iomap: add a swapfile activation function

Add a new iomap_swapfile_activate function so that filesystems can
activate swap files without having to use the obsolete and slow bmap
function.  This enables XFS to support fallocate'd swap files and
swap files on realtime devices.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Jan Kara <jack@suse.cz>

1 files changed, 162 insertions, 0 deletions

diff --git a/fs/iomap.c b/fs/iomap.c
index bcfd7f3654d4..d193390a1c20 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -27,6 +27,7 @@
 #include <linux/task_io_accounting_ops.h>
 #include <linux/dax.h>
 #include <linux/sched/signal.h>
+#include <linux/swap.h>
 
 #include "internal.h"
 
@@ -1139,3 +1140,164 @@ out_free_dio:
 	return ret;
 }
 EXPORT_SYMBOL_GPL(iomap_dio_rw);
+
+/* Swapfile activation */
+
+#ifdef CONFIG_SWAP
+struct iomap_swapfile_info {
+	struct iomap iomap;		/* accumulated iomap */
+	struct swap_info_struct *sis;
+	uint64_t lowest_ppage;		/* lowest physical addr seen (pages) */
+	uint64_t highest_ppage;		/* highest physical addr seen (pages) */
+	unsigned long nr_pages;		/* number of pages collected */
+	int nr_extents;			/* extent count */
+};
+
+/*
+ * Collect physical extents for this swap file.  Physical extents reported to
+ * the swap code must be trimmed to align to a page boundary.  The logical
+ * offset within the file is irrelevant since the swapfile code maps logical
+ * page numbers of the swap device to the physical page-aligned extents.
+ */
+static int iomap_swapfile_add_extent(struct iomap_swapfile_info *isi)
+{
+	struct iomap *iomap = &isi->iomap;
+	unsigned long nr_pages;
+	uint64_t first_ppage;
+	uint64_t first_ppage_reported;
+	uint64_t next_ppage;
+	int error;
+
+	/*
+	 * Round the start up and the end down so that the physical
+	 * extent aligns to a page boundary.
+	 */
+	first_ppage = ALIGN(iomap->addr, PAGE_SIZE) >> PAGE_SHIFT;
+	next_ppage = ALIGN_DOWN(iomap->addr + iomap->length, PAGE_SIZE) >>
+			PAGE_SHIFT;
+
+	/* Skip too-short physical extents. */
+	if (first_ppage >= next_ppage)
+		return 0;
+	nr_pages = next_ppage - first_ppage;
+
+	/*
+	 * Calculate how much swap space we're adding; the first page contains
+	 * the swap header and doesn't count.  The mm still wants that first
+	 * page fed to add_swap_extent, however.
+	 */
+	first_ppage_reported = first_ppage;
+	if (iomap->offset == 0)
+		first_ppage_reported++;
+	if (isi->lowest_ppage > first_ppage_reported)
+		isi->lowest_ppage = first_ppage_reported;
+	if (isi->highest_ppage < (next_ppage - 1))
+		isi->highest_ppage = next_ppage - 1;
+
+	/* Add extent, set up for the next call. */
+	error = add_swap_extent(isi->sis, isi->nr_pages, nr_pages, first_ppage);
+	if (error < 0)
+		return error;
+	isi->nr_extents += error;
+	isi->nr_pages += nr_pages;
+	return 0;
+}
+
+/*
+ * Accumulate iomaps for this swap file.  We have to accumulate iomaps because
+ * swap only cares about contiguous page-aligned physical extents and makes no
+ * distinction between written and unwritten extents.
+ */
+static loff_t iomap_swapfile_activate_actor(struct inode *inode, loff_t pos,
+		loff_t count, void *data, struct iomap *iomap)
+{
+	struct iomap_swapfile_info *isi = data;
+	int error;
+
+	/* Skip holes. */
+	if (iomap->type == IOMAP_HOLE)
+		goto out;
+
+	/* Only one bdev per swap file. */
+	if (iomap->bdev != isi->sis->bdev)
+		goto err;
+
+	/* Only real or unwritten extents. */
+	if (iomap->type != IOMAP_MAPPED && iomap->type != IOMAP_UNWRITTEN)
+		goto err;
+
+	/* No uncommitted metadata or shared blocks or inline data. */
+	if (iomap->flags & (IOMAP_F_DIRTY | IOMAP_F_SHARED |
+			    IOMAP_F_DATA_INLINE))
+		goto err;
+
+	/* No null physical addresses. */
+	if (iomap->addr == IOMAP_NULL_ADDR)
+		goto err;
+
+	if (isi->iomap.length == 0) {
+		/* No accumulated extent, so just store it. */
+		memcpy(&isi->iomap, iomap, sizeof(isi->iomap));
+	} else if (isi->iomap.addr + isi->iomap.length == iomap->addr) {
+		/* Append this to the accumulated extent. */
+		isi->iomap.length += iomap->length;
+	} else {
+		/* Otherwise, add the retained iomap and store this one. */
+		error = iomap_swapfile_add_extent(isi);
+		if (error)
+			return error;
+		memcpy(&isi->iomap, iomap, sizeof(isi->iomap));
+	}
+out:
+	return count;
+err:
+	pr_err("swapon: file cannot be used for swap\n");
+	return -EINVAL;
+}
+
+/*
+ * Iterate a swap file's iomaps to construct physical extents that can be
+ * passed to the swapfile subsystem.
+ */
+int iomap_swapfile_activate(struct swap_info_struct *sis,
+		struct file *swap_file, sector_t *pagespan,
+		const struct iomap_ops *ops)
+{
+	struct iomap_swapfile_info isi = {
+		.sis = sis,
+		.lowest_ppage = (sector_t)-1ULL,
+	};
+	struct address_space *mapping = swap_file->f_mapping;
+	struct inode *inode = mapping->host;
+	loff_t pos = 0;
+	loff_t len = ALIGN_DOWN(i_size_read(inode), PAGE_SIZE);
+	loff_t ret;
+
+	ret = filemap_write_and_wait(inode->i_mapping);
+	if (ret)
+		return ret;
+
+	while (len > 0) {
+		ret = iomap_apply(inode, pos, len, IOMAP_REPORT,
+				ops, &isi, iomap_swapfile_activate_actor);
+		if (ret <= 0)
+			return ret;
+
+		pos += ret;
+		len -= ret;
+	}
+
+	if (isi.iomap.length) {
+		ret = iomap_swapfile_add_extent(&isi);
+		if (ret)
+			return ret;
+	}
+
+	*pagespan = 1 + isi.highest_ppage - isi.lowest_ppage;
+	sis->max = isi.nr_pages;
+	sis->pages = isi.nr_pages - 1;
+	sis->highest_bit = isi.nr_pages - 1;
+	return isi.nr_extents;
+}
+EXPORT_SYMBOL_GPL(iomap_swapfile_activate);
+#endif /* CONFIG_SWAP */