mm: factor out common parts between MADV_COLD and MADV_PAGEOUT

There are many common parts between MADV_COLD and MADV_PAGEOUT.
This patch factor them out to save code duplication.

Link: http://lkml.kernel.org/r/20190726023435.214162-6-minchan@kernel.orgSigned-off-by: Minchan Kim <minchan@kernel.org>
Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Daniel Colascione <dancol@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Hillf Danton <hdanton@sina.com>
Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com>
Cc: Joel Fernandes (Google) <joel@joelfernandes.org>
Cc: kbuild test robot <lkp@intel.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Oleksandr Natalenko <oleksandr@redhat.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Sonny Rao <sonnyrao@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Tim Murray <timmurray@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/madvise.c

@@ -32,6 +32,11 @@
 
 #include "internal.h"
 
+struct madvise_walk_private {
+	struct mmu_gather *tlb;
+	bool pageout;
+};
+
 /*
  * Any behaviour which results in changes to the vma->vm_flags needs to
  * take mmap_sem for writing. Others, which simply traverse vmas, need
@@ -292,15 +297,22 @@ static long madvise_willneed(struct vm_area_struct *vma,
 	return 0;
 }
 
-static int madvise_cold_pte_range(pmd_t *pmd, unsigned long addr,
-				unsigned long end, struct mm_walk *walk)
+static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
+				unsigned long addr, unsigned long end,
+				struct mm_walk *walk)
 {
-	struct mmu_gather *tlb = walk->private;
+	struct madvise_walk_private *private = walk->private;
+	struct mmu_gather *tlb = private->tlb;
+	bool pageout = private->pageout;
 	struct mm_struct *mm = tlb->mm;
 	struct vm_area_struct *vma = walk->vma;
 	pte_t *orig_pte, *pte, ptent;
 	spinlock_t *ptl;
-	struct page *page;
+	struct page *page = NULL;
+	LIST_HEAD(page_list);
+
+	if (fatal_signal_pending(current))
+		return -EINTR;
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	if (pmd_trans_huge(*pmd)) {
@@ -348,10 +360,17 @@ static int madvise_cold_pte_range(pmd_t *pmd, unsigned long addr,
 			tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
 		}
 
+		ClearPageReferenced(page);
 		test_and_clear_page_young(page);
-		deactivate_page(page);
+		if (pageout) {
+			if (!isolate_lru_page(page))
+				list_add(&page->lru, &page_list);
+		} else
+			deactivate_page(page);
 huge_unlock:
 		spin_unlock(ptl);
+		if (pageout)
+			reclaim_pages(&page_list);
 		return 0;
 	}
 
@@ -419,27 +438,39 @@ static int madvise_cold_pte_range(pmd_t *pmd, unsigned long addr,
 		 * As a side effect, it makes confuse idle-page tracking
 		 * because they will miss recent referenced history.
 		 */
+		ClearPageReferenced(page);
 		test_and_clear_page_young(page);
-		deactivate_page(page);
+		if (pageout) {
+			if (!isolate_lru_page(page))
+				list_add(&page->lru, &page_list);
+		} else
+			deactivate_page(page);
 	}
 
 	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(orig_pte, ptl);
+	if (pageout)
+		reclaim_pages(&page_list);
 	cond_resched();
 
 	return 0;
 }
 
 static const struct mm_walk_ops cold_walk_ops = {
-	.pmd_entry = madvise_cold_pte_range,
+	.pmd_entry = madvise_cold_or_pageout_pte_range,
 };
 
 static void madvise_cold_page_range(struct mmu_gather *tlb,
 			     struct vm_area_struct *vma,
 			     unsigned long addr, unsigned long end)
 {
+	struct madvise_walk_private walk_private = {
+		.pageout = false,
+		.tlb = tlb,
+	};
+
 	tlb_start_vma(tlb, vma);
-	walk_page_range(vma->vm_mm, addr, end, &cold_walk_ops, NULL);
+	walk_page_range(vma->vm_mm, addr, end, &cold_walk_ops, &walk_private);
 	tlb_end_vma(tlb, vma);
 }
 
@@ -462,150 +493,17 @@ static long madvise_cold(struct vm_area_struct *vma,
 	return 0;
 }
 
-static int madvise_pageout_pte_range(pmd_t *pmd, unsigned long addr,
-				unsigned long end, struct mm_walk *walk)
-{
-	struct mmu_gather *tlb = walk->private;
-	struct mm_struct *mm = tlb->mm;
-	struct vm_area_struct *vma = walk->vma;
-	pte_t *orig_pte, *pte, ptent;
-	spinlock_t *ptl;
-	LIST_HEAD(page_list);
-	struct page *page;
-
-	if (fatal_signal_pending(current))
-		return -EINTR;
-
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	if (pmd_trans_huge(*pmd)) {
-		pmd_t orig_pmd;
-		unsigned long next = pmd_addr_end(addr, end);
-
-		tlb_change_page_size(tlb, HPAGE_PMD_SIZE);
-		ptl = pmd_trans_huge_lock(pmd, vma);
-		if (!ptl)
-			return 0;
-
-		orig_pmd = *pmd;
-		if (is_huge_zero_pmd(orig_pmd))
-			goto huge_unlock;
-
-		if (unlikely(!pmd_present(orig_pmd))) {
-			VM_BUG_ON(thp_migration_supported() &&
-					!is_pmd_migration_entry(orig_pmd));
-			goto huge_unlock;
-		}
-
-		page = pmd_page(orig_pmd);
-		if (next - addr != HPAGE_PMD_SIZE) {
-			int err;
-
-			if (page_mapcount(page) != 1)
-				goto huge_unlock;
-			get_page(page);
-			spin_unlock(ptl);
-			lock_page(page);
-			err = split_huge_page(page);
-			unlock_page(page);
-			put_page(page);
-			if (!err)
-				goto regular_page;
-			return 0;
-		}
-
-		if (pmd_young(orig_pmd)) {
-			pmdp_invalidate(vma, addr, pmd);
-			orig_pmd = pmd_mkold(orig_pmd);
-
-			set_pmd_at(mm, addr, pmd, orig_pmd);
-			tlb_remove_tlb_entry(tlb, pmd, addr);
-		}
-
-		ClearPageReferenced(page);
-		test_and_clear_page_young(page);
-
-		if (!isolate_lru_page(page))
-			list_add(&page->lru, &page_list);
-huge_unlock:
-		spin_unlock(ptl);
-		reclaim_pages(&page_list);
-		return 0;
-	}
-
-	if (pmd_trans_unstable(pmd))
-		return 0;
-regular_page:
-#endif
-	tlb_change_page_size(tlb, PAGE_SIZE);
-	orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
-	flush_tlb_batched_pending(mm);
-	arch_enter_lazy_mmu_mode();
-	for (; addr < end; pte++, addr += PAGE_SIZE) {
-		ptent = *pte;
-		if (!pte_present(ptent))
-			continue;
-
-		page = vm_normal_page(vma, addr, ptent);
-		if (!page)
-			continue;
-
-		/*
-		 * creating a THP page is expensive so split it only if we
-		 * are sure it's worth. Split it if we are only owner.
-		 */
-		if (PageTransCompound(page)) {
-			if (page_mapcount(page) != 1)
-				break;
-			get_page(page);
-			if (!trylock_page(page)) {
-				put_page(page);
-				break;
-			}
-			pte_unmap_unlock(orig_pte, ptl);
-			if (split_huge_page(page)) {
-				unlock_page(page);
-				put_page(page);
-				pte_offset_map_lock(mm, pmd, addr, &ptl);
-				break;
-			}
-			unlock_page(page);
-			put_page(page);
-			pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
-			pte--;
-			addr -= PAGE_SIZE;
-			continue;
-		}
-
-		VM_BUG_ON_PAGE(PageTransCompound(page), page);
-
-		if (pte_young(ptent)) {
-			ptent = ptep_get_and_clear_full(mm, addr, pte,
-							tlb->fullmm);
-			ptent = pte_mkold(ptent);
-			set_pte_at(mm, addr, pte, ptent);
-			tlb_remove_tlb_entry(tlb, pte, addr);
-		}
-		ClearPageReferenced(page);
-		test_and_clear_page_young(page);
-
-		if (!isolate_lru_page(page))
-			list_add(&page->lru, &page_list);
-	}
-
-	arch_leave_lazy_mmu_mode();
-	pte_unmap_unlock(orig_pte, ptl);
-	reclaim_pages(&page_list);
-	cond_resched();
-
-	return 0;
-}
-
 static void madvise_pageout_page_range(struct mmu_gather *tlb,
 			     struct vm_area_struct *vma,
 			     unsigned long addr, unsigned long end)
 {
+	struct madvise_walk_private walk_private = {
+		.pageout = true,
+		.tlb = tlb,
+	};
+
 	tlb_start_vma(tlb, vma);
-	walk_page_range(vma->vm_mm, addr, end, &cold_walk_ops, NULL);
+	walk_page_range(vma->vm_mm, addr, end, &cold_walk_ops, &walk_private);
 	tlb_end_vma(tlb, vma);
 }