| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Tue, 22 May 2018 21:31:05 +0530
From: Chandan Rajendra <chandan@...ux.vnet.ibm.com>
To: linux-fscrypt@...r.kernel.org
Cc: Chandan Rajendra <chandan@...ux.vnet.ibm.com>, ebiggers3@...il.com,
tytso@....edu, linux-ext4@...r.kernel.org,
linux-fsdevel@...r.kernel.org
Subject: [RFC PATCH V3 07/12] mpage_readpage[s]: Introduce post process callback parameters
This commit introduces a new parameter to mpage_readpage[s]()
functions. This parameter contains pointers to functions that can be
used to decrypt data read from the backing device. These are stored in
the fscrypt_ctx structure and one of these functions is invoked after
the read operation is completed.
Signed-off-by: Chandan Rajendra <chandan@...ux.vnet.ibm.com>
---
fs/block_dev.c | 5 +-
fs/buffer.c | 298 ++++++++++++++++++++++++----------------
fs/crypto/bio.c | 95 ++++++++++++-
fs/crypto/crypto.c | 2 +
fs/ext2/inode.c | 4 +-
fs/ext4/Makefile | 2 +-
fs/ext4/inode.c | 13 +-
fs/ext4/readpage.c | 294 ---------------------------------------
fs/fat/inode.c | 4 +-
fs/isofs/inode.c | 5 +-
fs/mpage.c | 48 +++++--
fs/xfs/xfs_aops.c | 4 +-
include/linux/buffer_head.h | 2 +-
include/linux/fs.h | 4 +
include/linux/fscrypt_notsupp.h | 37 ++++-
include/linux/fscrypt_supp.h | 13 +-
include/linux/mpage.h | 6 +-
17 files changed, 392 insertions(+), 444 deletions(-)
delete mode 100644 fs/ext4/readpage.c
diff --git a/fs/block_dev.c b/fs/block_dev.c
index b549666..254af9a 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -568,13 +568,14 @@ static int blkdev_writepage(struct page *page, struct writeback_control *wbc)
static int blkdev_readpage(struct file * file, struct page * page)
{
- return block_read_full_page(page, blkdev_get_block);
+ return block_read_full_page(page, blkdev_get_block, NULL);
}
static int blkdev_readpages(struct file *file, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages)
{
- return mpage_readpages(mapping, pages, nr_pages, blkdev_get_block);
+ return mpage_readpages(mapping, pages, nr_pages, blkdev_get_block,
+ NULL);
}
static int blkdev_write_begin(struct file *file, struct address_space *mapping,
diff --git a/fs/buffer.c b/fs/buffer.c
index fda7926..978a8b7 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -45,8 +45,12 @@
#include <linux/mpage.h>
#include <linux/bit_spinlock.h>
#include <linux/pagevec.h>
+#include <linux/fs.h>
#include <trace/events/block.h>
+#define __FS_HAS_ENCRYPTION IS_ENABLED(CONFIG_EXT4_FS_ENCRYPTION)
+#include <linux/fscrypt.h>
+
static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
enum rw_hint hint, struct writeback_control *wbc);
@@ -2197,6 +2201,172 @@ int block_is_partially_uptodate(struct page *page, unsigned long from,
}
EXPORT_SYMBOL(block_is_partially_uptodate);
+static void end_bio_bh_io_sync(struct bio *bio)
+{
+ post_process_read_t *post_process;
+ struct fscrypt_ctx *ctx;
+ struct buffer_head *bh;
+
+ if (fscrypt_bio_encrypted(bio)) {
+ ctx = bio->bi_private;
+ post_process = fscrypt_get_post_process(ctx);
+
+ if (bio->bi_status || post_process->process_block == NULL) {
+ bh = fscrypt_get_bh(ctx);
+ fscrypt_release_ctx(ctx);
+ } else {
+ fscrypt_enqueue_decrypt_bio(ctx, bio,
+ post_process->process_block);
+ return;
+ }
+ } else {
+ bh = bio->bi_private;
+ }
+
+ if (unlikely(bio_flagged(bio, BIO_QUIET)))
+ set_bit(BH_Quiet, &bh->b_state);
+
+ bh->b_end_io(bh, !bio->bi_status);
+ bio_put(bio);
+}
+
+/*
+ * This allows us to do IO even on the odd last sectors
+ * of a device, even if the block size is some multiple
+ * of the physical sector size.
+ *
+ * We'll just truncate the bio to the size of the device,
+ * and clear the end of the buffer head manually.
+ *
+ * Truly out-of-range accesses will turn into actual IO
+ * errors, this only handles the "we need to be able to
+ * do IO at the final sector" case.
+ */
+void guard_bio_eod(int op, struct bio *bio)
+{
+ sector_t maxsector;
+ struct bio_vec *bvec = bio_last_bvec_all(bio);
+ unsigned truncated_bytes;
+ struct hd_struct *part;
+
+ rcu_read_lock();
+ part = __disk_get_part(bio->bi_disk, bio->bi_partno);
+ if (part)
+ maxsector = part_nr_sects_read(part);
+ else
+ maxsector = get_capacity(bio->bi_disk);
+ rcu_read_unlock();
+
+ if (!maxsector)
+ return;
+
+ /*
+ * If the *whole* IO is past the end of the device,
+ * let it through, and the IO layer will turn it into
+ * an EIO.
+ */
+ if (unlikely(bio->bi_iter.bi_sector >= maxsector))
+ return;
+
+ maxsector -= bio->bi_iter.bi_sector;
+ if (likely((bio->bi_iter.bi_size >> 9) <= maxsector))
+ return;
+
+ /* Uhhuh. We've got a bio that straddles the device size! */
+ truncated_bytes = bio->bi_iter.bi_size - (maxsector << 9);
+
+ /* Truncate the bio.. */
+ bio->bi_iter.bi_size -= truncated_bytes;
+ bvec->bv_len -= truncated_bytes;
+
+ /* ..and clear the end of the buffer for reads */
+ if (op == REQ_OP_READ) {
+ zero_user(bvec->bv_page, bvec->bv_offset + bvec->bv_len,
+ truncated_bytes);
+ }
+}
+
+struct bio *create_bh_bio(int op, int op_flags, struct buffer_head *bh,
+ enum rw_hint write_hint,
+ post_process_read_t *post_process)
+{
+ struct address_space *mapping;
+ struct fscrypt_ctx *ctx = NULL;
+ struct inode *inode;
+ struct page *page;
+ struct bio *bio;
+
+ BUG_ON(!buffer_locked(bh));
+ BUG_ON(!buffer_mapped(bh));
+ BUG_ON(!bh->b_end_io);
+ BUG_ON(buffer_delay(bh));
+ BUG_ON(buffer_unwritten(bh));
+
+ /*
+ * Only clear out a write error when rewriting
+ */
+ if (test_set_buffer_req(bh) && (op == REQ_OP_WRITE))
+ clear_buffer_write_io_error(bh);
+
+ page = bh->b_page;
+
+ if (op == REQ_OP_READ) {
+ mapping = page_mapping(page);
+ if (mapping && !PageSwapCache(page)) {
+ inode = mapping->host;
+ if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode)) {
+ ctx = fscrypt_get_ctx(inode, GFP_NOFS);
+ BUG_ON(!ctx);
+ fscrypt_set_bh(ctx, bh);
+ if (post_process)
+ fscrypt_set_post_process(ctx,
+ post_process);
+ }
+ }
+ }
+
+ /*
+ * from here on down, it's all bio -- do the initial mapping,
+ * submit_bio -> generic_make_request may further map this bio around
+ */
+ bio = bio_alloc(GFP_NOIO, 1);
+
+ bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
+ bio_set_dev(bio, bh->b_bdev);
+ bio->bi_write_hint = write_hint;
+
+ bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
+ BUG_ON(bio->bi_iter.bi_size != bh->b_size);
+
+ bio->bi_end_io = end_bio_bh_io_sync;
+
+ if (ctx)
+ bio->bi_private = ctx;
+ else
+ bio->bi_private = bh;
+
+ /* Take care of bh's that straddle the end of the device */
+ guard_bio_eod(op, bio);
+
+ if (buffer_meta(bh))
+ op_flags |= REQ_META;
+ if (buffer_prio(bh))
+ op_flags |= REQ_PRIO;
+ bio_set_op_attrs(bio, op, op_flags);
+
+ return bio;
+}
+
+static int submit_bh_post_process(int op, int op_flags, struct buffer_head *bh,
+ post_process_read_t *post_process)
+{
+ struct bio *bio;
+
+ bio = create_bh_bio(op, op_flags, bh, 0, post_process);
+ submit_bio(bio);
+ return 0;
+}
+
/*
* Generic "read page" function for block devices that have the normal
* get_block functionality. This is most of the block device filesystems.
@@ -2204,7 +2374,8 @@ EXPORT_SYMBOL(block_is_partially_uptodate);
* set/clear_buffer_uptodate() functions propagate buffer state into the
* page struct once IO has completed.
*/
-int block_read_full_page(struct page *page, get_block_t *get_block)
+int block_read_full_page(struct page *page, get_block_t *get_block,
+ post_process_read_t *post_process)
{
struct inode *inode = page->mapping->host;
sector_t iblock, lblock;
@@ -2284,7 +2455,8 @@ int block_read_full_page(struct page *page, get_block_t *get_block)
if (buffer_uptodate(bh))
end_buffer_async_read(bh, 1);
else
- submit_bh(REQ_OP_READ, 0, bh);
+ submit_bh_post_process(REQ_OP_READ, 0, bh,
+ post_process);
}
return 0;
}
@@ -2959,124 +3131,12 @@ sector_t generic_block_bmap(struct address_space *mapping, sector_t block,
}
EXPORT_SYMBOL(generic_block_bmap);
-static void end_bio_bh_io_sync(struct bio *bio)
-{
- struct buffer_head *bh = bio->bi_private;
-
- if (unlikely(bio_flagged(bio, BIO_QUIET)))
- set_bit(BH_Quiet, &bh->b_state);
-
- bh->b_end_io(bh, !bio->bi_status);
- bio_put(bio);
-}
-
-/*
- * This allows us to do IO even on the odd last sectors
- * of a device, even if the block size is some multiple
- * of the physical sector size.
- *
- * We'll just truncate the bio to the size of the device,
- * and clear the end of the buffer head manually.
- *
- * Truly out-of-range accesses will turn into actual IO
- * errors, this only handles the "we need to be able to
- * do IO at the final sector" case.
- */
-void guard_bio_eod(int op, struct bio *bio)
-{
- sector_t maxsector;
- struct bio_vec *bvec = bio_last_bvec_all(bio);
- unsigned truncated_bytes;
- struct hd_struct *part;
-
- rcu_read_lock();
- part = __disk_get_part(bio->bi_disk, bio->bi_partno);
- if (part)
- maxsector = part_nr_sects_read(part);
- else
- maxsector = get_capacity(bio->bi_disk);
- rcu_read_unlock();
-
- if (!maxsector)
- return;
-
- /*
- * If the *whole* IO is past the end of the device,
- * let it through, and the IO layer will turn it into
- * an EIO.
- */
- if (unlikely(bio->bi_iter.bi_sector >= maxsector))
- return;
-
- maxsector -= bio->bi_iter.bi_sector;
- if (likely((bio->bi_iter.bi_size >> 9) <= maxsector))
- return;
-
- /* Uhhuh. We've got a bio that straddles the device size! */
- truncated_bytes = bio->bi_iter.bi_size - (maxsector << 9);
-
- /* Truncate the bio.. */
- bio->bi_iter.bi_size -= truncated_bytes;
- bvec->bv_len -= truncated_bytes;
-
- /* ..and clear the end of the buffer for reads */
- if (op == REQ_OP_READ) {
- zero_user(bvec->bv_page, bvec->bv_offset + bvec->bv_len,
- truncated_bytes);
- }
-}
-
-struct bio *create_bh_bio(int op, int op_flags, struct buffer_head *bh,
- enum rw_hint write_hint)
-{
- struct bio *bio;
-
- BUG_ON(!buffer_locked(bh));
- BUG_ON(!buffer_mapped(bh));
- BUG_ON(!bh->b_end_io);
- BUG_ON(buffer_delay(bh));
- BUG_ON(buffer_unwritten(bh));
-
- /*
- * Only clear out a write error when rewriting
- */
- if (test_set_buffer_req(bh) && (op == REQ_OP_WRITE))
- clear_buffer_write_io_error(bh);
-
- /*
- * from here on down, it's all bio -- do the initial mapping,
- * submit_bio -> generic_make_request may further map this bio around
- */
- bio = bio_alloc(GFP_NOIO, 1);
-
- bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
- bio_set_dev(bio, bh->b_bdev);
- bio->bi_write_hint = write_hint;
-
- bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
- BUG_ON(bio->bi_iter.bi_size != bh->b_size);
-
- bio->bi_end_io = end_bio_bh_io_sync;
- bio->bi_private = bh;
-
- /* Take care of bh's that straddle the end of the device */
- guard_bio_eod(op, bio);
-
- if (buffer_meta(bh))
- op_flags |= REQ_META;
- if (buffer_prio(bh))
- op_flags |= REQ_PRIO;
- bio_set_op_attrs(bio, op, op_flags);
-
- return bio;
-}
-
static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
enum rw_hint write_hint, struct writeback_control *wbc)
{
struct bio *bio;
- bio = create_bh_bio(op, op_flags, bh, write_hint);
+ bio = create_bh_bio(op, op_flags, bh, write_hint, NULL);
if (wbc) {
wbc_init_bio(wbc, bio);
@@ -3092,7 +3152,7 @@ int submit_bh_blkcg_css(int op, int op_flags, struct buffer_head *bh,
{
struct bio *bio;
- bio = create_bh_bio(op, op_flags, bh, 0);
+ bio = create_bh_bio(op, op_flags, bh, 0, NULL);
bio_associate_blkcg(bio, blkcg_css);
submit_bio(bio);
return 0;
@@ -3101,11 +3161,7 @@ EXPORT_SYMBOL(submit_bh_blkcg_css);
int submit_bh(int op, int op_flags, struct buffer_head *bh)
{
- struct bio *bio;
-
- bio = create_bh_bio(op, op_flags, bh, 0);
- submit_bio(bio);
- return 0;
+ return submit_bh_post_process(op, op_flags, bh, NULL);
}
EXPORT_SYMBOL(submit_bh);
diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c
index 32288c3..aba22f7 100644
--- a/fs/crypto/bio.c
+++ b/fs/crypto/bio.c
@@ -24,6 +24,7 @@
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/namei.h>
+#include <linux/buffer_head.h>
#include "fscrypt_private.h"
static void __fscrypt_decrypt_bio(struct bio *bio, bool done)
@@ -59,7 +60,7 @@ void fscrypt_decrypt_bio(struct bio *bio)
}
EXPORT_SYMBOL(fscrypt_decrypt_bio);
-static void completion_pages(struct work_struct *work)
+void fscrypt_complete_pages(struct work_struct *work)
{
struct fscrypt_ctx *ctx =
container_of(work, struct fscrypt_ctx, r.work);
@@ -69,15 +70,103 @@ static void completion_pages(struct work_struct *work)
fscrypt_release_ctx(ctx);
bio_put(bio);
}
+EXPORT_SYMBOL(fscrypt_complete_pages);
-void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, struct bio *bio)
+void fscrypt_complete_block(struct work_struct *work)
{
- INIT_WORK(&ctx->r.work, completion_pages);
+ struct fscrypt_ctx *ctx =
+ container_of(work, struct fscrypt_ctx, r.work);
+ struct buffer_head *bh;
+ struct bio *bio;
+ struct bio_vec *bv;
+ struct page *page;
+ struct inode *inode;
+ u64 blk_nr;
+ int ret;
+
+ bio = ctx->r.bio;
+ WARN_ON(bio->bi_vcnt != 1);
+
+ bv = bio->bi_io_vec;
+ page = bv->bv_page;
+ inode = page->mapping->host;
+
+ WARN_ON(bv->bv_len != i_blocksize(inode));
+
+ blk_nr = page->index << (PAGE_SHIFT - inode->i_blkbits);
+ blk_nr += bv->bv_offset >> inode->i_blkbits;
+
+ bh = ctx->r.bh;
+
+ ret = fscrypt_decrypt_page(inode, page, bv->bv_len,
+ bv->bv_offset, blk_nr);
+
+ bh->b_end_io(bh, !ret);
+
+ fscrypt_release_ctx(ctx);
+ bio_put(bio);
+}
+EXPORT_SYMBOL(fscrypt_complete_block);
+
+bool fscrypt_bio_encrypted(struct bio *bio)
+{
+ struct address_space *mapping;
+ struct inode *inode;
+ struct page *page;
+
+ if (bio_op(bio) == REQ_OP_READ && bio->bi_vcnt) {
+ page = bio->bi_io_vec->bv_page;
+
+ if (!PageSwapCache(page)) {
+ mapping = page_mapping(page);
+ if (mapping) {
+ inode = mapping->host;
+
+ if (IS_ENCRYPTED(inode) &&
+ S_ISREG(inode->i_mode))
+ return true;
+ }
+ }
+ }
+
+ return false;
+}
+EXPORT_SYMBOL(fscrypt_bio_encrypted);
+
+void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, struct bio *bio,
+ void (*process_bio)(struct work_struct *))
+{
+ BUG_ON(!process_bio);
+ INIT_WORK(&ctx->r.work, process_bio);
ctx->r.bio = bio;
fscrypt_enqueue_decrypt_work(&ctx->r.work);
}
EXPORT_SYMBOL(fscrypt_enqueue_decrypt_bio);
+post_process_read_t *fscrypt_get_post_process(struct fscrypt_ctx *ctx)
+{
+ return &(ctx->r.post_process);
+}
+EXPORT_SYMBOL(fscrypt_get_post_process);
+
+void fscrypt_set_post_process(struct fscrypt_ctx *ctx,
+ post_process_read_t *post_process)
+{
+ ctx->r.post_process = *post_process;
+}
+
+struct buffer_head *fscrypt_get_bh(struct fscrypt_ctx *ctx)
+{
+ return ctx->r.bh;
+}
+EXPORT_SYMBOL(fscrypt_get_bh);
+
+void fscrypt_set_bh(struct fscrypt_ctx *ctx, struct buffer_head *bh)
+{
+ ctx->r.bh = bh;
+}
+EXPORT_SYMBOL(fscrypt_set_bh);
+
void fscrypt_pullback_bio_page(struct page **page, bool restore)
{
struct fscrypt_ctx *ctx;
diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
index 27509b1..2148651 100644
--- a/fs/crypto/crypto.c
+++ b/fs/crypto/crypto.c
@@ -127,6 +127,8 @@ struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *inode, gfp_t gfp_flags)
ctx->flags |= FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
} else {
ctx->flags &= ~FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
+ ctx->r.post_process.process_block = NULL;
+ ctx->r.post_process.process_pages = NULL;
}
ctx->flags &= ~FS_CTX_HAS_BOUNCE_BUFFER_FL;
return ctx;
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 1329b69..0a91f87 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -869,14 +869,14 @@ static int ext2_writepage(struct page *page, struct writeback_control *wbc)
static int ext2_readpage(struct file *file, struct page *page)
{
- return mpage_readpage(page, ext2_get_block);
+ return mpage_readpage(page, ext2_get_block, NULL);
}
static int
ext2_readpages(struct file *file, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages)
{
- return mpage_readpages(mapping, pages, nr_pages, ext2_get_block);
+ return mpage_readpages(mapping, pages, nr_pages, ext2_get_block, NULL);
}
static int
diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
index 8fdfcd3..7c38803 100644
--- a/fs/ext4/Makefile
+++ b/fs/ext4/Makefile
@@ -8,7 +8,7 @@ obj-$(CONFIG_EXT4_FS) += ext4.o
ext4-y := balloc.o bitmap.o block_validity.o dir.o ext4_jbd2.o extents.o \
extents_status.o file.o fsmap.o fsync.o hash.o ialloc.o \
indirect.o inline.o inode.o ioctl.o mballoc.o migrate.o \
- mmp.o move_extent.o namei.o page-io.o readpage.o resize.o \
+ mmp.o move_extent.o namei.o page-io.o resize.o \
super.o symlink.o sysfs.o xattr.o xattr_trusted.o xattr_user.o
ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index fbc89d9..5ae3c7b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3337,6 +3337,10 @@ static int ext4_readpage(struct file *file, struct page *page)
{
int ret = -EAGAIN;
struct inode *inode = page->mapping->host;
+ post_process_read_t post_process = {
+ .process_block = fscrypt_complete_block,
+ .process_pages = fscrypt_complete_pages,
+ };
trace_ext4_readpage(page);
@@ -3344,7 +3348,7 @@ static int ext4_readpage(struct file *file, struct page *page)
ret = ext4_readpage_inline(inode, page);
if (ret == -EAGAIN)
- return ext4_mpage_readpages(page->mapping, NULL, page, 1);
+ return mpage_readpage(page, ext4_get_block, &post_process);
return ret;
}
@@ -3354,12 +3358,17 @@ ext4_readpages(struct file *file, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages)
{
struct inode *inode = mapping->host;
+ post_process_read_t post_process = {
+ .process_block = fscrypt_complete_block,
+ .process_pages = fscrypt_complete_pages,
+ };
/* If the file has inline data, no need to do readpages. */
if (ext4_has_inline_data(inode))
return 0;
- return ext4_mpage_readpages(mapping, pages, NULL, nr_pages);
+ return mpage_readpages(mapping, pages, nr_pages, ext4_get_block,
+ &post_process);
}
static void ext4_invalidatepage(struct page *page, unsigned int offset,
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
deleted file mode 100644
index 19b87a8..0000000
--- a/fs/ext4/readpage.c
+++ /dev/null
@@ -1,294 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * linux/fs/ext4/readpage.c
- *
- * Copyright (C) 2002, Linus Torvalds.
- * Copyright (C) 2015, Google, Inc.
- *
- * This was originally taken from fs/mpage.c
- *
- * The intent is the ext4_mpage_readpages() function here is intended
- * to replace mpage_readpages() in the general case, not just for
- * encrypted files. It has some limitations (see below), where it
- * will fall back to read_block_full_page(), but these limitations
- * should only be hit when page_size != block_size.
- *
- * This will allow us to attach a callback function to support ext4
- * encryption.
- *
- * If anything unusual happens, such as:
- *
- * - encountering a page which has buffers
- * - encountering a page which has a non-hole after a hole
- * - encountering a page with non-contiguous blocks
- *
- * then this code just gives up and calls the buffer_head-based read function.
- * It does handle a page which has holes at the end - that is a common case:
- * the end-of-file on blocksize < PAGE_SIZE setups.
- *
- */
-
-#include <linux/kernel.h>
-#include <linux/export.h>
-#include <linux/mm.h>
-#include <linux/kdev_t.h>
-#include <linux/gfp.h>
-#include <linux/bio.h>
-#include <linux/fs.h>
-#include <linux/buffer_head.h>
-#include <linux/blkdev.h>
-#include <linux/highmem.h>
-#include <linux/prefetch.h>
-#include <linux/mpage.h>
-#include <linux/writeback.h>
-#include <linux/backing-dev.h>
-#include <linux/pagevec.h>
-#include <linux/cleancache.h>
-
-#include "ext4.h"
-
-static inline bool ext4_bio_encrypted(struct bio *bio)
-{
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
- return unlikely(bio->bi_private != NULL);
-#else
- return false;
-#endif
-}
-
-/*
- * I/O completion handler for multipage BIOs.
- *
- * The mpage code never puts partial pages into a BIO (except for end-of-file).
- * If a page does not map to a contiguous run of blocks then it simply falls
- * back to block_read_full_page().
- *
- * Why is this? If a page's completion depends on a number of different BIOs
- * which can complete in any order (or at the same time) then determining the
- * status of that page is hard. See end_buffer_async_read() for the details.
- * There is no point in duplicating all that complexity.
- */
-static void mpage_end_io(struct bio *bio)
-{
- struct bio_vec *bv;
- int i;
-
- if (ext4_bio_encrypted(bio)) {
- if (bio->bi_status) {
- fscrypt_release_ctx(bio->bi_private);
- } else {
- fscrypt_enqueue_decrypt_bio(bio->bi_private, bio);
- return;
- }
- }
- bio_for_each_segment_all(bv, bio, i) {
- struct page *page = bv->bv_page;
-
- if (!bio->bi_status) {
- SetPageUptodate(page);
- } else {
- ClearPageUptodate(page);
- SetPageError(page);
- }
- unlock_page(page);
- }
-
- bio_put(bio);
-}
-
-int ext4_mpage_readpages(struct address_space *mapping,
- struct list_head *pages, struct page *page,
- unsigned nr_pages)
-{
- struct bio *bio = NULL;
- sector_t last_block_in_bio = 0;
-
- struct inode *inode = mapping->host;
- const unsigned blkbits = inode->i_blkbits;
- const unsigned blocks_per_page = PAGE_SIZE >> blkbits;
- const unsigned blocksize = 1 << blkbits;
- sector_t block_in_file;
- sector_t last_block;
- sector_t last_block_in_file;
- sector_t blocks[MAX_BUF_PER_PAGE];
- unsigned page_block;
- struct block_device *bdev = inode->i_sb->s_bdev;
- int length;
- unsigned relative_block = 0;
- struct ext4_map_blocks map;
-
- map.m_pblk = 0;
- map.m_lblk = 0;
- map.m_len = 0;
- map.m_flags = 0;
-
- for (; nr_pages; nr_pages--) {
- int fully_mapped = 1;
- unsigned first_hole = blocks_per_page;
-
- prefetchw(&page->flags);
- if (pages) {
- page = list_entry(pages->prev, struct page, lru);
- list_del(&page->lru);
- if (add_to_page_cache_lru(page, mapping, page->index,
- readahead_gfp_mask(mapping)))
- goto next_page;
- }
-
- if (page_has_buffers(page))
- goto confused;
-
- block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits);
- last_block = block_in_file + nr_pages * blocks_per_page;
- last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits;
- if (last_block > last_block_in_file)
- last_block = last_block_in_file;
- page_block = 0;
-
- /*
- * Map blocks using the previous result first.
- */
- if ((map.m_flags & EXT4_MAP_MAPPED) &&
- block_in_file > map.m_lblk &&
- block_in_file < (map.m_lblk + map.m_len)) {
- unsigned map_offset = block_in_file - map.m_lblk;
- unsigned last = map.m_len - map_offset;
-
- for (relative_block = 0; ; relative_block++) {
- if (relative_block == last) {
- /* needed? */
- map.m_flags &= ~EXT4_MAP_MAPPED;
- break;
- }
- if (page_block == blocks_per_page)
- break;
- blocks[page_block] = map.m_pblk + map_offset +
- relative_block;
- page_block++;
- block_in_file++;
- }
- }
-
- /*
- * Then do more ext4_map_blocks() calls until we are
- * done with this page.
- */
- while (page_block < blocks_per_page) {
- if (block_in_file < last_block) {
- map.m_lblk = block_in_file;
- map.m_len = last_block - block_in_file;
-
- if (ext4_map_blocks(NULL, inode, &map, 0) < 0) {
- set_error_page:
- SetPageError(page);
- zero_user_segment(page, 0,
- PAGE_SIZE);
- unlock_page(page);
- goto next_page;
- }
- }
- if ((map.m_flags & EXT4_MAP_MAPPED) == 0) {
- fully_mapped = 0;
- if (first_hole == blocks_per_page)
- first_hole = page_block;
- page_block++;
- block_in_file++;
- continue;
- }
- if (first_hole != blocks_per_page)
- goto confused; /* hole -> non-hole */
-
- /* Contiguous blocks? */
- if (page_block && blocks[page_block-1] != map.m_pblk-1)
- goto confused;
- for (relative_block = 0; ; relative_block++) {
- if (relative_block == map.m_len) {
- /* needed? */
- map.m_flags &= ~EXT4_MAP_MAPPED;
- break;
- } else if (page_block == blocks_per_page)
- break;
- blocks[page_block] = map.m_pblk+relative_block;
- page_block++;
- block_in_file++;
- }
- }
- if (first_hole != blocks_per_page) {
- zero_user_segment(page, first_hole << blkbits,
- PAGE_SIZE);
- if (first_hole == 0) {
- SetPageUptodate(page);
- unlock_page(page);
- goto next_page;
- }
- } else if (fully_mapped) {
- SetPageMappedToDisk(page);
- }
- if (fully_mapped && blocks_per_page == 1 &&
- !PageUptodate(page) && cleancache_get_page(page) == 0) {
- SetPageUptodate(page);
- goto confused;
- }
-
- /*
- * This page will go to BIO. Do we need to send this
- * BIO off first?
- */
- if (bio && (last_block_in_bio != blocks[0] - 1)) {
- submit_and_realloc:
- submit_bio(bio);
- bio = NULL;
- }
- if (bio == NULL) {
- struct fscrypt_ctx *ctx = NULL;
-
- if (ext4_encrypted_inode(inode) &&
- S_ISREG(inode->i_mode)) {
- ctx = fscrypt_get_ctx(inode, GFP_NOFS);
- if (IS_ERR(ctx))
- goto set_error_page;
- }
- bio = bio_alloc(GFP_KERNEL,
- min_t(int, nr_pages, BIO_MAX_PAGES));
- if (!bio) {
- if (ctx)
- fscrypt_release_ctx(ctx);
- goto set_error_page;
- }
- bio_set_dev(bio, bdev);
- bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9);
- bio->bi_end_io = mpage_end_io;
- bio->bi_private = ctx;
- bio_set_op_attrs(bio, REQ_OP_READ, 0);
- }
-
- length = first_hole << blkbits;
- if (bio_add_page(bio, page, length, 0) < length)
- goto submit_and_realloc;
-
- if (((map.m_flags & EXT4_MAP_BOUNDARY) &&
- (relative_block == map.m_len)) ||
- (first_hole != blocks_per_page)) {
- submit_bio(bio);
- bio = NULL;
- } else
- last_block_in_bio = blocks[blocks_per_page - 1];
- goto next_page;
- confused:
- if (bio) {
- submit_bio(bio);
- bio = NULL;
- }
- if (!PageUptodate(page))
- block_read_full_page(page, ext4_get_block);
- else
- unlock_page(page);
- next_page:
- if (pages)
- put_page(page);
- }
- BUG_ON(pages && !list_empty(pages));
- if (bio)
- submit_bio(bio);
- return 0;
-}
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index ffbbf05..ee1ddc4f 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -194,13 +194,13 @@ static int fat_writepages(struct address_space *mapping,
static int fat_readpage(struct file *file, struct page *page)
{
- return mpage_readpage(page, fat_get_block);
+ return mpage_readpage(page, fat_get_block, NULL);
}
static int fat_readpages(struct file *file, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages)
{
- return mpage_readpages(mapping, pages, nr_pages, fat_get_block);
+ return mpage_readpages(mapping, pages, nr_pages, fat_get_block, NULL);
}
static void fat_write_failed(struct address_space *mapping, loff_t to)
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index ec3fba7..60df56f 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -1173,13 +1173,14 @@ struct buffer_head *isofs_bread(struct inode *inode, sector_t block)
static int isofs_readpage(struct file *file, struct page *page)
{
- return mpage_readpage(page, isofs_get_block);
+ return mpage_readpage(page, isofs_get_block, NULL);
}
static int isofs_readpages(struct file *file, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages)
{
- return mpage_readpages(mapping, pages, nr_pages, isofs_get_block);
+ return mpage_readpages(mapping, pages, nr_pages, isofs_get_block,
+ NULL);
}
static sector_t _isofs_bmap(struct address_space *mapping, sector_t block)
diff --git a/fs/mpage.c b/fs/mpage.c
index b7e7f57..c88fdd4 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -30,6 +30,8 @@
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
#include <linux/cleancache.h>
+#define __FS_HAS_ENCRYPTION IS_ENABLED(CONFIG_EXT4_FS_ENCRYPTION)
+#include <linux/fscrypt.h>
#include "internal.h"
/*
@@ -46,9 +48,24 @@
*/
static void mpage_end_io(struct bio *bio)
{
+ post_process_read_t *post_process;
+ struct fscrypt_ctx *ctx;
struct bio_vec *bv;
int i;
+ if (fscrypt_bio_encrypted(bio)) {
+ ctx = bio->bi_private;
+ post_process = fscrypt_get_post_process(ctx);
+
+ if (bio->bi_status || post_process->process_pages == NULL) {
+ fscrypt_release_ctx(ctx);
+ } else {
+ fscrypt_enqueue_decrypt_bio(ctx, bio,
+ post_process->process_pages);
+ return;
+ }
+ }
+
bio_for_each_segment_all(bv, bio, i) {
struct page *page = bv->bv_page;
page_endio(page, op_is_write(bio_op(bio)),
@@ -146,7 +163,7 @@ static struct bio *
do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages,
sector_t *last_block_in_bio, struct buffer_head *map_bh,
unsigned long *first_logical_block, get_block_t get_block,
- gfp_t gfp)
+ post_process_read_t *post_process, gfp_t gfp)
{
struct inode *inode = page->mapping->host;
const unsigned blkbits = inode->i_blkbits;
@@ -278,15 +295,26 @@ do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages,
alloc_new:
if (bio == NULL) {
- if (first_hole == blocks_per_page) {
+ struct fscrypt_ctx *ctx = NULL;
+
+ if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode)) {
+ ctx = fscrypt_get_ctx(inode, gfp & GFP_KERNEL);
+ if (IS_ERR(ctx))
+ goto confused;
+ fscrypt_set_post_process(ctx, post_process);
+ } else if (first_hole == blocks_per_page) {
if (!bdev_read_page(bdev, blocks[0] << (blkbits - 9),
page))
goto out;
}
bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
min_t(int, nr_pages, BIO_MAX_PAGES), gfp);
- if (bio == NULL)
+ if (bio == NULL) {
+ if (ctx)
+ fscrypt_release_ctx(ctx);
goto confused;
+ }
+ bio->bi_private = ctx;
}
length = first_hole << blkbits;
@@ -309,7 +337,7 @@ do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages,
if (bio)
bio = mpage_bio_submit(REQ_OP_READ, 0, bio);
if (!PageUptodate(page))
- block_read_full_page(page, get_block);
+ block_read_full_page(page, get_block, post_process);
else
unlock_page(page);
goto out;
@@ -361,7 +389,8 @@ do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages,
*/
int
mpage_readpages(struct address_space *mapping, struct list_head *pages,
- unsigned nr_pages, get_block_t get_block)
+ unsigned nr_pages, get_block_t get_block,
+ post_process_read_t *post_process)
{
struct bio *bio = NULL;
unsigned page_idx;
@@ -384,7 +413,8 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages,
nr_pages - page_idx,
&last_block_in_bio, &map_bh,
&first_logical_block,
- get_block, gfp);
+ get_block, post_process,
+ gfp);
}
put_page(page);
}
@@ -398,7 +428,8 @@ EXPORT_SYMBOL(mpage_readpages);
/*
* This isn't called much at all
*/
-int mpage_readpage(struct page *page, get_block_t get_block)
+int mpage_readpage(struct page *page, get_block_t get_block,
+ post_process_read_t *post_process)
{
struct bio *bio = NULL;
sector_t last_block_in_bio = 0;
@@ -409,7 +440,8 @@ int mpage_readpage(struct page *page, get_block_t get_block)
map_bh.b_state = 0;
map_bh.b_size = 0;
bio = do_mpage_readpage(bio, page, 1, &last_block_in_bio,
- &map_bh, &first_logical_block, get_block, gfp);
+ &map_bh, &first_logical_block, get_block,
+ post_process, gfp);
if (bio)
mpage_bio_submit(REQ_OP_READ, 0, bio);
return 0;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 0ab824f..74591b8 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1405,7 +1405,7 @@ xfs_vm_readpage(
struct page *page)
{
trace_xfs_vm_readpage(page->mapping->host, 1);
- return mpage_readpage(page, xfs_get_blocks);
+ return mpage_readpage(page, xfs_get_blocks, NULL);
}
STATIC int
@@ -1416,7 +1416,7 @@ xfs_vm_readpages(
unsigned nr_pages)
{
trace_xfs_vm_readpages(mapping->host, nr_pages);
- return mpage_readpages(mapping, pages, nr_pages, xfs_get_blocks);
+ return mpage_readpages(mapping, pages, nr_pages, xfs_get_blocks, NULL);
}
/*
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index c2fbd97..3718c20 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -224,7 +224,7 @@ int block_write_full_page(struct page *page, get_block_t *get_block,
int __block_write_full_page(struct inode *inode, struct page *page,
get_block_t *get_block, struct writeback_control *wbc,
bh_end_io_t *handler);
-int block_read_full_page(struct page*, get_block_t*);
+int block_read_full_page(struct page*, get_block_t*, post_process_read_t*);
int block_is_partially_uptodate(struct page *page, unsigned long from,
unsigned long count);
int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0eedf74..40e3537 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -83,6 +83,10 @@ typedef int (get_block_t)(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
ssize_t bytes, void *private);
+typedef struct post_process_read {
+ void (*process_block)(struct work_struct *);
+ void (*process_pages)(struct work_struct *);
+} post_process_read_t;
#define MAY_EXEC 0x00000001
#define MAY_WRITE 0x00000002
diff --git a/include/linux/fscrypt_notsupp.h b/include/linux/fscrypt_notsupp.h
index 9770be37..ceac8c8 100644
--- a/include/linux/fscrypt_notsupp.h
+++ b/include/linux/fscrypt_notsupp.h
@@ -168,9 +168,44 @@ static inline void fscrypt_decrypt_bio(struct bio *bio)
{
}
+static inline void fscrypt_complete_block(struct work_struct *work)
+{
+}
+
+static inline void fscrypt_complete_pages(struct work_struct *work)
+{
+}
+
static inline void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx,
- struct bio *bio)
+ struct bio *bio,
+ void (*process_bio)(struct work_struct *))
+{
+}
+
+static inline bool fscrypt_bio_encrypted(struct bio *bio)
+{
+ return false;
+}
+
+static inline post_process_read_t *
+fscrypt_get_post_process(struct fscrypt_ctx *ctx)
+{
+ return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline void
+fscrypt_set_post_process(struct fscrypt_ctx *ctx, post_process_read_t *post_process)
+{
+}
+
+static inline void
+fscrypt_set_bh(struct fscrypt_ctx *ctx, struct buffer_head *bh)
+{
+}
+
+static inline struct buffer_head *fscrypt_get_bh(struct fscrypt_ctx *ctx)
{
+ return ERR_PTR(-EOPNOTSUPP);
}
static inline void fscrypt_pullback_bio_page(struct page **page, bool restore)
diff --git a/include/linux/fscrypt_supp.h b/include/linux/fscrypt_supp.h
index 2c9a86a..b946eca 100644
--- a/include/linux/fscrypt_supp.h
+++ b/include/linux/fscrypt_supp.h
@@ -39,8 +39,10 @@ struct fscrypt_ctx {
struct page *control_page; /* Original page */
} w;
struct {
+ struct buffer_head *bh;
struct bio *bio;
struct work_struct work;
+ post_process_read_t post_process;
} r;
struct list_head free_list; /* Free list */
};
@@ -190,8 +192,17 @@ static inline bool fscrypt_match_name(const struct fscrypt_name *fname,
/* bio.c */
extern void fscrypt_decrypt_bio(struct bio *);
+extern void fscrypt_complete_pages(struct work_struct *work);
+extern void fscrypt_complete_block(struct work_struct *work);
extern void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx,
- struct bio *bio);
+ struct bio *bio,
+ void (*process_bio)(struct work_struct *));
+extern post_process_read_t *fscrypt_get_post_process(struct fscrypt_ctx *ctx);
+extern void fscrypt_set_post_process(struct fscrypt_ctx *ctx,
+ post_process_read_t *post_process);
+extern struct buffer_head *fscrypt_get_bh(struct fscrypt_ctx *ctx);
+extern void fscrypt_set_bh(struct fscrypt_ctx *ctx, struct buffer_head *bh);
+extern bool fscrypt_bio_encrypted(struct bio *bio);
extern void fscrypt_pullback_bio_page(struct page **, bool);
extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t,
unsigned int);
diff --git a/include/linux/mpage.h b/include/linux/mpage.h
index 001f1fc..da2526a 100644
--- a/include/linux/mpage.h
+++ b/include/linux/mpage.h
@@ -15,8 +15,10 @@
struct writeback_control;
int mpage_readpages(struct address_space *mapping, struct list_head *pages,
- unsigned nr_pages, get_block_t get_block);
-int mpage_readpage(struct page *page, get_block_t get_block);
+ unsigned nr_pages, get_block_t get_block,
+ post_process_read_t *post_process);
+int mpage_readpage(struct page *page, get_block_t get_block,
+ post_process_read_t *post_process);
int mpage_writepages(struct address_space *mapping,
struct writeback_control *wbc, get_block_t get_block);
int mpage_writepage(struct page *page, get_block_t *get_block,
--
2.9.5
Powered by blists - more mailing lists