1 files changed, 41 insertions, 26 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 65c515e7bbf0..4f3753f0a158 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -46,6 +46,7 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/splice.h>
 #include <linux/rcupdate_wait.h>
+#include <linux/sched/mm.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include "internal.h"
@@ -112,8 +113,8 @@
  *    ->swap_lock		(try_to_unmap_one)
  *    ->private_lock		(try_to_unmap_one)
  *    ->i_pages lock		(try_to_unmap_one)
- *    ->lruvec->lru_lock	(follow_page->mark_page_accessed)
- *    ->lruvec->lru_lock	(check_pte_range->isolate_lru_page)
+ *    ->lruvec->lru_lock	(follow_page_mask->mark_page_accessed)
+ *    ->lruvec->lru_lock	(check_pte_range->folio_isolate_lru)
  *    ->private_lock		(folio_remove_rmap_pte->set_page_dirty)
  *    ->i_pages lock		(folio_remove_rmap_pte->set_page_dirty)
  *    bdi.wb->list_lock		(folio_remove_rmap_pte->set_page_dirty)
@@ -530,7 +531,6 @@ static void __filemap_fdatawait_range(struct address_space *mapping,
 			struct folio *folio = fbatch.folios[i];
 
 			folio_wait_writeback(folio);
-			folio_clear_error(folio);
 		}
 		folio_batch_release(&fbatch);
 		cond_resched();
@@ -2049,17 +2049,20 @@ unsigned find_get_entries(struct address_space *mapping, pgoff_t *start,
 		if (!folio_batch_add(fbatch, folio))
 			break;
 	}
-	rcu_read_unlock();
 
 	if (folio_batch_count(fbatch)) {
-		unsigned long nr = 1;
+		unsigned long nr;
 		int idx = folio_batch_count(fbatch) - 1;
 
 		folio = fbatch->folios[idx];
 		if (!xa_is_value(folio))
 			nr = folio_nr_pages(folio);
-		*start = indices[idx] + nr;
+		else
+			nr = 1 << xa_get_order(&mapping->i_pages, indices[idx]);
+		*start = round_down(indices[idx] + nr, nr);
 	}
+	rcu_read_unlock();
+
 	return folio_batch_count(fbatch);
 }
 
@@ -2091,10 +2094,17 @@ unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start,
 
 	rcu_read_lock();
 	while ((folio = find_get_entry(&xas, end, XA_PRESENT))) {
+		unsigned long base;
+		unsigned long nr;
+
 		if (!xa_is_value(folio)) {
-			if (folio->index < *start)
+			nr = folio_nr_pages(folio);
+			base = folio->index;
+			/* Omit large folio which begins before the start */
+			if (base < *start)
 				goto put;
-			if (folio_next_index(folio) - 1 > end)
+			/* Omit large folio which extends beyond the end */
+			if (base + nr - 1 > end)
 				goto put;
 			if (!folio_trylock(folio))
 				goto put;
@@ -2103,7 +2113,19 @@ unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start,
 				goto unlock;
 			VM_BUG_ON_FOLIO(!folio_contains(folio, xas.xa_index),
 					folio);
+		} else {
+			nr = 1 << xas_get_order(&xas);
+			base = xas.xa_index & ~(nr - 1);
+			/* Omit order>0 value which begins before the start */
+			if (base < *start)
+				continue;
+			/* Omit order>0 value which extends beyond the end */
+			if (base + nr - 1 > end)
+				break;
 		}
+
+		/* Update start now so that last update is correct on return */
+		*start = base + nr;
 		indices[fbatch->nr] = xas.xa_index;
 		if (!folio_batch_add(fbatch, folio))
 			break;
@@ -2115,15 +2137,6 @@ put:
 	}
 	rcu_read_unlock();
 
-	if (folio_batch_count(fbatch)) {
-		unsigned long nr = 1;
-		int idx = folio_batch_count(fbatch) - 1;
-
-		folio = fbatch->folios[idx];
-		if (!xa_is_value(folio))
-			nr = folio_nr_pages(folio);
-		*start = indices[idx] + nr;
-	}
 	return folio_batch_count(fbatch);
 }
 
@@ -2344,13 +2357,6 @@ static int filemap_read_folio(struct file *file, filler_t filler,
 	unsigned long pflags;
 	int error;
 
-	/*
-	 * A previous I/O error may have been due to temporary failures,
-	 * eg. multipath errors.  PG_error will be set again if read_folio
-	 * fails.
-	 */
-	folio_clear_error(folio);
-
 	/* Start the actual read. The read will unlock the page. */
 	if (unlikely(workingset))
 		psi_memstall_enter(&pflags);
@@ -2519,6 +2525,7 @@ static int filemap_get_pages(struct kiocb *iocb, size_t count,
 	pgoff_t index = iocb->ki_pos >> PAGE_SHIFT;
 	pgoff_t last_index;
 	struct folio *folio;
+	unsigned int flags;
 	int err = 0;
 
 	/* "last_index" is the index of the page beyond the end of the read */
@@ -2531,8 +2538,12 @@ retry:
 	if (!folio_batch_count(fbatch)) {
 		if (iocb->ki_flags & IOCB_NOIO)
 			return -EAGAIN;
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			flags = memalloc_noio_save();
 		page_cache_sync_readahead(mapping, ra, filp, index,
 				last_index - index);
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			memalloc_noio_restore(flags);
 		filemap_get_read_batch(mapping, index, last_index - 1, fbatch);
 	}
 	if (!folio_batch_count(fbatch)) {
@@ -2560,6 +2571,7 @@ retry:
 			goto err;
 	}
 
+	trace_mm_filemap_get_pages(mapping, index, last_index - 1);
 	return 0;
 err:
 	if (err < 0)
@@ -3000,7 +3012,7 @@ unlock:
 static inline size_t seek_folio_size(struct xa_state *xas, struct folio *folio)
 {
 	if (xa_is_value(folio))
-		return PAGE_SIZE << xa_get_order(xas->xa, xas->xa_index);
+		return PAGE_SIZE << xas_get_order(xas);
 	return folio_size(folio);
 }
 
@@ -3298,6 +3310,8 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
 	if (unlikely(index >= max_idx))
 		return VM_FAULT_SIGBUS;
 
+	trace_mm_filemap_fault(mapping, index);
+
 	/*
 	 * Do we have something in the page cache already?
 	 */
@@ -3668,6 +3682,7 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 	} while ((folio = next_uptodate_folio(&xas, mapping, end_pgoff)) != NULL);
 	add_mm_counter(vma->vm_mm, folio_type, rss);
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
+	trace_mm_filemap_map_pages(mapping, start_pgoff, end_pgoff);
 out:
 	rcu_read_unlock();
 
@@ -4297,7 +4312,7 @@ static void filemap_cachestat(struct address_space *mapping,
 		if (xas_retry(&xas, folio))
 			continue;
 
-		order = xa_get_order(xas.xa, xas.xa_index);
+		order = xas_get_order(&xas);
 		nr_pages = 1 << order;
 		folio_first_index = round_down(xas.xa_index, 1 << order);
 		folio_last_index = folio_first_index + nr_pages - 1;