Merge tag 'vfs-6.12.blocksize' of gitolite.kernel.org:pub/scm/linux/kernel/git/vfs/vfs

Pull vfs blocksize updates from Christian Brauner:
 "This contains the vfs infrastructure as well as the xfs bits to enable
  support for block sizes (bs) larger than page sizes (ps) plus a few
  fixes to related infrastructure.

  There has been efforts over the last 16 years to enable enable Large
  Block Sizes (LBS), that is block sizes in filesystems where bs > page
  size. Through these efforts we have learned that one of the main
  blockers to supporting bs > ps in filesystems has been a way to
  allocate pages that are at least the filesystem block size on the page
  cache where bs > ps.

  Thanks to various previous efforts it is possible to support bs > ps
  in XFS with only a few changes in XFS itself. Most changes are to the
  page cache to support minimum order folio support for the target block
  size on the filesystem.

  A motivation for Large Block Sizes today is to support high-capacity
  (large amount of Terabytes) QLC SSDs where the internal Indirection
  Unit (IU) are typically greater than 4k to help reduce DRAM and so in
  turn cost and space. In practice this then allows different
  architectures to use a base page size of 4k while still enabling
  support for block sizes aligned to the larger IUs by relying on high
  order folios on the page cache when needed.

  It also allows to take advantage of the drive's support for atomics
  larger than 4k with buffered IO support in Linux. As described this
  year at LSFMM, supporting large atomics greater than 4k enables
  databases to remove the need to rely on their own journaling, so they
  can disable double buffered writes, which is a feature different cloud
  providers are already enabling through custom storage solutions"

* tag 'vfs-6.12.blocksize' of gitolite.kernel.org:pub/scm/linux/kernel/git/vfs/vfs: (22 commits)
  Documentation: iomap: fix a typo
  iomap: remove the iomap_file_buffered_write_punch_delalloc return value
  iomap: pass the iomap to the punch callback
  iomap: pass flags to iomap_file_buffered_write_punch_delalloc
  iomap: improve shared block detection in iomap_unshare_iter
  iomap: handle a post-direct I/O invalidate race in iomap_write_delalloc_release
  docs:filesystems: fix spelling and grammar mistakes in iomap design page
  filemap: fix htmldoc warning for mapping_align_index()
  iomap: make zero range flush conditional on unwritten mappings
  iomap: fix handling of dirty folios over unwritten extents
  iomap: add a private argument for iomap_file_buffered_write
  iomap: remove set_memor_ro() on zero page
  xfs: enable block size larger than page size support
  xfs: make the calculation generic in xfs_sb_validate_fsb_count()
  xfs: expose block size in stat
  xfs: use kvmalloc for xattr buffers
  iomap: fix iomap_dio_zero() for fs bs > system page size
  filemap: cap PTE range to be created to allowed zero fill in folio_map_range()
  mm: split a folio in minimum folio order chunks
  readahead: allocate folios with mapping_min_order in readahead
  ...

3 files changed, 147 insertions, 37 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 60a9cc593e9b..65c515e7bbf0 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -859,6 +859,8 @@ noinline int __filemap_add_folio(struct address_space *mapping,
 
 	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 	VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio);
+	VM_BUG_ON_FOLIO(folio_order(folio) < mapping_min_folio_order(mapping),
+			folio);
 	mapping_set_update(&xas, mapping);
 
 	VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio);
@@ -1919,8 +1921,10 @@ repeat:
 		folio_wait_stable(folio);
 no_page:
 	if (!folio && (fgp_flags & FGP_CREAT)) {
-		unsigned order = FGF_GET_ORDER(fgp_flags);
+		unsigned int min_order = mapping_min_folio_order(mapping);
+		unsigned int order = max(min_order, FGF_GET_ORDER(fgp_flags));
 		int err;
+		index = mapping_align_index(mapping, index);
 
 		if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping))
 			gfp |= __GFP_WRITE;
@@ -1933,10 +1937,8 @@ no_page:
 		if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP))))
 			fgp_flags |= FGP_LOCK;
 
-		if (!mapping_large_folio_support(mapping))
-			order = 0;
-		if (order > MAX_PAGECACHE_ORDER)
-			order = MAX_PAGECACHE_ORDER;
+		if (order > mapping_max_folio_order(mapping))
+			order = mapping_max_folio_order(mapping);
 		/* If we're not aligned, allocate a smaller folio */
 		if (index & ((1UL << order) - 1))
 			order = __ffs(index);
@@ -1945,7 +1947,7 @@ no_page:
 			gfp_t alloc_gfp = gfp;
 
 			err = -ENOMEM;
-			if (order > 0)
+			if (order > min_order)
 				alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN;
 			folio = filemap_alloc_folio(alloc_gfp, order);
 			if (!folio)
@@ -1960,7 +1962,7 @@ no_page:
 				break;
 			folio_put(folio);
 			folio = NULL;
-		} while (order-- > 0);
+		} while (order-- > min_order);
 
 		if (err == -EEXIST)
 			goto repeat;
@@ -2449,13 +2451,15 @@ unlock_mapping:
 }
 
 static int filemap_create_folio(struct file *file,
-		struct address_space *mapping, pgoff_t index,
+		struct address_space *mapping, loff_t pos,
 		struct folio_batch *fbatch)
 {
 	struct folio *folio;
 	int error;
+	unsigned int min_order = mapping_min_folio_order(mapping);
+	pgoff_t index;
 
-	folio = filemap_alloc_folio(mapping_gfp_mask(mapping), 0);
+	folio = filemap_alloc_folio(mapping_gfp_mask(mapping), min_order);
 	if (!folio)
 		return -ENOMEM;
 
@@ -2473,6 +2477,7 @@ static int filemap_create_folio(struct file *file,
 	 * well to keep locking rules simple.
 	 */
 	filemap_invalidate_lock_shared(mapping);
+	index = (pos >> (PAGE_SHIFT + min_order)) << min_order;
 	error = filemap_add_folio(mapping, folio, index,
 			mapping_gfp_constraint(mapping, GFP_KERNEL));
 	if (error == -EEXIST)
@@ -2533,8 +2538,7 @@ retry:
 	if (!folio_batch_count(fbatch)) {
 		if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ))
 			return -EAGAIN;
-		err = filemap_create_folio(filp, mapping,
-				iocb->ki_pos >> PAGE_SHIFT, fbatch);
+		err = filemap_create_folio(filp, mapping, iocb->ki_pos, fbatch);
 		if (err == AOP_TRUNCATED_PAGE)
 			goto retry;
 		return err;
@@ -3611,7 +3615,7 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 	struct vm_area_struct *vma = vmf->vma;
 	struct file *file = vma->vm_file;
 	struct address_space *mapping = file->f_mapping;
-	pgoff_t last_pgoff = start_pgoff;
+	pgoff_t file_end, last_pgoff = start_pgoff;
 	unsigned long addr;
 	XA_STATE(xas, &mapping->i_pages, start_pgoff);
 	struct folio *folio;
@@ -3637,6 +3641,10 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 		goto out;
 	}
 
+	file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1;
+	if (end_pgoff > file_end)
+		end_pgoff = file_end;
+
 	folio_type = mm_counter_file(folio);
 	do {
 		unsigned long end;
@@ -3757,9 +3765,11 @@ static struct folio *do_read_cache_folio(struct address_space *mapping,
 repeat:
 	folio = filemap_get_folio(mapping, index);
 	if (IS_ERR(folio)) {
-		folio = filemap_alloc_folio(gfp, 0);
+		folio = filemap_alloc_folio(gfp,
+					    mapping_min_folio_order(mapping));
 		if (!folio)
 			return ERR_PTR(-ENOMEM);
+		index = mapping_align_index(mapping, index);
 		err = filemap_add_folio(mapping, folio, index, gfp);
 		if (unlikely(err)) {
 			folio_put(folio);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 99b146d16a18..b71f744d360c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3081,6 +3081,9 @@ bool can_split_folio(struct folio *folio, int *pextra_pins)
  * released, or if some unexpected race happened (e.g., anon VMA disappeared,
  * truncation).
  *
+ * Callers should ensure that the order respects the address space mapping
+ * min-order if one is set for non-anonymous folios.
+ *
  * Returns -EINVAL when trying to split to an order that is incompatible
  * with the folio. Splitting to order 0 is compatible with all folios.
  */
@@ -3162,6 +3165,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
 		mapping = NULL;
 		anon_vma_lock_write(anon_vma);
 	} else {
+		unsigned int min_order;
 		gfp_t gfp;
 
 		mapping = folio->mapping;
@@ -3172,6 +3176,14 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
 			goto out;
 		}
 
+		min_order = mapping_min_folio_order(folio->mapping);
+		if (new_order < min_order) {
+			VM_WARN_ONCE(1, "Cannot split mapped folio below min-order: %u",
+				     min_order);
+			ret = -EINVAL;
+			goto out;
+		}
+
 		gfp = current_gfp_context(mapping_gfp_mask(mapping) &
 							GFP_RECLAIM_MASK);
 
@@ -3284,6 +3296,30 @@ out:
 	return ret;
 }
 
+int min_order_for_split(struct folio *folio)
+{
+	if (folio_test_anon(folio))
+		return 0;
+
+	if (!folio->mapping) {
+		if (folio_test_pmd_mappable(folio))
+			count_vm_event(THP_SPLIT_PAGE_FAILED);
+		return -EBUSY;
+	}
+
+	return mapping_min_folio_order(folio->mapping);
+}
+
+int split_folio_to_list(struct folio *folio, struct list_head *list)
+{
+	int ret = min_order_for_split(folio);
+
+	if (ret < 0)
+		return ret;
+
+	return split_huge_page_to_list_to_order(&folio->page, list, ret);
+}
+
 void __folio_undo_large_rmappable(struct folio *folio)
 {
 	struct deferred_split *ds_queue;
@@ -3514,6 +3550,8 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
 		struct vm_area_struct *vma = vma_lookup(mm, addr);
 		struct page *page;
 		struct folio *folio;
+		struct address_space *mapping;
+		unsigned int target_order = new_order;
 
 		if (!vma)
 			break;
@@ -3534,7 +3572,13 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
 		if (!is_transparent_hugepage(folio))
 			goto next;
 
-		if (new_order >= folio_order(folio))
+		if (!folio_test_anon(folio)) {
+			mapping = folio->mapping;
+			target_order = max(new_order,
+					   mapping_min_folio_order(mapping));
+		}
+
+		if (target_order >= folio_order(folio))
 			goto next;
 
 		total++;
@@ -3550,9 +3594,14 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
 		if (!folio_trylock(folio))
 			goto next;
 
-		if (!split_folio_to_order(folio, new_order))
+		if (!folio_test_anon(folio) && folio->mapping != mapping)
+			goto unlock;
+
+		if (!split_folio_to_order(folio, target_order))
 			split++;
 
+unlock:
+
 		folio_unlock(folio);
 next:
 		folio_put(folio);
@@ -3577,6 +3626,8 @@ static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start,
 	pgoff_t index;
 	int nr_pages = 1;
 	unsigned long total = 0, split = 0;
+	unsigned int min_order;
+	unsigned int target_order;
 
 	file = getname_kernel(file_path);
 	if (IS_ERR(file))
@@ -3590,6 +3641,8 @@ static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start,
 		 file_path, off_start, off_end);
 
 	mapping = candidate->f_mapping;
+	min_order = mapping_min_folio_order(mapping);
+	target_order = max(new_order, min_order);
 
 	for (index = off_start; index < off_end; index += nr_pages) {
 		struct folio *folio = filemap_get_folio(mapping, index);
@@ -3604,15 +3657,19 @@ static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start,
 		total++;
 		nr_pages = folio_nr_pages(folio);
 
-		if (new_order >= folio_order(folio))
+		if (target_order >= folio_order(folio))
 			goto next;
 
 		if (!folio_trylock(folio))
 			goto next;
 
-		if (!split_folio_to_order(folio, new_order))
+		if (folio->mapping != mapping)
+			goto unlock;
+
+		if (!split_folio_to_order(folio, target_order))
 			split++;
 
+unlock:
 		folio_unlock(folio);
 next:
 		folio_put(folio);
diff --git a/mm/readahead.c b/mm/readahead.c
index 517c0be7ce66..2078c42777a6 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -206,9 +206,10 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 		unsigned long nr_to_read, unsigned long lookahead_size)
 {
 	struct address_space *mapping = ractl->mapping;
-	unsigned long index = readahead_index(ractl);
+	unsigned long ra_folio_index, index = readahead_index(ractl);
 	gfp_t gfp_mask = readahead_gfp_mask(mapping);
-	unsigned long i;
+	unsigned long mark, i = 0;
+	unsigned int min_nrpages = mapping_min_folio_nrpages(mapping);
 
 	/*
 	 * Partway through the readahead operation, we will have added
@@ -223,10 +224,24 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 	unsigned int nofs = memalloc_nofs_save();
 
 	filemap_invalidate_lock_shared(mapping);
+	index = mapping_align_index(mapping, index);
+
+	/*
+	 * As iterator `i` is aligned to min_nrpages, round_up the
+	 * difference between nr_to_read and lookahead_size to mark the
+	 * index that only has lookahead or "async_region" to set the
+	 * readahead flag.
+	 */
+	ra_folio_index = round_up(readahead_index(ractl) + nr_to_read - lookahead_size,
+				  min_nrpages);
+	mark = ra_folio_index - index;
+	nr_to_read += readahead_index(ractl) - index;
+	ractl->_index = index;
+
 	/*
 	 * Preallocate as many pages as we will need.
 	 */
-	for (i = 0; i < nr_to_read; i++) {
+	while (i < nr_to_read) {
 		struct folio *folio = xa_load(&mapping->i_pages, index + i);
 		int ret;
 
@@ -240,12 +255,13 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 			 * not worth getting one just for that.
 			 */
 			read_pages(ractl);
-			ractl->_index++;
-			i = ractl->_index + ractl->_nr_pages - index - 1;
+			ractl->_index += min_nrpages;
+			i = ractl->_index + ractl->_nr_pages - index;
 			continue;
 		}
 
-		folio = filemap_alloc_folio(gfp_mask, 0);
+		folio = filemap_alloc_folio(gfp_mask,
+					    mapping_min_folio_order(mapping));
 		if (!folio)
 			break;
 
@@ -255,14 +271,15 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 			if (ret == -ENOMEM)
 				break;
 			read_pages(ractl);
-			ractl->_index++;
-			i = ractl->_index + ractl->_nr_pages - index - 1;
+			ractl->_index += min_nrpages;
+			i = ractl->_index + ractl->_nr_pages - index;
 			continue;
 		}
-		if (i == nr_to_read - lookahead_size)
+		if (i == mark)
 			folio_set_readahead(folio);
 		ractl->_workingset |= folio_test_workingset(folio);
-		ractl->_nr_pages++;
+		ractl->_nr_pages += min_nrpages;
+		i += min_nrpages;
 	}
 
 	/*
@@ -438,26 +455,41 @@ void page_cache_ra_order(struct readahead_control *ractl,
 	struct address_space *mapping = ractl->mapping;
 	pgoff_t start = readahead_index(ractl);
 	pgoff_t index = start;
+	unsigned int min_order = mapping_min_folio_order(mapping);
 	pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT;
 	pgoff_t mark = index + ra->size - ra->async_size;
 	unsigned int nofs;
 	int err = 0;
 	gfp_t gfp = readahead_gfp_mask(mapping);
+	unsigned int min_ra_size = max(4, mapping_min_folio_nrpages(mapping));
 
-	if (!mapping_large_folio_support(mapping) || ra->size < 4)
+	/*
+	 * Fallback when size < min_nrpages as each folio should be
+	 * at least min_nrpages anyway.
+	 */
+	if (!mapping_large_folio_support(mapping) || ra->size < min_ra_size)
 		goto fallback;
 
 	limit = min(limit, index + ra->size - 1);
 
-	if (new_order < MAX_PAGECACHE_ORDER)
+	if (new_order < mapping_max_folio_order(mapping))
 		new_order += 2;
 
-	new_order = min_t(unsigned int, MAX_PAGECACHE_ORDER, new_order);
+	new_order = min(mapping_max_folio_order(mapping), new_order);
 	new_order = min_t(unsigned int, new_order, ilog2(ra->size));
+	new_order = max(new_order, min_order);
 
 	/* See comment in page_cache_ra_unbounded() */
 	nofs = memalloc_nofs_save();
 	filemap_invalidate_lock_shared(mapping);
+	/*
+	 * If the new_order is greater than min_order and index is
+	 * already aligned to new_order, then this will be noop as index
+	 * aligned to new_order should also be aligned to min_order.
+	 */
+	ractl->_index = mapping_align_index(mapping, index);
+	index = readahead_index(ractl);
+
 	while (index <= limit) {
 		unsigned int order = new_order;
 
@@ -465,7 +497,7 @@ void page_cache_ra_order(struct readahead_control *ractl,
 		if (index & ((1UL << order) - 1))
 			order = __ffs(index);
 		/* Don't allocate pages past EOF */
-		while (index + (1UL << order) - 1 > limit)
+		while (order > min_order && index + (1UL << order) - 1 > limit)
 			order--;
 		err = ra_alloc_folio(ractl, index, mark, order, gfp);
 		if (err)
@@ -703,8 +735,15 @@ void readahead_expand(struct readahead_control *ractl,
 	struct file_ra_state *ra = ractl->ra;
 	pgoff_t new_index, new_nr_pages;
 	gfp_t gfp_mask = readahead_gfp_mask(mapping);
+	unsigned long min_nrpages = mapping_min_folio_nrpages(mapping);
+	unsigned int min_order = mapping_min_folio_order(mapping);
 
 	new_index = new_start / PAGE_SIZE;
+	/*
+	 * Readahead code should have aligned the ractl->_index to
+	 * min_nrpages before calling readahead aops.
+	 */
+	VM_BUG_ON(!IS_ALIGNED(ractl->_index, min_nrpages));
 
 	/* Expand the leading edge downwards */
 	while (ractl->_index > new_index) {
@@ -714,9 +753,11 @@ void readahead_expand(struct readahead_control *ractl,
 		if (folio && !xa_is_value(folio))
 			return; /* Folio apparently present */
 
-		folio = filemap_alloc_folio(gfp_mask, 0);
+		folio = filemap_alloc_folio(gfp_mask, min_order);
 		if (!folio)
 			return;
+
+		index = mapping_align_index(mapping, index);
 		if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) {
 			folio_put(folio);
 			return;
@@ -726,7 +767,7 @@ void readahead_expand(struct readahead_control *ractl,
 			ractl->_workingset = true;
 			psi_memstall_enter(&ractl->_pflags);
 		}
-		ractl->_nr_pages++;
+		ractl->_nr_pages += min_nrpages;
 		ractl->_index = folio->index;
 	}
 
@@ -741,9 +782,11 @@ void readahead_expand(struct readahead_control *ractl,
 		if (folio && !xa_is_value(folio))
 			return; /* Folio apparently present */
 
-		folio = filemap_alloc_folio(gfp_mask, 0);
+		folio = filemap_alloc_folio(gfp_mask, min_order);
 		if (!folio)
 			return;
+
+		index = mapping_align_index(mapping, index);
 		if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) {
 			folio_put(folio);
 			return;
@@ -753,10 +796,10 @@ void readahead_expand(struct readahead_control *ractl,
 			ractl->_workingset = true;
 			psi_memstall_enter(&ractl->_pflags);
 		}
-		ractl->_nr_pages++;
+		ractl->_nr_pages += min_nrpages;
 		if (ra) {
-			ra->size++;
-			ra->async_size++;
+			ra->size += min_nrpages;
+			ra->async_size += min_nrpages;
 		}
 	}
 }