[PATCH 2/4] mm: bypass mmap_miss heuristic for VM_EXEC readahead

[Usama Arif]

The mmap_miss counter in do_sync_mmap_readahead() tracks whether
readahead is useful for mmap'd file access. It is incremented by 1 on
every page cache miss in do_sync_mmap_readahead(), and decremented in
two places:

  - filemap_map_pages(): decremented by N for each of N pages
    successfully mapped via fault-around (pages found already in cache,
    evidence readahead was useful). Only pages not in the workingset
    count as hits.

  - do_async_mmap_readahead(): decremented by 1 when a page with
    PG_readahead is found in cache.

When the counter exceeds MMAP_LOTSAMISS (100), all readahead is
disabled, including the targeted VM_EXEC readahead [1] that requests
arch-preferred folio orders for contpte mapping.

On arm64 with 64K base pages, both decrement paths are inactive:

  1. filemap_map_pages() is never called because fault_around_pages
     (65536 >> PAGE_SHIFT = 1) disables should_fault_around(), which
     requires fault_around_pages > 1. With only 1 page in the
     fault-around window, there is nothing "around" to map.

  2. do_async_mmap_readahead() never fires for exec mappings because
     exec readahead sets async_size = 0, so no PG_readahead markers
     are placed.

With no decrements, mmap_miss monotonically increases past
MMAP_LOTSAMISS after 100 page faults, disabling all subsequent
exec readahead.

Fix this by moving the VM_EXEC readahead block above the mmap_miss
check. The exec readahead path is targeted. It reads a single folio at
the fault location with async_size=0, not speculative prefetch, so the
mmap_miss heuristic designed to throttle wasteful speculative readahead
should not gate it. The page would need to be faulted in regardless,
the only question is at what order.

[1] https://lore.kernel.org/all/20250430145920.3748738-6-ryan.roberts@xxxxxxx/

Signed-off-by: Usama Arif <usama.arif@xxxxxxxxx>
---
 mm/filemap.c | 72 ++++++++++++++++++++++++++++------------------------
 1 file changed, 39 insertions(+), 33 deletions(-)

diff --git a/mm/filemap.c b/mm/filemap.c
index 6cd7974d4adab..c064f31ecec5a 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3331,6 +3331,37 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 		}
 	}
 
+	if (vm_flags & VM_EXEC) {
+		/*
+		 * Allow arch to request a preferred minimum folio order for
+		 * executable memory. This can often be beneficial to
+		 * performance if (e.g.) arm64 can contpte-map the folio.
+		 * Executable memory rarely benefits from readahead, due to its
+		 * random access nature, so set async_size to 0.
+		 *
+		 * Limit to the boundaries of the VMA to avoid reading in any
+		 * pad that might exist between sections, which would be a waste
+		 * of memory.
+		 *
+		 * This is targeted readahead (one folio at the fault location),
+		 * not speculative prefetch, so bypass the mmap_miss heuristic
+		 * which would otherwise disable it after MMAP_LOTSAMISS faults.
+		 */
+		struct vm_area_struct *vma = vmf->vma;
+		unsigned long start = vma->vm_pgoff;
+		unsigned long end = start + vma_pages(vma);
+		unsigned long ra_end;
+
+		ra->order = exec_folio_order();
+		ra->start = round_down(vmf->pgoff, 1UL << ra->order);
+		ra->start = max(ra->start, start);
+		ra_end = round_up(ra->start + ra->ra_pages, 1UL << ra->order);
+		ra_end = min(ra_end, end);
+		ra->size = ra_end - ra->start;
+		ra->async_size = 0;
+		goto do_readahead;
+	}
+
 	if (!(vm_flags & VM_SEQ_READ)) {
 		/* Avoid banging the cache line if not needed */
 		mmap_miss = READ_ONCE(ra->mmap_miss);
@@ -3361,40 +3392,15 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 		return fpin;
 	}
 
-	if (vm_flags & VM_EXEC) {
-		/*
-		 * Allow arch to request a preferred minimum folio order for
-		 * executable memory. This can often be beneficial to
-		 * performance if (e.g.) arm64 can contpte-map the folio.
-		 * Executable memory rarely benefits from readahead, due to its
-		 * random access nature, so set async_size to 0.
-		 *
-		 * Limit to the boundaries of the VMA to avoid reading in any
-		 * pad that might exist between sections, which would be a waste
-		 * of memory.
-		 */
-		struct vm_area_struct *vma = vmf->vma;
-		unsigned long start = vma->vm_pgoff;
-		unsigned long end = start + vma_pages(vma);
-		unsigned long ra_end;
-
-		ra->order = exec_folio_order();
-		ra->start = round_down(vmf->pgoff, 1UL << ra->order);
-		ra->start = max(ra->start, start);
-		ra_end = round_up(ra->start + ra->ra_pages, 1UL << ra->order);
-		ra_end = min(ra_end, end);
-		ra->size = ra_end - ra->start;
-		ra->async_size = 0;
-	} else {
-		/*
-		 * mmap read-around
-		 */
-		ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2);
-		ra->size = ra->ra_pages;
-		ra->async_size = ra->ra_pages / 4;
-		ra->order = 0;
-	}
+	/*
+	 * mmap read-around
+	 */
+	ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2);
+	ra->size = ra->ra_pages;
+	ra->async_size = ra->ra_pages / 4;
+	ra->order = 0;
 
+do_readahead:
 	fpin = maybe_unlock_mmap_for_io(vmf, fpin);
 	ractl._index = ra->start;
 	page_cache_ra_order(&ractl, ra);
-- 
2.47.3