[PATCH v3] mm: readahead: make thp readahead conditional to mmap_miss logic

[Roman Gushchin <roman.gushchin@linux.dev>]

Commit 4687fdbb805a ("mm/filemap: Support VM_HUGEPAGE for file mappings")
introduced a special handling for VM_HUGEPAGE mappings: even if the
readahead is disabled, 1 or 2 HPAGE_PMD_ORDER pages are
allocated.

This change causes a significant regression for containers with a
tight memory.max limit, if VM_HUGEPAGE is widely used. Prior to this
commit, mmap_miss logic would eventually lead to the readahead
disablement, effectively reducing the memory pressure in the
cgroup. With this change the kernel is trying to allocate 1-2 huge
pages for each fault, no matter if these pages are used or not
before being evicted, increasing the memory pressure multi-fold.

To fix the regression, let's make the new VM_HUGEPAGE conditional
to the mmap_miss check, but keep independent from the ra->ra_pages.
This way the main intention of commit 4687fdbb805a ("mm/filemap:
Support VM_HUGEPAGE for file mappings") stays intact, but the
regression is resolved.

The logic behind this changes is simple: even if a user explicitly
requests using huge pages to back the file mapping (using VM_HUGEPAGE
flag), under a very strong memory pressure it's better to fall back
to ordinary pages.

Signed-off-by: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Dev Jain <dev.jain@arm.com>
Cc: linux-mm@kvack.org

--

v3: fixed VM_SEQ_READ handling for the THP case (by Jan Kara)
v2: fixed VM_SEQ_READ handling (by Dev Jain)
---
 mm/filemap.c | 68 +++++++++++++++++++++++++++++-----------------------
 1 file changed, 38 insertions(+), 30 deletions(-)

diff --git a/mm/filemap.c b/mm/filemap.c
index a52dd38d2b4a..ec731ac05551 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3235,11 +3235,47 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 	DEFINE_READAHEAD(ractl, file, ra, mapping, vmf->pgoff);
 	struct file *fpin = NULL;
 	vm_flags_t vm_flags = vmf->vma->vm_flags;
+	bool force_thp_readahead = false;
 	unsigned short mmap_miss;
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	/* Use the readahead code, even if readahead is disabled */
-	if ((vm_flags & VM_HUGEPAGE) && HPAGE_PMD_ORDER <= MAX_PAGECACHE_ORDER) {
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
+	    (vm_flags & VM_HUGEPAGE) && HPAGE_PMD_ORDER <= MAX_PAGECACHE_ORDER)
+		force_thp_readahead = true;
+
+	if (!force_thp_readahead) {
+		/*
+		 * If we don't want any read-ahead, don't bother.
+		 * VM_EXEC case below is already intended for random access.
+		 */
+		if ((vm_flags & (VM_RAND_READ | VM_EXEC)) == VM_RAND_READ)
+			return fpin;
+
+		if (!ra->ra_pages)
+			return fpin;
+
+		if (vm_flags & VM_SEQ_READ) {
+			fpin = maybe_unlock_mmap_for_io(vmf, fpin);
+			page_cache_sync_ra(&ractl, ra->ra_pages);
+			return fpin;
+		}
+	}
+
+	if (!(vm_flags & VM_SEQ_READ)) {
+		/* Avoid banging the cache line if not needed */
+		mmap_miss = READ_ONCE(ra->mmap_miss);
+		if (mmap_miss < MMAP_LOTSAMISS * 10)
+			WRITE_ONCE(ra->mmap_miss, ++mmap_miss);
+
+		/*
+		 * Do we miss much more than hit in this file? If so,
+		 * stop bothering with read-ahead. It will only hurt.
+		 */
+		if (mmap_miss > MMAP_LOTSAMISS)
+			return fpin;
+	}
+
+	if (force_thp_readahead) {
 		fpin = maybe_unlock_mmap_for_io(vmf, fpin);
 		ractl._index &= ~((unsigned long)HPAGE_PMD_NR - 1);
 		ra->size = HPAGE_PMD_NR;
@@ -3254,34 +3290,6 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 		page_cache_ra_order(&ractl, ra);
 		return fpin;
 	}
-#endif
-
-	/*
-	 * If we don't want any read-ahead, don't bother. VM_EXEC case below is
-	 * already intended for random access.
-	 */
-	if ((vm_flags & (VM_RAND_READ | VM_EXEC)) == VM_RAND_READ)
-		return fpin;
-	if (!ra->ra_pages)
-		return fpin;
-
-	if (vm_flags & VM_SEQ_READ) {
-		fpin = maybe_unlock_mmap_for_io(vmf, fpin);
-		page_cache_sync_ra(&ractl, ra->ra_pages);
-		return fpin;
-	}
-
-	/* Avoid banging the cache line if not needed */
-	mmap_miss = READ_ONCE(ra->mmap_miss);
-	if (mmap_miss < MMAP_LOTSAMISS * 10)
-		WRITE_ONCE(ra->mmap_miss, ++mmap_miss);
-
-	/*
-	 * Do we miss much more than hit in this file? If so,
-	 * stop bothering with read-ahead. It will only hurt.
-	 */
-	if (mmap_miss > MMAP_LOTSAMISS)
-		return fpin;
 
 	if (vm_flags & VM_EXEC) {
 		/*
-- 
2.51.0