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 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 --- include/linux/page-isolation.h | 4 ++-- mm/memory_hotplug.c | 2 +- mm/page_alloc.c | 21 +++++++-------------- mm/page_isolation.c | 2 +- 4 files changed, 11 insertions(+), 18 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 6861df759fad..148e65a9c606 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -33,8 +33,8 @@ static inline bool is_migrate_isolate(int migratetype) #define MEMORY_OFFLINE 0x1 #define REPORT_FAILURE 0x2 -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); void set_pageblock_migratetype(struct page *page, int migratetype); int move_freepages_block(struct zone *zone, struct page *page, int migratetype, int *num_movable); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 0ddff29079c3..c3dc6b27fd6d 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1182,7 +1182,7 @@ static bool is_pageblock_removable_nolock(unsigned long pfn) if (!zone_spans_pfn(zone, pfn)) return false; - return !has_unmovable_pages(zone, page, 0, MIGRATE_MOVABLE, + return !has_unmovable_pages(zone, page, MIGRATE_MOVABLE, MEMORY_OFFLINE); } 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: diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 21af88b718aa..1f8b9dfecbe8 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -37,7 +37,7 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_ * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself. * We just check MOVABLE pages. */ - if (!has_unmovable_pages(zone, page, 0, migratetype, isol_flags)) { + if (!has_unmovable_pages(zone, page, migratetype, isol_flags)) { unsigned long nr_pages; int mt = get_pageblock_migratetype(page); -- cgit 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 --- include/linux/page-isolation.h | 4 ++-- mm/debug.c | 10 +++++++++- mm/page_alloc.c | 23 ++++++++++------------- mm/page_isolation.c | 11 ++++++++++- 4 files changed, 31 insertions(+), 17 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 148e65a9c606..572458016331 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -33,8 +33,8 @@ static inline bool is_migrate_isolate(int migratetype) #define MEMORY_OFFLINE 0x1 #define REPORT_FAILURE 0x2 -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); void set_pageblock_migratetype(struct page *page, int migratetype); int move_freepages_block(struct zone *zone, struct page *page, int migratetype, int *num_movable); diff --git a/mm/debug.c b/mm/debug.c index 4a9ded0d3504..ecccd9f17801 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -46,6 +46,13 @@ void __dump_page(struct page *page, const char *reason) { struct address_space *mapping; bool page_poisoned = PagePoisoned(page); + /* + * Accessing the pageblock without the zone lock. It could change to + * "isolate" again in the meantime, but since we are just dumping the + * state for debugging, it should be fine to accept a bit of + * inaccuracy here due to racing. + */ + bool page_cma = is_migrate_cma_page(page); int mapcount; char *type = ""; @@ -92,7 +99,8 @@ void __dump_page(struct page *page, const char *reason) } BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS + 1); - pr_warn("%sflags: %#lx(%pGp)\n", type, page->flags, &page->flags); + pr_warn("%sflags: %#lx(%pGp)%s\n", type, page->flags, &page->flags, + page_cma ? " CMA" : ""); hex_only: print_hex_dump(KERN_WARNING, "raw: ", DUMP_PREFIX_NONE, 32, 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); } diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 1f8b9dfecbe8..e70586523ca3 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -17,6 +17,7 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_flags) { + struct page *unmovable = NULL; struct zone *zone; unsigned long flags; int ret = -EBUSY; @@ -37,7 +38,8 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_ * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself. * We just check MOVABLE pages. */ - if (!has_unmovable_pages(zone, page, migratetype, isol_flags)) { + unmovable = has_unmovable_pages(zone, page, migratetype, isol_flags); + if (!unmovable) { unsigned long nr_pages; int mt = get_pageblock_migratetype(page); @@ -54,6 +56,13 @@ out: spin_unlock_irqrestore(&zone->lock, flags); if (!ret) drain_all_pages(zone); + else if ((isol_flags & REPORT_FAILURE) && unmovable) + /* + * printk() with zone->lock held will guarantee to trigger a + * lockdep splat, so defer it here. + */ + dump_page(unmovable, "unmovable page"); + return ret; } -- cgit 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 ++++------- mm/page_isolation.c | 18 +++++++++++------- 2 files changed, 15 insertions(+), 14 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 diff --git a/mm/page_isolation.c b/mm/page_isolation.c index e70586523ca3..a9fd7c740c23 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -54,14 +54,18 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_ out: spin_unlock_irqrestore(&zone->lock, flags); - if (!ret) + if (!ret) { drain_all_pages(zone); - else if ((isol_flags & REPORT_FAILURE) && unmovable) - /* - * printk() with zone->lock held will guarantee to trigger a - * lockdep splat, so defer it here. - */ - dump_page(unmovable, "unmovable page"); + } else { + WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE); + + if ((isol_flags & REPORT_FAILURE) && unmovable) + /* + * printk() with zone->lock held will likely trigger a + * lockdep splat, so defer it here. + */ + dump_page(unmovable, "unmovable page"); + } return ret; } -- cgit From e822969cab48b786b64246aad1a3ba2a774f5d23 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 3 Feb 2020 17:33:48 -0800 Subject: mm/page_alloc.c: fix uninitialized memmaps on a partially populated last section Patch series "mm: fix max_pfn not falling on section boundary", v2. Playing with different memory sizes for a x86-64 guest, I discovered that some memmaps (highest section if max_mem does not fall on the section boundary) are marked as being valid and online, but contain garbage. We have to properly initialize these memmaps. Looking at /proc/kpageflags and friends, I found some more issues, partially related to this. This patch (of 3): If max_pfn is not aligned to a section boundary, we can easily run into BUGs. This can e.g., be triggered on x86-64 under QEMU by specifying a memory size that is not a multiple of 128MB (e.g., 4097MB, but also 4160MB). I was told that on real HW, we can easily have this scenario (esp., one of the main reasons sub-section hotadd of devmem was added). The issue is, that we have a valid memmap (pfn_valid()) for the whole section, and the whole section will be marked "online". pfn_to_online_page() will succeed, but the memmap contains garbage. E.g., doing a "./page-types -r -a 0x144001" when QEMU was started with "-m 4160M" - (see tools/vm/page-types.c): [ 200.476376] BUG: unable to handle page fault for address: fffffffffffffffe [ 200.477500] #PF: supervisor read access in kernel mode [ 200.478334] #PF: error_code(0x0000) - not-present page [ 200.479076] PGD 59614067 P4D 59614067 PUD 59616067 PMD 0 [ 200.479557] Oops: 0000 [#4] SMP NOPTI [ 200.479875] CPU: 0 PID: 603 Comm: page-types Tainted: G D W 5.5.0-rc1-next-20191209 #93 [ 200.480646] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu4 [ 200.481648] RIP: 0010:stable_page_flags+0x4d/0x410 [ 200.482061] Code: f3 ff 41 89 c0 48 b8 00 00 00 00 01 00 00 00 45 84 c0 0f 85 cd 02 00 00 48 8b 53 08 48 8b 2b 48f [ 200.483644] RSP: 0018:ffffb139401cbe60 EFLAGS: 00010202 [ 200.484091] RAX: fffffffffffffffe RBX: fffffbeec5100040 RCX: 0000000000000000 [ 200.484697] RDX: 0000000000000001 RSI: ffffffff9535c7cd RDI: 0000000000000246 [ 200.485313] RBP: ffffffffffffffff R08: 0000000000000000 R09: 0000000000000000 [ 200.485917] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000144001 [ 200.486523] R13: 00007ffd6ba55f48 R14: 00007ffd6ba55f40 R15: ffffb139401cbf08 [ 200.487130] FS: 00007f68df717580(0000) GS:ffff9ec77fa00000(0000) knlGS:0000000000000000 [ 200.487804] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 200.488295] CR2: fffffffffffffffe CR3: 0000000135d48000 CR4: 00000000000006f0 [ 200.488897] Call Trace: [ 200.489115] kpageflags_read+0xe9/0x140 [ 200.489447] proc_reg_read+0x3c/0x60 [ 200.489755] vfs_read+0xc2/0x170 [ 200.490037] ksys_pread64+0x65/0xa0 [ 200.490352] do_syscall_64+0x5c/0xa0 [ 200.490665] entry_SYSCALL_64_after_hwframe+0x49/0xbe But it can be triggered much easier via "cat /proc/kpageflags > /dev/null" after cold/hot plugging a DIMM to such a system: [root@localhost ~]# cat /proc/kpageflags > /dev/null [ 111.517275] BUG: unable to handle page fault for address: fffffffffffffffe [ 111.517907] #PF: supervisor read access in kernel mode [ 111.518333] #PF: error_code(0x0000) - not-present page [ 111.518771] PGD a240e067 P4D a240e067 PUD a2410067 PMD 0 This patch fixes that by at least zero-ing out that memmap (so e.g., page_to_pfn() will not crash). Commit 907ec5fca3dc ("mm: zero remaining unavailable struct pages") tried to fix a similar issue, but forgot to consider this special case. After this patch, there are still problems to solve. E.g., not all of these pages falling into a memory hole will actually get initialized later and set PageReserved - they are only zeroed out - but at least the immediate crashes are gone. A follow-up patch will take care of this. Link: http://lkml.kernel.org/r/20191211163201.17179-2-david@redhat.com Fixes: f7f99100d8d9 ("mm: stop zeroing memory during allocation in vmemmap") Signed-off-by: David Hildenbrand Tested-by: Daniel Jordan Cc: Naoya Horiguchi Cc: Pavel Tatashin Cc: Andrew Morton Cc: Steven Sistare Cc: Michal Hocko Cc: Daniel Jordan Cc: Bob Picco Cc: Oscar Salvador Cc: Alexey Dobriyan Cc: Dan Williams Cc: Michal Hocko Cc: Stephen Rothwell Cc: [4.15+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 15e908ad933b..10eeaaadf53a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6947,7 +6947,8 @@ static u64 zero_pfn_range(unsigned long spfn, unsigned long epfn) * This function also addresses a similar issue where struct pages are left * uninitialized because the physical address range is not covered by * memblock.memory or memblock.reserved. That could happen when memblock - * layout is manually configured via memmap=. + * layout is manually configured via memmap=, or when the highest physical + * address (max_pfn) does not end on a section boundary. */ void __init zero_resv_unavail(void) { @@ -6965,7 +6966,16 @@ void __init zero_resv_unavail(void) pgcnt += zero_pfn_range(PFN_DOWN(next), PFN_UP(start)); next = end; } - pgcnt += zero_pfn_range(PFN_DOWN(next), max_pfn); + + /* + * Early sections always have a fully populated memmap for the whole + * section - see pfn_valid(). If the last section has holes at the + * end and that section is marked "online", the memmap will be + * considered initialized. Make sure that memmap has a well defined + * state. + */ + pgcnt += zero_pfn_range(PFN_DOWN(next), + round_up(max_pfn, PAGES_PER_SECTION)); /* * Struct pages that do not have backing memory. This could be because -- cgit From 4b094b7851bf4bf551ad456195d3f26e1c03bd74 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 3 Feb 2020 17:33:55 -0800 Subject: mm/page_alloc.c: initialize memmap of unavailable memory directly Let's make sure that all memory holes are actually marked PageReserved(), that page_to_pfn() produces reliable results, and that these pages are not detected as "mmap" pages due to the mapcount. E.g., booting a x86-64 QEMU guest with 4160 MB: [ 0.010585] Early memory node ranges [ 0.010586] node 0: [mem 0x0000000000001000-0x000000000009efff] [ 0.010588] node 0: [mem 0x0000000000100000-0x00000000bffdefff] [ 0.010589] node 0: [mem 0x0000000100000000-0x0000000143ffffff] max_pfn is 0x144000. Before this change: [root@localhost ~]# ./page-types -r -a 0x144000, flags page-count MB symbolic-flags long-symbolic-flags 0x0000000000000800 16384 64 ___________M_______________________________ mmap total 16384 64 After this change: [root@localhost ~]# ./page-types -r -a 0x144000, flags page-count MB symbolic-flags long-symbolic-flags 0x0000000100000000 16384 64 ___________________________r_______________ reserved total 16384 64 IOW, especially the unavailable physical memory ("memory hole") in the last section would not get properly marked PageReserved() and is indicated to be "mmap" memory. Drop the trace of that function from include/linux/mm.h - nobody else needs it, and rename it accordingly. Note: The fake zone/node might not be covered by the zone/node span. This is not an urgent issue (for now, we had the same node/zone due to the zeroing). We'll need a clean way to mark memory holes (e.g., using a page type PageHole() if possible or a fake ZONE_INVALID) and eventually stop marking these memory holes PageReserved(). Link: http://lkml.kernel.org/r/20191211163201.17179-4-david@redhat.com Signed-off-by: David Hildenbrand Cc: Oscar Salvador Cc: Michal Hocko Cc: Dan Williams Cc: Alexey Dobriyan Cc: Bob Picco Cc: Daniel Jordan Cc: Michal Hocko Cc: Naoya Horiguchi Cc: Pavel Tatashin Cc: Stephen Rothwell Cc: Steven Sistare Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 ------ mm/page_alloc.c | 33 ++++++++++++++++++++++----------- 2 files changed, 22 insertions(+), 17 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/include/linux/mm.h b/include/linux/mm.h index 73a044ed6981..080f8ac8bfb7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2182,12 +2182,6 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn, struct mminit_pfnnid_cache *state); #endif -#if !defined(CONFIG_FLAT_NODE_MEM_MAP) -void zero_resv_unavail(void); -#else -static inline void zero_resv_unavail(void) {} -#endif - extern void set_dma_reserve(unsigned long new_dma_reserve); extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long, enum memmap_context, struct vmem_altmap *); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 10eeaaadf53a..7d5b9dbf4087 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6916,10 +6916,10 @@ void __init free_area_init_node(int nid, unsigned long *zones_size, #if !defined(CONFIG_FLAT_NODE_MEM_MAP) /* - * Zero all valid struct pages in range [spfn, epfn), return number of struct - * pages zeroed + * Initialize all valid struct pages in the range [spfn, epfn) and mark them + * PageReserved(). Return the number of struct pages that were initialized. */ -static u64 zero_pfn_range(unsigned long spfn, unsigned long epfn) +static u64 __init init_unavailable_range(unsigned long spfn, unsigned long epfn) { unsigned long pfn; u64 pgcnt = 0; @@ -6930,7 +6930,13 @@ static u64 zero_pfn_range(unsigned long spfn, unsigned long epfn) + pageblock_nr_pages - 1; continue; } - mm_zero_struct_page(pfn_to_page(pfn)); + /* + * Use a fake node/zone (0) for now. Some of these pages + * (in memblock.reserved but not in memblock.memory) will + * get re-initialized via reserve_bootmem_region() later. + */ + __init_single_page(pfn_to_page(pfn), pfn, 0, 0); + __SetPageReserved(pfn_to_page(pfn)); pgcnt++; } @@ -6942,7 +6948,7 @@ static u64 zero_pfn_range(unsigned long spfn, unsigned long epfn) * initialized by going through __init_single_page(). But, there are some * struct pages which are reserved in memblock allocator and their fields * may be accessed (for example page_to_pfn() on some configuration accesses - * flags). We must explicitly zero those struct pages. + * flags). We must explicitly initialize those struct pages. * * This function also addresses a similar issue where struct pages are left * uninitialized because the physical address range is not covered by @@ -6950,7 +6956,7 @@ static u64 zero_pfn_range(unsigned long spfn, unsigned long epfn) * layout is manually configured via memmap=, or when the highest physical * address (max_pfn) does not end on a section boundary. */ -void __init zero_resv_unavail(void) +static void __init init_unavailable_mem(void) { phys_addr_t start, end; u64 i, pgcnt; @@ -6963,7 +6969,8 @@ void __init zero_resv_unavail(void) for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) { if (next < start) - pgcnt += zero_pfn_range(PFN_DOWN(next), PFN_UP(start)); + pgcnt += init_unavailable_range(PFN_DOWN(next), + PFN_UP(start)); next = end; } @@ -6974,8 +6981,8 @@ void __init zero_resv_unavail(void) * considered initialized. Make sure that memmap has a well defined * state. */ - pgcnt += zero_pfn_range(PFN_DOWN(next), - round_up(max_pfn, PAGES_PER_SECTION)); + pgcnt += init_unavailable_range(PFN_DOWN(next), + round_up(max_pfn, PAGES_PER_SECTION)); /* * Struct pages that do not have backing memory. This could be because @@ -6984,6 +6991,10 @@ void __init zero_resv_unavail(void) if (pgcnt) pr_info("Zeroed struct page in unavailable ranges: %lld pages", pgcnt); } +#else +static inline void __init init_unavailable_mem(void) +{ +} #endif /* !CONFIG_FLAT_NODE_MEM_MAP */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP @@ -7413,7 +7424,7 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) /* Initialise every node */ mminit_verify_pageflags_layout(); setup_nr_node_ids(); - zero_resv_unavail(); + init_unavailable_mem(); for_each_online_node(nid) { pg_data_t *pgdat = NODE_DATA(nid); free_area_init_node(nid, NULL, @@ -7608,7 +7619,7 @@ void __init set_dma_reserve(unsigned long new_dma_reserve) void __init free_area_init(unsigned long *zones_size) { - zero_resv_unavail(); + init_unavailable_mem(); free_area_init_node(0, zones_size, __pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL); } -- cgit From 948c436e463d34e0d716aff0f333bb74471e5399 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 3 Feb 2020 17:33:59 -0800 Subject: mm/page_alloc: fix and rework pfn handling in memmap_init_zone() Let's update the pfn manually whenever we continue the loop. This makes the code easier to read but also less error prone (and we can directly fix one issue). When overlap_memmap_init() returns true, pfn is updated to "memblock_region_memory_end_pfn(r)". So it already points at the *next* pfn to process. Incrementing the pfn another time is wrong, we might leave one uninitialized. I spotted this by inspecting the code, so I have no idea if this is relevant in practise (with kernelcore=mirror). Link: http://lkml.kernel.org/r/20200113144035.10848-2-david@redhat.com Fixes: a9a9e77fbf27 ("mm: move mirrored memory specific code outside of memmap_init_zone") Signed-off-by: David Hildenbrand Acked-by: Kirill A. Shutemov Reviewed-by: Alexander Duyck Cc: Pavel Tatashin Cc: Michal Hocko Cc: Oscar Salvador Cc: Kirill A. Shutemov Cc: Baoquan He Cc: Dan Williams Cc: Vlastimil Babka Cc: Mel Gorman Cc: "Jin, Zhi" Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7d5b9dbf4087..461ed73bc30f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5905,18 +5905,20 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, } #endif - for (pfn = start_pfn; pfn < end_pfn; pfn++) { + for (pfn = start_pfn; pfn < end_pfn; ) { /* * There can be holes in boot-time mem_map[]s handed to this * function. They do not exist on hotplugged memory. */ if (context == MEMMAP_EARLY) { if (!early_pfn_valid(pfn)) { - pfn = next_pfn(pfn) - 1; + pfn = next_pfn(pfn); continue; } - if (!early_pfn_in_nid(pfn, nid)) + if (!early_pfn_in_nid(pfn, nid)) { + pfn++; continue; + } if (overlap_memmap_init(zone, &pfn)) continue; if (defer_init(nid, pfn, end_pfn)) @@ -5944,6 +5946,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, set_pageblock_migratetype(page, MIGRATE_MOVABLE); cond_resched(); } + pfn++; } } -- cgit From 4c6058814ec4460c25111e29452ef596acdcd61b Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 3 Feb 2020 17:34:02 -0800 Subject: mm: factor out next_present_section_nr() Let's move it to the header and use the shorter variant from mm/page_alloc.c (the original one will also check "__highest_present_section_nr + 1", which is not necessary). While at it, make the section_nr in next_pfn() const. In next_pfn(), we now return section_nr_to_pfn(-1) instead of -1 once we exceed __highest_present_section_nr, which doesn't make a difference in the caller as it is big enough (>= all sane end_pfn). Link: http://lkml.kernel.org/r/20200113144035.10848-3-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Kirill A. Shutemov Cc: Baoquan He Cc: Dan Williams Cc: "Jin, Zhi" Cc: "Kirill A. Shutemov" Cc: Mel Gorman Cc: Michal Hocko Cc: Michal Hocko Cc: Oscar Salvador Cc: Pavel Tatashin Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 10 ++++++++++ mm/page_alloc.c | 11 ++--------- mm/sparse.c | 10 ---------- 3 files changed, 12 insertions(+), 19 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c2bc309d1634..462f6873905a 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1379,6 +1379,16 @@ static inline int pfn_present(unsigned long pfn) return present_section(__nr_to_section(pfn_to_section_nr(pfn))); } +static inline unsigned long next_present_section_nr(unsigned long section_nr) +{ + while (++section_nr <= __highest_present_section_nr) { + if (present_section_nr(section_nr)) + return section_nr; + } + + return -1; +} + /* * These are _only_ used during initialisation, therefore they * can use __initdata ... They could have names to indicate diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 461ed73bc30f..494f74a1725d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5852,18 +5852,11 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn) /* Skip PFNs that belong to non-present sections */ static inline __meminit unsigned long next_pfn(unsigned long pfn) { - unsigned long section_nr; + const unsigned long section_nr = pfn_to_section_nr(++pfn); - 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; + return section_nr_to_pfn(next_present_section_nr(section_nr)); } #else static inline __meminit unsigned long next_pfn(unsigned long pfn) diff --git a/mm/sparse.c b/mm/sparse.c index 3918fc3eaef1..c184b69460b7 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -198,16 +198,6 @@ static void section_mark_present(struct mem_section *ms) ms->section_mem_map |= SECTION_MARKED_PRESENT; } -static inline unsigned long next_present_section_nr(unsigned long section_nr) -{ - do { - section_nr++; - if (present_section_nr(section_nr)) - return section_nr; - } while ((section_nr <= __highest_present_section_nr)); - - return -1; -} #define for_each_present_section_nr(start, section_nr) \ for (section_nr = next_present_section_nr(start-1); \ ((section_nr != -1) && \ -- cgit From 1f8d75c1b7dc62f017c542ca99e7da4a0839fb1e Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Mon, 3 Feb 2020 17:34:06 -0800 Subject: mm/memmap_init: update variable name in memmap_init_zone Patch series "mm/memory_hotplug: Shrink zones before removing memory", v6. This series fixes the access of uninitialized memmaps when shrinking zones/nodes and when removing memory. Also, it contains all fixes for crashes that can be triggered when removing certain namespace using memunmap_pages() - ZONE_DEVICE, reported by Aneesh. We stop trying to shrink ZONE_DEVICE, as it's buggy, fixing it would be more involved (we don't have SECTION_IS_ONLINE as an indicator), and shrinking is only of limited use (set_zone_contiguous() cannot detect the ZONE_DEVICE as contiguous). We continue shrinking !ZONE_DEVICE zones, however, I reduced the amount of code to a minimum. Shrinking is especially necessary to keep zone->contiguous set where possible, especially, on memory unplug of DIMMs at zone boundaries. -------------------------------------------------------------------------- Zones are now properly shrunk when offlining memory blocks or when onlining failed. This allows to properly shrink zones on memory unplug even if the separate memory blocks of a DIMM were onlined to different zones or re-onlined to a different zone after offlining. Example: :/# cat /proc/zoneinfo Node 1, zone Movable spanned 0 present 0 managed 0 :/# echo "online_movable" > /sys/devices/system/memory/memory41/state :/# echo "online_movable" > /sys/devices/system/memory/memory43/state :/# cat /proc/zoneinfo Node 1, zone Movable spanned 98304 present 65536 managed 65536 :/# echo 0 > /sys/devices/system/memory/memory43/online :/# cat /proc/zoneinfo Node 1, zone Movable spanned 32768 present 32768 managed 32768 :/# echo 0 > /sys/devices/system/memory/memory41/online :/# cat /proc/zoneinfo Node 1, zone Movable spanned 0 present 0 managed 0 This patch (of 6): The third argument is actually number of pages. Change the variable name from size to nr_pages to indicate this better. No functional change in this patch. Link: http://lkml.kernel.org/r/20191006085646.5768-3-david@redhat.com Signed-off-by: Aneesh Kumar K.V Signed-off-by: David Hildenbrand Reviewed-by: Pankaj Gupta Reviewed-by: David Hildenbrand Cc: Michal Hocko Cc: "Matthew Wilcox (Oracle)" Cc: "Aneesh Kumar K.V" Cc: Pavel Tatashin Cc: Greg Kroah-Hartman Cc: Dan Williams Cc: Logan Gunthorpe Cc: Oscar Salvador Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 494f74a1725d..3c4eb750a199 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5946,10 +5946,10 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, #ifdef CONFIG_ZONE_DEVICE void __ref memmap_init_zone_device(struct zone *zone, unsigned long start_pfn, - unsigned long size, + unsigned long nr_pages, struct dev_pagemap *pgmap) { - unsigned long pfn, end_pfn = start_pfn + size; + unsigned long pfn, end_pfn = start_pfn + nr_pages; struct pglist_data *pgdat = zone->zone_pgdat; struct vmem_altmap *altmap = pgmap_altmap(pgmap); unsigned long zone_idx = zone_idx(zone); @@ -5966,7 +5966,7 @@ void __ref memmap_init_zone_device(struct zone *zone, */ if (altmap) { start_pfn = altmap->base_pfn + vmem_altmap_offset(altmap); - size = end_pfn - start_pfn; + nr_pages = end_pfn - start_pfn; } for (pfn = start_pfn; pfn < end_pfn; pfn++) { @@ -6013,7 +6013,7 @@ void __ref memmap_init_zone_device(struct zone *zone, } pr_info("%s initialised %lu pages in %ums\n", __func__, - size, jiffies_to_msecs(jiffies - start)); + nr_pages, jiffies_to_msecs(jiffies - start)); } #endif -- cgit