From 3f1353552e256cb3bf0f23334c48f50476044673 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 30 Jan 2020 22:13:57 -0800 Subject: mm/page_alloc: skip non present sections on zone initialization memmap_init_zone() can be called on the ranges with holes during the boot. It will skip any non-valid PFNs one-by-one. It works fine as long as holes are not too big. But huge holes in the memory map causes a problem. It takes over 20 seconds to walk 32TiB hole. x86-64 with 5-level paging allows for much larger holes in the memory map which would practically hang the system. Deferred struct page init doesn't help here. It only works on the present ranges. Skipping non-present sections would fix the issue. Link: http://lkml.kernel.org/r/20191230093828.24613-1-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Reviewed-by: Baoquan He Acked-by: Michal Hocko Cc: Dan Williams Cc: Vlastimil Babka Cc: Mel Gorman Cc: "Jin, Zhi" Cc: David Hildenbrand Cc: Michal Hocko Cc: Oscar Salvador Cc: Pavel Tatashin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 28 +++++++++++++++++++++++++++- 1 file changed, 27 insertions(+), 1 deletion(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d047bf7d8fd4..fe8a529f7fd8 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5848,6 +5848,30 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn) return false; } +#ifdef CONFIG_SPARSEMEM +/* Skip PFNs that belong to non-present sections */ +static inline __meminit unsigned long next_pfn(unsigned long pfn) +{ + unsigned long section_nr; + + section_nr = pfn_to_section_nr(++pfn); + if (present_section_nr(section_nr)) + return pfn; + + while (++section_nr <= __highest_present_section_nr) { + if (present_section_nr(section_nr)) + return section_nr_to_pfn(section_nr); + } + + return -1; +} +#else +static inline __meminit unsigned long next_pfn(unsigned long pfn) +{ + return pfn++; +} +#endif + /* * Initially all pages are reserved - free ones are freed * up by memblock_free_all() once the early boot process is @@ -5887,8 +5911,10 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, * function. They do not exist on hotplugged memory. */ if (context == MEMMAP_EARLY) { - if (!early_pfn_valid(pfn)) + if (!early_pfn_valid(pfn)) { + pfn = next_pfn(pfn) - 1; continue; + } if (!early_pfn_in_nid(pfn, nid)) continue; if (overlap_memmap_init(zone, &pfn)) -- cgit v1.2.3 From fe4c86c916d9151113372369f322e7436167e6f3 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 30 Jan 2020 22:14:04 -0800 Subject: mm: remove "count" parameter from has_unmovable_pages() Now that the memory isolate notifier is gone, the parameter is always 0. Drop it and cleanup has_unmovable_pages(). Link: http://lkml.kernel.org/r/20191114131911.11783-3-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Michal Hocko Cc: Oscar Salvador Cc: Anshuman Khandual Cc: Qian Cai Cc: Pingfan Liu Cc: Stephen Rothwell Cc: Dan Williams Cc: Pavel Tatashin Cc: Vlastimil Babka Cc: Mel Gorman Cc: Mike Rapoport Cc: Wei Yang Cc: Alexander Duyck Cc: Alexander Potapenko Cc: Arun KS Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 21 +++++++-------------- 1 file changed, 7 insertions(+), 14 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index fe8a529f7fd8..3aec60ddd6d6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8180,17 +8180,15 @@ void *__init alloc_large_system_hash(const char *tablename, /* * This function checks whether pageblock includes unmovable pages or not. - * If @count is not zero, it is okay to include less @count unmovable pages * * PageLRU check without isolation or lru_lock could race so that * MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable * check without lock_page also may miss some movable non-lru pages at * race condition. So you can't expect this function should be exact. */ -bool has_unmovable_pages(struct zone *zone, struct page *page, int count, - int migratetype, int flags) +bool has_unmovable_pages(struct zone *zone, struct page *page, int migratetype, + int flags) { - unsigned long found; unsigned long iter = 0; unsigned long pfn = page_to_pfn(page); const char *reason = "unmovable page"; @@ -8216,13 +8214,11 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, goto unmovable; } - for (found = 0; iter < pageblock_nr_pages; iter++) { - unsigned long check = pfn + iter; - - if (!pfn_valid_within(check)) + for (; iter < pageblock_nr_pages; iter++) { + if (!pfn_valid_within(pfn + iter)) continue; - page = pfn_to_page(check); + page = pfn_to_page(pfn + iter); if (PageReserved(page)) goto unmovable; @@ -8271,11 +8267,9 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, if ((flags & MEMORY_OFFLINE) && PageHWPoison(page)) continue; - if (__PageMovable(page)) + if (__PageMovable(page) || PageLRU(page)) continue; - if (!PageLRU(page)) - found++; /* * If there are RECLAIMABLE pages, we need to check * it. But now, memory offline itself doesn't call @@ -8289,8 +8283,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, * is set to both of a memory hole page and a _used_ kernel * page at boot. */ - if (found > count) - goto unmovable; + goto unmovable; } return false; unmovable: -- cgit v1.2.3 From 4a55c0474a92d5c418bcbbe122368de0910aeac2 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 30 Jan 2020 22:14:57 -0800 Subject: mm/hotplug: silence a lockdep splat with printk() It is not that hard to trigger lockdep splats by calling printk from under zone->lock. Most of them are false positives caused by lock chains introduced early in the boot process and they do not cause any real problems (although most of the early boot lock dependencies could happen after boot as well). There are some console drivers which do allocate from the printk context as well and those should be fixed. In any case, false positives are not that trivial to workaround and it is far from optimal to lose lockdep functionality for something that is a non-issue. So change has_unmovable_pages() so that it no longer calls dump_page() itself - instead it returns a "struct page *" of the unmovable page back to the caller so that in the case of a has_unmovable_pages() failure, the caller can call dump_page() after releasing zone->lock. Also, make dump_page() is able to report a CMA page as well, so the reason string from has_unmovable_pages() can be removed. Even though has_unmovable_pages doesn't hold any reference to the returned page this should be reasonably safe for the purpose of reporting the page (dump_page) because it cannot be hotremoved in the context of memory unplug. The state of the page might change but that is the case even with the existing code as zone->lock only plays role for free pages. While at it, remove a similar but unnecessary debug-only printk() as well. A sample of one of those lockdep splats is, WARNING: possible circular locking dependency detected ------------------------------------------------------ test.sh/8653 is trying to acquire lock: ffffffff865a4460 (console_owner){-.-.}, at: console_unlock+0x207/0x750 but task is already holding lock: ffff88883fff3c58 (&(&zone->lock)->rlock){-.-.}, at: __offline_isolated_pages+0x179/0x3e0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #3 (&(&zone->lock)->rlock){-.-.}: __lock_acquire+0x5b3/0xb40 lock_acquire+0x126/0x280 _raw_spin_lock+0x2f/0x40 rmqueue_bulk.constprop.21+0xb6/0x1160 get_page_from_freelist+0x898/0x22c0 __alloc_pages_nodemask+0x2f3/0x1cd0 alloc_pages_current+0x9c/0x110 allocate_slab+0x4c6/0x19c0 new_slab+0x46/0x70 ___slab_alloc+0x58b/0x960 __slab_alloc+0x43/0x70 __kmalloc+0x3ad/0x4b0 __tty_buffer_request_room+0x100/0x250 tty_insert_flip_string_fixed_flag+0x67/0x110 pty_write+0xa2/0xf0 n_tty_write+0x36b/0x7b0 tty_write+0x284/0x4c0 __vfs_write+0x50/0xa0 vfs_write+0x105/0x290 redirected_tty_write+0x6a/0xc0 do_iter_write+0x248/0x2a0 vfs_writev+0x106/0x1e0 do_writev+0xd4/0x180 __x64_sys_writev+0x45/0x50 do_syscall_64+0xcc/0x76c entry_SYSCALL_64_after_hwframe+0x49/0xbe -> #2 (&(&port->lock)->rlock){-.-.}: __lock_acquire+0x5b3/0xb40 lock_acquire+0x126/0x280 _raw_spin_lock_irqsave+0x3a/0x50 tty_port_tty_get+0x20/0x60 tty_port_default_wakeup+0xf/0x30 tty_port_tty_wakeup+0x39/0x40 uart_write_wakeup+0x2a/0x40 serial8250_tx_chars+0x22e/0x440 serial8250_handle_irq.part.8+0x14a/0x170 serial8250_default_handle_irq+0x5c/0x90 serial8250_interrupt+0xa6/0x130 __handle_irq_event_percpu+0x78/0x4f0 handle_irq_event_percpu+0x70/0x100 handle_irq_event+0x5a/0x8b handle_edge_irq+0x117/0x370 do_IRQ+0x9e/0x1e0 ret_from_intr+0x0/0x2a cpuidle_enter_state+0x156/0x8e0 cpuidle_enter+0x41/0x70 call_cpuidle+0x5e/0x90 do_idle+0x333/0x370 cpu_startup_entry+0x1d/0x1f start_secondary+0x290/0x330 secondary_startup_64+0xb6/0xc0 -> #1 (&port_lock_key){-.-.}: __lock_acquire+0x5b3/0xb40 lock_acquire+0x126/0x280 _raw_spin_lock_irqsave+0x3a/0x50 serial8250_console_write+0x3e4/0x450 univ8250_console_write+0x4b/0x60 console_unlock+0x501/0x750 vprintk_emit+0x10d/0x340 vprintk_default+0x1f/0x30 vprintk_func+0x44/0xd4 printk+0x9f/0xc5 -> #0 (console_owner){-.-.}: check_prev_add+0x107/0xea0 validate_chain+0x8fc/0x1200 __lock_acquire+0x5b3/0xb40 lock_acquire+0x126/0x280 console_unlock+0x269/0x750 vprintk_emit+0x10d/0x340 vprintk_default+0x1f/0x30 vprintk_func+0x44/0xd4 printk+0x9f/0xc5 __offline_isolated_pages.cold.52+0x2f/0x30a offline_isolated_pages_cb+0x17/0x30 walk_system_ram_range+0xda/0x160 __offline_pages+0x79c/0xa10 offline_pages+0x11/0x20 memory_subsys_offline+0x7e/0xc0 device_offline+0xd5/0x110 state_store+0xc6/0xe0 dev_attr_store+0x3f/0x60 sysfs_kf_write+0x89/0xb0 kernfs_fop_write+0x188/0x240 __vfs_write+0x50/0xa0 vfs_write+0x105/0x290 ksys_write+0xc6/0x160 __x64_sys_write+0x43/0x50 do_syscall_64+0xcc/0x76c entry_SYSCALL_64_after_hwframe+0x49/0xbe other info that might help us debug this: Chain exists of: console_owner --> &(&port->lock)->rlock --> &(&zone->lock)->rlock Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&(&zone->lock)->rlock); lock(&(&port->lock)->rlock); lock(&(&zone->lock)->rlock); lock(console_owner); *** DEADLOCK *** 9 locks held by test.sh/8653: #0: ffff88839ba7d408 (sb_writers#4){.+.+}, at: vfs_write+0x25f/0x290 #1: ffff888277618880 (&of->mutex){+.+.}, at: kernfs_fop_write+0x128/0x240 #2: ffff8898131fc218 (kn->count#115){.+.+}, at: kernfs_fop_write+0x138/0x240 #3: ffffffff86962a80 (device_hotplug_lock){+.+.}, at: lock_device_hotplug_sysfs+0x16/0x50 #4: ffff8884374f4990 (&dev->mutex){....}, at: device_offline+0x70/0x110 #5: ffffffff86515250 (cpu_hotplug_lock.rw_sem){++++}, at: __offline_pages+0xbf/0xa10 #6: ffffffff867405f0 (mem_hotplug_lock.rw_sem){++++}, at: percpu_down_write+0x87/0x2f0 #7: ffff88883fff3c58 (&(&zone->lock)->rlock){-.-.}, at: __offline_isolated_pages+0x179/0x3e0 #8: ffffffff865a4920 (console_lock){+.+.}, at: vprintk_emit+0x100/0x340 stack backtrace: Hardware name: HPE ProLiant DL560 Gen10/ProLiant DL560 Gen10, BIOS U34 05/21/2019 Call Trace: dump_stack+0x86/0xca print_circular_bug.cold.31+0x243/0x26e check_noncircular+0x29e/0x2e0 check_prev_add+0x107/0xea0 validate_chain+0x8fc/0x1200 __lock_acquire+0x5b3/0xb40 lock_acquire+0x126/0x280 console_unlock+0x269/0x750 vprintk_emit+0x10d/0x340 vprintk_default+0x1f/0x30 vprintk_func+0x44/0xd4 printk+0x9f/0xc5 __offline_isolated_pages.cold.52+0x2f/0x30a offline_isolated_pages_cb+0x17/0x30 walk_system_ram_range+0xda/0x160 __offline_pages+0x79c/0xa10 offline_pages+0x11/0x20 memory_subsys_offline+0x7e/0xc0 device_offline+0xd5/0x110 state_store+0xc6/0xe0 dev_attr_store+0x3f/0x60 sysfs_kf_write+0x89/0xb0 kernfs_fop_write+0x188/0x240 __vfs_write+0x50/0xa0 vfs_write+0x105/0x290 ksys_write+0xc6/0x160 __x64_sys_write+0x43/0x50 do_syscall_64+0xcc/0x76c entry_SYSCALL_64_after_hwframe+0x49/0xbe Link: http://lkml.kernel.org/r/20200117181200.20299-1-cai@lca.pw Signed-off-by: Qian Cai Reviewed-by: David Hildenbrand Cc: Michal Hocko Cc: Sergey Senozhatsky Cc: Petr Mladek Cc: Steven Rostedt (VMware) Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 23 ++++++++++------------- 1 file changed, 10 insertions(+), 13 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3aec60ddd6d6..2a1a816c7992 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8185,13 +8185,17 @@ void *__init alloc_large_system_hash(const char *tablename, * MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable * check without lock_page also may miss some movable non-lru pages at * race condition. So you can't expect this function should be exact. + * + * Returns a page without holding a reference. If the caller wants to + * dereference that page (e.g., dumping), it has to make sure that that it + * cannot get removed (e.g., via memory unplug) concurrently. + * */ -bool has_unmovable_pages(struct zone *zone, struct page *page, int migratetype, - int flags) +struct page *has_unmovable_pages(struct zone *zone, struct page *page, + int migratetype, int flags) { unsigned long iter = 0; unsigned long pfn = page_to_pfn(page); - const char *reason = "unmovable page"; /* * TODO we could make this much more efficient by not checking every @@ -8208,9 +8212,8 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int migratetype, * so consider them movable here. */ if (is_migrate_cma(migratetype)) - return false; + return NULL; - reason = "CMA page"; goto unmovable; } @@ -8285,12 +8288,10 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int migratetype, */ goto unmovable; } - return false; + return NULL; unmovable: WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE); - if (flags & REPORT_FAILURE) - dump_page(pfn_to_page(pfn + iter), reason); - return true; + return pfn_to_page(pfn + iter); } #ifdef CONFIG_CONTIG_ALLOC @@ -8694,10 +8695,6 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) BUG_ON(!PageBuddy(page)); order = page_order(page); offlined_pages += 1 << order; -#ifdef CONFIG_DEBUG_VM - pr_info("remove from free list %lx %d %lx\n", - pfn, 1 << order, end_pfn); -#endif del_page_from_free_area(page, &zone->free_area[order]); pfn += (1 << order); } -- cgit v1.2.3 From 3d680bdf60a5bade3e8cbd049927e7f8b1d3fe97 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 30 Jan 2020 22:15:01 -0800 Subject: mm/page_isolation: fix potential warning from user It makes sense to call the WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE) from start_isolate_page_range(), but should avoid triggering it from userspace, i.e, from is_mem_section_removable() because it could crash the system by a non-root user if warn_on_panic is set. While at it, simplify the code a bit by removing an unnecessary jump label. Link: http://lkml.kernel.org/r/20200120163915.1469-1-cai@lca.pw Signed-off-by: Qian Cai Suggested-by: Michal Hocko Acked-by: Michal Hocko Reviewed-by: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2a1a816c7992..15e908ad933b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8214,7 +8214,7 @@ struct page *has_unmovable_pages(struct zone *zone, struct page *page, if (is_migrate_cma(migratetype)) return NULL; - goto unmovable; + return page; } for (; iter < pageblock_nr_pages; iter++) { @@ -8224,7 +8224,7 @@ struct page *has_unmovable_pages(struct zone *zone, struct page *page, page = pfn_to_page(pfn + iter); if (PageReserved(page)) - goto unmovable; + return page; /* * If the zone is movable and we have ruled out all reserved @@ -8244,7 +8244,7 @@ struct page *has_unmovable_pages(struct zone *zone, struct page *page, unsigned int skip_pages; if (!hugepage_migration_supported(page_hstate(head))) - goto unmovable; + return page; skip_pages = compound_nr(head) - (page - head); iter += skip_pages - 1; @@ -8286,12 +8286,9 @@ struct page *has_unmovable_pages(struct zone *zone, struct page *page, * is set to both of a memory hole page and a _used_ kernel * page at boot. */ - goto unmovable; + return page; } return NULL; -unmovable: - WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE); - return pfn_to_page(pfn + iter); } #ifdef CONFIG_CONTIG_ALLOC -- cgit v1.2.3