->i_sb)->s_clustersize_bits; - u32 clusters = - ocfs2_clusters_for_bytes(inode->i_sb, pos + count) - cpos; + int ret = 0; - ret = ocfs2_inode_lock(inode, &di_bh, 1); - if (ret) { - mlog_errno(ret); + if (wait) + ret = ocfs2_inode_lock(inode, NULL, meta_level); + else + ret = ocfs2_try_inode_lock(inode, + overwrite_io ? NULL : di_bh, meta_level); + if (ret < 0) goto out; + + if (wait) { + if (write_sem) + down_write(&OCFS2_I(inode)->ip_alloc_sem); + else + down_read(&OCFS2_I(inode)->ip_alloc_sem); + } else { + if (write_sem) + ret = down_write_trylock(&OCFS2_I(inode)->ip_alloc_sem); + else + ret = down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem); + + if (!ret) { + ret = -EAGAIN; + goto out_unlock; + } } - *meta_level = 1; + return ret; - ret = ocfs2_refcount_cow(inode, di_bh, cpos, clusters, UINT_MAX); - if (ret) - mlog_errno(ret); +out_unlock: + brelse(*di_bh); + ocfs2_inode_unlock(inode, meta_level); out: - brelse(di_bh); return ret; } +static void ocfs2_inode_unlock_for_extent_tree(struct inode *inode, + struct buffer_head **di_bh, + int meta_level, + int write_sem) +{ + if (write_sem) + up_write(&OCFS2_I(inode)->ip_alloc_sem); + else + up_read(&OCFS2_I(inode)->ip_alloc_sem); + + brelse(*di_bh); + *di_bh = NULL; + + if (meta_level >= 0) + ocfs2_inode_unlock(inode, meta_level); +} + static int ocfs2_prepare_inode_for_write(struct file *file, loff_t pos, size_t count, int wait) { int ret = 0, meta_level = 0, overwrite_io = 0; + int write_sem = 0; struct dentry *dentry = file->f_path.dentry; struct inode *inode = d_inode(dentry); struct buffer_head *di_bh = NULL; + u32 cpos; + u32 clusters; /* * We start with a read level meta lock and only jump to an ex * if we need to make modifications here. */ for(;;) { - if (wait) - ret = ocfs2_inode_lock(inode, NULL, meta_level); - else - ret = ocfs2_try_inode_lock(inode, - overwrite_io ? NULL : &di_bh, meta_level); + ret = ocfs2_inode_lock_for_extent_tree(inode, + &di_bh, + meta_level, + overwrite_io, + write_sem, + wait); if (ret < 0) { - meta_level = -1; if (ret != -EAGAIN) mlog_errno(ret); goto out; @@ -2156,15 +2192,8 @@ static int ocfs2_prepare_inode_for_write(struct file *file, */ if (!wait && !overwrite_io) { overwrite_io = 1; - if (!down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem)) { - ret = -EAGAIN; - goto out_unlock; - } ret = ocfs2_overwrite_io(inode, di_bh, pos, count); - brelse(di_bh); - di_bh = NULL; - up_read(&OCFS2_I(inode)->ip_alloc_sem); if (ret < 0) { if (ret != -EAGAIN) mlog_errno(ret); @@ -2183,7 +2212,10 @@ static int ocfs2_prepare_inode_for_write(struct file *file, * set inode->i_size at the end of a write. */ if (should_remove_suid(dentry)) { if (meta_level == 0) { - ocfs2_inode_unlock(inode, meta_level); + ocfs2_inode_unlock_for_extent_tree(inode, + &di_bh, + meta_level, + write_sem); meta_level = 1; continue; } @@ -2197,18 +2229,32 @@ static int ocfs2_prepare_inode_for_write(struct file *file, ret = ocfs2_check_range_for_refcount(inode, pos, count); if (ret == 1) { - ocfs2_inode_unlock(inode, meta_level); - meta_level = -1; - - ret = ocfs2_prepare_inode_for_refcount(inode, - file, - pos, - count, - &meta_level); + ocfs2_inode_unlock_for_extent_tree(inode, + &di_bh, + meta_level, + write_sem); + ret = ocfs2_inode_lock_for_extent_tree(inode, + &di_bh, + meta_level, + overwrite_io, + 1, + wait); + write_sem = 1; + if (ret < 0) { + if (ret != -EAGAIN) + mlog_errno(ret); + goto out; + } + + cpos = pos >> OCFS2_SB(inode->i_sb)->s_clustersize_bits; + clusters = + ocfs2_clusters_for_bytes(inode->i_sb, pos + count) - cpos; + ret = ocfs2_refcount_cow(inode, di_bh, cpos, clusters, UINT_MAX); } if (ret < 0) { - mlog_errno(ret); + if (ret != -EAGAIN) + mlog_errno(ret); goto out_unlock; } @@ -2219,10 +2265,10 @@ out_unlock: trace_ocfs2_prepare_inode_for_write(OCFS2_I(inode)->ip_blkno, pos, count, wait); - brelse(di_bh); - - if (meta_level >= 0) - ocfs2_inode_unlock(inode, meta_level); + ocfs2_inode_unlock_for_extent_tree(inode, + &di_bh, + meta_level, + write_sem); out: return ret; diff --git a/include/linux/mm.h b/include/linux/mm.h index cc29227..a2adf95 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -695,11 +695,6 @@ static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) extern void kvfree(const void *addr); -static inline atomic_t *compound_mapcount_ptr(struct page *page) -{ - return &page[1].compound_mapcount; -} - static inline int compound_mapcount(struct page *page) { VM_BUG_ON_PAGE(!PageCompound(page), page); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 2222fa7..270aa8f 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -221,6 +221,11 @@ struct page { #endif } _struct_page_alignment; +static inline atomic_t *compound_mapcount_ptr(struct page *page) +{ + return &page[1].compound_mapcount; +} + /* * Used for sizing the vmemmap region on some architectures */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index f91cb88..1bf83c8 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -622,12 +622,28 @@ static inline int PageTransCompound(struct page *page) * * Unlike PageTransCompound, this is safe to be called only while * split_huge_pmd() cannot run from under us, like if protected by the - * MMU notifier, otherwise it may result in page->_mapcount < 0 false + * MMU notifier, otherwise it may result in page->_mapcount check false * positives. + * + * We have to treat page cache THP differently since every subpage of it + * would get _mapcount inc'ed once it is PMD mapped. But, it may be PTE + * mapped in the current process so comparing subpage's _mapcount to + * compound_mapcount to filter out PTE mapped case. */ static inline int PageTransCompoundMap(struct page *page) { - return PageTransCompound(page) && atomic_read(&page->_mapcount) < 0; + struct page *head; + + if (!PageTransCompound(page)) + return 0; + + if (PageAnon(page)) + return atomic_read(&page->_mapcount) < 0; + + head = compound_head(page); + /* File THP is PMD mapped and not PTE mapped */ + return atomic_read(&page->_mapcount) == + atomic_read(compound_mapcount_ptr(head)); } /* diff --git a/lib/dump_stack.c b/lib/dump_stack.c index 5cff72f..33ffbf3 100644 --- a/lib/dump_stack.c +++ b/lib/dump_stack.c @@ -106,7 +106,12 @@ retry: was_locked = 1; } else { local_irq_restore(flags); - cpu_relax(); + /* + * Wait for the lock to release before jumping to + * atomic_cmpxchg() in order to mitigate the thundering herd + * problem. + */ + do { cpu_relax(); } while (atomic_read(&dump_lock) != -1); goto retry; } diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 0a1b4b4..f05d27b 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1028,12 +1028,13 @@ static void collapse_huge_page(struct mm_struct *mm, anon_vma_lock_write(vma->anon_vma); - pte = pte_offset_map(pmd, address); - pte_ptl = pte_lockptr(mm, pmd); - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm, address, address + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); + + pte = pte_offset_map(pmd, address); + pte_ptl = pte_lockptr(mm, pmd); + pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */ /* * After this gup_fast can't run anymore. This also removes diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3631065..37592dd 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -484,7 +484,7 @@ ino_t page_cgroup_ino(struct page *page) unsigned long ino = 0; rcu_read_lock(); - if (PageHead(page) && PageSlab(page)) + if (PageSlab(page) && !PageTail(page)) memcg = memcg_from_slab_page(page); else memcg = READ_ONCE(page->mem_cgroup); @@ -2535,6 +2535,15 @@ retry: } /* + * Memcg doesn't have a dedicated reserve for atomic + * allocations. But like the global atomic pool, we need to + * put the burden of reclaim on regular allocation requests + * and let these go through as privileged allocations. + */ + if (gfp_mask & __GFP_ATOMIC) + goto force; + + /* * Unlike in global OOM situations, memcg is not in a physical * memory shortage. Allow dying and OOM-killed tasks to * bypass the last charges so that they can exit quickly and @@ -5014,12 +5023,6 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) { int node; - /* - * Flush percpu vmstats and vmevents to guarantee the value correctness - * on parent's and all ancestor levels. - */ - memcg_flush_percpu_vmstats(memcg, false); - memcg_flush_percpu_vmevents(memcg); for_each_node(node) free_mem_cgroup_per_node_info(memcg, node); free_percpu(memcg->vmstats_percpu); @@ -5030,6 +5033,12 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) static void mem_cgroup_free(struct mem_cgroup *memcg) { memcg_wb_domain_exit(memcg); + /* + * Flush percpu vmstats and vmevents to guarantee the value correctness + * on parent's and all ancestor levels. + */ + memcg_flush_percpu_vmstats(memcg, false); + memcg_flush_percpu_vmevents(memcg); __mem_cgroup_free(memcg); } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index df570e5..07e5c67 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -447,6 +447,14 @@ static void update_pgdat_span(struct pglist_data *pgdat) zone->spanned_pages; /* No need to lock the zones, they can't change. */ + if (!zone->spanned_pages) + continue; + if (!node_end_pfn) { + node_start_pfn = zone->zone_start_pfn; + node_end_pfn = zone_end_pfn; + continue; + } + if (zone_end_pfn > node_end_pfn) node_end_pfn = zone_end_pfn; if (zone->zone_start_pfn < node_start_pfn) diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 7fde886..9a889e4 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -180,7 +180,7 @@ int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) mn->ops->invalidate_range_start, _ret, !mmu_notifier_range_blockable(range) ? "non-" : ""); WARN_ON(mmu_notifier_range_blockable(range) || - ret != -EAGAIN); + _ret != -EAGAIN); ret = _ret; } } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ecc3dba..f391c0c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1948,6 +1948,14 @@ void __init page_alloc_init_late(void) wait_for_completion(&pgdat_init_all_done_comp); /* + * The number of managed pages has changed due to the initialisation + * so the pcpu batch and high limits needs to be updated or the limits + * will be artificially small. + */ + for_each_populated_zone(zone) + zone_pcp_update(zone); + + /* * We initialized the rest of the deferred pages. Permanently disable * on-demand struct page initialization. */ @@ -3720,10 +3728,6 @@ try_this_zone: static void warn_alloc_show_mem(gfp_t gfp_mask, nodemask_t *nodemask) { unsigned int filter = SHOW_MEM_FILTER_NODES; - static DEFINE_RATELIMIT_STATE(show_mem_rs, HZ, 1); - - if (!__ratelimit(&show_mem_rs)) - return; /* * This documents exceptions given to allocations in certain @@ -3744,8 +3748,7 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...) { struct va_format vaf; va_list args; - static DEFINE_RATELIMIT_STATE(nopage_rs, DEFAULT_RATELIMIT_INTERVAL, - DEFAULT_RATELIMIT_BURST); + static DEFINE_RATELIMIT_STATE(nopage_rs, 10*HZ, 1); if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs)) return; @@ -8514,7 +8517,6 @@ void free_contig_range(unsigned long pfn, unsigned int nr_pages) WARN(count != 0, "%d pages are still in use!\n", count); } -#ifdef CONFIG_MEMORY_HOTPLUG /* * The zone indicated has a new number of managed_pages; batch sizes and percpu * page high values need to be recalulated. @@ -8528,7 +8530,6 @@ void __meminit zone_pcp_update(struct zone *zone) per_cpu_ptr(zone->pageset, cpu)); mutex_unlock(&pcp_batch_high_lock); } -#endif void zone_pcp_reset(struct zone *zone) { diff --git a/mm/slab.h b/mm/slab.h index 68e455f..b2b0169 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -323,8 +323,8 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s) * Expects a pointer to a slab page. Please note, that PageSlab() check * isn't sufficient, as it returns true also for tail compound slab pages, * which do not have slab_cache pointer set. - * So this function assumes that the page can pass PageHead() and PageSlab() - * checks. + * So this function assumes that the page can pass PageSlab() && !PageTail() + * check. * * The kmem_cache can be reparented asynchronously. The caller must ensure * the memcg lifetime, e.g. by taking rcu_read_lock() or cgroup_mutex. diff --git a/mm/vmstat.c b/mm/vmstat.c index 6afc892..a822204 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1383,12 +1383,29 @@ static void pagetypeinfo_showfree_print(struct seq_file *m, unsigned long freecount = 0; struct free_area *area; struct list_head *curr; + bool overflow = false; area = &(zone->free_area[order]); - list_for_each(curr, &area->free_list[mtype]) - freecount++; - seq_printf(m, "%6lu ", freecount); + list_for_each(curr, &area->free_list[mtype]) { + /* + * Cap the free_list iteration because it might + * be really large and we are under a spinlock + * so a long time spent here could trigger a + * hard lockup detector. Anyway this is a + * debugging tool so knowing there is a handful + * of pages of this order should be more than + * sufficient. + */ + if (++freecount >= 100000) { + overflow = true; + break; + } + } + seq_printf(m, "%s%6lu ", overflow ? ">" : "", freecount); + spin_unlock_irq(&zone->lock); + cond_resched(); + spin_lock_irq(&zone->lock); } seq_putc(m, '\n'); } @@ -1972,7 +1989,7 @@ void __init init_mm_internals(void) #endif #ifdef CONFIG_PROC_FS proc_create_seq("buddyinfo", 0444, NULL, &fragmentation_op); - proc_create_seq("pagetypeinfo", 0444, NULL, &pagetypeinfo_op); + proc_create_seq("pagetypeinfo", 0400, NULL, &pagetypeinfo_op); proc_create_seq("vmstat", 0444, NULL, &vmstat_op); proc_create_seq("zoneinfo", 0444, NULL, &zoneinfo_op); #endif diff --git a/scripts/gdb/linux/symbols.py b/scripts/gdb/linux/symbols.py index 7b7c2fa..be984aa 100644 --- a/scripts/gdb/linux/symbols.py +++ b/scripts/gdb/linux/symbols.py @@ -99,7 +99,8 @@ lx-symbols command.""" attrs[n]['name'].string(): attrs[n]['address'] for n in range(int(sect_attrs['nsections']))} args = [] - for section_name in [".data", ".data..read_mostly", ".rodata", ".bss"]: + for section_name in [".data", ".data..read_mostly", ".rodata", ".bss", + ".text", ".text.hot", ".text.unlikely"]: address = section_name_to_address.get(section_name) if address: args.append(" -s {name} {addr}".format( diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c index cb3fc09..485cf06 100644 --- a/tools/testing/selftests/vm/gup_benchmark.c +++ b/tools/testing/selftests/vm/gup_benchmark.c @@ -71,7 +71,7 @@ int main(int argc, char **argv) flags |= MAP_SHARED; break; case 'H': - flags |= MAP_HUGETLB; + flags |= (MAP_HUGETLB | MAP_ANONYMOUS); break; default: return -1;