Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "This merge request includes the dax-4.0-iomap-pmd branch which is
  needed for both ext4 and xfs dax changes to use iomap for DAX. It also
  includes the fscrypt branch which is needed for ubifs encryption work
  as well as ext4 encryption and fscrypt cleanups.

  Lots of cleanups and bug fixes, especially making sure ext4 is robust
  against maliciously corrupted file systems --- especially maliciously
  corrupted xattr blocks and a maliciously corrupted superblock. Also
  fix ext4 support for 64k block sizes so it works well on ppcle. Fixed
  mbcache so we don't miss some common xattr blocks that can be merged"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (86 commits)
  dax: Fix sleep in atomic contex in grab_mapping_entry()
  fscrypt: Rename FS_WRITE_PATH_FL to FS_CTX_HAS_BOUNCE_BUFFER_FL
  fscrypt: Delay bounce page pool allocation until needed
  fscrypt: Cleanup page locking requirements for fscrypt_{decrypt,encrypt}_page()
  fscrypt: Cleanup fscrypt_{decrypt,encrypt}_page()
  fscrypt: Never allocate fscrypt_ctx on in-place encryption
  fscrypt: Use correct index in decrypt path.
  fscrypt: move the policy flags and encryption mode definitions to uapi header
  fscrypt: move non-public structures and constants to fscrypt_private.h
  fscrypt: unexport fscrypt_initialize()
  fscrypt: rename get_crypt_info() to fscrypt_get_crypt_info()
  fscrypto: move ioctl processing more fully into common code
  fscrypto: remove unneeded Kconfig dependencies
  MAINTAINERS: fscrypto: recommend linux-fsdevel for fscrypto patches
  ext4: do not perform data journaling when data is encrypted
  ext4: return -ENOMEM instead of success
  ext4: reject inodes with negative size
  ext4: remove another test in ext4_alloc_file_blocks()
  Documentation: fix description of ext4's block_validity mount option
  ext4: fix checks for data=ordered and journal_async_commit options
  ...

Documentation/filesystems/dax.txt

@@ -58,22 +58,22 @@ Implementation Tips for Filesystem Writers
 Filesystem support consists of
 - adding support to mark inodes as being DAX by setting the S_DAX flag in
   i_flags
-- implementing the direct_IO address space operation, and calling
-  dax_do_io() instead of blockdev_direct_IO() if S_DAX is set
+- implementing ->read_iter and ->write_iter operations which use dax_iomap_rw()
+  when inode has S_DAX flag set
 - implementing an mmap file operation for DAX files which sets the
   VM_MIXEDMAP and VM_HUGEPAGE flags on the VMA, and setting the vm_ops to
-  include handlers for fault, pmd_fault and page_mkwrite (which should
-  probably call dax_fault(), dax_pmd_fault() and dax_mkwrite(), passing the
-  appropriate get_block() callback)
-- calling dax_truncate_page() instead of block_truncate_page() for DAX files
-- calling dax_zero_page_range() instead of zero_user() for DAX files
+  include handlers for fault, pmd_fault, page_mkwrite, pfn_mkwrite. These
+  handlers should probably call dax_iomap_fault() (for fault and page_mkwrite
+  handlers), dax_iomap_pmd_fault(), dax_pfn_mkwrite() passing the appropriate
+  iomap operations.
+- calling iomap_zero_range() passing appropriate iomap operations instead of
+  block_truncate_page() for DAX files
 - ensuring that there is sufficient locking between reads, writes,
   truncates and page faults
 
-The get_block() callback passed to the DAX functions may return
-uninitialised extents.  If it does, it must ensure that simultaneous
-calls to get_block() (for example by a page-fault racing with a read()
-or a write()) work correctly.
+The iomap handlers for allocating blocks must make sure that allocated blocks
+are zeroed out and converted to written extents before being returned to avoid
+exposure of uninitialized data through mmap.
 
 These filesystems may be used for inspiration:
 - ext2: see Documentation/filesystems/ext2.txt

Documentation/filesystems/ext4.txt

@@ -351,14 +351,13 @@ nouid32			Disables 32-bit UIDs and GIDs.  This is for
 			interoperability  with  older kernels which only
 			store and expect 16-bit values.
 
-block_validity		This options allows to enables/disables the in-kernel
+block_validity(*)	These options enable or disable the in-kernel
 noblock_validity	facility for tracking filesystem metadata blocks
-			within internal data structures. This allows multi-
-			block allocator and other routines to quickly locate
-			extents which might overlap with filesystem metadata
-			blocks. This option is intended for debugging
-			purposes and since it negatively affects the
-			performance, it is off by default.
+			within internal data structures.  This allows multi-
+			block allocator and other routines to notice
+			bugs or corrupted allocation bitmaps which cause
+			blocks to be allocated which overlap with
+			filesystem metadata blocks.
 
 dioread_lock		Controls whether or not ext4 should use the DIO read
 dioread_nolock		locking. If the dioread_nolock option is specified

MAINTAINERS

@@ -5240,6 +5240,7 @@ F:	include/linux/fscache*.h
 FS-CRYPTO: FILE SYSTEM LEVEL ENCRYPTION SUPPORT
 M:	Theodore Y. Ts'o <tytso@mit.edu>
 M:	Jaegeuk Kim <jaegeuk@kernel.org>
+L:	linux-fsdevel@vger.kernel.org
 S:	Supported
 F:	fs/crypto/
 F:	include/linux/fscrypto.h

fs/Kconfig

@@ -55,7 +55,6 @@ config FS_DAX_PMD
 	depends on FS_DAX
 	depends on ZONE_DEVICE
 	depends on TRANSPARENT_HUGEPAGE
-	depends on BROKEN
 
 endif # BLOCK
 

fs/crypto/Kconfig

@@ -8,9 +8,7 @@ config FS_ENCRYPTION
 	select CRYPTO_XTS
 	select CRYPTO_CTS
 	select CRYPTO_CTR
-	select CRYPTO_SHA256
 	select KEYS
-	select ENCRYPTED_KEYS
 	help
 	  Enable encryption of files and directories.  This
 	  feature is similar to ecryptfs, but it is more memory

fs/crypto/crypto.c

@@ -27,7 +27,7 @@
 #include <linux/bio.h>
 #include <linux/dcache.h>
 #include <linux/namei.h>
-#include <linux/fscrypto.h>
+#include "fscrypt_private.h"
 
 static unsigned int num_prealloc_crypto_pages = 32;
 static unsigned int num_prealloc_crypto_ctxs = 128;
@@ -63,7 +63,7 @@ void fscrypt_release_ctx(struct fscrypt_ctx *ctx)
 {
 	unsigned long flags;
 
-	if (ctx->flags & FS_WRITE_PATH_FL && ctx->w.bounce_page) {
+	if (ctx->flags & FS_CTX_HAS_BOUNCE_BUFFER_FL && ctx->w.bounce_page) {
 		mempool_free(ctx->w.bounce_page, fscrypt_bounce_page_pool);
 		ctx->w.bounce_page = NULL;
 	}
@@ -88,7 +88,7 @@ EXPORT_SYMBOL(fscrypt_release_ctx);
  * Return: An allocated and initialized encryption context on success; error
  * value or NULL otherwise.
  */
-struct fscrypt_ctx *fscrypt_get_ctx(struct inode *inode, gfp_t gfp_flags)
+struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *inode, gfp_t gfp_flags)
 {
 	struct fscrypt_ctx *ctx = NULL;
 	struct fscrypt_info *ci = inode->i_crypt_info;
@@ -121,7 +121,7 @@ struct fscrypt_ctx *fscrypt_get_ctx(struct inode *inode, gfp_t gfp_flags)
 	} else {
 		ctx->flags &= ~FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
 	}
-	ctx->flags &= ~FS_WRITE_PATH_FL;
+	ctx->flags &= ~FS_CTX_HAS_BOUNCE_BUFFER_FL;
 	return ctx;
 }
 EXPORT_SYMBOL(fscrypt_get_ctx);
@@ -146,9 +146,10 @@ typedef enum {
 	FS_ENCRYPT,
 } fscrypt_direction_t;
 
-static int do_page_crypto(struct inode *inode,
-			fscrypt_direction_t rw, pgoff_t index,
+static int do_page_crypto(const struct inode *inode,
+			fscrypt_direction_t rw, u64 lblk_num,
 			struct page *src_page, struct page *dest_page,
+			unsigned int len, unsigned int offs,
 			gfp_t gfp_flags)
 {
 	struct {
@@ -162,6 +163,8 @@ static int do_page_crypto(struct inode *inode,
 	struct crypto_skcipher *tfm = ci->ci_ctfm;
 	int res = 0;
 
+	BUG_ON(len == 0);
+
 	req = skcipher_request_alloc(tfm, gfp_flags);
 	if (!req) {
 		printk_ratelimited(KERN_ERR
@@ -175,14 +178,14 @@ static int do_page_crypto(struct inode *inode,
 		page_crypt_complete, &ecr);
 
 	BUILD_BUG_ON(sizeof(xts_tweak) != FS_XTS_TWEAK_SIZE);
-	xts_tweak.index = cpu_to_le64(index);
+	xts_tweak.index = cpu_to_le64(lblk_num);
 	memset(xts_tweak.padding, 0, sizeof(xts_tweak.padding));
 
 	sg_init_table(&dst, 1);
-	sg_set_page(&dst, dest_page, PAGE_SIZE, 0);
+	sg_set_page(&dst, dest_page, len, offs);
 	sg_init_table(&src, 1);
-	sg_set_page(&src, src_page, PAGE_SIZE, 0);
-	skcipher_request_set_crypt(req, &src, &dst, PAGE_SIZE, &xts_tweak);
+	sg_set_page(&src, src_page, len, offs);
+	skcipher_request_set_crypt(req, &src, &dst, len, &xts_tweak);
 	if (rw == FS_DECRYPT)
 		res = crypto_skcipher_decrypt(req);
 	else
@@ -207,34 +210,66 @@ static struct page *alloc_bounce_page(struct fscrypt_ctx *ctx, gfp_t gfp_flags)
 	ctx->w.bounce_page = mempool_alloc(fscrypt_bounce_page_pool, gfp_flags);
 	if (ctx->w.bounce_page == NULL)
 		return ERR_PTR(-ENOMEM);
-	ctx->flags |= FS_WRITE_PATH_FL;
+	ctx->flags |= FS_CTX_HAS_BOUNCE_BUFFER_FL;
 	return ctx->w.bounce_page;
 }
 
 /**
  * fscypt_encrypt_page() - Encrypts a page
- * @inode:          The inode for which the encryption should take place
- * @plaintext_page: The page to encrypt. Must be locked.
- * @gfp_flags:      The gfp flag for memory allocation
+ * @inode:     The inode for which the encryption should take place
+ * @page:      The page to encrypt. Must be locked for bounce-page
+ *             encryption.
+ * @len:       Length of data to encrypt in @page and encrypted
+ *             data in returned page.
+ * @offs:      Offset of data within @page and returned
+ *             page holding encrypted data.
+ * @lblk_num:  Logical block number. This must be unique for multiple
+ *             calls with same inode, except when overwriting
+ *             previously written data.
+ * @gfp_flags: The gfp flag for memory allocation
  *
- * Allocates a ciphertext page and encrypts plaintext_page into it using the ctx
- * encryption context.
+ * Encrypts @page using the ctx encryption context. Performs encryption
+ * either in-place or into a newly allocated bounce page.
+ * Called on the page write path.
  *
- * Called on the page write path.  The caller must call
+ * Bounce page allocation is the default.
+ * In this case, the contents of @page are encrypted and stored in an
+ * allocated bounce page. @page has to be locked and the caller must call
  * fscrypt_restore_control_page() on the returned ciphertext page to
  * release the bounce buffer and the encryption context.
  *
- * Return: An allocated page with the encrypted content on success. Else, an
+ * In-place encryption is used by setting the FS_CFLG_OWN_PAGES flag in
+ * fscrypt_operations. Here, the input-page is returned with its content
+ * encrypted.
+ *
+ * Return: A page with the encrypted content on success. Else, an
  * error value or NULL.
  */
-struct page *fscrypt_encrypt_page(struct inode *inode,
-				struct page *plaintext_page, gfp_t gfp_flags)
+struct page *fscrypt_encrypt_page(const struct inode *inode,
+				struct page *page,
+				unsigned int len,
+				unsigned int offs,
+				u64 lblk_num, gfp_t gfp_flags)
+
 {
 	struct fscrypt_ctx *ctx;
-	struct page *ciphertext_page = NULL;
+	struct page *ciphertext_page = page;
 	int err;
 
-	BUG_ON(!PageLocked(plaintext_page));
+	BUG_ON(len % FS_CRYPTO_BLOCK_SIZE != 0);
+
+	if (inode->i_sb->s_cop->flags & FS_CFLG_OWN_PAGES) {
+		/* with inplace-encryption we just encrypt the page */
+		err = do_page_crypto(inode, FS_ENCRYPT, lblk_num,
+					page, ciphertext_page,
+					len, offs, gfp_flags);
+		if (err)
+			return ERR_PTR(err);
+
+		return ciphertext_page;
+	}
+
+	BUG_ON(!PageLocked(page));
 
 	ctx = fscrypt_get_ctx(inode, gfp_flags);
 	if (IS_ERR(ctx))
@@ -245,10 +280,10 @@ struct page *fscrypt_encrypt_page(struct inode *inode,
 	if (IS_ERR(ciphertext_page))
 		goto errout;
 
-	ctx->w.control_page = plaintext_page;
-	err = do_page_crypto(inode, FS_ENCRYPT, plaintext_page->index,
-					plaintext_page, ciphertext_page,
-					gfp_flags);
+	ctx->w.control_page = page;
+	err = do_page_crypto(inode, FS_ENCRYPT, lblk_num,
+					page, ciphertext_page,
+					len, offs, gfp_flags);
 	if (err) {
 		ciphertext_page = ERR_PTR(err);
 		goto errout;
@@ -265,8 +300,13 @@ struct page *fscrypt_encrypt_page(struct inode *inode,
 EXPORT_SYMBOL(fscrypt_encrypt_page);
 
 /**
- * f2crypt_decrypt_page() - Decrypts a page in-place
- * @page: The page to decrypt. Must be locked.
+ * fscrypt_decrypt_page() - Decrypts a page in-place
+ * @inode:     The corresponding inode for the page to decrypt.
+ * @page:      The page to decrypt. Must be locked in case
+ *             it is a writeback page (FS_CFLG_OWN_PAGES unset).
+ * @len:       Number of bytes in @page to be decrypted.
+ * @offs:      Start of data in @page.
+ * @lblk_num:  Logical block number.
  *
  * Decrypts page in-place using the ctx encryption context.
  *
@@ -274,16 +314,18 @@ EXPORT_SYMBOL(fscrypt_encrypt_page);
  *
  * Return: Zero on success, non-zero otherwise.
  */
-int fscrypt_decrypt_page(struct page *page)
+int fscrypt_decrypt_page(const struct inode *inode, struct page *page,
+			unsigned int len, unsigned int offs, u64 lblk_num)
 {
-	BUG_ON(!PageLocked(page));
+	if (!(inode->i_sb->s_cop->flags & FS_CFLG_OWN_PAGES))
+		BUG_ON(!PageLocked(page));
 
-	return do_page_crypto(page->mapping->host,
-			FS_DECRYPT, page->index, page, page, GFP_NOFS);
+	return do_page_crypto(inode, FS_DECRYPT, lblk_num, page, page, len,
+			offs, GFP_NOFS);
 }
 EXPORT_SYMBOL(fscrypt_decrypt_page);
 
-int fscrypt_zeroout_range(struct inode *inode, pgoff_t lblk,
+int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
 				sector_t pblk, unsigned int len)
 {
 	struct fscrypt_ctx *ctx;
@@ -306,7 +348,7 @@ int fscrypt_zeroout_range(struct inode *inode, pgoff_t lblk,
 	while (len--) {
 		err = do_page_crypto(inode, FS_ENCRYPT, lblk,
 					ZERO_PAGE(0), ciphertext_page,
-					GFP_NOFS);
+					PAGE_SIZE, 0, GFP_NOFS);
 		if (err)
 			goto errout;
 
@@ -414,7 +456,8 @@ static void completion_pages(struct work_struct *work)
 
 	bio_for_each_segment_all(bv, bio, i) {
 		struct page *page = bv->bv_page;
-		int ret = fscrypt_decrypt_page(page);
+		int ret = fscrypt_decrypt_page(page->mapping->host, page,
+				PAGE_SIZE, 0, page->index);
 
 		if (ret) {
 			WARN_ON_ONCE(1);
@@ -482,17 +525,22 @@ static void fscrypt_destroy(void)
 
 /**
  * fscrypt_initialize() - allocate major buffers for fs encryption.
+ * @cop_flags:  fscrypt operations flags
  *
  * We only call this when we start accessing encrypted files, since it
  * results in memory getting allocated that wouldn't otherwise be used.
  *
  * Return: Zero on success, non-zero otherwise.
  */
-int fscrypt_initialize(void)
+int fscrypt_initialize(unsigned int cop_flags)
 {
 	int i, res = -ENOMEM;
 
-	if (fscrypt_bounce_page_pool)
+	/*
+	 * No need to allocate a bounce page pool if there already is one or
+	 * this FS won't use it.
+	 */
+	if (cop_flags & FS_CFLG_OWN_PAGES || fscrypt_bounce_page_pool)
 		return 0;
 
 	mutex_lock(&fscrypt_init_mutex);
@@ -521,7 +569,6 @@ int fscrypt_initialize(void)
 	mutex_unlock(&fscrypt_init_mutex);
 	return res;
 }
-EXPORT_SYMBOL(fscrypt_initialize);
 
 /**
  * fscrypt_init() - Set up for fs encryption.

fs/crypto/fname.c

@@ -12,7 +12,7 @@
 
 #include <linux/scatterlist.h>
 #include <linux/ratelimit.h>
-#include <linux/fscrypto.h>
+#include "fscrypt_private.h"
 
 /**
  * fname_crypt_complete() - completion callback for filename crypto
@@ -209,7 +209,7 @@ static int digest_decode(const char *src, int len, char *dst)
 	return cp - dst;
 }
 
-u32 fscrypt_fname_encrypted_size(struct inode *inode, u32 ilen)
+u32 fscrypt_fname_encrypted_size(const struct inode *inode, u32 ilen)
 {
 	int padding = 32;
 	struct fscrypt_info *ci = inode->i_crypt_info;
@@ -227,7 +227,7 @@ EXPORT_SYMBOL(fscrypt_fname_encrypted_size);
  * Allocates an output buffer that is sufficient for the crypto operation
  * specified by the context and the direction.
  */
-int fscrypt_fname_alloc_buffer(struct inode *inode,
+int fscrypt_fname_alloc_buffer(const struct inode *inode,
 				u32 ilen, struct fscrypt_str *crypto_str)
 {
 	unsigned int olen = fscrypt_fname_encrypted_size(inode, ilen);
@@ -350,7 +350,7 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
 		fname->disk_name.len = iname->len;
 		return 0;
 	}
-	ret = get_crypt_info(dir);
+	ret = fscrypt_get_crypt_info(dir);
 	if (ret && ret != -EOPNOTSUPP)
 		return ret;
 

fs/crypto/fscrypt_private.h

+/*
+ * fscrypt_private.h
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This contains encryption key functions.
+ *
+ * Written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar, 2015.
+ */
+
+#ifndef _FSCRYPT_PRIVATE_H
+#define _FSCRYPT_PRIVATE_H
+
+#include <linux/fscrypto.h>
+
+#define FS_FNAME_CRYPTO_DIGEST_SIZE	32
+
+/* Encryption parameters */
+#define FS_XTS_TWEAK_SIZE		16
+#define FS_AES_128_ECB_KEY_SIZE		16
+#define FS_AES_256_GCM_KEY_SIZE		32
+#define FS_AES_256_CBC_KEY_SIZE		32
+#define FS_AES_256_CTS_KEY_SIZE		32
+#define FS_AES_256_XTS_KEY_SIZE		64
+#define FS_MAX_KEY_SIZE			64
+
+#define FS_KEY_DESC_PREFIX		"fscrypt:"
+#define FS_KEY_DESC_PREFIX_SIZE		8
+
+#define FS_KEY_DERIVATION_NONCE_SIZE		16
+
+/**
+ * Encryption context for inode
+ *
+ * Protector format:
+ *  1 byte: Protector format (1 = this version)
+ *  1 byte: File contents encryption mode
+ *  1 byte: File names encryption mode
+ *  1 byte: Flags
+ *  8 bytes: Master Key descriptor
+ *  16 bytes: Encryption Key derivation nonce
+ */
+struct fscrypt_context {
+	u8 format;
+	u8 contents_encryption_mode;
+	u8 filenames_encryption_mode;
+	u8 flags;
+	u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
+	u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE];
+} __packed;
+
+#define FS_ENCRYPTION_CONTEXT_FORMAT_V1		1
+
+/* This is passed in from userspace into the kernel keyring */
+struct fscrypt_key {
+	u32 mode;
+	u8 raw[FS_MAX_KEY_SIZE];
+	u32 size;
+} __packed;
+
+/*
+ * A pointer to this structure is stored in the file system's in-core
+ * representation of an inode.
+ */
+struct fscrypt_info {
+	u8 ci_data_mode;
+	u8 ci_filename_mode;
+	u8 ci_flags;
+	struct crypto_skcipher *ci_ctfm;
+	struct key *ci_keyring_key;
+	u8 ci_master_key[FS_KEY_DESCRIPTOR_SIZE];
+};
+
+#define FS_CTX_REQUIRES_FREE_ENCRYPT_FL		0x00000001
+#define FS_CTX_HAS_BOUNCE_BUFFER_FL		0x00000002
+
+struct fscrypt_completion_result {
+	struct completion completion;
+	int res;
+};
+
+#define DECLARE_FS_COMPLETION_RESULT(ecr) \
+	struct fscrypt_completion_result ecr = { \
+		COMPLETION_INITIALIZER((ecr).completion), 0 }
+
+
+/* crypto.c */
+int fscrypt_initialize(unsigned int cop_flags);
+
+/* keyinfo.c */
+extern int fscrypt_get_crypt_info(struct inode *);
+
+#endif /* _FSCRYPT_PRIVATE_H */

fs/crypto/keyinfo.c

@@ -10,7 +10,7 @@
 
 #include <keys/user-type.h>
 #include <linux/scatterlist.h>
-#include <linux/fscrypto.h>
+#include "fscrypt_private.h"
 
 static void derive_crypt_complete(struct crypto_async_request *req, int rc)
 {
@@ -178,7 +178,7 @@ static void put_crypt_info(struct fscrypt_info *ci)
 	kmem_cache_free(fscrypt_info_cachep, ci);
 }
 
-int get_crypt_info(struct inode *inode)
+int fscrypt_get_crypt_info(struct inode *inode)
 {
 	struct fscrypt_info *crypt_info;
 	struct fscrypt_context ctx;
@@ -188,7 +188,7 @@ int get_crypt_info(struct inode *inode)
 	u8 *raw_key = NULL;
 	int res;
 
-	res = fscrypt_initialize();
+	res = fscrypt_initialize(inode->i_sb->s_cop->flags);
 	if (res)
 		return res;
 
@@ -327,7 +327,7 @@ int fscrypt_get_encryption_info(struct inode *inode)
 		 (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
 					       (1 << KEY_FLAG_REVOKED) |
 					       (1 << KEY_FLAG_DEAD)))))
-		return get_crypt_info(inode);
+		return fscrypt_get_crypt_info(inode);
 	return 0;
 }
 EXPORT_SYMBOL(fscrypt_get_encryption_info);

fs/crypto/policy.c

@@ -10,8 +10,8 @@
 
 #include <linux/random.h>
 #include <linux/string.h>
-#include <linux/fscrypto.h>
 #include <linux/mount.h>
+#include "fscrypt_private.h"
 
 static int inode_has_encryption_context(struct inode *inode)
 {
@@ -93,16 +93,19 @@ static int create_encryption_context_from_policy(struct inode *inode,
 	return inode->i_sb->s_cop->set_context(inode, &ctx, sizeof(ctx), NULL);
 }
 
-int fscrypt_process_policy(struct file *filp,
-				const struct fscrypt_policy *policy)
+int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg)
 {
+	struct fscrypt_policy policy;
 	struct inode *inode = file_inode(filp);
 	int ret;
 
+	if (copy_from_user(&policy, arg, sizeof(policy)))
+		return -EFAULT;
+
 	if (!inode_owner_or_capable(inode))
 		return -EACCES;
 
-	if (policy->version != 0)
+	if (policy.version != 0)
 		return -EINVAL;
 
 	ret = mnt_want_write_file(filp);
@@ -120,9 +123,9 @@ int fscrypt_process_policy(struct file *filp,
 			ret = -ENOTEMPTY;
 		else
 			ret = create_encryption_context_from_policy(inode,
-								    policy);
+								    &policy);
 	} else if (!is_encryption_context_consistent_with_policy(inode,
-								 policy)) {
+								 &policy)) {
 		printk(KERN_WARNING
 		       "%s: Policy inconsistent with encryption context\n",
 		       __func__);
@@ -134,11 +137,13 @@ int fscrypt_process_policy(struct file *filp,
 	mnt_drop_write_file(filp);
 	return ret;
 }
-EXPORT_SYMBOL(fscrypt_process_policy);
+EXPORT_SYMBOL(fscrypt_ioctl_set_policy);
 
-int fscrypt_get_policy(struct inode *inode, struct fscrypt_policy *policy)
+int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg)
 {
+	struct inode *inode = file_inode(filp);
 	struct fscrypt_context ctx;
+	struct fscrypt_policy policy;
 	int res;
 
 	if (!inode->i_sb->s_cop->get_context ||
@@ -151,15 +156,18 @@ int fscrypt_get_policy(struct inode *inode, struct fscrypt_policy *policy)
 	if (ctx.format != FS_ENCRYPTION_CONTEXT_FORMAT_V1)
 		return -EINVAL;
 
-	policy->version = 0;
-	policy->contents_encryption_mode = ctx.contents_encryption_mode;
-	policy->filenames_encryption_mode = ctx.filenames_encryption_mode;
-	policy->flags = ctx.flags;
-	memcpy(&policy->master_key_descriptor, ctx.master_key_descriptor,
+	policy.version = 0;
+	policy.contents_encryption_mode = ctx.contents_encryption_mode;
+	policy.filenames_encryption_mode = ctx.filenames_encryption_mode;
+	policy.flags = ctx.flags;
+	memcpy(policy.master_key_descriptor, ctx.master_key_descriptor,
 				FS_KEY_DESCRIPTOR_SIZE);
+
+	if (copy_to_user(arg, &policy, sizeof(policy)))
+		return -EFAULT;
 	return 0;
 }
-EXPORT_SYMBOL(fscrypt_get_policy);
+EXPORT_SYMBOL(fscrypt_ioctl_get_policy);
 
 int fscrypt_has_permitted_context(struct inode *parent, struct inode *child)
 {

fs/ext2/file.c

@@ -38,7 +38,7 @@ static ssize_t ext2_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		return 0; /* skip atime */
 
 	inode_lock_shared(inode);
-	ret = iomap_dax_rw(iocb, to, &ext2_iomap_ops);
+	ret = dax_iomap_rw(iocb, to, &ext2_iomap_ops);
 	inode_unlock_shared(inode);
 
 	file_accessed(iocb->ki_filp);
@@ -62,7 +62,7 @@ static ssize_t ext2_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (ret)
 		goto out_unlock;
 
-	ret = iomap_dax_rw(iocb, from, &ext2_iomap_ops);
+	ret = dax_iomap_rw(iocb, from, &ext2_iomap_ops);
 	if (ret > 0 && iocb->ki_pos > i_size_read(inode)) {
 		i_size_write(inode, iocb->ki_pos);
 		mark_inode_dirty(inode);
@@ -99,7 +99,7 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	}
 	down_read(&ei->dax_sem);
 
-	ret = iomap_dax_fault(vma, vmf, &ext2_iomap_ops);
+	ret = dax_iomap_fault(vma, vmf, &ext2_iomap_ops);
 
 	up_read(&ei->dax_sem);
 	if (vmf->flags & FAULT_FLAG_WRITE)
@@ -107,27 +107,6 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	return ret;
 }
 
-static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
-						pmd_t *pmd, unsigned int flags)
-{
-	struct inode *inode = file_inode(vma->vm_file);
-	struct ext2_inode_info *ei = EXT2_I(inode);
-	int ret;
-
-	if (flags & FAULT_FLAG_WRITE) {
-		sb_start_pagefault(inode->i_sb);
-		file_update_time(vma->vm_file);
-	}
-	down_read(&ei->dax_sem);
-
-	ret = dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block);
-
-	up_read(&ei->dax_sem);
-	if (flags & FAULT_FLAG_WRITE)
-		sb_end_pagefault(inode->i_sb);
-	return ret;
-}
-
 static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
 		struct vm_fault *vmf)
 {
@@ -154,7 +133,11 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
 
 static const struct vm_operations_struct ext2_dax_vm_ops = {
 	.fault		= ext2_dax_fault,
-	.pmd_fault	= ext2_dax_pmd_fault,
+	/*
+	 * .pmd_fault is not supported for DAX because allocation in ext2
+	 * cannot be reliably aligned to huge page sizes and so pmd faults
+	 * will always fail and fail back to regular faults.
+	 */
 	.page_mkwrite	= ext2_dax_fault,
 	.pfn_mkwrite	= ext2_dax_pfn_mkwrite,
 };
@@ -166,7 +149,7 @@ static int ext2_file_mmap(struct file *file, struct vm_area_struct *vma)
 
 	file_accessed(file);
 	vma->vm_ops = &ext2_dax_vm_ops;
-	vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
+	vma->vm_flags |= VM_MIXEDMAP;
 	return 0;
 }
 #else

fs/ext2/inode.c

@@ -850,6 +850,9 @@ struct iomap_ops ext2_iomap_ops = {
 	.iomap_begin		= ext2_iomap_begin,
 	.iomap_end		= ext2_iomap_end,
 };
+#else
+/* Define empty ops for !CONFIG_FS_DAX case to avoid ugly ifdefs */
+struct iomap_ops ext2_iomap_ops;
 #endif /* CONFIG_FS_DAX */
 
 int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
@@ -1293,9 +1296,11 @@ static int ext2_setsize(struct inode *inode, loff_t newsize)
 
 	inode_dio_wait(inode);
 
-	if (IS_DAX(inode))
-		error = dax_truncate_page(inode, newsize, ext2_get_block);
-	else if (test_opt(inode->i_sb, NOBH))
+	if (IS_DAX(inode)) {
+		error = iomap_zero_range(inode, newsize,
+					 PAGE_ALIGN(newsize) - newsize, NULL,
+					 &ext2_iomap_ops);
+	} else if (test_opt(inode->i_sb, NOBH))
 		error = nobh_truncate_page(inode->i_mapping,
 				newsize, ext2_get_block);
 	else

fs/ext4/Kconfig

@@ -37,6 +37,7 @@ config EXT4_FS
 	select CRC16
 	select CRYPTO
 	select CRYPTO_CRC32C
+	select FS_IOMAP if FS_DAX
 	help
 	  This is the next generation of the ext3 filesystem.
 

fs/ext4/acl.c

@@ -196,7 +196,7 @@ __ext4_set_acl(handle_t *handle, struct inode *inode, int type,
 			error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
 			if (error)
 				return error;
-			inode->i_ctime = ext4_current_time(inode);
+			inode->i_ctime = current_time(inode);
 			ext4_mark_inode_dirty(handle, inode);
 		}
 		break;

fs/ext4/ext4.h

@@ -397,8 +397,9 @@ struct flex_groups {
 #define EXT4_RESERVED_FL		0x80000000 /* reserved for ext4 lib */
 
 #define EXT4_FL_USER_VISIBLE		0x304BDFFF /* User visible flags */
-#define EXT4_FL_USER_MODIFIABLE		0x204380FF /* User modifiable flags */
+#define EXT4_FL_USER_MODIFIABLE		0x204BC0FF /* User modifiable flags */
 
+/* Flags we can manipulate with through EXT4_IOC_FSSETXATTR */
 #define EXT4_FL_XFLAG_VISIBLE		(EXT4_SYNC_FL | \
 					 EXT4_IMMUTABLE_FL | \
 					 EXT4_APPEND_FL | \
@@ -1533,12 +1534,6 @@ static inline struct ext4_inode_info *EXT4_I(struct inode *inode)
 	return container_of(inode, struct ext4_inode_info, vfs_inode);
 }
 
-static inline struct timespec ext4_current_time(struct inode *inode)
-{
-	return (inode->i_sb->s_time_gran < NSEC_PER_SEC) ?
-		current_fs_time(inode->i_sb) : CURRENT_TIME_SEC;
-}
-
 static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 {
 	return ino == EXT4_ROOT_INO ||
@@ -2277,11 +2272,6 @@ extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
 					      struct ext4_group_desc *gdp);
 ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
 
-static inline int ext4_sb_has_crypto(struct super_block *sb)
-{
-	return ext4_has_feature_encrypt(sb);
-}
-
 static inline bool ext4_encrypted_inode(struct inode *inode)
 {
 	return ext4_test_inode_flag(inode, EXT4_INODE_ENCRYPT);
@@ -2339,8 +2329,8 @@ static inline void ext4_fname_free_filename(struct ext4_filename *fname) { }
 #define fscrypt_pullback_bio_page	fscrypt_notsupp_pullback_bio_page
 #define fscrypt_restore_control_page	fscrypt_notsupp_restore_control_page
 #define fscrypt_zeroout_range		fscrypt_notsupp_zeroout_range
-#define fscrypt_process_policy		fscrypt_notsupp_process_policy
-#define fscrypt_get_policy		fscrypt_notsupp_get_policy
+#define fscrypt_ioctl_set_policy	fscrypt_notsupp_ioctl_set_policy
+#define fscrypt_ioctl_get_policy	fscrypt_notsupp_ioctl_get_policy
 #define fscrypt_has_permitted_context	fscrypt_notsupp_has_permitted_context
 #define fscrypt_inherit_context		fscrypt_notsupp_inherit_context
 #define fscrypt_get_encryption_info	fscrypt_notsupp_get_encryption_info
@@ -2458,8 +2448,6 @@ struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int);
 struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int);
 int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
 			     struct buffer_head *bh_result, int create);
-int ext4_dax_get_block(struct inode *inode, sector_t iblock,
-		       struct buffer_head *bh_result, int create);
 int ext4_get_block(struct inode *inode, sector_t iblock,
 		   struct buffer_head *bh_result, int create);
 int ext4_dio_get_block(struct inode *inode, sector_t iblock,
@@ -2492,7 +2480,7 @@ extern int ext4_change_inode_journal_flag(struct inode *, int);
 extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
 extern int ext4_inode_attach_jinode(struct inode *inode);
 extern int ext4_can_truncate(struct inode *inode);
-extern void ext4_truncate(struct inode *);
+extern int ext4_truncate(struct inode *);
 extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length);
 extern int ext4_truncate_restart_trans(handle_t *, struct inode *, int nblocks);
 extern void ext4_set_inode_flags(struct inode *);
@@ -3129,7 +3117,7 @@ extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
 extern int ext4_ext_index_trans_blocks(struct inode *inode, int extents);
 extern int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 			       struct ext4_map_blocks *map, int flags);
-extern void ext4_ext_truncate(handle_t *, struct inode *);
+extern int ext4_ext_truncate(handle_t *, struct inode *);
 extern int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start,
 				 ext4_lblk_t end);
 extern void ext4_ext_init(struct super_block *);
@@ -3265,12 +3253,7 @@ static inline void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end)
 	}
 }
 
-static inline bool ext4_aligned_io(struct inode *inode, loff_t off, loff_t len)
-{
-	int blksize = 1 << inode->i_blkbits;
-
-	return IS_ALIGNED(off, blksize) && IS_ALIGNED(len, blksize);
-}
+extern struct iomap_ops ext4_iomap_ops;
 
 #endif	/* __KERNEL__ */
 

fs/ext4/ext4_jbd2.h

@@ -414,17 +414,19 @@ static inline int ext4_inode_journal_mode(struct inode *inode)
 		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
 	/* We do not support data journalling with delayed allocation */
 	if (!S_ISREG(inode->i_mode) ||
-	    test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
-		return EXT4_INODE_JOURNAL_DATA_MODE;	/* journal data */
-	if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
-	    !test_opt(inode->i_sb, DELALLOC))
+	    test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
+	    (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
+	    !test_opt(inode->i_sb, DELALLOC))) {
+		/* We do not support data journalling for encrypted data */
+		if (S_ISREG(inode->i_mode) && ext4_encrypted_inode(inode))
+			return EXT4_INODE_ORDERED_DATA_MODE;  /* ordered */
 		return EXT4_INODE_JOURNAL_DATA_MODE;	/* journal data */
+	}
 	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
 		return EXT4_INODE_ORDERED_DATA_MODE;	/* ordered */
 	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
 		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
-	else
-		BUG();
+	BUG();
 }
 
 static inline int ext4_should_journal_data(struct inode *inode)

fs/ext4/extents.c

@@ -4631,7 +4631,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 	return err ? err : allocated;
 }
 
-void ext4_ext_truncate(handle_t *handle, struct inode *inode)
+int ext4_ext_truncate(handle_t *handle, struct inode *inode)
 {
 	struct super_block *sb = inode->i_sb;
 	ext4_lblk_t last_block;
@@ -4645,7 +4645,9 @@ void ext4_ext_truncate(handle_t *handle, struct inode *inode)
 
 	/* we have to know where to truncate from in crash case */
 	EXT4_I(inode)->i_disksize = inode->i_size;
-	ext4_mark_inode_dirty(handle, inode);
+	err = ext4_mark_inode_dirty(handle, inode);
+	if (err)
+		return err;
 
 	last_block = (inode->i_size + sb->s_blocksize - 1)
 			>> EXT4_BLOCK_SIZE_BITS(sb);
@@ -4657,12 +4659,9 @@ void ext4_ext_truncate(handle_t *handle, struct inode *inode)
 		congestion_wait(BLK_RW_ASYNC, HZ/50);
 		goto retry;
 	}
-	if (err) {
-		ext4_std_error(inode->i_sb, err);
-		return;
-	}
-	err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1);
-	ext4_std_error(inode->i_sb, err);
+	if (err)
+		return err;
+	return ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1);
 }
 
 static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
@@ -4701,7 +4700,7 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
 		/*
 		 * Recalculate credits when extent tree depth changes.
 		 */
-		if (depth >= 0 && depth != ext_depth(inode)) {
+		if (depth != ext_depth(inode)) {
 			credits = ext4_chunk_trans_blocks(inode, len);
 			depth = ext_depth(inode);
 		}
@@ -4725,7 +4724,7 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
 		map.m_lblk += ret;
 		map.m_len = len = len - ret;
 		epos = (loff_t)map.m_lblk << inode->i_blkbits;
-		inode->i_ctime = ext4_current_time(inode);
+		inode->i_ctime = current_time(inode);
 		if (new_size) {
 			if (epos > new_size)
 				epos = new_size;
@@ -4853,7 +4852,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		}
 		/* Now release the pages and zero block aligned part of pages */
 		truncate_pagecache_range(inode, start, end - 1);
-		inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+		inode->i_mtime = inode->i_ctime = current_time(inode);
 
 		ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
 					     flags, mode);
@@ -4878,7 +4877,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		goto out_dio;
 	}
 
-	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+	inode->i_mtime = inode->i_ctime = current_time(inode);
 	if (new_size) {
 		ext4_update_inode_size(inode, new_size);
 	} else {
@@ -5568,7 +5567,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	up_write(&EXT4_I(inode)->i_data_sem);
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
-	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+	inode->i_mtime = inode->i_ctime = current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
 
 out_stop:
@@ -5678,7 +5677,7 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	/* Expand file to avoid data loss if there is error while shifting */
 	inode->i_size += len;
 	EXT4_I(inode)->i_disksize += len;
-	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+	inode->i_mtime = inode->i_ctime = current_time(inode);
 	ret = ext4_mark_inode_dirty(handle, inode);
 	if (ret)
 		goto out_stop;

fs/ext4/file.c

@@ -31,6 +31,42 @@
 #include "xattr.h"
 #include "acl.h"
 
+#ifdef CONFIG_FS_DAX
+static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	ssize_t ret;
+
+	inode_lock_shared(inode);
+	/*
+	 * Recheck under inode lock - at this point we are sure it cannot
+	 * change anymore
+	 */
+	if (!IS_DAX(inode)) {
+		inode_unlock_shared(inode);
+		/* Fallback to buffered IO in case we cannot support DAX */
+		return generic_file_read_iter(iocb, to);
+	}
+	ret = dax_iomap_rw(iocb, to, &ext4_iomap_ops);
+	inode_unlock_shared(inode);
+
+	file_accessed(iocb->ki_filp);
+	return ret;
+}
+#endif
+
+static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	if (!iov_iter_count(to))
+		return 0; /* skip atime */
+
+#ifdef CONFIG_FS_DAX
+	if (IS_DAX(file_inode(iocb->ki_filp)))
+		return ext4_dax_read_iter(iocb, to);
+#endif
+	return generic_file_read_iter(iocb, to);
+}
+
 /*
  * Called when an inode is released. Note that this is different
  * from ext4_file_open: open gets called at every open, but release
@@ -88,6 +124,86 @@ ext4_unaligned_aio(struct inode *inode, struct iov_iter *from, loff_t pos)
 	return 0;
 }
 
+/* Is IO overwriting allocated and initialized blocks? */
+static bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len)
+{
+	struct ext4_map_blocks map;
+	unsigned int blkbits = inode->i_blkbits;
+	int err, blklen;
+
+	if (pos + len > i_size_read(inode))
+		return false;
+
+	map.m_lblk = pos >> blkbits;
+	map.m_len = EXT4_MAX_BLOCKS(len, pos, blkbits);
+	blklen = map.m_len;
+
+	err = ext4_map_blocks(NULL, inode, &map, 0);
+	/*
+	 * 'err==len' means that all of the blocks have been preallocated,
+	 * regardless of whether they have been initialized or not. To exclude
+	 * unwritten extents, we need to check m_flags.
+	 */
+	return err == blklen && (map.m_flags & EXT4_MAP_MAPPED);
+}
+
+static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	ssize_t ret;
+
+	ret = generic_write_checks(iocb, from);
+	if (ret <= 0)
+		return ret;
+	/*
+	 * If we have encountered a bitmap-format file, the size limit
+	 * is smaller than s_maxbytes, which is for extent-mapped files.
+	 */
+	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
+		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
+		if (iocb->ki_pos >= sbi->s_bitmap_maxbytes)
+			return -EFBIG;
+		iov_iter_truncate(from, sbi->s_bitmap_maxbytes - iocb->ki_pos);
+	}
+	return iov_iter_count(from);
+}
+
+#ifdef CONFIG_FS_DAX
+static ssize_t
+ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	ssize_t ret;
+	bool overwrite = false;
+
+	inode_lock(inode);
+	ret = ext4_write_checks(iocb, from);
+	if (ret <= 0)
+		goto out;
+	ret = file_remove_privs(iocb->ki_filp);
+	if (ret)
+		goto out;
+	ret = file_update_time(iocb->ki_filp);
+	if (ret)
+		goto out;
+
+	if (ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from))) {
+		overwrite = true;
+		downgrade_write(&inode->i_rwsem);
+	}
+	ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops);
+out:
+	if (!overwrite)
+		inode_unlock(inode);
+	else
+		inode_unlock_shared(inode);
+	if (ret > 0)
+		ret = generic_write_sync(iocb, ret);
+	return ret;
+}
+#endif
+
 static ssize_t
 ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
@@ -97,8 +213,13 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	int overwrite = 0;
 	ssize_t ret;
 
+#ifdef CONFIG_FS_DAX
+	if (IS_DAX(inode))
+		return ext4_dax_write_iter(iocb, from);
+#endif
+
 	inode_lock(inode);
-	ret = generic_write_checks(iocb, from);
+	ret = ext4_write_checks(iocb, from);
 	if (ret <= 0)
 		goto out;
 
@@ -114,53 +235,11 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		ext4_unwritten_wait(inode);
 	}
 
-	/*
-	 * If we have encountered a bitmap-format file, the size limit
-	 * is smaller than s_maxbytes, which is for extent-mapped files.
-	 */
-	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
-		struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-
-		if (iocb->ki_pos >= sbi->s_bitmap_maxbytes) {
-			ret = -EFBIG;
-			goto out;
-		}
-		iov_iter_truncate(from, sbi->s_bitmap_maxbytes - iocb->ki_pos);
-	}
-
 	iocb->private = &overwrite;
-	if (o_direct) {
-		size_t length = iov_iter_count(from);
-		loff_t pos = iocb->ki_pos;
-
-		/* check whether we do a DIO overwrite or not */
-		if (ext4_should_dioread_nolock(inode) && !unaligned_aio &&
-		    pos + length <= i_size_read(inode)) {
-			struct ext4_map_blocks map;
-			unsigned int blkbits = inode->i_blkbits;
-			int err, len;
-
-			map.m_lblk = pos >> blkbits;
-			map.m_len = EXT4_MAX_BLOCKS(length, pos, blkbits);
-			len = map.m_len;
-
-			err = ext4_map_blocks(NULL, inode, &map, 0);
-			/*
-			 * 'err==len' means that all of blocks has
-			 * been preallocated no matter they are
-			 * initialized or not.  For excluding
-			 * unwritten extents, we need to check
-			 * m_flags.  There are two conditions that
-			 * indicate for initialized extents.  1) If we
-			 * hit extent cache, EXT4_MAP_MAPPED flag is
-			 * returned; 2) If we do a real lookup,
-			 * non-flags are returned.  So we should check
-			 * these two conditions.
-			 */
-			if (err == len && (map.m_flags & EXT4_MAP_MAPPED))
-				overwrite = 1;
-		}
-	}
+	/* Check whether we do a DIO overwrite or not */
+	if (o_direct && ext4_should_dioread_nolock(inode) && !unaligned_aio &&
+	    ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from)))
+		overwrite = 1;
 
 	ret = __generic_file_write_iter(iocb, from);
 	inode_unlock(inode);
@@ -196,7 +275,7 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (IS_ERR(handle))
 		result = VM_FAULT_SIGBUS;
 	else
-		result = dax_fault(vma, vmf, ext4_dax_get_block);
+		result = dax_iomap_fault(vma, vmf, &ext4_iomap_ops);
 
 	if (write) {
 		if (!IS_ERR(handle))
@@ -230,9 +309,10 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 
 	if (IS_ERR(handle))
 		result = VM_FAULT_SIGBUS;
-	else
-		result = dax_pmd_fault(vma, addr, pmd, flags,
-					 ext4_dax_get_block);
+	else {
+		result = dax_iomap_pmd_fault(vma, addr, pmd, flags,
+					     &ext4_iomap_ops);
+	}
 
 	if (write) {
 		if (!IS_ERR(handle))
@@ -687,7 +767,7 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int whence)
 
 const struct file_operations ext4_file_operations = {
 	.llseek		= ext4_llseek,
-	.read_iter	= generic_file_read_iter,
+	.read_iter	= ext4_file_read_iter,
 	.write_iter	= ext4_file_write_iter,
 	.unlocked_ioctl = ext4_ioctl,
 #ifdef CONFIG_COMPAT

fs/ext4/ialloc.c

@@ -1039,7 +1039,7 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 	/* This is the optimal IO size (for stat), not the fs block size */
 	inode->i_blocks = 0;
 	inode->i_mtime = inode->i_atime = inode->i_ctime = ei->i_crtime =
-						       ext4_current_time(inode);
+						       current_time(inode);
 
 	memset(ei->i_data, 0, sizeof(ei->i_data));
 	ei->i_dir_start_lookup = 0;
@@ -1115,8 +1115,7 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 	}
 
 	if (encrypt) {
-		/* give pointer to avoid set_context with journal ops. */
-		err = fscrypt_inherit_context(dir, inode, &encrypt, true);
+		err = fscrypt_inherit_context(dir, inode, handle, true);
 		if (err)
 			goto fail_free_drop;
 	}

fs/ext4/inline.c

@@ -299,6 +299,11 @@ static int ext4_create_inline_data(handle_t *handle,
 	EXT4_I(inode)->i_inline_size = len + EXT4_MIN_INLINE_DATA_SIZE;
 	ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
 	ext4_set_inode_flag(inode, EXT4_INODE_INLINE_DATA);
+	/*
+	 * Propagate changes to inode->i_flags as well - e.g. S_DAX may
+	 * get cleared
+	 */
+	ext4_set_inode_flags(inode);
 	get_bh(is.iloc.bh);
 	error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
 
@@ -336,8 +341,10 @@ static int ext4_update_inline_data(handle_t *handle, struct inode *inode,
 
 	len -= EXT4_MIN_INLINE_DATA_SIZE;
 	value = kzalloc(len, GFP_NOFS);
-	if (!value)
+	if (!value) {
+		error = -ENOMEM;
 		goto out;
+	}
 
 	error = ext4_xattr_ibody_get(inode, i.name_index, i.name,
 				     value, len);
@@ -442,6 +449,11 @@ static int ext4_destroy_inline_data_nolock(handle_t *handle,
 		}
 	}
 	ext4_clear_inode_flag(inode, EXT4_INODE_INLINE_DATA);
+	/*
+	 * Propagate changes to inode->i_flags as well - e.g. S_DAX may
+	 * get set.
+	 */
+	ext4_set_inode_flags(inode);
 
 	get_bh(is.iloc.bh);
 	error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
@@ -1028,7 +1040,7 @@ static int ext4_add_dirent_to_inline(handle_t *handle,
 	 * happen is that the times are slightly out of date
 	 * and/or different from the directory change time.
 	 */
-	dir->i_mtime = dir->i_ctime = ext4_current_time(dir);
+	dir->i_mtime = dir->i_ctime = current_time(dir);
 	ext4_update_dx_flag(dir);
 	dir->i_version++;
 	ext4_mark_inode_dirty(handle, dir);
@@ -1971,7 +1983,7 @@ void ext4_inline_data_truncate(struct inode *inode, int *has_inline)
 	if (inode->i_nlink)
 		ext4_orphan_del(handle, inode);
 
-	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+	inode->i_mtime = inode->i_ctime = current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);

fs/ext4/ioctl.c

@@ -153,7 +153,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 
 	swap_inode_data(inode, inode_bl);
 
-	inode->i_ctime = inode_bl->i_ctime = ext4_current_time(inode);
+	inode->i_ctime = inode_bl->i_ctime = current_time(inode);
 
 	spin_lock(&sbi->s_next_gen_lock);
 	inode->i_generation = sbi->s_next_generation++;
@@ -191,6 +191,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 	return err;
 }
 
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
 static int uuid_is_zero(__u8 u[16])
 {
 	int	i;
@@ -200,6 +201,7 @@ static int uuid_is_zero(__u8 u[16])
 			return 0;
 	return 1;
 }
+#endif
 
 static int ext4_ioctl_setflags(struct inode *inode,
 			       unsigned int flags)
@@ -248,8 +250,11 @@ static int ext4_ioctl_setflags(struct inode *inode,
 			err = -EOPNOTSUPP;
 			goto flags_out;
 		}
-	} else if (oldflags & EXT4_EOFBLOCKS_FL)
-		ext4_truncate(inode);
+	} else if (oldflags & EXT4_EOFBLOCKS_FL) {
+		err = ext4_truncate(inode);
+		if (err)
+			goto flags_out;
+	}
 
 	handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
 	if (IS_ERR(handle)) {
@@ -265,6 +270,9 @@ static int ext4_ioctl_setflags(struct inode *inode,
 	for (i = 0, mask = 1; i < 32; i++, mask <<= 1) {
 		if (!(mask & EXT4_FL_USER_MODIFIABLE))
 			continue;
+		/* These flags get special treatment later */
+		if (mask == EXT4_JOURNAL_DATA_FL || mask == EXT4_EXTENTS_FL)
+			continue;
 		if (mask & flags)
 			ext4_set_inode_flag(inode, i);
 		else
@@ -272,7 +280,7 @@ static int ext4_ioctl_setflags(struct inode *inode,
 	}
 
 	ext4_set_inode_flags(inode);
-	inode->i_ctime = ext4_current_time(inode);
+	inode->i_ctime = current_time(inode);
 
 	err = ext4_mark_iloc_dirty(handle, inode, &iloc);
 flags_err:
@@ -368,7 +376,7 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
 	}
 
 	EXT4_I(inode)->i_projid = kprojid;
-	inode->i_ctime = ext4_current_time(inode);
+	inode->i_ctime = current_time(inode);
 out_dirty:
 	rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
 	if (!err)
@@ -409,6 +417,10 @@ static inline __u32 ext4_iflags_to_xflags(unsigned long iflags)
 	return xflags;
 }
 
+#define EXT4_SUPPORTED_FS_XFLAGS (FS_XFLAG_SYNC | FS_XFLAG_IMMUTABLE | \
+				  FS_XFLAG_APPEND | FS_XFLAG_NODUMP | \
+				  FS_XFLAG_NOATIME | FS_XFLAG_PROJINHERIT)
+
 /* Transfer xflags flags to internal */
 static inline unsigned long ext4_xflags_to_iflags(__u32 xflags)
 {
@@ -453,12 +465,22 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		if (get_user(flags, (int __user *) arg))
 			return -EFAULT;
 
+		if (flags & ~EXT4_FL_USER_VISIBLE)
+			return -EOPNOTSUPP;
+		/*
+		 * chattr(1) grabs flags via GETFLAGS, modifies the result and
+		 * passes that to SETFLAGS. So we cannot easily make SETFLAGS
+		 * more restrictive than just silently masking off visible but
+		 * not settable flags as we always did.
+		 */
+		flags &= EXT4_FL_USER_MODIFIABLE;
+		if (ext4_mask_flags(inode->i_mode, flags) != flags)
+			return -EOPNOTSUPP;
+
 		err = mnt_want_write_file(filp);
 		if (err)
 			return err;
 
-		flags = ext4_mask_flags(inode->i_mode, flags);
-
 		inode_lock(inode);
 		err = ext4_ioctl_setflags(inode, flags);
 		inode_unlock(inode);
@@ -500,7 +522,7 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		}
 		err = ext4_reserve_inode_write(handle, inode, &iloc);
 		if (err == 0) {
-			inode->i_ctime = ext4_current_time(inode);
+			inode->i_ctime = current_time(inode);
 			inode->i_generation = generation;
 			err = ext4_mark_iloc_dirty(handle, inode, &iloc);
 		}
@@ -765,28 +787,19 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	}
 	case EXT4_IOC_PRECACHE_EXTENTS:
 		return ext4_ext_precache(inode);
-	case EXT4_IOC_SET_ENCRYPTION_POLICY: {
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
-		struct fscrypt_policy policy;
 
+	case EXT4_IOC_SET_ENCRYPTION_POLICY:
 		if (!ext4_has_feature_encrypt(sb))
 			return -EOPNOTSUPP;
+		return fscrypt_ioctl_set_policy(filp, (const void __user *)arg);
 
-		if (copy_from_user(&policy,
-				   (struct fscrypt_policy __user *)arg,
-				   sizeof(policy)))
-			return -EFAULT;
-		return fscrypt_process_policy(filp, &policy);
-#else
-		return -EOPNOTSUPP;
-#endif
-	}
 	case EXT4_IOC_GET_ENCRYPTION_PWSALT: {
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
 		int err, err2;
 		struct ext4_sb_info *sbi = EXT4_SB(sb);
 		handle_t *handle;
 
-		if (!ext4_sb_has_crypto(sb))
+		if (!ext4_has_feature_encrypt(sb))
 			return -EOPNOTSUPP;
 		if (uuid_is_zero(sbi->s_es->s_encrypt_pw_salt)) {
 			err = mnt_want_write_file(filp);
@@ -816,24 +829,13 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 				 sbi->s_es->s_encrypt_pw_salt, 16))
 			return -EFAULT;
 		return 0;
-	}
-	case EXT4_IOC_GET_ENCRYPTION_POLICY: {
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
-		struct fscrypt_policy policy;
-		int err = 0;
-
-		if (!ext4_encrypted_inode(inode))
-			return -ENOENT;
-		err = fscrypt_get_policy(inode, &policy);
-		if (err)
-			return err;
-		if (copy_to_user((void __user *)arg, &policy, sizeof(policy)))
-			return -EFAULT;
-		return 0;
 #else
 		return -EOPNOTSUPP;
 #endif
 	}
+	case EXT4_IOC_GET_ENCRYPTION_POLICY:
+		return fscrypt_ioctl_get_policy(filp, (void __user *)arg);
+
 	case EXT4_IOC_FSGETXATTR:
 	{
 		struct fsxattr fa;
@@ -865,13 +867,17 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		if (!inode_owner_or_capable(inode))
 			return -EACCES;
 
+		if (fa.fsx_xflags & ~EXT4_SUPPORTED_FS_XFLAGS)
+			return -EOPNOTSUPP;
+
+		flags = ext4_xflags_to_iflags(fa.fsx_xflags);
+		if (ext4_mask_flags(inode->i_mode, flags) != flags)
+			return -EOPNOTSUPP;
+
 		err = mnt_want_write_file(filp);
 		if (err)
 			return err;
 
-		flags = ext4_xflags_to_iflags(fa.fsx_xflags);
-		flags = ext4_mask_flags(inode->i_mode, flags);
-
 		inode_lock(inode);
 		flags = (ei->i_flags & ~EXT4_FL_XFLAG_VISIBLE) |
 			 (flags & EXT4_FL_XFLAG_VISIBLE);

fs/ext4/mballoc.c

@@ -669,7 +669,7 @@ static void ext4_mb_mark_free_simple(struct super_block *sb,
 	ext4_grpblk_t min;
 	ext4_grpblk_t max;
 	ext4_grpblk_t chunk;
-	unsigned short border;
+	unsigned int border;
 
 	BUG_ON(len > EXT4_CLUSTERS_PER_GROUP(sb));
 
@@ -2287,7 +2287,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 	struct ext4_group_info *grinfo;
 	struct sg {
 		struct ext4_group_info info;
-		ext4_grpblk_t counters[16];
+		ext4_grpblk_t counters[EXT4_MAX_BLOCK_LOG_SIZE + 2];
 	} sg;
 
 	group--;

fs/ext4/namei.c

@@ -1941,7 +1941,7 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname,
 	 * happen is that the times are slightly out of date
 	 * and/or different from the directory change time.
 	 */
-	dir->i_mtime = dir->i_ctime = ext4_current_time(dir);
+	dir->i_mtime = dir->i_ctime = current_time(dir);
 	ext4_update_dx_flag(dir);
 	dir->i_version++;
 	ext4_mark_inode_dirty(handle, dir);
@@ -2987,7 +2987,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
 	 * recovery. */
 	inode->i_size = 0;
 	ext4_orphan_add(handle, inode);
-	inode->i_ctime = dir->i_ctime = dir->i_mtime = ext4_current_time(inode);
+	inode->i_ctime = dir->i_ctime = dir->i_mtime = current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
 	ext4_dec_count(handle, dir);
 	ext4_update_dx_flag(dir);
@@ -3050,13 +3050,13 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
 	retval = ext4_delete_entry(handle, dir, de, bh);
 	if (retval)
 		goto end_unlink;
-	dir->i_ctime = dir->i_mtime = ext4_current_time(dir);
+	dir->i_ctime = dir->i_mtime = current_time(dir);
 	ext4_update_dx_flag(dir);
 	ext4_mark_inode_dirty(handle, dir);
 	drop_nlink(inode);
 	if (!inode->i_nlink)
 		ext4_orphan_add(handle, inode);
-	inode->i_ctime = ext4_current_time(inode);
+	inode->i_ctime = current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
 
 end_unlink:
@@ -3254,7 +3254,7 @@ static int ext4_link(struct dentry *old_dentry,
 	if (IS_DIRSYNC(dir))
 		ext4_handle_sync(handle);
 
-	inode->i_ctime = ext4_current_time(inode);
+	inode->i_ctime = current_time(inode);
 	ext4_inc_count(handle, inode);
 	ihold(inode);
 
@@ -3381,7 +3381,7 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent,
 		ent->de->file_type = file_type;
 	ent->dir->i_version++;
 	ent->dir->i_ctime = ent->dir->i_mtime =
-		ext4_current_time(ent->dir);
+		current_time(ent->dir);
 	ext4_mark_inode_dirty(handle, ent->dir);
 	BUFFER_TRACE(ent->bh, "call ext4_handle_dirty_metadata");
 	if (!ent->inlined) {
@@ -3651,7 +3651,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 	 * Like most other Unix systems, set the ctime for inodes on a
 	 * rename.
 	 */
-	old.inode->i_ctime = ext4_current_time(old.inode);
+	old.inode->i_ctime = current_time(old.inode);
 	ext4_mark_inode_dirty(handle, old.inode);
 
 	if (!whiteout) {
@@ -3663,9 +3663,9 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	if (new.inode) {
 		ext4_dec_count(handle, new.inode);
-		new.inode->i_ctime = ext4_current_time(new.inode);
+		new.inode->i_ctime = current_time(new.inode);
 	}
-	old.dir->i_ctime = old.dir->i_mtime = ext4_current_time(old.dir);
+	old.dir->i_ctime = old.dir->i_mtime = current_time(old.dir);
 	ext4_update_dx_flag(old.dir);
 	if (old.dir_bh) {
 		retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino);
@@ -3723,6 +3723,7 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 	};
 	u8 new_file_type;
 	int retval;
+	struct timespec ctime;
 
 	if ((ext4_encrypted_inode(old_dir) ||
 	     ext4_encrypted_inode(new_dir)) &&
@@ -3823,8 +3824,9 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 	 * Like most other Unix systems, set the ctime for inodes on a
 	 * rename.
 	 */
-	old.inode->i_ctime = ext4_current_time(old.inode);
-	new.inode->i_ctime = ext4_current_time(new.inode);
+	ctime = current_time(old.inode);
+	old.inode->i_ctime = ctime;
+	new.inode->i_ctime = ctime;
 	ext4_mark_inode_dirty(handle, old.inode);
 	ext4_mark_inode_dirty(handle, new.inode);
 

fs/ext4/page-io.c

@@ -470,7 +470,8 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 		gfp_t gfp_flags = GFP_NOFS;
 
 	retry_encrypt:
-		data_page = fscrypt_encrypt_page(inode, page, gfp_flags);
+		data_page = fscrypt_encrypt_page(inode, page, PAGE_SIZE, 0,
+						page->index, gfp_flags);
 		if (IS_ERR(data_page)) {
 			ret = PTR_ERR(data_page);
 			if (ret == -ENOMEM && wbc->sync_mode == WB_SYNC_ALL) {

fs/ext4/xattr.c

@@ -185,6 +185,7 @@ ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end,
 {
 	struct ext4_xattr_entry *e = entry;
 
+	/* Find the end of the names list */
 	while (!IS_LAST_ENTRY(e)) {
 		struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(e);
 		if ((void *)next >= end)
@@ -192,15 +193,29 @@ ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end,
 		e = next;
 	}
 
+	/* Check the values */
 	while (!IS_LAST_ENTRY(entry)) {
 		if (entry->e_value_block != 0)
 			return -EFSCORRUPTED;
-		if (entry->e_value_size != 0 &&
-		    (value_start + le16_to_cpu(entry->e_value_offs) <
-		     (void *)e + sizeof(__u32) ||
-		     value_start + le16_to_cpu(entry->e_value_offs) +
-		    le32_to_cpu(entry->e_value_size) > end))
-			return -EFSCORRUPTED;
+		if (entry->e_value_size != 0) {
+			u16 offs = le16_to_cpu(entry->e_value_offs);
+			u32 size = le32_to_cpu(entry->e_value_size);
+			void *value;
+
+			/*
+			 * The value cannot overlap the names, and the value
+			 * with padding cannot extend beyond 'end'.  Check both
+			 * the padded and unpadded sizes, since the size may
+			 * overflow to 0 when adding padding.
+			 */
+			if (offs > end - value_start)
+				return -EFSCORRUPTED;
+			value = value_start + offs;
+			if (value < (void *)e + sizeof(u32) ||
+			    size > end - value ||
+			    EXT4_XATTR_SIZE(size) > end - value)
+				return -EFSCORRUPTED;
+		}
 		entry = EXT4_XATTR_NEXT(entry);
 	}
 
@@ -231,13 +246,12 @@ static int
 __xattr_check_inode(struct inode *inode, struct ext4_xattr_ibody_header *header,
 			 void *end, const char *function, unsigned int line)
 {
-	struct ext4_xattr_entry *entry = IFIRST(header);
 	int error = -EFSCORRUPTED;
 
-	if (((void *) header >= end) ||
+	if (end - (void *)header < sizeof(*header) + sizeof(u32) ||
 	    (header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)))
 		goto errout;
-	error = ext4_xattr_check_names(entry, end, entry);
+	error = ext4_xattr_check_names(IFIRST(header), end, IFIRST(header));
 errout:
 	if (error)
 		__ext4_error_inode(inode, function, line, 0,
@@ -1109,7 +1123,7 @@ int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
 	return 0;
 }
 
-static int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
+static int ext4_xattr_ibody_set(struct inode *inode,
 				struct ext4_xattr_info *i,
 				struct ext4_xattr_ibody_find *is)
 {
@@ -1216,7 +1230,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 	}
 	if (!value) {
 		if (!is.s.not_found)
-			error = ext4_xattr_ibody_set(handle, inode, &i, &is);
+			error = ext4_xattr_ibody_set(inode, &i, &is);
 		else if (!bs.s.not_found)
 			error = ext4_xattr_block_set(handle, inode, &i, &bs);
 	} else {
@@ -1227,7 +1241,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 		if (!bs.s.not_found && ext4_xattr_value_same(&bs.s, &i))
 			goto cleanup;
 
-		error = ext4_xattr_ibody_set(handle, inode, &i, &is);
+		error = ext4_xattr_ibody_set(inode, &i, &is);
 		if (!error && !bs.s.not_found) {
 			i.value = NULL;
 			error = ext4_xattr_block_set(handle, inode, &i, &bs);
@@ -1242,14 +1256,13 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 				goto cleanup;
 			if (!is.s.not_found) {
 				i.value = NULL;
-				error = ext4_xattr_ibody_set(handle, inode, &i,
-							     &is);
+				error = ext4_xattr_ibody_set(inode, &i, &is);
 			}
 		}
 	}
 	if (!error) {
 		ext4_xattr_update_super_block(handle, inode->i_sb);
-		inode->i_ctime = ext4_current_time(inode);
+		inode->i_ctime = current_time(inode);
 		if (!value)
 			ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
 		error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
@@ -1384,7 +1397,7 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode,
 		goto out;
 
 	/* Remove the chosen entry from the inode */
-	error = ext4_xattr_ibody_set(handle, inode, &i, is);
+	error = ext4_xattr_ibody_set(inode, &i, is);
 	if (error)
 		goto out;
 

fs/f2fs/data.c

@@ -1246,7 +1246,9 @@ int do_write_data_page(struct f2fs_io_info *fio)
 							fio->old_blkaddr);
 retry_encrypt:
 		fio->encrypted_page = fscrypt_encrypt_page(inode, fio->page,
-								gfp_flags);
+							PAGE_SIZE, 0,
+							fio->page->index,
+							gfp_flags);
 		if (IS_ERR(fio->encrypted_page)) {
 			err = PTR_ERR(fio->encrypted_page);
 			if (err == -ENOMEM) {

fs/f2fs/f2fs.h

@@ -2520,8 +2520,8 @@ static inline bool f2fs_may_encrypt(struct inode *inode)
 #define fscrypt_pullback_bio_page	fscrypt_notsupp_pullback_bio_page
 #define fscrypt_restore_control_page	fscrypt_notsupp_restore_control_page
 #define fscrypt_zeroout_range		fscrypt_notsupp_zeroout_range
-#define fscrypt_process_policy		fscrypt_notsupp_process_policy
-#define fscrypt_get_policy		fscrypt_notsupp_get_policy
+#define fscrypt_ioctl_set_policy	fscrypt_notsupp_ioctl_set_policy
+#define fscrypt_ioctl_get_policy	fscrypt_notsupp_ioctl_get_policy
 #define fscrypt_has_permitted_context	fscrypt_notsupp_has_permitted_context
 #define fscrypt_inherit_context		fscrypt_notsupp_inherit_context
 #define fscrypt_get_encryption_info	fscrypt_notsupp_get_encryption_info

fs/f2fs/file.c

@@ -1762,31 +1762,16 @@ static bool uuid_is_nonzero(__u8 u[16])
 
 static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg)
 {
-	struct fscrypt_policy policy;
 	struct inode *inode = file_inode(filp);
 
-	if (copy_from_user(&policy, (struct fscrypt_policy __user *)arg,
-							sizeof(policy)))
-		return -EFAULT;
-
 	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 
-	return fscrypt_process_policy(filp, &policy);
+	return fscrypt_ioctl_set_policy(filp, (const void __user *)arg);
 }
 
 static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg)
 {
-	struct fscrypt_policy policy;
-	struct inode *inode = file_inode(filp);
-	int err;
-
-	err = fscrypt_get_policy(inode, &policy);
-	if (err)
-		return err;
-
-	if (copy_to_user((struct fscrypt_policy __user *)arg, &policy, sizeof(policy)))
-		return -EFAULT;
-	return 0;
+	return fscrypt_ioctl_get_policy(filp, (void __user *)arg);
 }
 
 static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg)

fs/iomap.c

@@ -467,8 +467,9 @@ int iomap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 
 	offset = page_offset(page);
 	while (length > 0) {
-		ret = iomap_apply(inode, offset, length, IOMAP_WRITE,
-				ops, page, iomap_page_mkwrite_actor);
+		ret = iomap_apply(inode, offset, length,
+				IOMAP_WRITE | IOMAP_FAULT, ops, page,
+				iomap_page_mkwrite_actor);
 		if (unlikely(ret <= 0))
 			goto out_unlock;
 		offset += ret;

fs/mbcache.c

@@ -29,7 +29,7 @@ struct mb_cache {
 	/* log2 of hash table size */
 	int			c_bucket_bits;
 	/* Maximum entries in cache to avoid degrading hash too much */
-	int			c_max_entries;
+	unsigned long		c_max_entries;
 	/* Protects c_list, c_entry_count */
 	spinlock_t		c_list_lock;
 	struct list_head	c_list;
@@ -43,7 +43,7 @@ struct mb_cache {
 static struct kmem_cache *mb_entry_cache;
 
 static unsigned long mb_cache_shrink(struct mb_cache *cache,
-				     unsigned int nr_to_scan);
+				     unsigned long nr_to_scan);
 
 static inline struct hlist_bl_head *mb_cache_entry_head(struct mb_cache *cache,
 							u32 key)
@@ -155,12 +155,12 @@ static struct mb_cache_entry *__entry_find(struct mb_cache *cache,
 }
 
 /*
- * mb_cache_entry_find_first - find the first entry in cache with given key
+ * mb_cache_entry_find_first - find the first reusable entry with the given key
  * @cache: cache where we should search
  * @key: key to look for
  *
- * Search in @cache for entry with key @key. Grabs reference to the first
- * entry found and returns the entry.
+ * Search in @cache for a reusable entry with key @key. Grabs reference to the
+ * first reusable entry found and returns the entry.
  */
 struct mb_cache_entry *mb_cache_entry_find_first(struct mb_cache *cache,
 						 u32 key)
@@ -170,14 +170,14 @@ struct mb_cache_entry *mb_cache_entry_find_first(struct mb_cache *cache,
 EXPORT_SYMBOL(mb_cache_entry_find_first);
 
 /*
- * mb_cache_entry_find_next - find next entry in cache with the same
+ * mb_cache_entry_find_next - find next reusable entry with the same key
  * @cache: cache where we should search
  * @entry: entry to start search from
  *
- * Finds next entry in the hash chain which has the same key as @entry.
- * If @entry is unhashed (which can happen when deletion of entry races
- * with the search), finds the first entry in the hash chain. The function
- * drops reference to @entry and returns with a reference to the found entry.
+ * Finds next reusable entry in the hash chain which has the same key as @entry.
+ * If @entry is unhashed (which can happen when deletion of entry races with the
+ * search), finds the first reusable entry in the hash chain. The function drops
+ * reference to @entry and returns with a reference to the found entry.
  */
 struct mb_cache_entry *mb_cache_entry_find_next(struct mb_cache *cache,
 						struct mb_cache_entry *entry)
@@ -274,11 +274,11 @@ static unsigned long mb_cache_count(struct shrinker *shrink,
 
 /* Shrink number of entries in cache */
 static unsigned long mb_cache_shrink(struct mb_cache *cache,
-				     unsigned int nr_to_scan)
+				     unsigned long nr_to_scan)
 {
 	struct mb_cache_entry *entry;
 	struct hlist_bl_head *head;
-	unsigned int shrunk = 0;
+	unsigned long shrunk = 0;
 
 	spin_lock(&cache->c_list_lock);
 	while (nr_to_scan-- && !list_empty(&cache->c_list)) {
@@ -286,7 +286,7 @@ static unsigned long mb_cache_shrink(struct mb_cache *cache,
 					 struct mb_cache_entry, e_list);
 		if (entry->e_referenced) {
 			entry->e_referenced = 0;
-			list_move_tail(&cache->c_list, &entry->e_list);
+			list_move_tail(&entry->e_list, &cache->c_list);
 			continue;
 		}
 		list_del_init(&entry->e_list);
@@ -316,10 +316,9 @@ static unsigned long mb_cache_shrink(struct mb_cache *cache,
 static unsigned long mb_cache_scan(struct shrinker *shrink,
 				   struct shrink_control *sc)
 {
-	int nr_to_scan = sc->nr_to_scan;
 	struct mb_cache *cache = container_of(shrink, struct mb_cache,
 					      c_shrink);
-	return mb_cache_shrink(cache, nr_to_scan);
+	return mb_cache_shrink(cache, sc->nr_to_scan);
 }
 
 /* We shrink 1/X of the cache when we have too many entries in it */
@@ -341,11 +340,8 @@ static void mb_cache_shrink_worker(struct work_struct *work)
 struct mb_cache *mb_cache_create(int bucket_bits)
 {
 	struct mb_cache *cache;
-	int bucket_count = 1 << bucket_bits;
-	int i;
-
-	if (!try_module_get(THIS_MODULE))
-		return NULL;
+	unsigned long bucket_count = 1UL << bucket_bits;
+	unsigned long i;
 
 	cache = kzalloc(sizeof(struct mb_cache), GFP_KERNEL);
 	if (!cache)
@@ -377,7 +373,6 @@ struct mb_cache *mb_cache_create(int bucket_bits)
 	return cache;
 
 err_out:
-	module_put(THIS_MODULE);
 	return NULL;
 }
 EXPORT_SYMBOL(mb_cache_create);
@@ -411,7 +406,6 @@ void mb_cache_destroy(struct mb_cache *cache)
 	}
 	kfree(cache->c_hash);
 	kfree(cache);
-	module_put(THIS_MODULE);
 }
 EXPORT_SYMBOL(mb_cache_destroy);
 
@@ -420,7 +414,8 @@ static int __init mbcache_init(void)
 	mb_entry_cache = kmem_cache_create("mbcache",
 				sizeof(struct mb_cache_entry), 0,
 				SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL);
-	BUG_ON(!mb_entry_cache);
+	if (!mb_entry_cache)
+		return -ENOMEM;
 	return 0;
 }
 

fs/xfs/xfs_aops.c

@@ -1297,8 +1297,7 @@ __xfs_get_blocks(
 	sector_t		iblock,
 	struct buffer_head	*bh_result,
 	int			create,
-	bool			direct,
-	bool			dax_fault)
+	bool			direct)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
@@ -1419,13 +1418,8 @@ __xfs_get_blocks(
 		if (ISUNWRITTEN(&imap))
 			set_buffer_unwritten(bh_result);
 		/* direct IO needs special help */
-		if (create) {
-			if (dax_fault)
-				ASSERT(!ISUNWRITTEN(&imap));
-			else
-				xfs_map_direct(inode, bh_result, &imap, offset,
-						is_cow);
-		}
+		if (create)
+			xfs_map_direct(inode, bh_result, &imap, offset, is_cow);
 	}
 
 	/*
@@ -1465,7 +1459,7 @@ xfs_get_blocks(
 	struct buffer_head	*bh_result,
 	int			create)
 {
-	return __xfs_get_blocks(inode, iblock, bh_result, create, false, false);
+	return __xfs_get_blocks(inode, iblock, bh_result, create, false);
 }
 
 int
@@ -1475,17 +1469,7 @@ xfs_get_blocks_direct(
 	struct buffer_head	*bh_result,
 	int			create)
 {
-	return __xfs_get_blocks(inode, iblock, bh_result, create, true, false);
-}
-
-int
-xfs_get_blocks_dax_fault(
-	struct inode		*inode,
-	sector_t		iblock,
-	struct buffer_head	*bh_result,
-	int			create)
-{
-	return __xfs_get_blocks(inode, iblock, bh_result, create, true, true);
+	return __xfs_get_blocks(inode, iblock, bh_result, create, true);
 }
 
 /*

fs/xfs/xfs_aops.h

@@ -59,9 +59,6 @@ int	xfs_get_blocks(struct inode *inode, sector_t offset,
 		       struct buffer_head *map_bh, int create);
 int	xfs_get_blocks_direct(struct inode *inode, sector_t offset,
 			      struct buffer_head *map_bh, int create);
-int	xfs_get_blocks_dax_fault(struct inode *inode, sector_t offset,
-			         struct buffer_head *map_bh, int create);
-
 int	xfs_end_io_direct_write(struct kiocb *iocb, loff_t offset,
 		ssize_t size, void *private);
 int	xfs_setfilesize(struct xfs_inode *ip, xfs_off_t offset, size_t size);

fs/xfs/xfs_file.c

@@ -318,7 +318,7 @@ xfs_file_dax_read(
 		return 0; /* skip atime */
 
 	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
-	ret = iomap_dax_rw(iocb, to, &xfs_iomap_ops);
+	ret = dax_iomap_rw(iocb, to, &xfs_iomap_ops);
 	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 
 	file_accessed(iocb->ki_filp);
@@ -653,7 +653,7 @@ xfs_file_dax_write(
 
 	trace_xfs_file_dax_write(ip, count, pos);
 
-	ret = iomap_dax_rw(iocb, from, &xfs_iomap_ops);
+	ret = dax_iomap_rw(iocb, from, &xfs_iomap_ops);
 	if (ret > 0 && iocb->ki_pos > i_size_read(inode)) {
 		i_size_write(inode, iocb->ki_pos);
 		error = xfs_setfilesize(ip, pos, ret);
@@ -1474,7 +1474,7 @@ xfs_filemap_page_mkwrite(
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (IS_DAX(inode)) {
-		ret = iomap_dax_fault(vma, vmf, &xfs_iomap_ops);
+		ret = dax_iomap_fault(vma, vmf, &xfs_iomap_ops);
 	} else {
 		ret = iomap_page_mkwrite(vma, vmf, &xfs_iomap_ops);
 		ret = block_page_mkwrite_return(ret);
@@ -1508,7 +1508,7 @@ xfs_filemap_fault(
 		 * changes to xfs_get_blocks_direct() to map unwritten extent
 		 * ioend for conversion on read-only mappings.
 		 */
-		ret = iomap_dax_fault(vma, vmf, &xfs_iomap_ops);
+		ret = dax_iomap_fault(vma, vmf, &xfs_iomap_ops);
 	} else
 		ret = filemap_fault(vma, vmf);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
@@ -1545,7 +1545,7 @@ xfs_filemap_pmd_fault(
 	}
 
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	ret = dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault);
+	ret = dax_iomap_pmd_fault(vma, addr, pmd, flags, &xfs_iomap_ops);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (flags & FAULT_FLAG_WRITE)

include/linux/dax.h

@@ -8,21 +8,41 @@
 
 struct iomap_ops;
 
-/* We use lowest available exceptional entry bit for locking */
+/*
+ * We use lowest available bit in exceptional entry for locking, one bit for
+ * the entry size (PMD) and two more to tell us if the entry is a huge zero
+ * page (HZP) or an empty entry that is just used for locking.  In total four
+ * special bits.
+ *
+ * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the HZP and
+ * EMPTY bits aren't set the entry is a normal DAX entry with a filesystem
+ * block allocation.
+ */
+#define RADIX_DAX_SHIFT	(RADIX_TREE_EXCEPTIONAL_SHIFT + 4)
 #define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
+#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1))
+#define RADIX_DAX_HZP (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2))
+#define RADIX_DAX_EMPTY (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3))
 
-ssize_t iomap_dax_rw(struct kiocb *iocb, struct iov_iter *iter,
+static inline unsigned long dax_radix_sector(void *entry)
+{
+	return (unsigned long)entry >> RADIX_DAX_SHIFT;
+}
+
+static inline void *dax_radix_locked_entry(sector_t sector, unsigned long flags)
+{
+	return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags |
+			((unsigned long)sector << RADIX_DAX_SHIFT) |
+			RADIX_DAX_ENTRY_LOCK);
+}
+
+ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 		struct iomap_ops *ops);
-ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *,
-		  get_block_t, dio_iodone_t, int flags);
-int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
-int dax_truncate_page(struct inode *, loff_t from, get_block_t);
-int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 			struct iomap_ops *ops);
-int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t);
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
 void dax_wake_mapping_entry_waiter(struct address_space *mapping,
-				   pgoff_t index, bool wake_all);
+		pgoff_t index, void *entry, bool wake_all);
 
 #ifdef CONFIG_FS_DAX
 struct page *read_dax_sector(struct block_device *bdev, sector_t n);
@@ -48,18 +68,28 @@ static inline int __dax_zero_page_range(struct block_device *bdev,
 }
 #endif
 
-#if defined(CONFIG_TRANSPARENT_HUGEPAGE)
-int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
-				unsigned int flags, get_block_t);
+#ifdef CONFIG_FS_DAX_PMD
+static inline unsigned int dax_radix_order(void *entry)
+{
+	if ((unsigned long)entry & RADIX_DAX_PMD)
+		return PMD_SHIFT - PAGE_SHIFT;
+	return 0;
+}
+int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
+		pmd_t *pmd, unsigned int flags, struct iomap_ops *ops);
 #else
-static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
-				pmd_t *pmd, unsigned int flags, get_block_t gb)
+static inline unsigned int dax_radix_order(void *entry)
+{
+	return 0;
+}
+static inline int dax_iomap_pmd_fault(struct vm_area_struct *vma,
+		unsigned long address, pmd_t *pmd, unsigned int flags,
+		struct iomap_ops *ops)
 {
 	return VM_FAULT_FALLBACK;
 }
 #endif
 int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *);
-#define dax_mkwrite(vma, vmf, gb)	dax_fault(vma, vmf, gb)
 
 static inline bool vma_is_dax(struct vm_area_struct *vma)
 {

include/linux/fscrypto.h

@@ -18,73 +18,9 @@
 #include <crypto/skcipher.h>
 #include <uapi/linux/fs.h>
 
-#define FS_KEY_DERIVATION_NONCE_SIZE		16
-#define FS_ENCRYPTION_CONTEXT_FORMAT_V1		1
-
-#define FS_POLICY_FLAGS_PAD_4		0x00
-#define FS_POLICY_FLAGS_PAD_8		0x01
-#define FS_POLICY_FLAGS_PAD_16		0x02
-#define FS_POLICY_FLAGS_PAD_32		0x03
-#define FS_POLICY_FLAGS_PAD_MASK	0x03
-#define FS_POLICY_FLAGS_VALID		0x03
-
-/* Encryption algorithms */
-#define FS_ENCRYPTION_MODE_INVALID		0
-#define FS_ENCRYPTION_MODE_AES_256_XTS		1
-#define FS_ENCRYPTION_MODE_AES_256_GCM		2
-#define FS_ENCRYPTION_MODE_AES_256_CBC		3
-#define FS_ENCRYPTION_MODE_AES_256_CTS		4
-
-/**
- * Encryption context for inode
- *
- * Protector format:
- *  1 byte: Protector format (1 = this version)
- *  1 byte: File contents encryption mode
- *  1 byte: File names encryption mode
- *  1 byte: Flags
- *  8 bytes: Master Key descriptor
- *  16 bytes: Encryption Key derivation nonce
- */
-struct fscrypt_context {
-	u8 format;
-	u8 contents_encryption_mode;
-	u8 filenames_encryption_mode;
-	u8 flags;
-	u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
-	u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE];
-} __packed;
-
-/* Encryption parameters */
-#define FS_XTS_TWEAK_SIZE		16
-#define FS_AES_128_ECB_KEY_SIZE		16
-#define FS_AES_256_GCM_KEY_SIZE		32
-#define FS_AES_256_CBC_KEY_SIZE		32
-#define FS_AES_256_CTS_KEY_SIZE		32
-#define FS_AES_256_XTS_KEY_SIZE		64
-#define FS_MAX_KEY_SIZE			64
-
-#define FS_KEY_DESC_PREFIX		"fscrypt:"
-#define FS_KEY_DESC_PREFIX_SIZE		8
-
-/* This is passed in from userspace into the kernel keyring */
-struct fscrypt_key {
-	u32 mode;
-	u8 raw[FS_MAX_KEY_SIZE];
-	u32 size;
-} __packed;
-
-struct fscrypt_info {
-	u8 ci_data_mode;
-	u8 ci_filename_mode;
-	u8 ci_flags;
-	struct crypto_skcipher *ci_ctfm;
-	struct key *ci_keyring_key;
-	u8 ci_master_key[FS_KEY_DESCRIPTOR_SIZE];
-};
+#define FS_CRYPTO_BLOCK_SIZE		16
 
-#define FS_CTX_REQUIRES_FREE_ENCRYPT_FL		0x00000001
-#define FS_WRITE_PATH_FL			0x00000002
+struct fscrypt_info;
 
 struct fscrypt_ctx {
 	union {
@@ -102,19 +38,6 @@ struct fscrypt_ctx {
 	u8 mode;				/* Encryption mode for tfm */
 };
 
-struct fscrypt_completion_result {
-	struct completion completion;
-	int res;
-};
-
-#define DECLARE_FS_COMPLETION_RESULT(ecr) \
-	struct fscrypt_completion_result ecr = { \
-		COMPLETION_INITIALIZER((ecr).completion), 0 }
-
-#define FS_FNAME_NUM_SCATTER_ENTRIES	4
-#define FS_CRYPTO_BLOCK_SIZE		16
-#define FS_FNAME_CRYPTO_DIGEST_SIZE	32
-
 /**
  * For encrypted symlinks, the ciphertext length is stored at the beginning
  * of the string in little-endian format.
@@ -153,10 +76,16 @@ struct fscrypt_name {
 #define fname_name(p)		((p)->disk_name.name)
 #define fname_len(p)		((p)->disk_name.len)
 
+/*
+ * fscrypt superblock flags
+ */
+#define FS_CFLG_OWN_PAGES (1U << 1)
+
 /*
  * crypto opertions for filesystems
  */
 struct fscrypt_operations {
+	unsigned int flags;
 	int (*get_context)(struct inode *, void *, size_t);
 	int (*key_prefix)(struct inode *, u8 **);
 	int (*prepare_context)(struct inode *);
@@ -206,7 +135,7 @@ static inline struct page *fscrypt_control_page(struct page *page)
 #endif
 }
 
-static inline int fscrypt_has_encryption_key(struct inode *inode)
+static inline int fscrypt_has_encryption_key(const struct inode *inode)
 {
 #if IS_ENABLED(CONFIG_FS_ENCRYPTION)
 	return (inode->i_crypt_info != NULL);
@@ -238,25 +167,25 @@ static inline void fscrypt_set_d_op(struct dentry *dentry)
 #if IS_ENABLED(CONFIG_FS_ENCRYPTION)
 /* crypto.c */
 extern struct kmem_cache *fscrypt_info_cachep;
-int fscrypt_initialize(void);
-
-extern struct fscrypt_ctx *fscrypt_get_ctx(struct inode *, gfp_t);
+extern struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *, gfp_t);
 extern void fscrypt_release_ctx(struct fscrypt_ctx *);
-extern struct page *fscrypt_encrypt_page(struct inode *, struct page *, gfp_t);
-extern int fscrypt_decrypt_page(struct page *);
+extern struct page *fscrypt_encrypt_page(const struct inode *, struct page *,
+						unsigned int, unsigned int,
+						u64, gfp_t);
+extern int fscrypt_decrypt_page(const struct inode *, struct page *, unsigned int,
+				unsigned int, u64);
 extern void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *, struct bio *);
 extern void fscrypt_pullback_bio_page(struct page **, bool);
 extern void fscrypt_restore_control_page(struct page *);
-extern int fscrypt_zeroout_range(struct inode *, pgoff_t, sector_t,
+extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t,
 						unsigned int);
 /* policy.c */
-extern int fscrypt_process_policy(struct file *, const struct fscrypt_policy *);
-extern int fscrypt_get_policy(struct inode *, struct fscrypt_policy *);
+extern int fscrypt_ioctl_set_policy(struct file *, const void __user *);
+extern int fscrypt_ioctl_get_policy(struct file *, void __user *);
 extern int fscrypt_has_permitted_context(struct inode *, struct inode *);
 extern int fscrypt_inherit_context(struct inode *, struct inode *,
 					void *, bool);
 /* keyinfo.c */
-extern int get_crypt_info(struct inode *);
 extern int fscrypt_get_encryption_info(struct inode *);
 extern void fscrypt_put_encryption_info(struct inode *, struct fscrypt_info *);
 
@@ -264,8 +193,8 @@ extern void fscrypt_put_encryption_info(struct inode *, struct fscrypt_info *);
 extern int fscrypt_setup_filename(struct inode *, const struct qstr *,
 				int lookup, struct fscrypt_name *);
 extern void fscrypt_free_filename(struct fscrypt_name *);
-extern u32 fscrypt_fname_encrypted_size(struct inode *, u32);
-extern int fscrypt_fname_alloc_buffer(struct inode *, u32,
+extern u32 fscrypt_fname_encrypted_size(const struct inode *, u32);
+extern int fscrypt_fname_alloc_buffer(const struct inode *, u32,
 				struct fscrypt_str *);
 extern void fscrypt_fname_free_buffer(struct fscrypt_str *);
 extern int fscrypt_fname_disk_to_usr(struct inode *, u32, u32,
@@ -275,7 +204,7 @@ extern int fscrypt_fname_usr_to_disk(struct inode *, const struct qstr *,
 #endif
 
 /* crypto.c */
-static inline struct fscrypt_ctx *fscrypt_notsupp_get_ctx(struct inode *i,
+static inline struct fscrypt_ctx *fscrypt_notsupp_get_ctx(const struct inode *i,
 							gfp_t f)
 {
 	return ERR_PTR(-EOPNOTSUPP);
@@ -286,13 +215,18 @@ static inline void fscrypt_notsupp_release_ctx(struct fscrypt_ctx *c)
 	return;
 }
 
-static inline struct page *fscrypt_notsupp_encrypt_page(struct inode *i,
-						struct page *p, gfp_t f)
+static inline struct page *fscrypt_notsupp_encrypt_page(const struct inode *i,
+						struct page *p,
+						unsigned int len,
+						unsigned int offs,
+						u64 lblk_num, gfp_t f)
 {
 	return ERR_PTR(-EOPNOTSUPP);
 }
 
-static inline int fscrypt_notsupp_decrypt_page(struct page *p)
+static inline int fscrypt_notsupp_decrypt_page(const struct inode *i, struct page *p,
+						unsigned int len, unsigned int offs,
+						u64 lblk_num)
 {
 	return -EOPNOTSUPP;
 }
@@ -313,21 +247,21 @@ static inline void fscrypt_notsupp_restore_control_page(struct page *p)
 	return;
 }
 
-static inline int fscrypt_notsupp_zeroout_range(struct inode *i, pgoff_t p,
+static inline int fscrypt_notsupp_zeroout_range(const struct inode *i, pgoff_t p,
 					sector_t s, unsigned int f)
 {
 	return -EOPNOTSUPP;
 }
 
 /* policy.c */
-static inline int fscrypt_notsupp_process_policy(struct file *f,
-				const struct fscrypt_policy *p)
+static inline int fscrypt_notsupp_ioctl_set_policy(struct file *f,
+				const void __user *arg)
 {
 	return -EOPNOTSUPP;
 }
 
-static inline int fscrypt_notsupp_get_policy(struct inode *i,
-				struct fscrypt_policy *p)
+static inline int fscrypt_notsupp_ioctl_get_policy(struct file *f,
+				void __user *arg)
 {
 	return -EOPNOTSUPP;
 }

include/linux/iomap.h

@@ -49,6 +49,7 @@ struct iomap {
 #define IOMAP_WRITE		(1 << 0) /* writing, must allocate blocks */
 #define IOMAP_ZERO		(1 << 1) /* zeroing operation, may skip holes */
 #define IOMAP_REPORT		(1 << 2) /* report extent status, e.g. FIEMAP */
+#define IOMAP_FAULT		(1 << 3) /* mapping for page fault */
 
 struct iomap_ops {
 	/*

include/uapi/linux/fs.h

@@ -258,6 +258,20 @@ struct fsxattr {
 /* Policy provided via an ioctl on the topmost directory */
 #define FS_KEY_DESCRIPTOR_SIZE	8
 
+#define FS_POLICY_FLAGS_PAD_4		0x00
+#define FS_POLICY_FLAGS_PAD_8		0x01
+#define FS_POLICY_FLAGS_PAD_16		0x02
+#define FS_POLICY_FLAGS_PAD_32		0x03
+#define FS_POLICY_FLAGS_PAD_MASK	0x03
+#define FS_POLICY_FLAGS_VALID		0x03
+
+/* Encryption algorithms */
+#define FS_ENCRYPTION_MODE_INVALID		0
+#define FS_ENCRYPTION_MODE_AES_256_XTS		1
+#define FS_ENCRYPTION_MODE_AES_256_GCM		2
+#define FS_ENCRYPTION_MODE_AES_256_CBC		3
+#define FS_ENCRYPTION_MODE_AES_256_CTS		4
+
 struct fscrypt_policy {
 	__u8 version;
 	__u8 contents_encryption_mode;

mm/filemap.c

@@ -135,10 +135,9 @@ static int page_cache_tree_insert(struct address_space *mapping,
 		} else {
 			/* DAX can replace empty locked entry with a hole */
 			WARN_ON_ONCE(p !=
-				(void *)(RADIX_TREE_EXCEPTIONAL_ENTRY |
-					 RADIX_DAX_ENTRY_LOCK));
+				dax_radix_locked_entry(0, RADIX_DAX_EMPTY));
 			/* Wakeup waiters for exceptional entry lock */
-			dax_wake_mapping_entry_waiter(mapping, page->index,
+			dax_wake_mapping_entry_waiter(mapping, page->index, p,
 						      false);
 		}
 	}