diff mbox series

[4/6] mm: don't remap unused subpages when splitting isolated thp

Message ID 20240730125346.1580150-5-usamaarif642@gmail.com (mailing list archive)
State New
Headers show
Series mm: split underutilized THPs | expand

Commit Message

Usama Arif July 30, 2024, 12:46 p.m. UTC 
From: Yu Zhao <yuzhao@google.com>

Here being unused means containing only zeros and inaccessible to
userspace. When splitting an isolated thp under reclaim or migration,
there is no need to remap its unused subpages because they can be
faulted in anew. Not remapping them avoids writeback or copying during
reclaim or migration. This is particularly helpful when the internal
fragmentation of a thp is high, i.e., it has many untouched subpages.

This is also a prerequisite for THP low utilization shrinker which will
be introduced in later patches, where underutilized THPs are split, and
the zero-filled split pages are freed saving memory.

Signed-off-by: Yu Zhao <yuzhao@google.com>
Tested-by: Shuang Zhai <zhais@google.com>
Signed-off-by: Usama Arif <usamaarif642@gmail.com>
---
 include/linux/rmap.h |  2 +-
 mm/huge_memory.c     |  8 ++---
 mm/migrate.c         | 73 +++++++++++++++++++++++++++++++++++++++-----
 mm/migrate_device.c  |  4 +--
 4 files changed, 72 insertions(+), 15 deletions(-)

Comments

Rik van Riel July 30, 2024, 6:07 p.m. UTC | #1 
On Tue, 2024-07-30 at 13:46 +0100, Usama Arif wrote:
> 
> +	/*
> +	 * The pmd entry mapping the old thp was flushed and the pte
> mapping
> +	 * this subpage has been non present. Therefore, this
> subpage is
> +	 * inaccessible. We don't need to remap it if it contains
> only zeros.
> +	 */
> +	addr = kmap_local_page(page);
> +	dirty = memchr_inv(addr, 0, PAGE_SIZE);
> +	kunmap_local(addr);
> +
> +	if (dirty)
> +		return false;
> 

A minor nitpick here. The word dirty has a few different meanings
in memory management already.

Could it be clearer to use something like "contains_data" ?
Usama Arif July 31, 2024, 5:08 p.m. UTC | #2 
On 30/07/2024 19:07, Rik van Riel wrote:
> On Tue, 2024-07-30 at 13:46 +0100, Usama Arif wrote:
>>
>> +	/*
>> +	 * The pmd entry mapping the old thp was flushed and the pte
>> mapping
>> +	 * this subpage has been non present. Therefore, this
>> subpage is
>> +	 * inaccessible. We don't need to remap it if it contains
>> only zeros.
>> +	 */
>> +	addr = kmap_local_page(page);
>> +	dirty = memchr_inv(addr, 0, PAGE_SIZE);
>> +	kunmap_local(addr);
>> +
>> +	if (dirty)
>> +		return false;
>>
> 
> A minor nitpick here. The word dirty has a few different meanings
> in memory management already.
> 
> Could it be clearer to use something like "contains_data" ?
> 

Thanks, yes makes much more sense, will use contains_data in the next revision.
diff mbox series

Patch

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 0978c64f49d8..805ab09057ed 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -745,7 +745,7 @@  int folio_mkclean(struct folio *);
 int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff,
 		      struct vm_area_struct *vma);
 
-void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked);
+void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked, bool unmap_unused);
 
 /*
  * rmap_walk_control: To control rmap traversing for specific needs
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 76a3b6a2b796..892467d85f3a 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2775,7 +2775,7 @@  bool unmap_huge_pmd_locked(struct vm_area_struct *vma, unsigned long addr,
 	return false;
 }
 
-static void remap_page(struct folio *folio, unsigned long nr)
+static void remap_page(struct folio *folio, unsigned long nr, bool unmap_unused)
 {
 	int i = 0;
 
@@ -2783,7 +2783,7 @@  static void remap_page(struct folio *folio, unsigned long nr)
 	if (!folio_test_anon(folio))
 		return;
 	for (;;) {
-		remove_migration_ptes(folio, folio, true);
+		remove_migration_ptes(folio, folio, true, unmap_unused);
 		i += folio_nr_pages(folio);
 		if (i >= nr)
 			break;
@@ -2993,7 +2993,7 @@  static void __split_huge_page(struct page *page, struct list_head *list,
 
 	if (nr_dropped)
 		shmem_uncharge(folio->mapping->host, nr_dropped);
-	remap_page(folio, nr);
+	remap_page(folio, nr, PageAnon(head));
 
 	/*
 	 * set page to its compound_head when split to non order-0 pages, so
@@ -3286,7 +3286,7 @@  int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
 		if (mapping)
 			xas_unlock(&xas);
 		local_irq_enable();
-		remap_page(folio, folio_nr_pages(folio));
+		remap_page(folio, folio_nr_pages(folio), false);
 		ret = -EAGAIN;
 	}
 
diff --git a/mm/migrate.c b/mm/migrate.c
index b273bac0d5ae..f4f06bdded70 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -177,13 +177,61 @@  void putback_movable_pages(struct list_head *l)
 	}
 }
 
+static bool try_to_unmap_unused(struct page_vma_mapped_walk *pvmw,
+			       struct folio *folio,
+			       unsigned long idx)
+{
+	struct page *page = folio_page(folio, idx);
+	void *addr;
+	bool dirty;
+	pte_t newpte;
+
+	VM_BUG_ON_PAGE(PageCompound(page), page);
+	VM_BUG_ON_PAGE(!PageAnon(page), page);
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
+	VM_BUG_ON_PAGE(pte_present(*pvmw->pte), page);
+
+	if (PageMlocked(page) || (pvmw->vma->vm_flags & VM_LOCKED))
+		return false;
+
+	/*
+	 * The pmd entry mapping the old thp was flushed and the pte mapping
+	 * this subpage has been non present. Therefore, this subpage is
+	 * inaccessible. We don't need to remap it if it contains only zeros.
+	 */
+	addr = kmap_local_page(page);
+	dirty = memchr_inv(addr, 0, PAGE_SIZE);
+	kunmap_local(addr);
+
+	if (dirty)
+		return false;
+
+	pte_clear_not_present_full(pvmw->vma->vm_mm, pvmw->address, pvmw->pte, false);
+
+	if (userfaultfd_armed(pvmw->vma)) {
+		newpte = pte_mkspecial(pfn_pte(page_to_pfn(ZERO_PAGE(pvmw->address)),
+					       pvmw->vma->vm_page_prot));
+		ptep_clear_flush(pvmw->vma, pvmw->address, pvmw->pte);
+		set_pte_at(pvmw->vma->vm_mm, pvmw->address, pvmw->pte, newpte);
+	}
+
+	dec_mm_counter(pvmw->vma->vm_mm, mm_counter(folio));
+	return true;
+}
+
+struct rmap_walk_arg {
+	struct folio *folio;
+	bool unmap_unused;
+};
+
 /*
  * Restore a potential migration pte to a working pte entry
  */
 static bool remove_migration_pte(struct folio *folio,
-		struct vm_area_struct *vma, unsigned long addr, void *old)
+		struct vm_area_struct *vma, unsigned long addr, void *arg)
 {
-	DEFINE_FOLIO_VMA_WALK(pvmw, old, vma, addr, PVMW_SYNC | PVMW_MIGRATION);
+	struct rmap_walk_arg *rmap_walk_arg = arg;
+	DEFINE_FOLIO_VMA_WALK(pvmw, rmap_walk_arg->folio, vma, addr, PVMW_SYNC | PVMW_MIGRATION);
 
 	while (page_vma_mapped_walk(&pvmw)) {
 		rmap_t rmap_flags = RMAP_NONE;
@@ -207,6 +255,8 @@  static bool remove_migration_pte(struct folio *folio,
 			continue;
 		}
 #endif
+		if (rmap_walk_arg->unmap_unused && try_to_unmap_unused(&pvmw, folio, idx))
+			continue;
 
 		folio_get(folio);
 		pte = mk_pte(new, READ_ONCE(vma->vm_page_prot));
@@ -285,13 +335,20 @@  static bool remove_migration_pte(struct folio *folio,
  * Get rid of all migration entries and replace them by
  * references to the indicated page.
  */
-void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked)
+void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked, bool unmap_unused)
 {
+	struct rmap_walk_arg rmap_walk_arg = {
+		.folio = src,
+		.unmap_unused = unmap_unused,
+	};
+
 	struct rmap_walk_control rwc = {
 		.rmap_one = remove_migration_pte,
-		.arg = src,
+		.arg = &rmap_walk_arg,
 	};
 
+	VM_BUG_ON_FOLIO(unmap_unused && src != dst, src);
+
 	if (locked)
 		rmap_walk_locked(dst, &rwc);
 	else
@@ -904,7 +961,7 @@  static int writeout(struct address_space *mapping, struct folio *folio)
 	 * At this point we know that the migration attempt cannot
 	 * be successful.
 	 */
-	remove_migration_ptes(folio, folio, false);
+	remove_migration_ptes(folio, folio, false, false);
 
 	rc = mapping->a_ops->writepage(&folio->page, &wbc);
 
@@ -1068,7 +1125,7 @@  static void migrate_folio_undo_src(struct folio *src,
 				   struct list_head *ret)
 {
 	if (page_was_mapped)
-		remove_migration_ptes(src, src, false);
+		remove_migration_ptes(src, src, false, false);
 	/* Drop an anon_vma reference if we took one */
 	if (anon_vma)
 		put_anon_vma(anon_vma);
@@ -1306,7 +1363,7 @@  static int migrate_folio_move(free_folio_t put_new_folio, unsigned long private,
 		lru_add_drain();
 
 	if (old_page_state & PAGE_WAS_MAPPED)
-		remove_migration_ptes(src, dst, false);
+		remove_migration_ptes(src, dst, false, false);
 
 out_unlock_both:
 	folio_unlock(dst);
@@ -1444,7 +1501,7 @@  static int unmap_and_move_huge_page(new_folio_t get_new_folio,
 
 	if (page_was_mapped)
 		remove_migration_ptes(src,
-			rc == MIGRATEPAGE_SUCCESS ? dst : src, false);
+			rc == MIGRATEPAGE_SUCCESS ? dst : src, false, false);
 
 unlock_put_anon:
 	folio_unlock(dst);
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index 6d66dc1c6ffa..a1630d8e0d95 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -424,7 +424,7 @@  static unsigned long migrate_device_unmap(unsigned long *src_pfns,
 			continue;
 
 		folio = page_folio(page);
-		remove_migration_ptes(folio, folio, false);
+		remove_migration_ptes(folio, folio, false, false);
 
 		src_pfns[i] = 0;
 		folio_unlock(folio);
@@ -837,7 +837,7 @@  void migrate_device_finalize(unsigned long *src_pfns,
 
 		src = page_folio(page);
 		dst = page_folio(newpage);
-		remove_migration_ptes(src, dst, false);
+		remove_migration_ptes(src, dst, false, false);
 		folio_unlock(src);
 
 		if (is_zone_device_page(page))