[v3,5/6] mm/gup: migrate pinned pages out of movable zone

Message ID	20201211202140.396852-6-pasha.tatashin@soleen.com (mailing list archive)
State	New, archived
Headers	show Return-Path: <SRS0=fS8n=FP=kvack.org=owner-linux-mm@kernel.org> DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org A508923F38 From: Pavel Tatashin <pasha.tatashin@soleen.com> To: pasha.tatashin@soleen.com, linux-kernel@vger.kernel.org, linux-mm@kvack.org, akpm@linux-foundation.org, vbabka@suse.cz, mhocko@suse.com, david@redhat.com, osalvador@suse.de, dan.j.williams@intel.com, sashal@kernel.org, tyhicks@linux.microsoft.com, iamjoonsoo.kim@lge.com, mike.kravetz@oracle.com, rostedt@goodmis.org, mingo@redhat.com, jgg@ziepe.ca, peterz@infradead.org, mgorman@suse.de, willy@infradead.org, rientjes@google.com, jhubbard@nvidia.com, linux-doc@vger.kernel.org Subject: [PATCH v3 5/6] mm/gup: migrate pinned pages out of movable zone Date: Fri, 11 Dec 2020 15:21:39 -0500 Message-Id: <20201211202140.396852-6-pasha.tatashin@soleen.com> In-Reply-To: <20201211202140.396852-1-pasha.tatashin@soleen.com> References: <20201211202140.396852-1-pasha.tatashin@soleen.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Sender: owner-linux-mm@kvack.org Precedence: bulk
Series	prohibit pinning pages in ZONE_MOVABLE \| expand [v3,0/6] prohibit pinning pages in ZONE_MOVABLE [v3,1/6] mm/gup: don't pin migrated cma pages in movable zone [v3,2/6] mm cma: rename PF_MEMALLOC_NOCMA to PF_MEMALLOC_PIN [v3,3/6] mm: apply per-task gfp constraints in fast path [v3,4/6] mm: honor PF_MEMALLOC_PIN for all movable pages [v3,5/6] mm/gup: migrate pinned pages out of movable zone [v3,6/6] memory-hotplug.rst: add a note about ZONE_MOVABLE and page pinning

diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 4594838a0f7c..aae5ef0b3ba1 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -27,6 +27,7 @@ enum migrate_reason { MR_MEMPOLICY_MBIND, MR_NUMA_MISPLACED, MR_CONTIG_RANGE, + MR_LONGTERM_PIN, MR_TYPES }; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b593316bff3d..25c0c13ba4b1 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -386,9 +386,14 @@ enum zone_type { * likely to succeed, and to locally limit unmovable allocations - e.g., * to increase the number of THP/huge pages. Notable special cases are: * - * 1. Pinned pages: (long-term) pinning of movable pages might - * essentially turn such pages unmovable. Memory offlining might - * retry a long time. + * 1. Pinned pages: (long-term) pinning of movable pages is avoided + * when pages are pinned and faulted, but it is still possible that + * address space already has pages in ZONE_MOVABLE at the time when + * pages are pinned (i.e. user has touches that memory before + * pinning). In such case we try to migrate them to a different zone, + * but if migration fails the pages can still end-up pinned in + * ZONE_MOVABLE. In such case, memory offlining might retry a long + * time and will only succeed once user application unpins pages. * 2. memblock allocations: kernelcore/movablecore setups might create * situations where ZONE_MOVABLE contains unmovable allocations * after boot. Memory offlining and allocations fail early. diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h index 4d434398d64d..363b54ce104c 100644 --- a/include/trace/events/migrate.h +++ b/include/trace/events/migrate.h @@ -20,7 +20,8 @@ EM( MR_SYSCALL, "syscall_or_cpuset") \ EM( MR_MEMPOLICY_MBIND, "mempolicy_mbind") \ EM( MR_NUMA_MISPLACED, "numa_misplaced") \ - EMe(MR_CONTIG_RANGE, "contig_range") + EM( MR_CONTIG_RANGE, "contig_range") \ + EMe(MR_LONGTERM_PIN, "longterm_pin") /* * First define the enums in the above macros to be exported to userspace diff --git a/mm/gup.c b/mm/gup.c index 007060e66a48..d5e9c459952e 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -89,11 +89,12 @@ static __maybe_unused struct page *try_grab_compound_head(struct page *page, int orig_refs = refs; /* - * Can't do FOLL_LONGTERM + FOLL_PIN with CMA in the gup fast - * path, so fail and let the caller fall back to the slow path. + * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a + * right zone, so fail and let the caller fall back to the slow + * path. */ - if (unlikely(flags & FOLL_LONGTERM) && - is_migrate_cma_page(page)) + if (unlikely((flags & FOLL_LONGTERM) && + !is_pinnable_page(page))) return NULL; /* @@ -1549,19 +1550,18 @@ struct page *get_dump_page(unsigned long addr) } #endif /* CONFIG_ELF_CORE */ -#ifdef CONFIG_CMA -static long check_and_migrate_cma_pages(struct mm_struct *mm, - unsigned long start, - unsigned long nr_pages, - struct page **pages, - struct vm_area_struct **vmas, - unsigned int gup_flags) +static long check_and_migrate_movable_pages(struct mm_struct *mm, + unsigned long start, + unsigned long nr_pages, + struct page **pages, + struct vm_area_struct **vmas, + unsigned int gup_flags) { unsigned long i; unsigned long step; bool drain_allow = true; bool migrate_allow = true; - LIST_HEAD(cma_page_list); + LIST_HEAD(movable_page_list); long ret = nr_pages; struct migration_target_control mtc = { .nid = NUMA_NO_NODE, @@ -1579,13 +1579,12 @@ static long check_and_migrate_cma_pages(struct mm_struct *mm, */ step = compound_nr(head) - (pages[i] - head); /* - * 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 we get a movable page, since we are going to be pinning + * these entries, try to move them out if possible. */ - if (is_migrate_cma_page(head)) { + if (!is_pinnable_page(head)) { if (PageHuge(head)) - isolate_huge_page(head, &cma_page_list); + isolate_huge_page(head, &movable_page_list); else { if (!PageLRU(head) && drain_allow) { lru_add_drain_all(); @@ -1593,7 +1592,7 @@ static long check_and_migrate_cma_pages(struct mm_struct *mm, } if (!isolate_lru_page(head)) { - list_add_tail(&head->lru, &cma_page_list); + list_add_tail(&head->lru, &movable_page_list); mod_node_page_state(page_pgdat(head), NR_ISOLATED_ANON + page_is_file_lru(head), @@ -1605,7 +1604,7 @@ static long check_and_migrate_cma_pages(struct mm_struct *mm, i += step; } - if (!list_empty(&cma_page_list)) { + if (!list_empty(&movable_page_list)) { /* * drop the above get_user_pages reference. */ @@ -1615,7 +1614,7 @@ static long check_and_migrate_cma_pages(struct mm_struct *mm, for (i = 0; i < nr_pages; i++) put_page(pages[i]); - if (migrate_pages(&cma_page_list, alloc_migration_target, NULL, + if (migrate_pages(&movable_page_list, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_CONTIG_RANGE)) { /* * some of the pages failed migration. Do get_user_pages @@ -1623,17 +1622,16 @@ static long check_and_migrate_cma_pages(struct mm_struct *mm, */ migrate_allow = false; - if (!list_empty(&cma_page_list)) - putback_movable_pages(&cma_page_list); + if (!list_empty(&movable_page_list)) + putback_movable_pages(&movable_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. + * again migrating any pages which we failed to isolate earlier. */ ret = __get_user_pages_locked(mm, start, nr_pages, - pages, vmas, NULL, - gup_flags); + pages, vmas, NULL, + gup_flags); if ((ret > 0) && migrate_allow) { nr_pages = ret; @@ -1644,17 +1642,6 @@ static long check_and_migrate_cma_pages(struct mm_struct *mm, return ret; } -#else -static long check_and_migrate_cma_pages(struct mm_struct *mm, - unsigned long start, - unsigned long nr_pages, - struct page **pages, - struct vm_area_struct **vmas, - unsigned int gup_flags) -{ - return nr_pages; -} -#endif /* CONFIG_CMA */ /* * __gup_longterm_locked() is a wrapper for __get_user_pages_locked which @@ -1678,8 +1665,9 @@ static long __gup_longterm_locked(struct mm_struct *mm, if (gup_flags & FOLL_LONGTERM) { if (rc > 0) - rc = check_and_migrate_cma_pages(mm, start, rc, pages, - vmas, gup_flags); + rc = check_and_migrate_movable_pages(mm, start, rc, + pages, vmas, + gup_flags); memalloc_pin_restore(flags); } return rc;

[v3,5/6] mm/gup: migrate pinned pages out of movable zone

Commit Message

Comments

Patch