From bcf6f55a0d05eedd8ebb6ecc60ae3f93205ad833 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 5 Mar 2019 15:41:27 -0800 Subject: kasan: fix kasan_check_read/write definitions Building little-endian allmodconfig kernels on arm64 started failing with the generated atomic.h implementation, since we now try to call kasan helpers from the EFI stub: aarch64-linux-gnu-ld: drivers/firmware/efi/libstub/arm-stub.stub.o: in function `atomic_set': include/generated/atomic-instrumented.h:44: undefined reference to `__efistub_kasan_check_write' I suspect that we get similar problems in other files that explicitly disable KASAN for some reason but call atomic_t based helper functions. We can fix this by checking the predefined __SANITIZE_ADDRESS__ macro that the compiler sets instead of checking CONFIG_KASAN, but this in turn requires a small hack in mm/kasan/common.c so we do see the extern declaration there instead of the inline function. Link: http://lkml.kernel.org/r/20181211133453.2835077-1-arnd@arndb.de Fixes: b1864b828644 ("locking/atomics: build atomic headers as required") Signed-off-by: Arnd Bergmann Reported-by: Anders Roxell Acked-by: Andrey Ryabinin Cc: Ard Biesheuvel Cc: Will Deacon Cc: Mark Rutland Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Andrey Konovalov Cc: Stephen Rothwell , Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan-checks.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kasan-checks.h b/include/linux/kasan-checks.h index d314150658a4..a61dc075e2ce 100644 --- a/include/linux/kasan-checks.h +++ b/include/linux/kasan-checks.h @@ -2,7 +2,7 @@ #ifndef _LINUX_KASAN_CHECKS_H #define _LINUX_KASAN_CHECKS_H -#ifdef CONFIG_KASAN +#if defined(__SANITIZE_ADDRESS__) || defined(__KASAN_INTERNAL) void kasan_check_read(const volatile void *p, unsigned int size); void kasan_check_write(const volatile void *p, unsigned int size); #else -- cgit v1.2.3-71-gd317 From de810f490db7ed4c1db2bbfa458b2e27681d2ccb Mon Sep 17 00:00:00 2001 From: "Tobin C. Harding" Date: Tue, 5 Mar 2019 15:42:07 -0800 Subject: include/linux/slub_def.h: comment fixes Capitialize comment string, use C89 comment style, correct grammar/punctuation in comments. Link: http://lkml.kernel.org/r/20190204005713.9463-2-tobin@kernel.org Link: http://lkml.kernel.org/r/20190204005713.9463-3-tobin@kernel.org Link: http://lkml.kernel.org/r/20190204005713.9463-4-tobin@kernel.org Signed-off-by: Tobin C. Harding Reviewed-by: Andrew Morton Reviewed-by: William Kucharski Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slub_def.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 3a1a1dbc6f49..d2153789bd9f 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -81,12 +81,12 @@ struct kmem_cache_order_objects { */ struct kmem_cache { struct kmem_cache_cpu __percpu *cpu_slab; - /* Used for retriving partial slabs etc */ + /* Used for retrieving partial slabs, etc. */ slab_flags_t flags; unsigned long min_partial; - unsigned int size; /* The size of an object including meta data */ - unsigned int object_size;/* The size of an object without meta data */ - unsigned int offset; /* Free pointer offset. */ + unsigned int size; /* The size of an object including metadata */ + unsigned int object_size;/* The size of an object without metadata */ + unsigned int offset; /* Free pointer offset */ #ifdef CONFIG_SLUB_CPU_PARTIAL /* Number of per cpu partial objects to keep around */ unsigned int cpu_partial; @@ -110,7 +110,7 @@ struct kmem_cache { #endif #ifdef CONFIG_MEMCG struct memcg_cache_params memcg_params; - /* for propagation, maximum size of a stored attr */ + /* For propagation, maximum size of a stored attr */ unsigned int max_attr_size; #ifdef CONFIG_SYSFS struct kset *memcg_kset; @@ -151,7 +151,7 @@ struct kmem_cache { #else #define slub_cpu_partial(s) (0) #define slub_set_cpu_partial(s, n) -#endif // CONFIG_SLUB_CPU_PARTIAL +#endif /* CONFIG_SLUB_CPU_PARTIAL */ #ifdef CONFIG_SYSFS #define SLAB_SUPPORTS_SYSFS -- cgit v1.2.3-71-gd317 From a9cd410a3d296846a8125aa43d97a573a354c472 Mon Sep 17 00:00:00 2001 From: Arun KS Date: Tue, 5 Mar 2019 15:42:14 -0800 Subject: mm/page_alloc.c: memory hotplug: free pages as higher order When freeing pages are done with higher order, time spent on coalescing pages by buddy allocator can be reduced. With section size of 256MB, hot add latency of a single section shows improvement from 50-60 ms to less than 1 ms, hence improving the hot add latency by 60 times. Modify external providers of online callback to align with the change. [arunks@codeaurora.org: v11] Link: http://lkml.kernel.org/r/1547792588-18032-1-git-send-email-arunks@codeaurora.org [akpm@linux-foundation.org: remove unused local, per Arun] [akpm@linux-foundation.org: avoid return of void-returning __free_pages_core(), per Oscar] [akpm@linux-foundation.org: fix it for mm-convert-totalram_pages-and-totalhigh_pages-variables-to-atomic.patch] [arunks@codeaurora.org: v8] Link: http://lkml.kernel.org/r/1547032395-24582-1-git-send-email-arunks@codeaurora.org [arunks@codeaurora.org: v9] Link: http://lkml.kernel.org/r/1547098543-26452-1-git-send-email-arunks@codeaurora.org Link: http://lkml.kernel.org/r/1538727006-5727-1-git-send-email-arunks@codeaurora.org Signed-off-by: Arun KS Reviewed-by: Andrew Morton Acked-by: Michal Hocko Reviewed-by: Oscar Salvador Reviewed-by: Alexander Duyck Cc: K. Y. Srinivasan Cc: Haiyang Zhang Cc: Stephen Hemminger Cc: Boris Ostrovsky Cc: Juergen Gross Cc: Dan Williams Cc: Vlastimil Babka Cc: Joonsoo Kim Cc: Greg Kroah-Hartman Cc: Mathieu Malaterre Cc: "Kirill A. Shutemov" Cc: Souptick Joarder Cc: Mel Gorman Cc: Aaron Lu Cc: Srivatsa Vaddagiri Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/hv/hv_balloon.c | 7 ++++--- drivers/xen/balloon.c | 15 ++++++++++----- include/linux/memory_hotplug.h | 2 +- mm/internal.h | 1 + mm/memory_hotplug.c | 37 +++++++++++++++++++++++++------------ mm/page_alloc.c | 8 ++++---- 6 files changed, 45 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index 7c6349a50ef1..a50b7624b2a3 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -771,7 +771,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size, } } -static void hv_online_page(struct page *pg) +static void hv_online_page(struct page *pg, unsigned int order) { struct hv_hotadd_state *has; unsigned long flags; @@ -780,10 +780,11 @@ static void hv_online_page(struct page *pg) spin_lock_irqsave(&dm_device.ha_lock, flags); list_for_each_entry(has, &dm_device.ha_region_list, list) { /* The page belongs to a different HAS. */ - if ((pfn < has->start_pfn) || (pfn >= has->end_pfn)) + if ((pfn < has->start_pfn) || + (pfn + (1UL << order) > has->end_pfn)) continue; - hv_page_online_one(has, pg); + hv_bring_pgs_online(has, pfn, 1UL << order); break; } spin_unlock_irqrestore(&dm_device.ha_lock, flags); diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index ceb5048de9a7..d107447c47de 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -369,14 +369,19 @@ static enum bp_state reserve_additional_memory(void) return BP_ECANCELED; } -static void xen_online_page(struct page *page) +static void xen_online_page(struct page *page, unsigned int order) { - __online_page_set_limits(page); + unsigned long i, size = (1 << order); + unsigned long start_pfn = page_to_pfn(page); + struct page *p; + pr_debug("Online %lu pages starting at pfn 0x%lx\n", size, start_pfn); mutex_lock(&balloon_mutex); - - __balloon_append(page); - + for (i = 0; i < size; i++) { + p = pfn_to_page(start_pfn + i); + __online_page_set_limits(p); + __balloon_append(p); + } mutex_unlock(&balloon_mutex); } diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 368267c1b71b..52869d6d38b3 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -89,7 +89,7 @@ extern int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, unsigned long *valid_start, unsigned long *valid_end); extern void __offline_isolated_pages(unsigned long, unsigned long); -typedef void (*online_page_callback_t)(struct page *page); +typedef void (*online_page_callback_t)(struct page *page, unsigned int order); extern int set_online_page_callback(online_page_callback_t callback); extern int restore_online_page_callback(online_page_callback_t callback); diff --git a/mm/internal.h b/mm/internal.h index f4a7bb02decf..536bc2a839b9 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -163,6 +163,7 @@ static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn, extern int __isolate_free_page(struct page *page, unsigned int order); extern void memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order); +extern void __free_pages_core(struct page *page, unsigned int order); extern void prep_compound_page(struct page *page, unsigned int order); extern void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 1ad28323fb9f..4f07c8ddfdd7 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -47,7 +47,7 @@ * and restore_online_page_callback() for generic callback restore. */ -static void generic_online_page(struct page *page); +static void generic_online_page(struct page *page, unsigned int order); static online_page_callback_t online_page_callback = generic_online_page; static DEFINE_MUTEX(online_page_callback_lock); @@ -656,26 +656,39 @@ void __online_page_free(struct page *page) } EXPORT_SYMBOL_GPL(__online_page_free); -static void generic_online_page(struct page *page) +static void generic_online_page(struct page *page, unsigned int order) { - __online_page_set_limits(page); - __online_page_increment_counters(page); - __online_page_free(page); + __free_pages_core(page, order); + totalram_pages_add(1UL << order); +#ifdef CONFIG_HIGHMEM + if (PageHighMem(page)) + totalhigh_pages_add(1UL << order); +#endif +} + +static int online_pages_blocks(unsigned long start, unsigned long nr_pages) +{ + unsigned long end = start + nr_pages; + int order, onlined_pages = 0; + + while (start < end) { + order = min(MAX_ORDER - 1, + get_order(PFN_PHYS(end) - PFN_PHYS(start))); + (*online_page_callback)(pfn_to_page(start), order); + + onlined_pages += (1UL << order); + start += (1UL << order); + } + return onlined_pages; } static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages, void *arg) { - unsigned long i; unsigned long onlined_pages = *(unsigned long *)arg; - struct page *page; if (PageReserved(pfn_to_page(start_pfn))) - for (i = 0; i < nr_pages; i++) { - page = pfn_to_page(start_pfn + i); - (*online_page_callback)(page); - onlined_pages++; - } + onlined_pages += online_pages_blocks(start_pfn, nr_pages); online_mem_sections(start_pfn, start_pfn + nr_pages); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 10d0f2ed9f69..5361bd078493 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1303,7 +1303,7 @@ static void __free_pages_ok(struct page *page, unsigned int order) local_irq_restore(flags); } -static void __init __free_pages_boot_core(struct page *page, unsigned int order) +void __free_pages_core(struct page *page, unsigned int order) { unsigned int nr_pages = 1 << order; struct page *p = page; @@ -1382,7 +1382,7 @@ void __init memblock_free_pages(struct page *page, unsigned long pfn, { if (early_page_uninitialised(pfn)) return; - return __free_pages_boot_core(page, order); + __free_pages_core(page, order); } /* @@ -1472,14 +1472,14 @@ static void __init deferred_free_range(unsigned long pfn, if (nr_pages == pageblock_nr_pages && (pfn & (pageblock_nr_pages - 1)) == 0) { set_pageblock_migratetype(page, MIGRATE_MOVABLE); - __free_pages_boot_core(page, pageblock_order); + __free_pages_core(page, pageblock_order); return; } for (i = 0; i < nr_pages; i++, page++, pfn++) { if ((pfn & (pageblock_nr_pages - 1)) == 0) set_pageblock_migratetype(page, MIGRATE_MOVABLE); - __free_pages_boot_core(page, 0); + __free_pages_core(page, 0); } } -- cgit v1.2.3-71-gd317 From 4d3467e171f8a8ef8f1dd205769cf2f21fbc8e1e Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 5 Mar 2019 15:42:18 -0800 Subject: mm: balloon: update comment about isolation/migration/compaction Patch series "mm/kdump: allow to exclude pages that are logically offline" Right now, pages inflated as part of a balloon driver will be dumped by dump tools like makedumpfile. While XEN is able to check in the crash kernel whether a certain pfn is actuall backed by memory in the hypervisor (see xen_oldmem_pfn_is_ram) and optimize this case, dumps of virtio-balloon, hv-balloon and VMWare balloon inflated memory will essentially result in zero pages getting allocated by the hypervisor and the dump getting filled with this data. The allocation and reading of zero pages can directly be avoided if a dumping tool could know which pages only contain stale information not to be dumped. Also for XEN, calling into the kernel and asking the hypervisor if a pfn is backed can be avoided if the duming tool would skip such pages right from the beginning. Dumping tools have no idea whether a given page is part of a balloon driver and shall not be dumped. Esp. PG_reserved cannot be used for that purpose as all memory allocated during early boot is also PG_reserved, see discussion at [1]. So some other way of indication is required and a new page flag is frowned upon. We have PG_balloon (MAPCOUNT value), which is essentially unused now. I suggest renaming it to something more generic (PG_offline) to mark pages as logically offline. This flag can than e.g. also be used by virtio-mem in the future to mark subsections as offline. Or by other code that wants to put pages logically offline (e.g. later maybe poisoned pages that shall no longer be used). This series converts PG_balloon to PG_offline, allows dumping tools to query the value to detect such pages and marks pages in the hv-balloon and XEN balloon properly as PG_offline. Note that virtio-balloon already set pages to PG_balloon (and now PG_offline). Please note that this is also helpful for a problem we were seeing under Hyper-V: Dumping logically offline memory (pages kept fake offline while onlining a section via online_page_callback) would under some condicions result in a kernel panic when dumping them. As I don't have access to neither XEN nor Hyper-V nor VMWare installations, this was only tested with the virtio-balloon and pages were properly skipped when dumping. I'll also attach the makedumpfile patch to this series. [1] https://lkml.org/lkml/2018/7/20/566 This patch (of 8): Commit b1123ea6d3b3 ("mm: balloon: use general non-lru movable page feature") reworked balloon handling to make use of the general non-lru movable page feature. The big comment block in balloon_compaction.h contains quite some outdated information. Let's fix this. Link: http://lkml.kernel.org/r/20181119101616.8901-2-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Michael S. Tsirkin Cc: Matthew Wilcox Cc: Michal Hocko Cc: Alexander Duyck Cc: Alexey Dobriyan Cc: Arnd Bergmann Cc: Baoquan He Cc: Borislav Petkov Cc: Boris Ostrovsky Cc: Christian Hansen Cc: Dave Young Cc: David Rientjes Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Jonathan Corbet Cc: Juergen Gross Cc: Julien Freche Cc: Kairui Song Cc: Kazuhito Hagio Cc: "Kirill A. Shutemov" Cc: Konstantin Khlebnikov Cc: "K. Y. Srinivasan" Cc: Len Brown Cc: Lianbo Jiang Cc: Michal Hocko Cc: Mike Rapoport Cc: Miles Chen Cc: Nadav Amit Cc: Naoya Horiguchi Cc: Omar Sandoval Cc: Pankaj gupta Cc: Pavel Machek Cc: Pavel Tatashin Cc: Rafael J. Wysocki Cc: "Rafael J. Wysocki" Cc: Stefano Stabellini Cc: Stephen Hemminger Cc: Stephen Rothwell Cc: Vitaly Kuznetsov Cc: Vlastimil Babka Cc: Xavier Deguillard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/balloon_compaction.h | 26 +++++++++----------------- 1 file changed, 9 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h index 53051f3d8f25..cbe50da5a59d 100644 --- a/include/linux/balloon_compaction.h +++ b/include/linux/balloon_compaction.h @@ -4,15 +4,18 @@ * * Common interface definitions for making balloon pages movable by compaction. * - * Despite being perfectly possible to perform ballooned pages migration, they - * make a special corner case to compaction scans because balloon pages are not - * enlisted at any LRU list like the other pages we do compact / migrate. + * Balloon page migration makes use of the general non-lru movable page + * feature. + * + * page->private is used to reference the responsible balloon device. + * page->mapping is used in context of non-lru page migration to reference + * the address space operations for page isolation/migration/compaction. * * As the page isolation scanning step a compaction thread does is a lockless * procedure (from a page standpoint), it might bring some racy situations while * performing balloon page compaction. In order to sort out these racy scenarios * and safely perform balloon's page compaction and migration we must, always, - * ensure following these three simple rules: + * ensure following these simple rules: * * i. when updating a balloon's page ->mapping element, strictly do it under * the following lock order, independently of the far superior @@ -21,19 +24,8 @@ * +--spin_lock_irq(&b_dev_info->pages_lock); * ... page->mapping updates here ... * - * ii. before isolating or dequeueing a balloon page from the balloon device - * pages list, the page reference counter must be raised by one and the - * extra refcount must be dropped when the page is enqueued back into - * the balloon device page list, thus a balloon page keeps its reference - * counter raised only while it is under our special handling; - * - * iii. after the lockless scan step have selected a potential balloon page for - * isolation, re-test the PageBalloon mark and the PagePrivate flag - * under the proper page lock, to ensure isolating a valid balloon page - * (not yet isolated, nor under release procedure) - * - * iv. isolation or dequeueing procedure must clear PagePrivate flag under - * page lock together with removing page from balloon device page list. + * ii. isolation or dequeueing procedure must remove the page from balloon + * device page list under b_dev_info->pages_lock. * * The functions provided by this interface are placed to help on coping with * the aforementioned balloon page corner case, as well as to ensure the simple -- cgit v1.2.3-71-gd317 From ca215086b14b89a0e70fc211314944aa6ce50020 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 5 Mar 2019 15:42:23 -0800 Subject: mm: convert PG_balloon to PG_offline PG_balloon was introduced to implement page migration/compaction for pages inflated in virtio-balloon. Nowadays, it is only a marker that a page is part of virtio-balloon and therefore logically offline. We also want to make use of this flag in other balloon drivers - for inflated pages or when onlining a section but keeping some pages offline (e.g. used right now by XEN and Hyper-V via set_online_page_callback()). We are going to expose this flag to dump tools like makedumpfile. But instead of exposing PG_balloon, let's generalize the concept of marking pages as logically offline, so it can be reused for other purposes later on. Rename PG_balloon to PG_offline. This is an indicator that the page is logically offline, the content stale and that it should not be touched (e.g. a hypervisor would have to allocate backing storage in order for the guest to dump an unused page). We can then e.g. exclude such pages from dumps. We replace and reuse KPF_BALLOON (23), as this shouldn't really harm (and for now the semantics stay the same). In following patches, we will make use of this bit also in other balloon drivers. While at it, document PGTABLE. [akpm@linux-foundation.org: fix comment text, per David] Link: http://lkml.kernel.org/r/20181119101616.8901-3-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Konstantin Khlebnikov Acked-by: Michael S. Tsirkin Acked-by: Pankaj gupta Cc: Jonathan Corbet Cc: Alexey Dobriyan Cc: Mike Rapoport Cc: Christian Hansen Cc: Vlastimil Babka Cc: "Kirill A. Shutemov" Cc: Stephen Rothwell Cc: Matthew Wilcox Cc: Michal Hocko Cc: Pavel Tatashin Cc: Alexander Duyck Cc: Naoya Horiguchi Cc: Miles Chen Cc: David Rientjes Cc: Kazuhito Hagio Cc: Arnd Bergmann Cc: Baoquan He Cc: Borislav Petkov Cc: Boris Ostrovsky Cc: Dave Young Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Juergen Gross Cc: Julien Freche Cc: Kairui Song Cc: "K. Y. Srinivasan" Cc: Len Brown Cc: Lianbo Jiang Cc: Michal Hocko Cc: Nadav Amit Cc: Omar Sandoval Cc: Pavel Machek Cc: Rafael J. Wysocki Cc: "Rafael J. Wysocki" Cc: Stefano Stabellini Cc: Stephen Hemminger Cc: Vitaly Kuznetsov Cc: Xavier Deguillard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/mm/pagemap.rst | 9 ++++++--- fs/proc/page.c | 4 ++-- include/linux/balloon_compaction.h | 8 ++++---- include/linux/page-flags.h | 11 +++++++---- include/uapi/linux/kernel-page-flags.h | 2 +- tools/vm/page-types.c | 2 +- 6 files changed, 21 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/mm/pagemap.rst b/Documentation/admin-guide/mm/pagemap.rst index 3f7bade2c231..340a5aee9b80 100644 --- a/Documentation/admin-guide/mm/pagemap.rst +++ b/Documentation/admin-guide/mm/pagemap.rst @@ -75,9 +75,10 @@ number of times a page is mapped. 20. NOPAGE 21. KSM 22. THP - 23. BALLOON + 23. OFFLINE 24. ZERO_PAGE 25. IDLE + 26. PGTABLE * ``/proc/kpagecgroup``. This file contains a 64-bit inode number of the memory cgroup each page is charged to, indexed by PFN. Only available when @@ -118,8 +119,8 @@ Short descriptions to the page flags identical memory pages dynamically shared between one or more processes 22 - THP contiguous pages which construct transparent hugepages -23 - BALLOON - balloon compaction page +23 - OFFLINE + page is logically offline 24 - ZERO_PAGE zero page for pfn_zero or huge_zero page 25 - IDLE @@ -128,6 +129,8 @@ Short descriptions to the page flags Note that this flag may be stale in case the page was accessed via a PTE. To make sure the flag is up-to-date one has to read ``/sys/kernel/mm/page_idle/bitmap`` first. +26 - PGTABLE + page is in use as a page table IO related page flags --------------------- diff --git a/fs/proc/page.c b/fs/proc/page.c index 40b05e0d4274..544d1ee15aee 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -152,8 +152,8 @@ u64 stable_page_flags(struct page *page) else if (page_count(page) == 0 && is_free_buddy_page(page)) u |= 1 << KPF_BUDDY; - if (PageBalloon(page)) - u |= 1 << KPF_BALLOON; + if (PageOffline(page)) + u |= 1 << KPF_OFFLINE; if (PageTable(page)) u |= 1 << KPF_PGTABLE; diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h index cbe50da5a59d..f111c780ef1d 100644 --- a/include/linux/balloon_compaction.h +++ b/include/linux/balloon_compaction.h @@ -95,7 +95,7 @@ extern int balloon_page_migrate(struct address_space *mapping, static inline void balloon_page_insert(struct balloon_dev_info *balloon, struct page *page) { - __SetPageBalloon(page); + __SetPageOffline(page); __SetPageMovable(page, balloon->inode->i_mapping); set_page_private(page, (unsigned long)balloon); list_add(&page->lru, &balloon->pages); @@ -111,7 +111,7 @@ static inline void balloon_page_insert(struct balloon_dev_info *balloon, */ static inline void balloon_page_delete(struct page *page) { - __ClearPageBalloon(page); + __ClearPageOffline(page); __ClearPageMovable(page); set_page_private(page, 0); /* @@ -141,13 +141,13 @@ static inline gfp_t balloon_mapping_gfp_mask(void) static inline void balloon_page_insert(struct balloon_dev_info *balloon, struct page *page) { - __SetPageBalloon(page); + __SetPageOffline(page); list_add(&page->lru, &balloon->pages); } static inline void balloon_page_delete(struct page *page) { - __ClearPageBalloon(page); + __ClearPageOffline(page); list_del(&page->lru); } diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 39b4494e29f1..808b4183e30d 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -671,7 +671,7 @@ PAGEFLAG_FALSE(DoubleMap) /* Reserve 0x0000007f to catch underflows of page_mapcount */ #define PAGE_MAPCOUNT_RESERVE -128 #define PG_buddy 0x00000080 -#define PG_balloon 0x00000100 +#define PG_offline 0x00000100 #define PG_kmemcg 0x00000200 #define PG_table 0x00000400 @@ -706,10 +706,13 @@ static __always_inline void __ClearPage##uname(struct page *page) \ PAGE_TYPE_OPS(Buddy, buddy) /* - * PageBalloon() is true for pages that are on the balloon page list - * (see mm/balloon_compaction.c). + * PageOffline() indicates that the page is logically offline although the + * containing section is online. (e.g. inflated in a balloon driver or + * not onlined when onlining the section). + * The content of these pages is effectively stale. Such pages should not + * be touched (read/write/dump/save) except by their owner. */ -PAGE_TYPE_OPS(Balloon, balloon) +PAGE_TYPE_OPS(Offline, offline) /* * If kmemcg is enabled, the buddy allocator will set PageKmemcg() on diff --git a/include/uapi/linux/kernel-page-flags.h b/include/uapi/linux/kernel-page-flags.h index 21b9113c69da..6f2f2720f3ac 100644 --- a/include/uapi/linux/kernel-page-flags.h +++ b/include/uapi/linux/kernel-page-flags.h @@ -32,7 +32,7 @@ #define KPF_KSM 21 #define KPF_THP 22 -#define KPF_BALLOON 23 +#define KPF_OFFLINE 23 #define KPF_ZERO_PAGE 24 #define KPF_IDLE 25 #define KPF_PGTABLE 26 diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c index 1ff3a6c0367b..6f64b2b93234 100644 --- a/tools/vm/page-types.c +++ b/tools/vm/page-types.c @@ -133,7 +133,7 @@ static const char * const page_flag_names[] = { [KPF_NOPAGE] = "n:nopage", [KPF_KSM] = "x:ksm", [KPF_THP] = "t:thp", - [KPF_BALLOON] = "o:balloon", + [KPF_OFFLINE] = "o:offline", [KPF_PGTABLE] = "g:pgtable", [KPF_ZERO_PAGE] = "z:zero_page", [KPF_IDLE] = "i:idle_page", -- cgit v1.2.3-71-gd317 From 98fa15f34cb379864757670b8e8743b21456a20e Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Tue, 5 Mar 2019 15:42:58 -0800 Subject: mm: replace all open encodings for NUMA_NO_NODE Patch series "Replace all open encodings for NUMA_NO_NODE", v3. All these places for replacement were found by running the following grep patterns on the entire kernel code. Please let me know if this might have missed some instances. This might also have replaced some false positives. I will appreciate suggestions, inputs and review. 1. git grep "nid == -1" 2. git grep "node == -1" 3. git grep "nid = -1" 4. git grep "node = -1" This patch (of 2): At present there are multiple places where invalid node number is encoded as -1. Even though implicitly understood it is always better to have macros in there. Replace these open encodings for an invalid node number with the global macro NUMA_NO_NODE. This helps remove NUMA related assumptions like 'invalid node' from various places redirecting them to a common definition. Link: http://lkml.kernel.org/r/1545127933-10711-2-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Reviewed-by: David Hildenbrand Acked-by: Jeff Kirsher [ixgbe] Acked-by: Jens Axboe [mtip32xx] Acked-by: Vinod Koul [dmaengine.c] Acked-by: Michael Ellerman [powerpc] Acked-by: Doug Ledford [drivers/infiniband] Cc: Joseph Qi Cc: Hans Verkuil Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/include/asm/topology.h | 3 ++- arch/ia64/kernel/numa.c | 2 +- arch/ia64/mm/discontig.c | 6 +++--- arch/powerpc/include/asm/pci-bridge.h | 3 ++- arch/powerpc/kernel/paca.c | 3 ++- arch/powerpc/kernel/pci-common.c | 3 ++- arch/powerpc/mm/numa.c | 14 +++++++------- arch/powerpc/platforms/powernv/memtrace.c | 5 +++-- arch/sparc/kernel/pci_fire.c | 3 ++- arch/sparc/kernel/pci_schizo.c | 3 ++- arch/sparc/kernel/psycho_common.c | 3 ++- arch/sparc/kernel/sbus.c | 3 ++- arch/sparc/mm/init_64.c | 6 +++--- arch/x86/include/asm/pci.h | 3 ++- arch/x86/kernel/apic/x2apic_uv_x.c | 7 ++++--- arch/x86/kernel/smpboot.c | 3 ++- drivers/block/mtip32xx/mtip32xx.c | 5 +++-- drivers/dma/dmaengine.c | 4 +++- drivers/infiniband/hw/hfi1/affinity.c | 3 ++- drivers/infiniband/hw/hfi1/init.c | 3 ++- drivers/iommu/dmar.c | 5 +++-- drivers/iommu/intel-iommu.c | 3 ++- drivers/misc/sgi-xp/xpc_uv.c | 3 ++- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 5 +++-- include/linux/device.h | 2 +- init/init_task.c | 3 ++- kernel/kthread.c | 3 ++- kernel/sched/fair.c | 15 ++++++++------- lib/cpumask.c | 3 ++- mm/huge_memory.c | 13 +++++++------ mm/hugetlb.c | 3 ++- mm/ksm.c | 2 +- mm/memory.c | 7 ++++--- mm/memory_hotplug.c | 12 ++++++------ mm/mempolicy.c | 2 +- mm/page_alloc.c | 4 ++-- mm/page_ext.c | 2 +- net/core/pktgen.c | 3 ++- net/qrtr/qrtr.c | 3 ++- 39 files changed, 104 insertions(+), 74 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/include/asm/topology.h b/arch/alpha/include/asm/topology.h index e6e13a85796a..5a77a40567fa 100644 --- a/arch/alpha/include/asm/topology.h +++ b/arch/alpha/include/asm/topology.h @@ -4,6 +4,7 @@ #include #include +#include #include #ifdef CONFIG_NUMA @@ -29,7 +30,7 @@ static const struct cpumask *cpumask_of_node(int node) { int cpu; - if (node == -1) + if (node == NUMA_NO_NODE) return cpu_all_mask; cpumask_clear(&node_to_cpumask_map[node]); diff --git a/arch/ia64/kernel/numa.c b/arch/ia64/kernel/numa.c index 92c376279c6d..1315da6c7aeb 100644 --- a/arch/ia64/kernel/numa.c +++ b/arch/ia64/kernel/numa.c @@ -74,7 +74,7 @@ void __init build_cpu_to_node_map(void) cpumask_clear(&node_to_cpu_mask[node]); for_each_possible_early_cpu(cpu) { - node = -1; + node = NUMA_NO_NODE; for (i = 0; i < NR_CPUS; ++i) if (cpu_physical_id(cpu) == node_cpuid[i].phys_id) { node = node_cpuid[i].nid; diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index 8a965784340c..f9c36750c6a4 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -227,7 +227,7 @@ void __init setup_per_cpu_areas(void) * CPUs are put into groups according to node. Walk cpu_map * and create new groups at node boundaries. */ - prev_node = -1; + prev_node = NUMA_NO_NODE; ai->nr_groups = 0; for (unit = 0; unit < nr_units; unit++) { cpu = cpu_map[unit]; @@ -435,7 +435,7 @@ static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize) { void *ptr = NULL; u8 best = 0xff; - int bestnode = -1, node, anynode = 0; + int bestnode = NUMA_NO_NODE, node, anynode = 0; for_each_online_node(node) { if (node_isset(node, memory_less_mask)) @@ -447,7 +447,7 @@ static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize) anynode = node; } - if (bestnode == -1) + if (bestnode == NUMA_NO_NODE) bestnode = anynode; ptr = memblock_alloc_try_nid(pernodesize, PERCPU_PAGE_SIZE, diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index aee4fcc24990..77fc21278fa2 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -10,6 +10,7 @@ #include #include #include +#include struct device_node; @@ -265,7 +266,7 @@ extern int pcibios_map_io_space(struct pci_bus *bus); #ifdef CONFIG_NUMA #define PHB_SET_NODE(PHB, NODE) ((PHB)->node = (NODE)) #else -#define PHB_SET_NODE(PHB, NODE) ((PHB)->node = -1) +#define PHB_SET_NODE(PHB, NODE) ((PHB)->node = NUMA_NO_NODE) #endif #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 913bfca09c4f..b8480127793d 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -36,7 +37,7 @@ static void *__init alloc_paca_data(unsigned long size, unsigned long align, * which will put its paca in the right place. */ if (cpu == boot_cpuid) { - nid = -1; + nid = NUMA_NO_NODE; memblock_set_bottom_up(true); } else { nid = early_cpu_to_node(cpu); diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 88e4f69a09e5..4538e8ddde80 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include @@ -132,7 +133,7 @@ struct pci_controller *pcibios_alloc_controller(struct device_node *dev) int nid = of_node_to_nid(dev); if (nid < 0 || !node_online(nid)) - nid = -1; + nid = NUMA_NO_NODE; PHB_SET_NODE(phb, nid); } diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 87f0dd004295..270cefb75cca 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -215,7 +215,7 @@ static void initialize_distance_lookup_table(int nid, */ static int associativity_to_nid(const __be32 *associativity) { - int nid = -1; + int nid = NUMA_NO_NODE; if (min_common_depth == -1) goto out; @@ -225,7 +225,7 @@ static int associativity_to_nid(const __be32 *associativity) /* POWER4 LPAR uses 0xffff as invalid node */ if (nid == 0xffff || nid >= MAX_NUMNODES) - nid = -1; + nid = NUMA_NO_NODE; if (nid > 0 && of_read_number(associativity, 1) >= distance_ref_points_depth) { @@ -244,7 +244,7 @@ out: */ static int of_node_to_nid_single(struct device_node *device) { - int nid = -1; + int nid = NUMA_NO_NODE; const __be32 *tmp; tmp = of_get_associativity(device); @@ -256,7 +256,7 @@ static int of_node_to_nid_single(struct device_node *device) /* Walk the device tree upwards, looking for an associativity id */ int of_node_to_nid(struct device_node *device) { - int nid = -1; + int nid = NUMA_NO_NODE; of_node_get(device); while (device) { @@ -454,7 +454,7 @@ static int of_drconf_to_nid_single(struct drmem_lmb *lmb) */ static int numa_setup_cpu(unsigned long lcpu) { - int nid = -1; + int nid = NUMA_NO_NODE; struct device_node *cpu; /* @@ -930,7 +930,7 @@ static int hot_add_drconf_scn_to_nid(unsigned long scn_addr) { struct drmem_lmb *lmb; unsigned long lmb_size; - int nid = -1; + int nid = NUMA_NO_NODE; lmb_size = drmem_lmb_size(); @@ -960,7 +960,7 @@ static int hot_add_drconf_scn_to_nid(unsigned long scn_addr) static int hot_add_node_scn_to_nid(unsigned long scn_addr) { struct device_node *memory; - int nid = -1; + int nid = NUMA_NO_NODE; for_each_node_by_type(memory, "memory") { unsigned long start, size; diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c index 84d038ed3882..248a38ad25c7 100644 --- a/arch/powerpc/platforms/powernv/memtrace.c +++ b/arch/powerpc/platforms/powernv/memtrace.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -223,7 +224,7 @@ static int memtrace_online(void) ent = &memtrace_array[i]; /* We have onlined this chunk previously */ - if (ent->nid == -1) + if (ent->nid == NUMA_NO_NODE) continue; /* Remove from io mappings */ @@ -257,7 +258,7 @@ static int memtrace_online(void) */ debugfs_remove_recursive(ent->dir); pr_info("Added trace memory back to node %d\n", ent->nid); - ent->size = ent->start = ent->nid = -1; + ent->size = ent->start = ent->nid = NUMA_NO_NODE; } if (ret) return ret; diff --git a/arch/sparc/kernel/pci_fire.c b/arch/sparc/kernel/pci_fire.c index be71ae086622..0ca08d455e80 100644 --- a/arch/sparc/kernel/pci_fire.c +++ b/arch/sparc/kernel/pci_fire.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -416,7 +417,7 @@ static int pci_fire_pbm_init(struct pci_pbm_info *pbm, struct device_node *dp = op->dev.of_node; int err; - pbm->numa_node = -1; + pbm->numa_node = NUMA_NO_NODE; pbm->pci_ops = &sun4u_pci_ops; pbm->config_space_reg_bits = 12; diff --git a/arch/sparc/kernel/pci_schizo.c b/arch/sparc/kernel/pci_schizo.c index 934b97c72f7c..421aba00e6b0 100644 --- a/arch/sparc/kernel/pci_schizo.c +++ b/arch/sparc/kernel/pci_schizo.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include @@ -1347,7 +1348,7 @@ static int schizo_pbm_init(struct pci_pbm_info *pbm, pbm->next = pci_pbm_root; pci_pbm_root = pbm; - pbm->numa_node = -1; + pbm->numa_node = NUMA_NO_NODE; pbm->pci_ops = &sun4u_pci_ops; pbm->config_space_reg_bits = 8; diff --git a/arch/sparc/kernel/psycho_common.c b/arch/sparc/kernel/psycho_common.c index 81aa91e5c0e6..e90bcb6bad7f 100644 --- a/arch/sparc/kernel/psycho_common.c +++ b/arch/sparc/kernel/psycho_common.c @@ -5,6 +5,7 @@ */ #include #include +#include #include @@ -454,7 +455,7 @@ void psycho_pbm_init_common(struct pci_pbm_info *pbm, struct platform_device *op struct device_node *dp = op->dev.of_node; pbm->name = dp->full_name; - pbm->numa_node = -1; + pbm->numa_node = NUMA_NO_NODE; pbm->chip_type = chip_type; pbm->chip_version = of_getintprop_default(dp, "version#", 0); pbm->chip_revision = of_getintprop_default(dp, "module-revision#", 0); diff --git a/arch/sparc/kernel/sbus.c b/arch/sparc/kernel/sbus.c index 41c5deb581b8..32141e1006c4 100644 --- a/arch/sparc/kernel/sbus.c +++ b/arch/sparc/kernel/sbus.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -561,7 +562,7 @@ static void __init sbus_iommu_init(struct platform_device *op) op->dev.archdata.iommu = iommu; op->dev.archdata.stc = strbuf; - op->dev.archdata.numa_node = -1; + op->dev.archdata.numa_node = NUMA_NO_NODE; reg_base = regs + SYSIO_IOMMUREG_BASE; iommu->iommu_control = reg_base + IOMMU_CONTROL; diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index b4221d3727d0..9e6bd868ba6f 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -976,13 +976,13 @@ static u64 __init memblock_nid_range_sun4u(u64 start, u64 end, int *nid) { int prev_nid, new_nid; - prev_nid = -1; + prev_nid = NUMA_NO_NODE; for ( ; start < end; start += PAGE_SIZE) { for (new_nid = 0; new_nid < num_node_masks; new_nid++) { struct node_mem_mask *p = &node_masks[new_nid]; if ((start & p->mask) == p->match) { - if (prev_nid == -1) + if (prev_nid == NUMA_NO_NODE) prev_nid = new_nid; break; } @@ -1208,7 +1208,7 @@ int of_node_to_nid(struct device_node *dp) md = mdesc_grab(); count = 0; - nid = -1; + nid = NUMA_NO_NODE; mdesc_for_each_node_by_name(md, grp, "group") { if (!scan_arcs_for_cfg_handle(md, grp, cfg_handle)) { nid = count; diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 662963681ea6..e662f987dfa2 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -141,7 +142,7 @@ cpumask_of_pcibus(const struct pci_bus *bus) int node; node = __pcibus_to_node(bus); - return (node == -1) ? cpu_online_mask : + return (node == NUMA_NO_NODE) ? cpu_online_mask : cpumask_of_node(node); } #endif diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index a555da094157..1e225528f0d7 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include @@ -1390,7 +1391,7 @@ static void __init build_socket_tables(void) } /* Set socket -> node values: */ - lnid = -1; + lnid = NUMA_NO_NODE; for_each_present_cpu(cpu) { int nid = cpu_to_node(cpu); int apicid, sockid; @@ -1521,7 +1522,7 @@ static void __init uv_system_init_hub(void) new_hub->pnode = 0xffff; new_hub->numa_blade_id = uv_node_to_blade_id(nodeid); - new_hub->memory_nid = -1; + new_hub->memory_nid = NUMA_NO_NODE; new_hub->nr_possible_cpus = 0; new_hub->nr_online_cpus = 0; } @@ -1538,7 +1539,7 @@ static void __init uv_system_init_hub(void) uv_cpu_info_per(cpu)->p_uv_hub_info = uv_hub_info_list(nodeid); uv_cpu_info_per(cpu)->blade_cpu_id = uv_cpu_hub_info(cpu)->nr_possible_cpus++; - if (uv_cpu_hub_info(cpu)->memory_nid == -1) + if (uv_cpu_hub_info(cpu)->memory_nid == NUMA_NO_NODE) uv_cpu_hub_info(cpu)->memory_nid = cpu_to_node(cpu); /* Init memoryless node: */ diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index ccd1f2a8e557..c91ff9f9fe8a 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -56,6 +56,7 @@ #include #include #include +#include #include #include @@ -841,7 +842,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) /* reduce the number of lines printed when booting a large cpu count system */ static void announce_cpu(int cpu, int apicid) { - static int current_node = -1; + static int current_node = NUMA_NO_NODE; int node = early_cpu_to_node(cpu); static int width, node_width; diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 88e8440e75c3..2f3ee4d6af82 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -40,6 +40,7 @@ #include #include #include +#include #include "mtip32xx.h" #define HW_CMD_SLOT_SZ (MTIP_MAX_COMMAND_SLOTS * 32) @@ -4018,9 +4019,9 @@ static int get_least_used_cpu_on_node(int node) /* Helper for selecting a node in round robin mode */ static inline int mtip_get_next_rr_node(void) { - static int next_node = -1; + static int next_node = NUMA_NO_NODE; - if (next_node == -1) { + if (next_node == NUMA_NO_NODE) { next_node = first_online_node; return next_node; } diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index f1a441ab395d..3a11b1092e80 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -63,6 +63,7 @@ #include #include #include +#include static DEFINE_MUTEX(dma_list_mutex); static DEFINE_IDA(dma_ida); @@ -386,7 +387,8 @@ EXPORT_SYMBOL(dma_issue_pending_all); static bool dma_chan_is_local(struct dma_chan *chan, int cpu) { int node = dev_to_node(chan->device->dev); - return node == -1 || cpumask_test_cpu(cpu, cpumask_of_node(node)); + return node == NUMA_NO_NODE || + cpumask_test_cpu(cpu, cpumask_of_node(node)); } /** diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c index 2baf38cc1e23..4fe662c3bbc1 100644 --- a/drivers/infiniband/hw/hfi1/affinity.c +++ b/drivers/infiniband/hw/hfi1/affinity.c @@ -48,6 +48,7 @@ #include #include #include +#include #include "hfi.h" #include "affinity.h" @@ -777,7 +778,7 @@ void hfi1_dev_affinity_clean_up(struct hfi1_devdata *dd) _dev_comp_vect_cpu_mask_clean_up(dd, entry); unlock: mutex_unlock(&node_affinity.lock); - dd->node = -1; + dd->node = NUMA_NO_NODE; } /* diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c index 7835eb52e7c5..441b06e2a154 100644 --- a/drivers/infiniband/hw/hfi1/init.c +++ b/drivers/infiniband/hw/hfi1/init.c @@ -54,6 +54,7 @@ #include #include #include +#include #include #include "hfi.h" @@ -1303,7 +1304,7 @@ static struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, dd->unit = ret; list_add(&dd->list, &hfi1_dev_list); } - dd->node = -1; + dd->node = NUMA_NO_NODE; spin_unlock_irqrestore(&hfi1_devs_lock, flags); idr_preload_end(); diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 58dc70bffd5b..9c49300e9fb7 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -39,6 +39,7 @@ #include #include #include +#include #include #include @@ -477,7 +478,7 @@ static int dmar_parse_one_rhsa(struct acpi_dmar_header *header, void *arg) int node = acpi_map_pxm_to_node(rhsa->proximity_domain); if (!node_online(node)) - node = -1; + node = NUMA_NO_NODE; drhd->iommu->node = node; return 0; } @@ -1062,7 +1063,7 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd) iommu->msagaw = msagaw; iommu->segment = drhd->segment; - iommu->node = -1; + iommu->node = NUMA_NO_NODE; ver = readl(iommu->reg + DMAR_VER_REG); pr_info("%s: reg_base_addr %llx ver %d:%d cap %llx ecap %llx\n", diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 78188bf7e90d..39a33dec4d0b 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -47,6 +47,7 @@ #include #include #include +#include #include #include #include @@ -1716,7 +1717,7 @@ static struct dmar_domain *alloc_domain(int flags) return NULL; memset(domain, 0, sizeof(*domain)); - domain->nid = -1; + domain->nid = NUMA_NO_NODE; domain->flags = flags; domain->has_iotlb_device = false; INIT_LIST_HEAD(&domain->devices); diff --git a/drivers/misc/sgi-xp/xpc_uv.c b/drivers/misc/sgi-xp/xpc_uv.c index 0441abe87880..9e443df44b3b 100644 --- a/drivers/misc/sgi-xp/xpc_uv.c +++ b/drivers/misc/sgi-xp/xpc_uv.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #if defined CONFIG_X86_64 #include @@ -61,7 +62,7 @@ static struct xpc_heartbeat_uv *xpc_heartbeat_uv; XPC_NOTIFY_MSG_SIZE_UV) #define XPC_NOTIFY_IRQ_NAME "xpc_notify" -static int xpc_mq_node = -1; +static int xpc_mq_node = NUMA_NO_NODE; static struct xpc_gru_mq_uv *xpc_activate_mq_uv; static struct xpc_gru_mq_uv *xpc_notify_mq_uv; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index a4e7584a50cb..e100054a3765 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -6418,7 +6419,7 @@ int ixgbe_setup_tx_resources(struct ixgbe_ring *tx_ring) { struct device *dev = tx_ring->dev; int orig_node = dev_to_node(dev); - int ring_node = -1; + int ring_node = NUMA_NO_NODE; int size; size = sizeof(struct ixgbe_tx_buffer) * tx_ring->count; @@ -6512,7 +6513,7 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter, { struct device *dev = rx_ring->dev; int orig_node = dev_to_node(dev); - int ring_node = -1; + int ring_node = NUMA_NO_NODE; int size; size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count; diff --git a/include/linux/device.h b/include/linux/device.h index 6cb4640b6160..4d2f13e8c540 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1095,7 +1095,7 @@ static inline void set_dev_node(struct device *dev, int node) #else static inline int dev_to_node(struct device *dev) { - return -1; + return NUMA_NO_NODE; } static inline void set_dev_node(struct device *dev, int node) { diff --git a/init/init_task.c b/init/init_task.c index 5aebe3be4d7c..26131e73aa6d 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -154,7 +155,7 @@ struct task_struct init_task .vtime.state = VTIME_SYS, #endif #ifdef CONFIG_NUMA_BALANCING - .numa_preferred_nid = -1, + .numa_preferred_nid = NUMA_NO_NODE, .numa_group = NULL, .numa_faults = NULL, #endif diff --git a/kernel/kthread.c b/kernel/kthread.c index 087d18d771b5..ebebbcf3c5de 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -20,6 +20,7 @@ #include #include #include +#include #include static DEFINE_SPINLOCK(kthread_create_lock); @@ -675,7 +676,7 @@ __kthread_create_worker(int cpu, unsigned int flags, { struct kthread_worker *worker; struct task_struct *task; - int node = -1; + int node = NUMA_NO_NODE; worker = kzalloc(sizeof(*worker), GFP_KERNEL); if (!worker) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 310d0637fe4b..0e6a0ef129c5 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1160,7 +1160,7 @@ void init_numa_balancing(unsigned long clone_flags, struct task_struct *p) /* New address space, reset the preferred nid */ if (!(clone_flags & CLONE_VM)) { - p->numa_preferred_nid = -1; + p->numa_preferred_nid = NUMA_NO_NODE; return; } @@ -1180,13 +1180,13 @@ void init_numa_balancing(unsigned long clone_flags, struct task_struct *p) static void account_numa_enqueue(struct rq *rq, struct task_struct *p) { - rq->nr_numa_running += (p->numa_preferred_nid != -1); + rq->nr_numa_running += (p->numa_preferred_nid != NUMA_NO_NODE); rq->nr_preferred_running += (p->numa_preferred_nid == task_node(p)); } static void account_numa_dequeue(struct rq *rq, struct task_struct *p) { - rq->nr_numa_running -= (p->numa_preferred_nid != -1); + rq->nr_numa_running -= (p->numa_preferred_nid != NUMA_NO_NODE); rq->nr_preferred_running -= (p->numa_preferred_nid == task_node(p)); } @@ -1400,7 +1400,7 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page, * two full passes of the "multi-stage node selection" test that is * executed below. */ - if ((p->numa_preferred_nid == -1 || p->numa_scan_seq <= 4) && + if ((p->numa_preferred_nid == NUMA_NO_NODE || p->numa_scan_seq <= 4) && (cpupid_pid_unset(last_cpupid) || cpupid_match_pid(p, last_cpupid))) return true; @@ -1848,7 +1848,7 @@ static void numa_migrate_preferred(struct task_struct *p) unsigned long interval = HZ; /* This task has no NUMA fault statistics yet */ - if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults)) + if (unlikely(p->numa_preferred_nid == NUMA_NO_NODE || !p->numa_faults)) return; /* Periodically retry migrating the task to the preferred node */ @@ -2095,7 +2095,7 @@ static int preferred_group_nid(struct task_struct *p, int nid) static void task_numa_placement(struct task_struct *p) { - int seq, nid, max_nid = -1; + int seq, nid, max_nid = NUMA_NO_NODE; unsigned long max_faults = 0; unsigned long fault_types[2] = { 0, 0 }; unsigned long total_faults; @@ -2638,7 +2638,8 @@ static void update_scan_period(struct task_struct *p, int new_cpu) * the preferred node. */ if (dst_nid == p->numa_preferred_nid || - (p->numa_preferred_nid != -1 && src_nid != p->numa_preferred_nid)) + (p->numa_preferred_nid != NUMA_NO_NODE && + src_nid != p->numa_preferred_nid)) return; } diff --git a/lib/cpumask.c b/lib/cpumask.c index 8d666ab84b5c..087a3e9a0202 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -5,6 +5,7 @@ #include #include #include +#include /** * cpumask_next - get the next cpu in a cpumask @@ -206,7 +207,7 @@ unsigned int cpumask_local_spread(unsigned int i, int node) /* Wrap: we always want a cpu. */ i %= num_online_cpus(); - if (node == -1) { + if (node == NUMA_NO_NODE) { for_each_cpu(cpu, cpu_online_mask) if (i-- == 0) return cpu; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index faf357eaf0ce..d066f7ca1ee8 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include @@ -1475,7 +1476,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) struct anon_vma *anon_vma = NULL; struct page *page; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; - int page_nid = -1, this_nid = numa_node_id(); + int page_nid = NUMA_NO_NODE, this_nid = numa_node_id(); int target_nid, last_cpupid = -1; bool page_locked; bool migrated = false; @@ -1520,7 +1521,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) */ page_locked = trylock_page(page); target_nid = mpol_misplaced(page, vma, haddr); - if (target_nid == -1) { + if (target_nid == NUMA_NO_NODE) { /* If the page was locked, there are no parallel migrations */ if (page_locked) goto clear_pmdnuma; @@ -1528,7 +1529,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) /* Migration could have started since the pmd_trans_migrating check */ if (!page_locked) { - page_nid = -1; + page_nid = NUMA_NO_NODE; if (!get_page_unless_zero(page)) goto out_unlock; spin_unlock(vmf->ptl); @@ -1549,14 +1550,14 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) if (unlikely(!pmd_same(pmd, *vmf->pmd))) { unlock_page(page); put_page(page); - page_nid = -1; + page_nid = NUMA_NO_NODE; goto out_unlock; } /* Bail if we fail to protect against THP splits for any reason */ if (unlikely(!anon_vma)) { put_page(page); - page_nid = -1; + page_nid = NUMA_NO_NODE; goto clear_pmdnuma; } @@ -1618,7 +1619,7 @@ out: if (anon_vma) page_unlock_anon_vma_read(anon_vma); - if (page_nid != -1) + if (page_nid != NUMA_NO_NODE) task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, flags); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 8dfdffc34a99..3c504fa6b460 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include @@ -887,7 +888,7 @@ static struct page *dequeue_huge_page_nodemask(struct hstate *h, gfp_t gfp_mask, struct zonelist *zonelist; struct zone *zone; struct zoneref *z; - int node = -1; + int node = NUMA_NO_NODE; zonelist = node_zonelist(nid, gfp_mask); diff --git a/mm/ksm.c b/mm/ksm.c index 6c48ad13b4c9..fd2db6a74d3c 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -598,7 +598,7 @@ static struct stable_node *alloc_stable_node_chain(struct stable_node *dup, chain->chain_prune_time = jiffies; chain->rmap_hlist_len = STABLE_NODE_CHAIN; #if defined (CONFIG_DEBUG_VM) && defined(CONFIG_NUMA) - chain->nid = -1; /* debug */ + chain->nid = NUMA_NO_NODE; /* debug */ #endif ksm_stable_node_chains++; diff --git a/mm/memory.c b/mm/memory.c index e11ca9dd823f..eb40f32295d2 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -69,6 +69,7 @@ #include #include #include +#include #include #include @@ -3586,7 +3587,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct page *page = NULL; - int page_nid = -1; + int page_nid = NUMA_NO_NODE; int last_cpupid; int target_nid; bool migrated = false; @@ -3653,7 +3654,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) target_nid = numa_migrate_prep(page, vma, vmf->address, page_nid, &flags); pte_unmap_unlock(vmf->pte, vmf->ptl); - if (target_nid == -1) { + if (target_nid == NUMA_NO_NODE) { put_page(page); goto out; } @@ -3667,7 +3668,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf) flags |= TNF_MIGRATE_FAIL; out: - if (page_nid != -1) + if (page_nid != NUMA_NO_NODE) task_numa_fault(last_cpupid, page_nid, 1, flags); return 0; } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 4f07c8ddfdd7..b3d3c64d15df 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -702,9 +702,9 @@ static void node_states_check_changes_online(unsigned long nr_pages, { int nid = zone_to_nid(zone); - arg->status_change_nid = -1; - arg->status_change_nid_normal = -1; - arg->status_change_nid_high = -1; + arg->status_change_nid = NUMA_NO_NODE; + arg->status_change_nid_normal = NUMA_NO_NODE; + arg->status_change_nid_high = NUMA_NO_NODE; if (!node_state(nid, N_MEMORY)) arg->status_change_nid = nid; @@ -1509,9 +1509,9 @@ static void node_states_check_changes_offline(unsigned long nr_pages, unsigned long present_pages = 0; enum zone_type zt; - arg->status_change_nid = -1; - arg->status_change_nid_normal = -1; - arg->status_change_nid_high = -1; + arg->status_change_nid = NUMA_NO_NODE; + arg->status_change_nid_normal = NUMA_NO_NODE; + arg->status_change_nid_high = NUMA_NO_NODE; /* * Check whether node_states[N_NORMAL_MEMORY] will be changed. diff --git a/mm/mempolicy.c b/mm/mempolicy.c index ee2bce59d2bf..76e7e4bc3335 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2304,7 +2304,7 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long unsigned long pgoff; int thiscpu = raw_smp_processor_id(); int thisnid = cpu_to_node(thiscpu); - int polnid = -1; + int polnid = NUMA_NO_NODE; int ret = -1; pol = get_vma_policy(vma, addr); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5361bd078493..1f9f1409df9b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6016,7 +6016,7 @@ int __meminit __early_pfn_to_nid(unsigned long pfn, return state->last_nid; nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn); - if (nid != -1) { + if (nid != NUMA_NO_NODE) { state->last_start = start_pfn; state->last_end = end_pfn; state->last_nid = nid; @@ -6771,7 +6771,7 @@ unsigned long __init node_map_pfn_alignment(void) { unsigned long accl_mask = 0, last_end = 0; unsigned long start, end, mask; - int last_nid = -1; + int last_nid = NUMA_NO_NODE; int i, nid; for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) { diff --git a/mm/page_ext.c b/mm/page_ext.c index 8c78b8d45117..762d5b7eb523 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -300,7 +300,7 @@ static int __meminit online_page_ext(unsigned long start_pfn, start = SECTION_ALIGN_DOWN(start_pfn); end = SECTION_ALIGN_UP(start_pfn + nr_pages); - if (nid == -1) { + if (nid == NUMA_NO_NODE) { /* * In this case, "nid" already exists and contains valid memory. * "start_pfn" passed to us is a pfn which is an arg for diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 6ac919847ce6..f3f5a78cd062 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -158,6 +158,7 @@ #include #include #include +#include #include #include #include @@ -3625,7 +3626,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) pkt_dev->svlan_cfi = 0; pkt_dev->svlan_id = 0xffff; pkt_dev->burst = 1; - pkt_dev->node = -1; + pkt_dev->node = NUMA_NO_NODE; err = pktgen_setup_dev(t->net, pkt_dev, ifname); if (err) diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 86e1e37eb4e8..b37e6e0a1026 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -15,6 +15,7 @@ #include #include #include /* For TIOCINQ/OUTQ */ +#include #include @@ -101,7 +102,7 @@ static inline struct qrtr_sock *qrtr_sk(struct sock *sk) return container_of(sk, struct qrtr_sock, sk); } -static unsigned int qrtr_local_nid = -1; +static unsigned int qrtr_local_nid = NUMA_NO_NODE; /* for node ids */ static RADIX_TREE(qrtr_nodes, GFP_KERNEL); -- cgit v1.2.3-71-gd317 From 52d1e606ee733921e984770d47539a6bb91e8506 Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Tue, 5 Mar 2019 15:43:06 -0800 Subject: mm: reuse only-pte-mapped KSM page in do_wp_page() Add an optimization for KSM pages almost in the same way that we have for ordinary anonymous pages. If there is a write fault in a page, which is mapped to an only pte, and it is not related to swap cache; the page may be reused without copying its content. [ Note that we do not consider PageSwapCache() pages at least for now, since we don't want to complicate __get_ksm_page(), which has nice optimization based on this (for the migration case). Currenly it is spinning on PageSwapCache() pages, waiting for when they have unfreezed counters (i.e., for the migration finish). But we don't want to make it also spinning on swap cache pages, which we try to reuse, since there is not a very high probability to reuse them. So, for now we do not consider PageSwapCache() pages at all. ] So in reuse_ksm_page() we check for 1) PageSwapCache() and 2) page_stable_node(), to skip a page, which KSM is currently trying to link to stable tree. Then we do page_ref_freeze() to prohibit KSM to merge one more page into the page, we are reusing. After that, nobody can refer to the reusing page: KSM skips !PageSwapCache() pages with zero refcount; and the protection against of all other participants is the same as for reused ordinary anon pages pte lock, page lock and mmap_sem. [akpm@linux-foundation.org: replace BUG_ON()s with WARN_ON()s] Link: http://lkml.kernel.org/r/154471491016.31352.1168978849911555609.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai Reviewed-by: Yang Shi Cc: "Kirill A. Shutemov" Cc: Hugh Dickins Cc: Andrea Arcangeli Cc: Christian Koenig Cc: Claudio Imbrenda Cc: Rik van Riel Cc: Huang Ying Cc: Minchan Kim Cc: Kirill Tkhai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ksm.h | 7 +++++++ mm/ksm.c | 30 ++++++++++++++++++++++++++++-- mm/memory.c | 16 ++++++++++++++-- 3 files changed, 49 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 161e8164abcf..e48b1e453ff5 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -53,6 +53,8 @@ struct page *ksm_might_need_to_copy(struct page *page, void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc); void ksm_migrate_page(struct page *newpage, struct page *oldpage); +bool reuse_ksm_page(struct page *page, + struct vm_area_struct *vma, unsigned long address); #else /* !CONFIG_KSM */ @@ -86,6 +88,11 @@ static inline void rmap_walk_ksm(struct page *page, static inline void ksm_migrate_page(struct page *newpage, struct page *oldpage) { } +static inline bool reuse_ksm_page(struct page *page, + struct vm_area_struct *vma, unsigned long address) +{ + return false; +} #endif /* CONFIG_MMU */ #endif /* !CONFIG_KSM */ diff --git a/mm/ksm.c b/mm/ksm.c index fd2db6a74d3c..983fbac24bda 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -706,8 +706,9 @@ again: * case this node is no longer referenced, and should be freed; * however, it might mean that the page is under page_ref_freeze(). * The __remove_mapping() case is easy, again the node is now stale; - * but if page is swapcache in migrate_page_move_mapping(), it might - * still be our page, in which case it's essential to keep the node. + * the same is in reuse_ksm_page() case; but if page is swapcache + * in migrate_page_move_mapping(), it might still be our page, + * in which case it's essential to keep the node. */ while (!get_page_unless_zero(page)) { /* @@ -2642,6 +2643,31 @@ again: goto again; } +bool reuse_ksm_page(struct page *page, + struct vm_area_struct *vma, + unsigned long address) +{ +#ifdef CONFIG_DEBUG_VM + if (WARN_ON(is_zero_pfn(page_to_pfn(page))) || + WARN_ON(!page_mapped(page)) || + WARN_ON(!PageLocked(page))) { + dump_page(page, "reuse_ksm_page"); + return false; + } +#endif + + if (PageSwapCache(page) || !page_stable_node(page)) + return false; + /* Prohibit parallel get_ksm_page() */ + if (!page_ref_freeze(page, 1)) + return false; + + page_move_anon_rmap(page, vma); + page->index = linear_page_index(vma, address); + page_ref_unfreeze(page, 1); + + return true; +} #ifdef CONFIG_MIGRATION void ksm_migrate_page(struct page *newpage, struct page *oldpage) { diff --git a/mm/memory.c b/mm/memory.c index eb40f32295d2..222da66f16b4 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2505,8 +2505,11 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) * Take out anonymous pages first, anonymous shared vmas are * not dirty accountable. */ - if (PageAnon(vmf->page) && !PageKsm(vmf->page)) { + if (PageAnon(vmf->page)) { int total_map_swapcount; + if (PageKsm(vmf->page) && (PageSwapCache(vmf->page) || + page_count(vmf->page) != 1)) + goto copy; if (!trylock_page(vmf->page)) { get_page(vmf->page); pte_unmap_unlock(vmf->pte, vmf->ptl); @@ -2521,6 +2524,15 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) } put_page(vmf->page); } + if (PageKsm(vmf->page)) { + bool reused = reuse_ksm_page(vmf->page, vmf->vma, + vmf->address); + unlock_page(vmf->page); + if (!reused) + goto copy; + wp_page_reuse(vmf); + return VM_FAULT_WRITE; + } if (reuse_swap_page(vmf->page, &total_map_swapcount)) { if (total_map_swapcount == 1) { /* @@ -2541,7 +2553,7 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) (VM_WRITE|VM_SHARED))) { return wp_page_shared(vmf); } - +copy: /* * Ok, we need to copy. Oh, well.. */ -- cgit v1.2.3-71-gd317 From 60cd4bcd62384cfa1e5890cebacccf08b3161156 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Tue, 5 Mar 2019 15:43:13 -0800 Subject: memcg: localize memcg_kmem_enabled() check Move the memcg_kmem_enabled() checks into memcg kmem charge/uncharge functions, so, the users don't have to explicitly check that condition. This is purely code cleanup patch without any functional change. Only the order of checks in memcg_charge_slab() can potentially be changed but the functionally it will be same. This should not matter as memcg_charge_slab() is not in the hot path. Link: http://lkml.kernel.org/r/20190103161203.162375-1-shakeelb@google.com Signed-off-by: Shakeel Butt Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Vladimir Davydov Cc: Roman Gushchin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/pipe.c | 3 +-- include/linux/memcontrol.h | 37 +++++++++++++++++++++++++++++++++---- mm/memcontrol.c | 16 ++++++++-------- mm/page_alloc.c | 4 ++-- mm/slab.h | 4 ---- 5 files changed, 44 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/fs/pipe.c b/fs/pipe.c index bdc5d3c0977d..51d5fd8840ab 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -140,8 +140,7 @@ static int anon_pipe_buf_steal(struct pipe_inode_info *pipe, struct page *page = buf->page; if (page_count(page) == 1) { - if (memcg_kmem_enabled()) - memcg_kmem_uncharge(page, 0); + memcg_kmem_uncharge(page, 0); __SetPageLocked(page); return 0; } diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 83ae11cbd12c..b0eb29ea0d9c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1273,12 +1273,12 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep); void memcg_kmem_put_cache(struct kmem_cache *cachep); -int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, - struct mem_cgroup *memcg); #ifdef CONFIG_MEMCG_KMEM -int memcg_kmem_charge(struct page *page, gfp_t gfp, int order); -void memcg_kmem_uncharge(struct page *page, int order); +int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order); +void __memcg_kmem_uncharge(struct page *page, int order); +int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, + struct mem_cgroup *memcg); extern struct static_key_false memcg_kmem_enabled_key; extern struct workqueue_struct *memcg_kmem_cache_wq; @@ -1300,6 +1300,26 @@ static inline bool memcg_kmem_enabled(void) return static_branch_unlikely(&memcg_kmem_enabled_key); } +static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) +{ + if (memcg_kmem_enabled()) + return __memcg_kmem_charge(page, gfp, order); + return 0; +} + +static inline void memcg_kmem_uncharge(struct page *page, int order) +{ + if (memcg_kmem_enabled()) + __memcg_kmem_uncharge(page, order); +} + +static inline int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, + int order, struct mem_cgroup *memcg) +{ + if (memcg_kmem_enabled()) + return __memcg_kmem_charge_memcg(page, gfp, order, memcg); + return 0; +} /* * helper for accessing a memcg's index. It will be used as an index in the * child cache array in kmem_cache, and also to derive its name. This function @@ -1325,6 +1345,15 @@ static inline void memcg_kmem_uncharge(struct page *page, int order) { } +static inline int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order) +{ + return 0; +} + +static inline void __memcg_kmem_uncharge(struct page *page, int order) +{ +} + #define for_each_memcg_cache_index(_idx) \ for (; NULL; ) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index af7f18b32389..72414bb7e226 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2573,7 +2573,7 @@ void memcg_kmem_put_cache(struct kmem_cache *cachep) } /** - * memcg_kmem_charge_memcg: charge a kmem page + * __memcg_kmem_charge_memcg: charge a kmem page * @page: page to charge * @gfp: reclaim mode * @order: allocation order @@ -2581,7 +2581,7 @@ void memcg_kmem_put_cache(struct kmem_cache *cachep) * * Returns 0 on success, an error code on failure. */ -int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, +int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, struct mem_cgroup *memcg) { unsigned int nr_pages = 1 << order; @@ -2604,24 +2604,24 @@ int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, } /** - * memcg_kmem_charge: charge a kmem page to the current memory cgroup + * __memcg_kmem_charge: charge a kmem page to the current memory cgroup * @page: page to charge * @gfp: reclaim mode * @order: allocation order * * Returns 0 on success, an error code on failure. */ -int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) +int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order) { struct mem_cgroup *memcg; int ret = 0; - if (mem_cgroup_disabled() || memcg_kmem_bypass()) + if (memcg_kmem_bypass()) return 0; memcg = get_mem_cgroup_from_current(); if (!mem_cgroup_is_root(memcg)) { - ret = memcg_kmem_charge_memcg(page, gfp, order, memcg); + ret = __memcg_kmem_charge_memcg(page, gfp, order, memcg); if (!ret) __SetPageKmemcg(page); } @@ -2629,11 +2629,11 @@ int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) return ret; } /** - * memcg_kmem_uncharge: uncharge a kmem page + * __memcg_kmem_uncharge: uncharge a kmem page * @page: page to uncharge * @order: allocation order */ -void memcg_kmem_uncharge(struct page *page, int order) +void __memcg_kmem_uncharge(struct page *page, int order) { struct mem_cgroup *memcg = page->mem_cgroup; unsigned int nr_pages = 1 << order; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 1f9f1409df9b..034b8b6043a3 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1056,7 +1056,7 @@ static __always_inline bool free_pages_prepare(struct page *page, if (PageMappingFlags(page)) page->mapping = NULL; if (memcg_kmem_enabled() && PageKmemcg(page)) - memcg_kmem_uncharge(page, order); + __memcg_kmem_uncharge(page, order); if (check_free) bad += free_pages_check(page); if (bad) @@ -4568,7 +4568,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid, out: if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page && - unlikely(memcg_kmem_charge(page, gfp_mask, order) != 0)) { + unlikely(__memcg_kmem_charge(page, gfp_mask, order) != 0)) { __free_pages(page, order); page = NULL; } diff --git a/mm/slab.h b/mm/slab.h index 384105318779..e5e6658eeacc 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -276,8 +276,6 @@ static __always_inline int memcg_charge_slab(struct page *page, gfp_t gfp, int order, struct kmem_cache *s) { - if (!memcg_kmem_enabled()) - return 0; if (is_root_cache(s)) return 0; return memcg_kmem_charge_memcg(page, gfp, order, s->memcg_params.memcg); @@ -286,8 +284,6 @@ static __always_inline int memcg_charge_slab(struct page *page, static __always_inline void memcg_uncharge_slab(struct page *page, int order, struct kmem_cache *s) { - if (!memcg_kmem_enabled()) - return; memcg_kmem_uncharge(page, order); } -- cgit v1.2.3-71-gd317 From 6b7e5cad651a2b1031a4c69a98f87e3532dd4cef Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 5 Mar 2019 15:43:41 -0800 Subject: mm: remove sysctl_extfrag_handler() sysctl_extfrag_handler() neglects to propagate the return value from proc_dointvec_minmax() to its caller. It's a wrapper that doesn't need to exist, so just use proc_dointvec_minmax() directly. Link: http://lkml.kernel.org/r/20190104032557.3056-1-willy@infradead.org Signed-off-by: Matthew Wilcox Reported-by: Aditya Pakki Acked-by: Mel Gorman Acked-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 2 -- kernel/sysctl.c | 2 +- mm/compaction.c | 8 -------- 3 files changed, 1 insertion(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 68250a57aace..70d0256edd31 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -88,8 +88,6 @@ extern int sysctl_compact_memory; extern int sysctl_compaction_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); extern int sysctl_extfrag_threshold; -extern int sysctl_extfrag_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos); extern int sysctl_compact_unevictable_allowed; extern int fragmentation_index(struct zone *zone, unsigned int order); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 7578e21a711b..9c78e06f7ba4 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1460,7 +1460,7 @@ static struct ctl_table vm_table[] = { .data = &sysctl_extfrag_threshold, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = sysctl_extfrag_handler, + .proc_handler = proc_dointvec_minmax, .extra1 = &min_extfrag_threshold, .extra2 = &max_extfrag_threshold, }, diff --git a/mm/compaction.c b/mm/compaction.c index ef29490b0f46..c15b4bbc9e9e 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1876,14 +1876,6 @@ int sysctl_compaction_handler(struct ctl_table *table, int write, return 0; } -int sysctl_extfrag_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *length, loff_t *ppos) -{ - proc_dointvec_minmax(table, write, buffer, length, ppos); - - return 0; -} - #if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) static ssize_t sysfs_compact_node(struct device *dev, struct device_attribute *attr, -- cgit v1.2.3-71-gd317 From 7ed2c31dabdeb3ee6abe8ff5aac7287821a50cba Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Tue, 5 Mar 2019 15:43:44 -0800 Subject: mm/hugetlb: distinguish between migratability and movability Patch series "arm64/mm: Enable HugeTLB migration", v4. This patch series enables HugeTLB migration support for all supported huge page sizes at all levels including contiguous bit implementation. Following HugeTLB migration support matrix has been enabled with this patch series. All permutations have been tested except for the 16GB. CONT PTE PMD CONT PMD PUD -------- --- -------- --- 4K: 64K 2M 32M 1G 16K: 2M 32M 1G 64K: 2M 512M 16G First the series adds migration support for PUD based huge pages. It then adds a platform specific hook to query an architecture if a given huge page size is supported for migration while also providing a default fallback option preserving the existing semantics which just checks for (PMD|PUD|PGDIR)_SHIFT macros. The last two patches enables HugeTLB migration on arm64 and subscribe to this new platform specific hook by defining an override. The second patch differentiates between movability and migratability aspects of huge pages and implements hugepage_movable_supported() which can then be used during allocation to decide whether to place the huge page in movable zone or not. This patch (of 5): During huge page allocation it's migratability is checked to determine if it should be placed under movable zones with GFP_HIGHUSER_MOVABLE. But the movability aspect of the huge page could depend on other factors than just migratability. Movability in itself is a distinct property which should not be tied with migratability alone. This differentiates these two and implements an enhanced movability check which also considers huge page size to determine if it is feasible to be placed under a movable zone. At present it just checks for gigantic pages but going forward it can incorporate other enhanced checks. Link: http://lkml.kernel.org/r/1545121450-1663-2-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Reviewed-by: Steve Capper Reviewed-by: Naoya Horiguchi Suggested-by: Michal Hocko Acked-by: Michal Hocko Cc: Catalin Marinas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 30 ++++++++++++++++++++++++++++++ mm/hugetlb.c | 2 +- mm/migrate.c | 2 +- 3 files changed, 32 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 087fd5f48c91..1b858d795731 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -506,6 +506,31 @@ static inline bool hugepage_migration_supported(struct hstate *h) #endif } +/* + * Movability check is different as compared to migration check. + * It determines whether or not a huge page should be placed on + * movable zone or not. Movability of any huge page should be + * required only if huge page size is supported for migration. + * There wont be any reason for the huge page to be movable if + * it is not migratable to start with. Also the size of the huge + * page should be large enough to be placed under a movable zone + * and still feasible enough to be migratable. Just the presence + * in movable zone does not make the migration feasible. + * + * So even though large huge page sizes like the gigantic ones + * are migratable they should not be movable because its not + * feasible to migrate them from movable zone. + */ +static inline bool hugepage_movable_supported(struct hstate *h) +{ + if (!hugepage_migration_supported(h)) + return false; + + if (hstate_is_gigantic(h)) + return false; + return true; +} + static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { @@ -602,6 +627,11 @@ static inline bool hugepage_migration_supported(struct hstate *h) return false; } +static inline bool hugepage_movable_supported(struct hstate *h) +{ + return false; +} + static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3c504fa6b460..2fb3062a3595 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -920,7 +920,7 @@ retry_cpuset: /* Movability of hugepages depends on migration support. */ static inline gfp_t htlb_alloc_mask(struct hstate *h) { - if (hugepage_migration_supported(h)) + if (hugepage_movable_supported(h)) return GFP_HIGHUSER_MOVABLE; else return GFP_HIGHUSER; diff --git a/mm/migrate.c b/mm/migrate.c index 181f5d2718a9..0413596fc523 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1287,7 +1287,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, struct anon_vma *anon_vma = NULL; /* - * Movability of hugepages depends on architectures and hugepage size. + * Migratability of hugepages depends on architectures and their size. * This check is necessary because some callers of hugepage migration * like soft offline and memory hotremove don't walk through page * tables or check whether the hugepage is pmd-based or not before -- cgit v1.2.3-71-gd317 From 9b553bf5eb99dd1b2d8ae23136da46da5c205dfd Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Tue, 5 Mar 2019 15:43:48 -0800 Subject: mm/hugetlb: enable PUD level huge page migration Architectures like arm64 have PUD level HugeTLB pages for certain configs (1GB huge page is PUD based on ARM64_4K_PAGES base page size) that can be enabled for migration. It can be achieved through checking for PUD_SHIFT order based HugeTLB pages during migration. Link: http://lkml.kernel.org/r/1545121450-1663-3-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Reviewed-by: Naoya Horiguchi Reviewed-by: Steve Capper Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 1b858d795731..70bcd8973323 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -497,7 +497,8 @@ static inline bool hugepage_migration_supported(struct hstate *h) { #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION if ((huge_page_shift(h) == PMD_SHIFT) || - (huge_page_shift(h) == PGDIR_SHIFT)) + (huge_page_shift(h) == PUD_SHIFT) || + (huge_page_shift(h) == PGDIR_SHIFT)) return true; else return false; -- cgit v1.2.3-71-gd317 From e693de186414ae66f2a316ff9befcd2b7a6d07b6 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Tue, 5 Mar 2019 15:43:51 -0800 Subject: mm/hugetlb: enable arch specific huge page size support for migration Architectures like arm64 have HugeTLB page sizes which are different than generic sizes at PMD, PUD, PGD level and implemented via contiguous bits. At present these special size HugeTLB pages cannot be identified through macros like (PMD|PUD|PGDIR)_SHIFT and hence chosen not be migrated. Enabling migration support for these special HugeTLB page sizes along with the generic ones (PMD|PUD|PGD) would require identifying all of them on a given platform. A platform specific hook can precisely enumerate all huge page sizes supported for migration. Instead of comparing against standard huge page orders let hugetlb_migration_support() function call a platform hook arch_hugetlb_migration_support(). Default definition for the platform hook maintains existing semantics which checks standard huge page order. But an architecture can choose to override the default and provide support for a comprehensive set of huge page sizes. Link: http://lkml.kernel.org/r/1545121450-1663-4-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Reviewed-by: Naoya Horiguchi Reviewed-by: Steve Capper Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 70bcd8973323..4cc3871b65fc 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -493,18 +493,29 @@ static inline pgoff_t basepage_index(struct page *page) extern int dissolve_free_huge_page(struct page *page); extern int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn); -static inline bool hugepage_migration_supported(struct hstate *h) -{ + #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION +#ifndef arch_hugetlb_migration_supported +static inline bool arch_hugetlb_migration_supported(struct hstate *h) +{ if ((huge_page_shift(h) == PMD_SHIFT) || (huge_page_shift(h) == PUD_SHIFT) || (huge_page_shift(h) == PGDIR_SHIFT)) return true; else return false; +} +#endif #else +static inline bool arch_hugetlb_migration_supported(struct hstate *h) +{ return false; +} #endif + +static inline bool hugepage_migration_supported(struct hstate *h) +{ + return arch_hugetlb_migration_supported(h); } /* -- cgit v1.2.3-71-gd317 From d71e53cee7c2e553b85c572e76da778a93d32135 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 5 Mar 2019 15:44:18 -0800 Subject: mm: shuffle GFP_* flags GFP_KERNEL is one of the most used constant but on archs like arm with fixed length instruction some constants are more equal than the others. Constants with tightly packed bits can be injected directly into instruction stream: 0: e3a00d33 mov r0, #3264 ; 0xcc0 Others require multiple instructions or even loading out of instruction stream: 0: e3a000c0 mov r0, #192 ; 0xc0 4: e3400060 movt r0, #96 ; 0x60 Shuffle GFP_* flags so that GFP_KERNEL/GFP_ATOMIC + __GFP_ZERO bits are close to each other. Savings on arm configs are ~0.1%. Link: http://lkml.kernel.org/r/20190109201838.GA9140@avx2 Signed-off-by: Alexey Dobriyan Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 5f5e25fd6149..fdab7de7490d 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -24,21 +24,21 @@ struct vm_area_struct; #define ___GFP_HIGH 0x20u #define ___GFP_IO 0x40u #define ___GFP_FS 0x80u -#define ___GFP_WRITE 0x100u -#define ___GFP_NOWARN 0x200u -#define ___GFP_RETRY_MAYFAIL 0x400u -#define ___GFP_NOFAIL 0x800u -#define ___GFP_NORETRY 0x1000u -#define ___GFP_MEMALLOC 0x2000u -#define ___GFP_COMP 0x4000u -#define ___GFP_ZERO 0x8000u -#define ___GFP_NOMEMALLOC 0x10000u -#define ___GFP_HARDWALL 0x20000u -#define ___GFP_THISNODE 0x40000u -#define ___GFP_ATOMIC 0x80000u -#define ___GFP_ACCOUNT 0x100000u -#define ___GFP_DIRECT_RECLAIM 0x200000u -#define ___GFP_KSWAPD_RECLAIM 0x400000u +#define ___GFP_ZERO 0x100u +#define ___GFP_ATOMIC 0x200u +#define ___GFP_DIRECT_RECLAIM 0x400u +#define ___GFP_KSWAPD_RECLAIM 0x800u +#define ___GFP_WRITE 0x1000u +#define ___GFP_NOWARN 0x2000u +#define ___GFP_RETRY_MAYFAIL 0x4000u +#define ___GFP_NOFAIL 0x8000u +#define ___GFP_NORETRY 0x10000u +#define ___GFP_MEMALLOC 0x20000u +#define ___GFP_COMP 0x40000u +#define ___GFP_NOMEMALLOC 0x80000u +#define ___GFP_HARDWALL 0x100000u +#define ___GFP_THISNODE 0x200000u +#define ___GFP_ACCOUNT 0x400000u #ifdef CONFIG_LOCKDEP #define ___GFP_NOLOCKDEP 0x800000u #else -- cgit v1.2.3-71-gd317 From 70b44595eafe9c7c235f076d653a268ca1ab9fdb Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 5 Mar 2019 15:44:54 -0800 Subject: mm, compaction: use free lists to quickly locate a migration source The migration scanner is a linear scan of a zone with a potentiall large search space. Furthermore, many pageblocks are unusable such as those filled with reserved pages or partially filled with pages that cannot migrate. These still get scanned in the common case of allocating a THP and the cost accumulates. The patch uses a partial search of the free lists to locate a migration source candidate that is marked as MOVABLE when allocating a THP. It prefers picking a block with a larger number of free pages already on the basis that there are fewer pages to migrate to free the entire block. The lowest PFN found during searches is tracked as the basis of the start for the linear search after the first search of the free list fails. After the search, the free list is shuffled so that the next search will not encounter the same page. If the search fails then the subsequent searches will be shorter and the linear scanner is used. If this search fails, or if the request is for a small or unmovable/reclaimable allocation then the linear scanner is still used. It is somewhat pointless to use the list search in those cases. Small free pages must be used for the search and there is no guarantee that movable pages are located within that block that are contiguous. 5.0.0-rc1 5.0.0-rc1 noboost-v3r10 findmig-v3r15 Amean fault-both-3 3771.41 ( 0.00%) 3390.40 ( 10.10%) Amean fault-both-5 5409.05 ( 0.00%) 5082.28 ( 6.04%) Amean fault-both-7 7040.74 ( 0.00%) 7012.51 ( 0.40%) Amean fault-both-12 11887.35 ( 0.00%) 11346.63 ( 4.55%) Amean fault-both-18 16718.19 ( 0.00%) 15324.19 ( 8.34%) Amean fault-both-24 21157.19 ( 0.00%) 16088.50 * 23.96%* Amean fault-both-30 21175.92 ( 0.00%) 18723.42 * 11.58%* Amean fault-both-32 21339.03 ( 0.00%) 18612.01 * 12.78%* 5.0.0-rc1 5.0.0-rc1 noboost-v3r10 findmig-v3r15 Percentage huge-3 86.50 ( 0.00%) 89.83 ( 3.85%) Percentage huge-5 92.52 ( 0.00%) 91.96 ( -0.61%) Percentage huge-7 92.44 ( 0.00%) 92.85 ( 0.44%) Percentage huge-12 92.98 ( 0.00%) 92.74 ( -0.25%) Percentage huge-18 91.70 ( 0.00%) 91.71 ( 0.02%) Percentage huge-24 91.59 ( 0.00%) 92.13 ( 0.60%) Percentage huge-30 90.14 ( 0.00%) 93.79 ( 4.04%) Percentage huge-32 90.03 ( 0.00%) 91.27 ( 1.37%) This shows an improvement in allocation latencies with similar allocation success rates. While not presented, there was a 31% reduction in migration scanning and a 8% reduction on system CPU usage. A 2-socket machine showed similar benefits. [mgorman@techsingularity.net: several fixes] Link: http://lkml.kernel.org/r/20190204120111.GL9565@techsingularity.net [vbabka@suse.cz: migrate block that was found-fast, some optimisations] Link: http://lkml.kernel.org/r/20190118175136.31341-10-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Dan Carpenter Cc: David Rientjes Cc: YueHaibing Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/gpu/drm/i915/i915_utils.h | 6 -- include/linux/list.h | 11 +++ mm/compaction.c | 178 +++++++++++++++++++++++++++++++++++++- mm/internal.h | 2 + 4 files changed, 188 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h index 9726df37c4c4..540e20eb032c 100644 --- a/drivers/gpu/drm/i915/i915_utils.h +++ b/drivers/gpu/drm/i915/i915_utils.h @@ -123,12 +123,6 @@ static inline u64 ptr_to_u64(const void *ptr) #include -static inline int list_is_first(const struct list_head *list, - const struct list_head *head) -{ - return head->next == list; -} - static inline void __list_del_many(struct list_head *head, struct list_head *first) { diff --git a/include/linux/list.h b/include/linux/list.h index edb7628e46ed..79626b5ab36c 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -206,6 +206,17 @@ static inline void list_bulk_move_tail(struct list_head *head, head->prev = last; } +/** + * list_is_first -- tests whether @ list is the first entry in list @head + * @list: the entry to test + * @head: the head of the list + */ +static inline int list_is_first(const struct list_head *list, + const struct list_head *head) +{ + return list->prev == head; +} + /** * list_is_last - tests whether @list is the last entry in list @head * @list: the entry to test diff --git a/mm/compaction.c b/mm/compaction.c index 3d11c209614a..55f7ab142af2 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1040,6 +1040,12 @@ static bool suitable_migration_target(struct compact_control *cc, return false; } +static inline unsigned int +freelist_scan_limit(struct compact_control *cc) +{ + return (COMPACT_CLUSTER_MAX >> cc->fast_search_fail) + 1; +} + /* * Test whether the free scanner has reached the same or lower pageblock than * the migration scanner, and compaction should thus terminate. @@ -1050,6 +1056,19 @@ static inline bool compact_scanners_met(struct compact_control *cc) <= (cc->migrate_pfn >> pageblock_order); } +/* Reorder the free list to reduce repeated future searches */ +static void +move_freelist_tail(struct list_head *freelist, struct page *freepage) +{ + LIST_HEAD(sublist); + + if (!list_is_first(freelist, &freepage->lru)) { + list_cut_position(&sublist, freelist, &freepage->lru); + if (!list_empty(&sublist)) + list_splice_tail(&sublist, freelist); + } +} + /* * Based on information in the current compact_control, find blocks * suitable for isolating free pages from and then isolate them. @@ -1207,6 +1226,148 @@ typedef enum { */ int sysctl_compact_unevictable_allowed __read_mostly = 1; +static inline void +update_fast_start_pfn(struct compact_control *cc, unsigned long pfn) +{ + if (cc->fast_start_pfn == ULONG_MAX) + return; + + if (!cc->fast_start_pfn) + cc->fast_start_pfn = pfn; + + cc->fast_start_pfn = min(cc->fast_start_pfn, pfn); +} + +static inline unsigned long +reinit_migrate_pfn(struct compact_control *cc) +{ + if (!cc->fast_start_pfn || cc->fast_start_pfn == ULONG_MAX) + return cc->migrate_pfn; + + cc->migrate_pfn = cc->fast_start_pfn; + cc->fast_start_pfn = ULONG_MAX; + + return cc->migrate_pfn; +} + +/* + * Briefly search the free lists for a migration source that already has + * some free pages to reduce the number of pages that need migration + * before a pageblock is free. + */ +static unsigned long fast_find_migrateblock(struct compact_control *cc) +{ + unsigned int limit = freelist_scan_limit(cc); + unsigned int nr_scanned = 0; + unsigned long distance; + unsigned long pfn = cc->migrate_pfn; + unsigned long high_pfn; + int order; + + /* Skip hints are relied on to avoid repeats on the fast search */ + if (cc->ignore_skip_hint) + return pfn; + + /* + * If the migrate_pfn is not at the start of a zone or the start + * of a pageblock then assume this is a continuation of a previous + * scan restarted due to COMPACT_CLUSTER_MAX. + */ + if (pfn != cc->zone->zone_start_pfn && pfn != pageblock_start_pfn(pfn)) + return pfn; + + /* + * For smaller orders, just linearly scan as the number of pages + * to migrate should be relatively small and does not necessarily + * justify freeing up a large block for a small allocation. + */ + if (cc->order <= PAGE_ALLOC_COSTLY_ORDER) + return pfn; + + /* + * Only allow kcompactd and direct requests for movable pages to + * quickly clear out a MOVABLE pageblock for allocation. This + * reduces the risk that a large movable pageblock is freed for + * an unmovable/reclaimable small allocation. + */ + if (cc->direct_compaction && cc->migratetype != MIGRATE_MOVABLE) + return pfn; + + /* + * When starting the migration scanner, pick any pageblock within the + * first half of the search space. Otherwise try and pick a pageblock + * within the first eighth to reduce the chances that a migration + * target later becomes a source. + */ + distance = (cc->free_pfn - cc->migrate_pfn) >> 1; + if (cc->migrate_pfn != cc->zone->zone_start_pfn) + distance >>= 2; + high_pfn = pageblock_start_pfn(cc->migrate_pfn + distance); + + for (order = cc->order - 1; + order >= PAGE_ALLOC_COSTLY_ORDER && pfn == cc->migrate_pfn && nr_scanned < limit; + order--) { + struct free_area *area = &cc->zone->free_area[order]; + struct list_head *freelist; + unsigned long flags; + struct page *freepage; + + if (!area->nr_free) + continue; + + spin_lock_irqsave(&cc->zone->lock, flags); + freelist = &area->free_list[MIGRATE_MOVABLE]; + list_for_each_entry(freepage, freelist, lru) { + unsigned long free_pfn; + + nr_scanned++; + free_pfn = page_to_pfn(freepage); + if (free_pfn < high_pfn) { + update_fast_start_pfn(cc, free_pfn); + + /* + * Avoid if skipped recently. Ideally it would + * move to the tail but even safe iteration of + * the list assumes an entry is deleted, not + * reordered. + */ + if (get_pageblock_skip(freepage)) { + if (list_is_last(freelist, &freepage->lru)) + break; + + continue; + } + + /* Reorder to so a future search skips recent pages */ + move_freelist_tail(freelist, freepage); + + pfn = pageblock_start_pfn(free_pfn); + cc->fast_search_fail = 0; + set_pageblock_skip(freepage); + break; + } + + if (nr_scanned >= limit) { + cc->fast_search_fail++; + move_freelist_tail(freelist, freepage); + break; + } + } + spin_unlock_irqrestore(&cc->zone->lock, flags); + } + + cc->total_migrate_scanned += nr_scanned; + + /* + * If fast scanning failed then use a cached entry for a page block + * that had free pages as the basis for starting a linear scan. + */ + if (pfn == cc->migrate_pfn) + pfn = reinit_migrate_pfn(cc); + + return pfn; +} + /* * Isolate all pages that can be migrated from the first suitable block, * starting at the block pointed to by the migrate scanner pfn within @@ -1222,16 +1383,25 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, const isolate_mode_t isolate_mode = (sysctl_compact_unevictable_allowed ? ISOLATE_UNEVICTABLE : 0) | (cc->mode != MIGRATE_SYNC ? ISOLATE_ASYNC_MIGRATE : 0); + bool fast_find_block; /* * Start at where we last stopped, or beginning of the zone as - * initialized by compact_zone() + * initialized by compact_zone(). The first failure will use + * the lowest PFN as the starting point for linear scanning. */ - low_pfn = cc->migrate_pfn; + low_pfn = fast_find_migrateblock(cc); block_start_pfn = pageblock_start_pfn(low_pfn); if (block_start_pfn < zone->zone_start_pfn) block_start_pfn = zone->zone_start_pfn; + /* + * fast_find_migrateblock marks a pageblock skipped so to avoid + * the isolation_suitable check below, check whether the fast + * search was successful. + */ + fast_find_block = low_pfn != cc->migrate_pfn && !cc->fast_search_fail; + /* Only scan within a pageblock boundary */ block_end_pfn = pageblock_end_pfn(low_pfn); @@ -1240,6 +1410,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, * Do not cross the free scanner. */ for (; block_end_pfn <= cc->free_pfn; + fast_find_block = false, low_pfn = block_end_pfn, block_start_pfn = block_end_pfn, block_end_pfn += pageblock_nr_pages) { @@ -1259,7 +1430,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, continue; /* If isolation recently failed, do not retry */ - if (!isolation_suitable(cc, page)) + if (!isolation_suitable(cc, page) && !fast_find_block) continue; /* @@ -1550,6 +1721,7 @@ static enum compact_result compact_zone(struct compact_control *cc) * want to compact the whole zone), but check that it is initialised * by ensuring the values are within zone boundaries. */ + cc->fast_start_pfn = 0; if (cc->whole_zone) { cc->migrate_pfn = start_pfn; cc->free_pfn = pageblock_start_pfn(end_pfn - 1); diff --git a/mm/internal.h b/mm/internal.h index 9b32f4cab0ae..983cb975545f 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -188,9 +188,11 @@ struct compact_control { unsigned int nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ unsigned long migrate_pfn; /* isolate_migratepages search base */ + unsigned long fast_start_pfn; /* a pfn to start linear scan from */ struct zone *zone; unsigned long total_migrate_scanned; unsigned long total_free_scanned; + unsigned int fast_search_fail; /* failures to use free list searches */ const gfp_t gfp_mask; /* gfp mask of a direct compactor */ int order; /* order a direct compactor needs */ int migratetype; /* migratetype of direct compactor */ -- cgit v1.2.3-71-gd317 From e332f741a8dd1ec9a6dc8aa997296ecbfe64323e Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 5 Mar 2019 15:45:38 -0800 Subject: mm, compaction: be selective about what pageblocks to clear skip hints Pageblock hints are cleared when compaction restarts or kswapd makes enough progress that it can sleep but it's over-eager in that the bit is cleared for migration sources with no LRU pages and migration targets with no free pages. As pageblock skip hint flushes are relatively rare and out-of-band with respect to kswapd, this patch makes a few more expensive checks to see if it's appropriate to even clear the bit. Every pageblock that is not cleared will avoid 512 pages being scanned unnecessarily on x86-64. The impact is variable with different workloads showing small differences in latency, success rates and scan rates. This is expected as clearing the hints is not that common but doing a small amount of work out-of-band to avoid a large amount of work in-band later is generally a good thing. Link: http://lkml.kernel.org/r/20190118175136.31341-22-mgorman@techsingularity.net Signed-off-by: Mel Gorman Signed-off-by: Qian Cai Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Dan Carpenter Cc: David Rientjes Cc: YueHaibing [cai@lca.pw: no stuck in __reset_isolation_pfn()] Link: http://lkml.kernel.org/r/20190206034732.75687-1-cai@lca.pw Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 + mm/compaction.c | 124 ++++++++++++++++++++++++++++++++++++++++++------- 2 files changed, 108 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 842f9189537b..90c13cdeefb5 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -480,6 +480,8 @@ struct zone { unsigned long compact_cached_free_pfn; /* pfn where async and sync compaction migration scanner should start */ unsigned long compact_cached_migrate_pfn[2]; + unsigned long compact_init_migrate_pfn; + unsigned long compact_init_free_pfn; #endif #ifdef CONFIG_COMPACTION diff --git a/mm/compaction.c b/mm/compaction.c index b83cdb42f249..3084cee77fda 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -237,6 +237,70 @@ static bool pageblock_skip_persistent(struct page *page) return false; } +static bool +__reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source, + bool check_target) +{ + struct page *page = pfn_to_online_page(pfn); + struct page *end_page; + unsigned long block_pfn; + + if (!page) + return false; + if (zone != page_zone(page)) + return false; + if (pageblock_skip_persistent(page)) + return false; + + /* + * If skip is already cleared do no further checking once the + * restart points have been set. + */ + if (check_source && check_target && !get_pageblock_skip(page)) + return true; + + /* + * If clearing skip for the target scanner, do not select a + * non-movable pageblock as the starting point. + */ + if (!check_source && check_target && + get_pageblock_migratetype(page) != MIGRATE_MOVABLE) + return false; + + /* + * Only clear the hint if a sample indicates there is either a + * free page or an LRU page in the block. One or other condition + * is necessary for the block to be a migration source/target. + */ + block_pfn = pageblock_start_pfn(pfn); + pfn = max(block_pfn, zone->zone_start_pfn); + page = pfn_to_page(pfn); + if (zone != page_zone(page)) + return false; + pfn = block_pfn + pageblock_nr_pages; + pfn = min(pfn, zone_end_pfn(zone)); + end_page = pfn_to_page(pfn); + + do { + if (pfn_valid_within(pfn)) { + if (check_source && PageLRU(page)) { + clear_pageblock_skip(page); + return true; + } + + if (check_target && PageBuddy(page)) { + clear_pageblock_skip(page); + return true; + } + } + + page += (1 << PAGE_ALLOC_COSTLY_ORDER); + pfn += (1 << PAGE_ALLOC_COSTLY_ORDER); + } while (page < end_page); + + return false; +} + /* * This function is called to clear all cached information on pageblocks that * should be skipped for page isolation when the migrate and free page scanner @@ -244,30 +308,54 @@ static bool pageblock_skip_persistent(struct page *page) */ static void __reset_isolation_suitable(struct zone *zone) { - unsigned long start_pfn = zone->zone_start_pfn; - unsigned long end_pfn = zone_end_pfn(zone); - unsigned long pfn; + unsigned long migrate_pfn = zone->zone_start_pfn; + unsigned long free_pfn = zone_end_pfn(zone); + unsigned long reset_migrate = free_pfn; + unsigned long reset_free = migrate_pfn; + bool source_set = false; + bool free_set = false; - zone->compact_blockskip_flush = false; + if (!zone->compact_blockskip_flush) + return; - /* Walk the zone and mark every pageblock as suitable for isolation */ - for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) { - struct page *page; + zone->compact_blockskip_flush = false; + /* + * Walk the zone and update pageblock skip information. Source looks + * for PageLRU while target looks for PageBuddy. When the scanner + * is found, both PageBuddy and PageLRU are checked as the pageblock + * is suitable as both source and target. + */ + for (; migrate_pfn < free_pfn; migrate_pfn += pageblock_nr_pages, + free_pfn -= pageblock_nr_pages) { cond_resched(); - page = pfn_to_online_page(pfn); - if (!page) - continue; - if (zone != page_zone(page)) - continue; - if (pageblock_skip_persistent(page)) - continue; + /* Update the migrate PFN */ + if (__reset_isolation_pfn(zone, migrate_pfn, true, source_set) && + migrate_pfn < reset_migrate) { + source_set = true; + reset_migrate = migrate_pfn; + zone->compact_init_migrate_pfn = reset_migrate; + zone->compact_cached_migrate_pfn[0] = reset_migrate; + zone->compact_cached_migrate_pfn[1] = reset_migrate; + } - clear_pageblock_skip(page); + /* Update the free PFN */ + if (__reset_isolation_pfn(zone, free_pfn, free_set, true) && + free_pfn > reset_free) { + free_set = true; + reset_free = free_pfn; + zone->compact_init_free_pfn = reset_free; + zone->compact_cached_free_pfn = reset_free; + } } - reset_cached_positions(zone); + /* Leave no distance if no suitable block was reset */ + if (reset_migrate >= reset_free) { + zone->compact_cached_migrate_pfn[0] = migrate_pfn; + zone->compact_cached_migrate_pfn[1] = migrate_pfn; + zone->compact_cached_free_pfn = free_pfn; + } } void reset_isolation_suitable(pg_data_t *pgdat) @@ -1190,7 +1278,7 @@ fast_isolate_freepages(struct compact_control *cc) * If starting the scan, use a deeper search and use the highest * PFN found if a suitable one is not found. */ - if (cc->free_pfn == pageblock_start_pfn(zone_end_pfn(cc->zone) - 1)) { + if (cc->free_pfn >= cc->zone->compact_init_free_pfn) { limit = pageblock_nr_pages >> 1; scan_start = true; } @@ -2017,7 +2105,7 @@ static enum compact_result compact_zone(struct compact_control *cc) cc->zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn; } - if (cc->migrate_pfn == start_pfn) + if (cc->migrate_pfn <= cc->zone->compact_init_migrate_pfn) cc->whole_zone = true; } -- cgit v1.2.3-71-gd317 From 5e1f0f098b4649fad53011246bcaeff011ffdf5d Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 5 Mar 2019 15:45:41 -0800 Subject: mm, compaction: capture a page under direct compaction Compaction is inherently race-prone as a suitable page freed during compaction can be allocated by any parallel task. This patch uses a capture_control structure to isolate a page immediately when it is freed by a direct compactor in the slow path of the page allocator. The intent is to avoid redundant scanning. 5.0.0-rc1 5.0.0-rc1 selective-v3r17 capture-v3r19 Amean fault-both-1 0.00 ( 0.00%) 0.00 * 0.00%* Amean fault-both-3 2582.11 ( 0.00%) 2563.68 ( 0.71%) Amean fault-both-5 4500.26 ( 0.00%) 4233.52 ( 5.93%) Amean fault-both-7 5819.53 ( 0.00%) 6333.65 ( -8.83%) Amean fault-both-12 9321.18 ( 0.00%) 9759.38 ( -4.70%) Amean fault-both-18 9782.76 ( 0.00%) 10338.76 ( -5.68%) Amean fault-both-24 15272.81 ( 0.00%) 13379.55 * 12.40%* Amean fault-both-30 15121.34 ( 0.00%) 16158.25 ( -6.86%) Amean fault-both-32 18466.67 ( 0.00%) 18971.21 ( -2.73%) Latency is only moderately affected but the devil is in the details. A closer examination indicates that base page fault latency is reduced but latency of huge pages is increased as it takes creater care to succeed. Part of the "problem" is that allocation success rates are close to 100% even when under pressure and compaction gets harder 5.0.0-rc1 5.0.0-rc1 selective-v3r17 capture-v3r19 Percentage huge-3 96.70 ( 0.00%) 98.23 ( 1.58%) Percentage huge-5 96.99 ( 0.00%) 95.30 ( -1.75%) Percentage huge-7 94.19 ( 0.00%) 97.24 ( 3.24%) Percentage huge-12 94.95 ( 0.00%) 97.35 ( 2.53%) Percentage huge-18 96.74 ( 0.00%) 97.30 ( 0.58%) Percentage huge-24 97.07 ( 0.00%) 97.55 ( 0.50%) Percentage huge-30 95.69 ( 0.00%) 98.50 ( 2.95%) Percentage huge-32 96.70 ( 0.00%) 99.27 ( 2.65%) And scan rates are reduced as expected by 6% for the migration scanner and 29% for the free scanner indicating that there is less redundant work. Compaction migrate scanned 20815362 19573286 Compaction free scanned 16352612 11510663 [mgorman@techsingularity.net: remove redundant check] Link: http://lkml.kernel.org/r/20190201143853.GH9565@techsingularity.net Link: http://lkml.kernel.org/r/20190118175136.31341-23-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: Dan Carpenter Cc: David Rientjes Cc: YueHaibing Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 3 +- include/linux/sched.h | 4 +++ kernel/sched/core.c | 3 ++ mm/compaction.c | 31 +++++++++++++++----- mm/internal.h | 9 ++++++ mm/page_alloc.c | 73 +++++++++++++++++++++++++++++++++++++++++++--- 6 files changed, 111 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 70d0256edd31..c960923d9ec2 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -93,7 +93,8 @@ extern int sysctl_compact_unevictable_allowed; extern int fragmentation_index(struct zone *zone, unsigned int order); extern enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, unsigned int alloc_flags, - const struct alloc_context *ac, enum compact_priority prio); + const struct alloc_context *ac, enum compact_priority prio, + struct page **page); extern void reset_isolation_suitable(pg_data_t *pgdat); extern enum compact_result compaction_suitable(struct zone *zone, int order, unsigned int alloc_flags, int classzone_idx); diff --git a/include/linux/sched.h b/include/linux/sched.h index f9b43c989577..ebfb34fb9b30 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -47,6 +47,7 @@ struct pid_namespace; struct pipe_inode_info; struct rcu_node; struct reclaim_state; +struct capture_control; struct robust_list_head; struct sched_attr; struct sched_param; @@ -958,6 +959,9 @@ struct task_struct { struct io_context *io_context; +#ifdef CONFIG_COMPACTION + struct capture_control *capture_control; +#endif /* Ptrace state: */ unsigned long ptrace_message; kernel_siginfo_t *last_siginfo; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7cbb5658be80..916e956e92be 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2190,6 +2190,9 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) INIT_HLIST_HEAD(&p->preempt_notifiers); #endif +#ifdef CONFIG_COMPACTION + p->capture_control = NULL; +#endif init_numa_balancing(clone_flags, p); } diff --git a/mm/compaction.c b/mm/compaction.c index 3084cee77fda..1cc871da3fda 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -2056,7 +2056,8 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order, return false; } -static enum compact_result compact_zone(struct compact_control *cc) +static enum compact_result +compact_zone(struct compact_control *cc, struct capture_control *capc) { enum compact_result ret; unsigned long start_pfn = cc->zone->zone_start_pfn; @@ -2225,6 +2226,11 @@ check_drain: } } + /* Stop if a page has been captured */ + if (capc && capc->page) { + ret = COMPACT_SUCCESS; + break; + } } out: @@ -2258,7 +2264,8 @@ out: static enum compact_result compact_zone_order(struct zone *zone, int order, gfp_t gfp_mask, enum compact_priority prio, - unsigned int alloc_flags, int classzone_idx) + unsigned int alloc_flags, int classzone_idx, + struct page **capture) { enum compact_result ret; struct compact_control cc = { @@ -2279,14 +2286,24 @@ static enum compact_result compact_zone_order(struct zone *zone, int order, .ignore_skip_hint = (prio == MIN_COMPACT_PRIORITY), .ignore_block_suitable = (prio == MIN_COMPACT_PRIORITY) }; + struct capture_control capc = { + .cc = &cc, + .page = NULL, + }; + + if (capture) + current->capture_control = &capc; INIT_LIST_HEAD(&cc.freepages); INIT_LIST_HEAD(&cc.migratepages); - ret = compact_zone(&cc); + ret = compact_zone(&cc, &capc); VM_BUG_ON(!list_empty(&cc.freepages)); VM_BUG_ON(!list_empty(&cc.migratepages)); + *capture = capc.page; + current->capture_control = NULL; + return ret; } @@ -2304,7 +2321,7 @@ int sysctl_extfrag_threshold = 500; */ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, unsigned int alloc_flags, const struct alloc_context *ac, - enum compact_priority prio) + enum compact_priority prio, struct page **capture) { int may_perform_io = gfp_mask & __GFP_IO; struct zoneref *z; @@ -2332,7 +2349,7 @@ enum compact_result try_to_compact_pages(gfp_t gfp_mask, unsigned int order, } status = compact_zone_order(zone, order, gfp_mask, prio, - alloc_flags, ac_classzone_idx(ac)); + alloc_flags, ac_classzone_idx(ac), capture); rc = max(status, rc); /* The allocation should succeed, stop compacting */ @@ -2400,7 +2417,7 @@ static void compact_node(int nid) INIT_LIST_HEAD(&cc.freepages); INIT_LIST_HEAD(&cc.migratepages); - compact_zone(&cc); + compact_zone(&cc, NULL); VM_BUG_ON(!list_empty(&cc.freepages)); VM_BUG_ON(!list_empty(&cc.migratepages)); @@ -2535,7 +2552,7 @@ static void kcompactd_do_work(pg_data_t *pgdat) if (kthread_should_stop()) return; - status = compact_zone(&cc); + status = compact_zone(&cc, NULL); if (status == COMPACT_SUCCESS) { compaction_defer_reset(zone, cc.order, false); diff --git a/mm/internal.h b/mm/internal.h index 31bb0be6fd52..9eeaf2b95166 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -209,6 +209,15 @@ struct compact_control { bool rescan; /* Rescanning the same pageblock */ }; +/* + * Used in direct compaction when a page should be taken from the freelists + * immediately when one is created during the free path. + */ +struct capture_control { + struct compact_control *cc; + struct page *page; +}; + unsigned long isolate_freepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2e132b9e7a93..09bf2c5f8b4b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -789,6 +789,57 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, return 0; } +#ifdef CONFIG_COMPACTION +static inline struct capture_control *task_capc(struct zone *zone) +{ + struct capture_control *capc = current->capture_control; + + return capc && + !(current->flags & PF_KTHREAD) && + !capc->page && + capc->cc->zone == zone && + capc->cc->direct_compaction ? capc : NULL; +} + +static inline bool +compaction_capture(struct capture_control *capc, struct page *page, + int order, int migratetype) +{ + if (!capc || order != capc->cc->order) + return false; + + /* Do not accidentally pollute CMA or isolated regions*/ + if (is_migrate_cma(migratetype) || + is_migrate_isolate(migratetype)) + return false; + + /* + * Do not let lower order allocations polluate a movable pageblock. + * This might let an unmovable request use a reclaimable pageblock + * and vice-versa but no more than normal fallback logic which can + * have trouble finding a high-order free page. + */ + if (order < pageblock_order && migratetype == MIGRATE_MOVABLE) + return false; + + capc->page = page; + return true; +} + +#else +static inline struct capture_control *task_capc(struct zone *zone) +{ + return NULL; +} + +static inline bool +compaction_capture(struct capture_control *capc, struct page *page, + int order, int migratetype) +{ + return false; +} +#endif /* CONFIG_COMPACTION */ + /* * Freeing function for a buddy system allocator. * @@ -822,6 +873,7 @@ static inline void __free_one_page(struct page *page, unsigned long uninitialized_var(buddy_pfn); struct page *buddy; unsigned int max_order; + struct capture_control *capc = task_capc(zone); max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1); @@ -837,6 +889,11 @@ static inline void __free_one_page(struct page *page, continue_merging: while (order < max_order - 1) { + if (compaction_capture(capc, page, order, migratetype)) { + __mod_zone_freepage_state(zone, -(1 << order), + migratetype); + return; + } buddy_pfn = __find_buddy_pfn(pfn, order); buddy = page + (buddy_pfn - pfn); @@ -3710,7 +3767,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, unsigned int alloc_flags, const struct alloc_context *ac, enum compact_priority prio, enum compact_result *compact_result) { - struct page *page; + struct page *page = NULL; unsigned long pflags; unsigned int noreclaim_flag; @@ -3721,13 +3778,15 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, noreclaim_flag = memalloc_noreclaim_save(); *compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac, - prio); + prio, &page); memalloc_noreclaim_restore(noreclaim_flag); psi_memstall_leave(&pflags); - if (*compact_result <= COMPACT_INACTIVE) + if (*compact_result <= COMPACT_INACTIVE) { + WARN_ON_ONCE(page); return NULL; + } /* * At least in one zone compaction wasn't deferred or skipped, so let's @@ -3735,7 +3794,13 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, */ count_vm_event(COMPACTSTALL); - page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac); + /* Prep a captured page if available */ + if (page) + prep_new_page(page, order, gfp_mask, alloc_flags); + + /* Try get a page from the freelist if available */ + if (!page) + page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac); if (page) { struct zone *zone = page_zone(page); -- cgit v1.2.3-71-gd317 From 147e1a97c4a0bdd43f55a582a9416bb9092563a9 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 5 Mar 2019 15:45:45 -0800 Subject: fs: kernfs: add poll file operation Patch series "psi: pressure stall monitors", v3. Android is adopting psi to detect and remedy memory pressure that results in stuttering and decreased responsiveness on mobile devices. Psi gives us the stall information, but because we're dealing with latencies in the millisecond range, periodically reading the pressure files to detect stalls in a timely fashion is not feasible. Psi also doesn't aggregate its averages at a high enough frequency right now. This patch series extends the psi interface such that users can configure sensitive latency thresholds and use poll() and friends to be notified when these are breached. As high-frequency aggregation is costly, it implements an aggregation method that is optimized for fast, short-interval averaging, and makes the aggregation frequency adaptive, such that high-frequency updates only happen while monitored stall events are actively occurring. With these patches applied, Android can monitor for, and ward off, mounting memory shortages before they cause problems for the user. For example, using memory stall monitors in userspace low memory killer daemon (lmkd) we can detect mounting pressure and kill less important processes before device becomes visibly sluggish. In our memory stress testing psi memory monitors produce roughly 10x less false positives compared to vmpressure signals. Having ability to specify multiple triggers for the same psi metric allows other parts of Android framework to monitor memory state of the device and act accordingly. The new interface is straightforward. The user opens one of the pressure files for writing and writes a trigger description into the file descriptor that defines the stall state - some or full, and the maximum stall time over a given window of time. E.g.: /* Signal when stall time exceeds 100ms of a 1s window */ char trigger[] = "full 100000 1000000"; fd = open("/proc/pressure/memory"); write(fd, trigger, sizeof(trigger)); while (poll() >= 0) { ... } close(fd); When the monitored stall state is entered, psi adapts its aggregation frequency according to what the configured time window requires in order to emit event signals in a timely fashion. Once the stalling subsides, aggregation reverts back to normal. The trigger is associated with the open file descriptor. To stop monitoring, the user only needs to close the file descriptor and the trigger is discarded. Patches 1-4 prepare the psi code for polling support. Patch 5 implements the adaptive polling logic, the pressure growth detection optimized for short intervals, and hooks up write() and poll() on the pressure files. The patches were developed in collaboration with Johannes Weiner. This patch (of 5): Kernfs has a standardized poll/notification mechanism for waking all pollers on all fds when a filesystem node changes. To allow polling for custom events, add a .poll callback that can override the default. This is in preparation for pollable cgroup pressure files which have per-fd trigger configurations. Link: http://lkml.kernel.org/r/20190124211518.244221-2-surenb@google.com Signed-off-by: Johannes Weiner Signed-off-by: Suren Baghdasaryan Cc: Dennis Zhou Cc: Ingo Molnar Cc: Jens Axboe Cc: Li Zefan Cc: Peter Zijlstra Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/kernfs/file.c | 31 ++++++++++++++++++++----------- include/linux/kernfs.h | 6 ++++++ 2 files changed, 26 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index f8d5021a652e..ae948aaa4c53 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -832,26 +832,35 @@ void kernfs_drain_open_files(struct kernfs_node *kn) * to see if it supports poll (Neither 'poll' nor 'select' return * an appropriate error code). When in doubt, set a suitable timeout value. */ +__poll_t kernfs_generic_poll(struct kernfs_open_file *of, poll_table *wait) +{ + struct kernfs_node *kn = kernfs_dentry_node(of->file->f_path.dentry); + struct kernfs_open_node *on = kn->attr.open; + + poll_wait(of->file, &on->poll, wait); + + if (of->event != atomic_read(&on->event)) + return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; + + return DEFAULT_POLLMASK; +} + static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait) { struct kernfs_open_file *of = kernfs_of(filp); struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry); - struct kernfs_open_node *on = kn->attr.open; + __poll_t ret; if (!kernfs_get_active(kn)) - goto trigger; + return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; - poll_wait(filp, &on->poll, wait); + if (kn->attr.ops->poll) + ret = kn->attr.ops->poll(of, wait); + else + ret = kernfs_generic_poll(of, wait); kernfs_put_active(kn); - - if (of->event != atomic_read(&on->event)) - goto trigger; - - return DEFAULT_POLLMASK; - - trigger: - return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; + return ret; } static void kernfs_notify_workfn(struct work_struct *work) diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 5b36b1287a5a..0cac1207bb00 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -25,6 +25,7 @@ struct seq_file; struct vm_area_struct; struct super_block; struct file_system_type; +struct poll_table_struct; struct kernfs_open_node; struct kernfs_iattrs; @@ -261,6 +262,9 @@ struct kernfs_ops { ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t bytes, loff_t off); + __poll_t (*poll)(struct kernfs_open_file *of, + struct poll_table_struct *pt); + int (*mmap)(struct kernfs_open_file *of, struct vm_area_struct *vma); #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -350,6 +354,8 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name, const void *new_ns); int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr); +__poll_t kernfs_generic_poll(struct kernfs_open_file *of, + struct poll_table_struct *pt); void kernfs_notify(struct kernfs_node *kn); const void *kernfs_super_ns(struct super_block *sb); -- cgit v1.2.3-71-gd317 From dc50537bdd1a0804fa2cbc990565ee9a944e66fa Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 5 Mar 2019 15:45:48 -0800 Subject: kernel: cgroup: add poll file operation Cgroup has a standardized poll/notification mechanism for waking all pollers on all fds when a filesystem node changes. To allow polling for custom events, add a .poll callback that can override the default. This is in preparation for pollable cgroup pressure files which have per-fd trigger configurations. Link: http://lkml.kernel.org/r/20190124211518.244221-3-surenb@google.com Signed-off-by: Johannes Weiner Signed-off-by: Suren Baghdasaryan Cc: Dennis Zhou Cc: Ingo Molnar Cc: Jens Axboe Cc: Li Zefan Cc: Peter Zijlstra Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cgroup-defs.h | 4 ++++ kernel/cgroup/cgroup.c | 12 ++++++++++++ 2 files changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 8fcbae1b8db0..aad3babef007 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -32,6 +32,7 @@ struct kernfs_node; struct kernfs_ops; struct kernfs_open_file; struct seq_file; +struct poll_table_struct; #define MAX_CGROUP_TYPE_NAMELEN 32 #define MAX_CGROUP_ROOT_NAMELEN 64 @@ -574,6 +575,9 @@ struct cftype { ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off); + __poll_t (*poll)(struct kernfs_open_file *of, + struct poll_table_struct *pt); + #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lock_class_key lockdep_key; #endif diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index cef98502b124..17828333f7c3 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3534,6 +3534,16 @@ static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, return ret ?: nbytes; } +static __poll_t cgroup_file_poll(struct kernfs_open_file *of, poll_table *pt) +{ + struct cftype *cft = of->kn->priv; + + if (cft->poll) + return cft->poll(of, pt); + + return kernfs_generic_poll(of, pt); +} + static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos) { return seq_cft(seq)->seq_start(seq, ppos); @@ -3572,6 +3582,7 @@ static struct kernfs_ops cgroup_kf_single_ops = { .open = cgroup_file_open, .release = cgroup_file_release, .write = cgroup_file_write, + .poll = cgroup_file_poll, .seq_show = cgroup_seqfile_show, }; @@ -3580,6 +3591,7 @@ static struct kernfs_ops cgroup_kf_ops = { .open = cgroup_file_open, .release = cgroup_file_release, .write = cgroup_file_write, + .poll = cgroup_file_poll, .seq_start = cgroup_seqfile_start, .seq_next = cgroup_seqfile_next, .seq_stop = cgroup_seqfile_stop, -- cgit v1.2.3-71-gd317 From aa9694bb78bf6eb03810108d5f6064fafa4ae1e1 Mon Sep 17 00:00:00 2001 From: Chris Down Date: Tue, 5 Mar 2019 15:45:52 -0800 Subject: mm, memcg: create mem_cgroup_from_seq This is the start of a series of patches similar to my earlier DEFINE_MEMCG_MAX_OR_VAL work, but with less Macro Magic(tm). There are a bunch of places we go from seq_file to mem_cgroup, which currently requires manually getting the css, then getting the mem_cgroup from the css. It's in enough places now that having mem_cgroup_from_seq makes sense (and also makes the next patch a bit nicer). Link: http://lkml.kernel.org/r/20190124194050.GA31341@chrisdown.name Signed-off-by: Chris Down Acked-by: Johannes Weiner Acked-by: Michal Hocko Cc: Tejun Heo Cc: Roman Gushchin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 10 ++++++++++ mm/memcontrol.c | 24 ++++++++++++------------ mm/slab_common.c | 6 +++--- 3 files changed, 25 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b0eb29ea0d9c..1f3d880b7ca1 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -429,6 +429,11 @@ static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) } struct mem_cgroup *mem_cgroup_from_id(unsigned short id); +static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) +{ + return mem_cgroup_from_css(seq_css(m)); +} + static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) { struct mem_cgroup_per_node *mz; @@ -937,6 +942,11 @@ static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) return NULL; } +static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) +{ + return NULL; +} + static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) { return NULL; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index f93f7f22a6f4..027abf9935d0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3337,7 +3337,7 @@ static int memcg_numa_stat_show(struct seq_file *m, void *v) const struct numa_stat *stat; int nid; unsigned long nr; - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) { nr = mem_cgroup_nr_lru_pages(memcg, stat->lru_mask); @@ -3388,7 +3388,7 @@ static const char *const memcg1_event_names[] = { static int memcg_stat_show(struct seq_file *m, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); unsigned long memory, memsw; struct mem_cgroup *mi; unsigned int i; @@ -3820,7 +3820,7 @@ static void mem_cgroup_oom_unregister_event(struct mem_cgroup *memcg, static int mem_cgroup_oom_control_read(struct seq_file *sf, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(sf)); + struct mem_cgroup *memcg = mem_cgroup_from_seq(sf); seq_printf(sf, "oom_kill_disable %d\n", memcg->oom_kill_disable); seq_printf(sf, "under_oom %d\n", (bool)memcg->under_oom); @@ -5363,7 +5363,7 @@ static u64 memory_current_read(struct cgroup_subsys_state *css, static int memory_min_show(struct seq_file *m, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); unsigned long min = READ_ONCE(memcg->memory.min); if (min == PAGE_COUNTER_MAX) @@ -5393,7 +5393,7 @@ static ssize_t memory_min_write(struct kernfs_open_file *of, static int memory_low_show(struct seq_file *m, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); unsigned long low = READ_ONCE(memcg->memory.low); if (low == PAGE_COUNTER_MAX) @@ -5423,7 +5423,7 @@ static ssize_t memory_low_write(struct kernfs_open_file *of, static int memory_high_show(struct seq_file *m, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); unsigned long high = READ_ONCE(memcg->high); if (high == PAGE_COUNTER_MAX) @@ -5460,7 +5460,7 @@ static ssize_t memory_high_write(struct kernfs_open_file *of, static int memory_max_show(struct seq_file *m, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); unsigned long max = READ_ONCE(memcg->memory.max); if (max == PAGE_COUNTER_MAX) @@ -5522,7 +5522,7 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, static int memory_events_show(struct seq_file *m, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); seq_printf(m, "low %lu\n", atomic_long_read(&memcg->memory_events[MEMCG_LOW])); @@ -5540,7 +5540,7 @@ static int memory_events_show(struct seq_file *m, void *v) static int memory_stat_show(struct seq_file *m, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); struct accumulated_stats acc; int i; @@ -5617,7 +5617,7 @@ static int memory_stat_show(struct seq_file *m, void *v) static int memory_oom_group_show(struct seq_file *m, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); seq_printf(m, "%d\n", memcg->oom_group); @@ -6600,7 +6600,7 @@ static u64 swap_current_read(struct cgroup_subsys_state *css, static int swap_max_show(struct seq_file *m, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); unsigned long max = READ_ONCE(memcg->swap.max); if (max == PAGE_COUNTER_MAX) @@ -6630,7 +6630,7 @@ static ssize_t swap_max_write(struct kernfs_open_file *of, static int swap_events_show(struct seq_file *m, void *v) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); seq_printf(m, "max %lu\n", atomic_long_read(&memcg->memory_events[MEMCG_SWAP_MAX])); diff --git a/mm/slab_common.c b/mm/slab_common.c index f9d89c1b5977..cd75b8985707 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -1425,7 +1425,7 @@ void dump_unreclaimable_slab(void) #if defined(CONFIG_MEMCG) void *memcg_slab_start(struct seq_file *m, loff_t *pos) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); mutex_lock(&slab_mutex); return seq_list_start(&memcg->kmem_caches, *pos); @@ -1433,7 +1433,7 @@ void *memcg_slab_start(struct seq_file *m, loff_t *pos) void *memcg_slab_next(struct seq_file *m, void *p, loff_t *pos) { - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); return seq_list_next(p, &memcg->kmem_caches, pos); } @@ -1447,7 +1447,7 @@ int memcg_slab_show(struct seq_file *m, void *p) { struct kmem_cache *s = list_entry(p, struct kmem_cache, memcg_params.kmem_caches_node); - struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); if (p == memcg->kmem_caches.next) print_slabinfo_header(m); -- cgit v1.2.3-71-gd317 From 8bb4e7a2ee26c05a94ae6cb0aec2f82a3523cf35 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Tue, 5 Mar 2019 15:46:22 -0800 Subject: mm: fix some typos in mm directory No functional change. Link: http://lkml.kernel.org/r/20190118235123.27843-1-richard.weiyang@gmail.com Signed-off-by: Wei Yang Reviewed-by: Pekka Enberg Acked-by: Mike Rapoport Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- mm/migrate.c | 2 +- mm/mmap.c | 8 ++++---- mm/page_alloc.c | 4 ++-- mm/slub.c | 2 +- mm/vmscan.c | 2 +- 6 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 90c13cdeefb5..6d3290cd1f6f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1301,7 +1301,7 @@ void memory_present(int nid, unsigned long start, unsigned long end); /* * If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we - * need to check pfn validility within that MAX_ORDER_NR_PAGES block. + * need to check pfn validity within that MAX_ORDER_NR_PAGES block. * pfn_valid_within() should be used in this case; we optimise this away * when we have no holes within a MAX_ORDER_NR_PAGES block. */ diff --git a/mm/migrate.c b/mm/migrate.c index 0e9888cb33ad..5308d6abd384 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -100,7 +100,7 @@ int isolate_movable_page(struct page *page, isolate_mode_t mode) /* * Check PageMovable before holding a PG_lock because page's owner * assumes anybody doesn't touch PG_lock of newly allocated page - * so unconditionally grapping the lock ruins page's owner side. + * so unconditionally grabbing the lock ruins page's owner side. */ if (unlikely(!__PageMovable(page))) goto out_putpage; diff --git a/mm/mmap.c b/mm/mmap.c index eccba2650ef6..41eb48d9b527 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -438,7 +438,7 @@ static void vma_gap_update(struct vm_area_struct *vma) { /* * As it turns out, RB_DECLARE_CALLBACKS() already created a callback - * function that does exacltly what we want. + * function that does exactly what we want. */ vma_gap_callbacks_propagate(&vma->vm_rb, NULL); } @@ -1012,7 +1012,7 @@ static inline int is_mergeable_vma(struct vm_area_struct *vma, * VM_SOFTDIRTY should not prevent from VMA merging, if we * match the flags but dirty bit -- the caller should mark * merged VMA as dirty. If dirty bit won't be excluded from - * comparison, we increase pressue on the memory system forcing + * comparison, we increase pressure on the memory system forcing * the kernel to generate new VMAs when old one could be * extended instead. */ @@ -1115,7 +1115,7 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, * PPPP NNNN PPPPPPPPPPPP PPPPPPPPNNNN PPPPNNNNNNNN * might become case 1 below case 2 below case 3 below * - * It is important for case 8 that the the vma NNNN overlapping the + * It is important for case 8 that the vma NNNN overlapping the * region AAAA is never going to extended over XXXX. Instead XXXX must * be extended in region AAAA and NNNN must be removed. This way in * all cases where vma_merge succeeds, the moment vma_adjust drops the @@ -1645,7 +1645,7 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg) #endif /* __ARCH_WANT_SYS_OLD_MMAP */ /* - * Some shared mappigns will want the pages marked read-only + * Some shared mappings will want the pages marked read-only * to track write events. If so, we'll downgrade vm_page_prot * to the private version (using protection_map[] without the * VM_SHARED bit). diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 9be9a22ebe35..ec250453f5e8 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7551,7 +7551,7 @@ static void __setup_per_zone_wmarks(void) * value here. * * The WMARK_HIGH-WMARK_LOW and (WMARK_LOW-WMARK_MIN) - * deltas control asynch page reclaim, and so should + * deltas control async page reclaim, and so should * not be capped for highmem. */ unsigned long min_pages; @@ -8028,7 +8028,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, /* * Hugepages are not in LRU lists, but they're movable. - * We need not scan over tail pages bacause we don't + * We need not scan over tail pages because we don't * handle each tail page individually in migration. */ if (PageHuge(page)) { diff --git a/mm/slub.c b/mm/slub.c index d8b1eee2dd86..017a2ce5ba23 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2129,7 +2129,7 @@ redo: if (!lock) { lock = 1; /* - * Taking the spinlock removes the possiblity + * Taking the spinlock removes the possibility * that acquire_slab() will see a slab page that * is frozen */ diff --git a/mm/vmscan.c b/mm/vmscan.c index e979705bbf32..63195364ab2e 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3527,7 +3527,7 @@ static bool kswapd_shrink_node(pg_data_t *pgdat, * * kswapd scans the zones in the highmem->normal->dma direction. It skips * zones which have free_pages > high_wmark_pages(zone), but once a zone is - * found to have free_pages <= high_wmark_pages(zone), any page is that zone + * found to have free_pages <= high_wmark_pages(zone), any page in that zone * or lower is eligible for reclaim until at least one usable zone is * balanced. */ -- cgit v1.2.3-71-gd317 From 023bdd00235eb0dcb71fd98f0b8347a9bb85d417 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Tue, 5 Mar 2019 15:46:37 -0800 Subject: mm/hugetlb: add prot_modify_start/commit sequence for hugetlb update Architectures like ppc64 require to do a conditional tlb flush based on the old and new value of pte. Follow the regular pte change protection sequence for hugetlb too. This allows the architectures to override the update sequence. Link: http://lkml.kernel.org/r/20190116085035.29729-5-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Reviewed-by: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Martin Schwidefsky Cc: Nicholas Piggin Cc: Paul Mackerras Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 20 ++++++++++++++++++++ mm/hugetlb.c | 8 +++++--- 2 files changed, 25 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 4cc3871b65fc..54c317c8355f 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -580,6 +580,26 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr set_huge_pte_at(mm, addr, ptep, pte); } #endif + +#ifndef huge_ptep_modify_prot_start +#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start +static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ + return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); +} +#endif + +#ifndef huge_ptep_modify_prot_commit +#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit +static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t pte) +{ + set_huge_pte_at(vma->vm_mm, addr, ptep, pte); +} +#endif + #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; #define alloc_huge_page(v, a, r) NULL diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 2fb3062a3595..0c7848fccf93 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4399,10 +4399,12 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, continue; } if (!huge_pte_none(pte)) { - pte = huge_ptep_get_and_clear(mm, address, ptep); - pte = pte_mkhuge(huge_pte_modify(pte, newprot)); + pte_t old_pte; + + old_pte = huge_ptep_modify_prot_start(vma, address, ptep); + pte = pte_mkhuge(huge_pte_modify(old_pte, newprot)); pte = arch_make_huge_pte(pte, vma, NULL, 0); - set_huge_pte_at(mm, address, ptep, pte); + huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte); pages++; } spin_unlock(ptl); -- cgit v1.2.3-71-gd317 From b56a2d8af9147a4efe4011b60d93779c0461ca97 Mon Sep 17 00:00:00 2001 From: Vineeth Remanan Pillai Date: Tue, 5 Mar 2019 15:47:03 -0800 Subject: mm: rid swapoff of quadratic complexity This patch was initially posted by Kelley Nielsen. Reposting the patch with all review comments addressed and with minor modifications and optimizations. Also, folding in the fixes offered by Hugh Dickins and Huang Ying. Tests were rerun and commit message updated with new results. try_to_unuse() is of quadratic complexity, with a lot of wasted effort. It unuses swap entries one by one, potentially iterating over all the page tables for all the processes in the system for each one. This new proposed implementation of try_to_unuse simplifies its complexity to linear. It iterates over the system's mms once, unusing all the affected entries as it walks each set of page tables. It also makes similar changes to shmem_unuse. Improvement swapoff was called on a swap partition containing about 6G of data, in a VM(8cpu, 16G RAM), and calls to unuse_pte_range() were counted. Present implementation....about 1200M calls(8min, avg 80% cpu util). Prototype.................about 9.0K calls(3min, avg 5% cpu util). Details In shmem_unuse(), iterate over the shmem_swaplist and, for each shmem_inode_info that contains a swap entry, pass it to shmem_unuse_inode(), along with the swap type. In shmem_unuse_inode(), iterate over its associated xarray, and store the index and value of each swap entry in an array for passing to shmem_swapin_page() outside of the RCU critical section. In try_to_unuse(), instead of iterating over the entries in the type and unusing them one by one, perhaps walking all the page tables for all the processes for each one, iterate over the mmlist, making one pass. Pass each mm to unuse_mm() to begin its page table walk, and during the walk, unuse all the ptes that have backing store in the swap type received by try_to_unuse(). After the walk, check the type for orphaned swap entries with find_next_to_unuse(), and remove them from the swap cache. If find_next_to_unuse() starts over at the beginning of the type, repeat the check of the shmem_swaplist and the walk a maximum of three times. Change unuse_mm() and the intervening walk functions down to unuse_pte_range() to take the type as a parameter, and to iterate over their entire range, calling the next function down on every iteration. In unuse_pte_range(), make a swap entry from each pte in the range using the passed in type. If it has backing store in the type, call swapin_readahead() to retrieve the page and pass it to unuse_pte(). Pass the count of pages_to_unuse down the page table walks in try_to_unuse(), and return from the walk when the desired number of pages has been swapped back in. Link: http://lkml.kernel.org/r/20190114153129.4852-2-vpillai@digitalocean.com Signed-off-by: Vineeth Remanan Pillai Signed-off-by: Kelley Nielsen Signed-off-by: Huang Ying Acked-by: Hugh Dickins Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/frontswap.h | 7 + include/linux/shmem_fs.h | 3 +- mm/shmem.c | 267 +++++++++++++++------------- mm/swapfile.c | 433 +++++++++++++++++----------------------------- 4 files changed, 319 insertions(+), 391 deletions(-) (limited to 'include/linux') diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h index 011965c08b93..6d775984905b 100644 --- a/include/linux/frontswap.h +++ b/include/linux/frontswap.h @@ -7,6 +7,13 @@ #include #include +/* + * Return code to denote that requested number of + * frontswap pages are unused(moved to page cache). + * Used in in shmem_unuse and try_to_unuse. + */ +#define FRONTSWAP_PAGES_UNUSED 2 + struct frontswap_ops { void (*init)(unsigned); /* this swap type was just swapon'ed */ int (*store)(unsigned, pgoff_t, struct page *); /* store a page */ diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index f155dc607112..f3fb1edb3526 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -72,7 +72,8 @@ extern void shmem_unlock_mapping(struct address_space *mapping); extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); -extern int shmem_unuse(swp_entry_t entry, struct page *page); +extern int shmem_unuse(unsigned int type, bool frontswap, + unsigned long *fs_pages_to_unuse); extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); extern unsigned long shmem_partial_swap_usage(struct address_space *mapping, diff --git a/mm/shmem.c b/mm/shmem.c index b4d27ef87496..283a1833dafc 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -36,6 +36,7 @@ #include #include #include +#include #include /* for arch/microblaze update_mmu_cache() */ @@ -1093,159 +1094,184 @@ static void shmem_evict_inode(struct inode *inode) clear_inode(inode); } -static unsigned long find_swap_entry(struct xarray *xa, void *item) +extern struct swap_info_struct *swap_info[]; + +static int shmem_find_swap_entries(struct address_space *mapping, + pgoff_t start, unsigned int nr_entries, + struct page **entries, pgoff_t *indices, + bool frontswap) { - XA_STATE(xas, xa, 0); - unsigned int checked = 0; - void *entry; + XA_STATE(xas, &mapping->i_pages, start); + struct page *page; + unsigned int ret = 0; + + if (!nr_entries) + return 0; rcu_read_lock(); - xas_for_each(&xas, entry, ULONG_MAX) { - if (xas_retry(&xas, entry)) + xas_for_each(&xas, page, ULONG_MAX) { + if (xas_retry(&xas, page)) continue; - if (entry == item) - break; - checked++; - if ((checked % XA_CHECK_SCHED) != 0) + + if (!xa_is_value(page)) continue; - xas_pause(&xas); - cond_resched_rcu(); + + if (frontswap) { + swp_entry_t entry = radix_to_swp_entry(page); + + if (!frontswap_test(swap_info[swp_type(entry)], + swp_offset(entry))) + continue; + } + + indices[ret] = xas.xa_index; + entries[ret] = page; + + if (need_resched()) { + xas_pause(&xas); + cond_resched_rcu(); + } + if (++ret == nr_entries) + break; } rcu_read_unlock(); - return entry ? xas.xa_index : -1; + return ret; } /* - * If swap found in inode, free it and move page from swapcache to filecache. + * Move the swapped pages for an inode to page cache. Returns the count + * of pages swapped in, or the error in case of failure. */ -static int shmem_unuse_inode(struct shmem_inode_info *info, - swp_entry_t swap, struct page **pagep) +static int shmem_unuse_swap_entries(struct inode *inode, struct pagevec pvec, + pgoff_t *indices) { - struct address_space *mapping = info->vfs_inode.i_mapping; - void *radswap; - pgoff_t index; - gfp_t gfp; + int i = 0; + int ret = 0; int error = 0; + struct address_space *mapping = inode->i_mapping; - radswap = swp_to_radix_entry(swap); - index = find_swap_entry(&mapping->i_pages, radswap); - if (index == -1) - return -EAGAIN; /* tell shmem_unuse we found nothing */ - - /* - * Move _head_ to start search for next from here. - * But be careful: shmem_evict_inode checks list_empty without taking - * mutex, and there's an instant in list_move_tail when info->swaplist - * would appear empty, if it were the only one on shmem_swaplist. - */ - if (shmem_swaplist.next != &info->swaplist) - list_move_tail(&shmem_swaplist, &info->swaplist); + for (i = 0; i < pvec.nr; i++) { + struct page *page = pvec.pages[i]; - gfp = mapping_gfp_mask(mapping); - if (shmem_should_replace_page(*pagep, gfp)) { - mutex_unlock(&shmem_swaplist_mutex); - error = shmem_replace_page(pagep, gfp, info, index); - mutex_lock(&shmem_swaplist_mutex); - /* - * We needed to drop mutex to make that restrictive page - * allocation, but the inode might have been freed while we - * dropped it: although a racing shmem_evict_inode() cannot - * complete without emptying the page cache, our page lock - * on this swapcache page is not enough to prevent that - - * free_swap_and_cache() of our swap entry will only - * trylock_page(), removing swap from page cache whatever. - * - * We must not proceed to shmem_add_to_page_cache() if the - * inode has been freed, but of course we cannot rely on - * inode or mapping or info to check that. However, we can - * safely check if our swap entry is still in use (and here - * it can't have got reused for another page): if it's still - * in use, then the inode cannot have been freed yet, and we - * can safely proceed (if it's no longer in use, that tells - * nothing about the inode, but we don't need to unuse swap). - */ - if (!page_swapcount(*pagep)) - error = -ENOENT; + if (!xa_is_value(page)) + continue; + error = shmem_swapin_page(inode, indices[i], + &page, SGP_CACHE, + mapping_gfp_mask(mapping), + NULL, NULL); + if (error == 0) { + unlock_page(page); + put_page(page); + ret++; + } + if (error == -ENOMEM) + break; + error = 0; } + return error ? error : ret; +} - /* - * We rely on shmem_swaplist_mutex, not only to protect the swaplist, - * but also to hold up shmem_evict_inode(): so inode cannot be freed - * beneath us (pagelock doesn't help until the page is in pagecache). - */ - if (!error) - error = shmem_add_to_page_cache(*pagep, mapping, index, - radswap, gfp); - if (error != -ENOMEM) { - /* - * Truncation and eviction use free_swap_and_cache(), which - * only does trylock page: if we raced, best clean up here. - */ - delete_from_swap_cache(*pagep); - set_page_dirty(*pagep); - if (!error) { - spin_lock_irq(&info->lock); - info->swapped--; - spin_unlock_irq(&info->lock); - swap_free(swap); +/* + * If swap found in inode, free it and move page from swapcache to filecache. + */ +static int shmem_unuse_inode(struct inode *inode, unsigned int type, + bool frontswap, unsigned long *fs_pages_to_unuse) +{ + struct address_space *mapping = inode->i_mapping; + pgoff_t start = 0; + struct pagevec pvec; + pgoff_t indices[PAGEVEC_SIZE]; + bool frontswap_partial = (frontswap && *fs_pages_to_unuse > 0); + int ret = 0; + + pagevec_init(&pvec); + do { + unsigned int nr_entries = PAGEVEC_SIZE; + + if (frontswap_partial && *fs_pages_to_unuse < PAGEVEC_SIZE) + nr_entries = *fs_pages_to_unuse; + + pvec.nr = shmem_find_swap_entries(mapping, start, nr_entries, + pvec.pages, indices, + frontswap); + if (pvec.nr == 0) { + ret = 0; + break; } - } - return error; + + ret = shmem_unuse_swap_entries(inode, pvec, indices); + if (ret < 0) + break; + + if (frontswap_partial) { + *fs_pages_to_unuse -= ret; + if (*fs_pages_to_unuse == 0) { + ret = FRONTSWAP_PAGES_UNUSED; + break; + } + } + + start = indices[pvec.nr - 1]; + } while (true); + + return ret; } /* - * Search through swapped inodes to find and replace swap by page. + * Read all the shared memory data that resides in the swap + * device 'type' back into memory, so the swap device can be + * unused. */ -int shmem_unuse(swp_entry_t swap, struct page *page) +int shmem_unuse(unsigned int type, bool frontswap, + unsigned long *fs_pages_to_unuse) { - struct list_head *this, *next; - struct shmem_inode_info *info; - struct mem_cgroup *memcg; + struct shmem_inode_info *info, *next; + struct inode *inode; + struct inode *prev_inode = NULL; int error = 0; - /* - * There's a faint possibility that swap page was replaced before - * caller locked it: caller will come back later with the right page. - */ - if (unlikely(!PageSwapCache(page) || page_private(page) != swap.val)) - goto out; + if (list_empty(&shmem_swaplist)) + return 0; + + mutex_lock(&shmem_swaplist_mutex); /* - * Charge page using GFP_KERNEL while we can wait, before taking - * the shmem_swaplist_mutex which might hold up shmem_writepage(). - * Charged back to the user (not to caller) when swap account is used. + * The extra refcount on the inode is necessary to safely dereference + * p->next after re-acquiring the lock. New shmem inodes with swap + * get added to the end of the list and we will scan them all. */ - error = mem_cgroup_try_charge_delay(page, current->mm, GFP_KERNEL, - &memcg, false); - if (error) - goto out; - /* No memory allocation: swap entry occupies the slot for the page */ - error = -EAGAIN; - - mutex_lock(&shmem_swaplist_mutex); - list_for_each_safe(this, next, &shmem_swaplist) { - info = list_entry(this, struct shmem_inode_info, swaplist); - if (info->swapped) - error = shmem_unuse_inode(info, swap, &page); - else + list_for_each_entry_safe(info, next, &shmem_swaplist, swaplist) { + if (!info->swapped) { list_del_init(&info->swaplist); + continue; + } + + inode = igrab(&info->vfs_inode); + if (!inode) + continue; + + mutex_unlock(&shmem_swaplist_mutex); + if (prev_inode) + iput(prev_inode); + prev_inode = inode; + + error = shmem_unuse_inode(inode, type, frontswap, + fs_pages_to_unuse); cond_resched(); - if (error != -EAGAIN) + + mutex_lock(&shmem_swaplist_mutex); + next = list_next_entry(info, swaplist); + if (!info->swapped) + list_del_init(&info->swaplist); + if (error) break; - /* found nothing in this: move on to search the next */ } mutex_unlock(&shmem_swaplist_mutex); - if (error) { - if (error != -ENOMEM) - error = 0; - mem_cgroup_cancel_charge(page, memcg, false); - } else - mem_cgroup_commit_charge(page, memcg, true, false); -out: - unlock_page(page); - put_page(page); + if (prev_inode) + iput(prev_inode); + return error; } @@ -1329,7 +1355,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) */ mutex_lock(&shmem_swaplist_mutex); if (list_empty(&info->swaplist)) - list_add_tail(&info->swaplist, &shmem_swaplist); + list_add(&info->swaplist, &shmem_swaplist); if (add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) { spin_lock_irq(&info->lock); @@ -3886,7 +3912,8 @@ int __init shmem_init(void) return 0; } -int shmem_unuse(swp_entry_t swap, struct page *page) +int shmem_unuse(unsigned int type, bool frontswap, + unsigned long *fs_pages_to_unuse) { return 0; } diff --git a/mm/swapfile.c b/mm/swapfile.c index dbac1d49469d..6de46984d59d 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1799,44 +1799,77 @@ out_nolock: } static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, unsigned long end, - swp_entry_t entry, struct page *page) + unsigned long addr, unsigned long end, + unsigned int type, bool frontswap, + unsigned long *fs_pages_to_unuse) { - pte_t swp_pte = swp_entry_to_pte(entry); + struct page *page; + swp_entry_t entry; pte_t *pte; + struct swap_info_struct *si; + unsigned long offset; int ret = 0; + volatile unsigned char *swap_map; - /* - * We don't actually need pte lock while scanning for swp_pte: since - * we hold page lock and mmap_sem, swp_pte cannot be inserted into the - * page table while we're scanning; though it could get zapped, and on - * some architectures (e.g. x86_32 with PAE) we might catch a glimpse - * of unmatched parts which look like swp_pte, so unuse_pte must - * recheck under pte lock. Scanning without pte lock lets it be - * preemptable whenever CONFIG_PREEMPT but not CONFIG_HIGHPTE. - */ + si = swap_info[type]; pte = pte_offset_map(pmd, addr); do { - /* - * swapoff spends a _lot_ of time in this loop! - * Test inline before going to call unuse_pte. - */ - if (unlikely(pte_same_as_swp(*pte, swp_pte))) { - pte_unmap(pte); - ret = unuse_pte(vma, pmd, addr, entry, page); - if (ret) - goto out; - pte = pte_offset_map(pmd, addr); + struct vm_fault vmf; + + if (!is_swap_pte(*pte)) + continue; + + entry = pte_to_swp_entry(*pte); + if (swp_type(entry) != type) + continue; + + offset = swp_offset(entry); + if (frontswap && !frontswap_test(si, offset)) + continue; + + pte_unmap(pte); + swap_map = &si->swap_map[offset]; + vmf.vma = vma; + vmf.address = addr; + vmf.pmd = pmd; + page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, &vmf); + if (!page) { + if (*swap_map == 0 || *swap_map == SWAP_MAP_BAD) + goto try_next; + return -ENOMEM; + } + + lock_page(page); + wait_on_page_writeback(page); + ret = unuse_pte(vma, pmd, addr, entry, page); + if (ret < 0) { + unlock_page(page); + put_page(page); + goto out; + } + + try_to_free_swap(page); + unlock_page(page); + put_page(page); + + if (*fs_pages_to_unuse && !--(*fs_pages_to_unuse)) { + ret = FRONTSWAP_PAGES_UNUSED; + goto out; } +try_next: + pte = pte_offset_map(pmd, addr); } while (pte++, addr += PAGE_SIZE, addr != end); pte_unmap(pte - 1); + + ret = 0; out: return ret; } static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, - swp_entry_t entry, struct page *page) + unsigned int type, bool frontswap, + unsigned long *fs_pages_to_unuse) { pmd_t *pmd; unsigned long next; @@ -1848,7 +1881,8 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, next = pmd_addr_end(addr, end); if (pmd_none_or_trans_huge_or_clear_bad(pmd)) continue; - ret = unuse_pte_range(vma, pmd, addr, next, entry, page); + ret = unuse_pte_range(vma, pmd, addr, next, type, + frontswap, fs_pages_to_unuse); if (ret) return ret; } while (pmd++, addr = next, addr != end); @@ -1857,7 +1891,8 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, - swp_entry_t entry, struct page *page) + unsigned int type, bool frontswap, + unsigned long *fs_pages_to_unuse) { pud_t *pud; unsigned long next; @@ -1868,7 +1903,8 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; - ret = unuse_pmd_range(vma, pud, addr, next, entry, page); + ret = unuse_pmd_range(vma, pud, addr, next, type, + frontswap, fs_pages_to_unuse); if (ret) return ret; } while (pud++, addr = next, addr != end); @@ -1877,7 +1913,8 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, - swp_entry_t entry, struct page *page) + unsigned int type, bool frontswap, + unsigned long *fs_pages_to_unuse) { p4d_t *p4d; unsigned long next; @@ -1888,78 +1925,66 @@ static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; - ret = unuse_pud_range(vma, p4d, addr, next, entry, page); + ret = unuse_pud_range(vma, p4d, addr, next, type, + frontswap, fs_pages_to_unuse); if (ret) return ret; } while (p4d++, addr = next, addr != end); return 0; } -static int unuse_vma(struct vm_area_struct *vma, - swp_entry_t entry, struct page *page) +static int unuse_vma(struct vm_area_struct *vma, unsigned int type, + bool frontswap, unsigned long *fs_pages_to_unuse) { pgd_t *pgd; unsigned long addr, end, next; int ret; - if (page_anon_vma(page)) { - addr = page_address_in_vma(page, vma); - if (addr == -EFAULT) - return 0; - else - end = addr + PAGE_SIZE; - } else { - addr = vma->vm_start; - end = vma->vm_end; - } + addr = vma->vm_start; + end = vma->vm_end; pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - ret = unuse_p4d_range(vma, pgd, addr, next, entry, page); + ret = unuse_p4d_range(vma, pgd, addr, next, type, + frontswap, fs_pages_to_unuse); if (ret) return ret; } while (pgd++, addr = next, addr != end); return 0; } -static int unuse_mm(struct mm_struct *mm, - swp_entry_t entry, struct page *page) +static int unuse_mm(struct mm_struct *mm, unsigned int type, + bool frontswap, unsigned long *fs_pages_to_unuse) { struct vm_area_struct *vma; int ret = 0; - if (!down_read_trylock(&mm->mmap_sem)) { - /* - * Activate page so shrink_inactive_list is unlikely to unmap - * its ptes while lock is dropped, so swapoff can make progress. - */ - activate_page(page); - unlock_page(page); - down_read(&mm->mmap_sem); - lock_page(page); - } + down_read(&mm->mmap_sem); for (vma = mm->mmap; vma; vma = vma->vm_next) { - if (vma->anon_vma && (ret = unuse_vma(vma, entry, page))) - break; + if (vma->anon_vma) { + ret = unuse_vma(vma, type, frontswap, + fs_pages_to_unuse); + if (ret) + break; + } cond_resched(); } up_read(&mm->mmap_sem); - return (ret < 0)? ret: 0; + return ret; } /* * Scan swap_map (or frontswap_map if frontswap parameter is true) - * from current position to next entry still in use. - * Recycle to start on reaching the end, returning 0 when empty. + * from current position to next entry still in use. Return 0 + * if there are no inuse entries after prev till end of the map. */ static unsigned int find_next_to_unuse(struct swap_info_struct *si, unsigned int prev, bool frontswap) { - unsigned int max = si->max; - unsigned int i = prev; + unsigned int i; unsigned char count; /* @@ -1968,20 +1993,7 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, * hits are okay, and sys_swapoff() has already prevented new * allocations from this area (while holding swap_lock). */ - for (;;) { - if (++i >= max) { - if (!prev) { - i = 0; - break; - } - /* - * No entries in use at top of swap_map, - * loop back to start and recheck there. - */ - max = prev + 1; - prev = 0; - i = 1; - } + for (i = prev + 1; i < si->max; i++) { count = READ_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) if (!frontswap || frontswap_test(si, i)) @@ -1989,240 +2001,121 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, if ((i % LATENCY_LIMIT) == 0) cond_resched(); } + + if (i == si->max) + i = 0; + return i; } /* - * We completely avoid races by reading each swap page in advance, - * and then search for the process using it. All the necessary - * page table adjustments can then be made atomically. - * - * if the boolean frontswap is true, only unuse pages_to_unuse pages; + * If the boolean frontswap is true, only unuse pages_to_unuse pages; * pages_to_unuse==0 means all pages; ignored if frontswap is false */ +#define SWAP_UNUSE_MAX_TRIES 3 int try_to_unuse(unsigned int type, bool frontswap, unsigned long pages_to_unuse) { + struct mm_struct *prev_mm; + struct mm_struct *mm; + struct list_head *p; + int retval = 0; struct swap_info_struct *si = swap_info[type]; - struct mm_struct *start_mm; - volatile unsigned char *swap_map; /* swap_map is accessed without - * locking. Mark it as volatile - * to prevent compiler doing - * something odd. - */ - unsigned char swcount; struct page *page; swp_entry_t entry; - unsigned int i = 0; - int retval = 0; + unsigned int i; + int retries = 0; - /* - * When searching mms for an entry, a good strategy is to - * start at the first mm we freed the previous entry from - * (though actually we don't notice whether we or coincidence - * freed the entry). Initialize this start_mm with a hold. - * - * A simpler strategy would be to start at the last mm we - * freed the previous entry from; but that would take less - * advantage of mmlist ordering, which clusters forked mms - * together, child after parent. If we race with dup_mmap(), we - * prefer to resolve parent before child, lest we miss entries - * duplicated after we scanned child: using last mm would invert - * that. - */ - start_mm = &init_mm; - mmget(&init_mm); + if (!si->inuse_pages) + return 0; - /* - * Keep on scanning until all entries have gone. Usually, - * one pass through swap_map is enough, but not necessarily: - * there are races when an instance of an entry might be missed. - */ - while ((i = find_next_to_unuse(si, i, frontswap)) != 0) { + if (!frontswap) + pages_to_unuse = 0; + +retry: + retval = shmem_unuse(type, frontswap, &pages_to_unuse); + if (retval) + goto out; + + prev_mm = &init_mm; + mmget(prev_mm); + + spin_lock(&mmlist_lock); + p = &init_mm.mmlist; + while ((p = p->next) != &init_mm.mmlist) { if (signal_pending(current)) { retval = -EINTR; break; } - /* - * Get a page for the entry, using the existing swap - * cache page if there is one. Otherwise, get a clean - * page and read the swap into it. - */ - swap_map = &si->swap_map[i]; - entry = swp_entry(type, i); - page = read_swap_cache_async(entry, - GFP_HIGHUSER_MOVABLE, NULL, 0, false); - if (!page) { - /* - * Either swap_duplicate() failed because entry - * has been freed independently, and will not be - * reused since sys_swapoff() already disabled - * allocation from here, or alloc_page() failed. - */ - swcount = *swap_map; - /* - * We don't hold lock here, so the swap entry could be - * SWAP_MAP_BAD (when the cluster is discarding). - * Instead of fail out, We can just skip the swap - * entry because swapoff will wait for discarding - * finish anyway. - */ - if (!swcount || swcount == SWAP_MAP_BAD) - continue; - retval = -ENOMEM; - break; - } + mm = list_entry(p, struct mm_struct, mmlist); + if (!mmget_not_zero(mm)) + continue; + spin_unlock(&mmlist_lock); + mmput(prev_mm); + prev_mm = mm; + retval = unuse_mm(mm, type, frontswap, &pages_to_unuse); - /* - * Don't hold on to start_mm if it looks like exiting. - */ - if (atomic_read(&start_mm->mm_users) == 1) { - mmput(start_mm); - start_mm = &init_mm; - mmget(&init_mm); + if (retval) { + mmput(prev_mm); + goto out; } /* - * Wait for and lock page. When do_swap_page races with - * try_to_unuse, do_swap_page can handle the fault much - * faster than try_to_unuse can locate the entry. This - * apparently redundant "wait_on_page_locked" lets try_to_unuse - * defer to do_swap_page in such a case - in some tests, - * do_swap_page and try_to_unuse repeatedly compete. - */ - wait_on_page_locked(page); - wait_on_page_writeback(page); - lock_page(page); - wait_on_page_writeback(page); - - /* - * Remove all references to entry. + * Make sure that we aren't completely killing + * interactive performance. */ - swcount = *swap_map; - if (swap_count(swcount) == SWAP_MAP_SHMEM) { - retval = shmem_unuse(entry, page); - /* page has already been unlocked and released */ - if (retval < 0) - break; - continue; - } - if (swap_count(swcount) && start_mm != &init_mm) - retval = unuse_mm(start_mm, entry, page); - - if (swap_count(*swap_map)) { - int set_start_mm = (*swap_map >= swcount); - struct list_head *p = &start_mm->mmlist; - struct mm_struct *new_start_mm = start_mm; - struct mm_struct *prev_mm = start_mm; - struct mm_struct *mm; - - mmget(new_start_mm); - mmget(prev_mm); - spin_lock(&mmlist_lock); - while (swap_count(*swap_map) && !retval && - (p = p->next) != &start_mm->mmlist) { - mm = list_entry(p, struct mm_struct, mmlist); - if (!mmget_not_zero(mm)) - continue; - spin_unlock(&mmlist_lock); - mmput(prev_mm); - prev_mm = mm; + cond_resched(); + spin_lock(&mmlist_lock); + } + spin_unlock(&mmlist_lock); - cond_resched(); + mmput(prev_mm); - swcount = *swap_map; - if (!swap_count(swcount)) /* any usage ? */ - ; - else if (mm == &init_mm) - set_start_mm = 1; - else - retval = unuse_mm(mm, entry, page); - - if (set_start_mm && *swap_map < swcount) { - mmput(new_start_mm); - mmget(mm); - new_start_mm = mm; - set_start_mm = 0; - } - spin_lock(&mmlist_lock); - } - spin_unlock(&mmlist_lock); - mmput(prev_mm); - mmput(start_mm); - start_mm = new_start_mm; - } - if (retval) { - unlock_page(page); - put_page(page); - break; - } + i = 0; + while ((i = find_next_to_unuse(si, i, frontswap)) != 0) { - /* - * If a reference remains (rare), we would like to leave - * the page in the swap cache; but try_to_unmap could - * then re-duplicate the entry once we drop page lock, - * so we might loop indefinitely; also, that page could - * not be swapped out to other storage meanwhile. So: - * delete from cache even if there's another reference, - * after ensuring that the data has been saved to disk - - * since if the reference remains (rarer), it will be - * read from disk into another page. Splitting into two - * pages would be incorrect if swap supported "shared - * private" pages, but they are handled by tmpfs files. - * - * Given how unuse_vma() targets one particular offset - * in an anon_vma, once the anon_vma has been determined, - * this splitting happens to be just what is needed to - * handle where KSM pages have been swapped out: re-reading - * is unnecessarily slow, but we can fix that later on. - */ - if (swap_count(*swap_map) && - PageDirty(page) && PageSwapCache(page)) { - struct writeback_control wbc = { - .sync_mode = WB_SYNC_NONE, - }; - - swap_writepage(compound_head(page), &wbc); - lock_page(page); - wait_on_page_writeback(page); - } + entry = swp_entry(type, i); + page = find_get_page(swap_address_space(entry), i); + if (!page) + continue; /* * It is conceivable that a racing task removed this page from - * swap cache just before we acquired the page lock at the top, - * or while we dropped it in unuse_mm(). The page might even - * be back in swap cache on another swap area: that we must not - * delete, since it may not have been written out to swap yet. - */ - if (PageSwapCache(page) && - likely(page_private(page) == entry.val) && - (!PageTransCompound(page) || - !swap_page_trans_huge_swapped(si, entry))) - delete_from_swap_cache(compound_head(page)); - - /* - * So we could skip searching mms once swap count went - * to 1, we did not mark any present ptes as dirty: must - * mark page dirty so shrink_page_list will preserve it. + * swap cache just before we acquired the page lock. The page + * might even be back in swap cache on another swap area. But + * that is okay, try_to_free_swap() only removes stale pages. */ - SetPageDirty(page); + lock_page(page); + wait_on_page_writeback(page); + try_to_free_swap(page); unlock_page(page); put_page(page); /* - * Make sure that we aren't completely killing - * interactive performance. + * For frontswap, we just need to unuse pages_to_unuse, if + * it was specified. Need not check frontswap again here as + * we already zeroed out pages_to_unuse if not frontswap. */ - cond_resched(); - if (frontswap && pages_to_unuse > 0) { - if (!--pages_to_unuse) - break; - } + if (pages_to_unuse && --pages_to_unuse == 0) + goto out; } - mmput(start_mm); - return retval; + /* + * Lets check again to see if there are still swap entries in the map. + * If yes, we would need to do retry the unuse logic again. + * Under global memory pressure, swap entries can be reinserted back + * into process space after the mmlist loop above passes over them. + * Its not worth continuosuly retrying to unuse the swap in this case. + * So we try SWAP_UNUSE_MAX_TRIES times. + */ + if (++retries >= SWAP_UNUSE_MAX_TRIES) + retval = -EBUSY; + else if (si->inuse_pages) + goto retry; + +out: + return (retval == FRONTSWAP_PAGES_UNUSED) ? 0 : retval; } /* -- cgit v1.2.3-71-gd317 From 6e2e07cd35f6f72d1950453b170f6bfb6c668c46 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 5 Mar 2019 15:47:36 -0800 Subject: mm: better document PG_reserved The usage of PG_reserved and how PG_reserved pages are to be treated is buried deep down in different parts of the kernel. Let's shine some light onto these details by documenting current users and expected behavior. Especially, clarify on the "Some of them might not even exist" case. These are physical memory gaps that will never be dumped as they are not marked as IORESOURCE_SYSRAM. PG_reserved does in general not hinder anybody from dumping or swapping. In some cases, these pages will not be stored in the hibernation image. Link: http://lkml.kernel.org/r/20190114125903.24845-10-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Andrew Morton Cc: Stephen Rothwell Cc: Pavel Tatashin Cc: Michal Hocko Cc: Alexander Duyck Cc: Matthew Wilcox Cc: Anthony Yznaga Cc: Miles Chen Cc: Cc: Dan Williams Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 33 +++++++++++++++++++++++++++++++-- 1 file changed, 31 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 808b4183e30d..9f8712a4b1a5 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -17,8 +17,37 @@ /* * Various page->flags bits: * - * PG_reserved is set for special pages, which can never be swapped out. Some - * of them might not even exist... + * PG_reserved is set for special pages. The "struct page" of such a page + * should in general not be touched (e.g. set dirty) except by its owner. + * Pages marked as PG_reserved include: + * - Pages part of the kernel image (including vDSO) and similar (e.g. BIOS, + * initrd, HW tables) + * - Pages reserved or allocated early during boot (before the page allocator + * was initialized). This includes (depending on the architecture) the + * initial vmemmap, initial page tables, crashkernel, elfcorehdr, and much + * much more. Once (if ever) freed, PG_reserved is cleared and they will + * be given to the page allocator. + * - Pages falling into physical memory gaps - not IORESOURCE_SYSRAM. Trying + * to read/write these pages might end badly. Don't touch! + * - The zero page(s) + * - Pages not added to the page allocator when onlining a section because + * they were excluded via the online_page_callback() or because they are + * PG_hwpoison. + * - Pages allocated in the context of kexec/kdump (loaded kernel image, + * control pages, vmcoreinfo) + * - MMIO/DMA pages. Some architectures don't allow to ioremap pages that are + * not marked PG_reserved (as they might be in use by somebody else who does + * not respect the caching strategy). + * - Pages part of an offline section (struct pages of offline sections should + * not be trusted as they will be initialized when first onlined). + * - MCA pages on ia64 + * - Pages holding CPU notes for POWER Firmware Assisted Dump + * - Device memory (e.g. PMEM, DAX, HMM) + * Some PG_reserved pages will be excluded from the hibernation image. + * PG_reserved does in general not hinder anybody from dumping or swapping + * and is no longer required for remap_pfn_range(). ioremap might require it. + * Consequently, PG_reserved for a page mapped into user space can indicate + * the zero page, the vDSO, MMIO pages or device memory. * * The PG_private bitflag is set on pagecache pages if they contain filesystem * specific data (which is normally at page->private). It can be used by -- cgit v1.2.3-71-gd317 From d7fefcc8de9147cc37d0c00df12e7ea4f77999b5 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Tue, 5 Mar 2019 15:47:40 -0800 Subject: mm/cma: add PF flag to force non cma alloc Patch series "mm/kvm/vfio/ppc64: Migrate compound pages out of CMA region", v8. ppc64 uses the CMA area for the allocation of guest page table (hash page table). We won't be able to start guest if we fail to allocate hash page table. We have observed hash table allocation failure because we failed to migrate pages out of CMA region because they were pinned. This happen when we are using VFIO. VFIO on ppc64 pins the entire guest RAM. If the guest RAM pages get allocated out of CMA region, we won't be able to migrate those pages. The pages are also pinned for the lifetime of the guest. Currently we support migration of non-compound pages. With THP and with the addition of hugetlb migration we can end up allocating compound pages from CMA region. This patch series add support for migrating compound pages. This patch (of 4): Add PF_MEMALLOC_NOCMA which make sure any allocation in that context is marked non-movable and hence cannot be satisfied by CMA region. This is useful with get_user_pages_longterm where we want to take a page pin by migrating pages from CMA region. Marking the section PF_MEMALLOC_NOCMA ensures that we avoid unnecessary page migration later. Link: http://lkml.kernel.org/r/20190114095438.32470-2-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Suggested-by: Andrea Arcangeli Reviewed-by: Andrea Arcangeli Cc: Michal Hocko Cc: Alexey Kardashevskiy Cc: David Gibson Cc: Michael Ellerman Cc: Mel Gorman Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 + include/linux/sched/mm.h | 48 ++++++++++++++++++++++++++++++++++++++++-------- 2 files changed, 41 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index ebfb34fb9b30..36ec6e7e8291 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1407,6 +1407,7 @@ extern struct pid *cad_pid; #define PF_UMH 0x02000000 /* I'm an Usermodehelper process */ #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ +#define PF_MEMALLOC_NOCMA 0x10000000 /* All allocation request will have _GFP_MOVABLE cleared */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 3bfa6a0cbba4..0cd9f10423fb 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -148,17 +148,25 @@ static inline bool in_vfork(struct task_struct *tsk) * Applies per-task gfp context to the given allocation flags. * PF_MEMALLOC_NOIO implies GFP_NOIO * PF_MEMALLOC_NOFS implies GFP_NOFS + * PF_MEMALLOC_NOCMA implies no allocation from CMA region. */ static inline gfp_t current_gfp_context(gfp_t flags) { - /* - * NOIO implies both NOIO and NOFS and it is a weaker context - * so always make sure it makes precedence - */ - if (unlikely(current->flags & PF_MEMALLOC_NOIO)) - flags &= ~(__GFP_IO | __GFP_FS); - else if (unlikely(current->flags & PF_MEMALLOC_NOFS)) - flags &= ~__GFP_FS; + if (unlikely(current->flags & + (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_NOCMA))) { + /* + * NOIO implies both NOIO and NOFS and it is a weaker context + * so always make sure it makes precedence + */ + if (current->flags & PF_MEMALLOC_NOIO) + flags &= ~(__GFP_IO | __GFP_FS); + else if (current->flags & PF_MEMALLOC_NOFS) + flags &= ~__GFP_FS; +#ifdef CONFIG_CMA + if (current->flags & PF_MEMALLOC_NOCMA) + flags &= ~__GFP_MOVABLE; +#endif + } return flags; } @@ -248,6 +256,30 @@ static inline void memalloc_noreclaim_restore(unsigned int flags) current->flags = (current->flags & ~PF_MEMALLOC) | flags; } +#ifdef CONFIG_CMA +static inline unsigned int memalloc_nocma_save(void) +{ + unsigned int flags = current->flags & PF_MEMALLOC_NOCMA; + + current->flags |= PF_MEMALLOC_NOCMA; + return flags; +} + +static inline void memalloc_nocma_restore(unsigned int flags) +{ + current->flags = (current->flags & ~PF_MEMALLOC_NOCMA) | flags; +} +#else +static inline unsigned int memalloc_nocma_save(void) +{ + return 0; +} + +static inline void memalloc_nocma_restore(unsigned int flags) +{ +} +#endif + #ifdef CONFIG_MEMCG /** * memalloc_use_memcg - Starts the remote memcg charging scope. -- cgit v1.2.3-71-gd317 From 9a4e9f3b2d7393d50256762c21e7466b4b6b1c9c Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Tue, 5 Mar 2019 15:47:44 -0800 Subject: mm: update get_user_pages_longterm to migrate pages allocated from CMA region This patch updates get_user_pages_longterm to migrate pages allocated out of CMA region. This makes sure that we don't keep non-movable pages (due to page reference count) in the CMA area. This will be used by ppc64 in a later patch to avoid pinning pages in the CMA region. ppc64 uses CMA region for allocation of the hardware page table (hash page table) and not able to migrate pages out of CMA region results in page table allocation failures. One case where we hit this easy is when a guest using a VFIO passthrough device. VFIO locks all the guest's memory and if the guest memory is backed by CMA region, it becomes unmovable resulting in fragmenting the CMA and possibly preventing other guests from allocation a large enough hash page table. NOTE: We allocate the new page without using __GFP_THISNODE Link: http://lkml.kernel.org/r/20190114095438.32470-3-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Cc: Alexey Kardashevskiy Cc: Andrea Arcangeli Cc: David Gibson Cc: Michael Ellerman Cc: Michal Hocko Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 2 + include/linux/mm.h | 3 +- mm/gup.c | 200 ++++++++++++++++++++++++++++++++++++++++++------ mm/hugetlb.c | 4 +- 4 files changed, 182 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 54c317c8355f..ea35263eb76b 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -371,6 +371,8 @@ struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask); struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address); +struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask, + int nid, nodemask_t *nmask); int huge_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t idx); diff --git a/include/linux/mm.h b/include/linux/mm.h index 80bb6408fe73..20ec56f8e2bb 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1536,7 +1536,8 @@ long get_user_pages_locked(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); -#ifdef CONFIG_FS_DAX + +#if defined(CONFIG_FS_DAX) || defined(CONFIG_CMA) long get_user_pages_longterm(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas); diff --git a/mm/gup.c b/mm/gup.c index 75029649baca..22291db50013 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -13,6 +13,9 @@ #include #include #include +#include +#include +#include #include #include @@ -1126,7 +1129,167 @@ long get_user_pages(unsigned long start, unsigned long nr_pages, } EXPORT_SYMBOL(get_user_pages); +#if defined(CONFIG_FS_DAX) || defined (CONFIG_CMA) + #ifdef CONFIG_FS_DAX +static bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages) +{ + long i; + struct vm_area_struct *vma_prev = NULL; + + for (i = 0; i < nr_pages; i++) { + struct vm_area_struct *vma = vmas[i]; + + if (vma == vma_prev) + continue; + + vma_prev = vma; + + if (vma_is_fsdax(vma)) + return true; + } + return false; +} +#else +static inline bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages) +{ + return false; +} +#endif + +#ifdef CONFIG_CMA +static struct page *new_non_cma_page(struct page *page, unsigned long private) +{ + /* + * We want to make sure we allocate the new page from the same node + * as the source page. + */ + int nid = page_to_nid(page); + /* + * Trying to allocate a page for migration. Ignore allocation + * failure warnings. We don't force __GFP_THISNODE here because + * this node here is the node where we have CMA reservation and + * in some case these nodes will have really less non movable + * allocation memory. + */ + gfp_t gfp_mask = GFP_USER | __GFP_NOWARN; + + if (PageHighMem(page)) + gfp_mask |= __GFP_HIGHMEM; + +#ifdef CONFIG_HUGETLB_PAGE + if (PageHuge(page)) { + struct hstate *h = page_hstate(page); + /* + * We don't want to dequeue from the pool because pool pages will + * mostly be from the CMA region. + */ + return alloc_migrate_huge_page(h, gfp_mask, nid, NULL); + } +#endif + if (PageTransHuge(page)) { + struct page *thp; + /* + * ignore allocation failure warnings + */ + gfp_t thp_gfpmask = GFP_TRANSHUGE | __GFP_NOWARN; + + /* + * Remove the movable mask so that we don't allocate from + * CMA area again. + */ + thp_gfpmask &= ~__GFP_MOVABLE; + thp = __alloc_pages_node(nid, thp_gfpmask, HPAGE_PMD_ORDER); + if (!thp) + return NULL; + prep_transhuge_page(thp); + return thp; + } + + return __alloc_pages_node(nid, gfp_mask, 0); +} + +static long check_and_migrate_cma_pages(unsigned long start, long nr_pages, + unsigned int gup_flags, + struct page **pages, + struct vm_area_struct **vmas) +{ + long i; + bool drain_allow = true; + bool migrate_allow = true; + LIST_HEAD(cma_page_list); + +check_again: + for (i = 0; i < nr_pages; i++) { + /* + * If we get a page from the CMA zone, since we are going to + * be pinning these entries, we might as well move them out + * of the CMA zone if possible. + */ + if (is_migrate_cma_page(pages[i])) { + + struct page *head = compound_head(pages[i]); + + if (PageHuge(head)) { + isolate_huge_page(head, &cma_page_list); + } else { + if (!PageLRU(head) && drain_allow) { + lru_add_drain_all(); + drain_allow = false; + } + + if (!isolate_lru_page(head)) { + list_add_tail(&head->lru, &cma_page_list); + mod_node_page_state(page_pgdat(head), + NR_ISOLATED_ANON + + page_is_file_cache(head), + hpage_nr_pages(head)); + } + } + } + } + + if (!list_empty(&cma_page_list)) { + /* + * drop the above get_user_pages reference. + */ + for (i = 0; i < nr_pages; i++) + put_page(pages[i]); + + if (migrate_pages(&cma_page_list, new_non_cma_page, + NULL, 0, MIGRATE_SYNC, MR_CONTIG_RANGE)) { + /* + * some of the pages failed migration. Do get_user_pages + * without migration. + */ + migrate_allow = false; + + if (!list_empty(&cma_page_list)) + putback_movable_pages(&cma_page_list); + } + /* + * We did migrate all the pages, Try to get the page references again + * migrating any new CMA pages which we failed to isolate earlier. + */ + nr_pages = get_user_pages(start, nr_pages, gup_flags, pages, vmas); + if ((nr_pages > 0) && migrate_allow) { + drain_allow = true; + goto check_again; + } + } + + return nr_pages; +} +#else +static inline long check_and_migrate_cma_pages(unsigned long start, long nr_pages, + unsigned int gup_flags, + struct page **pages, + struct vm_area_struct **vmas) +{ + return nr_pages; +} +#endif + /* * This is the same as get_user_pages() in that it assumes we are * operating on the current task's mm, but it goes further to validate @@ -1140,11 +1303,11 @@ EXPORT_SYMBOL(get_user_pages); * Contrast this to iov_iter_get_pages() usages which are transient. */ long get_user_pages_longterm(unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, - struct vm_area_struct **vmas_arg) + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas_arg) { struct vm_area_struct **vmas = vmas_arg; - struct vm_area_struct *vma_prev = NULL; + unsigned long flags; long rc, i; if (!pages) @@ -1157,31 +1320,20 @@ long get_user_pages_longterm(unsigned long start, unsigned long nr_pages, return -ENOMEM; } + flags = memalloc_nocma_save(); rc = get_user_pages(start, nr_pages, gup_flags, pages, vmas); + memalloc_nocma_restore(flags); + if (rc < 0) + goto out; - for (i = 0; i < rc; i++) { - struct vm_area_struct *vma = vmas[i]; - - if (vma == vma_prev) - continue; - - vma_prev = vma; - - if (vma_is_fsdax(vma)) - break; - } - - /* - * Either get_user_pages() failed, or the vma validation - * succeeded, in either case we don't need to put_page() before - * returning. - */ - if (i >= rc) + if (check_dax_vmas(vmas, rc)) { + for (i = 0; i < rc; i++) + put_page(pages[i]); + rc = -EOPNOTSUPP; goto out; + } - for (i = 0; i < rc; i++) - put_page(pages[i]); - rc = -EOPNOTSUPP; + rc = check_and_migrate_cma_pages(start, rc, gup_flags, pages, vmas); out: if (vmas != vmas_arg) kfree(vmas); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 0c7848fccf93..97b1e0290c66 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1587,8 +1587,8 @@ out_unlock: return page; } -static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask, - int nid, nodemask_t *nmask) +struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask, + int nid, nodemask_t *nmask) { struct page *page; -- cgit v1.2.3-71-gd317 From 59118c42a60b997d277ad04d2309a6ec30682e5e Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Tue, 5 Mar 2019 15:48:02 -0800 Subject: mm: swap: use mem_cgroup_is_root() instead of deferencing css->parent mem_cgroup_is_root() is the preferred API to check if memcg is root or not. Use it instead of deferencing css->parent. Link: http://lkml.kernel.org/r/1547232913-118148-1-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi Acked-by: Michal Hocko Cc: Huang Ying Cc: Tim Chen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 622025ac1461..649529be91f2 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -625,7 +625,7 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) return vm_swappiness; /* root ? */ - if (mem_cgroup_disabled() || !memcg->css.parent) + if (mem_cgroup_disabled() || mem_cgroup_is_root(memcg)) return vm_swappiness; return memcg->swappiness; -- cgit v1.2.3-71-gd317 From b9726c26dc21b15a2faea96fae3a42f2f7fffdcb Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 5 Mar 2019 15:48:26 -0800 Subject: numa: make "nr_node_ids" unsigned int Number of NUMA nodes can't be negative. This saves a few bytes on x86_64: add/remove: 0/0 grow/shrink: 4/21 up/down: 27/-265 (-238) Function old new delta hv_synic_alloc.cold 88 110 +22 prealloc_shrinker 260 262 +2 bootstrap 249 251 +2 sched_init_numa 1566 1567 +1 show_slab_objects 778 777 -1 s_show 1201 1200 -1 kmem_cache_init 346 345 -1 __alloc_workqueue_key 1146 1145 -1 mem_cgroup_css_alloc 1614 1612 -2 __do_sys_swapon 4702 4699 -3 __list_lru_init 655 651 -4 nic_probe 2379 2374 -5 store_user_store 118 111 -7 red_zone_store 106 99 -7 poison_store 106 99 -7 wq_numa_init 348 338 -10 __kmem_cache_empty 75 65 -10 task_numa_free 186 173 -13 merge_across_nodes_store 351 336 -15 irq_create_affinity_masks 1261 1246 -15 do_numa_crng_init 343 321 -22 task_numa_fault 4760 4737 -23 swapfile_init 179 156 -23 hv_synic_alloc 536 492 -44 apply_wqattrs_prepare 746 695 -51 Link: http://lkml.kernel.org/r/20190201223029.GA15820@avx2 Signed-off-by: Alexey Dobriyan Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/mm/numa.c | 2 +- arch/powerpc/mm/numa.c | 2 +- arch/x86/kernel/setup_percpu.c | 2 +- arch/x86/mm/numa.c | 4 ++-- include/linux/nodemask.h | 4 ++-- mm/list_lru.c | 3 +-- mm/memcontrol.c | 2 +- mm/page_alloc.c | 2 +- mm/slab.c | 3 +-- mm/slub.c | 2 +- mm/swapfile.c | 2 +- mm/vmscan.c | 2 +- 12 files changed, 14 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index ae34e3a1cef1..7a0a555b366a 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -120,7 +120,7 @@ static void __init setup_node_to_cpumask_map(void) } /* cpumask_of_node() will now work */ - pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids); + pr_debug("Node to cpumask map for %u nodes\n", nr_node_ids); } /* diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 270cefb75cca..df1e11ebbabb 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -84,7 +84,7 @@ static void __init setup_node_to_cpumask_map(void) alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]); /* cpumask_of_node() will now work */ - dbg("Node to cpumask map for %d nodes\n", nr_node_ids); + dbg("Node to cpumask map for %u nodes\n", nr_node_ids); } static int __init fake_numa_create_new_node(unsigned long end_pfn, diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index e8796fcd7e5a..13af08827eef 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -171,7 +171,7 @@ void __init setup_per_cpu_areas(void) unsigned long delta; int rc; - pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%u nr_node_ids:%d\n", + pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%u nr_node_ids:%u\n", NR_CPUS, nr_cpumask_bits, nr_cpu_ids, nr_node_ids); /* diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 1308f5408bf7..12c1b7a83ed7 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -123,7 +123,7 @@ void __init setup_node_to_cpumask_map(void) alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]); /* cpumask_of_node() will now work */ - pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids); + pr_debug("Node to cpumask map for %u nodes\n", nr_node_ids); } static int __init numa_add_memblk_to(int nid, u64 start, u64 end, @@ -866,7 +866,7 @@ const struct cpumask *cpumask_of_node(int node) { if (node >= nr_node_ids) { printk(KERN_WARNING - "cpumask_of_node(%d): node > nr_node_ids(%d)\n", + "cpumask_of_node(%d): node > nr_node_ids(%u)\n", node, nr_node_ids); dump_stack(); return cpu_none_mask; diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 5a30ad594ccc..962c5e783d50 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -444,7 +444,7 @@ static inline int next_memory_node(int nid) return next_node(nid, node_states[N_MEMORY]); } -extern int nr_node_ids; +extern unsigned int nr_node_ids; extern int nr_online_nodes; static inline void node_set_online(int nid) @@ -485,7 +485,7 @@ static inline int num_node_state(enum node_states state) #define first_online_node 0 #define first_memory_node 0 #define next_online_node(nid) (MAX_NUMNODES) -#define nr_node_ids 1 +#define nr_node_ids 1U #define nr_online_nodes 1 #define node_set_online(node) node_set_state((node), N_ONLINE) diff --git a/mm/list_lru.c b/mm/list_lru.c index 5b30625fd365..0730bf8ff39f 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -601,7 +601,6 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware, struct lock_class_key *key, struct shrinker *shrinker) { int i; - size_t size = sizeof(*lru->node) * nr_node_ids; int err = -ENOMEM; #ifdef CONFIG_MEMCG_KMEM @@ -612,7 +611,7 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware, #endif memcg_get_cache_ids(); - lru->node = kzalloc(size, GFP_KERNEL); + lru->node = kcalloc(nr_node_ids, sizeof(*lru->node), GFP_KERNEL); if (!lru->node) goto out; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 30bda8d7fb5c..45cd1f84268a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4429,7 +4429,7 @@ static void mem_cgroup_free(struct mem_cgroup *memcg) static struct mem_cgroup *mem_cgroup_alloc(void) { struct mem_cgroup *memcg; - size_t size; + unsigned int size; int node; size = sizeof(struct mem_cgroup); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 11a5f50efd97..8df43caf2eb7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -289,7 +289,7 @@ EXPORT_SYMBOL(movable_zone); #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ #if MAX_NUMNODES > 1 -int nr_node_ids __read_mostly = MAX_NUMNODES; +unsigned int nr_node_ids __read_mostly = MAX_NUMNODES; int nr_online_nodes __read_mostly = 1; EXPORT_SYMBOL(nr_node_ids); EXPORT_SYMBOL(nr_online_nodes); diff --git a/mm/slab.c b/mm/slab.c index 757e646baa5d..7510a1b489df 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -677,12 +677,11 @@ static struct alien_cache *__alloc_alien_cache(int node, int entries, static struct alien_cache **alloc_alien_cache(int node, int limit, gfp_t gfp) { struct alien_cache **alc_ptr; - size_t memsize = sizeof(void *) * nr_node_ids; int i; if (limit > 1) limit = 12; - alc_ptr = kzalloc_node(memsize, gfp, node); + alc_ptr = kcalloc_node(nr_node_ids, sizeof(void *), gfp, node); if (!alc_ptr) return NULL; diff --git a/mm/slub.c b/mm/slub.c index 017a2ce5ba23..1b08fbcb7e61 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -4262,7 +4262,7 @@ void __init kmem_cache_init(void) cpuhp_setup_state_nocalls(CPUHP_SLUB_DEAD, "slub:dead", NULL, slub_cpu_dead); - pr_info("SLUB: HWalign=%d, Order=%u-%u, MinObjects=%u, CPUs=%u, Nodes=%d\n", + pr_info("SLUB: HWalign=%d, Order=%u-%u, MinObjects=%u, CPUs=%u, Nodes=%u\n", cache_line_size(), slub_min_order, slub_max_order, slub_min_objects, nr_cpu_ids, nr_node_ids); diff --git a/mm/swapfile.c b/mm/swapfile.c index 57e9b1b31d55..a14257ac0476 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2713,7 +2713,7 @@ static struct swap_info_struct *alloc_swap_info(void) struct swap_info_struct *p; unsigned int type; int i; - int size = sizeof(*p) + nr_node_ids * sizeof(struct plist_node); + unsigned int size = sizeof(*p) + nr_node_ids * sizeof(struct plist_node); p = kvzalloc(size, GFP_KERNEL); if (!p) diff --git a/mm/vmscan.c b/mm/vmscan.c index 209c2c78a087..e1f7ccdc0a90 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -374,7 +374,7 @@ unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone */ int prealloc_shrinker(struct shrinker *shrinker) { - size_t size = sizeof(*shrinker->nr_deferred); + unsigned int size = sizeof(*shrinker->nr_deferred); if (shrinker->flags & SHRINKER_NUMA_AWARE) size *= nr_node_ids; -- cgit v1.2.3-71-gd317 From ce0725f78a56a59bdb07cef003bc6fef722da38e Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Tue, 5 Mar 2019 15:48:29 -0800 Subject: numa: make "nr_online_nodes" unsigned int Number of online NUMA nodes can't be negative as well. This doesn't save space as the variable is used only in 32-bit context, but do it anyway for consistency. Link: http://lkml.kernel.org/r/20190201223151.GB15820@avx2 Signed-off-by: Alexey Dobriyan Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/nodemask.h | 4 ++-- mm/page_alloc.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 962c5e783d50..27e7fa36f707 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -445,7 +445,7 @@ static inline int next_memory_node(int nid) } extern unsigned int nr_node_ids; -extern int nr_online_nodes; +extern unsigned int nr_online_nodes; static inline void node_set_online(int nid) { @@ -486,7 +486,7 @@ static inline int num_node_state(enum node_states state) #define first_memory_node 0 #define next_online_node(nid) (MAX_NUMNODES) #define nr_node_ids 1U -#define nr_online_nodes 1 +#define nr_online_nodes 1U #define node_set_online(node) node_set_state((node), N_ONLINE) #define node_set_offline(node) node_clear_state((node), N_ONLINE) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8df43caf2eb7..c29828ec9183 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -290,7 +290,7 @@ EXPORT_SYMBOL(movable_zone); #if MAX_NUMNODES > 1 unsigned int nr_node_ids __read_mostly = MAX_NUMNODES; -int nr_online_nodes __read_mostly = 1; +unsigned int nr_online_nodes __read_mostly = 1; EXPORT_SYMBOL(nr_node_ids); EXPORT_SYMBOL(nr_online_nodes); #endif @@ -5664,7 +5664,7 @@ void __ref build_all_zonelists(pg_data_t *pgdat) else page_group_by_mobility_disabled = 0; - pr_info("Built %i zonelists, mobility grouping %s. Total pages: %ld\n", + pr_info("Built %u zonelists, mobility grouping %s. Total pages: %ld\n", nr_online_nodes, page_group_by_mobility_disabled ? "off" : "on", vm_total_pages); -- cgit v1.2.3-71-gd317 From 6d2bef9df7ccf3a2db0160be24f8b92a3f24708a Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Tue, 5 Mar 2019 15:48:33 -0800 Subject: mm/page_poison: update comment after code moved mm/debug-pagealloc.c is no more, so of course header now needs to be updated. This seems like something checkpatch should be able to catch - worth looking into? Link: http://lkml.kernel.org/r/20190207191113.14039-1-mst@redhat.com Fixes: 8823b1dbc05f ("mm/page_poison.c: enable PAGE_POISONING as a separate option") Signed-off-by: Michael S. Tsirkin Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/poison.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/poison.h b/include/linux/poison.h index 15927ebc22f2..5046bad0c1c5 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -30,7 +30,7 @@ */ #define TIMER_ENTRY_STATIC ((void *) 0x300 + POISON_POINTER_DELTA) -/********** mm/debug-pagealloc.c **********/ +/********** mm/page_poison.c **********/ #ifdef CONFIG_PAGE_POISONING_ZERO #define PAGE_POISON 0x00 #else -- cgit v1.2.3-71-gd317 From 494eec70f054965e2e699db450cde2c08db1c008 Mon Sep 17 00:00:00 2001 From: "john.hubbard@gmail.com" Date: Tue, 5 Mar 2019 15:48:49 -0800 Subject: mm: page_cache_add_speculative(): refactor out some code duplication From: John Hubbard This combines the common elements of these routines: page_cache_get_speculative() page_cache_add_speculative() This was anticipated by the original author, as shown by the comment in commit ce0ad7f095258 ("powerpc/mm: Lockless get_user_pages_fast() for 64-bit (v3)"): "Same as above, but add instead of inc (could just be merged)" There is no intention to introduce any behavioral change, but there is a small risk of that, due to slightly differing ways of expressing the TINY_RCU and related configurations. This also removes the VM_BUG_ON(in_interrupt()) that was in page_cache_add_speculative(), but not in page_cache_get_speculative(). This provides slightly less detection of such bugs, but it given that it was only there on the "add" path anyway, we can likely do without it just fine. And it removes the VM_BUG_ON_PAGE(PageCompound(page) && page != compound_head(page), page); that page_cache_add_speculative() had. Link: http://lkml.kernel.org/r/20190206231016.22734-2-jhubbard@nvidia.com Signed-off-by: John Hubbard Reviewed-by: Andrew Morton Cc: Benjamin Herrenschmidt Cc: Dave Kleikamp Cc: Hugh Dickins Cc: Jeff Layton Cc: Matthew Wilcox Cc: Nicholas Piggin Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 31 +++++++++---------------------- 1 file changed, 9 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index e2d7039af6a3..b477a70cc2e4 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -164,7 +164,7 @@ void release_pages(struct page **pages, int nr); * will find the page or it will not. Likewise, the old find_get_page could run * either before the insertion or afterwards, depending on timing. */ -static inline int page_cache_get_speculative(struct page *page) +static inline int __page_cache_add_speculative(struct page *page, int count) { #ifdef CONFIG_TINY_RCU # ifdef CONFIG_PREEMPT_COUNT @@ -180,10 +180,10 @@ static inline int page_cache_get_speculative(struct page *page) * SMP requires. */ VM_BUG_ON_PAGE(page_count(page) == 0, page); - page_ref_inc(page); + page_ref_add(page, count); #else - if (unlikely(!get_page_unless_zero(page))) { + if (unlikely(!page_ref_add_unless(page, count, 0))) { /* * Either the page has been freed, or will be freed. * In either case, retry here and the caller should @@ -197,27 +197,14 @@ static inline int page_cache_get_speculative(struct page *page) return 1; } -/* - * Same as above, but add instead of inc (could just be merged) - */ -static inline int page_cache_add_speculative(struct page *page, int count) +static inline int page_cache_get_speculative(struct page *page) { - VM_BUG_ON(in_interrupt()); - -#if !defined(CONFIG_SMP) && defined(CONFIG_TREE_RCU) -# ifdef CONFIG_PREEMPT_COUNT - VM_BUG_ON(!in_atomic() && !irqs_disabled()); -# endif - VM_BUG_ON_PAGE(page_count(page) == 0, page); - page_ref_add(page, count); - -#else - if (unlikely(!page_ref_add_unless(page, count, 0))) - return 0; -#endif - VM_BUG_ON_PAGE(PageCompound(page) && page != compound_head(page), page); + return __page_cache_add_speculative(page, 1); +} - return 1; +static inline int page_cache_add_speculative(struct page *page, int count) +{ + return __page_cache_add_speculative(page, count); } #ifdef CONFIG_NUMA -- cgit v1.2.3-71-gd317 From ace451eb5ec5bb432fc28d8a723838b88e28643e Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Tue, 5 Mar 2019 15:48:56 -0800 Subject: include/linux/compaction.h: fix potential build error Declaration of struct node is required regardless. On UMA systems, including compaction.h without preceding node.h shouldn't cause a build error. Link: http://lkml.kernel.org/r/20190208080437.253322-1-yuzhao@google.com Signed-off-by: Yu Zhao Reviewed-by: Andrew Morton Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index c960923d9ec2..9569e7c786d3 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -226,8 +226,8 @@ static inline void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_i #endif /* CONFIG_COMPACTION */ -#if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) struct node; +#if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA) extern int compaction_register_node(struct node *node); extern void compaction_unregister_node(struct node *node); -- cgit v1.2.3-71-gd317 From a7ca12f9d905e7437dd3beb9cbb8e85bc2b991f4 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Tue, 5 Mar 2019 15:49:35 -0800 Subject: mm/workingset: remove unused @mapping argument in workingset_eviction() workingset_eviction() doesn't use and never did use the @mapping argument. Remove it. Link: http://lkml.kernel.org/r/20190228083329.31892-1-aryabinin@virtuozzo.com Signed-off-by: Andrey Ryabinin Acked-by: Johannes Weiner Acked-by: Rik van Riel Acked-by: Vlastimil Babka Acked-by: Mel Gorman Cc: Michal Hocko Cc: William Kucharski Cc: John Hubbard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 2 +- mm/vmscan.c | 2 +- mm/workingset.c | 5 ++--- 3 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 649529be91f2..fc50e21b3b88 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -307,7 +307,7 @@ struct vma_swap_readahead { }; /* linux/mm/workingset.c */ -void *workingset_eviction(struct address_space *mapping, struct page *page); +void *workingset_eviction(struct page *page); void workingset_refault(struct page *page, void *shadow); void workingset_activation(struct page *page); diff --git a/mm/vmscan.c b/mm/vmscan.c index e1f7ccdc0a90..dda6b80d045f 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -952,7 +952,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, */ if (reclaimed && page_is_file_cache(page) && !mapping_exiting(mapping) && !dax_mapping(mapping)) - shadow = workingset_eviction(mapping, page); + shadow = workingset_eviction(page); __delete_from_page_cache(page, shadow); xa_unlock_irqrestore(&mapping->i_pages, flags); diff --git a/mm/workingset.c b/mm/workingset.c index dcb994f2acc2..0bedf67502d5 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -215,13 +215,12 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, /** * workingset_eviction - note the eviction of a page from memory - * @mapping: address space the page was backing * @page: the page being evicted * - * Returns a shadow entry to be stored in @mapping->i_pages in place + * Returns a shadow entry to be stored in @page->mapping->i_pages in place * of the evicted @page so that a later refault can be detected. */ -void *workingset_eviction(struct address_space *mapping, struct page *page) +void *workingset_eviction(struct page *page) { struct pglist_data *pgdat = page_pgdat(page); struct mem_cgroup *memcg = page_memcg(page); -- cgit v1.2.3-71-gd317 From f4b7e272b5c0425915e2115068e0a5a20a3a628e Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Tue, 5 Mar 2019 15:49:39 -0800 Subject: mm: remove zone_lru_lock() function, access ->lru_lock directly We have common pattern to access lru_lock from a page pointer: zone_lru_lock(page_zone(page)) Which is silly, because it unfolds to this: &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)]->zone_pgdat->lru_lock while we can simply do &NODE_DATA(page_to_nid(page))->lru_lock Remove zone_lru_lock() function, since it's only complicate things. Use 'page_pgdat(page)->lru_lock' pattern instead. [aryabinin@virtuozzo.com: a slightly better version of __split_huge_page()] Link: http://lkml.kernel.org/r/20190301121651.7741-1-aryabinin@virtuozzo.com Link: http://lkml.kernel.org/r/20190228083329.31892-2-aryabinin@virtuozzo.com Signed-off-by: Andrey Ryabinin Acked-by: Vlastimil Babka Acked-by: Mel Gorman Cc: Johannes Weiner Cc: Michal Hocko Cc: Rik van Riel Cc: William Kucharski Cc: John Hubbard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroup-v1/memcg_test.txt | 4 ++-- Documentation/cgroup-v1/memory.txt | 4 ++-- include/linux/mm_types.h | 2 +- include/linux/mmzone.h | 4 ---- mm/compaction.c | 15 ++++++++------- mm/filemap.c | 4 ++-- mm/huge_memory.c | 10 +++++----- mm/memcontrol.c | 14 +++++++------- mm/mlock.c | 14 +++++++------- mm/page_idle.c | 8 ++++---- mm/rmap.c | 2 +- mm/swap.c | 16 ++++++++-------- mm/vmscan.c | 16 ++++++++-------- 13 files changed, 55 insertions(+), 58 deletions(-) (limited to 'include/linux') diff --git a/Documentation/cgroup-v1/memcg_test.txt b/Documentation/cgroup-v1/memcg_test.txt index 5c7f310f32bb..621e29ffb358 100644 --- a/Documentation/cgroup-v1/memcg_test.txt +++ b/Documentation/cgroup-v1/memcg_test.txt @@ -107,9 +107,9 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y. 8. LRU Each memcg has its own private LRU. Now, its handling is under global - VM's control (means that it's handled under global zone_lru_lock). + VM's control (means that it's handled under global pgdat->lru_lock). Almost all routines around memcg's LRU is called by global LRU's - list management functions under zone_lru_lock(). + list management functions under pgdat->lru_lock. A special function is mem_cgroup_isolate_pages(). This scans memcg's private LRU and call __isolate_lru_page() to extract a page diff --git a/Documentation/cgroup-v1/memory.txt b/Documentation/cgroup-v1/memory.txt index 3682e99234c2..a347fc9293e5 100644 --- a/Documentation/cgroup-v1/memory.txt +++ b/Documentation/cgroup-v1/memory.txt @@ -267,11 +267,11 @@ When oom event notifier is registered, event will be delivered. Other lock order is following: PG_locked. mm->page_table_lock - zone_lru_lock + pgdat->lru_lock lock_page_cgroup. In many cases, just lock_page_cgroup() is called. per-zone-per-cgroup LRU (cgroup's private LRU) is just guarded by - zone_lru_lock, it has no lock of its own. + pgdat->lru_lock, it has no lock of its own. 2.7 Kernel Memory Extension (CONFIG_MEMCG_KMEM) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 0a36a22228e7..ab9b48420200 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -80,7 +80,7 @@ struct page { struct { /* Page cache and anonymous pages */ /** * @lru: Pageout list, eg. active_list protected by - * zone_lru_lock. Sometimes used as a generic list + * pgdat->lru_lock. Sometimes used as a generic list * by the page owner. */ struct list_head lru; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 6d3290cd1f6f..fba7741533be 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -730,10 +730,6 @@ typedef struct pglist_data { #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid)) -static inline spinlock_t *zone_lru_lock(struct zone *zone) -{ - return &zone->zone_pgdat->lru_lock; -} static inline struct lruvec *node_lruvec(struct pglist_data *pgdat) { diff --git a/mm/compaction.c b/mm/compaction.c index 1cc871da3fda..e054276cf397 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -775,6 +775,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn, isolate_mode_t isolate_mode) { struct zone *zone = cc->zone; + pg_data_t *pgdat = zone->zone_pgdat; unsigned long nr_scanned = 0, nr_isolated = 0; struct lruvec *lruvec; unsigned long flags = 0; @@ -839,8 +840,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, * if contended. */ if (!(low_pfn % SWAP_CLUSTER_MAX) - && compact_unlock_should_abort(zone_lru_lock(zone), flags, - &locked, cc)) + && compact_unlock_should_abort(&pgdat->lru_lock, + flags, &locked, cc)) break; if (!pfn_valid_within(low_pfn)) @@ -910,7 +911,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, if (unlikely(__PageMovable(page)) && !PageIsolated(page)) { if (locked) { - spin_unlock_irqrestore(zone_lru_lock(zone), + spin_unlock_irqrestore(&pgdat->lru_lock, flags); locked = false; } @@ -940,7 +941,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, /* If we already hold the lock, we can skip some rechecking */ if (!locked) { - locked = compact_lock_irqsave(zone_lru_lock(zone), + locked = compact_lock_irqsave(&pgdat->lru_lock, &flags, cc); /* Try get exclusive access under lock */ @@ -965,7 +966,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, } } - lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat); + lruvec = mem_cgroup_page_lruvec(page, pgdat); /* Try isolate the page */ if (__isolate_lru_page(page, isolate_mode) != 0) @@ -1007,7 +1008,7 @@ isolate_fail: */ if (nr_isolated) { if (locked) { - spin_unlock_irqrestore(zone_lru_lock(zone), flags); + spin_unlock_irqrestore(&pgdat->lru_lock, flags); locked = false; } putback_movable_pages(&cc->migratepages); @@ -1034,7 +1035,7 @@ isolate_fail: isolate_abort: if (locked) - spin_unlock_irqrestore(zone_lru_lock(zone), flags); + spin_unlock_irqrestore(&pgdat->lru_lock, flags); /* * Updated the cached scanner pfn once the pageblock has been scanned diff --git a/mm/filemap.c b/mm/filemap.c index a41e01c472f3..a3b4021c448f 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -98,8 +98,8 @@ * ->swap_lock (try_to_unmap_one) * ->private_lock (try_to_unmap_one) * ->i_pages lock (try_to_unmap_one) - * ->zone_lru_lock(zone) (follow_page->mark_page_accessed) - * ->zone_lru_lock(zone) (check_pte_range->isolate_lru_page) + * ->pgdat->lru_lock (follow_page->mark_page_accessed) + * ->pgdat->lru_lock (check_pte_range->isolate_lru_page) * ->private_lock (page_remove_rmap->set_page_dirty) * ->i_pages lock (page_remove_rmap->set_page_dirty) * bdi.wb->list_lock (page_remove_rmap->set_page_dirty) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index d4847026d4b1..fcf657886b4b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2440,11 +2440,11 @@ static void __split_huge_page(struct page *page, struct list_head *list, pgoff_t end, unsigned long flags) { struct page *head = compound_head(page); - struct zone *zone = page_zone(head); + pg_data_t *pgdat = page_pgdat(head); struct lruvec *lruvec; int i; - lruvec = mem_cgroup_page_lruvec(head, zone->zone_pgdat); + lruvec = mem_cgroup_page_lruvec(head, pgdat); /* complete memcg works before add pages to LRU */ mem_cgroup_split_huge_fixup(head); @@ -2475,7 +2475,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, xa_unlock(&head->mapping->i_pages); } - spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags); + spin_unlock_irqrestore(&pgdat->lru_lock, flags); remap_page(head); @@ -2686,7 +2686,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) lru_add_drain(); /* prevent PageLRU to go away from under us, and freeze lru stats */ - spin_lock_irqsave(zone_lru_lock(page_zone(head)), flags); + spin_lock_irqsave(&pgdata->lru_lock, flags); if (mapping) { XA_STATE(xas, &mapping->i_pages, page_index(head)); @@ -2731,7 +2731,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) spin_unlock(&pgdata->split_queue_lock); fail: if (mapping) xa_unlock(&mapping->i_pages); - spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags); + spin_unlock_irqrestore(&pgdata->lru_lock, flags); remap_page(head); ret = -EBUSY; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 45cd1f84268a..7160cfab8107 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2362,13 +2362,13 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) static void lock_page_lru(struct page *page, int *isolated) { - struct zone *zone = page_zone(page); + pg_data_t *pgdat = page_pgdat(page); - spin_lock_irq(zone_lru_lock(zone)); + spin_lock_irq(&pgdat->lru_lock); if (PageLRU(page)) { struct lruvec *lruvec; - lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat); + lruvec = mem_cgroup_page_lruvec(page, pgdat); ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_lru(page)); *isolated = 1; @@ -2378,17 +2378,17 @@ static void lock_page_lru(struct page *page, int *isolated) static void unlock_page_lru(struct page *page, int isolated) { - struct zone *zone = page_zone(page); + pg_data_t *pgdat = page_pgdat(page); if (isolated) { struct lruvec *lruvec; - lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat); + lruvec = mem_cgroup_page_lruvec(page, pgdat); VM_BUG_ON_PAGE(PageLRU(page), page); SetPageLRU(page); add_page_to_lru_list(page, lruvec, page_lru(page)); } - spin_unlock_irq(zone_lru_lock(zone)); + spin_unlock_irq(&pgdat->lru_lock); } static void commit_charge(struct page *page, struct mem_cgroup *memcg, @@ -2674,7 +2674,7 @@ void __memcg_kmem_uncharge(struct page *page, int order) /* * Because tail pages are not marked as "used", set it. We're under - * zone_lru_lock and migration entries setup in all page mappings. + * pgdat->lru_lock and migration entries setup in all page mappings. */ void mem_cgroup_split_huge_fixup(struct page *head) { diff --git a/mm/mlock.c b/mm/mlock.c index 41cc47e28ad6..080f3b36415b 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -182,7 +182,7 @@ static void __munlock_isolation_failed(struct page *page) unsigned int munlock_vma_page(struct page *page) { int nr_pages; - struct zone *zone = page_zone(page); + pg_data_t *pgdat = page_pgdat(page); /* For try_to_munlock() and to serialize with page migration */ BUG_ON(!PageLocked(page)); @@ -194,7 +194,7 @@ unsigned int munlock_vma_page(struct page *page) * might otherwise copy PageMlocked to part of the tail pages before * we clear it in the head page. It also stabilizes hpage_nr_pages(). */ - spin_lock_irq(zone_lru_lock(zone)); + spin_lock_irq(&pgdat->lru_lock); if (!TestClearPageMlocked(page)) { /* Potentially, PTE-mapped THP: do not skip the rest PTEs */ @@ -203,17 +203,17 @@ unsigned int munlock_vma_page(struct page *page) } nr_pages = hpage_nr_pages(page); - __mod_zone_page_state(zone, NR_MLOCK, -nr_pages); + __mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages); if (__munlock_isolate_lru_page(page, true)) { - spin_unlock_irq(zone_lru_lock(zone)); + spin_unlock_irq(&pgdat->lru_lock); __munlock_isolated_page(page); goto out; } __munlock_isolation_failed(page); unlock_out: - spin_unlock_irq(zone_lru_lock(zone)); + spin_unlock_irq(&pgdat->lru_lock); out: return nr_pages - 1; @@ -298,7 +298,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) pagevec_init(&pvec_putback); /* Phase 1: page isolation */ - spin_lock_irq(zone_lru_lock(zone)); + spin_lock_irq(&zone->zone_pgdat->lru_lock); for (i = 0; i < nr; i++) { struct page *page = pvec->pages[i]; @@ -325,7 +325,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) pvec->pages[i] = NULL; } __mod_zone_page_state(zone, NR_MLOCK, delta_munlocked); - spin_unlock_irq(zone_lru_lock(zone)); + spin_unlock_irq(&zone->zone_pgdat->lru_lock); /* Now we can release pins of pages that we are not munlocking */ pagevec_release(&pvec_putback); diff --git a/mm/page_idle.c b/mm/page_idle.c index b9e4b42b33ab..0b39ec0c945c 100644 --- a/mm/page_idle.c +++ b/mm/page_idle.c @@ -31,7 +31,7 @@ static struct page *page_idle_get_page(unsigned long pfn) { struct page *page; - struct zone *zone; + pg_data_t *pgdat; if (!pfn_valid(pfn)) return NULL; @@ -41,13 +41,13 @@ static struct page *page_idle_get_page(unsigned long pfn) !get_page_unless_zero(page)) return NULL; - zone = page_zone(page); - spin_lock_irq(zone_lru_lock(zone)); + pgdat = page_pgdat(page); + spin_lock_irq(&pgdat->lru_lock); if (unlikely(!PageLRU(page))) { put_page(page); page = NULL; } - spin_unlock_irq(zone_lru_lock(zone)); + spin_unlock_irq(&pgdat->lru_lock); return page; } diff --git a/mm/rmap.c b/mm/rmap.c index 0454ecc29537..b30c7c71d1d9 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -27,7 +27,7 @@ * mapping->i_mmap_rwsem * anon_vma->rwsem * mm->page_table_lock or pte_lock - * zone_lru_lock (in mark_page_accessed, isolate_lru_page) + * pgdat->lru_lock (in mark_page_accessed, isolate_lru_page) * swap_lock (in swap_duplicate, swap_info_get) * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in __set_page_dirty_buffers) diff --git a/mm/swap.c b/mm/swap.c index 4d7d37eb3c40..301ed4e04320 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -58,16 +58,16 @@ static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs); static void __page_cache_release(struct page *page) { if (PageLRU(page)) { - struct zone *zone = page_zone(page); + pg_data_t *pgdat = page_pgdat(page); struct lruvec *lruvec; unsigned long flags; - spin_lock_irqsave(zone_lru_lock(zone), flags); - lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat); + spin_lock_irqsave(&pgdat->lru_lock, flags); + lruvec = mem_cgroup_page_lruvec(page, pgdat); VM_BUG_ON_PAGE(!PageLRU(page), page); __ClearPageLRU(page); del_page_from_lru_list(page, lruvec, page_off_lru(page)); - spin_unlock_irqrestore(zone_lru_lock(zone), flags); + spin_unlock_irqrestore(&pgdat->lru_lock, flags); } __ClearPageWaiters(page); mem_cgroup_uncharge(page); @@ -322,12 +322,12 @@ static inline void activate_page_drain(int cpu) void activate_page(struct page *page) { - struct zone *zone = page_zone(page); + pg_data_t *pgdat = page_pgdat(page); page = compound_head(page); - spin_lock_irq(zone_lru_lock(zone)); - __activate_page(page, mem_cgroup_page_lruvec(page, zone->zone_pgdat), NULL); - spin_unlock_irq(zone_lru_lock(zone)); + spin_lock_irq(&pgdat->lru_lock); + __activate_page(page, mem_cgroup_page_lruvec(page, pgdat), NULL); + spin_unlock_irq(&pgdat->lru_lock); } #endif diff --git a/mm/vmscan.c b/mm/vmscan.c index dda6b80d045f..a5ad0b35ab8e 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1614,8 +1614,8 @@ static __always_inline void update_lru_sizes(struct lruvec *lruvec, } -/* - * zone_lru_lock is heavily contended. Some of the functions that +/** + * pgdat->lru_lock is heavily contended. Some of the functions that * shrink the lists perform better by taking out a batch of pages * and working on them outside the LRU lock. * @@ -1750,11 +1750,11 @@ int isolate_lru_page(struct page *page) WARN_RATELIMIT(PageTail(page), "trying to isolate tail page"); if (PageLRU(page)) { - struct zone *zone = page_zone(page); + pg_data_t *pgdat = page_pgdat(page); struct lruvec *lruvec; - spin_lock_irq(zone_lru_lock(zone)); - lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat); + spin_lock_irq(&pgdat->lru_lock); + lruvec = mem_cgroup_page_lruvec(page, pgdat); if (PageLRU(page)) { int lru = page_lru(page); get_page(page); @@ -1762,7 +1762,7 @@ int isolate_lru_page(struct page *page) del_page_from_lru_list(page, lruvec, lru); ret = 0; } - spin_unlock_irq(zone_lru_lock(zone)); + spin_unlock_irq(&pgdat->lru_lock); } return ret; } @@ -1990,9 +1990,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, * processes, from rmap. * * If the pages are mostly unmapped, the processing is fast and it is - * appropriate to hold zone_lru_lock across the whole operation. But if + * appropriate to hold pgdat->lru_lock across the whole operation. But if * the pages are mapped, the processing is slow (page_referenced()) so we - * should drop zone_lru_lock around each page. It's impossible to balance + * should drop pgdat->lru_lock around each page. It's impossible to balance * this, so instead we remove the pages from the LRU while processing them. * It is safe to rely on PG_active against the non-LRU pages in here because * nobody will play with that bit on a non-LRU page. -- cgit v1.2.3-71-gd317 From a9519defc771d574888ffe01e84747889152ec35 Mon Sep 17 00:00:00 2001 From: Greg Thelen Date: Tue, 5 Mar 2019 15:50:03 -0800 Subject: writeback: fix inode cgroup switching comment Commit 682aa8e1a6a1 ("writeback: implement unlocked_inode_to_wb transaction and use it for stat updates") refers to inode_switch_wb_work_fn() which never got merged. Switch the comments to inode_switch_wbs_work_fn(). Link: http://lkml.kernel.org/r/20190305004617.142590-1-gthelen@google.com Fixes: 682aa8e1a6a1 ("writeback: implement unlocked_inode_to_wb transaction and use it for stat updates") Signed-off-by: Greg Thelen Reviewed-by: Andrew Morton Acked-by: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev.h | 2 +- include/linux/fs.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index c28a47cbe355..f9b029180241 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -365,7 +365,7 @@ unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) rcu_read_lock(); /* - * Paired with store_release in inode_switch_wb_work_fn() and + * Paired with store_release in inode_switch_wbs_work_fn() and * ensures that we see the new wb if we see cleared I_WB_SWITCH. */ cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH; diff --git a/include/linux/fs.h b/include/linux/fs.h index fd423fec8d83..08f26046233e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2091,7 +2091,7 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to * synchronize competing switching instances and to tell * wb stat updates to grab the i_pages lock. See - * inode_switch_wb_work_fn() for details. + * inode_switch_wbs_work_fn() for details. * * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper * and work dirs among overlayfs mounts. -- cgit v1.2.3-71-gd317