@@ -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);
@@ -285,6 +285,9 @@ static inline int migrate_vma(const struct migrate_vma_ops *ops,
}
#endif /* IS_ENABLED(CONFIG_MIGRATE_VMA_HELPER) */
+extern int get_user_pages_cma_migrate(unsigned long start, int nr_pages, int write,
+ struct page **pages);
+
#endif /* CONFIG_MIGRATION */
#endif /* _LINUX_MIGRATE_H */
@@ -1586,8 +1586,8 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask,
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;
@@ -2982,3 +2982,152 @@ int migrate_vma(const struct migrate_vma_ops *ops,
}
EXPORT_SYMBOL(migrate_vma);
#endif /* defined(MIGRATE_VMA_HELPER) */
+
+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);
+}
+
+/**
+ * get_user_pages_cma_migrate() - pin user pages in memory by migrating pages in CMA region
+ * @start: starting user address
+ * @nr_pages: number of pages from start to pin
+ * @write: whether pages will be written to
+ * @pages: array that receives pointers to the pages pinned.
+ * Should be at least nr_pages long.
+ *
+ * Attempt to pin user pages in memory without taking mm->mmap_sem.
+ * If not successful, it will fall back to taking the lock and
+ * calling get_user_pages().
+ *
+ * If the pinned pages are backed by CMA region, we migrate those pages out,
+ * allocating new pages from non-CMA region. This helps in avoiding keeping
+ * pages pinned in the CMA region for a long time thereby resulting in
+ * CMA allocation failures.
+ *
+ * Returns number of pages pinned. This may be fewer than the number
+ * requested. If nr_pages is 0 or negative, returns 0. If no pages
+ * were pinned, returns -errno.
+ */
+
+int get_user_pages_cma_migrate(unsigned long start, int nr_pages, int write,
+ struct page **pages)
+{
+ int i, ret;
+ unsigned long flags;
+ bool drain_allow = true;
+ bool migrate_allow = true;
+ LIST_HEAD(cma_page_list);
+
+get_user_again:
+ /*
+ * If get_user_pages ends up allocating pages, make sure we don't
+ * allocate from CMA region so that we can avoid the migration below.
+ */
+ flags = memalloc_nocma_save();
+ ret = get_user_pages_fast(start, nr_pages, write, pages);
+ memalloc_nocma_restore(flags);
+ if (ret <= 0)
+ return ret;
+
+ for (i = 0; i < ret; ++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]) && migrate_allow) {
+
+ 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 < ret; ++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.
+ */
+ drain_allow = true;
+ goto get_user_again;
+ }
+ return ret;
+}
This helper does a get_user_pages_fast making sure we migrate pages found in the CMA area before taking page reference. 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 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 VFIO passthrough device. VFIO locks all the guests memory and if the guest memory is backed by CMA region, it becomes unmovable resulting in fragmenting the CMA and possibly preventing other guest from allocation a large enough hash page table. NOTE: We allocate new page without using __GFP_THISNODE Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> --- include/linux/hugetlb.h | 2 + include/linux/migrate.h | 3 + mm/hugetlb.c | 4 +- mm/migrate.c | 149 ++++++++++++++++++++++++++++++++++++++++ 4 files changed, 156 insertions(+), 2 deletions(-)