iomap: fix iomap_dio_zero() for fs bs > system page size

iomap_dio_zero() will pad a fs block with zeroes if the direct IO size
< fs block size. iomap_dio_zero() has an implicit assumption that fs block
size < page_size. This is true for most filesystems at the moment.

If the block size > page size, this will send the contents of the page
next to zero page(as len > PAGE_SIZE) to the underlying block device,
causing FS corruption.

iomap is a generic infrastructure and it should not make any assumptions
about the fs block size and the page size of the system.

Signed-off-by: Pankaj Raghav <p.raghav@samsung.com>
Link: https://lore.kernel.org/r/20240822135018.1931258-7-kernel@pankajraghav.com
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Daniel Gomez <da.gomez@samsung.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index f420c53d86acc5753a76c34e0c2a05ff9673f36f..d745f718bcde854aabf5d0ea2f316840cab9b4ca 100644 (file)
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -2007,10 +2007,10 @@ iomap_writepages(struct address_space *mapping, struct writeback_control *wbc,
 }
 EXPORT_SYMBOL_GPL(iomap_writepages);
 
-static int __init iomap_init(void)
+static int __init iomap_buffered_init(void)
 {
        return bioset_init(&iomap_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE),
                           offsetof(struct iomap_ioend, io_bio),
                           BIOSET_NEED_BVECS);
 }
-fs_initcall(iomap_init);
+fs_initcall(iomap_buffered_init);

diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index f3b43d223a46ee9064315b6bc902852f16172ce1..c02b266bba525121ea176d3ef188f6769c2a99d1 100644 (file)
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -11,6 +11,7 @@
 #include <linux/iomap.h>
 #include <linux/backing-dev.h>
 #include <linux/uio.h>
+#include <linux/set_memory.h>
 #include <linux/task_io_accounting_ops.h>
 #include "trace.h"
 
@@ -27,6 +28,13 @@
 #define IOMAP_DIO_WRITE                (1U << 30)
 #define IOMAP_DIO_DIRTY                (1U << 31)
 
+/*
+ * Used for sub block zeroing in iomap_dio_zero()
+ */
+#define IOMAP_ZERO_PAGE_SIZE (SZ_64K)
+#define IOMAP_ZERO_PAGE_ORDER (get_order(IOMAP_ZERO_PAGE_SIZE))
+static struct page *zero_page;
+
 struct iomap_dio {
        struct kiocb            *iocb;
        const struct iomap_dio_ops *dops;
@@ -232,13 +240,20 @@ release_bio:
 }
 EXPORT_SYMBOL_GPL(iomap_dio_bio_end_io);
 
-static void iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio,
+static int iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio,
                loff_t pos, unsigned len)
 {
        struct inode *inode = file_inode(dio->iocb->ki_filp);
-       struct page *page = ZERO_PAGE(0);
        struct bio *bio;
 
+       if (!len)
+               return 0;
+       /*
+        * Max block size supported is 64k
+        */
+       if (WARN_ON_ONCE(len > IOMAP_ZERO_PAGE_SIZE))
+               return -EINVAL;
+
        bio = iomap_dio_alloc_bio(iter, dio, 1, REQ_OP_WRITE | REQ_SYNC | REQ_IDLE);
        fscrypt_set_bio_crypt_ctx(bio, inode, pos >> inode->i_blkbits,
                                  GFP_KERNEL);
@@ -246,8 +261,9 @@ static void iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio,
        bio->bi_private = dio;
        bio->bi_end_io = iomap_dio_bio_end_io;
 
-       __bio_add_page(bio, page, len, 0);
+       __bio_add_page(bio, zero_page, len, 0);
        iomap_dio_submit_bio(iter, dio, bio, pos);
+       return 0;
 }
 
 /*
@@ -356,8 +372,10 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
        if (need_zeroout) {
                /* zero out from the start of the block to the write offset */
                pad = pos & (fs_block_size - 1);
-               if (pad)
-                       iomap_dio_zero(iter, dio, pos - pad, pad);
+
+               ret = iomap_dio_zero(iter, dio, pos - pad, pad);
+               if (ret)
+                       goto out;
        }
 
        /*
@@ -431,7 +449,8 @@ zero_tail:
                /* zero out from the end of the write to the end of the block */
                pad = pos & (fs_block_size - 1);
                if (pad)
-                       iomap_dio_zero(iter, dio, pos, fs_block_size - pad);
+                       ret = iomap_dio_zero(iter, dio, pos,
+                                            fs_block_size - pad);
        }
 out:
        /* Undo iter limitation to current extent */
@@ -753,3 +772,17 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
        return iomap_dio_complete(dio);
 }
 EXPORT_SYMBOL_GPL(iomap_dio_rw);
+
+static int __init iomap_dio_init(void)
+{
+       zero_page = alloc_pages(GFP_KERNEL | __GFP_ZERO,
+                               IOMAP_ZERO_PAGE_ORDER);
+
+       if (!zero_page)
+               return -ENOMEM;
+
+       set_memory_ro((unsigned long)page_address(zero_page),
+                     1U << IOMAP_ZERO_PAGE_ORDER);
+       return 0;
+}
+fs_initcall(iomap_dio_init);