Merge tag 'for-f2fs-4.6' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs

Pull f2fs updates from Jaegeuk Kim:
 "New Features:
   - uplift filesystem encryption into fs/crypto/
   - give sysfs entries to control memroy consumption

  Enhancements:
   - aio performance by preallocating blocks in ->write_iter
   - use writepages lock for only WB_SYNC_ALL
   - avoid redundant inline_data conversion
   - enhance forground GC
   - use wait_for_stable_page as possible
   - speed up SEEK_DATA and fiiemap

  Bug Fixes:
   - corner case in terms of -ENOSPC for inline_data
   - hung task caused by long latency in shrinker
   - corruption between atomic write and f2fs_trace_pid
   - avoid garbage lengths in dentries
   - revoke atomicly written pages if an error occurs

  In addition, there are various minor bug fixes and clean-ups"

* tag 'for-f2fs-4.6' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs: (81 commits)
  f2fs: submit node page write bios when really required
  f2fs: add missing argument to f2fs_setxattr stub
  f2fs: fix to avoid unneeded unlock_new_inode
  f2fs: clean up opened code with f2fs_update_dentry
  f2fs: declare static functions
  f2fs: use cryptoapi crc32 functions
  f2fs: modify the readahead method in ra_node_page()
  f2fs crypto: sync ext4_lookup and ext4_file_open
  fs crypto: move per-file encryption from f2fs tree to fs/crypto
  f2fs: mutex can't be used by down_write_nest_lock()
  f2fs: recovery missing dot dentries in root directory
  f2fs: fix to avoid deadlock when merging inline data
  f2fs: introduce f2fs_flush_merged_bios for cleanup
  f2fs: introduce f2fs_update_data_blkaddr for cleanup
  f2fs crypto: fix incorrect positioning for GCing encrypted data page
  f2fs: fix incorrect upper bound when iterating inode mapping tree
  f2fs: avoid hungtask problem caused by losing wake_up
  f2fs: trace old block address for CoWed page
  f2fs: try to flush inode after merging inline data
  f2fs: show more info about superblock recovery
  ...

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -98,3 +98,17 @@ Date:		October 2015
 Contact:	"Chao Yu" <chao2.yu@samsung.com>
 Description:
 		 Controls the count of nid pages to be readaheaded.
+
+What:		/sys/fs/f2fs/<disk>/dirty_nats_ratio
+Date:		January 2016
+Contact:	"Chao Yu" <chao2.yu@samsung.com>
+Description:
+		 Controls dirty nat entries ratio threshold, if current
+		 ratio exceeds configured threshold, checkpoint will
+		 be triggered for flushing dirty nat entries.
+
+What:		/sys/fs/f2fs/<disk>/lifetime_write_kbytes
+Date:		January 2016
+Contact:	"Shuoran Liu" <liushuoran@huawei.com>
+Description:
+		 Shows total written kbytes issued to disk.

fs/Kconfig

@@ -84,6 +84,8 @@ config MANDATORY_FILE_LOCKING
 
 	  To the best of my knowledge this is dead code that no one cares about.
 
+source "fs/crypto/Kconfig"
+
 source "fs/notify/Kconfig"
 
 source "fs/quota/Kconfig"

fs/Makefile

@@ -30,6 +30,7 @@ obj-$(CONFIG_EVENTFD)		+= eventfd.o
 obj-$(CONFIG_USERFAULTFD)	+= userfaultfd.o
 obj-$(CONFIG_AIO)               += aio.o
 obj-$(CONFIG_FS_DAX)		+= dax.o
+obj-$(CONFIG_FS_ENCRYPTION)	+= crypto/
 obj-$(CONFIG_FILE_LOCKING)      += locks.o
 obj-$(CONFIG_COMPAT)		+= compat.o compat_ioctl.o
 obj-$(CONFIG_BINFMT_AOUT)	+= binfmt_aout.o

fs/crypto/Kconfig

@@ -0,0 +1,18 @@
+config FS_ENCRYPTION
+	tristate "FS Encryption (Per-file encryption)"
+	depends on BLOCK
+	select CRYPTO
+	select CRYPTO_AES
+	select CRYPTO_CBC
+	select CRYPTO_ECB
+	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
+	  efficient since it avoids caching the encrypted and
+	  decrypted pages in the page cache.

fs/crypto/Makefile

@@ -0,0 +1,3 @@
+obj-$(CONFIG_FS_ENCRYPTION)	+= fscrypto.o
+
+fscrypto-y := crypto.o fname.o policy.o keyinfo.o

fs/crypto/crypto.c

@@ -0,0 +1,555 @@
+/*
+ * This contains encryption functions for per-file encryption.
+ *
+ * Copyright (C) 2015, Google, Inc.
+ * Copyright (C) 2015, Motorola Mobility
+ *
+ * Written by Michael Halcrow, 2014.
+ *
+ * Filename encryption additions
+ *	Uday Savagaonkar, 2014
+ * Encryption policy handling additions
+ *	Ildar Muslukhov, 2014
+ * Add fscrypt_pullback_bio_page()
+ *	Jaegeuk Kim, 2015.
+ *
+ * This has not yet undergone a rigorous security audit.
+ *
+ * The usage of AES-XTS should conform to recommendations in NIST
+ * Special Publication 800-38E and IEEE P1619/D16.
+ */
+
+#include <linux/pagemap.h>
+#include <linux/mempool.h>
+#include <linux/module.h>
+#include <linux/scatterlist.h>
+#include <linux/ratelimit.h>
+#include <linux/bio.h>
+#include <linux/dcache.h>
+#include <linux/fscrypto.h>
+#include <linux/ecryptfs.h>
+
+static unsigned int num_prealloc_crypto_pages = 32;
+static unsigned int num_prealloc_crypto_ctxs = 128;
+
+module_param(num_prealloc_crypto_pages, uint, 0444);
+MODULE_PARM_DESC(num_prealloc_crypto_pages,
+		"Number of crypto pages to preallocate");
+module_param(num_prealloc_crypto_ctxs, uint, 0444);
+MODULE_PARM_DESC(num_prealloc_crypto_ctxs,
+		"Number of crypto contexts to preallocate");
+
+static mempool_t *fscrypt_bounce_page_pool = NULL;
+
+static LIST_HEAD(fscrypt_free_ctxs);
+static DEFINE_SPINLOCK(fscrypt_ctx_lock);
+
+static struct workqueue_struct *fscrypt_read_workqueue;
+static DEFINE_MUTEX(fscrypt_init_mutex);
+
+static struct kmem_cache *fscrypt_ctx_cachep;
+struct kmem_cache *fscrypt_info_cachep;
+
+/**
+ * fscrypt_release_ctx() - Releases an encryption context
+ * @ctx: The encryption context to release.
+ *
+ * If the encryption context was allocated from the pre-allocated pool, returns
+ * it to that pool. Else, frees it.
+ *
+ * If there's a bounce page in the context, this frees that.
+ */
+void fscrypt_release_ctx(struct fscrypt_ctx *ctx)
+{
+	unsigned long flags;
+
+	if (ctx->flags & FS_WRITE_PATH_FL && ctx->w.bounce_page) {
+		mempool_free(ctx->w.bounce_page, fscrypt_bounce_page_pool);
+		ctx->w.bounce_page = NULL;
+	}
+	ctx->w.control_page = NULL;
+	if (ctx->flags & FS_CTX_REQUIRES_FREE_ENCRYPT_FL) {
+		kmem_cache_free(fscrypt_ctx_cachep, ctx);
+	} else {
+		spin_lock_irqsave(&fscrypt_ctx_lock, flags);
+		list_add(&ctx->free_list, &fscrypt_free_ctxs);
+		spin_unlock_irqrestore(&fscrypt_ctx_lock, flags);
+	}
+}
+EXPORT_SYMBOL(fscrypt_release_ctx);
+
+/**
+ * fscrypt_get_ctx() - Gets an encryption context
+ * @inode:       The inode for which we are doing the crypto
+ *
+ * Allocates and initializes an encryption context.
+ *
+ * Return: An allocated and initialized encryption context on success; error
+ * value or NULL otherwise.
+ */
+struct fscrypt_ctx *fscrypt_get_ctx(struct inode *inode)
+{
+	struct fscrypt_ctx *ctx = NULL;
+	struct fscrypt_info *ci = inode->i_crypt_info;
+	unsigned long flags;
+
+	if (ci == NULL)
+		return ERR_PTR(-ENOKEY);
+
+	/*
+	 * We first try getting the ctx from a free list because in
+	 * the common case the ctx will have an allocated and
+	 * initialized crypto tfm, so it's probably a worthwhile
+	 * optimization. For the bounce page, we first try getting it
+	 * from the kernel allocator because that's just about as fast
+	 * as getting it from a list and because a cache of free pages
+	 * should generally be a "last resort" option for a filesystem
+	 * to be able to do its job.
+	 */
+	spin_lock_irqsave(&fscrypt_ctx_lock, flags);
+	ctx = list_first_entry_or_null(&fscrypt_free_ctxs,
+					struct fscrypt_ctx, free_list);
+	if (ctx)
+		list_del(&ctx->free_list);
+	spin_unlock_irqrestore(&fscrypt_ctx_lock, flags);
+	if (!ctx) {
+		ctx = kmem_cache_zalloc(fscrypt_ctx_cachep, GFP_NOFS);
+		if (!ctx)
+			return ERR_PTR(-ENOMEM);
+		ctx->flags |= FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
+	} else {
+		ctx->flags &= ~FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
+	}
+	ctx->flags &= ~FS_WRITE_PATH_FL;
+	return ctx;
+}
+EXPORT_SYMBOL(fscrypt_get_ctx);
+
+/**
+ * fscrypt_complete() - The completion callback for page encryption
+ * @req: The asynchronous encryption request context
+ * @res: The result of the encryption operation
+ */
+static void fscrypt_complete(struct crypto_async_request *req, int res)
+{
+	struct fscrypt_completion_result *ecr = req->data;
+
+	if (res == -EINPROGRESS)
+		return;
+	ecr->res = res;
+	complete(&ecr->completion);
+}
+
+typedef enum {
+	FS_DECRYPT = 0,
+	FS_ENCRYPT,
+} fscrypt_direction_t;
+
+static int do_page_crypto(struct inode *inode,
+			fscrypt_direction_t rw, pgoff_t index,
+			struct page *src_page, struct page *dest_page)
+{
+	u8 xts_tweak[FS_XTS_TWEAK_SIZE];
+	struct skcipher_request *req = NULL;
+	DECLARE_FS_COMPLETION_RESULT(ecr);
+	struct scatterlist dst, src;
+	struct fscrypt_info *ci = inode->i_crypt_info;
+	struct crypto_skcipher *tfm = ci->ci_ctfm;
+	int res = 0;
+
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
+	if (!req) {
+		printk_ratelimited(KERN_ERR
+				"%s: crypto_request_alloc() failed\n",
+				__func__);
+		return -ENOMEM;
+	}
+
+	skcipher_request_set_callback(
+		req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+		fscrypt_complete, &ecr);
+
+	BUILD_BUG_ON(FS_XTS_TWEAK_SIZE < sizeof(index));
+	memcpy(xts_tweak, &inode->i_ino, sizeof(index));
+	memset(&xts_tweak[sizeof(index)], 0,
+			FS_XTS_TWEAK_SIZE - sizeof(index));
+
+	sg_init_table(&dst, 1);
+	sg_set_page(&dst, dest_page, PAGE_CACHE_SIZE, 0);
+	sg_init_table(&src, 1);
+	sg_set_page(&src, src_page, PAGE_CACHE_SIZE, 0);
+	skcipher_request_set_crypt(req, &src, &dst, PAGE_CACHE_SIZE,
+					xts_tweak);
+	if (rw == FS_DECRYPT)
+		res = crypto_skcipher_decrypt(req);
+	else
+		res = crypto_skcipher_encrypt(req);
+	if (res == -EINPROGRESS || res == -EBUSY) {
+		BUG_ON(req->base.data != &ecr);
+		wait_for_completion(&ecr.completion);
+		res = ecr.res;
+	}
+	skcipher_request_free(req);
+	if (res) {
+		printk_ratelimited(KERN_ERR
+			"%s: crypto_skcipher_encrypt() returned %d\n",
+			__func__, res);
+		return res;
+	}
+	return 0;
+}
+
+static struct page *alloc_bounce_page(struct fscrypt_ctx *ctx)
+{
+	ctx->w.bounce_page = mempool_alloc(fscrypt_bounce_page_pool,
+							GFP_NOWAIT);
+	if (ctx->w.bounce_page == NULL)
+		return ERR_PTR(-ENOMEM);
+	ctx->flags |= FS_WRITE_PATH_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.
+ *
+ * Allocates a ciphertext page and encrypts plaintext_page into it using the ctx
+ * encryption context.
+ *
+ * Called on the page write path.  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
+ * error value or NULL.
+ */
+struct page *fscrypt_encrypt_page(struct inode *inode,
+				struct page *plaintext_page)
+{
+	struct fscrypt_ctx *ctx;
+	struct page *ciphertext_page = NULL;
+	int err;
+
+	BUG_ON(!PageLocked(plaintext_page));
+
+	ctx = fscrypt_get_ctx(inode);
+	if (IS_ERR(ctx))
+		return (struct page *)ctx;
+
+	/* The encryption operation will require a bounce page. */
+	ciphertext_page = alloc_bounce_page(ctx);
+	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);
+	if (err) {
+		ciphertext_page = ERR_PTR(err);
+		goto errout;
+	}
+	SetPagePrivate(ciphertext_page);
+	set_page_private(ciphertext_page, (unsigned long)ctx);
+	lock_page(ciphertext_page);
+	return ciphertext_page;
+
+errout:
+	fscrypt_release_ctx(ctx);
+	return ciphertext_page;
+}
+EXPORT_SYMBOL(fscrypt_encrypt_page);
+
+/**
+ * f2crypt_decrypt_page() - Decrypts a page in-place
+ * @page: The page to decrypt. Must be locked.
+ *
+ * Decrypts page in-place using the ctx encryption context.
+ *
+ * Called from the read completion callback.
+ *
+ * Return: Zero on success, non-zero otherwise.
+ */
+int fscrypt_decrypt_page(struct page *page)
+{
+	BUG_ON(!PageLocked(page));
+
+	return do_page_crypto(page->mapping->host,
+			FS_DECRYPT, page->index, page, page);
+}
+EXPORT_SYMBOL(fscrypt_decrypt_page);
+
+int fscrypt_zeroout_range(struct inode *inode, pgoff_t lblk,
+				sector_t pblk, unsigned int len)
+{
+	struct fscrypt_ctx *ctx;
+	struct page *ciphertext_page = NULL;
+	struct bio *bio;
+	int ret, err = 0;
+
+	BUG_ON(inode->i_sb->s_blocksize != PAGE_CACHE_SIZE);
+
+	ctx = fscrypt_get_ctx(inode);
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
+
+	ciphertext_page = alloc_bounce_page(ctx);
+	if (IS_ERR(ciphertext_page)) {
+		err = PTR_ERR(ciphertext_page);
+		goto errout;
+	}
+
+	while (len--) {
+		err = do_page_crypto(inode, FS_ENCRYPT, lblk,
+						ZERO_PAGE(0), ciphertext_page);
+		if (err)
+			goto errout;
+
+		bio = bio_alloc(GFP_KERNEL, 1);
+		if (!bio) {
+			err = -ENOMEM;
+			goto errout;
+		}
+		bio->bi_bdev = inode->i_sb->s_bdev;
+		bio->bi_iter.bi_sector =
+			pblk << (inode->i_sb->s_blocksize_bits - 9);
+		ret = bio_add_page(bio, ciphertext_page,
+					inode->i_sb->s_blocksize, 0);
+		if (ret != inode->i_sb->s_blocksize) {
+			/* should never happen! */
+			WARN_ON(1);
+			bio_put(bio);
+			err = -EIO;
+			goto errout;
+		}
+		err = submit_bio_wait(WRITE, bio);
+		if ((err == 0) && bio->bi_error)
+			err = -EIO;
+		bio_put(bio);
+		if (err)
+			goto errout;
+		lblk++;
+		pblk++;
+	}
+	err = 0;
+errout:
+	fscrypt_release_ctx(ctx);
+	return err;
+}
+EXPORT_SYMBOL(fscrypt_zeroout_range);
+
+/*
+ * Validate dentries for encrypted directories to make sure we aren't
+ * potentially caching stale data after a key has been added or
+ * removed.
+ */
+static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	struct inode *dir = d_inode(dentry->d_parent);
+	struct fscrypt_info *ci = dir->i_crypt_info;
+	int dir_has_key, cached_with_key;
+
+	if (!dir->i_sb->s_cop->is_encrypted(dir))
+		return 0;
+
+	if (ci && ci->ci_keyring_key &&
+	    (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
+					  (1 << KEY_FLAG_REVOKED) |
+					  (1 << KEY_FLAG_DEAD))))
+		ci = NULL;
+
+	/* this should eventually be an flag in d_flags */
+	spin_lock(&dentry->d_lock);
+	cached_with_key = dentry->d_flags & DCACHE_ENCRYPTED_WITH_KEY;
+	spin_unlock(&dentry->d_lock);
+	dir_has_key = (ci != NULL);
+
+	/*
+	 * If the dentry was cached without the key, and it is a
+	 * negative dentry, it might be a valid name.  We can't check
+	 * if the key has since been made available due to locking
+	 * reasons, so we fail the validation so ext4_lookup() can do
+	 * this check.
+	 *
+	 * We also fail the validation if the dentry was created with
+	 * the key present, but we no longer have the key, or vice versa.
+	 */
+	if ((!cached_with_key && d_is_negative(dentry)) ||
+			(!cached_with_key && dir_has_key) ||
+			(cached_with_key && !dir_has_key))
+		return 0;
+	return 1;
+}
+
+const struct dentry_operations fscrypt_d_ops = {
+	.d_revalidate = fscrypt_d_revalidate,
+};
+EXPORT_SYMBOL(fscrypt_d_ops);
+
+/*
+ * Call fscrypt_decrypt_page on every single page, reusing the encryption
+ * context.
+ */
+static void completion_pages(struct work_struct *work)
+{
+	struct fscrypt_ctx *ctx =
+		container_of(work, struct fscrypt_ctx, r.work);
+	struct bio *bio = ctx->r.bio;
+	struct bio_vec *bv;
+	int i;
+
+	bio_for_each_segment_all(bv, bio, i) {
+		struct page *page = bv->bv_page;
+		int ret = fscrypt_decrypt_page(page);
+
+		if (ret) {
+			WARN_ON_ONCE(1);
+			SetPageError(page);
+		} else {
+			SetPageUptodate(page);
+		}
+		unlock_page(page);
+	}
+	fscrypt_release_ctx(ctx);
+	bio_put(bio);
+}
+
+void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *ctx, struct bio *bio)
+{
+	INIT_WORK(&ctx->r.work, completion_pages);
+	ctx->r.bio = bio;
+	queue_work(fscrypt_read_workqueue, &ctx->r.work);
+}
+EXPORT_SYMBOL(fscrypt_decrypt_bio_pages);
+
+void fscrypt_pullback_bio_page(struct page **page, bool restore)
+{
+	struct fscrypt_ctx *ctx;
+	struct page *bounce_page;
+
+	/* The bounce data pages are unmapped. */
+	if ((*page)->mapping)
+		return;
+
+	/* The bounce data page is unmapped. */
+	bounce_page = *page;
+	ctx = (struct fscrypt_ctx *)page_private(bounce_page);
+
+	/* restore control page */
+	*page = ctx->w.control_page;
+
+	if (restore)
+		fscrypt_restore_control_page(bounce_page);
+}
+EXPORT_SYMBOL(fscrypt_pullback_bio_page);
+
+void fscrypt_restore_control_page(struct page *page)
+{
+	struct fscrypt_ctx *ctx;
+
+	ctx = (struct fscrypt_ctx *)page_private(page);
+	set_page_private(page, (unsigned long)NULL);
+	ClearPagePrivate(page);
+	unlock_page(page);
+	fscrypt_release_ctx(ctx);
+}
+EXPORT_SYMBOL(fscrypt_restore_control_page);
+
+static void fscrypt_destroy(void)
+{
+	struct fscrypt_ctx *pos, *n;
+
+	list_for_each_entry_safe(pos, n, &fscrypt_free_ctxs, free_list)
+		kmem_cache_free(fscrypt_ctx_cachep, pos);
+	INIT_LIST_HEAD(&fscrypt_free_ctxs);
+	mempool_destroy(fscrypt_bounce_page_pool);
+	fscrypt_bounce_page_pool = NULL;
+}
+
+/**
+ * fscrypt_initialize() - allocate major buffers for fs encryption.
+ *
+ * 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 i, res = -ENOMEM;
+
+	if (fscrypt_bounce_page_pool)
+		return 0;
+
+	mutex_lock(&fscrypt_init_mutex);
+	if (fscrypt_bounce_page_pool)
+		goto already_initialized;
+
+	for (i = 0; i < num_prealloc_crypto_ctxs; i++) {
+		struct fscrypt_ctx *ctx;
+
+		ctx = kmem_cache_zalloc(fscrypt_ctx_cachep, GFP_NOFS);
+		if (!ctx)
+			goto fail;
+		list_add(&ctx->free_list, &fscrypt_free_ctxs);
+	}
+
+	fscrypt_bounce_page_pool =
+		mempool_create_page_pool(num_prealloc_crypto_pages, 0);
+	if (!fscrypt_bounce_page_pool)
+		goto fail;
+
+already_initialized:
+	mutex_unlock(&fscrypt_init_mutex);
+	return 0;
+fail:
+	fscrypt_destroy();
+	mutex_unlock(&fscrypt_init_mutex);
+	return res;
+}
+EXPORT_SYMBOL(fscrypt_initialize);
+
+/**
+ * fscrypt_init() - Set up for fs encryption.
+ */
+static int __init fscrypt_init(void)
+{
+	fscrypt_read_workqueue = alloc_workqueue("fscrypt_read_queue",
+							WQ_HIGHPRI, 0);
+	if (!fscrypt_read_workqueue)
+		goto fail;
+
+	fscrypt_ctx_cachep = KMEM_CACHE(fscrypt_ctx, SLAB_RECLAIM_ACCOUNT);
+	if (!fscrypt_ctx_cachep)
+		goto fail_free_queue;
+
+	fscrypt_info_cachep = KMEM_CACHE(fscrypt_info, SLAB_RECLAIM_ACCOUNT);
+	if (!fscrypt_info_cachep)
+		goto fail_free_ctx;
+
+	return 0;
+
+fail_free_ctx:
+	kmem_cache_destroy(fscrypt_ctx_cachep);
+fail_free_queue:
+	destroy_workqueue(fscrypt_read_workqueue);
+fail:
+	return -ENOMEM;
+}
+module_init(fscrypt_init)
+
+/**
+ * fscrypt_exit() - Shutdown the fs encryption system
+ */
+static void __exit fscrypt_exit(void)
+{
+	fscrypt_destroy();
+
+	if (fscrypt_read_workqueue)
+		destroy_workqueue(fscrypt_read_workqueue);
+	kmem_cache_destroy(fscrypt_ctx_cachep);
+	kmem_cache_destroy(fscrypt_info_cachep);
+}
+module_exit(fscrypt_exit);
+
+MODULE_LICENSE("GPL");

fs/crypto/fname.c

@@ -1,44 +1,32 @@
 /*
- * linux/fs/f2fs/crypto_fname.c
+ * This contains functions for filename crypto management
- *
- * Copied from linux/fs/ext4/crypto.c
  *
  * Copyright (C) 2015, Google, Inc.
  * Copyright (C) 2015, Motorola Mobility
  *
- * This contains functions for filename crypto management in f2fs
- *
  * Written by Uday Savagaonkar, 2014.
- *
+ * Modified by Jaegeuk Kim, 2015.
- * Adjust f2fs dentry structure
- *	Jaegeuk Kim, 2015.
  *
  * This has not yet undergone a rigorous security audit.
  */
-#include <crypto/skcipher.h>
+
 #include <keys/encrypted-type.h>
 #include <keys/user-type.h>
-#include <linux/gfp.h>
-#include <linux/kernel.h>
-#include <linux/key.h>
-#include <linux/list.h>
-#include <linux/mempool.h>
-#include <linux/random.h>
 #include <linux/scatterlist.h>
-#include <linux/spinlock_types.h>
-#include <linux/f2fs_fs.h>
 #include <linux/ratelimit.h>
+#include <linux/fscrypto.h>
 
-#include "f2fs.h"
+static u32 size_round_up(size_t size, size_t blksize)
-#include "f2fs_crypto.h"
+{
-#include "xattr.h"
+	return ((size + blksize - 1) / blksize) * blksize;
+}
 
 /**
- * f2fs_dir_crypt_complete() -
+ * dir_crypt_complete() -
  */
-static void f2fs_dir_crypt_complete(struct crypto_async_request *req, int res)
+static void dir_crypt_complete(struct crypto_async_request *req, int res)
 {
-	struct f2fs_completion_result *ecr = req->data;
+	struct fscrypt_completion_result *ecr = req->data;
 
 	if (res == -EINPROGRESS)
 		return;
@@ -46,45 +34,35 @@ static void f2fs_dir_crypt_complete(struct crypto_async_request *req, int res)
 	complete(&ecr->completion);
 }
 
-bool f2fs_valid_filenames_enc_mode(uint32_t mode)
-{
-	return (mode == F2FS_ENCRYPTION_MODE_AES_256_CTS);
-}
-
-static unsigned max_name_len(struct inode *inode)
-{
-	return S_ISLNK(inode->i_mode) ? inode->i_sb->s_blocksize :
-					F2FS_NAME_LEN;
-}
-
 /**
- * f2fs_fname_encrypt() -
+ * fname_encrypt() -
  *
  * This function encrypts the input filename, and returns the length of the
  * ciphertext. Errors are returned as negative numbers.  We trust the caller to
  * allocate sufficient memory to oname string.
  */
-static int f2fs_fname_encrypt(struct inode *inode,
+static int fname_encrypt(struct inode *inode,
-			const struct qstr *iname, struct f2fs_str *oname)
+			const struct qstr *iname, struct fscrypt_str *oname)
 {
 	u32 ciphertext_len;
 	struct skcipher_request *req = NULL;
-	DECLARE_F2FS_COMPLETION_RESULT(ecr);
+	DECLARE_FS_COMPLETION_RESULT(ecr);
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
+	struct fscrypt_info *ci = inode->i_crypt_info;
 	struct crypto_skcipher *tfm = ci->ci_ctfm;
 	int res = 0;
-	char iv[F2FS_CRYPTO_BLOCK_SIZE];
+	char iv[FS_CRYPTO_BLOCK_SIZE];
 	struct scatterlist src_sg, dst_sg;
-	int padding = 4 << (ci->ci_flags & F2FS_POLICY_FLAGS_PAD_MASK);
+	int padding = 4 << (ci->ci_flags & FS_POLICY_FLAGS_PAD_MASK);
 	char *workbuf, buf[32], *alloc_buf = NULL;
-	unsigned lim = max_name_len(inode);
+	unsigned lim;
 
+	lim = inode->i_sb->s_cop->max_namelen(inode);
 	if (iname->len <= 0 || iname->len > lim)
 		return -EIO;
 
-	ciphertext_len = (iname->len < F2FS_CRYPTO_BLOCK_SIZE) ?
+	ciphertext_len = (iname->len < FS_CRYPTO_BLOCK_SIZE) ?
-		F2FS_CRYPTO_BLOCK_SIZE : iname->len;
+					FS_CRYPTO_BLOCK_SIZE : iname->len;
-	ciphertext_len = f2fs_fname_crypto_round_up(ciphertext_len, padding);
+	ciphertext_len = size_round_up(ciphertext_len, padding);
 	ciphertext_len = (ciphertext_len > lim) ? lim : ciphertext_len;
 
 	if (ciphertext_len <= sizeof(buf)) {
@@ -106,7 +84,7 @@ static int f2fs_fname_encrypt(struct inode *inode,
 	}
 	skcipher_request_set_callback(req,
 			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
-			f2fs_dir_crypt_complete, &ecr);
+			dir_crypt_complete, &ecr);
 
 	/* Copy the input */
 	memcpy(workbuf, iname->name, iname->len);
@@ -114,7 +92,7 @@ static int f2fs_fname_encrypt(struct inode *inode,
 		memset(workbuf + iname->len, 0, ciphertext_len - iname->len);
 
 	/* Initialize IV */
-	memset(iv, 0, F2FS_CRYPTO_BLOCK_SIZE);
+	memset(iv, 0, FS_CRYPTO_BLOCK_SIZE);
 
 	/* Create encryption request */
 	sg_init_one(&src_sg, workbuf, ciphertext_len);
@@ -122,39 +100,40 @@ static int f2fs_fname_encrypt(struct inode *inode,
 	skcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv);
 	res = crypto_skcipher_encrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
-		BUG_ON(req->base.data != &ecr);
 		wait_for_completion(&ecr.completion);
 		res = ecr.res;
 	}
 	kfree(alloc_buf);
 	skcipher_request_free(req);
-	if (res < 0) {
+	if (res < 0)
 		printk_ratelimited(KERN_ERR
 				"%s: Error (error code %d)\n", __func__, res);
-	}
+
 	oname->len = ciphertext_len;
 	return res;
 }
 
 /*
- * f2fs_fname_decrypt()
+ * fname_decrypt()
  *	This function decrypts the input filename, and returns
  *	the length of the plaintext.
  *	Errors are returned as negative numbers.
  *	We trust the caller to allocate sufficient memory to oname string.
  */
-static int f2fs_fname_decrypt(struct inode *inode,
+static int fname_decrypt(struct inode *inode,
-			const struct f2fs_str *iname, struct f2fs_str *oname)
+				const struct fscrypt_str *iname,
+				struct fscrypt_str *oname)
 {
 	struct skcipher_request *req = NULL;
-	DECLARE_F2FS_COMPLETION_RESULT(ecr);
+	DECLARE_FS_COMPLETION_RESULT(ecr);
 	struct scatterlist src_sg, dst_sg;
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
+	struct fscrypt_info *ci = inode->i_crypt_info;
 	struct crypto_skcipher *tfm = ci->ci_ctfm;
 	int res = 0;
-	char iv[F2FS_CRYPTO_BLOCK_SIZE];
+	char iv[FS_CRYPTO_BLOCK_SIZE];
-	unsigned lim = max_name_len(inode);
+	unsigned lim;
 
+	lim = inode->i_sb->s_cop->max_namelen(inode);
 	if (iname->len <= 0 || iname->len > lim)
 		return -EIO;
 
@@ -167,10 +146,10 @@ static int f2fs_fname_decrypt(struct inode *inode,
 	}
 	skcipher_request_set_callback(req,
 		CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
-		f2fs_dir_crypt_complete, &ecr);
+		dir_crypt_complete, &ecr);
 
 	/* Initialize IV */
-	memset(iv, 0, F2FS_CRYPTO_BLOCK_SIZE);
+	memset(iv, 0, FS_CRYPTO_BLOCK_SIZE);
 
 	/* Create decryption request */
 	sg_init_one(&src_sg, iname->name, iname->len);
@@ -178,15 +157,13 @@ static int f2fs_fname_decrypt(struct inode *inode,
 	skcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv);
 	res = crypto_skcipher_decrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
-		BUG_ON(req->base.data != &ecr);
 		wait_for_completion(&ecr.completion);
 		res = ecr.res;
 	}
 	skcipher_request_free(req);
 	if (res < 0) {
 		printk_ratelimited(KERN_ERR
-			"%s: Error in f2fs_fname_decrypt (error code %d)\n",
+				"%s: Error (error code %d)\n", __func__, res);
-			__func__, res);
 		return res;
 	}
 
@@ -198,7 +175,7 @@ static const char *lookup_table =
 	"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,";
 
 /**
- * f2fs_fname_encode_digest() -
+ * digest_encode() -
  *
  * Encodes the input digest using characters from the set [a-zA-Z0-9_+].
  * The encoded string is roughly 4/3 times the size of the input string.
@@ -247,148 +224,152 @@ static int digest_decode(const char *src, int len, char *dst)
 	return cp - dst;
 }
 
-/**
+u32 fscrypt_fname_encrypted_size(struct inode *inode, u32 ilen)
- * f2fs_fname_crypto_round_up() -
- *
- * Return: The next multiple of block size
- */
-u32 f2fs_fname_crypto_round_up(u32 size, u32 blksize)
 {
-	return ((size + blksize - 1) / blksize) * blksize;
+	int padding = 32;
+	struct fscrypt_info *ci = inode->i_crypt_info;
+
+	if (ci)
+		padding = 4 << (ci->ci_flags & FS_POLICY_FLAGS_PAD_MASK);
+	if (ilen < FS_CRYPTO_BLOCK_SIZE)
+		ilen = FS_CRYPTO_BLOCK_SIZE;
+	return size_round_up(ilen, padding);
 }
+EXPORT_SYMBOL(fscrypt_fname_encrypted_size);
 
 /**
- * f2fs_fname_crypto_alloc_obuff() -
+ * fscrypt_fname_crypto_alloc_obuff() -
  *
  * Allocates an output buffer that is sufficient for the crypto operation
  * specified by the context and the direction.
  */
-int f2fs_fname_crypto_alloc_buffer(struct inode *inode,
+int fscrypt_fname_alloc_buffer(struct inode *inode,
-				   u32 ilen, struct f2fs_str *crypto_str)
+				u32 ilen, struct fscrypt_str *crypto_str)
 {
-	unsigned int olen;
+	unsigned int olen = fscrypt_fname_encrypted_size(inode, ilen);
-	int padding = 16;
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
 
-	if (ci)
-		padding = 4 << (ci->ci_flags & F2FS_POLICY_FLAGS_PAD_MASK);
-	if (padding < F2FS_CRYPTO_BLOCK_SIZE)
-		padding = F2FS_CRYPTO_BLOCK_SIZE;
-	olen = f2fs_fname_crypto_round_up(ilen, padding);
 	crypto_str->len = olen;
-	if (olen < F2FS_FNAME_CRYPTO_DIGEST_SIZE * 2)
+	if (olen < FS_FNAME_CRYPTO_DIGEST_SIZE * 2)
-		olen = F2FS_FNAME_CRYPTO_DIGEST_SIZE * 2;
+		olen = FS_FNAME_CRYPTO_DIGEST_SIZE * 2;
-	/* Allocated buffer can hold one more character to null-terminate the
+	/*
-	 * string */
+	 * Allocated buffer can hold one more character to null-terminate the
+	 * string
+	 */
 	crypto_str->name = kmalloc(olen + 1, GFP_NOFS);
 	if (!(crypto_str->name))
 		return -ENOMEM;
 	return 0;
 }
+EXPORT_SYMBOL(fscrypt_fname_alloc_buffer);
 
 /**
- * f2fs_fname_crypto_free_buffer() -
+ * fscrypt_fname_crypto_free_buffer() -
  *
  * Frees the buffer allocated for crypto operation.
  */
-void f2fs_fname_crypto_free_buffer(struct f2fs_str *crypto_str)
+void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str)
 {
 	if (!crypto_str)
 		return;
 	kfree(crypto_str->name);
 	crypto_str->name = NULL;
 }
+EXPORT_SYMBOL(fscrypt_fname_free_buffer);
 
 /**
- * f2fs_fname_disk_to_usr() - converts a filename from disk space to user space
+ * fscrypt_fname_disk_to_usr() - converts a filename from disk space to user
+ * space
  */
-int f2fs_fname_disk_to_usr(struct inode *inode,
+int fscrypt_fname_disk_to_usr(struct inode *inode,
-			f2fs_hash_t *hash,
+			u32 hash, u32 minor_hash,
-			const struct f2fs_str *iname,
+			const struct fscrypt_str *iname,
-			struct f2fs_str *oname)
+			struct fscrypt_str *oname)
 {
 	const struct qstr qname = FSTR_TO_QSTR(iname);
 	char buf[24];
 	int ret;
 
-	if (is_dot_dotdot(&qname)) {
+	if (fscrypt_is_dot_dotdot(&qname)) {
 		oname->name[0] = '.';
 		oname->name[iname->len - 1] = '.';
 		oname->len = iname->len;
 		return oname->len;
 	}
 
-	if (F2FS_I(inode)->i_crypt_info)
+	if (iname->len < FS_CRYPTO_BLOCK_SIZE)
-		return f2fs_fname_decrypt(inode, iname, oname);
+		return -EUCLEAN;
 
-	if (iname->len <= F2FS_FNAME_CRYPTO_DIGEST_SIZE) {
+	if (inode->i_crypt_info)
+		return fname_decrypt(inode, iname, oname);
+
+	if (iname->len <= FS_FNAME_CRYPTO_DIGEST_SIZE) {
 		ret = digest_encode(iname->name, iname->len, oname->name);
 		oname->len = ret;
 		return ret;
 	}
 	if (hash) {
-		memcpy(buf, hash, 4);
+		memcpy(buf, &hash, 4);
-		memset(buf + 4, 0, 4);
+		memcpy(buf + 4, &minor_hash, 4);
-	} else
+	} else {
 		memset(buf, 0, 8);
+	}
 	memcpy(buf + 8, iname->name + iname->len - 16, 16);
 	oname->name[0] = '_';
 	ret = digest_encode(buf, 24, oname->name + 1);
 	oname->len = ret + 1;
 	return ret + 1;
 }
+EXPORT_SYMBOL(fscrypt_fname_disk_to_usr);
 
 /**
- * f2fs_fname_usr_to_disk() - converts a filename from user space to disk space
+ * fscrypt_fname_usr_to_disk() - converts a filename from user space to disk
+ * space
  */
-int f2fs_fname_usr_to_disk(struct inode *inode,
+int fscrypt_fname_usr_to_disk(struct inode *inode,
 			const struct qstr *iname,
-			struct f2fs_str *oname)
+			struct fscrypt_str *oname)
 {
-	int res;
+	if (fscrypt_is_dot_dotdot(iname)) {
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
-
-	if (is_dot_dotdot(iname)) {
 		oname->name[0] = '.';
 		oname->name[iname->len - 1] = '.';
 		oname->len = iname->len;
 		return oname->len;
 	}
-
+	if (inode->i_crypt_info)
-	if (ci) {
+		return fname_encrypt(inode, iname, oname);
-		res = f2fs_fname_encrypt(inode, iname, oname);
+	/*
-		return res;
+	 * Without a proper key, a user is not allowed to modify the filenames
-	}
-	/* Without a proper key, a user is not allowed to modify the filenames
 	 * in a directory. Consequently, a user space name cannot be mapped to
-	 * a disk-space name */
+	 * a disk-space name
+	 */
 	return -EACCES;
 }
+EXPORT_SYMBOL(fscrypt_fname_usr_to_disk);
 
-int f2fs_fname_setup_filename(struct inode *dir, const struct qstr *iname,
+int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
-			      int lookup, struct f2fs_filename *fname)
+			      int lookup, struct fscrypt_name *fname)
 {
-	struct f2fs_crypt_info *ci;
 	int ret = 0, bigname = 0;
 
-	memset(fname, 0, sizeof(struct f2fs_filename));
+	memset(fname, 0, sizeof(struct fscrypt_name));
 	fname->usr_fname = iname;
 
-	if (!f2fs_encrypted_inode(dir) || is_dot_dotdot(iname)) {
+	if (!dir->i_sb->s_cop->is_encrypted(dir) ||
+				fscrypt_is_dot_dotdot(iname)) {
 		fname->disk_name.name = (unsigned char *)iname->name;
 		fname->disk_name.len = iname->len;
 		return 0;
 	}
-	ret = f2fs_get_encryption_info(dir);
+	ret = get_crypt_info(dir);
-	if (ret)
+	if (ret && ret != -EOPNOTSUPP)
 		return ret;
-	ci = F2FS_I(dir)->i_crypt_info;
+
-	if (ci) {
+	if (dir->i_crypt_info) {
-		ret = f2fs_fname_crypto_alloc_buffer(dir, iname->len,
+		ret = fscrypt_fname_alloc_buffer(dir, iname->len,
-						     &fname->crypto_buf);
+							&fname->crypto_buf);
 		if (ret < 0)
 			return ret;
-		ret = f2fs_fname_encrypt(dir, iname, &fname->crypto_buf);
+		ret = fname_encrypt(dir, iname, &fname->crypto_buf);
 		if (ret < 0)
 			goto errout;
 		fname->disk_name.name = fname->crypto_buf.name;
@@ -398,18 +379,19 @@ int f2fs_fname_setup_filename(struct inode *dir, const struct qstr *iname,
 	if (!lookup)
 		return -EACCES;
 
-	/* We don't have the key and we are doing a lookup; decode the
+	/*
+	 * We don't have the key and we are doing a lookup; decode the
 	 * user-supplied name
 	 */
 	if (iname->name[0] == '_')
 		bigname = 1;
-	if ((bigname && (iname->len != 33)) ||
+	if ((bigname && (iname->len != 33)) || (!bigname && (iname->len > 43)))
-	    (!bigname && (iname->len > 43)))
 		return -ENOENT;
 
 	fname->crypto_buf.name = kmalloc(32, GFP_KERNEL);
 	if (fname->crypto_buf.name == NULL)
 		return -ENOMEM;
+
 	ret = digest_decode(iname->name + bigname, iname->len - bigname,
 				fname->crypto_buf.name);
 	if (ret < 0) {
@@ -419,20 +401,24 @@ int f2fs_fname_setup_filename(struct inode *dir, const struct qstr *iname,
 	fname->crypto_buf.len = ret;
 	if (bigname) {
 		memcpy(&fname->hash, fname->crypto_buf.name, 4);
+		memcpy(&fname->minor_hash, fname->crypto_buf.name + 4, 4);
 	} else {
 		fname->disk_name.name = fname->crypto_buf.name;
 		fname->disk_name.len = fname->crypto_buf.len;
 	}
 	return 0;
+
 errout:
-	f2fs_fname_crypto_free_buffer(&fname->crypto_buf);
+	fscrypt_fname_free_buffer(&fname->crypto_buf);
 	return ret;
 }
+EXPORT_SYMBOL(fscrypt_setup_filename);
 
-void f2fs_fname_free_filename(struct f2fs_filename *fname)
+void fscrypt_free_filename(struct fscrypt_name *fname)
 {
 	kfree(fname->crypto_buf.name);
 	fname->crypto_buf.name = NULL;
 	fname->usr_fname = NULL;
 	fname->disk_name.name = NULL;
 }
+EXPORT_SYMBOL(fscrypt_free_filename);

fs/crypto/keyinfo.c

@@ -0,0 +1,272 @@
+/*
+ * key management facility for FS encryption support.
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This contains encryption key functions.
+ *
+ * Written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar, 2015.
+ */
+
+#include <keys/encrypted-type.h>
+#include <keys/user-type.h>
+#include <linux/random.h>
+#include <linux/scatterlist.h>
+#include <uapi/linux/keyctl.h>
+#include <linux/fscrypto.h>
+
+static void derive_crypt_complete(struct crypto_async_request *req, int rc)
+{
+	struct fscrypt_completion_result *ecr = req->data;
+
+	if (rc == -EINPROGRESS)
+		return;
+
+	ecr->res = rc;
+	complete(&ecr->completion);
+}
+
+/**
+ * derive_key_aes() - Derive a key using AES-128-ECB
+ * @deriving_key: Encryption key used for derivation.
+ * @source_key:   Source key to which to apply derivation.
+ * @derived_key:  Derived key.
+ *
+ * Return: Zero on success; non-zero otherwise.
+ */
+static int derive_key_aes(u8 deriving_key[FS_AES_128_ECB_KEY_SIZE],
+				u8 source_key[FS_AES_256_XTS_KEY_SIZE],
+				u8 derived_key[FS_AES_256_XTS_KEY_SIZE])
+{
+	int res = 0;
+	struct skcipher_request *req = NULL;
+	DECLARE_FS_COMPLETION_RESULT(ecr);
+	struct scatterlist src_sg, dst_sg;
+	struct crypto_skcipher *tfm = crypto_alloc_skcipher("ecb(aes)", 0, 0);
+
+	if (IS_ERR(tfm)) {
+		res = PTR_ERR(tfm);
+		tfm = NULL;
+		goto out;
+	}
+	crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
+	if (!req) {
+		res = -ENOMEM;
+		goto out;
+	}
+	skcipher_request_set_callback(req,
+			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+			derive_crypt_complete, &ecr);
+	res = crypto_skcipher_setkey(tfm, deriving_key,
+					FS_AES_128_ECB_KEY_SIZE);
+	if (res < 0)
+		goto out;
+
+	sg_init_one(&src_sg, source_key, FS_AES_256_XTS_KEY_SIZE);
+	sg_init_one(&dst_sg, derived_key, FS_AES_256_XTS_KEY_SIZE);
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg,
+					FS_AES_256_XTS_KEY_SIZE, NULL);
+	res = crypto_skcipher_encrypt(req);
+	if (res == -EINPROGRESS || res == -EBUSY) {
+		wait_for_completion(&ecr.completion);
+		res = ecr.res;
+	}
+out:
+	skcipher_request_free(req);
+	crypto_free_skcipher(tfm);
+	return res;
+}
+
+static void put_crypt_info(struct fscrypt_info *ci)
+{
+	if (!ci)
+		return;
+
+	key_put(ci->ci_keyring_key);
+	crypto_free_skcipher(ci->ci_ctfm);
+	kmem_cache_free(fscrypt_info_cachep, ci);
+}
+
+int get_crypt_info(struct inode *inode)
+{
+	struct fscrypt_info *crypt_info;
+	u8 full_key_descriptor[FS_KEY_DESC_PREFIX_SIZE +
+				(FS_KEY_DESCRIPTOR_SIZE * 2) + 1];
+	struct key *keyring_key = NULL;
+	struct fscrypt_key *master_key;
+	struct fscrypt_context ctx;
+	const struct user_key_payload *ukp;
+	struct crypto_skcipher *ctfm;
+	const char *cipher_str;
+	u8 raw_key[FS_MAX_KEY_SIZE];
+	u8 mode;
+	int res;
+
+	res = fscrypt_initialize();
+	if (res)
+		return res;
+
+	if (!inode->i_sb->s_cop->get_context)
+		return -EOPNOTSUPP;
+retry:
+	crypt_info = ACCESS_ONCE(inode->i_crypt_info);
+	if (crypt_info) {
+		if (!crypt_info->ci_keyring_key ||
+				key_validate(crypt_info->ci_keyring_key) == 0)
+			return 0;
+		fscrypt_put_encryption_info(inode, crypt_info);
+		goto retry;
+	}
+
+	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+	if (res < 0) {
+		if (!fscrypt_dummy_context_enabled(inode))
+			return res;
+		ctx.contents_encryption_mode = FS_ENCRYPTION_MODE_AES_256_XTS;
+		ctx.filenames_encryption_mode = FS_ENCRYPTION_MODE_AES_256_CTS;
+		ctx.flags = 0;
+	} else if (res != sizeof(ctx)) {
+		return -EINVAL;
+	}
+	res = 0;
+
+	crypt_info = kmem_cache_alloc(fscrypt_info_cachep, GFP_NOFS);
+	if (!crypt_info)
+		return -ENOMEM;
+
+	crypt_info->ci_flags = ctx.flags;
+	crypt_info->ci_data_mode = ctx.contents_encryption_mode;
+	crypt_info->ci_filename_mode = ctx.filenames_encryption_mode;
+	crypt_info->ci_ctfm = NULL;
+	crypt_info->ci_keyring_key = NULL;
+	memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor,
+				sizeof(crypt_info->ci_master_key));
+	if (S_ISREG(inode->i_mode))
+		mode = crypt_info->ci_data_mode;
+	else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+		mode = crypt_info->ci_filename_mode;
+	else
+		BUG();
+
+	switch (mode) {
+	case FS_ENCRYPTION_MODE_AES_256_XTS:
+		cipher_str = "xts(aes)";
+		break;
+	case FS_ENCRYPTION_MODE_AES_256_CTS:
+		cipher_str = "cts(cbc(aes))";
+		break;
+	default:
+		printk_once(KERN_WARNING
+			    "%s: unsupported key mode %d (ino %u)\n",
+			    __func__, mode, (unsigned) inode->i_ino);
+		res = -ENOKEY;
+		goto out;
+	}
+	if (fscrypt_dummy_context_enabled(inode)) {
+		memset(raw_key, 0x42, FS_AES_256_XTS_KEY_SIZE);
+		goto got_key;
+	}
+	memcpy(full_key_descriptor, FS_KEY_DESC_PREFIX,
+					FS_KEY_DESC_PREFIX_SIZE);
+	sprintf(full_key_descriptor + FS_KEY_DESC_PREFIX_SIZE,
+					"%*phN", FS_KEY_DESCRIPTOR_SIZE,
+					ctx.master_key_descriptor);
+	full_key_descriptor[FS_KEY_DESC_PREFIX_SIZE +
+					(2 * FS_KEY_DESCRIPTOR_SIZE)] = '\0';
+	keyring_key = request_key(&key_type_logon, full_key_descriptor, NULL);
+	if (IS_ERR(keyring_key)) {
+		res = PTR_ERR(keyring_key);
+		keyring_key = NULL;
+		goto out;
+	}
+	crypt_info->ci_keyring_key = keyring_key;
+	if (keyring_key->type != &key_type_logon) {
+		printk_once(KERN_WARNING
+				"%s: key type must be logon\n", __func__);
+		res = -ENOKEY;
+		goto out;
+	}
+	down_read(&keyring_key->sem);
+	ukp = user_key_payload(keyring_key);
+	if (ukp->datalen != sizeof(struct fscrypt_key)) {
+		res = -EINVAL;
+		up_read(&keyring_key->sem);
+		goto out;
+	}
+	master_key = (struct fscrypt_key *)ukp->data;
+	BUILD_BUG_ON(FS_AES_128_ECB_KEY_SIZE != FS_KEY_DERIVATION_NONCE_SIZE);
+
+	if (master_key->size != FS_AES_256_XTS_KEY_SIZE) {
+		printk_once(KERN_WARNING
+				"%s: key size incorrect: %d\n",
+				__func__, master_key->size);
+		res = -ENOKEY;
+		up_read(&keyring_key->sem);
+		goto out;
+	}
+	res = derive_key_aes(ctx.nonce, master_key->raw, raw_key);
+	up_read(&keyring_key->sem);
+	if (res)
+		goto out;
+got_key:
+	ctfm = crypto_alloc_skcipher(cipher_str, 0, 0);
+	if (!ctfm || IS_ERR(ctfm)) {
+		res = ctfm ? PTR_ERR(ctfm) : -ENOMEM;
+		printk(KERN_DEBUG
+		       "%s: error %d (inode %u) allocating crypto tfm\n",
+		       __func__, res, (unsigned) inode->i_ino);
+		goto out;
+	}
+	crypt_info->ci_ctfm = ctfm;
+	crypto_skcipher_clear_flags(ctfm, ~0);
+	crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_REQ_WEAK_KEY);
+	res = crypto_skcipher_setkey(ctfm, raw_key, fscrypt_key_size(mode));
+	if (res)
+		goto out;
+
+	memzero_explicit(raw_key, sizeof(raw_key));
+	if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) != NULL) {
+		put_crypt_info(crypt_info);
+		goto retry;
+	}
+	return 0;
+
+out:
+	if (res == -ENOKEY)
+		res = 0;
+	put_crypt_info(crypt_info);
+	memzero_explicit(raw_key, sizeof(raw_key));
+	return res;
+}
+
+void fscrypt_put_encryption_info(struct inode *inode, struct fscrypt_info *ci)
+{
+	struct fscrypt_info *prev;
+
+	if (ci == NULL)
+		ci = ACCESS_ONCE(inode->i_crypt_info);
+	if (ci == NULL)
+		return;
+
+	prev = cmpxchg(&inode->i_crypt_info, ci, NULL);
+	if (prev != ci)
+		return;
+
+	put_crypt_info(ci);
+}
+EXPORT_SYMBOL(fscrypt_put_encryption_info);
+
+int fscrypt_get_encryption_info(struct inode *inode)
+{
+	struct fscrypt_info *ci = inode->i_crypt_info;
+
+	if (!ci ||
+		(ci->ci_keyring_key &&
+		 (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
+					       (1 << KEY_FLAG_REVOKED) |
+					       (1 << KEY_FLAG_DEAD)))))
+		return get_crypt_info(inode);
+	return 0;
+}
+EXPORT_SYMBOL(fscrypt_get_encryption_info);

fs/crypto/policy.c

@@ -0,0 +1,229 @@
+/*
+ * Encryption policy functions for per-file encryption support.
+ *
+ * Copyright (C) 2015, Google, Inc.
+ * Copyright (C) 2015, Motorola Mobility.
+ *
+ * Written by Michael Halcrow, 2015.
+ * Modified by Jaegeuk Kim, 2015.
+ */
+
+#include <linux/random.h>
+#include <linux/string.h>
+#include <linux/fscrypto.h>
+
+static int inode_has_encryption_context(struct inode *inode)
+{
+	if (!inode->i_sb->s_cop->get_context)
+		return 0;
+	return (inode->i_sb->s_cop->get_context(inode, NULL, 0L) > 0);
+}
+
+/*
+ * check whether the policy is consistent with the encryption context
+ * for the inode
+ */
+static int is_encryption_context_consistent_with_policy(struct inode *inode,
+				const struct fscrypt_policy *policy)
+{
+	struct fscrypt_context ctx;
+	int res;
+
+	if (!inode->i_sb->s_cop->get_context)
+		return 0;
+
+	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+	if (res != sizeof(ctx))
+		return 0;
+
+	return (memcmp(ctx.master_key_descriptor, policy->master_key_descriptor,
+			FS_KEY_DESCRIPTOR_SIZE) == 0 &&
+			(ctx.flags == policy->flags) &&
+			(ctx.contents_encryption_mode ==
+			 policy->contents_encryption_mode) &&
+			(ctx.filenames_encryption_mode ==
+			 policy->filenames_encryption_mode));
+}
+
+static int create_encryption_context_from_policy(struct inode *inode,
+				const struct fscrypt_policy *policy)
+{
+	struct fscrypt_context ctx;
+	int res;
+
+	if (!inode->i_sb->s_cop->set_context)
+		return -EOPNOTSUPP;
+
+	if (inode->i_sb->s_cop->prepare_context) {
+		res = inode->i_sb->s_cop->prepare_context(inode);
+		if (res)
+			return res;
+	}
+
+	ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1;
+	memcpy(ctx.master_key_descriptor, policy->master_key_descriptor,
+					FS_KEY_DESCRIPTOR_SIZE);
+
+	if (!fscrypt_valid_contents_enc_mode(
+				policy->contents_encryption_mode)) {
+		printk(KERN_WARNING
+		       "%s: Invalid contents encryption mode %d\n", __func__,
+			policy->contents_encryption_mode);
+		return -EINVAL;
+	}
+
+	if (!fscrypt_valid_filenames_enc_mode(
+				policy->filenames_encryption_mode)) {
+		printk(KERN_WARNING
+			"%s: Invalid filenames encryption mode %d\n", __func__,
+			policy->filenames_encryption_mode);
+		return -EINVAL;
+	}
+
+	if (policy->flags & ~FS_POLICY_FLAGS_VALID)
+		return -EINVAL;
+
+	ctx.contents_encryption_mode = policy->contents_encryption_mode;
+	ctx.filenames_encryption_mode = policy->filenames_encryption_mode;
+	ctx.flags = policy->flags;
+	BUILD_BUG_ON(sizeof(ctx.nonce) != FS_KEY_DERIVATION_NONCE_SIZE);
+	get_random_bytes(ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE);
+
+	return inode->i_sb->s_cop->set_context(inode, &ctx, sizeof(ctx), NULL);
+}
+
+int fscrypt_process_policy(struct inode *inode,
+				const struct fscrypt_policy *policy)
+{
+	if (policy->version != 0)
+		return -EINVAL;
+
+	if (!inode_has_encryption_context(inode)) {
+		if (!inode->i_sb->s_cop->empty_dir)
+			return -EOPNOTSUPP;
+		if (!inode->i_sb->s_cop->empty_dir(inode))
+			return -ENOTEMPTY;
+		return create_encryption_context_from_policy(inode, policy);
+	}
+
+	if (is_encryption_context_consistent_with_policy(inode, policy))
+		return 0;
+
+	printk(KERN_WARNING "%s: Policy inconsistent with encryption context\n",
+	       __func__);
+	return -EINVAL;
+}
+EXPORT_SYMBOL(fscrypt_process_policy);
+
+int fscrypt_get_policy(struct inode *inode, struct fscrypt_policy *policy)
+{
+	struct fscrypt_context ctx;
+	int res;
+
+	if (!inode->i_sb->s_cop->get_context ||
+			!inode->i_sb->s_cop->is_encrypted(inode))
+		return -ENODATA;
+
+	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+	if (res != sizeof(ctx))
+		return -ENODATA;
+	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,
+				FS_KEY_DESCRIPTOR_SIZE);
+	return 0;
+}
+EXPORT_SYMBOL(fscrypt_get_policy);
+
+int fscrypt_has_permitted_context(struct inode *parent, struct inode *child)
+{
+	struct fscrypt_info *parent_ci, *child_ci;
+	int res;
+
+	if ((parent == NULL) || (child == NULL)) {
+		printk(KERN_ERR	"parent %p child %p\n", parent, child);
+		BUG_ON(1);
+	}
+
+	/* no restrictions if the parent directory is not encrypted */
+	if (!parent->i_sb->s_cop->is_encrypted(parent))
+		return 1;
+	/* if the child directory is not encrypted, this is always a problem */
+	if (!parent->i_sb->s_cop->is_encrypted(child))
+		return 0;
+	res = fscrypt_get_encryption_info(parent);
+	if (res)
+		return 0;
+	res = fscrypt_get_encryption_info(child);
+	if (res)
+		return 0;
+	parent_ci = parent->i_crypt_info;
+	child_ci = child->i_crypt_info;
+	if (!parent_ci && !child_ci)
+		return 1;
+	if (!parent_ci || !child_ci)
+		return 0;
+
+	return (memcmp(parent_ci->ci_master_key,
+			child_ci->ci_master_key,
+			FS_KEY_DESCRIPTOR_SIZE) == 0 &&
+		(parent_ci->ci_data_mode == child_ci->ci_data_mode) &&
+		(parent_ci->ci_filename_mode == child_ci->ci_filename_mode) &&
+		(parent_ci->ci_flags == child_ci->ci_flags));
+}
+EXPORT_SYMBOL(fscrypt_has_permitted_context);
+
+/**
+ * fscrypt_inherit_context() - Sets a child context from its parent
+ * @parent: Parent inode from which the context is inherited.
+ * @child:  Child inode that inherits the context from @parent.
+ * @fs_data:  private data given by FS.
+ * @preload:  preload child i_crypt_info
+ *
+ * Return: Zero on success, non-zero otherwise
+ */
+int fscrypt_inherit_context(struct inode *parent, struct inode *child,
+						void *fs_data, bool preload)
+{
+	struct fscrypt_context ctx;
+	struct fscrypt_info *ci;
+	int res;
+
+	if (!parent->i_sb->s_cop->set_context)
+		return -EOPNOTSUPP;
+
+	res = fscrypt_get_encryption_info(parent);
+	if (res < 0)
+		return res;
+
+	ci = parent->i_crypt_info;
+	if (ci == NULL)
+		return -ENOKEY;
+
+	ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1;
+	if (fscrypt_dummy_context_enabled(parent)) {
+		ctx.contents_encryption_mode = FS_ENCRYPTION_MODE_AES_256_XTS;
+		ctx.filenames_encryption_mode = FS_ENCRYPTION_MODE_AES_256_CTS;
+		ctx.flags = 0;
+		memset(ctx.master_key_descriptor, 0x42, FS_KEY_DESCRIPTOR_SIZE);
+		res = 0;
+	} else {
+		ctx.contents_encryption_mode = ci->ci_data_mode;
+		ctx.filenames_encryption_mode = ci->ci_filename_mode;
+		ctx.flags = ci->ci_flags;
+		memcpy(ctx.master_key_descriptor, ci->ci_master_key,
+				FS_KEY_DESCRIPTOR_SIZE);
+	}
+	get_random_bytes(ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE);
+	res = parent->i_sb->s_cop->set_context(child, &ctx,
+						sizeof(ctx), fs_data);
+	if (res)
+		return res;
+	return preload ? fscrypt_get_encryption_info(child): 0;
+}
+EXPORT_SYMBOL(fscrypt_inherit_context);

fs/f2fs/Kconfig

@@ -1,6 +1,8 @@
 config F2FS_FS
 	tristate "F2FS filesystem support"
 	depends on BLOCK
+	select CRYPTO
+	select CRYPTO_CRC32
 	help
 	  F2FS is based on Log-structured File System (LFS), which supports
 	  versatile "flash-friendly" features. The design has been focused on
@@ -76,15 +78,7 @@ config F2FS_FS_ENCRYPTION
 	bool "F2FS Encryption"
 	depends on F2FS_FS
 	depends on F2FS_FS_XATTR
-	select CRYPTO_AES
+	select FS_ENCRYPTION
-	select CRYPTO_CBC
-	select CRYPTO_ECB
-	select CRYPTO_XTS
-	select CRYPTO_CTS
-	select CRYPTO_CTR
-	select CRYPTO_SHA256
-	select KEYS
-	select ENCRYPTED_KEYS
 	help
 	  Enable encryption of f2fs files and directories.  This
 	  feature is similar to ecryptfs, but it is more memory

fs/f2fs/Makefile

@@ -7,5 +7,3 @@ f2fs-$(CONFIG_F2FS_STAT_FS) += debug.o
 f2fs-$(CONFIG_F2FS_FS_XATTR) += xattr.o
 f2fs-$(CONFIG_F2FS_FS_POSIX_ACL) += acl.o
 f2fs-$(CONFIG_F2FS_IO_TRACE) += trace.o
-f2fs-$(CONFIG_F2FS_FS_ENCRYPTION) += crypto_policy.o crypto.o \
-		crypto_key.o crypto_fname.o

fs/f2fs/checkpoint.c

@@ -39,7 +39,7 @@ repeat:
 		cond_resched();
 		goto repeat;
 	}
-	f2fs_wait_on_page_writeback(page, META);
+	f2fs_wait_on_page_writeback(page, META, true);
 	SetPageUptodate(page);
 	return page;
 }
@@ -56,7 +56,8 @@ static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
 		.sbi = sbi,
 		.type = META,
 		.rw = READ_SYNC | REQ_META | REQ_PRIO,
-		.blk_addr = index,
+		.old_blkaddr = index,
+		.new_blkaddr = index,
 		.encrypted_page = NULL,
 	};
 
@@ -143,7 +144,6 @@ bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type)
 int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 							int type, bool sync)
 {
-	block_t prev_blk_addr = 0;
 	struct page *page;
 	block_t blkno = start;
 	struct f2fs_io_info fio = {
@@ -152,10 +152,12 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 		.rw = sync ? (READ_SYNC | REQ_META | REQ_PRIO) : READA,
 		.encrypted_page = NULL,
 	};
+	struct blk_plug plug;
 
 	if (unlikely(type == META_POR))
 		fio.rw &= ~REQ_META;
 
+	blk_start_plug(&plug);
 	for (; nrpages-- > 0; blkno++) {
 
 		if (!is_valid_blkaddr(sbi, blkno, type))
@@ -167,27 +169,24 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 					NAT_BLOCK_OFFSET(NM_I(sbi)->max_nid)))
 				blkno = 0;
 			/* get nat block addr */
-			fio.blk_addr = current_nat_addr(sbi,
+			fio.new_blkaddr = current_nat_addr(sbi,
 					blkno * NAT_ENTRY_PER_BLOCK);
 			break;
 		case META_SIT:
 			/* get sit block addr */
-			fio.blk_addr = current_sit_addr(sbi,
+			fio.new_blkaddr = current_sit_addr(sbi,
 					blkno * SIT_ENTRY_PER_BLOCK);
-			if (blkno != start && prev_blk_addr + 1 != fio.blk_addr)
-				goto out;
-			prev_blk_addr = fio.blk_addr;
 			break;
 		case META_SSA:
 		case META_CP:
 		case META_POR:
-			fio.blk_addr = blkno;
+			fio.new_blkaddr = blkno;
 			break;
 		default:
 			BUG();
 		}
 
-		page = grab_cache_page(META_MAPPING(sbi), fio.blk_addr);
+		page = grab_cache_page(META_MAPPING(sbi), fio.new_blkaddr);
 		if (!page)
 			continue;
 		if (PageUptodate(page)) {
@@ -196,11 +195,13 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 		}
 
 		fio.page = page;
+		fio.old_blkaddr = fio.new_blkaddr;
 		f2fs_submit_page_mbio(&fio);
 		f2fs_put_page(page, 0);
 	}
 out:
 	f2fs_submit_merged_bio(sbi, META, READ);
+	blk_finish_plug(&plug);
 	return blkno - start;
 }
 
@@ -232,13 +233,17 @@ static int f2fs_write_meta_page(struct page *page,
 	if (unlikely(f2fs_cp_error(sbi)))
 		goto redirty_out;
 
-	f2fs_wait_on_page_writeback(page, META);
 	write_meta_page(sbi, page);
 	dec_page_count(sbi, F2FS_DIRTY_META);
+
+	if (wbc->for_reclaim)
+		f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, META, WRITE);
+
 	unlock_page(page);
 
-	if (wbc->for_reclaim || unlikely(f2fs_cp_error(sbi)))
+	if (unlikely(f2fs_cp_error(sbi)))
 		f2fs_submit_merged_bio(sbi, META, WRITE);
+
 	return 0;
 
 redirty_out:
@@ -252,13 +257,13 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
 	struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
 	long diff, written;
 
-	trace_f2fs_writepages(mapping->host, wbc, META);
-
 	/* collect a number of dirty meta pages and write together */
 	if (wbc->for_kupdate ||
 		get_pages(sbi, F2FS_DIRTY_META) < nr_pages_to_skip(sbi, META))
 		goto skip_write;
 
+	trace_f2fs_writepages(mapping->host, wbc, META);
+
 	/* if mounting is failed, skip writing node pages */
 	mutex_lock(&sbi->cp_mutex);
 	diff = nr_pages_to_write(sbi, META, wbc);
@@ -269,6 +274,7 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
 
 skip_write:
 	wbc->pages_skipped += get_pages(sbi, F2FS_DIRTY_META);
+	trace_f2fs_writepages(mapping->host, wbc, META);
 	return 0;
 }
 
@@ -276,15 +282,18 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
 						long nr_to_write)
 {
 	struct address_space *mapping = META_MAPPING(sbi);
-	pgoff_t index = 0, end = LONG_MAX, prev = LONG_MAX;
+	pgoff_t index = 0, end = ULONG_MAX, prev = ULONG_MAX;
 	struct pagevec pvec;
 	long nwritten = 0;
 	struct writeback_control wbc = {
 		.for_reclaim = 0,
 	};
+	struct blk_plug plug;
 
 	pagevec_init(&pvec, 0);
 
+	blk_start_plug(&plug);
+
 	while (index <= end) {
 		int i, nr_pages;
 		nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
@@ -296,7 +305,7 @@ long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 
-			if (prev == LONG_MAX)
+			if (prev == ULONG_MAX)
 				prev = page->index - 1;
 			if (nr_to_write != LONG_MAX && page->index != prev + 1) {
 				pagevec_release(&pvec);
@@ -315,6 +324,9 @@ continue_unlock:
 				goto continue_unlock;
 			}
 
+			f2fs_wait_on_page_writeback(page, META, true);
+
+			BUG_ON(PageWriteback(page));
 			if (!clear_page_dirty_for_io(page))
 				goto continue_unlock;
 
@@ -334,6 +346,8 @@ stop:
 	if (nwritten)
 		f2fs_submit_merged_bio(sbi, type, WRITE);
 
+	blk_finish_plug(&plug);
+
 	return nwritten;
 }
 
@@ -621,7 +635,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 		goto invalid_cp1;
 
 	crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
-	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
+	if (!f2fs_crc_valid(sbi, crc, cp_block, crc_offset))
 		goto invalid_cp1;
 
 	pre_version = cur_cp_version(cp_block);
@@ -636,7 +650,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 		goto invalid_cp2;
 
 	crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
-	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
+	if (!f2fs_crc_valid(sbi, crc, cp_block, crc_offset))
 		goto invalid_cp2;
 
 	cur_version = cur_cp_version(cp_block);
@@ -696,6 +710,10 @@ int get_valid_checkpoint(struct f2fs_sb_info *sbi)
 	cp_block = (struct f2fs_checkpoint *)page_address(cur_page);
 	memcpy(sbi->ckpt, cp_block, blk_size);
 
+	/* Sanity checking of checkpoint */
+	if (sanity_check_ckpt(sbi))
+		goto fail_no_cp;
+
 	if (cp_blks <= 1)
 		goto done;
 
@@ -902,7 +920,7 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
 		if (!get_pages(sbi, F2FS_WRITEBACK))
 			break;
 
-		io_schedule();
+		io_schedule_timeout(5*HZ);
 	}
 	finish_wait(&sbi->cp_wait, &wait);
 }
@@ -921,6 +939,9 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	int cp_payload_blks = __cp_payload(sbi);
 	block_t discard_blk = NEXT_FREE_BLKADDR(sbi, curseg);
 	bool invalidate = false;
+	struct super_block *sb = sbi->sb;
+	struct curseg_info *seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
+	u64 kbytes_written;
 
 	/*
 	 * This avoids to conduct wrong roll-forward operations and uses
@@ -1008,7 +1029,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP));
 	get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP));
 
-	crc32 = f2fs_crc32(ckpt, le32_to_cpu(ckpt->checksum_offset));
+	crc32 = f2fs_crc32(sbi, ckpt, le32_to_cpu(ckpt->checksum_offset));
 	*((__le32 *)((unsigned char *)ckpt +
 				le32_to_cpu(ckpt->checksum_offset)))
 				= cpu_to_le32(crc32);
@@ -1034,6 +1055,14 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	write_data_summaries(sbi, start_blk);
 	start_blk += data_sum_blocks;
+
+	/* Record write statistics in the hot node summary */
+	kbytes_written = sbi->kbytes_written;
+	if (sb->s_bdev->bd_part)
+		kbytes_written += BD_PART_WRITTEN(sbi);
+
+	seg_i->journal->info.kbytes_written = cpu_to_le64(kbytes_written);
+
 	if (__remain_node_summaries(cpc->reason)) {
 		write_node_summaries(sbi, start_blk);
 		start_blk += NR_CURSEG_NODE_TYPE;
@@ -1048,8 +1077,8 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	if (unlikely(f2fs_cp_error(sbi)))
 		return -EIO;
 
-	filemap_fdatawait_range(NODE_MAPPING(sbi), 0, LONG_MAX);
+	filemap_fdatawait_range(NODE_MAPPING(sbi), 0, LLONG_MAX);
-	filemap_fdatawait_range(META_MAPPING(sbi), 0, LONG_MAX);
+	filemap_fdatawait_range(META_MAPPING(sbi), 0, LLONG_MAX);
 
 	/* update user_block_counts */
 	sbi->last_valid_block_count = sbi->total_valid_block_count;
@@ -1112,9 +1141,7 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish block_ops");
 
-	f2fs_submit_merged_bio(sbi, DATA, WRITE);
+	f2fs_flush_merged_bios(sbi);
-	f2fs_submit_merged_bio(sbi, NODE, WRITE);
-	f2fs_submit_merged_bio(sbi, META, WRITE);
 
 	/*
 	 * update checkpoint pack index

fs/f2fs/crypto.c

@@ -1,489 +0,0 @@
-/*
- * linux/fs/f2fs/crypto.c
- *
- * Copied from linux/fs/ext4/crypto.c
- *
- * Copyright (C) 2015, Google, Inc.
- * Copyright (C) 2015, Motorola Mobility
- *
- * This contains encryption functions for f2fs
- *
- * Written by Michael Halcrow, 2014.
- *
- * Filename encryption additions
- *	Uday Savagaonkar, 2014
- * Encryption policy handling additions
- *	Ildar Muslukhov, 2014
- * Remove ext4_encrypted_zeroout(),
- *   add f2fs_restore_and_release_control_page()
- *	Jaegeuk Kim, 2015.
- *
- * This has not yet undergone a rigorous security audit.
- *
- * The usage of AES-XTS should conform to recommendations in NIST
- * Special Publication 800-38E and IEEE P1619/D16.
- */
-#include <crypto/skcipher.h>
-#include <keys/user-type.h>
-#include <keys/encrypted-type.h>
-#include <linux/ecryptfs.h>
-#include <linux/gfp.h>
-#include <linux/kernel.h>
-#include <linux/key.h>
-#include <linux/list.h>
-#include <linux/mempool.h>
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/random.h>
-#include <linux/scatterlist.h>
-#include <linux/spinlock_types.h>
-#include <linux/f2fs_fs.h>
-#include <linux/ratelimit.h>
-#include <linux/bio.h>
-
-#include "f2fs.h"
-#include "xattr.h"
-
-/* Encryption added and removed here! (L: */
-
-static unsigned int num_prealloc_crypto_pages = 32;
-static unsigned int num_prealloc_crypto_ctxs = 128;
-
-module_param(num_prealloc_crypto_pages, uint, 0444);
-MODULE_PARM_DESC(num_prealloc_crypto_pages,
-		"Number of crypto pages to preallocate");
-module_param(num_prealloc_crypto_ctxs, uint, 0444);
-MODULE_PARM_DESC(num_prealloc_crypto_ctxs,
-		"Number of crypto contexts to preallocate");
-
-static mempool_t *f2fs_bounce_page_pool;
-
-static LIST_HEAD(f2fs_free_crypto_ctxs);
-static DEFINE_SPINLOCK(f2fs_crypto_ctx_lock);
-
-static struct workqueue_struct *f2fs_read_workqueue;
-static DEFINE_MUTEX(crypto_init);
-
-static struct kmem_cache *f2fs_crypto_ctx_cachep;
-struct kmem_cache *f2fs_crypt_info_cachep;
-
-/**
- * f2fs_release_crypto_ctx() - Releases an encryption context
- * @ctx: The encryption context to release.
- *
- * If the encryption context was allocated from the pre-allocated pool, returns
- * it to that pool. Else, frees it.
- *
- * If there's a bounce page in the context, this frees that.
- */
-void f2fs_release_crypto_ctx(struct f2fs_crypto_ctx *ctx)
-{
-	unsigned long flags;
-
-	if (ctx->flags & F2FS_WRITE_PATH_FL && ctx->w.bounce_page) {
-		mempool_free(ctx->w.bounce_page, f2fs_bounce_page_pool);
-		ctx->w.bounce_page = NULL;
-	}
-	ctx->w.control_page = NULL;
-	if (ctx->flags & F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL) {
-		kmem_cache_free(f2fs_crypto_ctx_cachep, ctx);
-	} else {
-		spin_lock_irqsave(&f2fs_crypto_ctx_lock, flags);
-		list_add(&ctx->free_list, &f2fs_free_crypto_ctxs);
-		spin_unlock_irqrestore(&f2fs_crypto_ctx_lock, flags);
-	}
-}
-
-/**
- * f2fs_get_crypto_ctx() - Gets an encryption context
- * @inode:       The inode for which we are doing the crypto
- *
- * Allocates and initializes an encryption context.
- *
- * Return: An allocated and initialized encryption context on success; error
- * value or NULL otherwise.
- */
-struct f2fs_crypto_ctx *f2fs_get_crypto_ctx(struct inode *inode)
-{
-	struct f2fs_crypto_ctx *ctx = NULL;
-	unsigned long flags;
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
-
-	if (ci == NULL)
-		return ERR_PTR(-ENOKEY);
-
-	/*
-	 * We first try getting the ctx from a free list because in
-	 * the common case the ctx will have an allocated and
-	 * initialized crypto tfm, so it's probably a worthwhile
-	 * optimization. For the bounce page, we first try getting it
-	 * from the kernel allocator because that's just about as fast
-	 * as getting it from a list and because a cache of free pages
-	 * should generally be a "last resort" option for a filesystem
-	 * to be able to do its job.
-	 */
-	spin_lock_irqsave(&f2fs_crypto_ctx_lock, flags);
-	ctx = list_first_entry_or_null(&f2fs_free_crypto_ctxs,
-					struct f2fs_crypto_ctx, free_list);
-	if (ctx)
-		list_del(&ctx->free_list);
-	spin_unlock_irqrestore(&f2fs_crypto_ctx_lock, flags);
-	if (!ctx) {
-		ctx = kmem_cache_zalloc(f2fs_crypto_ctx_cachep, GFP_NOFS);
-		if (!ctx)
-			return ERR_PTR(-ENOMEM);
-		ctx->flags |= F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
-	} else {
-		ctx->flags &= ~F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL;
-	}
-	ctx->flags &= ~F2FS_WRITE_PATH_FL;
-	return ctx;
-}
-
-/*
- * Call f2fs_decrypt on every single page, reusing the encryption
- * context.
- */
-static void completion_pages(struct work_struct *work)
-{
-	struct f2fs_crypto_ctx *ctx =
-		container_of(work, struct f2fs_crypto_ctx, r.work);
-	struct bio *bio = ctx->r.bio;
-	struct bio_vec *bv;
-	int i;
-
-	bio_for_each_segment_all(bv, bio, i) {
-		struct page *page = bv->bv_page;
-		int ret = f2fs_decrypt(ctx, page);
-
-		if (ret) {
-			WARN_ON_ONCE(1);
-			SetPageError(page);
-		} else
-			SetPageUptodate(page);
-		unlock_page(page);
-	}
-	f2fs_release_crypto_ctx(ctx);
-	bio_put(bio);
-}
-
-void f2fs_end_io_crypto_work(struct f2fs_crypto_ctx *ctx, struct bio *bio)
-{
-	INIT_WORK(&ctx->r.work, completion_pages);
-	ctx->r.bio = bio;
-	queue_work(f2fs_read_workqueue, &ctx->r.work);
-}
-
-static void f2fs_crypto_destroy(void)
-{
-	struct f2fs_crypto_ctx *pos, *n;
-
-	list_for_each_entry_safe(pos, n, &f2fs_free_crypto_ctxs, free_list)
-		kmem_cache_free(f2fs_crypto_ctx_cachep, pos);
-	INIT_LIST_HEAD(&f2fs_free_crypto_ctxs);
-	if (f2fs_bounce_page_pool)
-		mempool_destroy(f2fs_bounce_page_pool);
-	f2fs_bounce_page_pool = NULL;
-}
-
-/**
- * f2fs_crypto_initialize() - Set up for f2fs encryption.
- *
- * 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 f2fs_crypto_initialize(void)
-{
-	int i, res = -ENOMEM;
-
-	if (f2fs_bounce_page_pool)
-		return 0;
-
-	mutex_lock(&crypto_init);
-	if (f2fs_bounce_page_pool)
-		goto already_initialized;
-
-	for (i = 0; i < num_prealloc_crypto_ctxs; i++) {
-		struct f2fs_crypto_ctx *ctx;
-
-		ctx = kmem_cache_zalloc(f2fs_crypto_ctx_cachep, GFP_KERNEL);
-		if (!ctx)
-			goto fail;
-		list_add(&ctx->free_list, &f2fs_free_crypto_ctxs);
-	}
-
-	/* must be allocated at the last step to avoid race condition above */
-	f2fs_bounce_page_pool =
-		mempool_create_page_pool(num_prealloc_crypto_pages, 0);
-	if (!f2fs_bounce_page_pool)
-		goto fail;
-
-already_initialized:
-	mutex_unlock(&crypto_init);
-	return 0;
-fail:
-	f2fs_crypto_destroy();
-	mutex_unlock(&crypto_init);
-	return res;
-}
-
-/**
- * f2fs_exit_crypto() - Shutdown the f2fs encryption system
- */
-void f2fs_exit_crypto(void)
-{
-	f2fs_crypto_destroy();
-
-	if (f2fs_read_workqueue)
-		destroy_workqueue(f2fs_read_workqueue);
-	if (f2fs_crypto_ctx_cachep)
-		kmem_cache_destroy(f2fs_crypto_ctx_cachep);
-	if (f2fs_crypt_info_cachep)
-		kmem_cache_destroy(f2fs_crypt_info_cachep);
-}
-
-int __init f2fs_init_crypto(void)
-{
-	int res = -ENOMEM;
-
-	f2fs_read_workqueue = alloc_workqueue("f2fs_crypto", WQ_HIGHPRI, 0);
-	if (!f2fs_read_workqueue)
-		goto fail;
-
-	f2fs_crypto_ctx_cachep = KMEM_CACHE(f2fs_crypto_ctx,
-						SLAB_RECLAIM_ACCOUNT);
-	if (!f2fs_crypto_ctx_cachep)
-		goto fail;
-
-	f2fs_crypt_info_cachep = KMEM_CACHE(f2fs_crypt_info,
-						SLAB_RECLAIM_ACCOUNT);
-	if (!f2fs_crypt_info_cachep)
-		goto fail;
-
-	return 0;
-fail:
-	f2fs_exit_crypto();
-	return res;
-}
-
-void f2fs_restore_and_release_control_page(struct page **page)
-{
-	struct f2fs_crypto_ctx *ctx;
-	struct page *bounce_page;
-
-	/* The bounce data pages are unmapped. */
-	if ((*page)->mapping)
-		return;
-
-	/* The bounce data page is unmapped. */
-	bounce_page = *page;
-	ctx = (struct f2fs_crypto_ctx *)page_private(bounce_page);
-
-	/* restore control page */
-	*page = ctx->w.control_page;
-
-	f2fs_restore_control_page(bounce_page);
-}
-
-void f2fs_restore_control_page(struct page *data_page)
-{
-	struct f2fs_crypto_ctx *ctx =
-		(struct f2fs_crypto_ctx *)page_private(data_page);
-
-	set_page_private(data_page, (unsigned long)NULL);
-	ClearPagePrivate(data_page);
-	unlock_page(data_page);
-	f2fs_release_crypto_ctx(ctx);
-}
-
-/**
- * f2fs_crypt_complete() - The completion callback for page encryption
- * @req: The asynchronous encryption request context
- * @res: The result of the encryption operation
- */
-static void f2fs_crypt_complete(struct crypto_async_request *req, int res)
-{
-	struct f2fs_completion_result *ecr = req->data;
-
-	if (res == -EINPROGRESS)
-		return;
-	ecr->res = res;
-	complete(&ecr->completion);
-}
-
-typedef enum {
-	F2FS_DECRYPT = 0,
-	F2FS_ENCRYPT,
-} f2fs_direction_t;
-
-static int f2fs_page_crypto(struct f2fs_crypto_ctx *ctx,
-				struct inode *inode,
-				f2fs_direction_t rw,
-				pgoff_t index,
-				struct page *src_page,
-				struct page *dest_page)
-{
-	u8 xts_tweak[F2FS_XTS_TWEAK_SIZE];
-	struct skcipher_request *req = NULL;
-	DECLARE_F2FS_COMPLETION_RESULT(ecr);
-	struct scatterlist dst, src;
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
-	struct crypto_skcipher *tfm = ci->ci_ctfm;
-	int res = 0;
-
-	req = skcipher_request_alloc(tfm, GFP_NOFS);
-	if (!req) {
-		printk_ratelimited(KERN_ERR
-				"%s: crypto_request_alloc() failed\n",
-				__func__);
-		return -ENOMEM;
-	}
-	skcipher_request_set_callback(
-		req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
-		f2fs_crypt_complete, &ecr);
-
-	BUILD_BUG_ON(F2FS_XTS_TWEAK_SIZE < sizeof(index));
-	memcpy(xts_tweak, &index, sizeof(index));
-	memset(&xts_tweak[sizeof(index)], 0,
-			F2FS_XTS_TWEAK_SIZE - sizeof(index));
-
-	sg_init_table(&dst, 1);
-	sg_set_page(&dst, dest_page, PAGE_CACHE_SIZE, 0);
-	sg_init_table(&src, 1);
-	sg_set_page(&src, src_page, PAGE_CACHE_SIZE, 0);
-	skcipher_request_set_crypt(req, &src, &dst, PAGE_CACHE_SIZE,
-				   xts_tweak);
-	if (rw == F2FS_DECRYPT)
-		res = crypto_skcipher_decrypt(req);
-	else
-		res = crypto_skcipher_encrypt(req);
-	if (res == -EINPROGRESS || res == -EBUSY) {
-		BUG_ON(req->base.data != &ecr);
-		wait_for_completion(&ecr.completion);
-		res = ecr.res;
-	}
-	skcipher_request_free(req);
-	if (res) {
-		printk_ratelimited(KERN_ERR
-			"%s: crypto_skcipher_encrypt() returned %d\n",
-			__func__, res);
-		return res;
-	}
-	return 0;
-}
-
-static struct page *alloc_bounce_page(struct f2fs_crypto_ctx *ctx)
-{
-	ctx->w.bounce_page = mempool_alloc(f2fs_bounce_page_pool, GFP_NOWAIT);
-	if (ctx->w.bounce_page == NULL)
-		return ERR_PTR(-ENOMEM);
-	ctx->flags |= F2FS_WRITE_PATH_FL;
-	return ctx->w.bounce_page;
-}
-
-/**
- * f2fs_encrypt() - Encrypts a page
- * @inode:          The inode for which the encryption should take place
- * @plaintext_page: The page to encrypt. Must be locked.
- *
- * Allocates a ciphertext page and encrypts plaintext_page into it using the ctx
- * encryption context.
- *
- * Called on the page write path.  The caller must call
- * f2fs_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
- * error value or NULL.
- */
-struct page *f2fs_encrypt(struct inode *inode,
-			  struct page *plaintext_page)
-{
-	struct f2fs_crypto_ctx *ctx;
-	struct page *ciphertext_page = NULL;
-	int err;
-
-	BUG_ON(!PageLocked(plaintext_page));
-
-	ctx = f2fs_get_crypto_ctx(inode);
-	if (IS_ERR(ctx))
-		return (struct page *)ctx;
-
-	/* The encryption operation will require a bounce page. */
-	ciphertext_page = alloc_bounce_page(ctx);
-	if (IS_ERR(ciphertext_page))
-		goto err_out;
-
-	ctx->w.control_page = plaintext_page;
-	err = f2fs_page_crypto(ctx, inode, F2FS_ENCRYPT, plaintext_page->index,
-					plaintext_page, ciphertext_page);
-	if (err) {
-		ciphertext_page = ERR_PTR(err);
-		goto err_out;
-	}
-
-	SetPagePrivate(ciphertext_page);
-	set_page_private(ciphertext_page, (unsigned long)ctx);
-	lock_page(ciphertext_page);
-	return ciphertext_page;
-
-err_out:
-	f2fs_release_crypto_ctx(ctx);
-	return ciphertext_page;
-}
-
-/**
- * f2fs_decrypt() - Decrypts a page in-place
- * @ctx:  The encryption context.
- * @page: The page to decrypt. Must be locked.
- *
- * Decrypts page in-place using the ctx encryption context.
- *
- * Called from the read completion callback.
- *
- * Return: Zero on success, non-zero otherwise.
- */
-int f2fs_decrypt(struct f2fs_crypto_ctx *ctx, struct page *page)
-{
-	BUG_ON(!PageLocked(page));
-
-	return f2fs_page_crypto(ctx, page->mapping->host,
-				F2FS_DECRYPT, page->index, page, page);
-}
-
-/*
- * Convenience function which takes care of allocating and
- * deallocating the encryption context
- */
-int f2fs_decrypt_one(struct inode *inode, struct page *page)
-{
-	struct f2fs_crypto_ctx *ctx = f2fs_get_crypto_ctx(inode);
-	int ret;
-
-	if (IS_ERR(ctx))
-		return PTR_ERR(ctx);
-	ret = f2fs_decrypt(ctx, page);
-	f2fs_release_crypto_ctx(ctx);
-	return ret;
-}
-
-bool f2fs_valid_contents_enc_mode(uint32_t mode)
-{
-	return (mode == F2FS_ENCRYPTION_MODE_AES_256_XTS);
-}
-
-/**
- * f2fs_validate_encryption_key_size() - Validate the encryption key size
- * @mode: The key mode.
- * @size: The key size to validate.
- *
- * Return: The validated key size for @mode. Zero if invalid.
- */
-uint32_t f2fs_validate_encryption_key_size(uint32_t mode, uint32_t size)
-{
-	if (size == f2fs_encryption_key_size(mode))
-		return size;
-	return 0;
-}

fs/f2fs/crypto_key.c

@@ -1,250 +0,0 @@
-/*
- * linux/fs/f2fs/crypto_key.c
- *
- * Copied from linux/fs/f2fs/crypto_key.c
- *
- * Copyright (C) 2015, Google, Inc.
- *
- * This contains encryption key functions for f2fs
- *
- * Written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar, 2015.
- */
-#include <keys/encrypted-type.h>
-#include <keys/user-type.h>
-#include <linux/random.h>
-#include <linux/scatterlist.h>
-#include <uapi/linux/keyctl.h>
-#include <crypto/skcipher.h>
-#include <linux/f2fs_fs.h>
-
-#include "f2fs.h"
-#include "xattr.h"
-
-static void derive_crypt_complete(struct crypto_async_request *req, int rc)
-{
-	struct f2fs_completion_result *ecr = req->data;
-
-	if (rc == -EINPROGRESS)
-		return;
-
-	ecr->res = rc;
-	complete(&ecr->completion);
-}
-
-/**
- * f2fs_derive_key_aes() - Derive a key using AES-128-ECB
- * @deriving_key: Encryption key used for derivatio.
- * @source_key:   Source key to which to apply derivation.
- * @derived_key:  Derived key.
- *
- * Return: Zero on success; non-zero otherwise.
- */
-static int f2fs_derive_key_aes(char deriving_key[F2FS_AES_128_ECB_KEY_SIZE],
-				char source_key[F2FS_AES_256_XTS_KEY_SIZE],
-				char derived_key[F2FS_AES_256_XTS_KEY_SIZE])
-{
-	int res = 0;
-	struct skcipher_request *req = NULL;
-	DECLARE_F2FS_COMPLETION_RESULT(ecr);
-	struct scatterlist src_sg, dst_sg;
-	struct crypto_skcipher *tfm = crypto_alloc_skcipher("ecb(aes)", 0, 0);
-
-	if (IS_ERR(tfm)) {
-		res = PTR_ERR(tfm);
-		tfm = NULL;
-		goto out;
-	}
-	crypto_skcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
-	req = skcipher_request_alloc(tfm, GFP_NOFS);
-	if (!req) {
-		res = -ENOMEM;
-		goto out;
-	}
-	skcipher_request_set_callback(req,
-			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
-			derive_crypt_complete, &ecr);
-	res = crypto_skcipher_setkey(tfm, deriving_key,
-				F2FS_AES_128_ECB_KEY_SIZE);
-	if (res < 0)
-		goto out;
-
-	sg_init_one(&src_sg, source_key, F2FS_AES_256_XTS_KEY_SIZE);
-	sg_init_one(&dst_sg, derived_key, F2FS_AES_256_XTS_KEY_SIZE);
-	skcipher_request_set_crypt(req, &src_sg, &dst_sg,
-					F2FS_AES_256_XTS_KEY_SIZE, NULL);
-	res = crypto_skcipher_encrypt(req);
-	if (res == -EINPROGRESS || res == -EBUSY) {
-		BUG_ON(req->base.data != &ecr);
-		wait_for_completion(&ecr.completion);
-		res = ecr.res;
-	}
-out:
-	skcipher_request_free(req);
-	crypto_free_skcipher(tfm);
-	return res;
-}
-
-static void f2fs_free_crypt_info(struct f2fs_crypt_info *ci)
-{
-	if (!ci)
-		return;
-
-	key_put(ci->ci_keyring_key);
-	crypto_free_skcipher(ci->ci_ctfm);
-	kmem_cache_free(f2fs_crypt_info_cachep, ci);
-}
-
-void f2fs_free_encryption_info(struct inode *inode, struct f2fs_crypt_info *ci)
-{
-	struct f2fs_inode_info *fi = F2FS_I(inode);
-	struct f2fs_crypt_info *prev;
-
-	if (ci == NULL)
-		ci = ACCESS_ONCE(fi->i_crypt_info);
-	if (ci == NULL)
-		return;
-	prev = cmpxchg(&fi->i_crypt_info, ci, NULL);
-	if (prev != ci)
-		return;
-
-	f2fs_free_crypt_info(ci);
-}
-
-int _f2fs_get_encryption_info(struct inode *inode)
-{
-	struct f2fs_inode_info *fi = F2FS_I(inode);
-	struct f2fs_crypt_info *crypt_info;
-	char full_key_descriptor[F2FS_KEY_DESC_PREFIX_SIZE +
-				(F2FS_KEY_DESCRIPTOR_SIZE * 2) + 1];
-	struct key *keyring_key = NULL;
-	struct f2fs_encryption_key *master_key;
-	struct f2fs_encryption_context ctx;
-	const struct user_key_payload *ukp;
-	struct crypto_skcipher *ctfm;
-	const char *cipher_str;
-	char raw_key[F2FS_MAX_KEY_SIZE];
-	char mode;
-	int res;
-
-	res = f2fs_crypto_initialize();
-	if (res)
-		return res;
-retry:
-	crypt_info = ACCESS_ONCE(fi->i_crypt_info);
-	if (crypt_info) {
-		if (!crypt_info->ci_keyring_key ||
-				key_validate(crypt_info->ci_keyring_key) == 0)
-			return 0;
-		f2fs_free_encryption_info(inode, crypt_info);
-		goto retry;
-	}
-
-	res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
-				F2FS_XATTR_NAME_ENCRYPTION_CONTEXT,
-				&ctx, sizeof(ctx), NULL);
-	if (res < 0)
-		return res;
-	else if (res != sizeof(ctx))
-		return -EINVAL;
-	res = 0;
-
-	crypt_info = kmem_cache_alloc(f2fs_crypt_info_cachep, GFP_NOFS);
-	if (!crypt_info)
-		return -ENOMEM;
-
-	crypt_info->ci_flags = ctx.flags;
-	crypt_info->ci_data_mode = ctx.contents_encryption_mode;
-	crypt_info->ci_filename_mode = ctx.filenames_encryption_mode;
-	crypt_info->ci_ctfm = NULL;
-	crypt_info->ci_keyring_key = NULL;
-	memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor,
-				sizeof(crypt_info->ci_master_key));
-	if (S_ISREG(inode->i_mode))
-		mode = crypt_info->ci_data_mode;
-	else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
-		mode = crypt_info->ci_filename_mode;
-	else
-		BUG();
-
-	switch (mode) {
-	case F2FS_ENCRYPTION_MODE_AES_256_XTS:
-		cipher_str = "xts(aes)";
-		break;
-	case F2FS_ENCRYPTION_MODE_AES_256_CTS:
-		cipher_str = "cts(cbc(aes))";
-		break;
-	default:
-		printk_once(KERN_WARNING
-			    "f2fs: unsupported key mode %d (ino %u)\n",
-			    mode, (unsigned) inode->i_ino);
-		res = -ENOKEY;
-		goto out;
-	}
-
-	memcpy(full_key_descriptor, F2FS_KEY_DESC_PREFIX,
-					F2FS_KEY_DESC_PREFIX_SIZE);
-	sprintf(full_key_descriptor + F2FS_KEY_DESC_PREFIX_SIZE,
-					"%*phN", F2FS_KEY_DESCRIPTOR_SIZE,
-					ctx.master_key_descriptor);
-	full_key_descriptor[F2FS_KEY_DESC_PREFIX_SIZE +
-					(2 * F2FS_KEY_DESCRIPTOR_SIZE)] = '\0';
-	keyring_key = request_key(&key_type_logon, full_key_descriptor, NULL);
-	if (IS_ERR(keyring_key)) {
-		res = PTR_ERR(keyring_key);
-		keyring_key = NULL;
-		goto out;
-	}
-	crypt_info->ci_keyring_key = keyring_key;
-	BUG_ON(keyring_key->type != &key_type_logon);
-	ukp = user_key_payload(keyring_key);
-	if (ukp->datalen != sizeof(struct f2fs_encryption_key)) {
-		res = -EINVAL;
-		goto out;
-	}
-	master_key = (struct f2fs_encryption_key *)ukp->data;
-	BUILD_BUG_ON(F2FS_AES_128_ECB_KEY_SIZE !=
-				F2FS_KEY_DERIVATION_NONCE_SIZE);
-	BUG_ON(master_key->size != F2FS_AES_256_XTS_KEY_SIZE);
-	res = f2fs_derive_key_aes(ctx.nonce, master_key->raw,
-				  raw_key);
-	if (res)
-		goto out;
-
-	ctfm = crypto_alloc_skcipher(cipher_str, 0, 0);
-	if (!ctfm || IS_ERR(ctfm)) {
-		res = ctfm ? PTR_ERR(ctfm) : -ENOMEM;
-		printk(KERN_DEBUG
-		       "%s: error %d (inode %u) allocating crypto tfm\n",
-		       __func__, res, (unsigned) inode->i_ino);
-		goto out;
-	}
-	crypt_info->ci_ctfm = ctfm;
-	crypto_skcipher_clear_flags(ctfm, ~0);
-	crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_REQ_WEAK_KEY);
-	res = crypto_skcipher_setkey(ctfm, raw_key,
-				     f2fs_encryption_key_size(mode));
-	if (res)
-		goto out;
-
-	memzero_explicit(raw_key, sizeof(raw_key));
-	if (cmpxchg(&fi->i_crypt_info, NULL, crypt_info) != NULL) {
-		f2fs_free_crypt_info(crypt_info);
-		goto retry;
-	}
-	return 0;
-
-out:
-	if (res == -ENOKEY && !S_ISREG(inode->i_mode))
-		res = 0;
-
-	f2fs_free_crypt_info(crypt_info);
-	memzero_explicit(raw_key, sizeof(raw_key));
-	return res;
-}
-
-int f2fs_has_encryption_key(struct inode *inode)
-{
-	struct f2fs_inode_info *fi = F2FS_I(inode);
-
-	return (fi->i_crypt_info != NULL);
-}

fs/f2fs/crypto_policy.c

@@ -1,209 +0,0 @@
-/*
- * copied from linux/fs/ext4/crypto_policy.c
- *
- * Copyright (C) 2015, Google, Inc.
- * Copyright (C) 2015, Motorola Mobility.
- *
- * This contains encryption policy functions for f2fs with some modifications
- * to support f2fs-specific xattr APIs.
- *
- * Written by Michael Halcrow, 2015.
- * Modified by Jaegeuk Kim, 2015.
- */
-#include <linux/random.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <linux/f2fs_fs.h>
-
-#include "f2fs.h"
-#include "xattr.h"
-
-static int f2fs_inode_has_encryption_context(struct inode *inode)
-{
-	int res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
-			F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, NULL, 0, NULL);
-	return (res > 0);
-}
-
-/*
- * check whether the policy is consistent with the encryption context
- * for the inode
- */
-static int f2fs_is_encryption_context_consistent_with_policy(
-	struct inode *inode, const struct f2fs_encryption_policy *policy)
-{
-	struct f2fs_encryption_context ctx;
-	int res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
-				F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
-				sizeof(ctx), NULL);
-
-	if (res != sizeof(ctx))
-		return 0;
-
-	return (memcmp(ctx.master_key_descriptor, policy->master_key_descriptor,
-				F2FS_KEY_DESCRIPTOR_SIZE) == 0 &&
-			(ctx.flags == policy->flags) &&
-			(ctx.contents_encryption_mode ==
-			 policy->contents_encryption_mode) &&
-			(ctx.filenames_encryption_mode ==
-			 policy->filenames_encryption_mode));
-}
-
-static int f2fs_create_encryption_context_from_policy(
-	struct inode *inode, const struct f2fs_encryption_policy *policy)
-{
-	struct f2fs_encryption_context ctx;
-
-	ctx.format = F2FS_ENCRYPTION_CONTEXT_FORMAT_V1;
-	memcpy(ctx.master_key_descriptor, policy->master_key_descriptor,
-			F2FS_KEY_DESCRIPTOR_SIZE);
-
-	if (!f2fs_valid_contents_enc_mode(policy->contents_encryption_mode)) {
-		printk(KERN_WARNING
-		       "%s: Invalid contents encryption mode %d\n", __func__,
-			policy->contents_encryption_mode);
-		return -EINVAL;
-	}
-
-	if (!f2fs_valid_filenames_enc_mode(policy->filenames_encryption_mode)) {
-		printk(KERN_WARNING
-		       "%s: Invalid filenames encryption mode %d\n", __func__,
-			policy->filenames_encryption_mode);
-		return -EINVAL;
-	}
-
-	if (policy->flags & ~F2FS_POLICY_FLAGS_VALID)
-		return -EINVAL;
-
-	ctx.contents_encryption_mode = policy->contents_encryption_mode;
-	ctx.filenames_encryption_mode = policy->filenames_encryption_mode;
-	ctx.flags = policy->flags;
-	BUILD_BUG_ON(sizeof(ctx.nonce) != F2FS_KEY_DERIVATION_NONCE_SIZE);
-	get_random_bytes(ctx.nonce, F2FS_KEY_DERIVATION_NONCE_SIZE);
-
-	return f2fs_setxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
-			F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
-			sizeof(ctx), NULL, XATTR_CREATE);
-}
-
-int f2fs_process_policy(const struct f2fs_encryption_policy *policy,
-			struct inode *inode)
-{
-	if (policy->version != 0)
-		return -EINVAL;
-
-	if (!S_ISDIR(inode->i_mode))
-		return -EINVAL;
-
-	if (!f2fs_inode_has_encryption_context(inode)) {
-		if (!f2fs_empty_dir(inode))
-			return -ENOTEMPTY;
-		return f2fs_create_encryption_context_from_policy(inode,
-								  policy);
-	}
-
-	if (f2fs_is_encryption_context_consistent_with_policy(inode, policy))
-		return 0;
-
-	printk(KERN_WARNING "%s: Policy inconsistent with encryption context\n",
-	       __func__);
-	return -EINVAL;
-}
-
-int f2fs_get_policy(struct inode *inode, struct f2fs_encryption_policy *policy)
-{
-	struct f2fs_encryption_context ctx;
-	int res;
-
-	if (!f2fs_encrypted_inode(inode))
-		return -ENODATA;
-
-	res = f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
-				F2FS_XATTR_NAME_ENCRYPTION_CONTEXT,
-				&ctx, sizeof(ctx), NULL);
-	if (res != sizeof(ctx))
-		return -ENODATA;
-	if (ctx.format != F2FS_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,
-			F2FS_KEY_DESCRIPTOR_SIZE);
-	return 0;
-}
-
-int f2fs_is_child_context_consistent_with_parent(struct inode *parent,
-						struct inode *child)
-{
-	struct f2fs_crypt_info *parent_ci, *child_ci;
-	int res;
-
-	if ((parent == NULL) || (child == NULL)) {
-		pr_err("parent %p child %p\n", parent, child);
-		BUG_ON(1);
-	}
-
-	/* no restrictions if the parent directory is not encrypted */
-	if (!f2fs_encrypted_inode(parent))
-		return 1;
-	/* if the child directory is not encrypted, this is always a problem */
-	if (!f2fs_encrypted_inode(child))
-		return 0;
-	res = f2fs_get_encryption_info(parent);
-	if (res)
-		return 0;
-	res = f2fs_get_encryption_info(child);
-	if (res)
-		return 0;
-	parent_ci = F2FS_I(parent)->i_crypt_info;
-	child_ci = F2FS_I(child)->i_crypt_info;
-	if (!parent_ci && !child_ci)
-		return 1;
-	if (!parent_ci || !child_ci)
-		return 0;
-
-	return (memcmp(parent_ci->ci_master_key,
-			child_ci->ci_master_key,
-			F2FS_KEY_DESCRIPTOR_SIZE) == 0 &&
-		(parent_ci->ci_data_mode == child_ci->ci_data_mode) &&
-		(parent_ci->ci_filename_mode == child_ci->ci_filename_mode) &&
-		(parent_ci->ci_flags == child_ci->ci_flags));
-}
-
-/**
- * f2fs_inherit_context() - Sets a child context from its parent
- * @parent: Parent inode from which the context is inherited.
- * @child:  Child inode that inherits the context from @parent.
- *
- * Return: Zero on success, non-zero otherwise
- */
-int f2fs_inherit_context(struct inode *parent, struct inode *child,
-						struct page *ipage)
-{
-	struct f2fs_encryption_context ctx;
-	struct f2fs_crypt_info *ci;
-	int res;
-
-	res = f2fs_get_encryption_info(parent);
-	if (res < 0)
-		return res;
-
-	ci = F2FS_I(parent)->i_crypt_info;
-	BUG_ON(ci == NULL);
-
-	ctx.format = F2FS_ENCRYPTION_CONTEXT_FORMAT_V1;
-
-	ctx.contents_encryption_mode = ci->ci_data_mode;
-	ctx.filenames_encryption_mode = ci->ci_filename_mode;
-	ctx.flags = ci->ci_flags;
-	memcpy(ctx.master_key_descriptor, ci->ci_master_key,
-			F2FS_KEY_DESCRIPTOR_SIZE);
-
-	get_random_bytes(ctx.nonce, F2FS_KEY_DERIVATION_NONCE_SIZE);
-	return f2fs_setxattr(child, F2FS_XATTR_INDEX_ENCRYPTION,
-				F2FS_XATTR_NAME_ENCRYPTION_CONTEXT, &ctx,
-				sizeof(ctx), ipage, XATTR_CREATE);
-}

fs/f2fs/data.c

@@ -34,9 +34,9 @@ static void f2fs_read_end_io(struct bio *bio)
 
 	if (f2fs_bio_encrypted(bio)) {
 		if (bio->bi_error) {
-			f2fs_release_crypto_ctx(bio->bi_private);
+			fscrypt_release_ctx(bio->bi_private);
 		} else {
-			f2fs_end_io_crypto_work(bio->bi_private, bio);
+			fscrypt_decrypt_bio_pages(bio->bi_private, bio);
 			return;
 		}
 	}
@@ -64,10 +64,9 @@ static void f2fs_write_end_io(struct bio *bio)
 	bio_for_each_segment_all(bvec, bio, i) {
 		struct page *page = bvec->bv_page;
 
-		f2fs_restore_and_release_control_page(&page);
+		fscrypt_pullback_bio_page(&page, true);
 
 		if (unlikely(bio->bi_error)) {
-			set_page_dirty(page);
 			set_bit(AS_EIO, &page->mapping->flags);
 			f2fs_stop_checkpoint(sbi);
 		}
@@ -75,8 +74,7 @@ static void f2fs_write_end_io(struct bio *bio)
 		dec_page_count(sbi, F2FS_WRITEBACK);
 	}
 
-	if (!get_pages(sbi, F2FS_WRITEBACK) &&
+	if (!get_pages(sbi, F2FS_WRITEBACK) && wq_has_sleeper(&sbi->cp_wait))
-			!list_empty(&sbi->cp_wait.task_list))
 		wake_up(&sbi->cp_wait);
 
 	bio_put(bio);
@@ -116,8 +114,54 @@ static void __submit_merged_bio(struct f2fs_bio_info *io)
 	io->bio = NULL;
 }
 
-void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
+static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode,
-				enum page_type type, int rw)
+						struct page *page, nid_t ino)
+{
+	struct bio_vec *bvec;
+	struct page *target;
+	int i;
+
+	if (!io->bio)
+		return false;
+
+	if (!inode && !page && !ino)
+		return true;
+
+	bio_for_each_segment_all(bvec, io->bio, i) {
+
+		if (bvec->bv_page->mapping)
+			target = bvec->bv_page;
+		else
+			target = fscrypt_control_page(bvec->bv_page);
+
+		if (inode && inode == target->mapping->host)
+			return true;
+		if (page && page == target)
+			return true;
+		if (ino && ino == ino_of_node(target))
+			return true;
+	}
+
+	return false;
+}
+
+static bool has_merged_page(struct f2fs_sb_info *sbi, struct inode *inode,
+						struct page *page, nid_t ino,
+						enum page_type type)
+{
+	enum page_type btype = PAGE_TYPE_OF_BIO(type);
+	struct f2fs_bio_info *io = &sbi->write_io[btype];
+	bool ret;
+
+	down_read(&io->io_rwsem);
+	ret = __has_merged_page(io, inode, page, ino);
+	up_read(&io->io_rwsem);
+	return ret;
+}
+
+static void __f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
+				struct inode *inode, struct page *page,
+				nid_t ino, enum page_type type, int rw)
 {
 	enum page_type btype = PAGE_TYPE_OF_BIO(type);
 	struct f2fs_bio_info *io;
@@ -126,6 +170,9 @@ void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
 
 	down_write(&io->io_rwsem);
 
+	if (!__has_merged_page(io, inode, page, ino))
+		goto out;
+
 	/* change META to META_FLUSH in the checkpoint procedure */
 	if (type >= META_FLUSH) {
 		io->fio.type = META_FLUSH;
@@ -135,9 +182,31 @@ void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
 			io->fio.rw = WRITE_FLUSH_FUA | REQ_META | REQ_PRIO;
 	}
 	__submit_merged_bio(io);
+out:
 	up_write(&io->io_rwsem);
 }
 
+void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, enum page_type type,
+									int rw)
+{
+	__f2fs_submit_merged_bio(sbi, NULL, NULL, 0, type, rw);
+}
+
+void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *sbi,
+				struct inode *inode, struct page *page,
+				nid_t ino, enum page_type type, int rw)
+{
+	if (has_merged_page(sbi, inode, page, ino, type))
+		__f2fs_submit_merged_bio(sbi, inode, page, ino, type, rw);
+}
+
+void f2fs_flush_merged_bios(struct f2fs_sb_info *sbi)
+{
+	f2fs_submit_merged_bio(sbi, DATA, WRITE);
+	f2fs_submit_merged_bio(sbi, NODE, WRITE);
+	f2fs_submit_merged_bio(sbi, META, WRITE);
+}
+
 /*
  * Fill the locked page with data located in the block address.
  * Return unlocked page.
@@ -145,13 +214,14 @@ void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
 int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 {
 	struct bio *bio;
-	struct page *page = fio->encrypted_page ? fio->encrypted_page : fio->page;
+	struct page *page = fio->encrypted_page ?
+			fio->encrypted_page : fio->page;
 
 	trace_f2fs_submit_page_bio(page, fio);
 	f2fs_trace_ios(fio, 0);
 
 	/* Allocate a new bio */
-	bio = __bio_alloc(fio->sbi, fio->blk_addr, 1, is_read_io(fio->rw));
+	bio = __bio_alloc(fio->sbi, fio->new_blkaddr, 1, is_read_io(fio->rw));
 
 	if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) {
 		bio_put(bio);
@@ -172,21 +242,24 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
 
 	io = is_read ? &sbi->read_io : &sbi->write_io[btype];
 
-	verify_block_addr(sbi, fio->blk_addr);
+	if (fio->old_blkaddr != NEW_ADDR)
+		verify_block_addr(sbi, fio->old_blkaddr);
+	verify_block_addr(sbi, fio->new_blkaddr);
 
 	down_write(&io->io_rwsem);
 
 	if (!is_read)
 		inc_page_count(sbi, F2FS_WRITEBACK);
 
-	if (io->bio && (io->last_block_in_bio != fio->blk_addr - 1 ||
+	if (io->bio && (io->last_block_in_bio != fio->new_blkaddr - 1 ||
 						io->fio.rw != fio->rw))
 		__submit_merged_bio(io);
 alloc_new:
 	if (io->bio == NULL) {
 		int bio_blocks = MAX_BIO_BLOCKS(sbi);
 
-		io->bio = __bio_alloc(sbi, fio->blk_addr, bio_blocks, is_read);
+		io->bio = __bio_alloc(sbi, fio->new_blkaddr,
+						bio_blocks, is_read);
 		io->fio = *fio;
 	}
 
@@ -198,7 +271,7 @@ alloc_new:
 		goto alloc_new;
 	}
 
-	io->last_block_in_bio = fio->blk_addr;
+	io->last_block_in_bio = fio->new_blkaddr;
 	f2fs_trace_ios(fio, 0);
 
 	up_write(&io->io_rwsem);
@@ -218,7 +291,7 @@ void set_data_blkaddr(struct dnode_of_data *dn)
 	struct page *node_page = dn->node_page;
 	unsigned int ofs_in_node = dn->ofs_in_node;
 
-	f2fs_wait_on_page_writeback(node_page, NODE);
+	f2fs_wait_on_page_writeback(node_page, NODE, true);
 
 	rn = F2FS_NODE(node_page);
 
@@ -229,6 +302,13 @@ void set_data_blkaddr(struct dnode_of_data *dn)
 		dn->node_changed = true;
 }
 
+void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr)
+{
+	dn->data_blkaddr = blkaddr;
+	set_data_blkaddr(dn);
+	f2fs_update_extent_cache(dn);
+}
+
 int reserve_new_block(struct dnode_of_data *dn)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
@@ -332,7 +412,7 @@ got_it:
 		return page;
 	}
 
-	fio.blk_addr = dn.data_blkaddr;
+	fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr;
 	fio.page = page;
 	err = f2fs_submit_page_bio(&fio);
 	if (err)
@@ -461,7 +541,6 @@ got_it:
 static int __allocate_data_block(struct dnode_of_data *dn)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
-	struct f2fs_inode_info *fi = F2FS_I(dn->inode);
 	struct f2fs_summary sum;
 	struct node_info ni;
 	int seg = CURSEG_WARM_DATA;
@@ -489,7 +568,7 @@ alloc:
 	set_data_blkaddr(dn);
 
 	/* update i_size */
-	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
+	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
 							dn->ofs_in_node;
 	if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_CACHE_SHIFT))
 		i_size_write(dn->inode,
@@ -497,67 +576,33 @@ alloc:
 	return 0;
 }
 
-static int __allocate_data_blocks(struct inode *inode, loff_t offset,
+ssize_t f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
-							size_t count)
 {
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct inode *inode = file_inode(iocb->ki_filp);
-	struct dnode_of_data dn;
+	struct f2fs_map_blocks map;
-	u64 start = F2FS_BYTES_TO_BLK(offset);
+	ssize_t ret = 0;
-	u64 len = F2FS_BYTES_TO_BLK(count);
-	bool allocated;
-	u64 end_offset;
-	int err = 0;
 
-	while (len) {
+	map.m_lblk = F2FS_BYTES_TO_BLK(iocb->ki_pos);
-		f2fs_lock_op(sbi);
+	map.m_len = F2FS_BLK_ALIGN(iov_iter_count(from));
+	map.m_next_pgofs = NULL;
 
-		/* When reading holes, we need its node page */
+	if (f2fs_encrypted_inode(inode))
-		set_new_dnode(&dn, inode, NULL, NULL, 0);
+		return 0;
-		err = get_dnode_of_data(&dn, start, ALLOC_NODE);
-		if (err)
-			goto out;
 
-		allocated = false;
+	if (iocb->ki_flags & IOCB_DIRECT) {
-		end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+		ret = f2fs_convert_inline_inode(inode);
-
+		if (ret)
-		while (dn.ofs_in_node < end_offset && len) {
+			return ret;
-			block_t blkaddr;
+		return f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_DIO);
-
-			if (unlikely(f2fs_cp_error(sbi))) {
-				err = -EIO;
-				goto sync_out;
-			}
-
-			blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
-			if (blkaddr == NULL_ADDR || blkaddr == NEW_ADDR) {
-				err = __allocate_data_block(&dn);
-				if (err)
-					goto sync_out;
-				allocated = true;
-			}
-			len--;
-			start++;
-			dn.ofs_in_node++;
-		}
-
-		if (allocated)
-			sync_inode_page(&dn);
-
-		f2fs_put_dnode(&dn);
-		f2fs_unlock_op(sbi);
-
-		f2fs_balance_fs(sbi, dn.node_changed);
 	}
-	return err;
+	if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA) {
-
+		ret = f2fs_convert_inline_inode(inode);
-sync_out:
+		if (ret)
-	if (allocated)
+			return ret;
-		sync_inode_page(&dn);
+	}
-	f2fs_put_dnode(&dn);
+	if (!f2fs_has_inline_data(inode))
-out:
+		return f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
-	f2fs_unlock_op(sbi);
+	return ret;
-	f2fs_balance_fs(sbi, dn.node_changed);
-	return err;
 }
 
 /*
@@ -588,13 +633,14 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 	/* it only supports block size == page size */
 	pgofs =	(pgoff_t)map->m_lblk;
 
-	if (f2fs_lookup_extent_cache(inode, pgofs, &ei)) {
+	if (!create && f2fs_lookup_extent_cache(inode, pgofs, &ei)) {
 		map->m_pblk = ei.blk + pgofs - ei.fofs;
 		map->m_len = min((pgoff_t)maxblocks, ei.fofs + ei.len - pgofs);
 		map->m_flags = F2FS_MAP_MAPPED;
 		goto out;
 	}
 
+next_dnode:
 	if (create)
 		f2fs_lock_op(sbi);
 
@@ -602,74 +648,18 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
 	err = get_dnode_of_data(&dn, pgofs, mode);
 	if (err) {
-		if (err == -ENOENT)
+		if (err == -ENOENT) {
 			err = 0;
+			if (map->m_next_pgofs)
+				*map->m_next_pgofs =
+					get_next_page_offset(&dn, pgofs);
+		}
 		goto unlock_out;
 	}
 
-	if (dn.data_blkaddr == NEW_ADDR || dn.data_blkaddr == NULL_ADDR) {
+	end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
-		if (create) {
-			if (unlikely(f2fs_cp_error(sbi))) {
-				err = -EIO;
-				goto put_out;
-			}
-			err = __allocate_data_block(&dn);
-			if (err)
-				goto put_out;
-			allocated = true;
-			map->m_flags = F2FS_MAP_NEW;
-		} else {
-			if (flag != F2FS_GET_BLOCK_FIEMAP ||
-						dn.data_blkaddr != NEW_ADDR) {
-				if (flag == F2FS_GET_BLOCK_BMAP)
-					err = -ENOENT;
-				goto put_out;
-			}
-
-			/*
-			 * preallocated unwritten block should be mapped
-			 * for fiemap.
-			 */
-			if (dn.data_blkaddr == NEW_ADDR)
-				map->m_flags = F2FS_MAP_UNWRITTEN;
-		}
-	}
-
-	map->m_flags |= F2FS_MAP_MAPPED;
-	map->m_pblk = dn.data_blkaddr;
-	map->m_len = 1;
-
-	end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
-	dn.ofs_in_node++;
-	pgofs++;
-
-get_next:
-	if (map->m_len >= maxblocks)
-		goto sync_out;
-
-	if (dn.ofs_in_node >= end_offset) {
-		if (allocated)
-			sync_inode_page(&dn);
-		allocated = false;
-		f2fs_put_dnode(&dn);
-
-		if (create) {
-			f2fs_unlock_op(sbi);
-			f2fs_balance_fs(sbi, dn.node_changed);
-			f2fs_lock_op(sbi);
-		}
-
-		set_new_dnode(&dn, inode, NULL, NULL, 0);
-		err = get_dnode_of_data(&dn, pgofs, mode);
-		if (err) {
-			if (err == -ENOENT)
-				err = 0;
-			goto unlock_out;
-		}
-
-		end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
-	}
 
+next_block:
 	blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
 
 	if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) {
@@ -678,44 +668,78 @@ get_next:
 				err = -EIO;
 				goto sync_out;
 			}
-			err = __allocate_data_block(&dn);
+			if (flag == F2FS_GET_BLOCK_PRE_AIO) {
+				if (blkaddr == NULL_ADDR)
+					err = reserve_new_block(&dn);
+			} else {
+				err = __allocate_data_block(&dn);
+			}
 			if (err)
 				goto sync_out;
 			allocated = true;
-			map->m_flags |= F2FS_MAP_NEW;
+			map->m_flags = F2FS_MAP_NEW;
 			blkaddr = dn.data_blkaddr;
 		} else {
-			/*
+			if (flag == F2FS_GET_BLOCK_FIEMAP &&
-			 * we only merge preallocated unwritten blocks
+						blkaddr == NULL_ADDR) {
-			 * for fiemap.
+				if (map->m_next_pgofs)
-			 */
+					*map->m_next_pgofs = pgofs + 1;
+			}
 			if (flag != F2FS_GET_BLOCK_FIEMAP ||
-					blkaddr != NEW_ADDR)
+						blkaddr != NEW_ADDR) {
+				if (flag == F2FS_GET_BLOCK_BMAP)
+					err = -ENOENT;
 				goto sync_out;
+			}
 		}
 	}
 
-	/* Give more consecutive addresses for the readahead */
+	if (map->m_len == 0) {
-	if ((map->m_pblk != NEW_ADDR &&
+		/* preallocated unwritten block should be mapped for fiemap. */
+		if (blkaddr == NEW_ADDR)
+			map->m_flags |= F2FS_MAP_UNWRITTEN;
+		map->m_flags |= F2FS_MAP_MAPPED;
+
+		map->m_pblk = blkaddr;
+		map->m_len = 1;
+	} else if ((map->m_pblk != NEW_ADDR &&
 			blkaddr == (map->m_pblk + ofs)) ||
-			(map->m_pblk == NEW_ADDR &&
+			(map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR) ||
-			blkaddr == NEW_ADDR)) {
+			flag == F2FS_GET_BLOCK_PRE_DIO ||
+			flag == F2FS_GET_BLOCK_PRE_AIO) {
 		ofs++;
-		dn.ofs_in_node++;
-		pgofs++;
 		map->m_len++;
-		goto get_next;
+	} else {
+		goto sync_out;
+	}
+
+	dn.ofs_in_node++;
+	pgofs++;
+
+	if (map->m_len < maxblocks) {
+		if (dn.ofs_in_node < end_offset)
+			goto next_block;
+
+		if (allocated)
+			sync_inode_page(&dn);
+		f2fs_put_dnode(&dn);
+
+		if (create) {
+			f2fs_unlock_op(sbi);
+			f2fs_balance_fs(sbi, allocated);
+		}
+		allocated = false;
+		goto next_dnode;
 	}
 
 sync_out:
 	if (allocated)
 		sync_inode_page(&dn);
-put_out:
 	f2fs_put_dnode(&dn);
 unlock_out:
 	if (create) {
 		f2fs_unlock_op(sbi);
-		f2fs_balance_fs(sbi, dn.node_changed);
+		f2fs_balance_fs(sbi, allocated);
 	}
 out:
 	trace_f2fs_map_blocks(inode, map, err);
@@ -723,13 +747,15 @@ out:
 }
 
 static int __get_data_block(struct inode *inode, sector_t iblock,
-			struct buffer_head *bh, int create, int flag)
+			struct buffer_head *bh, int create, int flag,
+			pgoff_t *next_pgofs)
 {
 	struct f2fs_map_blocks map;
 	int ret;
 
 	map.m_lblk = iblock;
 	map.m_len = bh->b_size >> inode->i_blkbits;
+	map.m_next_pgofs = next_pgofs;
 
 	ret = f2fs_map_blocks(inode, &map, create, flag);
 	if (!ret) {
@@ -741,16 +767,18 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
 }
 
 static int get_data_block(struct inode *inode, sector_t iblock,
-			struct buffer_head *bh_result, int create, int flag)
+			struct buffer_head *bh_result, int create, int flag,
+			pgoff_t *next_pgofs)
 {
-	return __get_data_block(inode, iblock, bh_result, create, flag);
+	return __get_data_block(inode, iblock, bh_result, create,
+							flag, next_pgofs);
 }
 
 static int get_data_block_dio(struct inode *inode, sector_t iblock,
 			struct buffer_head *bh_result, int create)
 {
 	return __get_data_block(inode, iblock, bh_result, create,
-						F2FS_GET_BLOCK_DIO);
+						F2FS_GET_BLOCK_DIO, NULL);
 }
 
 static int get_data_block_bmap(struct inode *inode, sector_t iblock,
@@ -761,7 +789,7 @@ static int get_data_block_bmap(struct inode *inode, sector_t iblock,
 		return -EFBIG;
 
 	return __get_data_block(inode, iblock, bh_result, create,
-						F2FS_GET_BLOCK_BMAP);
+						F2FS_GET_BLOCK_BMAP, NULL);
 }
 
 static inline sector_t logical_to_blk(struct inode *inode, loff_t offset)
@@ -779,6 +807,7 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 {
 	struct buffer_head map_bh;
 	sector_t start_blk, last_blk;
+	pgoff_t next_pgofs;
 	loff_t isize;
 	u64 logical = 0, phys = 0, size = 0;
 	u32 flags = 0;
@@ -814,14 +843,15 @@ next:
 	map_bh.b_size = len;
 
 	ret = get_data_block(inode, start_blk, &map_bh, 0,
-					F2FS_GET_BLOCK_FIEMAP);
+					F2FS_GET_BLOCK_FIEMAP, &next_pgofs);
 	if (ret)
 		goto out;
 
 	/* HOLE */
 	if (!buffer_mapped(&map_bh)) {
+		start_blk = next_pgofs;
 		/* Go through holes util pass the EOF */
-		if (blk_to_logical(inode, start_blk++) < isize)
+		if (blk_to_logical(inode, start_blk) < isize)
 			goto prep_next;
 		/* Found a hole beyond isize means no more extents.
 		 * Note that the premise is that filesystems don't
@@ -889,6 +919,7 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
 	map.m_lblk = 0;
 	map.m_len = 0;
 	map.m_flags = 0;
+	map.m_next_pgofs = NULL;
 
 	for (page_idx = 0; nr_pages; page_idx++, nr_pages--) {
 
@@ -927,7 +958,7 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
 			map.m_len = last_block - block_in_file;
 
 			if (f2fs_map_blocks(inode, &map, 0,
-							F2FS_GET_BLOCK_READ))
+						F2FS_GET_BLOCK_READ))
 				goto set_error_page;
 		}
 got_it:
@@ -956,12 +987,12 @@ submit_and_realloc:
 			bio = NULL;
 		}
 		if (bio == NULL) {
-			struct f2fs_crypto_ctx *ctx = NULL;
+			struct fscrypt_ctx *ctx = NULL;
 
 			if (f2fs_encrypted_inode(inode) &&
 					S_ISREG(inode->i_mode)) {
 
-				ctx = f2fs_get_crypto_ctx(inode);
+				ctx = fscrypt_get_ctx(inode);
 				if (IS_ERR(ctx))
 					goto set_error_page;
 
@@ -974,7 +1005,7 @@ submit_and_realloc:
 				min_t(int, nr_pages, BIO_MAX_PAGES));
 			if (!bio) {
 				if (ctx)
-					f2fs_release_crypto_ctx(ctx);
+					fscrypt_release_ctx(ctx);
 				goto set_error_page;
 			}
 			bio->bi_bdev = bdev;
@@ -1052,10 +1083,10 @@ int do_write_data_page(struct f2fs_io_info *fio)
 	if (err)
 		return err;
 
-	fio->blk_addr = dn.data_blkaddr;
+	fio->old_blkaddr = dn.data_blkaddr;
 
 	/* This page is already truncated */
-	if (fio->blk_addr == NULL_ADDR) {
+	if (fio->old_blkaddr == NULL_ADDR) {
 		ClearPageUptodate(page);
 		goto out_writepage;
 	}
@@ -1064,9 +1095,9 @@ int do_write_data_page(struct f2fs_io_info *fio)
 
 		/* wait for GCed encrypted page writeback */
 		f2fs_wait_on_encrypted_page_writeback(F2FS_I_SB(inode),
-							fio->blk_addr);
+							fio->old_blkaddr);
 
-		fio->encrypted_page = f2fs_encrypt(inode, fio->page);
+		fio->encrypted_page = fscrypt_encrypt_page(inode, fio->page);
 		if (IS_ERR(fio->encrypted_page)) {
 			err = PTR_ERR(fio->encrypted_page);
 			goto out_writepage;
@@ -1079,7 +1110,7 @@ int do_write_data_page(struct f2fs_io_info *fio)
 	 * If current allocation needs SSR,
 	 * it had better in-place writes for updated data.
 	 */
-	if (unlikely(fio->blk_addr != NEW_ADDR &&
+	if (unlikely(fio->old_blkaddr != NEW_ADDR &&
 			!is_cold_data(page) &&
 			!IS_ATOMIC_WRITTEN_PAGE(page) &&
 			need_inplace_update(inode))) {
@@ -1088,8 +1119,6 @@ int do_write_data_page(struct f2fs_io_info *fio)
 		trace_f2fs_do_write_data_page(page, IPU);
 	} else {
 		write_data_page(&dn, fio);
-		set_data_blkaddr(&dn);
-		f2fs_update_extent_cache(&dn);
 		trace_f2fs_do_write_data_page(page, OPU);
 		set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
 		if (page->index == 0)
@@ -1177,12 +1206,18 @@ out:
 	inode_dec_dirty_pages(inode);
 	if (err)
 		ClearPageUptodate(page);
-	unlock_page(page);
+
-	f2fs_balance_fs(sbi, need_balance_fs);
+	if (wbc->for_reclaim) {
-	if (wbc->for_reclaim || unlikely(f2fs_cp_error(sbi))) {
+		f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, DATA, WRITE);
-		f2fs_submit_merged_bio(sbi, DATA, WRITE);
 		remove_dirty_inode(inode);
 	}
+
+	unlock_page(page);
+	f2fs_balance_fs(sbi, need_balance_fs);
+
+	if (unlikely(f2fs_cp_error(sbi)))
+		f2fs_submit_merged_bio(sbi, DATA, WRITE);
+
 	return 0;
 
 redirty_out:
@@ -1282,7 +1317,8 @@ continue_unlock:
 
 			if (PageWriteback(page)) {
 				if (wbc->sync_mode != WB_SYNC_NONE)
-					f2fs_wait_on_page_writeback(page, DATA);
+					f2fs_wait_on_page_writeback(page,
+								DATA, true);
 				else
 					goto continue_unlock;
 			}
@@ -1339,8 +1375,6 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 	int ret;
 	long diff;
 
-	trace_f2fs_writepages(mapping->host, wbc, DATA);
-
 	/* deal with chardevs and other special file */
 	if (!mapping->a_ops->writepage)
 		return 0;
@@ -1362,14 +1396,16 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		goto skip_write;
 
+	trace_f2fs_writepages(mapping->host, wbc, DATA);
+
 	diff = nr_pages_to_write(sbi, DATA, wbc);
 
-	if (!S_ISDIR(inode->i_mode)) {
+	if (!S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_ALL) {
 		mutex_lock(&sbi->writepages);
 		locked = true;
 	}
 	ret = f2fs_write_cache_pages(mapping, wbc, __f2fs_writepage, mapping);
-	f2fs_submit_merged_bio(sbi, DATA, WRITE);
+	f2fs_submit_merged_bio_cond(sbi, inode, NULL, 0, DATA, WRITE);
 	if (locked)
 		mutex_unlock(&sbi->writepages);
 
@@ -1380,6 +1416,7 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 
 skip_write:
 	wbc->pages_skipped += get_dirty_pages(inode);
+	trace_f2fs_writepages(mapping->host, wbc, DATA);
 	return 0;
 }
 
@@ -1406,6 +1443,14 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi,
 	struct extent_info ei;
 	int err = 0;
 
+	/*
+	 * we already allocated all the blocks, so we don't need to get
+	 * the block addresses when there is no need to fill the page.
+	 */
+	if (!f2fs_has_inline_data(inode) && !f2fs_encrypted_inode(inode) &&
+					len == PAGE_CACHE_SIZE)
+		return 0;
+
 	if (f2fs_has_inline_data(inode) ||
 			(pos & PAGE_CACHE_MASK) >= i_size_read(inode)) {
 		f2fs_lock_op(sbi);
@@ -1425,7 +1470,7 @@ restart:
 		if (pos + len <= MAX_INLINE_DATA) {
 			read_inline_data(page, ipage);
 			set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
-			sync_inode_page(&dn);
+			set_inline_node(ipage);
 		} else {
 			err = f2fs_convert_inline_page(&dn, page);
 			if (err)
@@ -1439,13 +1484,9 @@ restart:
 		if (f2fs_lookup_extent_cache(inode, index, &ei)) {
 			dn.data_blkaddr = ei.blk + index - ei.fofs;
 		} else {
-			bool restart = false;
-
 			/* hole case */
 			err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
-			if (err || (!err && dn.data_blkaddr == NULL_ADDR))
+			if (err || (!err && dn.data_blkaddr == NULL_ADDR)) {
-				restart = true;
-			if (restart) {
 				f2fs_put_dnode(&dn);
 				f2fs_lock_op(sbi);
 				locked = true;
@@ -1514,7 +1555,7 @@ repeat:
 		}
 	}
 
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_wait_on_page_writeback(page, DATA, false);
 
 	/* wait for GCed encrypted page writeback */
 	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
@@ -1541,7 +1582,8 @@ repeat:
 			.sbi = sbi,
 			.type = DATA,
 			.rw = READ_SYNC,
-			.blk_addr = blkaddr,
+			.old_blkaddr = blkaddr,
+			.new_blkaddr = blkaddr,
 			.page = page,
 			.encrypted_page = NULL,
 		};
@@ -1561,7 +1603,7 @@ repeat:
 
 		/* avoid symlink page */
 		if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
-			err = f2fs_decrypt_one(inode, page);
+			err = fscrypt_decrypt_page(page);
 			if (err)
 				goto fail;
 		}
@@ -1592,7 +1634,6 @@ static int f2fs_write_end(struct file *file,
 	if (pos + copied > i_size_read(inode)) {
 		i_size_write(inode, pos + copied);
 		mark_inode_dirty(inode);
-		update_inode_page(inode);
 	}
 
 	f2fs_put_page(page, 1);
@@ -1617,34 +1658,21 @@ static int check_direct_IO(struct inode *inode, struct iov_iter *iter,
 static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 			      loff_t offset)
 {
-	struct file *file = iocb->ki_filp;
+	struct address_space *mapping = iocb->ki_filp->f_mapping;
-	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = mapping->host;
 	size_t count = iov_iter_count(iter);
 	int err;
 
-	/* we don't need to use inline_data strictly */
+	err = check_direct_IO(inode, iter, offset);
-	err = f2fs_convert_inline_inode(inode);
 	if (err)
 		return err;
 
 	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
 		return 0;
 
-	err = check_direct_IO(inode, iter, offset);
-	if (err)
-		return err;
-
 	trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
 
-	if (iov_iter_rw(iter) == WRITE) {
-		err = __allocate_data_blocks(inode, offset, count);
-		if (err)
-			goto out;
-	}
-
 	err = blockdev_direct_IO(iocb, inode, iter, offset, get_data_block_dio);
-out:
 	if (err < 0 && iov_iter_rw(iter) == WRITE)
 		f2fs_write_failed(mapping, offset + count);
 

fs/f2fs/dir.c

@@ -77,7 +77,7 @@ static unsigned long dir_block_index(unsigned int level,
 }
 
 static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
-				struct f2fs_filename *fname,
+				struct fscrypt_name *fname,
 				f2fs_hash_t namehash,
 				int *max_slots,
 				struct page **res_page)
@@ -103,15 +103,15 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
 	return de;
 }
 
-struct f2fs_dir_entry *find_target_dentry(struct f2fs_filename *fname,
+struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname,
 			f2fs_hash_t namehash, int *max_slots,
 			struct f2fs_dentry_ptr *d)
 {
 	struct f2fs_dir_entry *de;
 	unsigned long bit_pos = 0;
 	int max_len = 0;
-	struct f2fs_str de_name = FSTR_INIT(NULL, 0);
+	struct fscrypt_str de_name = FSTR_INIT(NULL, 0);
-	struct f2fs_str *name = &fname->disk_name;
+	struct fscrypt_str *name = &fname->disk_name;
 
 	if (max_slots)
 		*max_slots = 0;
@@ -157,7 +157,7 @@ found:
 
 static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 					unsigned int level,
-					struct f2fs_filename *fname,
+					struct fscrypt_name *fname,
 					struct page **res_page)
 {
 	struct qstr name = FSTR_TO_QSTR(&fname->disk_name);
@@ -218,12 +218,12 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
 	struct f2fs_dir_entry *de = NULL;
 	unsigned int max_depth;
 	unsigned int level;
-	struct f2fs_filename fname;
+	struct fscrypt_name fname;
 	int err;
 
 	*res_page = NULL;
 
-	err = f2fs_fname_setup_filename(dir, child, 1, &fname);
+	err = fscrypt_setup_filename(dir, child, 1, &fname);
 	if (err)
 		return NULL;
 
@@ -251,7 +251,7 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
 			break;
 	}
 out:
-	f2fs_fname_free_filename(&fname);
+	fscrypt_free_filename(&fname);
 	return de;
 }
 
@@ -296,7 +296,7 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
 {
 	enum page_type type = f2fs_has_inline_dentry(dir) ? NODE : DATA;
 	lock_page(page);
-	f2fs_wait_on_page_writeback(page, type);
+	f2fs_wait_on_page_writeback(page, type, true);
 	de->ino = cpu_to_le32(inode->i_ino);
 	set_de_type(de, inode->i_mode);
 	f2fs_dentry_kunmap(dir, page);
@@ -311,7 +311,7 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage)
 {
 	struct f2fs_inode *ri;
 
-	f2fs_wait_on_page_writeback(ipage, NODE);
+	f2fs_wait_on_page_writeback(ipage, NODE, true);
 
 	/* copy name info. to this inode page */
 	ri = F2FS_INODE(ipage);
@@ -341,24 +341,14 @@ int update_dent_inode(struct inode *inode, struct inode *to,
 void do_make_empty_dir(struct inode *inode, struct inode *parent,
 					struct f2fs_dentry_ptr *d)
 {
-	struct f2fs_dir_entry *de;
+	struct qstr dot = QSTR_INIT(".", 1);
+	struct qstr dotdot = QSTR_INIT("..", 2);
 
-	de = &d->dentry[0];
+	/* update dirent of "." */
-	de->name_len = cpu_to_le16(1);
+	f2fs_update_dentry(inode->i_ino, inode->i_mode, d, &dot, 0, 0);
-	de->hash_code = 0;
-	de->ino = cpu_to_le32(inode->i_ino);
-	memcpy(d->filename[0], ".", 1);
-	set_de_type(de, inode->i_mode);
 
-	de = &d->dentry[1];
+	/* update dirent of ".." */
-	de->hash_code = 0;
+	f2fs_update_dentry(parent->i_ino, parent->i_mode, d, &dotdot, 0, 1);
-	de->name_len = cpu_to_le16(2);
-	de->ino = cpu_to_le32(parent->i_ino);
-	memcpy(d->filename[1], "..", 2);
-	set_de_type(de, parent->i_mode);
-
-	test_and_set_bit_le(0, (void *)d->bitmap);
-	test_and_set_bit_le(1, (void *)d->bitmap);
 }
 
 static int make_empty_dir(struct inode *inode,
@@ -413,7 +403,7 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
 			goto put_error;
 
 		if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode)) {
-			err = f2fs_inherit_context(dir, inode, page);
+			err = fscrypt_inherit_context(dir, inode, page, false);
 			if (err)
 				goto put_error;
 		}
@@ -511,8 +501,12 @@ void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
 	memcpy(d->filename[bit_pos], name->name, name->len);
 	de->ino = cpu_to_le32(ino);
 	set_de_type(de, mode);
-	for (i = 0; i < slots; i++)
+	for (i = 0; i < slots; i++) {
 		test_and_set_bit_le(bit_pos + i, (void *)d->bitmap);
+		/* avoid wrong garbage data for readdir */
+		if (i)
+			(de + i)->name_len = 0;
+	}
 }
 
 /*
@@ -532,11 +526,11 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
 	struct f2fs_dentry_block *dentry_blk = NULL;
 	struct f2fs_dentry_ptr d;
 	struct page *page = NULL;
-	struct f2fs_filename fname;
+	struct fscrypt_name fname;
 	struct qstr new_name;
 	int slots, err;
 
-	err = f2fs_fname_setup_filename(dir, name, 0, &fname);
+	err = fscrypt_setup_filename(dir, name, 0, &fname);
 	if (err)
 		return err;
 
@@ -598,7 +592,7 @@ start:
 	++level;
 	goto start;
 add_dentry:
-	f2fs_wait_on_page_writeback(dentry_page, DATA);
+	f2fs_wait_on_page_writeback(dentry_page, DATA, true);
 
 	if (inode) {
 		down_write(&F2FS_I(inode)->i_sem);
@@ -635,7 +629,7 @@ fail:
 	kunmap(dentry_page);
 	f2fs_put_page(dentry_page, 1);
 out:
-	f2fs_fname_free_filename(&fname);
+	fscrypt_free_filename(&fname);
 	f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
 	return err;
 }
@@ -709,7 +703,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 		return f2fs_delete_inline_entry(dentry, page, dir, inode);
 
 	lock_page(page);
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_wait_on_page_writeback(page, DATA, true);
 
 	dentry_blk = page_address(page);
 	bit_pos = dentry - dentry_blk->dentry;
@@ -777,12 +771,12 @@ bool f2fs_empty_dir(struct inode *dir)
 }
 
 bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
-				unsigned int start_pos, struct f2fs_str *fstr)
+			unsigned int start_pos, struct fscrypt_str *fstr)
 {
 	unsigned char d_type = DT_UNKNOWN;
 	unsigned int bit_pos;
 	struct f2fs_dir_entry *de = NULL;
-	struct f2fs_str de_name = FSTR_INIT(NULL, 0);
+	struct fscrypt_str de_name = FSTR_INIT(NULL, 0);
 
 	bit_pos = ((unsigned long)ctx->pos % d->max);
 
@@ -792,6 +786,12 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 			break;
 
 		de = &d->dentry[bit_pos];
+		if (de->name_len == 0) {
+			bit_pos++;
+			ctx->pos = start_pos + bit_pos;
+			continue;
+		}
+
 		if (de->file_type < F2FS_FT_MAX)
 			d_type = f2fs_filetype_table[de->file_type];
 		else
@@ -810,8 +810,9 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 
 			memcpy(de_name.name, d->filename[bit_pos], de_name.len);
 
-			ret = f2fs_fname_disk_to_usr(d->inode, &de->hash_code,
+			ret = fscrypt_fname_disk_to_usr(d->inode,
-							&de_name, fstr);
+						(u32)de->hash_code, 0,
+						&de_name, fstr);
 			kfree(de_name.name);
 			if (ret < 0)
 				return true;
@@ -839,16 +840,15 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 	struct file_ra_state *ra = &file->f_ra;
 	unsigned int n = ((unsigned long)ctx->pos / NR_DENTRY_IN_BLOCK);
 	struct f2fs_dentry_ptr d;
-	struct f2fs_str fstr = FSTR_INIT(NULL, 0);
+	struct fscrypt_str fstr = FSTR_INIT(NULL, 0);
 	int err = 0;
 
 	if (f2fs_encrypted_inode(inode)) {
-		err = f2fs_get_encryption_info(inode);
+		err = fscrypt_get_encryption_info(inode);
-		if (err)
+		if (err && err != -ENOKEY)
 			return err;
 
-		err = f2fs_fname_crypto_alloc_buffer(inode, F2FS_NAME_LEN,
+		err = fscrypt_fname_alloc_buffer(inode, F2FS_NAME_LEN, &fstr);
-								&fstr);
 		if (err < 0)
 			return err;
 	}
@@ -888,15 +888,23 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 		f2fs_put_page(dentry_page, 1);
 	}
 out:
-	f2fs_fname_crypto_free_buffer(&fstr);
+	fscrypt_fname_free_buffer(&fstr);
 	return err;
 }
 
+static int f2fs_dir_open(struct inode *inode, struct file *filp)
+{
+	if (f2fs_encrypted_inode(inode))
+		return fscrypt_get_encryption_info(inode) ? -EACCES : 0;
+	return 0;
+}
+
 const struct file_operations f2fs_dir_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= generic_read_dir,
 	.iterate	= f2fs_readdir,
 	.fsync		= f2fs_sync_file,
+	.open		= f2fs_dir_open,
 	.unlocked_ioctl	= f2fs_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl   = f2fs_compat_ioctl,

fs/f2fs/extent_cache.c

@@ -33,6 +33,7 @@ static struct extent_node *__attach_extent_node(struct f2fs_sb_info *sbi,
 
 	en->ei = *ei;
 	INIT_LIST_HEAD(&en->list);
+	en->et = et;
 
 	rb_link_node(&en->rb_node, parent, p);
 	rb_insert_color(&en->rb_node, &et->root);
@@ -50,6 +51,24 @@ static void __detach_extent_node(struct f2fs_sb_info *sbi,
 
 	if (et->cached_en == en)
 		et->cached_en = NULL;
+	kmem_cache_free(extent_node_slab, en);
+}
+
+/*
+ * Flow to release an extent_node:
+ * 1. list_del_init
+ * 2. __detach_extent_node
+ * 3. kmem_cache_free.
+ */
+static void __release_extent_node(struct f2fs_sb_info *sbi,
+			struct extent_tree *et, struct extent_node *en)
+{
+	spin_lock(&sbi->extent_lock);
+	f2fs_bug_on(sbi, list_empty(&en->list));
+	list_del_init(&en->list);
+	spin_unlock(&sbi->extent_lock);
+
+	__detach_extent_node(sbi, et, en);
 }
 
 static struct extent_tree *__grab_extent_tree(struct inode *inode)
@@ -129,7 +148,7 @@ static struct extent_node *__init_extent_tree(struct f2fs_sb_info *sbi,
 }
 
 static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,
-					struct extent_tree *et, bool free_all)
+					struct extent_tree *et)
 {
 	struct rb_node *node, *next;
 	struct extent_node *en;
@@ -139,18 +158,7 @@ static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,
 	while (node) {
 		next = rb_next(node);
 		en = rb_entry(node, struct extent_node, rb_node);
-
+		__release_extent_node(sbi, et, en);
-		if (free_all) {
-			spin_lock(&sbi->extent_lock);
-			if (!list_empty(&en->list))
-				list_del_init(&en->list);
-			spin_unlock(&sbi->extent_lock);
-		}
-
-		if (free_all || list_empty(&en->list)) {
-			__detach_extent_node(sbi, et, en);
-			kmem_cache_free(extent_node_slab, en);
-		}
 		node = next;
 	}
 
@@ -232,9 +240,10 @@ static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
 	if (en) {
 		*ei = en->ei;
 		spin_lock(&sbi->extent_lock);
-		if (!list_empty(&en->list))
+		if (!list_empty(&en->list)) {
 			list_move_tail(&en->list, &sbi->extent_list);
-		et->cached_en = en;
+			et->cached_en = en;
+		}
 		spin_unlock(&sbi->extent_lock);
 		ret = true;
 	}
@@ -329,7 +338,6 @@ lookup_neighbors:
 
 static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi,
 				struct extent_tree *et, struct extent_info *ei,
-				struct extent_node **den,
 				struct extent_node *prev_ex,
 				struct extent_node *next_ex)
 {
@@ -342,20 +350,25 @@ static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi,
 	}
 
 	if (next_ex && __is_front_mergeable(ei, &next_ex->ei)) {
-		if (en) {
+		if (en)
-			__detach_extent_node(sbi, et, prev_ex);
+			__release_extent_node(sbi, et, prev_ex);
-			*den = prev_ex;
-		}
 		next_ex->ei.fofs = ei->fofs;
 		next_ex->ei.blk = ei->blk;
 		next_ex->ei.len += ei->len;
 		en = next_ex;
 	}
 
-	if (en) {
+	if (!en)
-		__try_update_largest_extent(et, en);
+		return NULL;
+
+	__try_update_largest_extent(et, en);
+
+	spin_lock(&sbi->extent_lock);
+	if (!list_empty(&en->list)) {
+		list_move_tail(&en->list, &sbi->extent_list);
 		et->cached_en = en;
 	}
+	spin_unlock(&sbi->extent_lock);
 	return en;
 }
 
@@ -391,7 +404,12 @@ do_insert:
 		return NULL;
 
 	__try_update_largest_extent(et, en);
+
+	/* update in global extent list */
+	spin_lock(&sbi->extent_lock);
+	list_add_tail(&en->list, &sbi->extent_list);
 	et->cached_en = en;
+	spin_unlock(&sbi->extent_lock);
 	return en;
 }
 
@@ -479,7 +497,7 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 		if (parts)
 			__try_update_largest_extent(et, en);
 		else
-			__detach_extent_node(sbi, et, en);
+			__release_extent_node(sbi, et, en);
 
 		/*
 		 * if original extent is split into zero or two parts, extent
@@ -490,31 +508,15 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 			insert_p = NULL;
 			insert_parent = NULL;
 		}
-
-		/* update in global extent list */
-		spin_lock(&sbi->extent_lock);
-		if (!parts && !list_empty(&en->list))
-			list_del(&en->list);
-		if (en1)
-			list_add_tail(&en1->list, &sbi->extent_list);
-		spin_unlock(&sbi->extent_lock);
-
-		/* release extent node */
-		if (!parts)
-			kmem_cache_free(extent_node_slab, en);
-
 		en = next_en;
 	}
 
 	/* 3. update extent in extent cache */
 	if (blkaddr) {
-		struct extent_node *den = NULL;
 
 		set_extent_info(&ei, fofs, blkaddr, len);
-		en1 = __try_merge_extent_node(sbi, et, &ei, &den,
+		if (!__try_merge_extent_node(sbi, et, &ei, prev_en, next_en))
-							prev_en, next_en);
+			__insert_extent_tree(sbi, et, &ei,
-		if (!en1)
-			en1 = __insert_extent_tree(sbi, et, &ei,
 						insert_p, insert_parent);
 
 		/* give up extent_cache, if split and small updates happen */
@@ -524,24 +526,10 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 			et->largest.len = 0;
 			set_inode_flag(F2FS_I(inode), FI_NO_EXTENT);
 		}
-
-		spin_lock(&sbi->extent_lock);
-		if (en1) {
-			if (list_empty(&en1->list))
-				list_add_tail(&en1->list, &sbi->extent_list);
-			else
-				list_move_tail(&en1->list, &sbi->extent_list);
-		}
-		if (den && !list_empty(&den->list))
-			list_del(&den->list);
-		spin_unlock(&sbi->extent_lock);
-
-		if (den)
-			kmem_cache_free(extent_node_slab, den);
 	}
 
 	if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT))
-		__free_extent_tree(sbi, et, true);
+		__free_extent_tree(sbi, et);
 
 	write_unlock(&et->lock);
 
@@ -550,14 +538,10 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 
 unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
 {
-	struct extent_tree *treevec[EXT_TREE_VEC_SIZE];
 	struct extent_tree *et, *next;
-	struct extent_node *en, *tmp;
+	struct extent_node *en;
-	unsigned long ino = F2FS_ROOT_INO(sbi);
-	unsigned int found;
 	unsigned int node_cnt = 0, tree_cnt = 0;
 	int remained;
-	bool do_free = false;
 
 	if (!test_opt(sbi, EXTENT_CACHE))
 		return 0;
@@ -572,10 +556,10 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
 	list_for_each_entry_safe(et, next, &sbi->zombie_list, list) {
 		if (atomic_read(&et->node_cnt)) {
 			write_lock(&et->lock);
-			node_cnt += __free_extent_tree(sbi, et, true);
+			node_cnt += __free_extent_tree(sbi, et);
 			write_unlock(&et->lock);
 		}
-
+		f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
 		list_del_init(&et->list);
 		radix_tree_delete(&sbi->extent_tree_root, et->ino);
 		kmem_cache_free(extent_tree_slab, et);
@@ -585,6 +569,7 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
 
 		if (node_cnt + tree_cnt >= nr_shrink)
 			goto unlock_out;
+		cond_resched();
 	}
 	up_write(&sbi->extent_tree_lock);
 
@@ -596,42 +581,29 @@ free_node:
 	remained = nr_shrink - (node_cnt + tree_cnt);
 
 	spin_lock(&sbi->extent_lock);
-	list_for_each_entry_safe(en, tmp, &sbi->extent_list, list) {
+	for (; remained > 0; remained--) {
-		if (!remained--)
+		if (list_empty(&sbi->extent_list))
 			break;
+		en = list_first_entry(&sbi->extent_list,
+					struct extent_node, list);
+		et = en->et;
+		if (!write_trylock(&et->lock)) {
+			/* refresh this extent node's position in extent list */
+			list_move_tail(&en->list, &sbi->extent_list);
+			continue;
+		}
+
 		list_del_init(&en->list);
-		do_free = true;
+		spin_unlock(&sbi->extent_lock);
+
+		__detach_extent_node(sbi, et, en);
+
+		write_unlock(&et->lock);
+		node_cnt++;
+		spin_lock(&sbi->extent_lock);
 	}
 	spin_unlock(&sbi->extent_lock);
 
-	if (do_free == false)
-		goto unlock_out;
-
-	/*
-	 * reset ino for searching victims from beginning of global extent tree.
-	 */
-	ino = F2FS_ROOT_INO(sbi);
-
-	while ((found = radix_tree_gang_lookup(&sbi->extent_tree_root,
-				(void **)treevec, ino, EXT_TREE_VEC_SIZE))) {
-		unsigned i;
-
-		ino = treevec[found - 1]->ino + 1;
-		for (i = 0; i < found; i++) {
-			struct extent_tree *et = treevec[i];
-
-			if (!atomic_read(&et->node_cnt))
-				continue;
-
-			if (write_trylock(&et->lock)) {
-				node_cnt += __free_extent_tree(sbi, et, false);
-				write_unlock(&et->lock);
-			}
-
-			if (node_cnt + tree_cnt >= nr_shrink)
-				goto unlock_out;
-		}
-	}
 unlock_out:
 	up_write(&sbi->extent_tree_lock);
 out:
@@ -650,7 +622,7 @@ unsigned int f2fs_destroy_extent_node(struct inode *inode)
 		return 0;
 
 	write_lock(&et->lock);
-	node_cnt = __free_extent_tree(sbi, et, true);
+	node_cnt = __free_extent_tree(sbi, et);
 	write_unlock(&et->lock);
 
 	return node_cnt;
@@ -701,19 +673,21 @@ bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
 
 void f2fs_update_extent_cache(struct dnode_of_data *dn)
 {
-	struct f2fs_inode_info *fi = F2FS_I(dn->inode);
 	pgoff_t fofs;
+	block_t blkaddr;
 
 	if (!f2fs_may_extent_tree(dn->inode))
 		return;
 
-	f2fs_bug_on(F2FS_I_SB(dn->inode), dn->data_blkaddr == NEW_ADDR);
+	if (dn->data_blkaddr == NEW_ADDR)
+		blkaddr = NULL_ADDR;
+	else
+		blkaddr = dn->data_blkaddr;
 
+	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
+								dn->ofs_in_node;
 
-	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
+	if (f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, 1))
-							dn->ofs_in_node;
-
-	if (f2fs_update_extent_tree_range(dn->inode, fofs, dn->data_blkaddr, 1))
 		sync_inode_page(dn);
 }
 

fs/f2fs/f2fs.h

@@ -22,10 +22,11 @@
 #include <linux/vmalloc.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
+#include <linux/fscrypto.h>
+#include <crypto/hash.h>
 
 #ifdef CONFIG_F2FS_CHECK_FS
 #define f2fs_bug_on(sbi, condition)	BUG_ON(condition)
-#define f2fs_down_write(x, y)	down_write_nest_lock(x, y)
 #else
 #define f2fs_bug_on(sbi, condition)					\
 	do {								\
@@ -34,7 +35,6 @@
 			set_sbi_flag(sbi, SBI_NEED_FSCK);		\
 		}							\
 	} while (0)
-#define f2fs_down_write(x, y)	down_write(x)
 #endif
 
 /*
@@ -84,27 +84,6 @@ struct f2fs_mount_info {
 #define F2FS_CLEAR_FEATURE(sb, mask)					\
 	F2FS_SB(sb)->raw_super->feature &= ~cpu_to_le32(mask)
 
-#define CRCPOLY_LE 0xedb88320
-
-static inline __u32 f2fs_crc32(void *buf, size_t len)
-{
-	unsigned char *p = (unsigned char *)buf;
-	__u32 crc = F2FS_SUPER_MAGIC;
-	int i;
-
-	while (len--) {
-		crc ^= *p++;
-		for (i = 0; i < 8; i++)
-			crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0);
-	}
-	return crc;
-}
-
-static inline bool f2fs_crc_valid(__u32 blk_crc, void *buf, size_t buf_size)
-{
-	return f2fs_crc32(buf, buf_size) == blk_crc;
-}
-
 /*
  * For checkpoint manager
  */
@@ -183,37 +162,37 @@ struct fsync_inode_entry {
 	block_t last_inode;	/* block address locating the last inode */
 };
 
-#define nats_in_cursum(sum)		(le16_to_cpu(sum->n_nats))
+#define nats_in_cursum(jnl)		(le16_to_cpu(jnl->n_nats))
-#define sits_in_cursum(sum)		(le16_to_cpu(sum->n_sits))
+#define sits_in_cursum(jnl)		(le16_to_cpu(jnl->n_sits))
 
-#define nat_in_journal(sum, i)		(sum->nat_j.entries[i].ne)
+#define nat_in_journal(jnl, i)		(jnl->nat_j.entries[i].ne)
-#define nid_in_journal(sum, i)		(sum->nat_j.entries[i].nid)
+#define nid_in_journal(jnl, i)		(jnl->nat_j.entries[i].nid)
-#define sit_in_journal(sum, i)		(sum->sit_j.entries[i].se)
+#define sit_in_journal(jnl, i)		(jnl->sit_j.entries[i].se)
-#define segno_in_journal(sum, i)	(sum->sit_j.entries[i].segno)
+#define segno_in_journal(jnl, i)	(jnl->sit_j.entries[i].segno)
 
-#define MAX_NAT_JENTRIES(sum)	(NAT_JOURNAL_ENTRIES - nats_in_cursum(sum))
+#define MAX_NAT_JENTRIES(jnl)	(NAT_JOURNAL_ENTRIES - nats_in_cursum(jnl))
-#define MAX_SIT_JENTRIES(sum)	(SIT_JOURNAL_ENTRIES - sits_in_cursum(sum))
+#define MAX_SIT_JENTRIES(jnl)	(SIT_JOURNAL_ENTRIES - sits_in_cursum(jnl))
 
-static inline int update_nats_in_cursum(struct f2fs_summary_block *rs, int i)
+static inline int update_nats_in_cursum(struct f2fs_journal *journal, int i)
 {
-	int before = nats_in_cursum(rs);
+	int before = nats_in_cursum(journal);
-	rs->n_nats = cpu_to_le16(before + i);
+	journal->n_nats = cpu_to_le16(before + i);
 	return before;
 }
 
-static inline int update_sits_in_cursum(struct f2fs_summary_block *rs, int i)
+static inline int update_sits_in_cursum(struct f2fs_journal *journal, int i)
 {
-	int before = sits_in_cursum(rs);
+	int before = sits_in_cursum(journal);
-	rs->n_sits = cpu_to_le16(before + i);
+	journal->n_sits = cpu_to_le16(before + i);
 	return before;
 }
 
-static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size,
+static inline bool __has_cursum_space(struct f2fs_journal *journal,
-								int type)
+							int size, int type)
 {
 	if (type == NAT_JOURNAL)
-		return size <= MAX_NAT_JENTRIES(sum);
+		return size <= MAX_NAT_JENTRIES(journal);
-	return size <= MAX_SIT_JENTRIES(sum);
+	return size <= MAX_SIT_JENTRIES(journal);
 }
 
 /*
@@ -233,12 +212,9 @@ static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size,
 #define F2FS_IOC_WRITE_CHECKPOINT	_IO(F2FS_IOCTL_MAGIC, 7)
 #define F2FS_IOC_DEFRAGMENT		_IO(F2FS_IOCTL_MAGIC, 8)
 
-#define F2FS_IOC_SET_ENCRYPTION_POLICY					\
+#define F2FS_IOC_SET_ENCRYPTION_POLICY	FS_IOC_SET_ENCRYPTION_POLICY
-		_IOR('f', 19, struct f2fs_encryption_policy)
+#define F2FS_IOC_GET_ENCRYPTION_POLICY	FS_IOC_GET_ENCRYPTION_POLICY
-#define F2FS_IOC_GET_ENCRYPTION_PWSALT					\
+#define F2FS_IOC_GET_ENCRYPTION_PWSALT	FS_IOC_GET_ENCRYPTION_PWSALT
-		_IOW('f', 20, __u8[16])
-#define F2FS_IOC_GET_ENCRYPTION_POLICY					\
-		_IOW('f', 21, struct f2fs_encryption_policy)
 
 /*
  * should be same as XFS_IOC_GOINGDOWN.
@@ -268,25 +244,6 @@ struct f2fs_defragment {
  * For INODE and NODE manager
  */
 /* for directory operations */
-struct f2fs_str {
-	unsigned char *name;
-	u32 len;
-};
-
-struct f2fs_filename {
-	const struct qstr *usr_fname;
-	struct f2fs_str disk_name;
-	f2fs_hash_t hash;
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-	struct f2fs_str crypto_buf;
-#endif
-};
-
-#define FSTR_INIT(n, l)		{ .name = n, .len = l }
-#define FSTR_TO_QSTR(f)		QSTR_INIT((f)->name, (f)->len)
-#define fname_name(p)		((p)->disk_name.name)
-#define fname_len(p)		((p)->disk_name.len)
-
 struct f2fs_dentry_ptr {
 	struct inode *inode;
 	const void *bitmap;
@@ -354,6 +311,7 @@ struct extent_node {
 	struct rb_node rb_node;		/* rb node located in rb-tree */
 	struct list_head list;		/* node in global extent list of sbi */
 	struct extent_info ei;		/* extent info */
+	struct extent_tree *et;		/* extent tree pointer */
 };
 
 struct extent_tree {
@@ -382,6 +340,7 @@ struct f2fs_map_blocks {
 	block_t m_lblk;
 	unsigned int m_len;
 	unsigned int m_flags;
+	pgoff_t *m_next_pgofs;		/* point next possible non-hole pgofs */
 };
 
 /* for flag in get_data_block */
@@ -389,6 +348,8 @@ struct f2fs_map_blocks {
 #define F2FS_GET_BLOCK_DIO		1
 #define F2FS_GET_BLOCK_FIEMAP		2
 #define F2FS_GET_BLOCK_BMAP		3
+#define F2FS_GET_BLOCK_PRE_DIO		4
+#define F2FS_GET_BLOCK_PRE_AIO		5
 
 /*
  * i_advise uses FADVISE_XXX_BIT. We can add additional hints later.
@@ -410,15 +371,6 @@ struct f2fs_map_blocks {
 #define file_enc_name(inode)	is_file(inode, FADVISE_ENC_NAME_BIT)
 #define file_set_enc_name(inode) set_file(inode, FADVISE_ENC_NAME_BIT)
 
-/* Encryption algorithms */
-#define F2FS_ENCRYPTION_MODE_INVALID		0
-#define F2FS_ENCRYPTION_MODE_AES_256_XTS	1
-#define F2FS_ENCRYPTION_MODE_AES_256_GCM	2
-#define F2FS_ENCRYPTION_MODE_AES_256_CBC	3
-#define F2FS_ENCRYPTION_MODE_AES_256_CTS	4
-
-#include "f2fs_crypto.h"
-
 #define DEF_DIR_LEVEL		0
 
 struct f2fs_inode_info {
@@ -442,13 +394,7 @@ struct f2fs_inode_info {
 	struct list_head dirty_list;	/* linked in global dirty list */
 	struct list_head inmem_pages;	/* inmemory pages managed by f2fs */
 	struct mutex inmem_lock;	/* lock for inmemory pages */
-
 	struct extent_tree *extent_tree;	/* cached extent_tree entry */
-
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-	/* Encryption params */
-	struct f2fs_crypt_info *i_crypt_info;
-#endif
 };
 
 static inline void get_extent_info(struct extent_info *ext,
@@ -515,6 +461,7 @@ struct f2fs_nm_info {
 	nid_t next_scan_nid;		/* the next nid to be scanned */
 	unsigned int ram_thresh;	/* control the memory footprint */
 	unsigned int ra_nid_pages;	/* # of nid pages to be readaheaded */
+	unsigned int dirty_nats_ratio;	/* control dirty nats ratio threshold */
 
 	/* NAT cache management */
 	struct radix_tree_root nat_root;/* root of the nat entry cache */
@@ -549,6 +496,8 @@ struct dnode_of_data {
 	unsigned int ofs_in_node;	/* data offset in the node page */
 	bool inode_page_locked;		/* inode page is locked or not */
 	bool node_changed;		/* is node block changed */
+	char cur_level;			/* level of hole node page */
+	char max_level;			/* level of current page located */
 	block_t	data_blkaddr;		/* block address of the node block */
 };
 
@@ -679,6 +628,7 @@ enum page_type {
 	META_FLUSH,
 	INMEM,		/* the below types are used by tracepoints only. */
 	INMEM_DROP,
+	INMEM_REVOKE,
 	IPU,
 	OPU,
 };
@@ -687,7 +637,8 @@ struct f2fs_io_info {
 	struct f2fs_sb_info *sbi;	/* f2fs_sb_info pointer */
 	enum page_type type;	/* contains DATA/NODE/META/META_FLUSH */
 	int rw;			/* contains R/RS/W/WS with REQ_META/REQ_PRIO */
-	block_t blk_addr;	/* block address to be written */
+	block_t new_blkaddr;	/* new block address to be written */
+	block_t old_blkaddr;	/* old block address before Cow */
 	struct page *page;	/* page to be written */
 	struct page *encrypted_page;	/* encrypted page */
 };
@@ -844,8 +795,22 @@ struct f2fs_sb_info {
 	struct list_head s_list;
 	struct mutex umount_mutex;
 	unsigned int shrinker_run_no;
+
+	/* For write statistics */
+	u64 sectors_written_start;
+	u64 kbytes_written;
+
+	/* Reference to checksum algorithm driver via cryptoapi */
+	struct crypto_shash *s_chksum_driver;
 };
 
+/* For write statistics. Suppose sector size is 512 bytes,
+ * and the return value is in kbytes. s is of struct f2fs_sb_info.
+ */
+#define BD_PART_WRITTEN(s)						 \
+(((u64)part_stat_read(s->sb->s_bdev->bd_part, sectors[1]) -		 \
+		s->sectors_written_start) >> 1)
+
 static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type)
 {
 	sbi->last_time[type] = jiffies;
@@ -874,6 +839,29 @@ static inline bool is_idle(struct f2fs_sb_info *sbi)
 /*
  * Inline functions
  */
+static inline u32 f2fs_crc32(struct f2fs_sb_info *sbi, const void *address,
+			   unsigned int length)
+{
+	SHASH_DESC_ON_STACK(shash, sbi->s_chksum_driver);
+	u32 *ctx = (u32 *)shash_desc_ctx(shash);
+	int err;
+
+	shash->tfm = sbi->s_chksum_driver;
+	shash->flags = 0;
+	*ctx = F2FS_SUPER_MAGIC;
+
+	err = crypto_shash_update(shash, address, length);
+	BUG_ON(err);
+
+	return *ctx;
+}
+
+static inline bool f2fs_crc_valid(struct f2fs_sb_info *sbi, __u32 blk_crc,
+				  void *buf, size_t buf_size)
+{
+	return f2fs_crc32(sbi, buf, buf_size) == blk_crc;
+}
+
 static inline struct f2fs_inode_info *F2FS_I(struct inode *inode)
 {
 	return container_of(inode, struct f2fs_inode_info, vfs_inode);
@@ -1006,7 +994,7 @@ static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
 
 static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
 {
-	f2fs_down_write(&sbi->cp_rwsem, &sbi->cp_mutex);
+	down_write(&sbi->cp_rwsem);
 }
 
 static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
@@ -1525,9 +1513,9 @@ static inline int f2fs_has_inline_xattr(struct inode *inode)
 	return is_inode_flag_set(F2FS_I(inode), FI_INLINE_XATTR);
 }
 
-static inline unsigned int addrs_per_inode(struct f2fs_inode_info *fi)
+static inline unsigned int addrs_per_inode(struct inode *inode)
 {
-	if (f2fs_has_inline_xattr(&fi->vfs_inode))
+	if (f2fs_has_inline_xattr(inode))
 		return DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS;
 	return DEF_ADDRS_PER_INODE;
 }
@@ -1681,10 +1669,10 @@ static inline void *f2fs_kvzalloc(size_t size, gfp_t flags)
 	 (F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
 
 /* get offset of first page in next direct node */
-#define PGOFS_OF_NEXT_DNODE(pgofs, fi)				\
+#define PGOFS_OF_NEXT_DNODE(pgofs, inode)				\
-	((pgofs < ADDRS_PER_INODE(fi)) ? ADDRS_PER_INODE(fi) :	\
+	((pgofs < ADDRS_PER_INODE(inode)) ? ADDRS_PER_INODE(inode) :	\
-	(pgofs - ADDRS_PER_INODE(fi) + ADDRS_PER_BLOCK) /	\
+	(pgofs - ADDRS_PER_INODE(inode) + ADDRS_PER_BLOCK) /	\
-	ADDRS_PER_BLOCK * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi))
+	ADDRS_PER_BLOCK * ADDRS_PER_BLOCK + ADDRS_PER_INODE(inode))
 
 /*
  * file.c
@@ -1723,10 +1711,10 @@ struct dentry *f2fs_get_parent(struct dentry *child);
 extern unsigned char f2fs_filetype_table[F2FS_FT_MAX];
 void set_de_type(struct f2fs_dir_entry *, umode_t);
 
-struct f2fs_dir_entry *find_target_dentry(struct f2fs_filename *,
+struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *,
 			f2fs_hash_t, int *, struct f2fs_dentry_ptr *);
 bool f2fs_fill_dentries(struct dir_context *, struct f2fs_dentry_ptr *,
-			unsigned int, struct f2fs_str *);
+			unsigned int, struct fscrypt_str *);
 void do_make_empty_dir(struct inode *, struct inode *,
 			struct f2fs_dentry_ptr *);
 struct page *init_inode_metadata(struct inode *, struct inode *,
@@ -1763,6 +1751,7 @@ int f2fs_commit_super(struct f2fs_sb_info *, bool);
 int f2fs_sync_fs(struct super_block *, int);
 extern __printf(3, 4)
 void f2fs_msg(struct super_block *, const char *, const char *, ...);
+int sanity_check_ckpt(struct f2fs_sb_info *sbi);
 
 /*
  * hash.c
@@ -1780,6 +1769,7 @@ int need_dentry_mark(struct f2fs_sb_info *, nid_t);
 bool is_checkpointed_node(struct f2fs_sb_info *, nid_t);
 bool need_inode_block_update(struct f2fs_sb_info *, nid_t);
 void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *);
+pgoff_t get_next_page_offset(struct dnode_of_data *, pgoff_t);
 int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int);
 int truncate_inode_blocks(struct inode *, pgoff_t);
 int truncate_xattr_node(struct inode *, struct page *);
@@ -1811,7 +1801,8 @@ void destroy_node_manager_caches(void);
  * segment.c
  */
 void register_inmem_page(struct inode *, struct page *);
-int commit_inmem_pages(struct inode *, bool);
+void drop_inmem_pages(struct inode *);
+int commit_inmem_pages(struct inode *);
 void f2fs_balance_fs(struct f2fs_sb_info *, bool);
 void f2fs_balance_fs_bg(struct f2fs_sb_info *);
 int f2fs_issue_flush(struct f2fs_sb_info *);
@@ -1832,16 +1823,17 @@ void write_meta_page(struct f2fs_sb_info *, struct page *);
 void write_node_page(unsigned int, struct f2fs_io_info *);
 void write_data_page(struct dnode_of_data *, struct f2fs_io_info *);
 void rewrite_data_page(struct f2fs_io_info *);
+void __f2fs_replace_block(struct f2fs_sb_info *, struct f2fs_summary *,
+					block_t, block_t, bool, bool);
 void f2fs_replace_block(struct f2fs_sb_info *, struct dnode_of_data *,
-				block_t, block_t, unsigned char, bool);
+				block_t, block_t, unsigned char, bool, bool);
 void allocate_data_block(struct f2fs_sb_info *, struct page *,
 		block_t, block_t *, struct f2fs_summary *, int);
-void f2fs_wait_on_page_writeback(struct page *, enum page_type);
+void f2fs_wait_on_page_writeback(struct page *, enum page_type, bool);
 void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *, block_t);
 void write_data_summaries(struct f2fs_sb_info *, block_t);
 void write_node_summaries(struct f2fs_sb_info *, block_t);
-int lookup_journal_in_cursum(struct f2fs_summary_block *,
+int lookup_journal_in_cursum(struct f2fs_journal *, int, unsigned int, int);
-					int, unsigned int, int);
 void flush_sit_entries(struct f2fs_sb_info *, struct cp_control *);
 int build_segment_manager(struct f2fs_sb_info *);
 void destroy_segment_manager(struct f2fs_sb_info *);
@@ -1881,11 +1873,16 @@ void destroy_checkpoint_caches(void);
  * data.c
  */
 void f2fs_submit_merged_bio(struct f2fs_sb_info *, enum page_type, int);
+void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *, struct inode *,
+				struct page *, nid_t, enum page_type, int);
+void f2fs_flush_merged_bios(struct f2fs_sb_info *);
 int f2fs_submit_page_bio(struct f2fs_io_info *);
 void f2fs_submit_page_mbio(struct f2fs_io_info *);
 void set_data_blkaddr(struct dnode_of_data *);
+void f2fs_update_data_blkaddr(struct dnode_of_data *, block_t);
 int reserve_new_block(struct dnode_of_data *);
 int f2fs_get_block(struct dnode_of_data *, pgoff_t);
+ssize_t f2fs_preallocate_blocks(struct kiocb *, struct iov_iter *);
 int f2fs_reserve_block(struct dnode_of_data *, pgoff_t);
 struct page *get_read_data_page(struct inode *, pgoff_t, int, bool);
 struct page *find_data_page(struct inode *, pgoff_t);
@@ -1902,7 +1899,7 @@ int f2fs_release_page(struct page *, gfp_t);
  */
 int start_gc_thread(struct f2fs_sb_info *);
 void stop_gc_thread(struct f2fs_sb_info *);
-block_t start_bidx_of_node(unsigned int, struct f2fs_inode_info *);
+block_t start_bidx_of_node(unsigned int, struct inode *);
 int f2fs_gc(struct f2fs_sb_info *, bool);
 void build_gc_manager(struct f2fs_sb_info *);
 
@@ -2093,7 +2090,7 @@ int f2fs_convert_inline_inode(struct inode *);
 int f2fs_write_inline_data(struct inode *, struct page *);
 bool recover_inline_data(struct inode *, struct page *);
 struct f2fs_dir_entry *find_in_inline_dir(struct inode *,
-				struct f2fs_filename *, struct page **);
+				struct fscrypt_name *, struct page **);
 struct f2fs_dir_entry *f2fs_parent_inline_dir(struct inode *, struct page **);
 int make_empty_inline_dir(struct inode *inode, struct inode *, struct page *);
 int f2fs_add_inline_entry(struct inode *, const struct qstr *, struct inode *,
@@ -2102,7 +2099,7 @@ void f2fs_delete_inline_entry(struct f2fs_dir_entry *, struct page *,
 						struct inode *, struct inode *);
 bool f2fs_empty_inline_dir(struct inode *);
 int f2fs_read_inline_dir(struct file *, struct dir_context *,
-						struct f2fs_str *);
+						struct fscrypt_str *);
 int f2fs_inline_data_fiemap(struct inode *,
 		struct fiemap_extent_info *, __u64, __u64);
 
@@ -2132,13 +2129,9 @@ void destroy_extent_cache(void);
 /*
  * crypto support
  */
-static inline int f2fs_encrypted_inode(struct inode *inode)
+static inline bool f2fs_encrypted_inode(struct inode *inode)
 {
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
 	return file_is_encrypt(inode);
-#else
-	return 0;
-#endif
 }
 
 static inline void f2fs_set_encrypted_inode(struct inode *inode)
@@ -2150,20 +2143,12 @@ static inline void f2fs_set_encrypted_inode(struct inode *inode)
 
 static inline bool f2fs_bio_encrypted(struct bio *bio)
 {
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
+	return bio->bi_private != NULL;
-	return unlikely(bio->bi_private != NULL);
-#else
-	return false;
-#endif
 }
 
 static inline int f2fs_sb_has_crypto(struct super_block *sb)
 {
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
 	return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_ENCRYPT);
-#else
-	return 0;
-#endif
 }
 
 static inline bool f2fs_may_encrypt(struct inode *inode)
@@ -2177,86 +2162,28 @@ static inline bool f2fs_may_encrypt(struct inode *inode)
 #endif
 }
 
-/* crypto_policy.c */
+#ifndef CONFIG_F2FS_FS_ENCRYPTION
-int f2fs_is_child_context_consistent_with_parent(struct inode *,
+#define fscrypt_set_d_op(i)
-							struct inode *);
+#define fscrypt_get_ctx			fscrypt_notsupp_get_ctx
-int f2fs_inherit_context(struct inode *, struct inode *, struct page *);
+#define fscrypt_release_ctx		fscrypt_notsupp_release_ctx
-int f2fs_process_policy(const struct f2fs_encryption_policy *, struct inode *);
+#define fscrypt_encrypt_page		fscrypt_notsupp_encrypt_page
-int f2fs_get_policy(struct inode *, struct f2fs_encryption_policy *);
+#define fscrypt_decrypt_page		fscrypt_notsupp_decrypt_page
-
+#define fscrypt_decrypt_bio_pages	fscrypt_notsupp_decrypt_bio_pages
-/* crypt.c */
+#define fscrypt_pullback_bio_page	fscrypt_notsupp_pullback_bio_page
-extern struct kmem_cache *f2fs_crypt_info_cachep;
+#define fscrypt_restore_control_page	fscrypt_notsupp_restore_control_page
-bool f2fs_valid_contents_enc_mode(uint32_t);
+#define fscrypt_zeroout_range		fscrypt_notsupp_zeroout_range
-uint32_t f2fs_validate_encryption_key_size(uint32_t, uint32_t);
+#define fscrypt_process_policy		fscrypt_notsupp_process_policy
-struct f2fs_crypto_ctx *f2fs_get_crypto_ctx(struct inode *);
+#define fscrypt_get_policy		fscrypt_notsupp_get_policy
-void f2fs_release_crypto_ctx(struct f2fs_crypto_ctx *);
+#define fscrypt_has_permitted_context	fscrypt_notsupp_has_permitted_context
-struct page *f2fs_encrypt(struct inode *, struct page *);
+#define fscrypt_inherit_context		fscrypt_notsupp_inherit_context
-int f2fs_decrypt(struct f2fs_crypto_ctx *, struct page *);
+#define fscrypt_get_encryption_info	fscrypt_notsupp_get_encryption_info
-int f2fs_decrypt_one(struct inode *, struct page *);
+#define fscrypt_put_encryption_info	fscrypt_notsupp_put_encryption_info
-void f2fs_end_io_crypto_work(struct f2fs_crypto_ctx *, struct bio *);
+#define fscrypt_setup_filename		fscrypt_notsupp_setup_filename
-
+#define fscrypt_free_filename		fscrypt_notsupp_free_filename
-/* crypto_key.c */
+#define fscrypt_fname_encrypted_size	fscrypt_notsupp_fname_encrypted_size
-void f2fs_free_encryption_info(struct inode *, struct f2fs_crypt_info *);
+#define fscrypt_fname_alloc_buffer	fscrypt_notsupp_fname_alloc_buffer
-int _f2fs_get_encryption_info(struct inode *inode);
+#define fscrypt_fname_free_buffer	fscrypt_notsupp_fname_free_buffer
-
+#define fscrypt_fname_disk_to_usr	fscrypt_notsupp_fname_disk_to_usr
-/* crypto_fname.c */
+#define fscrypt_fname_usr_to_disk	fscrypt_notsupp_fname_usr_to_disk
-bool f2fs_valid_filenames_enc_mode(uint32_t);
-u32 f2fs_fname_crypto_round_up(u32, u32);
-int f2fs_fname_crypto_alloc_buffer(struct inode *, u32, struct f2fs_str *);
-int f2fs_fname_disk_to_usr(struct inode *, f2fs_hash_t *,
-			const struct f2fs_str *, struct f2fs_str *);
-int f2fs_fname_usr_to_disk(struct inode *, const struct qstr *,
-			struct f2fs_str *);
-
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-void f2fs_restore_and_release_control_page(struct page **);
-void f2fs_restore_control_page(struct page *);
-
-int __init f2fs_init_crypto(void);
-int f2fs_crypto_initialize(void);
-void f2fs_exit_crypto(void);
-
-int f2fs_has_encryption_key(struct inode *);
-
-static inline int f2fs_get_encryption_info(struct inode *inode)
-{
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
-
-	if (!ci ||
-		(ci->ci_keyring_key &&
-		 (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
-					       (1 << KEY_FLAG_REVOKED) |
-					       (1 << KEY_FLAG_DEAD)))))
-		return _f2fs_get_encryption_info(inode);
-	return 0;
-}
-
-void f2fs_fname_crypto_free_buffer(struct f2fs_str *);
-int f2fs_fname_setup_filename(struct inode *, const struct qstr *,
-				int lookup, struct f2fs_filename *);
-void f2fs_fname_free_filename(struct f2fs_filename *);
-#else
-static inline void f2fs_restore_and_release_control_page(struct page **p) { }
-static inline void f2fs_restore_control_page(struct page *p) { }
-
-static inline int __init f2fs_init_crypto(void) { return 0; }
-static inline void f2fs_exit_crypto(void) { }
-
-static inline int f2fs_has_encryption_key(struct inode *i) { return 0; }
-static inline int f2fs_get_encryption_info(struct inode *i) { return 0; }
-static inline void f2fs_fname_crypto_free_buffer(struct f2fs_str *p) { }
-
-static inline int f2fs_fname_setup_filename(struct inode *dir,
-					const struct qstr *iname,
-					int lookup, struct f2fs_filename *fname)
-{
-	memset(fname, 0, sizeof(struct f2fs_filename));
-	fname->usr_fname = iname;
-	fname->disk_name.name = (unsigned char *)iname->name;
-	fname->disk_name.len = iname->len;
-	return 0;
-}
-
-static inline void f2fs_fname_free_filename(struct f2fs_filename *fname) { }
 #endif
 #endif

fs/f2fs/f2fs_crypto.h

@@ -1,151 +0,0 @@
-/*
- * linux/fs/f2fs/f2fs_crypto.h
- *
- * Copied from linux/fs/ext4/ext4_crypto.h
- *
- * Copyright (C) 2015, Google, Inc.
- *
- * This contains encryption header content for f2fs
- *
- * Written by Michael Halcrow, 2015.
- * Modified by Jaegeuk Kim, 2015.
- */
-#ifndef _F2FS_CRYPTO_H
-#define _F2FS_CRYPTO_H
-
-#include <linux/fs.h>
-
-#define F2FS_KEY_DESCRIPTOR_SIZE	8
-
-/* Policy provided via an ioctl on the topmost directory */
-struct f2fs_encryption_policy {
-	char version;
-	char contents_encryption_mode;
-	char filenames_encryption_mode;
-	char flags;
-	char master_key_descriptor[F2FS_KEY_DESCRIPTOR_SIZE];
-} __attribute__((__packed__));
-
-#define F2FS_ENCRYPTION_CONTEXT_FORMAT_V1	1
-#define F2FS_KEY_DERIVATION_NONCE_SIZE		16
-
-#define F2FS_POLICY_FLAGS_PAD_4		0x00
-#define F2FS_POLICY_FLAGS_PAD_8		0x01
-#define F2FS_POLICY_FLAGS_PAD_16	0x02
-#define F2FS_POLICY_FLAGS_PAD_32	0x03
-#define F2FS_POLICY_FLAGS_PAD_MASK	0x03
-#define F2FS_POLICY_FLAGS_VALID		0x03
-
-/**
- * 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 f2fs_encryption_context {
-	char format;
-	char contents_encryption_mode;
-	char filenames_encryption_mode;
-	char flags;
-	char master_key_descriptor[F2FS_KEY_DESCRIPTOR_SIZE];
-	char nonce[F2FS_KEY_DERIVATION_NONCE_SIZE];
-} __attribute__((__packed__));
-
-/* Encryption parameters */
-#define F2FS_XTS_TWEAK_SIZE 16
-#define F2FS_AES_128_ECB_KEY_SIZE 16
-#define F2FS_AES_256_GCM_KEY_SIZE 32
-#define F2FS_AES_256_CBC_KEY_SIZE 32
-#define F2FS_AES_256_CTS_KEY_SIZE 32
-#define F2FS_AES_256_XTS_KEY_SIZE 64
-#define F2FS_MAX_KEY_SIZE 64
-
-#define F2FS_KEY_DESC_PREFIX "f2fs:"
-#define F2FS_KEY_DESC_PREFIX_SIZE 5
-
-struct f2fs_encryption_key {
-	__u32 mode;
-	char raw[F2FS_MAX_KEY_SIZE];
-	__u32 size;
-} __attribute__((__packed__));
-
-struct f2fs_crypt_info {
-	char		ci_data_mode;
-	char		ci_filename_mode;
-	char		ci_flags;
-	struct crypto_skcipher *ci_ctfm;
-	struct key	*ci_keyring_key;
-	char		ci_master_key[F2FS_KEY_DESCRIPTOR_SIZE];
-};
-
-#define F2FS_CTX_REQUIRES_FREE_ENCRYPT_FL             0x00000001
-#define F2FS_WRITE_PATH_FL			      0x00000002
-
-struct f2fs_crypto_ctx {
-	union {
-		struct {
-			struct page *bounce_page;       /* Ciphertext page */
-			struct page *control_page;      /* Original page  */
-		} w;
-		struct {
-			struct bio *bio;
-			struct work_struct work;
-		} r;
-		struct list_head free_list;     /* Free list */
-	};
-	char flags;                      /* Flags */
-};
-
-struct f2fs_completion_result {
-	struct completion completion;
-	int res;
-};
-
-#define DECLARE_F2FS_COMPLETION_RESULT(ecr) \
-	struct f2fs_completion_result ecr = { \
-		COMPLETION_INITIALIZER((ecr).completion), 0 }
-
-static inline int f2fs_encryption_key_size(int mode)
-{
-	switch (mode) {
-	case F2FS_ENCRYPTION_MODE_AES_256_XTS:
-		return F2FS_AES_256_XTS_KEY_SIZE;
-	case F2FS_ENCRYPTION_MODE_AES_256_GCM:
-		return F2FS_AES_256_GCM_KEY_SIZE;
-	case F2FS_ENCRYPTION_MODE_AES_256_CBC:
-		return F2FS_AES_256_CBC_KEY_SIZE;
-	case F2FS_ENCRYPTION_MODE_AES_256_CTS:
-		return F2FS_AES_256_CTS_KEY_SIZE;
-	default:
-		BUG();
-	}
-	return 0;
-}
-
-#define F2FS_FNAME_NUM_SCATTER_ENTRIES	4
-#define F2FS_CRYPTO_BLOCK_SIZE		16
-#define F2FS_FNAME_CRYPTO_DIGEST_SIZE	32
-
-/**
- * For encrypted symlinks, the ciphertext length is stored at the beginning
- * of the string in little-endian format.
- */
-struct f2fs_encrypted_symlink_data {
-	__le16 len;
-	char encrypted_path[1];
-} __attribute__((__packed__));
-
-/**
- * This function is used to calculate the disk space required to
- * store a filename of length l in encrypted symlink format.
- */
-static inline u32 encrypted_symlink_data_len(u32 l)
-{
-	return (l + sizeof(struct f2fs_encrypted_symlink_data) - 1);
-}
-#endif	/* _F2FS_CRYPTO_H */

fs/f2fs/file.c

@@ -86,7 +86,7 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
 	trace_f2fs_vm_page_mkwrite(page, DATA);
 mapped:
 	/* fill the page */
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_wait_on_page_writeback(page, DATA, false);
 
 	/* wait for GCed encrypted page writeback */
 	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
@@ -301,7 +301,7 @@ static pgoff_t __get_first_dirty_index(struct address_space *mapping,
 	pagevec_init(&pvec, 0);
 	nr_pages = pagevec_lookup_tag(&pvec, mapping, &pgofs,
 					PAGECACHE_TAG_DIRTY, 1);
-	pgofs = nr_pages ? pvec.pages[0]->index : LONG_MAX;
+	pgofs = nr_pages ? pvec.pages[0]->index : ULONG_MAX;
 	pagevec_release(&pvec);
 	return pgofs;
 }
@@ -358,15 +358,14 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
 		} else if (err == -ENOENT) {
 			/* direct node does not exists */
 			if (whence == SEEK_DATA) {
-				pgofs = PGOFS_OF_NEXT_DNODE(pgofs,
+				pgofs = get_next_page_offset(&dn, pgofs);
-							F2FS_I(inode));
 				continue;
 			} else {
 				goto found;
 			}
 		}
 
-		end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+		end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
 
 		/* find data/hole in dnode block */
 		for (; dn.ofs_in_node < end_offset;
@@ -422,9 +421,11 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	int err;
 
 	if (f2fs_encrypted_inode(inode)) {
-		err = f2fs_get_encryption_info(inode);
+		err = fscrypt_get_encryption_info(inode);
 		if (err)
 			return 0;
+		if (!f2fs_encrypted_inode(inode))
+			return -ENOKEY;
 	}
 
 	/* we don't need to use inline_data strictly */
@@ -440,12 +441,18 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
 static int f2fs_file_open(struct inode *inode, struct file *filp)
 {
 	int ret = generic_file_open(inode, filp);
+	struct inode *dir = filp->f_path.dentry->d_parent->d_inode;
 
 	if (!ret && f2fs_encrypted_inode(inode)) {
-		ret = f2fs_get_encryption_info(inode);
+		ret = fscrypt_get_encryption_info(inode);
 		if (ret)
-			ret = -EACCES;
+			return -EACCES;
+		if (!fscrypt_has_encryption_key(inode))
+			return -ENOKEY;
 	}
+	if (f2fs_encrypted_inode(dir) &&
+			!fscrypt_has_permitted_context(dir, inode))
+		return -EPERM;
 	return ret;
 }
 
@@ -480,7 +487,7 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 		 * we will invalidate all blkaddr in the whole range.
 		 */
 		fofs = start_bidx_of_node(ofs_of_node(dn->node_page),
-						F2FS_I(dn->inode)) + ofs;
+							dn->inode) + ofs;
 		f2fs_update_extent_cache_range(dn, fofs, 0, len);
 		dec_valid_block_count(sbi, dn->inode, nr_free);
 		sync_inode_page(dn);
@@ -521,9 +528,10 @@ static int truncate_partial_data_page(struct inode *inode, u64 from,
 	if (IS_ERR(page))
 		return 0;
 truncate_out:
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_wait_on_page_writeback(page, DATA, true);
 	zero_user(page, offset, PAGE_CACHE_SIZE - offset);
-	if (!cache_only || !f2fs_encrypted_inode(inode) || !S_ISREG(inode->i_mode))
+	if (!cache_only || !f2fs_encrypted_inode(inode) ||
+					!S_ISREG(inode->i_mode))
 		set_page_dirty(page);
 	f2fs_put_page(page, 1);
 	return 0;
@@ -568,7 +576,7 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
 		goto out;
 	}
 
-	count = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+	count = ADDRS_PER_PAGE(dn.node_page, inode);
 
 	count -= dn.ofs_in_node;
 	f2fs_bug_on(sbi, count < 0);
@@ -671,7 +679,7 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 
 	if (attr->ia_valid & ATTR_SIZE) {
 		if (f2fs_encrypted_inode(inode) &&
-				f2fs_get_encryption_info(inode))
+				fscrypt_get_encryption_info(inode))
 			return -EACCES;
 
 		if (attr->ia_size <= i_size_read(inode)) {
@@ -743,7 +751,7 @@ static int fill_zero(struct inode *inode, pgoff_t index,
 	if (IS_ERR(page))
 		return PTR_ERR(page);
 
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_wait_on_page_writeback(page, DATA, true);
 	zero_user(page, start, len);
 	set_page_dirty(page);
 	f2fs_put_page(page, 1);
@@ -768,7 +776,7 @@ int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
 			return err;
 		}
 
-		end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+		end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
 		count = min(end_offset - dn.ofs_in_node, pg_end - pg_start);
 
 		f2fs_bug_on(F2FS_I_SB(inode), count == 0 || count > end_offset);
@@ -854,10 +862,8 @@ static int __exchange_data_block(struct inode *inode, pgoff_t src,
 	} else {
 		new_addr = dn.data_blkaddr;
 		if (!is_checkpointed_data(sbi, new_addr)) {
-			dn.data_blkaddr = NULL_ADDR;
 			/* do not invalidate this block address */
-			set_data_blkaddr(&dn);
+			f2fs_update_data_blkaddr(&dn, NULL_ADDR);
-			f2fs_update_extent_cache(&dn);
 			do_replace = true;
 		}
 		f2fs_put_dnode(&dn);
@@ -884,7 +890,7 @@ static int __exchange_data_block(struct inode *inode, pgoff_t src,
 
 		get_node_info(sbi, dn.nid, &ni);
 		f2fs_replace_block(sbi, &dn, dn.data_blkaddr, new_addr,
-				ni.version, true);
+				ni.version, true, false);
 		f2fs_put_dnode(&dn);
 	} else {
 		struct page *psrc, *pdst;
@@ -892,7 +898,7 @@ static int __exchange_data_block(struct inode *inode, pgoff_t src,
 		psrc = get_lock_data_page(inode, src, true);
 		if (IS_ERR(psrc))
 			return PTR_ERR(psrc);
-		pdst = get_new_data_page(inode, NULL, dst, false);
+		pdst = get_new_data_page(inode, NULL, dst, true);
 		if (IS_ERR(pdst)) {
 			f2fs_put_page(psrc, 1);
 			return PTR_ERR(pdst);
@@ -908,9 +914,7 @@ static int __exchange_data_block(struct inode *inode, pgoff_t src,
 
 err_out:
 	if (!get_dnode_of_data(&dn, src, LOOKUP_NODE)) {
-		dn.data_blkaddr = new_addr;
+		f2fs_update_data_blkaddr(&dn, new_addr);
-		set_data_blkaddr(&dn);
-		f2fs_update_extent_cache(&dn);
 		f2fs_put_dnode(&dn);
 	}
 	return ret;
@@ -1050,12 +1054,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 
 			if (dn.data_blkaddr != NEW_ADDR) {
 				invalidate_blocks(sbi, dn.data_blkaddr);
-
+				f2fs_update_data_blkaddr(&dn, NEW_ADDR);
-				dn.data_blkaddr = NEW_ADDR;
-				set_data_blkaddr(&dn);
-
-				dn.data_blkaddr = NULL_ADDR;
-				f2fs_update_extent_cache(&dn);
 			}
 			f2fs_put_dnode(&dn);
 			f2fs_unlock_op(sbi);
@@ -1253,7 +1252,7 @@ static int f2fs_release_file(struct inode *inode, struct file *filp)
 {
 	/* some remained atomic pages should discarded */
 	if (f2fs_is_atomic_file(inode))
-		commit_inmem_pages(inode, true);
+		drop_inmem_pages(inode);
 	if (f2fs_is_volatile_file(inode)) {
 		set_inode_flag(F2FS_I(inode), FI_DROP_CACHE);
 		filemap_fdatawrite(inode->i_mapping);
@@ -1377,7 +1376,7 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
 
 	if (f2fs_is_atomic_file(inode)) {
 		clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
-		ret = commit_inmem_pages(inode, false);
+		ret = commit_inmem_pages(inode);
 		if (ret) {
 			set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
 			goto err_out;
@@ -1440,7 +1439,7 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp)
 
 	if (f2fs_is_atomic_file(inode)) {
 		clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
-		commit_inmem_pages(inode, true);
+		drop_inmem_pages(inode);
 	}
 	if (f2fs_is_volatile_file(inode)) {
 		clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
@@ -1535,39 +1534,30 @@ static bool uuid_is_nonzero(__u8 u[16])
 
 static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg)
 {
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
+	struct fscrypt_policy policy;
-	struct f2fs_encryption_policy policy;
 	struct inode *inode = file_inode(filp);
 
-	if (copy_from_user(&policy, (struct f2fs_encryption_policy __user *)arg,
+	if (copy_from_user(&policy, (struct fscrypt_policy __user *)arg,
-				sizeof(policy)))
+							sizeof(policy)))
 		return -EFAULT;
 
 	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
-	return f2fs_process_policy(&policy, inode);
+	return fscrypt_process_policy(inode, &policy);
-#else
-	return -EOPNOTSUPP;
-#endif
 }
 
 static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg)
 {
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
+	struct fscrypt_policy policy;
-	struct f2fs_encryption_policy policy;
 	struct inode *inode = file_inode(filp);
 	int err;
 
-	err = f2fs_get_policy(inode, &policy);
+	err = fscrypt_get_policy(inode, &policy);
 	if (err)
 		return err;
 
-	if (copy_to_user((struct f2fs_encryption_policy __user *)arg, &policy,
+	if (copy_to_user((struct fscrypt_policy __user *)arg, &policy, sizeof(policy)))
-							sizeof(policy)))
 		return -EFAULT;
 	return 0;
-#else
-	return -EOPNOTSUPP;
-#endif
 }
 
 static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg)
@@ -1648,7 +1638,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
 					struct f2fs_defragment *range)
 {
 	struct inode *inode = file_inode(filp);
-	struct f2fs_map_blocks map;
+	struct f2fs_map_blocks map = { .m_next_pgofs = NULL };
 	struct extent_info ei;
 	pgoff_t pg_start, pg_end;
 	unsigned int blk_per_seg = sbi->blocks_per_seg;
@@ -1874,14 +1864,32 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 
 static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
-	struct inode *inode = file_inode(iocb->ki_filp);
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+	ssize_t ret;
 
 	if (f2fs_encrypted_inode(inode) &&
-				!f2fs_has_encryption_key(inode) &&
+				!fscrypt_has_encryption_key(inode) &&
-				f2fs_get_encryption_info(inode))
+				fscrypt_get_encryption_info(inode))
 		return -EACCES;
 
-	return generic_file_write_iter(iocb, from);
+	inode_lock(inode);
+	ret = generic_write_checks(iocb, from);
+	if (ret > 0) {
+		ret = f2fs_preallocate_blocks(iocb, from);
+		if (!ret)
+			ret = __generic_file_write_iter(iocb, from);
+	}
+	inode_unlock(inode);
+
+	if (ret > 0) {
+		ssize_t err;
+
+		err = generic_write_sync(file, iocb->ki_pos - ret, ret);
+		if (err < 0)
+			ret = err;
+	}
+	return ret;
 }
 
 #ifdef CONFIG_COMPAT

fs/f2fs/gc.c

@@ -245,6 +245,18 @@ static inline unsigned int get_gc_cost(struct f2fs_sb_info *sbi,
 		return get_cb_cost(sbi, segno);
 }
 
+static unsigned int count_bits(const unsigned long *addr,
+				unsigned int offset, unsigned int len)
+{
+	unsigned int end = offset + len, sum = 0;
+
+	while (offset < end) {
+		if (test_bit(offset++, addr))
+			++sum;
+	}
+	return sum;
+}
+
 /*
  * This function is called from two paths.
  * One is garbage collection and the other is SSR segment selection.
@@ -258,9 +270,9 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 {
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	struct victim_sel_policy p;
-	unsigned int secno, max_cost;
+	unsigned int secno, max_cost, last_victim;
 	unsigned int last_segment = MAIN_SEGS(sbi);
-	int nsearched = 0;
+	unsigned int nsearched = 0;
 
 	mutex_lock(&dirty_i->seglist_lock);
 
@@ -273,6 +285,7 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 	if (p.max_search == 0)
 		goto out;
 
+	last_victim = sbi->last_victim[p.gc_mode];
 	if (p.alloc_mode == LFS && gc_type == FG_GC) {
 		p.min_segno = check_bg_victims(sbi);
 		if (p.min_segno != NULL_SEGNO)
@@ -295,27 +308,35 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 		}
 
 		p.offset = segno + p.ofs_unit;
-		if (p.ofs_unit > 1)
+		if (p.ofs_unit > 1) {
 			p.offset -= segno % p.ofs_unit;
+			nsearched += count_bits(p.dirty_segmap,
+						p.offset - p.ofs_unit,
+						p.ofs_unit);
+		} else {
+			nsearched++;
+		}
+
 
 		secno = GET_SECNO(sbi, segno);
 
 		if (sec_usage_check(sbi, secno))
-			continue;
+			goto next;
 		if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap))
-			continue;
+			goto next;
 
 		cost = get_gc_cost(sbi, segno, &p);
 
 		if (p.min_cost > cost) {
 			p.min_segno = segno;
 			p.min_cost = cost;
-		} else if (unlikely(cost == max_cost)) {
-			continue;
 		}
-
+next:
-		if (nsearched++ >= p.max_search) {
+		if (nsearched >= p.max_search) {
-			sbi->last_victim[p.gc_mode] = segno;
+			if (!sbi->last_victim[p.gc_mode] && segno <= last_victim)
+				sbi->last_victim[p.gc_mode] = last_victim + 1;
+			else
+				sbi->last_victim[p.gc_mode] = segno + 1;
 			break;
 		}
 	}
@@ -399,7 +420,7 @@ static int check_valid_map(struct f2fs_sb_info *sbi,
  * On validity, copy that node with cold status, otherwise (invalid node)
  * ignore that.
  */
-static int gc_node_segment(struct f2fs_sb_info *sbi,
+static void gc_node_segment(struct f2fs_sb_info *sbi,
 		struct f2fs_summary *sum, unsigned int segno, int gc_type)
 {
 	bool initial = true;
@@ -419,7 +440,7 @@ next_step:
 
 		/* stop BG_GC if there is not enough free sections. */
 		if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0))
-			return 0;
+			return;
 
 		if (check_valid_map(sbi, segno, off) == 0)
 			continue;
@@ -446,7 +467,7 @@ next_step:
 
 		/* set page dirty and write it */
 		if (gc_type == FG_GC) {
-			f2fs_wait_on_page_writeback(node_page, NODE);
+			f2fs_wait_on_page_writeback(node_page, NODE, true);
 			set_page_dirty(node_page);
 		} else {
 			if (!PageWriteback(node_page))
@@ -460,20 +481,6 @@ next_step:
 		initial = false;
 		goto next_step;
 	}
-
-	if (gc_type == FG_GC) {
-		struct writeback_control wbc = {
-			.sync_mode = WB_SYNC_ALL,
-			.nr_to_write = LONG_MAX,
-			.for_reclaim = 0,
-		};
-		sync_node_pages(sbi, 0, &wbc);
-
-		/* return 1 only if FG_GC succefully reclaimed one */
-		if (get_valid_blocks(sbi, segno, 1) == 0)
-			return 1;
-	}
-	return 0;
 }
 
 /*
@@ -483,7 +490,7 @@ next_step:
  * as indirect or double indirect node blocks, are given, it must be a caller's
  * bug.
  */
-block_t start_bidx_of_node(unsigned int node_ofs, struct f2fs_inode_info *fi)
+block_t start_bidx_of_node(unsigned int node_ofs, struct inode *inode)
 {
 	unsigned int indirect_blks = 2 * NIDS_PER_BLOCK + 4;
 	unsigned int bidx;
@@ -500,7 +507,7 @@ block_t start_bidx_of_node(unsigned int node_ofs, struct f2fs_inode_info *fi)
 		int dec = (node_ofs - indirect_blks - 3) / (NIDS_PER_BLOCK + 1);
 		bidx = node_ofs - 5 - dec;
 	}
-	return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi);
+	return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE(inode);
 }
 
 static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
@@ -546,6 +553,7 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
 	struct f2fs_summary sum;
 	struct node_info ni;
 	struct page *page;
+	block_t newaddr;
 	int err;
 
 	/* do not read out */
@@ -567,21 +575,24 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
 	 * don't cache encrypted data into meta inode until previous dirty
 	 * data were writebacked to avoid racing between GC and flush.
 	 */
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_wait_on_page_writeback(page, DATA, true);
 
 	get_node_info(fio.sbi, dn.nid, &ni);
 	set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version);
 
 	/* read page */
 	fio.page = page;
-	fio.blk_addr = dn.data_blkaddr;
+	fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr;
 
-	fio.encrypted_page = pagecache_get_page(META_MAPPING(fio.sbi),
+	allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr,
-					fio.blk_addr,
+							&sum, CURSEG_COLD_DATA);
-					FGP_LOCK|FGP_CREAT,
+
-					GFP_NOFS);
+	fio.encrypted_page = pagecache_get_page(META_MAPPING(fio.sbi), newaddr,
-	if (!fio.encrypted_page)
+					FGP_LOCK | FGP_CREAT, GFP_NOFS);
-		goto put_out;
+	if (!fio.encrypted_page) {
+		err = -ENOMEM;
+		goto recover_block;
+	}
 
 	err = f2fs_submit_page_bio(&fio);
 	if (err)
@@ -590,33 +601,39 @@ static void move_encrypted_block(struct inode *inode, block_t bidx)
 	/* write page */
 	lock_page(fio.encrypted_page);
 
-	if (unlikely(!PageUptodate(fio.encrypted_page)))
+	if (unlikely(!PageUptodate(fio.encrypted_page))) {
+		err = -EIO;
 		goto put_page_out;
-	if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi)))
+	}
+	if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi))) {
+		err = -EIO;
 		goto put_page_out;
+	}
 
 	set_page_dirty(fio.encrypted_page);
-	f2fs_wait_on_page_writeback(fio.encrypted_page, DATA);
+	f2fs_wait_on_page_writeback(fio.encrypted_page, DATA, true);
 	if (clear_page_dirty_for_io(fio.encrypted_page))
 		dec_page_count(fio.sbi, F2FS_DIRTY_META);
 
 	set_page_writeback(fio.encrypted_page);
 
 	/* allocate block address */
-	f2fs_wait_on_page_writeback(dn.node_page, NODE);
+	f2fs_wait_on_page_writeback(dn.node_page, NODE, true);
-	allocate_data_block(fio.sbi, NULL, fio.blk_addr,
+
-					&fio.blk_addr, &sum, CURSEG_COLD_DATA);
 	fio.rw = WRITE_SYNC;
+	fio.new_blkaddr = newaddr;
 	f2fs_submit_page_mbio(&fio);
 
-	dn.data_blkaddr = fio.blk_addr;
+	f2fs_update_data_blkaddr(&dn, newaddr);
-	set_data_blkaddr(&dn);
-	f2fs_update_extent_cache(&dn);
 	set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
 	if (page->index == 0)
 		set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
 put_page_out:
 	f2fs_put_page(fio.encrypted_page, 1);
+recover_block:
+	if (err)
+		__f2fs_replace_block(fio.sbi, &sum, newaddr, fio.old_blkaddr,
+								true, true);
 put_out:
 	f2fs_put_dnode(&dn);
 out:
@@ -645,7 +662,7 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
 			.encrypted_page = NULL,
 		};
 		set_page_dirty(page);
-		f2fs_wait_on_page_writeback(page, DATA);
+		f2fs_wait_on_page_writeback(page, DATA, true);
 		if (clear_page_dirty_for_io(page))
 			inode_dec_dirty_pages(inode);
 		set_cold_data(page);
@@ -663,7 +680,7 @@ out:
  * If the parent node is not valid or the data block address is different,
  * the victim data block is ignored.
  */
-static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
+static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 		struct gc_inode_list *gc_list, unsigned int segno, int gc_type)
 {
 	struct super_block *sb = sbi->sb;
@@ -686,7 +703,7 @@ next_step:
 
 		/* stop BG_GC if there is not enough free sections. */
 		if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0))
-			return 0;
+			return;
 
 		if (check_valid_map(sbi, segno, off) == 0)
 			continue;
@@ -719,7 +736,7 @@ next_step:
 				continue;
 			}
 
-			start_bidx = start_bidx_of_node(nofs, F2FS_I(inode));
+			start_bidx = start_bidx_of_node(nofs, inode);
 			data_page = get_read_data_page(inode,
 					start_bidx + ofs_in_node, READA, true);
 			if (IS_ERR(data_page)) {
@@ -735,7 +752,7 @@ next_step:
 		/* phase 3 */
 		inode = find_gc_inode(gc_list, dni.ino);
 		if (inode) {
-			start_bidx = start_bidx_of_node(nofs, F2FS_I(inode))
+			start_bidx = start_bidx_of_node(nofs, inode)
 								+ ofs_in_node;
 			if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
 				move_encrypted_block(inode, start_bidx);
@@ -747,15 +764,6 @@ next_step:
 
 	if (++phase < 4)
 		goto next_step;
-
-	if (gc_type == FG_GC) {
-		f2fs_submit_merged_bio(sbi, DATA, WRITE);
-
-		/* return 1 only if FG_GC succefully reclaimed one */
-		if (get_valid_blocks(sbi, segno, 1) == 0)
-			return 1;
-	}
-	return 0;
 }
 
 static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
@@ -771,53 +779,92 @@ static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
 	return ret;
 }
 
-static int do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno,
+static int do_garbage_collect(struct f2fs_sb_info *sbi,
+				unsigned int start_segno,
 				struct gc_inode_list *gc_list, int gc_type)
 {
 	struct page *sum_page;
 	struct f2fs_summary_block *sum;
 	struct blk_plug plug;
-	int nfree = 0;
+	unsigned int segno = start_segno;
+	unsigned int end_segno = start_segno + sbi->segs_per_sec;
+	int seg_freed = 0;
+	unsigned char type = IS_DATASEG(get_seg_entry(sbi, segno)->type) ?
+						SUM_TYPE_DATA : SUM_TYPE_NODE;
 
-	/* read segment summary of victim */
+	/* readahead multi ssa blocks those have contiguous address */
-	sum_page = get_sum_page(sbi, segno);
+	if (sbi->segs_per_sec > 1)
+		ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno),
+					sbi->segs_per_sec, META_SSA, true);
+
+	/* reference all summary page */
+	while (segno < end_segno) {
+		sum_page = get_sum_page(sbi, segno++);
+		unlock_page(sum_page);
+	}
 
 	blk_start_plug(&plug);
 
-	sum = page_address(sum_page);
+	for (segno = start_segno; segno < end_segno; segno++) {
+		/* find segment summary of victim */
+		sum_page = find_get_page(META_MAPPING(sbi),
+					GET_SUM_BLOCK(sbi, segno));
+		f2fs_bug_on(sbi, !PageUptodate(sum_page));
+		f2fs_put_page(sum_page, 0);
 
-	/*
+		sum = page_address(sum_page);
-	 * this is to avoid deadlock:
+		f2fs_bug_on(sbi, type != GET_SUM_TYPE((&sum->footer)));
-	 * - lock_page(sum_page)         - f2fs_replace_block
-	 *  - check_valid_map()            - mutex_lock(sentry_lock)
-	 *   - mutex_lock(sentry_lock)     - change_curseg()
-	 *                                  - lock_page(sum_page)
-	 */
-	unlock_page(sum_page);
 
-	switch (GET_SUM_TYPE((&sum->footer))) {
+		/*
-	case SUM_TYPE_NODE:
+		 * this is to avoid deadlock:
-		nfree = gc_node_segment(sbi, sum->entries, segno, gc_type);
+		 * - lock_page(sum_page)         - f2fs_replace_block
-		break;
+		 *  - check_valid_map()            - mutex_lock(sentry_lock)
-	case SUM_TYPE_DATA:
+		 *   - mutex_lock(sentry_lock)     - change_curseg()
-		nfree = gc_data_segment(sbi, sum->entries, gc_list,
+		 *                                  - lock_page(sum_page)
-							segno, gc_type);
+		 */
-		break;
+
+		if (type == SUM_TYPE_NODE)
+			gc_node_segment(sbi, sum->entries, segno, gc_type);
+		else
+			gc_data_segment(sbi, sum->entries, gc_list, segno,
+								gc_type);
+
+		stat_inc_seg_count(sbi, type, gc_type);
+
+		f2fs_put_page(sum_page, 0);
 	}
+
+	if (gc_type == FG_GC) {
+		if (type == SUM_TYPE_NODE) {
+			struct writeback_control wbc = {
+				.sync_mode = WB_SYNC_ALL,
+				.nr_to_write = LONG_MAX,
+				.for_reclaim = 0,
+			};
+			sync_node_pages(sbi, 0, &wbc);
+		} else {
+			f2fs_submit_merged_bio(sbi, DATA, WRITE);
+		}
+	}
+
 	blk_finish_plug(&plug);
 
-	stat_inc_seg_count(sbi, GET_SUM_TYPE((&sum->footer)), gc_type);
+	if (gc_type == FG_GC) {
+		while (start_segno < end_segno)
+			if (get_valid_blocks(sbi, start_segno++, 1) == 0)
+				seg_freed++;
+	}
+
 	stat_inc_call_count(sbi->stat_info);
 
-	f2fs_put_page(sum_page, 0);
+	return seg_freed;
-	return nfree;
 }
 
 int f2fs_gc(struct f2fs_sb_info *sbi, bool sync)
 {
-	unsigned int segno, i;
+	unsigned int segno;
 	int gc_type = sync ? FG_GC : BG_GC;
-	int sec_freed = 0;
+	int sec_freed = 0, seg_freed;
 	int ret = -EINVAL;
 	struct cp_control cpc;
 	struct gc_inode_list gc_list = {
@@ -838,30 +885,24 @@ gc_more:
 
 	if (gc_type == BG_GC && has_not_enough_free_secs(sbi, sec_freed)) {
 		gc_type = FG_GC;
+		/*
+		 * If there is no victim and no prefree segment but still not
+		 * enough free sections, we should flush dent/node blocks and do
+		 * garbage collections.
+		 */
 		if (__get_victim(sbi, &segno, gc_type) || prefree_segments(sbi))
 			write_checkpoint(sbi, &cpc);
+		else if (has_not_enough_free_secs(sbi, 0))
+			write_checkpoint(sbi, &cpc);
 	}
 
 	if (segno == NULL_SEGNO && !__get_victim(sbi, &segno, gc_type))
 		goto stop;
 	ret = 0;
 
-	/* readahead multi ssa blocks those have contiguous address */
+	seg_freed = do_garbage_collect(sbi, segno, &gc_list, gc_type);
-	if (sbi->segs_per_sec > 1)
-		ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno), sbi->segs_per_sec,
-							META_SSA, true);
 
-	for (i = 0; i < sbi->segs_per_sec; i++) {
+	if (gc_type == FG_GC && seg_freed == sbi->segs_per_sec)
-		/*
-		 * for FG_GC case, halt gcing left segments once failed one
-		 * of segments in selected section to avoid long latency.
-		 */
-		if (!do_garbage_collect(sbi, segno + i, &gc_list, gc_type) &&
-				gc_type == FG_GC)
-			break;
-	}
-
-	if (i == sbi->segs_per_sec && gc_type == FG_GC)
 		sec_freed++;
 
 	if (gc_type == FG_GC)

fs/f2fs/inline.c

@@ -71,7 +71,7 @@ bool truncate_inline_inode(struct page *ipage, u64 from)
 
 	addr = inline_data_addr(ipage);
 
-	f2fs_wait_on_page_writeback(ipage, NODE);
+	f2fs_wait_on_page_writeback(ipage, NODE, true);
 	memset(addr + from, 0, MAX_INLINE_DATA - from);
 
 	return true;
@@ -105,7 +105,6 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page)
 
 int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 {
-	void *src_addr, *dst_addr;
 	struct f2fs_io_info fio = {
 		.sbi = F2FS_I_SB(dn->inode),
 		.type = DATA,
@@ -115,8 +114,6 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 	};
 	int dirty, err;
 
-	f2fs_bug_on(F2FS_I_SB(dn->inode), page->index);
-
 	if (!f2fs_exist_data(dn->inode))
 		goto clear_out;
 
@@ -124,21 +121,9 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 	if (err)
 		return err;
 
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_bug_on(F2FS_P_SB(page), PageWriteback(page));
 
-	if (PageUptodate(page))
+	read_inline_data(page, dn->inode_page);
-		goto no_update;
-
-	zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
-
-	/* Copy the whole inline data block */
-	src_addr = inline_data_addr(dn->inode_page);
-	dst_addr = kmap_atomic(page);
-	memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
-	flush_dcache_page(page);
-	kunmap_atomic(dst_addr);
-	SetPageUptodate(page);
-no_update:
 	set_page_dirty(page);
 
 	/* clear dirty state */
@@ -146,11 +131,9 @@ no_update:
 
 	/* write data page to try to make data consistent */
 	set_page_writeback(page);
-	fio.blk_addr = dn->data_blkaddr;
+	fio.old_blkaddr = dn->data_blkaddr;
 	write_data_page(dn, &fio);
-	set_data_blkaddr(dn);
+	f2fs_wait_on_page_writeback(page, DATA, true);
-	f2fs_update_extent_cache(dn);
-	f2fs_wait_on_page_writeback(page, DATA);
 	if (dirty)
 		inode_dec_dirty_pages(dn->inode);
 
@@ -159,6 +142,7 @@ no_update:
 
 	/* clear inline data and flag after data writeback */
 	truncate_inline_inode(dn->inode_page, 0);
+	clear_inline_node(dn->inode_page);
 clear_out:
 	stat_dec_inline_inode(dn->inode);
 	f2fs_clear_inline_inode(dn->inode);
@@ -223,7 +207,7 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page)
 
 	f2fs_bug_on(F2FS_I_SB(inode), page->index);
 
-	f2fs_wait_on_page_writeback(dn.inode_page, NODE);
+	f2fs_wait_on_page_writeback(dn.inode_page, NODE, true);
 	src_addr = kmap_atomic(page);
 	dst_addr = inline_data_addr(dn.inode_page);
 	memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
@@ -233,6 +217,7 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page)
 	set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
 
 	sync_inode_page(&dn);
+	clear_inline_node(dn.inode_page);
 	f2fs_put_dnode(&dn);
 	return 0;
 }
@@ -261,7 +246,7 @@ process_inline:
 		ipage = get_node_page(sbi, inode->i_ino);
 		f2fs_bug_on(sbi, IS_ERR(ipage));
 
-		f2fs_wait_on_page_writeback(ipage, NODE);
+		f2fs_wait_on_page_writeback(ipage, NODE, true);
 
 		src_addr = inline_data_addr(npage);
 		dst_addr = inline_data_addr(ipage);
@@ -292,7 +277,7 @@ process_inline:
 }
 
 struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
-			struct f2fs_filename *fname, struct page **res_page)
+			struct fscrypt_name *fname, struct page **res_page)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
 	struct f2fs_inline_dentry *inline_dentry;
@@ -389,7 +374,7 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
 	if (err)
 		goto out;
 
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_wait_on_page_writeback(page, DATA, true);
 	zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
 
 	dentry_blk = kmap_atomic(page);
@@ -469,7 +454,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name,
 		}
 	}
 
-	f2fs_wait_on_page_writeback(ipage, NODE);
+	f2fs_wait_on_page_writeback(ipage, NODE, true);
 
 	name_hash = f2fs_dentry_hash(name);
 	make_dentry_ptr(NULL, &d, (void *)dentry_blk, 2);
@@ -507,7 +492,7 @@ void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page,
 	int i;
 
 	lock_page(page);
-	f2fs_wait_on_page_writeback(page, NODE);
+	f2fs_wait_on_page_writeback(page, NODE, true);
 
 	inline_dentry = inline_data_addr(page);
 	bit_pos = dentry - inline_dentry->dentry;
@@ -550,7 +535,7 @@ bool f2fs_empty_inline_dir(struct inode *dir)
 }
 
 int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
-				struct f2fs_str *fstr)
+				struct fscrypt_str *fstr)
 {
 	struct inode *inode = file_inode(file);
 	struct f2fs_inline_dentry *inline_dentry = NULL;

fs/f2fs/inode.c

@@ -83,7 +83,7 @@ static void __recover_inline_status(struct inode *inode, struct page *ipage)
 
 	while (start < end) {
 		if (*start++) {
-			f2fs_wait_on_page_writeback(ipage, NODE);
+			f2fs_wait_on_page_writeback(ipage, NODE, true);
 
 			set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
 			set_raw_inline(F2FS_I(inode), F2FS_INODE(ipage));
@@ -227,7 +227,7 @@ int update_inode(struct inode *inode, struct page *node_page)
 {
 	struct f2fs_inode *ri;
 
-	f2fs_wait_on_page_writeback(node_page, NODE);
+	f2fs_wait_on_page_writeback(node_page, NODE, true);
 
 	ri = F2FS_INODE(node_page);
 
@@ -263,6 +263,10 @@ int update_inode(struct inode *inode, struct page *node_page)
 	set_cold_node(inode, node_page);
 	clear_inode_flag(F2FS_I(inode), FI_DIRTY_INODE);
 
+	/* deleted inode */
+	if (inode->i_nlink == 0)
+		clear_inline_node(node_page);
+
 	return set_page_dirty(node_page);
 }
 
@@ -320,7 +324,7 @@ void f2fs_evict_inode(struct inode *inode)
 
 	/* some remained atomic pages should discarded */
 	if (f2fs_is_atomic_file(inode))
-		commit_inmem_pages(inode, true);
+		drop_inmem_pages(inode);
 
 	trace_f2fs_evict_inode(inode);
 	truncate_inode_pages_final(&inode->i_data);
@@ -385,10 +389,7 @@ no_delete:
 		}
 	}
 out_clear:
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
+	fscrypt_put_encryption_info(inode, NULL);
-	if (fi->i_crypt_info)
-		f2fs_free_encryption_info(inode, fi->i_crypt_info);
-#endif
 	clear_inode(inode);
 }
 

fs/f2fs/namei.c

@@ -169,7 +169,7 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
 	int err;
 
 	if (f2fs_encrypted_inode(dir) &&
-		!f2fs_is_child_context_consistent_with_parent(dir, inode))
+			!fscrypt_has_permitted_context(dir, inode))
 		return -EPERM;
 
 	f2fs_balance_fs(sbi, true);
@@ -260,6 +260,22 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 	struct page *page;
 	nid_t ino;
 	int err = 0;
+	unsigned int root_ino = F2FS_ROOT_INO(F2FS_I_SB(dir));
+
+	if (f2fs_encrypted_inode(dir)) {
+		int res = fscrypt_get_encryption_info(dir);
+
+		/*
+		 * DCACHE_ENCRYPTED_WITH_KEY is set if the dentry is
+		 * created while the directory was encrypted and we
+		 * don't have access to the key.
+		 */
+		if (fscrypt_has_encryption_key(dir))
+			fscrypt_set_encrypted_dentry(dentry);
+		fscrypt_set_d_op(dentry);
+		if (res && res != -ENOKEY)
+			return ERR_PTR(res);
+	}
 
 	if (dentry->d_name.len > F2FS_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
@@ -276,15 +292,29 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
 
+	if ((dir->i_ino == root_ino) && f2fs_has_inline_dots(dir)) {
+		err = __recover_dot_dentries(dir, root_ino);
+		if (err)
+			goto err_out;
+	}
+
 	if (f2fs_has_inline_dots(inode)) {
 		err = __recover_dot_dentries(inode, dir->i_ino);
 		if (err)
 			goto err_out;
 	}
+	if (!IS_ERR(inode) && f2fs_encrypted_inode(dir) &&
+			(S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
+			!fscrypt_has_permitted_context(dir, inode)) {
+		bool nokey = f2fs_encrypted_inode(inode) &&
+			!fscrypt_has_encryption_key(inode);
+		err = nokey ? -ENOKEY : -EPERM;
+		goto err_out;
+	}
 	return d_splice_alias(inode, dentry);
 
 err_out:
-	iget_failed(inode);
+	iput(inode);
 	return ERR_PTR(err);
 }
 
@@ -345,13 +375,23 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
 	struct inode *inode;
 	size_t len = strlen(symname);
-	size_t p_len;
+	struct fscrypt_str disk_link = FSTR_INIT((char *)symname, len + 1);
-	char *p_str;
+	struct fscrypt_symlink_data *sd = NULL;
-	struct f2fs_str disk_link = FSTR_INIT(NULL, 0);
-	struct f2fs_encrypted_symlink_data *sd = NULL;
 	int err;
 
-	if (len > dir->i_sb->s_blocksize)
+	if (f2fs_encrypted_inode(dir)) {
+		err = fscrypt_get_encryption_info(dir);
+		if (err)
+			return err;
+
+		if (!fscrypt_has_encryption_key(dir))
+			return -EPERM;
+
+		disk_link.len = (fscrypt_fname_encrypted_size(dir, len) +
+				sizeof(struct fscrypt_symlink_data));
+	}
+
+	if (disk_link.len > dir->i_sb->s_blocksize)
 		return -ENAMETOOLONG;
 
 	inode = f2fs_new_inode(dir, S_IFLNK | S_IRWXUGO);
@@ -374,42 +414,36 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 	f2fs_unlock_op(sbi);
 	alloc_nid_done(sbi, inode->i_ino);
 
-	if (f2fs_encrypted_inode(dir)) {
+	if (f2fs_encrypted_inode(inode)) {
 		struct qstr istr = QSTR_INIT(symname, len);
+		struct fscrypt_str ostr;
 
-		err = f2fs_get_encryption_info(inode);
+		sd = kzalloc(disk_link.len, GFP_NOFS);
-		if (err)
-			goto err_out;
-
-		err = f2fs_fname_crypto_alloc_buffer(inode, len, &disk_link);
-		if (err)
-			goto err_out;
-
-		err = f2fs_fname_usr_to_disk(inode, &istr, &disk_link);
-		if (err < 0)
-			goto err_out;
-
-		p_len = encrypted_symlink_data_len(disk_link.len) + 1;
-
-		if (p_len > dir->i_sb->s_blocksize) {
-			err = -ENAMETOOLONG;
-			goto err_out;
-		}
-
-		sd = kzalloc(p_len, GFP_NOFS);
 		if (!sd) {
 			err = -ENOMEM;
 			goto err_out;
 		}
-		memcpy(sd->encrypted_path, disk_link.name, disk_link.len);
+
-		sd->len = cpu_to_le16(disk_link.len);
+		err = fscrypt_get_encryption_info(inode);
-		p_str = (char *)sd;
+		if (err)
-	} else {
+			goto err_out;
-		p_len = len + 1;
+
-		p_str = (char *)symname;
+		if (!fscrypt_has_encryption_key(inode)) {
+			err = -EPERM;
+			goto err_out;
+		}
+
+		ostr.name = sd->encrypted_path;
+		ostr.len = disk_link.len;
+		err = fscrypt_fname_usr_to_disk(inode, &istr, &ostr);
+		if (err < 0)
+			goto err_out;
+
+		sd->len = cpu_to_le16(ostr.len);
+		disk_link.name = (char *)sd;
 	}
 
-	err = page_symlink(inode, p_str, p_len);
+	err = page_symlink(inode, disk_link.name, disk_link.len);
 
 err_out:
 	d_instantiate(dentry, inode);
@@ -425,7 +459,8 @@ err_out:
 	 * performance regression.
 	 */
 	if (!err) {
-		filemap_write_and_wait_range(inode->i_mapping, 0, p_len - 1);
+		filemap_write_and_wait_range(inode->i_mapping, 0,
+							disk_link.len - 1);
 
 		if (IS_DIRSYNC(dir))
 			f2fs_sync_fs(sbi->sb, 1);
@@ -434,7 +469,6 @@ err_out:
 	}
 
 	kfree(sd);
-	f2fs_fname_crypto_free_buffer(&disk_link);
 	return err;
 out:
 	handle_failed_inode(inode);
@@ -582,7 +616,7 @@ out:
 static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 {
 	if (f2fs_encrypted_inode(dir)) {
-		int err = f2fs_get_encryption_info(dir);
+		int err = fscrypt_get_encryption_info(dir);
 		if (err)
 			return err;
 	}
@@ -608,11 +642,11 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct f2fs_dir_entry *old_dir_entry = NULL;
 	struct f2fs_dir_entry *old_entry;
 	struct f2fs_dir_entry *new_entry;
+	bool is_old_inline = f2fs_has_inline_dentry(old_dir);
 	int err = -ENOENT;
 
 	if ((old_dir != new_dir) && f2fs_encrypted_inode(new_dir) &&
-		!f2fs_is_child_context_consistent_with_parent(new_dir,
+			!fscrypt_has_permitted_context(new_dir, old_inode)) {
-							old_inode)) {
 		err = -EPERM;
 		goto out;
 	}
@@ -654,8 +688,9 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (err)
 			goto put_out_dir;
 
-		if (update_dent_inode(old_inode, new_inode,
+		err = update_dent_inode(old_inode, new_inode,
-						&new_dentry->d_name)) {
+						&new_dentry->d_name);
+		if (err) {
 			release_orphan_inode(sbi);
 			goto put_out_dir;
 		}
@@ -693,6 +728,26 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			inc_nlink(new_dir);
 			update_inode_page(new_dir);
 		}
+
+		/*
+		 * old entry and new entry can locate in the same inline
+		 * dentry in inode, when attaching new entry in inline dentry,
+		 * it could force inline dentry conversion, after that,
+		 * old_entry and old_page will point to wrong address, in
+		 * order to avoid this, let's do the check and update here.
+		 */
+		if (is_old_inline && !f2fs_has_inline_dentry(old_dir)) {
+			f2fs_put_page(old_page, 0);
+			old_page = NULL;
+
+			old_entry = f2fs_find_entry(old_dir,
+						&old_dentry->d_name, &old_page);
+			if (!old_entry) {
+				err = -EIO;
+				f2fs_unlock_op(sbi);
+				goto out_whiteout;
+			}
+		}
 	}
 
 	down_write(&F2FS_I(old_inode)->i_sem);
@@ -771,11 +826,9 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 	int err = -ENOENT;
 
 	if ((f2fs_encrypted_inode(old_dir) || f2fs_encrypted_inode(new_dir)) &&
-		(old_dir != new_dir) &&
+			(old_dir != new_dir) &&
-		(!f2fs_is_child_context_consistent_with_parent(new_dir,
+			(!fscrypt_has_permitted_context(new_dir, old_inode) ||
-								old_inode) ||
+			 !fscrypt_has_permitted_context(old_dir, new_inode)))
-		!f2fs_is_child_context_consistent_with_parent(old_dir,
-								new_inode)))
 		return -EPERM;
 
 	old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
@@ -937,16 +990,15 @@ static int f2fs_rename2(struct inode *old_dir, struct dentry *old_dentry,
 	return f2fs_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
 }
 
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
 static const char *f2fs_encrypted_get_link(struct dentry *dentry,
 					   struct inode *inode,
 					   struct delayed_call *done)
 {
 	struct page *cpage = NULL;
 	char *caddr, *paddr = NULL;
-	struct f2fs_str cstr = FSTR_INIT(NULL, 0);
+	struct fscrypt_str cstr = FSTR_INIT(NULL, 0);
-	struct f2fs_str pstr = FSTR_INIT(NULL, 0);
+	struct fscrypt_str pstr = FSTR_INIT(NULL, 0);
-	struct f2fs_encrypted_symlink_data *sd;
+	struct fscrypt_symlink_data *sd;
 	loff_t size = min_t(loff_t, i_size_read(inode), PAGE_SIZE - 1);
 	u32 max_size = inode->i_sb->s_blocksize;
 	int res;
@@ -954,7 +1006,7 @@ static const char *f2fs_encrypted_get_link(struct dentry *dentry,
 	if (!dentry)
 		return ERR_PTR(-ECHILD);
 
-	res = f2fs_get_encryption_info(inode);
+	res = fscrypt_get_encryption_info(inode);
 	if (res)
 		return ERR_PTR(res);
 
@@ -965,7 +1017,8 @@ static const char *f2fs_encrypted_get_link(struct dentry *dentry,
 	caddr[size] = 0;
 
 	/* Symlink is encrypted */
-	sd = (struct f2fs_encrypted_symlink_data *)caddr;
+	sd = (struct fscrypt_symlink_data *)caddr;
+	cstr.name = sd->encrypted_path;
 	cstr.len = le16_to_cpu(sd->len);
 
 	/* this is broken symlink case */
@@ -973,12 +1026,6 @@ static const char *f2fs_encrypted_get_link(struct dentry *dentry,
 		res = -ENOENT;
 		goto errout;
 	}
-	cstr.name = kmalloc(cstr.len, GFP_NOFS);
-	if (!cstr.name) {
-		res = -ENOMEM;
-		goto errout;
-	}
-	memcpy(cstr.name, sd->encrypted_path, cstr.len);
 
 	/* this is broken symlink case */
 	if (unlikely(cstr.name[0] == 0)) {
@@ -986,22 +1033,19 @@ static const char *f2fs_encrypted_get_link(struct dentry *dentry,
 		goto errout;
 	}
 
-	if ((cstr.len + sizeof(struct f2fs_encrypted_symlink_data) - 1) >
+	if ((cstr.len + sizeof(struct fscrypt_symlink_data) - 1) > max_size) {
-								max_size) {
 		/* Symlink data on the disk is corrupted */
 		res = -EIO;
 		goto errout;
 	}
-	res = f2fs_fname_crypto_alloc_buffer(inode, cstr.len, &pstr);
+	res = fscrypt_fname_alloc_buffer(inode, cstr.len, &pstr);
 	if (res)
 		goto errout;
 
-	res = f2fs_fname_disk_to_usr(inode, NULL, &cstr, &pstr);
+	res = fscrypt_fname_disk_to_usr(inode, 0, 0, &cstr, &pstr);
 	if (res < 0)
 		goto errout;
 
-	kfree(cstr.name);
-
 	paddr = pstr.name;
 
 	/* Null-terminate the name */
@@ -1011,8 +1055,7 @@ static const char *f2fs_encrypted_get_link(struct dentry *dentry,
 	set_delayed_call(done, kfree_link, paddr);
 	return paddr;
 errout:
-	kfree(cstr.name);
+	fscrypt_fname_free_buffer(&pstr);
-	f2fs_fname_crypto_free_buffer(&pstr);
 	page_cache_release(cpage);
 	return ERR_PTR(res);
 }
@@ -1029,7 +1072,6 @@ const struct inode_operations f2fs_encrypted_symlink_inode_operations = {
 	.removexattr	= generic_removexattr,
 #endif
 };
-#endif
 
 const struct inode_operations f2fs_dir_inode_operations = {
 	.create		= f2fs_create,

fs/f2fs/node.c

@@ -257,15 +257,20 @@ static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid)
 	return new;
 }
 
-static void cache_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid,
+static void cache_nat_entry(struct f2fs_sb_info *sbi, nid_t nid,
 						struct f2fs_nat_entry *ne)
 {
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct nat_entry *e;
 
 	e = __lookup_nat_cache(nm_i, nid);
 	if (!e) {
 		e = grab_nat_entry(nm_i, nid);
 		node_info_from_raw_nat(&e->ni, ne);
+	} else {
+		f2fs_bug_on(sbi, nat_get_ino(e) != ne->ino ||
+				nat_get_blkaddr(e) != ne->block_addr ||
+				nat_get_version(e) != ne->version);
 	}
 }
 
@@ -354,7 +359,7 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
-	struct f2fs_summary_block *sum = curseg->sum_blk;
+	struct f2fs_journal *journal = curseg->journal;
 	nid_t start_nid = START_NID(nid);
 	struct f2fs_nat_block *nat_blk;
 	struct page *page = NULL;
@@ -371,23 +376,20 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
 		ni->ino = nat_get_ino(e);
 		ni->blk_addr = nat_get_blkaddr(e);
 		ni->version = nat_get_version(e);
-	}
+		up_read(&nm_i->nat_tree_lock);
-	up_read(&nm_i->nat_tree_lock);
-	if (e)
 		return;
+	}
 
 	memset(&ne, 0, sizeof(struct f2fs_nat_entry));
 
-	down_write(&nm_i->nat_tree_lock);
-
 	/* Check current segment summary */
-	mutex_lock(&curseg->curseg_mutex);
+	down_read(&curseg->journal_rwsem);
-	i = lookup_journal_in_cursum(sum, NAT_JOURNAL, nid, 0);
+	i = lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 0);
 	if (i >= 0) {
-		ne = nat_in_journal(sum, i);
+		ne = nat_in_journal(journal, i);
 		node_info_from_raw_nat(ni, &ne);
 	}
-	mutex_unlock(&curseg->curseg_mutex);
+	up_read(&curseg->journal_rwsem);
 	if (i >= 0)
 		goto cache;
 
@@ -398,19 +400,52 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
 	node_info_from_raw_nat(ni, &ne);
 	f2fs_put_page(page, 1);
 cache:
+	up_read(&nm_i->nat_tree_lock);
 	/* cache nat entry */
-	cache_nat_entry(NM_I(sbi), nid, &ne);
+	down_write(&nm_i->nat_tree_lock);
+	cache_nat_entry(sbi, nid, &ne);
 	up_write(&nm_i->nat_tree_lock);
 }
 
+pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs)
+{
+	const long direct_index = ADDRS_PER_INODE(dn->inode);
+	const long direct_blks = ADDRS_PER_BLOCK;
+	const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK;
+	unsigned int skipped_unit = ADDRS_PER_BLOCK;
+	int cur_level = dn->cur_level;
+	int max_level = dn->max_level;
+	pgoff_t base = 0;
+
+	if (!dn->max_level)
+		return pgofs + 1;
+
+	while (max_level-- > cur_level)
+		skipped_unit *= NIDS_PER_BLOCK;
+
+	switch (dn->max_level) {
+	case 3:
+		base += 2 * indirect_blks;
+	case 2:
+		base += 2 * direct_blks;
+	case 1:
+		base += direct_index;
+		break;
+	default:
+		f2fs_bug_on(F2FS_I_SB(dn->inode), 1);
+	}
+
+	return ((pgofs - base) / skipped_unit + 1) * skipped_unit + base;
+}
+
 /*
  * The maximum depth is four.
  * Offset[0] will have raw inode offset.
  */
-static int get_node_path(struct f2fs_inode_info *fi, long block,
+static int get_node_path(struct inode *inode, long block,
 				int offset[4], unsigned int noffset[4])
 {
-	const long direct_index = ADDRS_PER_INODE(fi);
+	const long direct_index = ADDRS_PER_INODE(inode);
 	const long direct_blks = ADDRS_PER_BLOCK;
 	const long dptrs_per_blk = NIDS_PER_BLOCK;
 	const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK;
@@ -495,10 +530,10 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
 	int offset[4];
 	unsigned int noffset[4];
 	nid_t nids[4];
-	int level, i;
+	int level, i = 0;
 	int err = 0;
 
-	level = get_node_path(F2FS_I(dn->inode), index, offset, noffset);
+	level = get_node_path(dn->inode, index, offset, noffset);
 
 	nids[0] = dn->inode->i_ino;
 	npage[0] = dn->inode_page;
@@ -585,6 +620,10 @@ release_pages:
 release_out:
 	dn->inode_page = NULL;
 	dn->node_page = NULL;
+	if (err == -ENOENT) {
+		dn->cur_level = i;
+		dn->max_level = level;
+	}
 	return err;
 }
 
@@ -792,7 +831,7 @@ int truncate_inode_blocks(struct inode *inode, pgoff_t from)
 
 	trace_f2fs_truncate_inode_blocks_enter(inode, from);
 
-	level = get_node_path(F2FS_I(inode), from, offset, noffset);
+	level = get_node_path(inode, from, offset, noffset);
 restart:
 	page = get_node_page(sbi, inode->i_ino);
 	if (IS_ERR(page)) {
@@ -861,7 +900,7 @@ skip_partial:
 				f2fs_put_page(page, 1);
 				goto restart;
 			}
-			f2fs_wait_on_page_writeback(page, NODE);
+			f2fs_wait_on_page_writeback(page, NODE, true);
 			ri->i_nid[offset[0] - NODE_DIR1_BLOCK] = 0;
 			set_page_dirty(page);
 			unlock_page(page);
@@ -976,7 +1015,7 @@ struct page *new_node_page(struct dnode_of_data *dn,
 	new_ni.ino = dn->inode->i_ino;
 	set_node_addr(sbi, &new_ni, NEW_ADDR, false);
 
-	f2fs_wait_on_page_writeback(page, NODE);
+	f2fs_wait_on_page_writeback(page, NODE, true);
 	fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true);
 	set_cold_node(dn->inode, page);
 	SetPageUptodate(page);
@@ -1029,7 +1068,7 @@ static int read_node_page(struct page *page, int rw)
 	if (PageUptodate(page))
 		return LOCKED_PAGE;
 
-	fio.blk_addr = ni.blk_addr;
+	fio.new_blkaddr = fio.old_blkaddr = ni.blk_addr;
 	return f2fs_submit_page_bio(&fio);
 }
 
@@ -1045,12 +1084,11 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
 		return;
 	f2fs_bug_on(sbi, check_nid_range(sbi, nid));
 
-	apage = find_get_page(NODE_MAPPING(sbi), nid);
+	rcu_read_lock();
-	if (apage && PageUptodate(apage)) {
+	apage = radix_tree_lookup(&NODE_MAPPING(sbi)->page_tree, nid);
-		f2fs_put_page(apage, 0);
+	rcu_read_unlock();
+	if (apage)
 		return;
-	}
-	f2fs_put_page(apage, 0);
 
 	apage = grab_cache_page(NODE_MAPPING(sbi), nid);
 	if (!apage)
@@ -1063,7 +1101,7 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
 /*
  * readahead MAX_RA_NODE number of node pages.
  */
-void ra_node_pages(struct page *parent, int start)
+static void ra_node_pages(struct page *parent, int start)
 {
 	struct f2fs_sb_info *sbi = F2FS_P_SB(parent);
 	struct blk_plug plug;
@@ -1083,7 +1121,7 @@ void ra_node_pages(struct page *parent, int start)
 	blk_finish_plug(&plug);
 }
 
-struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
+static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
 					struct page *parent, int start)
 {
 	struct page *page;
@@ -1154,19 +1192,57 @@ void sync_inode_page(struct dnode_of_data *dn)
 	dn->node_changed = ret ? true: false;
 }
 
+static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
+{
+	struct inode *inode;
+	struct page *page;
+
+	/* should flush inline_data before evict_inode */
+	inode = ilookup(sbi->sb, ino);
+	if (!inode)
+		return;
+
+	page = pagecache_get_page(inode->i_mapping, 0, FGP_NOWAIT, 0);
+	if (!page)
+		goto iput_out;
+
+	if (!trylock_page(page))
+		goto release_out;
+
+	if (!PageUptodate(page))
+		goto page_out;
+
+	if (!PageDirty(page))
+		goto page_out;
+
+	if (!clear_page_dirty_for_io(page))
+		goto page_out;
+
+	if (!f2fs_write_inline_data(inode, page))
+		inode_dec_dirty_pages(inode);
+	else
+		set_page_dirty(page);
+page_out:
+	unlock_page(page);
+release_out:
+	f2fs_put_page(page, 0);
+iput_out:
+	iput(inode);
+}
+
 int sync_node_pages(struct f2fs_sb_info *sbi, nid_t ino,
 					struct writeback_control *wbc)
 {
 	pgoff_t index, end;
 	struct pagevec pvec;
 	int step = ino ? 2 : 0;
-	int nwritten = 0, wrote = 0;
+	int nwritten = 0;
 
 	pagevec_init(&pvec, 0);
 
 next_step:
 	index = 0;
-	end = LONG_MAX;
+	end = ULONG_MAX;
 
 	while (index <= end) {
 		int i, nr_pages;
@@ -1203,6 +1279,7 @@ next_step:
 			 * If an fsync mode,
 			 * we should not skip writing node pages.
 			 */
+lock_node:
 			if (ino && ino_of_node(page) == ino)
 				lock_page(page);
 			else if (!trylock_page(page))
@@ -1221,6 +1298,17 @@ continue_unlock:
 				goto continue_unlock;
 			}
 
+			/* flush inline_data */
+			if (!ino && is_inline_node(page)) {
+				clear_inline_node(page);
+				unlock_page(page);
+				flush_inline_data(sbi, ino_of_node(page));
+				goto lock_node;
+			}
+
+			f2fs_wait_on_page_writeback(page, NODE, true);
+
+			BUG_ON(PageWriteback(page));
 			if (!clear_page_dirty_for_io(page))
 				goto continue_unlock;
 
@@ -1238,8 +1326,6 @@ continue_unlock:
 
 			if (NODE_MAPPING(sbi)->a_ops->writepage(page, wbc))
 				unlock_page(page);
-			else
-				wrote++;
 
 			if (--wbc->nr_to_write == 0)
 				break;
@@ -1257,15 +1343,12 @@ continue_unlock:
 		step++;
 		goto next_step;
 	}
-
-	if (wrote)
-		f2fs_submit_merged_bio(sbi, NODE, WRITE);
 	return nwritten;
 }
 
 int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino)
 {
-	pgoff_t index = 0, end = LONG_MAX;
+	pgoff_t index = 0, end = ULONG_MAX;
 	struct pagevec pvec;
 	int ret2 = 0, ret = 0;
 
@@ -1287,7 +1370,7 @@ int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino)
 				continue;
 
 			if (ino && ino_of_node(page) == ino) {
-				f2fs_wait_on_page_writeback(page, NODE);
+				f2fs_wait_on_page_writeback(page, NODE, true);
 				if (TestClearPageError(page))
 					ret = -EIO;
 			}
@@ -1326,8 +1409,6 @@ static int f2fs_write_node_page(struct page *page,
 	if (unlikely(f2fs_cp_error(sbi)))
 		goto redirty_out;
 
-	f2fs_wait_on_page_writeback(page, NODE);
-
 	/* get old block addr of this node page */
 	nid = nid_of_node(page);
 	f2fs_bug_on(sbi, page->index != nid);
@@ -1351,14 +1432,18 @@ static int f2fs_write_node_page(struct page *page,
 	}
 
 	set_page_writeback(page);
-	fio.blk_addr = ni.blk_addr;
+	fio.old_blkaddr = ni.blk_addr;
 	write_node_page(nid, &fio);
-	set_node_addr(sbi, &ni, fio.blk_addr, is_fsync_dnode(page));
+	set_node_addr(sbi, &ni, fio.new_blkaddr, is_fsync_dnode(page));
 	dec_page_count(sbi, F2FS_DIRTY_NODES);
 	up_read(&sbi->node_write);
+
+	if (wbc->for_reclaim)
+		f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, NODE, WRITE);
+
 	unlock_page(page);
 
-	if (wbc->for_reclaim || unlikely(f2fs_cp_error(sbi)))
+	if (unlikely(f2fs_cp_error(sbi)))
 		f2fs_submit_merged_bio(sbi, NODE, WRITE);
 
 	return 0;
@@ -1374,8 +1459,6 @@ static int f2fs_write_node_pages(struct address_space *mapping,
 	struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
 	long diff;
 
-	trace_f2fs_writepages(mapping->host, wbc, NODE);
-
 	/* balancing f2fs's metadata in background */
 	f2fs_balance_fs_bg(sbi);
 
@@ -1383,6 +1466,8 @@ static int f2fs_write_node_pages(struct address_space *mapping,
 	if (get_pages(sbi, F2FS_DIRTY_NODES) < nr_pages_to_skip(sbi, NODE))
 		goto skip_write;
 
+	trace_f2fs_writepages(mapping->host, wbc, NODE);
+
 	diff = nr_pages_to_write(sbi, NODE, wbc);
 	wbc->sync_mode = WB_SYNC_NONE;
 	sync_node_pages(sbi, 0, wbc);
@@ -1391,6 +1476,7 @@ static int f2fs_write_node_pages(struct address_space *mapping,
 
 skip_write:
 	wbc->pages_skipped += get_pages(sbi, F2FS_DIRTY_NODES);
+	trace_f2fs_writepages(mapping->host, wbc, NODE);
 	return 0;
 }
 
@@ -1526,7 +1612,7 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
-	struct f2fs_summary_block *sum = curseg->sum_blk;
+	struct f2fs_journal *journal = curseg->journal;
 	int i = 0;
 	nid_t nid = nm_i->next_scan_nid;
 
@@ -1558,16 +1644,18 @@ static void build_free_nids(struct f2fs_sb_info *sbi)
 	nm_i->next_scan_nid = nid;
 
 	/* find free nids from current sum_pages */
-	mutex_lock(&curseg->curseg_mutex);
+	down_read(&curseg->journal_rwsem);
-	for (i = 0; i < nats_in_cursum(sum); i++) {
+	for (i = 0; i < nats_in_cursum(journal); i++) {
-		block_t addr = le32_to_cpu(nat_in_journal(sum, i).block_addr);
+		block_t addr;
-		nid = le32_to_cpu(nid_in_journal(sum, i));
+
+		addr = le32_to_cpu(nat_in_journal(journal, i).block_addr);
+		nid = le32_to_cpu(nid_in_journal(journal, i));
 		if (addr == NULL_ADDR)
 			add_free_nid(sbi, nid, true);
 		else
 			remove_free_nid(nm_i, nid);
 	}
-	mutex_unlock(&curseg->curseg_mutex);
+	up_read(&curseg->journal_rwsem);
 	up_read(&nm_i->nat_tree_lock);
 
 	ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid),
@@ -1703,7 +1791,7 @@ void recover_inline_xattr(struct inode *inode, struct page *page)
 	src_addr = inline_xattr_addr(page);
 	inline_size = inline_xattr_size(inode);
 
-	f2fs_wait_on_page_writeback(ipage, NODE);
+	f2fs_wait_on_page_writeback(ipage, NODE, true);
 	memcpy(dst_addr, src_addr, inline_size);
 update_inode:
 	update_inode(inode, ipage);
@@ -1831,16 +1919,16 @@ static void remove_nats_in_journal(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
-	struct f2fs_summary_block *sum = curseg->sum_blk;
+	struct f2fs_journal *journal = curseg->journal;
 	int i;
 
-	mutex_lock(&curseg->curseg_mutex);
+	down_write(&curseg->journal_rwsem);
-	for (i = 0; i < nats_in_cursum(sum); i++) {
+	for (i = 0; i < nats_in_cursum(journal); i++) {
 		struct nat_entry *ne;
 		struct f2fs_nat_entry raw_ne;
-		nid_t nid = le32_to_cpu(nid_in_journal(sum, i));
+		nid_t nid = le32_to_cpu(nid_in_journal(journal, i));
 
-		raw_ne = nat_in_journal(sum, i);
+		raw_ne = nat_in_journal(journal, i);
 
 		ne = __lookup_nat_cache(nm_i, nid);
 		if (!ne) {
@@ -1849,8 +1937,8 @@ static void remove_nats_in_journal(struct f2fs_sb_info *sbi)
 		}
 		__set_nat_cache_dirty(nm_i, ne);
 	}
-	update_nats_in_cursum(sum, -i);
+	update_nats_in_cursum(journal, -i);
-	mutex_unlock(&curseg->curseg_mutex);
+	up_write(&curseg->journal_rwsem);
 }
 
 static void __adjust_nat_entry_set(struct nat_entry_set *nes,
@@ -1875,7 +1963,7 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
 					struct nat_entry_set *set)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
-	struct f2fs_summary_block *sum = curseg->sum_blk;
+	struct f2fs_journal *journal = curseg->journal;
 	nid_t start_nid = set->set * NAT_ENTRY_PER_BLOCK;
 	bool to_journal = true;
 	struct f2fs_nat_block *nat_blk;
@@ -1887,11 +1975,11 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
 	 * #1, flush nat entries to journal in current hot data summary block.
 	 * #2, flush nat entries to nat page.
 	 */
-	if (!__has_cursum_space(sum, set->entry_cnt, NAT_JOURNAL))
+	if (!__has_cursum_space(journal, set->entry_cnt, NAT_JOURNAL))
 		to_journal = false;
 
 	if (to_journal) {
-		mutex_lock(&curseg->curseg_mutex);
+		down_write(&curseg->journal_rwsem);
 	} else {
 		page = get_next_nat_page(sbi, start_nid);
 		nat_blk = page_address(page);
@@ -1908,11 +1996,11 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
 			continue;
 
 		if (to_journal) {
-			offset = lookup_journal_in_cursum(sum,
+			offset = lookup_journal_in_cursum(journal,
 							NAT_JOURNAL, nid, 1);
 			f2fs_bug_on(sbi, offset < 0);
-			raw_ne = &nat_in_journal(sum, offset);
+			raw_ne = &nat_in_journal(journal, offset);
-			nid_in_journal(sum, offset) = cpu_to_le32(nid);
+			nid_in_journal(journal, offset) = cpu_to_le32(nid);
 		} else {
 			raw_ne = &nat_blk->entries[nid - start_nid];
 		}
@@ -1924,7 +2012,7 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
 	}
 
 	if (to_journal)
-		mutex_unlock(&curseg->curseg_mutex);
+		up_write(&curseg->journal_rwsem);
 	else
 		f2fs_put_page(page, 1);
 
@@ -1941,7 +2029,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
-	struct f2fs_summary_block *sum = curseg->sum_blk;
+	struct f2fs_journal *journal = curseg->journal;
 	struct nat_entry_set *setvec[SETVEC_SIZE];
 	struct nat_entry_set *set, *tmp;
 	unsigned int found;
@@ -1958,7 +2046,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 	 * entries, remove all entries from journal and merge them
 	 * into nat entry set.
 	 */
-	if (!__has_cursum_space(sum, nm_i->dirty_nat_cnt, NAT_JOURNAL))
+	if (!__has_cursum_space(journal, nm_i->dirty_nat_cnt, NAT_JOURNAL))
 		remove_nats_in_journal(sbi);
 
 	while ((found = __gang_lookup_nat_set(nm_i,
@@ -1967,7 +2055,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 		set_idx = setvec[found - 1]->set + 1;
 		for (idx = 0; idx < found; idx++)
 			__adjust_nat_entry_set(setvec[idx], &sets,
-							MAX_NAT_JENTRIES(sum));
+						MAX_NAT_JENTRIES(journal));
 	}
 
 	/* flush dirty nats in nat entry set */
@@ -2000,6 +2088,7 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
 	nm_i->nat_cnt = 0;
 	nm_i->ram_thresh = DEF_RAM_THRESHOLD;
 	nm_i->ra_nid_pages = DEF_RA_NID_PAGES;
+	nm_i->dirty_nats_ratio = DEF_DIRTY_NAT_RATIO_THRESHOLD;
 
 	INIT_RADIX_TREE(&nm_i->free_nid_root, GFP_ATOMIC);
 	INIT_LIST_HEAD(&nm_i->free_nid_list);

fs/f2fs/node.h

@@ -25,6 +25,9 @@
 /* control the memory footprint threshold (10MB per 1GB ram) */
 #define DEF_RAM_THRESHOLD	10
 
+/* control dirty nats ratio threshold (default: 10% over max nid count) */
+#define DEF_DIRTY_NAT_RATIO_THRESHOLD		10
+
 /* vector size for gang look-up from nat cache that consists of radix tree */
 #define NATVEC_SIZE	64
 #define SETVEC_SIZE	32
@@ -117,6 +120,12 @@ static inline void raw_nat_from_node_info(struct f2fs_nat_entry *raw_ne,
 	raw_ne->version = ni->version;
 }
 
+static inline bool excess_dirty_nats(struct f2fs_sb_info *sbi)
+{
+	return NM_I(sbi)->dirty_nat_cnt >= NM_I(sbi)->max_nid *
+					NM_I(sbi)->dirty_nats_ratio / 100;
+}
+
 enum mem_type {
 	FREE_NIDS,	/* indicates the free nid list */
 	NAT_ENTRIES,	/* indicates the cached nat entry */
@@ -321,7 +330,7 @@ static inline int set_nid(struct page *p, int off, nid_t nid, bool i)
 {
 	struct f2fs_node *rn = F2FS_NODE(p);
 
-	f2fs_wait_on_page_writeback(p, NODE);
+	f2fs_wait_on_page_writeback(p, NODE, true);
 
 	if (i)
 		rn->i.i_nid[off - NODE_DIR1_BLOCK] = cpu_to_le32(nid);
@@ -370,6 +379,21 @@ static inline int is_node(struct page *page, int type)
 #define is_fsync_dnode(page)	is_node(page, FSYNC_BIT_SHIFT)
 #define is_dent_dnode(page)	is_node(page, DENT_BIT_SHIFT)
 
+static inline int is_inline_node(struct page *page)
+{
+	return PageChecked(page);
+}
+
+static inline void set_inline_node(struct page *page)
+{
+	SetPageChecked(page);
+}
+
+static inline void clear_inline_node(struct page *page)
+{
+	ClearPageChecked(page);
+}
+
 static inline void set_cold_node(struct inode *inode, struct page *page)
 {
 	struct f2fs_node *rn = F2FS_NODE(page);

fs/f2fs/recovery.c

@@ -350,8 +350,7 @@ got_it:
 		inode = dn->inode;
 	}
 
-	bidx = start_bidx_of_node(offset, F2FS_I(inode)) +
+	bidx = start_bidx_of_node(offset, inode) + le16_to_cpu(sum.ofs_in_node);
-			le16_to_cpu(sum.ofs_in_node);
 
 	/*
 	 * if inode page is locked, unlock temporarily, but its reference
@@ -386,10 +385,9 @@ truncate_out:
 static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 					struct page *page, block_t blkaddr)
 {
-	struct f2fs_inode_info *fi = F2FS_I(inode);
-	unsigned int start, end;
 	struct dnode_of_data dn;
 	struct node_info ni;
+	unsigned int start, end;
 	int err = 0, recovered = 0;
 
 	/* step 1: recover xattr */
@@ -409,8 +407,8 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 		goto out;
 
 	/* step 3: recover data indices */
-	start = start_bidx_of_node(ofs_of_node(page), fi);
+	start = start_bidx_of_node(ofs_of_node(page), inode);
-	end = start + ADDRS_PER_PAGE(page, fi);
+	end = start + ADDRS_PER_PAGE(page, inode);
 
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
 
@@ -418,7 +416,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 	if (err)
 		goto out;
 
-	f2fs_wait_on_page_writeback(dn.node_page, NODE);
+	f2fs_wait_on_page_writeback(dn.node_page, NODE, true);
 
 	get_node_info(sbi, dn.nid, &ni);
 	f2fs_bug_on(sbi, ni.ino != ino_of_node(page));
@@ -467,7 +465,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 
 			/* write dummy data page */
 			f2fs_replace_block(sbi, &dn, src, dest,
-							ni.version, false);
+						ni.version, false, false);
 			recovered++;
 		}
 	}

fs/f2fs/segment.c

@@ -191,70 +191,145 @@ void register_inmem_page(struct inode *inode, struct page *page)
 	trace_f2fs_register_inmem_page(page, INMEM);
 }
 
-int commit_inmem_pages(struct inode *inode, bool abort)
+static int __revoke_inmem_pages(struct inode *inode,
+				struct list_head *head, bool drop, bool recover)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct inmem_pages *cur, *tmp;
+	int err = 0;
+
+	list_for_each_entry_safe(cur, tmp, head, list) {
+		struct page *page = cur->page;
+
+		if (drop)
+			trace_f2fs_commit_inmem_page(page, INMEM_DROP);
+
+		lock_page(page);
+
+		if (recover) {
+			struct dnode_of_data dn;
+			struct node_info ni;
+
+			trace_f2fs_commit_inmem_page(page, INMEM_REVOKE);
+
+			set_new_dnode(&dn, inode, NULL, NULL, 0);
+			if (get_dnode_of_data(&dn, page->index, LOOKUP_NODE)) {
+				err = -EAGAIN;
+				goto next;
+			}
+			get_node_info(sbi, dn.nid, &ni);
+			f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
+					cur->old_addr, ni.version, true, true);
+			f2fs_put_dnode(&dn);
+		}
+next:
+		ClearPageUptodate(page);
+		set_page_private(page, 0);
+		ClearPageUptodate(page);
+		f2fs_put_page(page, 1);
+
+		list_del(&cur->list);
+		kmem_cache_free(inmem_entry_slab, cur);
+		dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
+	}
+	return err;
+}
+
+void drop_inmem_pages(struct inode *inode)
+{
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+
+	mutex_lock(&fi->inmem_lock);
+	__revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
+	mutex_unlock(&fi->inmem_lock);
+}
+
+static int __commit_inmem_pages(struct inode *inode,
+					struct list_head *revoke_list)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct inmem_pages *cur, *tmp;
-	bool submit_bio = false;
 	struct f2fs_io_info fio = {
 		.sbi = sbi,
 		.type = DATA,
 		.rw = WRITE_SYNC | REQ_PRIO,
 		.encrypted_page = NULL,
 	};
+	bool submit_bio = false;
 	int err = 0;
 
-	/*
+	list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) {
-	 * The abort is true only when f2fs_evict_inode is called.
+		struct page *page = cur->page;
-	 * Basically, the f2fs_evict_inode doesn't produce any data writes, so
+
-	 * that we don't need to call f2fs_balance_fs.
+		lock_page(page);
-	 * Otherwise, f2fs_gc in f2fs_balance_fs can wait forever until this
+		if (page->mapping == inode->i_mapping) {
-	 * inode becomes free by iget_locked in f2fs_iget.
+			trace_f2fs_commit_inmem_page(page, INMEM);
-	 */
+
-	if (!abort) {
+			set_page_dirty(page);
-		f2fs_balance_fs(sbi, true);
+			f2fs_wait_on_page_writeback(page, DATA, true);
-		f2fs_lock_op(sbi);
+			if (clear_page_dirty_for_io(page))
+				inode_dec_dirty_pages(inode);
+
+			fio.page = page;
+			err = do_write_data_page(&fio);
+			if (err) {
+				unlock_page(page);
+				break;
+			}
+
+			/* record old blkaddr for revoking */
+			cur->old_addr = fio.old_blkaddr;
+
+			clear_cold_data(page);
+			submit_bio = true;
+		}
+		unlock_page(page);
+		list_move_tail(&cur->list, revoke_list);
 	}
 
-	mutex_lock(&fi->inmem_lock);
+	if (submit_bio)
-	list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) {
+		f2fs_submit_merged_bio_cond(sbi, inode, NULL, 0, DATA, WRITE);
-		lock_page(cur->page);
-		if (!abort) {
-			if (cur->page->mapping == inode->i_mapping) {
-				set_page_dirty(cur->page);
-				f2fs_wait_on_page_writeback(cur->page, DATA);
-				if (clear_page_dirty_for_io(cur->page))
-					inode_dec_dirty_pages(inode);
-				trace_f2fs_commit_inmem_page(cur->page, INMEM);
-				fio.page = cur->page;
-				err = do_write_data_page(&fio);
-				if (err) {
-					unlock_page(cur->page);
-					break;
-				}
-				clear_cold_data(cur->page);
-				submit_bio = true;
-			}
-		} else {
-			ClearPageUptodate(cur->page);
-			trace_f2fs_commit_inmem_page(cur->page, INMEM_DROP);
-		}
-		set_page_private(cur->page, 0);
-		ClearPagePrivate(cur->page);
-		f2fs_put_page(cur->page, 1);
 
-		list_del(&cur->list);
+	if (!err)
-		kmem_cache_free(inmem_entry_slab, cur);
+		__revoke_inmem_pages(inode, revoke_list, false, false);
-		dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
+
+	return err;
+}
+
+int commit_inmem_pages(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+	struct list_head revoke_list;
+	int err;
+
+	INIT_LIST_HEAD(&revoke_list);
+	f2fs_balance_fs(sbi, true);
+	f2fs_lock_op(sbi);
+
+	mutex_lock(&fi->inmem_lock);
+	err = __commit_inmem_pages(inode, &revoke_list);
+	if (err) {
+		int ret;
+		/*
+		 * try to revoke all committed pages, but still we could fail
+		 * due to no memory or other reason, if that happened, EAGAIN
+		 * will be returned, which means in such case, transaction is
+		 * already not integrity, caller should use journal to do the
+		 * recovery or rewrite & commit last transaction. For other
+		 * error number, revoking was done by filesystem itself.
+		 */
+		ret = __revoke_inmem_pages(inode, &revoke_list, false, true);
+		if (ret)
+			err = ret;
+
+		/* drop all uncommitted pages */
+		__revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
 	}
 	mutex_unlock(&fi->inmem_lock);
 
-	if (!abort) {
+	f2fs_unlock_op(sbi);
-		f2fs_unlock_op(sbi);
-		if (submit_bio)
-			f2fs_submit_merged_bio(sbi, DATA, WRITE);
-	}
 	return err;
 }
 
@@ -291,11 +366,17 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 
 	/* checkpoint is the only way to shrink partial cached entries */
 	if (!available_free_memory(sbi, NAT_ENTRIES) ||
-			excess_prefree_segs(sbi) ||
 			!available_free_memory(sbi, INO_ENTRIES) ||
+			excess_prefree_segs(sbi) ||
+			excess_dirty_nats(sbi) ||
 			(is_idle(sbi) && f2fs_time_over(sbi, CP_TIME))) {
-		if (test_opt(sbi, DATA_FLUSH))
+		if (test_opt(sbi, DATA_FLUSH)) {
+			struct blk_plug plug;
+
+			blk_start_plug(&plug);
 			sync_dirty_inodes(sbi, FILE_INODE);
+			blk_finish_plug(&plug);
+		}
 		f2fs_sync_fs(sbi->sb, true);
 		stat_inc_bg_cp_count(sbi->stat_info);
 	}
@@ -502,7 +583,7 @@ static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
 
 bool discard_next_dnode(struct f2fs_sb_info *sbi, block_t blkaddr)
 {
-	int err = -ENOTSUPP;
+	int err = -EOPNOTSUPP;
 
 	if (test_opt(sbi, DISCARD)) {
 		struct seg_entry *se = get_seg_entry(sbi,
@@ -841,6 +922,31 @@ static void write_sum_page(struct f2fs_sb_info *sbi,
 	update_meta_page(sbi, (void *)sum_blk, blk_addr);
 }
 
+static void write_current_sum_page(struct f2fs_sb_info *sbi,
+						int type, block_t blk_addr)
+{
+	struct curseg_info *curseg = CURSEG_I(sbi, type);
+	struct page *page = grab_meta_page(sbi, blk_addr);
+	struct f2fs_summary_block *src = curseg->sum_blk;
+	struct f2fs_summary_block *dst;
+
+	dst = (struct f2fs_summary_block *)page_address(page);
+
+	mutex_lock(&curseg->curseg_mutex);
+
+	down_read(&curseg->journal_rwsem);
+	memcpy(&dst->journal, curseg->journal, SUM_JOURNAL_SIZE);
+	up_read(&curseg->journal_rwsem);
+
+	memcpy(dst->entries, src->entries, SUM_ENTRY_SIZE);
+	memcpy(&dst->footer, &src->footer, SUM_FOOTER_SIZE);
+
+	mutex_unlock(&curseg->curseg_mutex);
+
+	set_page_dirty(page);
+	f2fs_put_page(page, 1);
+}
+
 static int is_next_segment_free(struct f2fs_sb_info *sbi, int type)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
@@ -873,9 +979,8 @@ static void get_new_segment(struct f2fs_sb_info *sbi,
 
 	if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) {
 		segno = find_next_zero_bit(free_i->free_segmap,
-					MAIN_SEGS(sbi), *newseg + 1);
+				(hint + 1) * sbi->segs_per_sec, *newseg + 1);
-		if (segno - *newseg < sbi->segs_per_sec -
+		if (segno < (hint + 1) * sbi->segs_per_sec)
-					(*newseg % sbi->segs_per_sec))
 			goto got_it;
 	}
 find_other_zone:
@@ -1280,8 +1385,8 @@ static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
 {
 	int type = __get_segment_type(fio->page, fio->type);
 
-	allocate_data_block(fio->sbi, fio->page, fio->blk_addr,
+	allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
-					&fio->blk_addr, sum, type);
+					&fio->new_blkaddr, sum, type);
 
 	/* writeout dirty page into bdev */
 	f2fs_submit_page_mbio(fio);
@@ -1293,7 +1398,8 @@ void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
 		.sbi = sbi,
 		.type = META,
 		.rw = WRITE_SYNC | REQ_META | REQ_PRIO,
-		.blk_addr = page->index,
+		.old_blkaddr = page->index,
+		.new_blkaddr = page->index,
 		.page = page,
 		.encrypted_page = NULL,
 	};
@@ -1323,19 +1429,19 @@ void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio)
 	get_node_info(sbi, dn->nid, &ni);
 	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
 	do_write_page(&sum, fio);
-	dn->data_blkaddr = fio->blk_addr;
+	f2fs_update_data_blkaddr(dn, fio->new_blkaddr);
 }
 
 void rewrite_data_page(struct f2fs_io_info *fio)
 {
+	fio->new_blkaddr = fio->old_blkaddr;
 	stat_inc_inplace_blocks(fio->sbi);
 	f2fs_submit_page_mbio(fio);
 }
 
-static void __f2fs_replace_block(struct f2fs_sb_info *sbi,
+void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
-				struct f2fs_summary *sum,
 				block_t old_blkaddr, block_t new_blkaddr,
-				bool recover_curseg)
+				bool recover_curseg, bool recover_newaddr)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
 	struct curseg_info *curseg;
@@ -1378,7 +1484,7 @@ static void __f2fs_replace_block(struct f2fs_sb_info *sbi,
 	curseg->next_blkoff = GET_BLKOFF_FROM_SEG0(sbi, new_blkaddr);
 	__add_sum_entry(sbi, type, sum);
 
-	if (!recover_curseg)
+	if (!recover_curseg || recover_newaddr)
 		update_sit_entry(sbi, new_blkaddr, 1);
 	if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
 		update_sit_entry(sbi, old_blkaddr, -1);
@@ -1402,66 +1508,30 @@ static void __f2fs_replace_block(struct f2fs_sb_info *sbi,
 
 void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
 				block_t old_addr, block_t new_addr,
-				unsigned char version, bool recover_curseg)
+				unsigned char version, bool recover_curseg,
+				bool recover_newaddr)
 {
 	struct f2fs_summary sum;
 
 	set_summary(&sum, dn->nid, dn->ofs_in_node, version);
 
-	__f2fs_replace_block(sbi, &sum, old_addr, new_addr, recover_curseg);
+	__f2fs_replace_block(sbi, &sum, old_addr, new_addr,
+					recover_curseg, recover_newaddr);
 
-	dn->data_blkaddr = new_addr;
+	f2fs_update_data_blkaddr(dn, new_addr);
-	set_data_blkaddr(dn);
-	f2fs_update_extent_cache(dn);
-}
-
-static inline bool is_merged_page(struct f2fs_sb_info *sbi,
-					struct page *page, enum page_type type)
-{
-	enum page_type btype = PAGE_TYPE_OF_BIO(type);
-	struct f2fs_bio_info *io = &sbi->write_io[btype];
-	struct bio_vec *bvec;
-	struct page *target;
-	int i;
-
-	down_read(&io->io_rwsem);
-	if (!io->bio) {
-		up_read(&io->io_rwsem);
-		return false;
-	}
-
-	bio_for_each_segment_all(bvec, io->bio, i) {
-
-		if (bvec->bv_page->mapping) {
-			target = bvec->bv_page;
-		} else {
-			struct f2fs_crypto_ctx *ctx;
-
-			/* encrypted page */
-			ctx = (struct f2fs_crypto_ctx *)page_private(
-								bvec->bv_page);
-			target = ctx->w.control_page;
-		}
-
-		if (page == target) {
-			up_read(&io->io_rwsem);
-			return true;
-		}
-	}
-
-	up_read(&io->io_rwsem);
-	return false;
 }
 
 void f2fs_wait_on_page_writeback(struct page *page,
-				enum page_type type)
+				enum page_type type, bool ordered)
 {
 	if (PageWriteback(page)) {
 		struct f2fs_sb_info *sbi = F2FS_P_SB(page);
 
-		if (is_merged_page(sbi, page, type))
+		f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, type, WRITE);
-			f2fs_submit_merged_bio(sbi, type, WRITE);
+		if (ordered)
-		wait_on_page_writeback(page);
+			wait_on_page_writeback(page);
+		else
+			wait_for_stable_page(page);
 	}
 }
 
@@ -1477,7 +1547,7 @@ void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi,
 
 	cpage = find_lock_page(META_MAPPING(sbi), blkaddr);
 	if (cpage) {
-		f2fs_wait_on_page_writeback(cpage, DATA);
+		f2fs_wait_on_page_writeback(cpage, DATA, true);
 		f2fs_put_page(cpage, 1);
 	}
 }
@@ -1498,12 +1568,11 @@ static int read_compacted_summaries(struct f2fs_sb_info *sbi)
 
 	/* Step 1: restore nat cache */
 	seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA);
-	memcpy(&seg_i->sum_blk->n_nats, kaddr, SUM_JOURNAL_SIZE);
+	memcpy(seg_i->journal, kaddr, SUM_JOURNAL_SIZE);
 
 	/* Step 2: restore sit cache */
 	seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA);
-	memcpy(&seg_i->sum_blk->n_sits, kaddr + SUM_JOURNAL_SIZE,
+	memcpy(seg_i->journal, kaddr + SUM_JOURNAL_SIZE, SUM_JOURNAL_SIZE);
-						SUM_JOURNAL_SIZE);
 	offset = 2 * SUM_JOURNAL_SIZE;
 
 	/* Step 3: restore summary entries */
@@ -1599,7 +1668,14 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 	/* set uncompleted segment to curseg */
 	curseg = CURSEG_I(sbi, type);
 	mutex_lock(&curseg->curseg_mutex);
-	memcpy(curseg->sum_blk, sum, PAGE_CACHE_SIZE);
+
+	/* update journal info */
+	down_write(&curseg->journal_rwsem);
+	memcpy(curseg->journal, &sum->journal, SUM_JOURNAL_SIZE);
+	up_write(&curseg->journal_rwsem);
+
+	memcpy(curseg->sum_blk->entries, sum->entries, SUM_ENTRY_SIZE);
+	memcpy(&curseg->sum_blk->footer, &sum->footer, SUM_FOOTER_SIZE);
 	curseg->next_segno = segno;
 	reset_curseg(sbi, type, 0);
 	curseg->alloc_type = ckpt->alloc_type[type];
@@ -1654,13 +1730,12 @@ static void write_compacted_summaries(struct f2fs_sb_info *sbi, block_t blkaddr)
 
 	/* Step 1: write nat cache */
 	seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA);
-	memcpy(kaddr, &seg_i->sum_blk->n_nats, SUM_JOURNAL_SIZE);
+	memcpy(kaddr, seg_i->journal, SUM_JOURNAL_SIZE);
 	written_size += SUM_JOURNAL_SIZE;
 
 	/* Step 2: write sit cache */
 	seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA);
-	memcpy(kaddr + written_size, &seg_i->sum_blk->n_sits,
+	memcpy(kaddr + written_size, seg_i->journal, SUM_JOURNAL_SIZE);
-						SUM_JOURNAL_SIZE);
 	written_size += SUM_JOURNAL_SIZE;
 
 	/* Step 3: write summary entries */
@@ -1706,12 +1781,8 @@ static void write_normal_summaries(struct f2fs_sb_info *sbi,
 	else
 		end = type + NR_CURSEG_NODE_TYPE;
 
-	for (i = type; i < end; i++) {
+	for (i = type; i < end; i++)
-		struct curseg_info *sum = CURSEG_I(sbi, i);
+		write_current_sum_page(sbi, i, blkaddr + (i - type));
-		mutex_lock(&sum->curseg_mutex);
-		write_sum_page(sbi, sum->sum_blk, blkaddr + (i - type));
-		mutex_unlock(&sum->curseg_mutex);
-	}
 }
 
 void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
@@ -1727,24 +1798,24 @@ void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
 	write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE);
 }
 
-int lookup_journal_in_cursum(struct f2fs_summary_block *sum, int type,
+int lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
 					unsigned int val, int alloc)
 {
 	int i;
 
 	if (type == NAT_JOURNAL) {
-		for (i = 0; i < nats_in_cursum(sum); i++) {
+		for (i = 0; i < nats_in_cursum(journal); i++) {
-			if (le32_to_cpu(nid_in_journal(sum, i)) == val)
+			if (le32_to_cpu(nid_in_journal(journal, i)) == val)
 				return i;
 		}
-		if (alloc && __has_cursum_space(sum, 1, NAT_JOURNAL))
+		if (alloc && __has_cursum_space(journal, 1, NAT_JOURNAL))
-			return update_nats_in_cursum(sum, 1);
+			return update_nats_in_cursum(journal, 1);
 	} else if (type == SIT_JOURNAL) {
-		for (i = 0; i < sits_in_cursum(sum); i++)
+		for (i = 0; i < sits_in_cursum(journal); i++)
-			if (le32_to_cpu(segno_in_journal(sum, i)) == val)
+			if (le32_to_cpu(segno_in_journal(journal, i)) == val)
 				return i;
-		if (alloc && __has_cursum_space(sum, 1, SIT_JOURNAL))
+		if (alloc && __has_cursum_space(journal, 1, SIT_JOURNAL))
-			return update_sits_in_cursum(sum, 1);
+			return update_sits_in_cursum(journal, 1);
 	}
 	return -1;
 }
@@ -1848,20 +1919,22 @@ static void add_sits_in_set(struct f2fs_sb_info *sbi)
 static void remove_sits_in_journal(struct f2fs_sb_info *sbi)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
-	struct f2fs_summary_block *sum = curseg->sum_blk;
+	struct f2fs_journal *journal = curseg->journal;
 	int i;
 
-	for (i = sits_in_cursum(sum) - 1; i >= 0; i--) {
+	down_write(&curseg->journal_rwsem);
+	for (i = 0; i < sits_in_cursum(journal); i++) {
 		unsigned int segno;
 		bool dirtied;
 
-		segno = le32_to_cpu(segno_in_journal(sum, i));
+		segno = le32_to_cpu(segno_in_journal(journal, i));
 		dirtied = __mark_sit_entry_dirty(sbi, segno);
 
 		if (!dirtied)
 			add_sit_entry(segno, &SM_I(sbi)->sit_entry_set);
 	}
-	update_sits_in_cursum(sum, -sits_in_cursum(sum));
+	update_sits_in_cursum(journal, -i);
+	up_write(&curseg->journal_rwsem);
 }
 
 /*
@@ -1873,13 +1946,12 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	struct sit_info *sit_i = SIT_I(sbi);
 	unsigned long *bitmap = sit_i->dirty_sentries_bitmap;
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
-	struct f2fs_summary_block *sum = curseg->sum_blk;
+	struct f2fs_journal *journal = curseg->journal;
 	struct sit_entry_set *ses, *tmp;
 	struct list_head *head = &SM_I(sbi)->sit_entry_set;
 	bool to_journal = true;
 	struct seg_entry *se;
 
-	mutex_lock(&curseg->curseg_mutex);
 	mutex_lock(&sit_i->sentry_lock);
 
 	if (!sit_i->dirty_sentries)
@@ -1896,7 +1968,7 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	 * entries, remove all entries from journal and add and account
 	 * them in sit entry set.
 	 */
-	if (!__has_cursum_space(sum, sit_i->dirty_sentries, SIT_JOURNAL))
+	if (!__has_cursum_space(journal, sit_i->dirty_sentries, SIT_JOURNAL))
 		remove_sits_in_journal(sbi);
 
 	/*
@@ -1913,10 +1985,12 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 		unsigned int segno = start_segno;
 
 		if (to_journal &&
-			!__has_cursum_space(sum, ses->entry_cnt, SIT_JOURNAL))
+			!__has_cursum_space(journal, ses->entry_cnt, SIT_JOURNAL))
 			to_journal = false;
 
-		if (!to_journal) {
+		if (to_journal) {
+			down_write(&curseg->journal_rwsem);
+		} else {
 			page = get_next_sit_page(sbi, start_segno);
 			raw_sit = page_address(page);
 		}
@@ -1934,13 +2008,13 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			}
 
 			if (to_journal) {
-				offset = lookup_journal_in_cursum(sum,
+				offset = lookup_journal_in_cursum(journal,
 							SIT_JOURNAL, segno, 1);
 				f2fs_bug_on(sbi, offset < 0);
-				segno_in_journal(sum, offset) =
+				segno_in_journal(journal, offset) =
 							cpu_to_le32(segno);
 				seg_info_to_raw_sit(se,
-						&sit_in_journal(sum, offset));
+					&sit_in_journal(journal, offset));
 			} else {
 				sit_offset = SIT_ENTRY_OFFSET(sit_i, segno);
 				seg_info_to_raw_sit(se,
@@ -1952,7 +2026,9 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			ses->entry_cnt--;
 		}
 
-		if (!to_journal)
+		if (to_journal)
+			up_write(&curseg->journal_rwsem);
+		else
 			f2fs_put_page(page, 1);
 
 		f2fs_bug_on(sbi, ses->entry_cnt);
@@ -1967,7 +2043,6 @@ out:
 			add_discard_addrs(sbi, cpc);
 	}
 	mutex_unlock(&sit_i->sentry_lock);
-	mutex_unlock(&curseg->curseg_mutex);
 
 	set_prefree_as_free_segments(sbi);
 }
@@ -2099,6 +2174,11 @@ static int build_curseg(struct f2fs_sb_info *sbi)
 		array[i].sum_blk = kzalloc(PAGE_CACHE_SIZE, GFP_KERNEL);
 		if (!array[i].sum_blk)
 			return -ENOMEM;
+		init_rwsem(&array[i].journal_rwsem);
+		array[i].journal = kzalloc(sizeof(struct f2fs_journal),
+							GFP_KERNEL);
+		if (!array[i].journal)
+			return -ENOMEM;
 		array[i].segno = NULL_SEGNO;
 		array[i].next_blkoff = 0;
 	}
@@ -2109,11 +2189,11 @@ static void build_sit_entries(struct f2fs_sb_info *sbi)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
-	struct f2fs_summary_block *sum = curseg->sum_blk;
+	struct f2fs_journal *journal = curseg->journal;
 	int sit_blk_cnt = SIT_BLK_CNT(sbi);
 	unsigned int i, start, end;
 	unsigned int readed, start_blk = 0;
-	int nrpages = MAX_BIO_BLOCKS(sbi);
+	int nrpages = MAX_BIO_BLOCKS(sbi) * 8;
 
 	do {
 		readed = ra_meta_pages(sbi, start_blk, nrpages, META_SIT, true);
@@ -2127,16 +2207,16 @@ static void build_sit_entries(struct f2fs_sb_info *sbi)
 			struct f2fs_sit_entry sit;
 			struct page *page;
 
-			mutex_lock(&curseg->curseg_mutex);
+			down_read(&curseg->journal_rwsem);
-			for (i = 0; i < sits_in_cursum(sum); i++) {
+			for (i = 0; i < sits_in_cursum(journal); i++) {
-				if (le32_to_cpu(segno_in_journal(sum, i))
+				if (le32_to_cpu(segno_in_journal(journal, i))
 								== start) {
-					sit = sit_in_journal(sum, i);
+					sit = sit_in_journal(journal, i);
-					mutex_unlock(&curseg->curseg_mutex);
+					up_read(&curseg->journal_rwsem);
 					goto got_it;
 				}
 			}
-			mutex_unlock(&curseg->curseg_mutex);
+			up_read(&curseg->journal_rwsem);
 
 			page = get_current_sit_page(sbi, start);
 			sit_blk = (struct f2fs_sit_block *)page_address(page);
@@ -2371,8 +2451,10 @@ static void destroy_curseg(struct f2fs_sb_info *sbi)
 	if (!array)
 		return;
 	SM_I(sbi)->curseg_array = NULL;
-	for (i = 0; i < NR_CURSEG_TYPE; i++)
+	for (i = 0; i < NR_CURSEG_TYPE; i++) {
 		kfree(array[i].sum_blk);
+		kfree(array[i].journal);
+	}
 	kfree(array);
 }
 

fs/f2fs/segment.h

@@ -183,7 +183,7 @@ struct segment_allocation {
  * this value is set in page as a private data which indicate that
  * the page is atomically written, and it is in inmem_pages list.
  */
-#define ATOMIC_WRITTEN_PAGE		0x0000ffff
+#define ATOMIC_WRITTEN_PAGE		((unsigned long)-1)
 
 #define IS_ATOMIC_WRITTEN_PAGE(page)			\
 		(page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE)
@@ -191,6 +191,7 @@ struct segment_allocation {
 struct inmem_pages {
 	struct list_head list;
 	struct page *page;
+	block_t old_addr;		/* for revoking when fail to commit */
 };
 
 struct sit_info {
@@ -257,6 +258,8 @@ struct victim_selection {
 struct curseg_info {
 	struct mutex curseg_mutex;		/* lock for consistency */
 	struct f2fs_summary_block *sum_blk;	/* cached summary block */
+	struct rw_semaphore journal_rwsem;	/* protect journal area */
+	struct f2fs_journal *journal;		/* cached journal info */
 	unsigned char alloc_type;		/* current allocation type */
 	unsigned int segno;			/* current segment number */
 	unsigned short next_blkoff;		/* next block offset to write */

fs/f2fs/super.c

@@ -126,6 +126,19 @@ static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
 	return NULL;
 }
 
+static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
+		struct f2fs_sb_info *sbi, char *buf)
+{
+	struct super_block *sb = sbi->sb;
+
+	if (!sb->s_bdev->bd_part)
+		return snprintf(buf, PAGE_SIZE, "0\n");
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n",
+		(unsigned long long)(sbi->kbytes_written +
+			BD_PART_WRITTEN(sbi)));
+}
+
 static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
 			struct f2fs_sb_info *sbi, char *buf)
 {
@@ -204,6 +217,9 @@ static struct f2fs_attr f2fs_attr_##_name = {			\
 		f2fs_sbi_show, f2fs_sbi_store,			\
 		offsetof(struct struct_name, elname))
 
+#define F2FS_GENERAL_RO_ATTR(name) \
+static struct f2fs_attr f2fs_attr_##name = __ATTR(name, 0444, name##_show, NULL)
+
 F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_min_sleep_time, min_sleep_time);
 F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_max_sleep_time, max_sleep_time);
 F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time);
@@ -216,10 +232,12 @@ F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks);
 F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh);
 F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ra_nid_pages, ra_nid_pages);
+F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, dirty_nats_ratio, dirty_nats_ratio);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, interval_time[CP_TIME]);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]);
+F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes);
 
 #define ATTR_LIST(name) (&f2fs_attr_##name.attr)
 static struct attribute *f2fs_attrs[] = {
@@ -237,8 +255,10 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(dir_level),
 	ATTR_LIST(ram_thresh),
 	ATTR_LIST(ra_nid_pages),
+	ATTR_LIST(dirty_nats_ratio),
 	ATTR_LIST(cp_interval),
 	ATTR_LIST(idle_interval),
+	ATTR_LIST(lifetime_write_kbytes),
 	NULL,
 };
 
@@ -450,10 +470,6 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
 
 	/* Will be used by directory only */
 	fi->i_dir_level = F2FS_SB(sb)->dir_level;
-
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-	fi->i_crypt_info = NULL;
-#endif
 	return &fi->vfs_inode;
 }
 
@@ -474,7 +490,7 @@ static int f2fs_drop_inode(struct inode *inode)
 
 			/* some remained atomic pages should discarded */
 			if (f2fs_is_atomic_file(inode))
-				commit_inmem_pages(inode, true);
+				drop_inmem_pages(inode);
 
 			/* should remain fi->extent_tree for writepage */
 			f2fs_destroy_extent_node(inode);
@@ -487,11 +503,7 @@ static int f2fs_drop_inode(struct inode *inode)
 
 			sb_end_intwrite(inode->i_sb);
 
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
+			fscrypt_put_encryption_info(inode, NULL);
-			if (F2FS_I(inode)->i_crypt_info)
-				f2fs_free_encryption_info(inode,
-					F2FS_I(inode)->i_crypt_info);
-#endif
 			spin_lock(&inode->i_lock);
 			atomic_dec(&inode->i_count);
 		}
@@ -562,6 +574,10 @@ static void f2fs_put_super(struct super_block *sb)
 	f2fs_leave_shrinker(sbi);
 	mutex_unlock(&sbi->umount_mutex);
 
+	/* our cp_error case, we can wait for any writeback page */
+	if (get_pages(sbi, F2FS_WRITEBACK))
+		f2fs_flush_merged_bios(sbi);
+
 	iput(sbi->node_inode);
 	iput(sbi->meta_inode);
 
@@ -574,6 +590,8 @@ static void f2fs_put_super(struct super_block *sb)
 	wait_for_completion(&sbi->s_kobj_unregister);
 
 	sb->s_fs_info = NULL;
+	if (sbi->s_chksum_driver)
+		crypto_free_shash(sbi->s_chksum_driver);
 	kfree(sbi->raw_super);
 	kfree(sbi);
 }
@@ -766,8 +784,6 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	bool need_stop_gc = false;
 	bool no_extent_cache = !test_opt(sbi, EXTENT_CACHE);
 
-	sync_filesystem(sb);
-
 	/*
 	 * Save the old mount options in case we
 	 * need to restore them.
@@ -775,6 +791,13 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	org_mount_opt = sbi->mount_opt;
 	active_logs = sbi->active_logs;
 
+	if (*flags & MS_RDONLY) {
+		set_opt(sbi, FASTBOOT);
+		set_sbi_flag(sbi, SBI_IS_DIRTY);
+	}
+
+	sync_filesystem(sb);
+
 	sbi->mount_opt.opt = 0;
 	default_options(sbi);
 
@@ -862,6 +885,41 @@ static struct super_operations f2fs_sops = {
 	.remount_fs	= f2fs_remount,
 };
 
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+static int f2fs_get_context(struct inode *inode, void *ctx, size_t len)
+{
+	return f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
+				F2FS_XATTR_NAME_ENCRYPTION_CONTEXT,
+				ctx, len, NULL);
+}
+
+static int f2fs_set_context(struct inode *inode, const void *ctx, size_t len,
+							void *fs_data)
+{
+	return f2fs_setxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
+				F2FS_XATTR_NAME_ENCRYPTION_CONTEXT,
+				ctx, len, fs_data, XATTR_CREATE);
+}
+
+static unsigned f2fs_max_namelen(struct inode *inode)
+{
+	return S_ISLNK(inode->i_mode) ?
+			inode->i_sb->s_blocksize : F2FS_NAME_LEN;
+}
+
+static struct fscrypt_operations f2fs_cryptops = {
+	.get_context	= f2fs_get_context,
+	.set_context	= f2fs_set_context,
+	.is_encrypted	= f2fs_encrypted_inode,
+	.empty_dir	= f2fs_empty_dir,
+	.max_namelen	= f2fs_max_namelen,
+};
+#else
+static struct fscrypt_operations f2fs_cryptops = {
+	.is_encrypted	= f2fs_encrypted_inode,
+};
+#endif
+
 static struct inode *f2fs_nfs_get_inode(struct super_block *sb,
 		u64 ino, u32 generation)
 {
@@ -1074,7 +1132,7 @@ static int sanity_check_raw_super(struct super_block *sb,
 	return 0;
 }
 
-static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
+int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 {
 	unsigned int total, fsmeta;
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
@@ -1134,14 +1192,15 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 
 /*
  * Read f2fs raw super block.
- * Because we have two copies of super block, so read the first one at first,
+ * Because we have two copies of super block, so read both of them
- * if the first one is invalid, move to read the second one.
+ * to get the first valid one. If any one of them is broken, we pass
+ * them recovery flag back to the caller.
  */
 static int read_raw_super_block(struct super_block *sb,
 			struct f2fs_super_block **raw_super,
 			int *valid_super_block, int *recovery)
 {
-	int block = 0;
+	int block;
 	struct buffer_head *bh;
 	struct f2fs_super_block *super, *buf;
 	int err = 0;
@@ -1149,50 +1208,48 @@ static int read_raw_super_block(struct super_block *sb,
 	super = kzalloc(sizeof(struct f2fs_super_block), GFP_KERNEL);
 	if (!super)
 		return -ENOMEM;
-retry:
+
-	bh = sb_bread(sb, block);
+	for (block = 0; block < 2; block++) {
-	if (!bh) {
+		bh = sb_bread(sb, block);
-		*recovery = 1;
+		if (!bh) {
-		f2fs_msg(sb, KERN_ERR, "Unable to read %dth superblock",
+			f2fs_msg(sb, KERN_ERR, "Unable to read %dth superblock",
 				block + 1);
-		err = -EIO;
+			err = -EIO;
-		goto next;
+			continue;
-	}
+		}
 
-	buf = (struct f2fs_super_block *)(bh->b_data + F2FS_SUPER_OFFSET);
+		buf = (struct f2fs_super_block *)
+				(bh->b_data + F2FS_SUPER_OFFSET);
 
-	/* sanity checking of raw super */
+		/* sanity checking of raw super */
-	if (sanity_check_raw_super(sb, buf)) {
+		if (sanity_check_raw_super(sb, buf)) {
+			f2fs_msg(sb, KERN_ERR,
+				"Can't find valid F2FS filesystem in %dth superblock",
+				block + 1);
+			err = -EINVAL;
+			brelse(bh);
+			continue;
+		}
+
+		if (!*raw_super) {
+			memcpy(super, buf, sizeof(*super));
+			*valid_super_block = block;
+			*raw_super = super;
+		}
 		brelse(bh);
+	}
+
+	/* Fail to read any one of the superblocks*/
+	if (err < 0)
 		*recovery = 1;
-		f2fs_msg(sb, KERN_ERR,
-			"Can't find valid F2FS filesystem in %dth superblock",
-								block + 1);
-		err = -EINVAL;
-		goto next;
-	}
-
-	if (!*raw_super) {
-		memcpy(super, buf, sizeof(*super));
-		*valid_super_block = block;
-		*raw_super = super;
-	}
-	brelse(bh);
-
-next:
-	/* check the validity of the second superblock */
-	if (block == 0) {
-		block++;
-		goto retry;
-	}
 
 	/* No valid superblock */
-	if (!*raw_super) {
+	if (!*raw_super)
 		kfree(super);
-		return err;
+	else
-	}
+		err = 0;
 
-	return 0;
+	return err;
 }
 
 static int __f2fs_commit_super(struct f2fs_sb_info *sbi, int block)
@@ -1242,6 +1299,7 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 	bool retry = true, need_fsck = false;
 	char *options = NULL;
 	int recovery, i, valid_super_block;
+	struct curseg_info *seg_i;
 
 try_onemore:
 	err = -EINVAL;
@@ -1254,6 +1312,15 @@ try_onemore:
 	if (!sbi)
 		return -ENOMEM;
 
+	/* Load the checksum driver */
+	sbi->s_chksum_driver = crypto_alloc_shash("crc32", 0, 0);
+	if (IS_ERR(sbi->s_chksum_driver)) {
+		f2fs_msg(sb, KERN_ERR, "Cannot load crc32 driver.");
+		err = PTR_ERR(sbi->s_chksum_driver);
+		sbi->s_chksum_driver = NULL;
+		goto free_sbi;
+	}
+
 	/* set a block size */
 	if (unlikely(!sb_set_blocksize(sb, F2FS_BLKSIZE))) {
 		f2fs_msg(sb, KERN_ERR, "unable to set blocksize");
@@ -1285,6 +1352,7 @@ try_onemore:
 	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
 
 	sb->s_op = &f2fs_sops;
+	sb->s_cop = &f2fs_cryptops;
 	sb->s_xattr = f2fs_xattr_handlers;
 	sb->s_export_op = &f2fs_export_ops;
 	sb->s_magic = F2FS_SUPER_MAGIC;
@@ -1333,13 +1401,6 @@ try_onemore:
 		goto free_meta_inode;
 	}
 
-	/* sanity checking of checkpoint */
-	err = -EINVAL;
-	if (sanity_check_ckpt(sbi)) {
-		f2fs_msg(sb, KERN_ERR, "Invalid F2FS checkpoint");
-		goto free_cp;
-	}
-
 	sbi->total_valid_node_count =
 				le32_to_cpu(sbi->ckpt->valid_node_count);
 	sbi->total_valid_inode_count =
@@ -1372,6 +1433,17 @@ try_onemore:
 		goto free_nm;
 	}
 
+	/* For write statistics */
+	if (sb->s_bdev->bd_part)
+		sbi->sectors_written_start =
+			(u64)part_stat_read(sb->s_bdev->bd_part, sectors[1]);
+
+	/* Read accumulated write IO statistics if exists */
+	seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
+	if (__exist_node_summaries(sbi))
+		sbi->kbytes_written =
+			le64_to_cpu(seg_i->sum_blk->journal.info.kbytes_written);
+
 	build_gc_manager(sbi);
 
 	/* get an inode for node space */
@@ -1466,8 +1538,10 @@ try_onemore:
 
 	/* recover broken superblock */
 	if (recovery && !f2fs_readonly(sb) && !bdev_read_only(sb->s_bdev)) {
-		f2fs_msg(sb, KERN_INFO, "Recover invalid superblock");
+		err = f2fs_commit_super(sbi, true);
-		f2fs_commit_super(sbi, true);
+		f2fs_msg(sb, KERN_INFO,
+			"Try to recover %dth superblock, ret: %ld",
+			sbi->valid_super_block ? 1 : 2, err);
 	}
 
 	f2fs_update_time(sbi, CP_TIME);
@@ -1496,7 +1570,6 @@ free_nm:
 	destroy_node_manager(sbi);
 free_sm:
 	destroy_segment_manager(sbi);
-free_cp:
 	kfree(sbi->ckpt);
 free_meta_inode:
 	make_bad_inode(sbi->meta_inode);
@@ -1506,6 +1579,8 @@ free_options:
 free_sb_buf:
 	kfree(raw_super);
 free_sbi:
+	if (sbi->s_chksum_driver)
+		crypto_free_shash(sbi->s_chksum_driver);
 	kfree(sbi);
 
 	/* give only one another chance */
@@ -1585,13 +1660,9 @@ static int __init init_f2fs_fs(void)
 		err = -ENOMEM;
 		goto free_extent_cache;
 	}
-	err = f2fs_init_crypto();
-	if (err)
-		goto free_kset;
-
 	err = register_shrinker(&f2fs_shrinker_info);
 	if (err)
-		goto free_crypto;
+		goto free_kset;
 
 	err = register_filesystem(&f2fs_fs_type);
 	if (err)
@@ -1606,8 +1677,6 @@ free_filesystem:
 	unregister_filesystem(&f2fs_fs_type);
 free_shrinker:
 	unregister_shrinker(&f2fs_shrinker_info);
-free_crypto:
-	f2fs_exit_crypto();
 free_kset:
 	kset_unregister(f2fs_kset);
 free_extent_cache:
@@ -1630,7 +1699,6 @@ static void __exit exit_f2fs_fs(void)
 	f2fs_destroy_root_stats();
 	unregister_shrinker(&f2fs_shrinker_info);
 	unregister_filesystem(&f2fs_fs_type);
-	f2fs_exit_crypto();
 	destroy_extent_cache();
 	destroy_checkpoint_caches();
 	destroy_segment_manager_caches();

fs/f2fs/trace.c

@@ -29,7 +29,8 @@ static inline void __print_last_io(void)
 			last_io.major, last_io.minor,
 			last_io.pid, "----------------",
 			last_io.type,
-			last_io.fio.rw, last_io.fio.blk_addr,
+			last_io.fio.rw,
+			last_io.fio.new_blkaddr,
 			last_io.len);
 	memset(&last_io, 0, sizeof(last_io));
 }
@@ -101,7 +102,8 @@ void f2fs_trace_ios(struct f2fs_io_info *fio, int flush)
 			last_io.pid == pid &&
 			last_io.type == __file_type(inode, pid) &&
 			last_io.fio.rw == fio->rw &&
-			last_io.fio.blk_addr + last_io.len == fio->blk_addr) {
+			last_io.fio.new_blkaddr + last_io.len ==
+							fio->new_blkaddr) {
 		last_io.len++;
 		return;
 	}

fs/f2fs/xattr.c

@@ -300,7 +300,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 
 		if (ipage) {
 			inline_addr = inline_xattr_addr(ipage);
-			f2fs_wait_on_page_writeback(ipage, NODE);
+			f2fs_wait_on_page_writeback(ipage, NODE, true);
 		} else {
 			page = get_node_page(sbi, inode->i_ino);
 			if (IS_ERR(page)) {
@@ -308,7 +308,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 				return PTR_ERR(page);
 			}
 			inline_addr = inline_xattr_addr(page);
-			f2fs_wait_on_page_writeback(page, NODE);
+			f2fs_wait_on_page_writeback(page, NODE, true);
 		}
 		memcpy(inline_addr, txattr_addr, inline_size);
 		f2fs_put_page(page, 1);
@@ -329,7 +329,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 			return PTR_ERR(xpage);
 		}
 		f2fs_bug_on(sbi, new_nid);
-		f2fs_wait_on_page_writeback(xpage, NODE);
+		f2fs_wait_on_page_writeback(xpage, NODE, true);
 	} else {
 		struct dnode_of_data dn;
 		set_new_dnode(&dn, inode, NULL, NULL, new_nid);

fs/f2fs/xattr.h

@@ -126,7 +126,8 @@ extern ssize_t f2fs_listxattr(struct dentry *, char *, size_t);
 
 #define f2fs_xattr_handlers	NULL
 static inline int f2fs_setxattr(struct inode *inode, int index,
-		const char *name, const void *value, size_t size, int flags)
+		const char *name, const void *value, size_t size,
+		struct page *page, int flags)
 {
 	return -EOPNOTSUPP;
 }

include/linux/dcache.h

@@ -228,6 +228,8 @@ struct dentry_operations {
 #define DCACHE_FALLTHRU			0x01000000 /* Fall through to lower layer */
 #define DCACHE_OP_SELECT_INODE		0x02000000 /* Unioned entry: dcache op selects inode */
 
+#define DCACHE_ENCRYPTED_WITH_KEY	0x04000000 /* dir is encrypted with a valid key */
+
 extern seqlock_t rename_lock;
 
 /*

include/linux/f2fs_fs.h

@@ -21,7 +21,7 @@
 #define F2FS_BLKSIZE			4096	/* support only 4KB block */
 #define F2FS_BLKSIZE_BITS		12	/* bits for F2FS_BLKSIZE */
 #define F2FS_MAX_EXTENSION		64	/* # of extension entries */
-#define F2FS_BLK_ALIGN(x)	(((x) + F2FS_BLKSIZE - 1) / F2FS_BLKSIZE)
+#define F2FS_BLK_ALIGN(x)	(((x) + F2FS_BLKSIZE - 1) >> F2FS_BLKSIZE_BITS)
 
 #define NULL_ADDR		((block_t)0)	/* used as block_t addresses */
 #define NEW_ADDR		((block_t)-1)	/* used as block_t addresses */
@@ -170,12 +170,12 @@ struct f2fs_extent {
 #define F2FS_INLINE_XATTR_ADDRS	50	/* 200 bytes for inline xattrs */
 #define DEF_ADDRS_PER_INODE	923	/* Address Pointers in an Inode */
 #define DEF_NIDS_PER_INODE	5	/* Node IDs in an Inode */
-#define ADDRS_PER_INODE(fi)	addrs_per_inode(fi)
+#define ADDRS_PER_INODE(inode)	addrs_per_inode(inode)
 #define ADDRS_PER_BLOCK		1018	/* Address Pointers in a Direct Block */
 #define NIDS_PER_BLOCK		1018	/* Node IDs in an Indirect Block */
 
-#define ADDRS_PER_PAGE(page, fi)	\
+#define ADDRS_PER_PAGE(page, inode)	\
-	(IS_INODE(page) ? ADDRS_PER_INODE(fi) : ADDRS_PER_BLOCK)
+	(IS_INODE(page) ? ADDRS_PER_INODE(inode) : ADDRS_PER_BLOCK)
 
 #define	NODE_DIR1_BLOCK		(DEF_ADDRS_PER_INODE + 1)
 #define	NODE_DIR2_BLOCK		(DEF_ADDRS_PER_INODE + 2)
@@ -345,7 +345,7 @@ struct f2fs_summary {
 
 struct summary_footer {
 	unsigned char entry_type;	/* SUM_TYPE_XXX */
-	__u32 check_sum;		/* summary checksum */
+	__le32 check_sum;		/* summary checksum */
 } __packed;
 
 #define SUM_JOURNAL_SIZE	(F2FS_BLKSIZE - SUM_FOOTER_SIZE -\
@@ -358,6 +358,12 @@ struct summary_footer {
 				sizeof(struct sit_journal_entry))
 #define SIT_JOURNAL_RESERVED	((SUM_JOURNAL_SIZE - 2) %\
 				sizeof(struct sit_journal_entry))
+
+/* Reserved area should make size of f2fs_extra_info equals to
+ * that of nat_journal and sit_journal.
+ */
+#define EXTRA_INFO_RESERVED	(SUM_JOURNAL_SIZE - 2 - 8)
+
 /*
  * frequently updated NAT/SIT entries can be stored in the spare area in
  * summary blocks
@@ -387,18 +393,28 @@ struct sit_journal {
 	__u8 reserved[SIT_JOURNAL_RESERVED];
 } __packed;
 
-/* 4KB-sized summary block structure */
+struct f2fs_extra_info {
-struct f2fs_summary_block {
+	__le64 kbytes_written;
-	struct f2fs_summary entries[ENTRIES_IN_SUM];
+	__u8 reserved[EXTRA_INFO_RESERVED];
+} __packed;
+
+struct f2fs_journal {
 	union {
 		__le16 n_nats;
 		__le16 n_sits;
 	};
-	/* spare area is used by NAT or SIT journals */
+	/* spare area is used by NAT or SIT journals or extra info */
 	union {
 		struct nat_journal nat_j;
 		struct sit_journal sit_j;
+		struct f2fs_extra_info info;
 	};
+} __packed;
+
+/* 4KB-sized summary block structure */
+struct f2fs_summary_block {
+	struct f2fs_summary entries[ENTRIES_IN_SUM];
+	struct f2fs_journal journal;
 	struct summary_footer footer;
 } __packed;
 

include/linux/fs.h

@@ -53,6 +53,8 @@ struct swap_info_struct;
 struct seq_file;
 struct workqueue_struct;
 struct iov_iter;
+struct fscrypt_info;
+struct fscrypt_operations;
 
 extern void __init inode_init(void);
 extern void __init inode_init_early(void);
@@ -679,6 +681,10 @@ struct inode {
 	struct hlist_head	i_fsnotify_marks;
 #endif
 
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+	struct fscrypt_info	*i_crypt_info;
+#endif
+
 	void			*i_private; /* fs or device private pointer */
 };
 
@@ -1324,6 +1330,8 @@ struct super_block {
 #endif
 	const struct xattr_handler **s_xattr;
 
+	const struct fscrypt_operations	*s_cop;
+
 	struct hlist_bl_head	s_anon;		/* anonymous dentries for (nfs) exporting */
 	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
 	struct block_device	*s_bdev;

include/linux/fscrypto.h

@@ -0,0 +1,434 @@
+/*
+ * General per-file encryption definition
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * Written by Michael Halcrow, 2015.
+ * Modified by Jaegeuk Kim, 2015.
+ */
+
+#ifndef _LINUX_FSCRYPTO_H
+#define _LINUX_FSCRYPTO_H
+
+#include <linux/key.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/bio.h>
+#include <linux/dcache.h>
+#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_CTX_REQUIRES_FREE_ENCRYPT_FL		0x00000001
+#define FS_WRITE_PATH_FL			0x00000002
+
+struct fscrypt_ctx {
+	union {
+		struct {
+			struct page *bounce_page;	/* Ciphertext page */
+			struct page *control_page;	/* Original page  */
+		} w;
+		struct {
+			struct bio *bio;
+			struct work_struct work;
+		} r;
+		struct list_head free_list;	/* Free list */
+	};
+	u8 flags;				/* Flags */
+	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 }
+
+static inline int fscrypt_key_size(int mode)
+{
+	switch (mode) {
+	case FS_ENCRYPTION_MODE_AES_256_XTS:
+		return FS_AES_256_XTS_KEY_SIZE;
+	case FS_ENCRYPTION_MODE_AES_256_GCM:
+		return FS_AES_256_GCM_KEY_SIZE;
+	case FS_ENCRYPTION_MODE_AES_256_CBC:
+		return FS_AES_256_CBC_KEY_SIZE;
+	case FS_ENCRYPTION_MODE_AES_256_CTS:
+		return FS_AES_256_CTS_KEY_SIZE;
+	default:
+		BUG();
+	}
+	return 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.
+ */
+struct fscrypt_symlink_data {
+	__le16 len;
+	char encrypted_path[1];
+} __packed;
+
+/**
+ * This function is used to calculate the disk space required to
+ * store a filename of length l in encrypted symlink format.
+ */
+static inline u32 fscrypt_symlink_data_len(u32 l)
+{
+	if (l < FS_CRYPTO_BLOCK_SIZE)
+		l = FS_CRYPTO_BLOCK_SIZE;
+	return (l + sizeof(struct fscrypt_symlink_data) - 1);
+}
+
+struct fscrypt_str {
+	unsigned char *name;
+	u32 len;
+};
+
+struct fscrypt_name {
+	const struct qstr *usr_fname;
+	struct fscrypt_str disk_name;
+	u32 hash;
+	u32 minor_hash;
+	struct fscrypt_str crypto_buf;
+};
+
+#define FSTR_INIT(n, l)		{ .name = n, .len = l }
+#define FSTR_TO_QSTR(f)		QSTR_INIT((f)->name, (f)->len)
+#define fname_name(p)		((p)->disk_name.name)
+#define fname_len(p)		((p)->disk_name.len)
+
+/*
+ * crypto opertions for filesystems
+ */
+struct fscrypt_operations {
+	int (*get_context)(struct inode *, void *, size_t);
+	int (*prepare_context)(struct inode *);
+	int (*set_context)(struct inode *, const void *, size_t, void *);
+	int (*dummy_context)(struct inode *);
+	bool (*is_encrypted)(struct inode *);
+	bool (*empty_dir)(struct inode *);
+	unsigned (*max_namelen)(struct inode *);
+};
+
+static inline bool fscrypt_dummy_context_enabled(struct inode *inode)
+{
+	if (inode->i_sb->s_cop->dummy_context &&
+				inode->i_sb->s_cop->dummy_context(inode))
+		return true;
+	return false;
+}
+
+static inline bool fscrypt_valid_contents_enc_mode(u32 mode)
+{
+	return (mode == FS_ENCRYPTION_MODE_AES_256_XTS);
+}
+
+static inline bool fscrypt_valid_filenames_enc_mode(u32 mode)
+{
+	return (mode == FS_ENCRYPTION_MODE_AES_256_CTS);
+}
+
+static inline u32 fscrypt_validate_encryption_key_size(u32 mode, u32 size)
+{
+	if (size == fscrypt_key_size(mode))
+		return size;
+	return 0;
+}
+
+static inline bool fscrypt_is_dot_dotdot(const struct qstr *str)
+{
+	if (str->len == 1 && str->name[0] == '.')
+		return true;
+
+	if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.')
+		return true;
+
+	return false;
+}
+
+static inline struct page *fscrypt_control_page(struct page *page)
+{
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+	return ((struct fscrypt_ctx *)page_private(page))->w.control_page;
+#else
+	WARN_ON_ONCE(1);
+	return ERR_PTR(-EINVAL);
+#endif
+}
+
+static inline int fscrypt_has_encryption_key(struct inode *inode)
+{
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+	return (inode->i_crypt_info != NULL);
+#else
+	return 0;
+#endif
+}
+
+static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry)
+{
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+	spin_lock(&dentry->d_lock);
+	dentry->d_flags |= DCACHE_ENCRYPTED_WITH_KEY;
+	spin_unlock(&dentry->d_lock);
+#endif
+}
+
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+extern const struct dentry_operations fscrypt_d_ops;
+#endif
+
+static inline void fscrypt_set_d_op(struct dentry *dentry)
+{
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+	d_set_d_op(dentry, &fscrypt_d_ops);
+#endif
+}
+
+#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 *);
+extern void fscrypt_release_ctx(struct fscrypt_ctx *);
+extern struct page *fscrypt_encrypt_page(struct inode *, struct page *);
+extern int fscrypt_decrypt_page(struct page *);
+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,
+						unsigned int);
+/* policy.c */
+extern int fscrypt_process_policy(struct inode *,
+					const struct fscrypt_policy *);
+extern int fscrypt_get_policy(struct inode *, struct fscrypt_policy *);
+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 *);
+
+/* fname.c */
+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,
+				struct fscrypt_str *);
+extern void fscrypt_fname_free_buffer(struct fscrypt_str *);
+extern int fscrypt_fname_disk_to_usr(struct inode *, u32, u32,
+			const struct fscrypt_str *, struct fscrypt_str *);
+extern int fscrypt_fname_usr_to_disk(struct inode *, const struct qstr *,
+			struct fscrypt_str *);
+#endif
+
+/* crypto.c */
+static inline struct fscrypt_ctx *fscrypt_notsupp_get_ctx(struct inode *i)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+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)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline int fscrypt_notsupp_decrypt_page(struct page *p)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void fscrypt_notsupp_decrypt_bio_pages(struct fscrypt_ctx *c,
+						struct bio *b)
+{
+	return;
+}
+
+static inline void fscrypt_notsupp_pullback_bio_page(struct page **p, bool b)
+{
+	return;
+}
+
+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,
+					sector_t s, unsigned int f)
+{
+	return -EOPNOTSUPP;
+}
+
+/* policy.c */
+static inline int fscrypt_notsupp_process_policy(struct inode *i,
+				const struct fscrypt_policy *p)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int fscrypt_notsupp_get_policy(struct inode *i,
+				struct fscrypt_policy *p)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int fscrypt_notsupp_has_permitted_context(struct inode *p,
+				struct inode *i)
+{
+	return 0;
+}
+
+static inline int fscrypt_notsupp_inherit_context(struct inode *p,
+				struct inode *i, void *v, bool b)
+{
+	return -EOPNOTSUPP;
+}
+
+/* keyinfo.c */
+static inline int fscrypt_notsupp_get_encryption_info(struct inode *i)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void fscrypt_notsupp_put_encryption_info(struct inode *i,
+					struct fscrypt_info *f)
+{
+	return;
+}
+
+ /* fname.c */
+static inline int fscrypt_notsupp_setup_filename(struct inode *dir,
+			const struct qstr *iname,
+			int lookup, struct fscrypt_name *fname)
+{
+	if (dir->i_sb->s_cop->is_encrypted(dir))
+		return -EOPNOTSUPP;
+
+	memset(fname, 0, sizeof(struct fscrypt_name));
+	fname->usr_fname = iname;
+	fname->disk_name.name = (unsigned char *)iname->name;
+	fname->disk_name.len = iname->len;
+	return 0;
+}
+
+static inline void fscrypt_notsupp_free_filename(struct fscrypt_name *fname)
+{
+	return;
+}
+
+static inline u32 fscrypt_notsupp_fname_encrypted_size(struct inode *i, u32 s)
+{
+	/* never happens */
+	WARN_ON(1);
+	return 0;
+}
+
+static inline int fscrypt_notsupp_fname_alloc_buffer(struct inode *inode,
+				u32 ilen, struct fscrypt_str *crypto_str)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void fscrypt_notsupp_fname_free_buffer(struct fscrypt_str *c)
+{
+	return;
+}
+
+static inline int fscrypt_notsupp_fname_disk_to_usr(struct inode *inode,
+			u32 hash, u32 minor_hash,
+			const struct fscrypt_str *iname,
+			struct fscrypt_str *oname)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int fscrypt_notsupp_fname_usr_to_disk(struct inode *inode,
+			const struct qstr *iname,
+			struct fscrypt_str *oname)
+{
+	return -EOPNOTSUPP;
+}
+#endif	/* _LINUX_FSCRYPTO_H */

include/trace/events/f2fs.h

@@ -52,6 +52,7 @@ TRACE_DEFINE_ENUM(CP_DISCARD);
 		{ META_FLUSH,	"META_FLUSH" },				\
 		{ INMEM,	"INMEM" },				\
 		{ INMEM_DROP,	"INMEM_DROP" },				\
+		{ INMEM_REVOKE,	"INMEM_REVOKE" },			\
 		{ IPU,		"IN-PLACE" },				\
 		{ OPU,		"OUT-OF-PLACE" })
 
@@ -727,7 +728,8 @@ DECLARE_EVENT_CLASS(f2fs__submit_page_bio,
 		__field(dev_t, dev)
 		__field(ino_t, ino)
 		__field(pgoff_t, index)
-		__field(block_t, blkaddr)
+		__field(block_t, old_blkaddr)
+		__field(block_t, new_blkaddr)
 		__field(int, rw)
 		__field(int, type)
 	),
@@ -736,16 +738,18 @@ DECLARE_EVENT_CLASS(f2fs__submit_page_bio,
 		__entry->dev		= page->mapping->host->i_sb->s_dev;
 		__entry->ino		= page->mapping->host->i_ino;
 		__entry->index		= page->index;
-		__entry->blkaddr	= fio->blk_addr;
+		__entry->old_blkaddr	= fio->old_blkaddr;
+		__entry->new_blkaddr	= fio->new_blkaddr;
 		__entry->rw		= fio->rw;
 		__entry->type		= fio->type;
 	),
 
 	TP_printk("dev = (%d,%d), ino = %lu, page_index = 0x%lx, "
-		"blkaddr = 0x%llx, rw = %s%s, type = %s",
+		"oldaddr = 0x%llx, newaddr = 0x%llx rw = %s%s, type = %s",
 		show_dev_ino(__entry),
 		(unsigned long)__entry->index,
-		(unsigned long long)__entry->blkaddr,
+		(unsigned long long)__entry->old_blkaddr,
+		(unsigned long long)__entry->new_blkaddr,
 		show_bio_type(__entry->rw),
 		show_block_type(__entry->type))
 );

include/uapi/linux/fs.h

@@ -246,6 +246,24 @@ struct fsxattr {
 #define FS_IOC_FSGETXATTR		_IOR ('X', 31, struct fsxattr)
 #define FS_IOC_FSSETXATTR		_IOW ('X', 32, struct fsxattr)
 
+/*
+ * File system encryption support
+ */
+/* Policy provided via an ioctl on the topmost directory */
+#define FS_KEY_DESCRIPTOR_SIZE	8
+
+struct fscrypt_policy {
+	__u8 version;
+	__u8 contents_encryption_mode;
+	__u8 filenames_encryption_mode;
+	__u8 flags;
+	__u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
+} __packed;
+
+#define FS_IOC_SET_ENCRYPTION_POLICY	_IOR('f', 19, struct fscrypt_policy)
+#define FS_IOC_GET_ENCRYPTION_PWSALT	_IOW('f', 20, __u8[16])
+#define FS_IOC_GET_ENCRYPTION_POLICY	_IOW('f', 21, struct fscrypt_policy)
+
 /*
  * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
  *