f2fs: backport from (4c1fad64 - Merge tag 'for-f2fs-4.9' of git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs)

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

Documentation/filesystems/f2fs.txt

@@ -102,14 +102,16 @@ background_gc=%s       Turn on/off cleaning operations, namely garbage
                        collection, triggered in background when I/O subsystem is
                        idle. If background_gc=on, it will turn on the garbage
                        collection and if background_gc=off, garbage collection
-                       will be truned off. If background_gc=sync, it will turn
+                       will be turned off. If background_gc=sync, it will turn
                        on synchronous garbage collection running in background.
                        Default value for this option is on. So garbage
                        collection is on by default.
 disable_roll_forward   Disable the roll-forward recovery routine
 norecovery             Disable the roll-forward recovery routine, mounted read-
                        only (i.e., -o ro,disable_roll_forward)
-discard                Issue discard/TRIM commands when a segment is cleaned.
+discard/nodiscard      Enable/disable real-time discard in f2fs, if discard is
+                       enabled, f2fs will issue discard/TRIM commands when a
+		       segment is cleaned.
 no_heap                Disable heap-style segment allocation which finds free
                        segments for data from the beginning of main area, while
 		       for node from the end of main area.
@@ -129,6 +131,7 @@ inline_dentry          Enable the inline dir feature: data in new created
                        directory entries can be written into inode block. The
                        space of inode block which is used to store inline
                        dentries is limited to ~3.4k.
+noinline_dentry        Diable the inline dentry feature.
 flush_merge	       Merge concurrent cache_flush commands as much as possible
                        to eliminate redundant command issues. If the underlying
 		       device handles the cache_flush command relatively slowly,
@@ -145,10 +148,15 @@ extent_cache           Enable an extent cache based on rb-tree, it can cache
                        as many as extent which map between contiguous logical
                        address and physical address per inode, resulting in
                        increasing the cache hit ratio. Set by default.
-noextent_cache         Diable an extent cache based on rb-tree explicitly, see
+noextent_cache         Disable an extent cache based on rb-tree explicitly, see
                        the above extent_cache mount option.
 noinline_data          Disable the inline data feature, inline data feature is
                        enabled by default.
+data_flush             Enable data flushing before checkpoint in order to
+                       persist data of regular and symlink.
+mode=%s                Control block allocation mode which supports "adaptive"
+                       and "lfs". In "lfs" mode, there should be no random
+                       writes towards main area.
 
 ================================================================================
 DEBUGFS ENTRIES
@@ -192,7 +200,7 @@ Files in /sys/fs/f2fs/<devname>
                               policy for garbage collection. Setting gc_idle = 0
                               (default) will disable this option. Setting
                               gc_idle = 1 will select the Cost Benefit approach
-                              & setting gc_idle = 2 will select the greedy aproach.
+                              & setting gc_idle = 2 will select the greedy approach.
 
  reclaim_segments             This parameter controls the number of prefree
                               segments to be reclaimed. If the number of prefree
@@ -298,7 +306,7 @@ The dump.f2fs shows the information of specific inode and dumps SSA and SIT to
 file. Each file is dump_ssa and dump_sit.
 
 The dump.f2fs is used to debug on-disk data structures of the f2fs filesystem.
-It shows on-disk inode information reconized by a given inode number, and is
+It shows on-disk inode information recognized by a given inode number, and is
 able to dump all the SSA and SIT entries into predefined files, ./dump_ssa and
 ./dump_sit respectively.
 

fs/Kconfig

@@ -73,6 +73,8 @@ config FILE_LOCKING
           for filesystems like NFS and for the flock() system
           call. Disabling this option saves about 11k.
 
+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 +1,568 @@
+/*
+ * 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/namei.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
+ * @gfp_flags:   The gfp flag for memory allocation
+ *
+ * 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, gfp_t gfp_flags)
+{
+	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_flags);
+		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,
+			gfp_t gfp_flags)
+{
+	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_flags);
+	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, &index, 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_SIZE, 0);
+	sg_init_table(&src, 1);
+	sg_set_page(&src, src_page, PAGE_SIZE, 0);
+	skcipher_request_set_crypt(req, &src, &dst, PAGE_SIZE,
+					xts_tweak);
+	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, gfp_t gfp_flags)
+{
+	ctx->w.bounce_page = mempool_alloc(fscrypt_bounce_page_pool, gfp_flags);
+	if (ctx->w.bounce_page == NULL)
+		return ERR_PTR(-ENOMEM);
+	ctx->flags |= FS_WRITE_PATH_FL;
+	return ctx->w.bounce_page;
+}
+
+/**
+ * fscypt_encrypt_page() - Encrypts a page
+ * @inode:          The inode for which the encryption should take place
+ * @plaintext_page: The page to encrypt. Must be locked.
+ * @gfp_flags:      The gfp flag for memory allocation
+ *
+ * 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, gfp_t gfp_flags)
+{
+	struct fscrypt_ctx *ctx;
+	struct page *ciphertext_page = NULL;
+	int err;
+
+	BUG_ON(!PageLocked(plaintext_page));
+
+	ctx = fscrypt_get_ctx(inode, gfp_flags);
+	if (IS_ERR(ctx))
+		return (struct page *)ctx;
+
+	/* The encryption operation will require a bounce page. */
+	ciphertext_page = alloc_bounce_page(ctx, gfp_flags);
+	if (IS_ERR(ciphertext_page))
+		goto errout;
+
+	ctx->w.control_page = plaintext_page;
+	err = do_page_crypto(inode, FS_ENCRYPT, plaintext_page->index,
+					plaintext_page, ciphertext_page,
+					gfp_flags);
+	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, GFP_NOFS);
+}
+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_SIZE);
+
+	ctx = fscrypt_get_ctx(inode, GFP_NOFS);
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
+
+	ciphertext_page = alloc_bounce_page(ctx, GFP_NOWAIT);
+	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,
+					GFP_NOFS);
+		if (err)
+			goto errout;
+
+		bio = bio_alloc(GFP_NOWAIT, 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 dentry *dir;
+	struct fscrypt_info *ci;
+	int dir_has_key, cached_with_key;
+
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	dir = dget_parent(dentry);
+	if (!d_inode(dir)->i_sb->s_cop->is_encrypted(d_inode(dir))) {
+		dput(dir);
+		return 0;
+	}
+
+	ci = d_inode(dir)->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))))
+		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);
+	dput(dir);
+
+	/*
+	 * 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

@@ -1,46 +1,32 @@
 /*
- * linux/fs/f2fs/crypto_fname.c
- *
- * Copied from linux/fs/ext4/crypto.c
+ * This contains functions for filename crypto management
  *
  * Copyright (C) 2015, Google, Inc.
  * Copyright (C) 2015, Motorola Mobility
  *
- * This contains functions for filename crypto management in f2fs
- *
  * Written by Uday Savagaonkar, 2014.
- *
- * Adjust f2fs dentry structure
- *	Jaegeuk Kim, 2015.
+ * Modified by Jaegeuk Kim, 2015.
  *
  * This has not yet undergone a rigorous security audit.
  */
-#include <crypto/hash.h>
-#include <crypto/sha.h>
+
 #include <keys/encrypted-type.h>
 #include <keys/user-type.h>
-#include <linux/crypto.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"
-#include "f2fs_crypto.h"
-#include "xattr.h"
+static u32 size_round_up(size_t size, size_t blksize)
+{
+	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;
@@ -48,45 +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,
-			const struct qstr *iname, struct f2fs_str *oname)
+static int fname_encrypt(struct inode *inode,
+			const struct qstr *iname, struct fscrypt_str *oname)
 {
 	u32 ciphertext_len;
-	struct ablkcipher_request *req = NULL;
-	DECLARE_F2FS_COMPLETION_RESULT(ecr);
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
-	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+	struct skcipher_request *req = NULL;
+	DECLARE_FS_COMPLETION_RESULT(ecr);
+	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) ?
-		F2FS_CRYPTO_BLOCK_SIZE : iname->len;
-	ciphertext_len = f2fs_fname_crypto_round_up(ciphertext_len, padding);
+	ciphertext_len = (iname->len < FS_CRYPTO_BLOCK_SIZE) ?
+					FS_CRYPTO_BLOCK_SIZE : iname->len;
+	ciphertext_len = size_round_up(ciphertext_len, padding);
 	ciphertext_len = (ciphertext_len > lim) ? lim : ciphertext_len;
 
 	if (ciphertext_len <= sizeof(buf)) {
@@ -99,16 +75,16 @@ static int f2fs_fname_encrypt(struct inode *inode,
 	}
 
 	/* Allocate request */
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
 	if (!req) {
 		printk_ratelimited(KERN_ERR
 			"%s: crypto_request_alloc() failed\n", __func__);
 		kfree(alloc_buf);
 		return -ENOMEM;
 	}
-	ablkcipher_request_set_callback(req,
+	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);
@@ -116,79 +92,78 @@ 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);
 	sg_init_one(&dst_sg, oname->name, ciphertext_len);
-	ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv);
-	res = crypto_ablkcipher_encrypt(req);
+	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);
-	ablkcipher_request_free(req);
-	if (res < 0) {
+	skcipher_request_free(req);
+	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,
-			const struct f2fs_str *iname, struct f2fs_str *oname)
+static int fname_decrypt(struct inode *inode,
+				const struct fscrypt_str *iname,
+				struct fscrypt_str *oname)
 {
-	struct ablkcipher_request *req = NULL;
-	DECLARE_F2FS_COMPLETION_RESULT(ecr);
+	struct skcipher_request *req = NULL;
+	DECLARE_FS_COMPLETION_RESULT(ecr);
 	struct scatterlist src_sg, dst_sg;
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
-	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+	struct fscrypt_info *ci = inode->i_crypt_info;
+	struct crypto_skcipher *tfm = ci->ci_ctfm;
 	int res = 0;
-	char iv[F2FS_CRYPTO_BLOCK_SIZE];
-	unsigned lim = max_name_len(inode);
+	char iv[FS_CRYPTO_BLOCK_SIZE];
+	unsigned lim;
 
+	lim = inode->i_sb->s_cop->max_namelen(inode);
 	if (iname->len <= 0 || iname->len > lim)
 		return -EIO;
 
 	/* Allocate request */
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
 	if (!req) {
 		printk_ratelimited(KERN_ERR
 			"%s: crypto_request_alloc() failed\n",  __func__);
 		return -ENOMEM;
 	}
-	ablkcipher_request_set_callback(req,
+	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);
 	sg_init_one(&dst_sg, oname->name, oname->len);
-	ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, iv);
-	res = crypto_ablkcipher_decrypt(req);
+	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;
 	}
-	ablkcipher_request_free(req);
+	skcipher_request_free(req);
 	if (res < 0) {
 		printk_ratelimited(KERN_ERR
-			"%s: Error in f2fs_fname_decrypt (error code %d)\n",
-			__func__, res);
+				"%s: Error (error code %d)\n", __func__, res);
 		return res;
 	}
 
@@ -200,7 +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.
@@ -249,148 +224,152 @@ static int digest_decode(const char *src, int len, char *dst)
 	return cp - dst;
 }
 
-/**
- * f2fs_fname_crypto_round_up() -
- *
- * Return: The next multiple of block size
- */
-u32 f2fs_fname_crypto_round_up(u32 size, u32 blksize)
+u32 fscrypt_fname_encrypted_size(struct inode *inode, u32 ilen)
 {
-	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,
-				   u32 ilen, struct f2fs_str *crypto_str)
+int fscrypt_fname_alloc_buffer(struct inode *inode,
+				u32 ilen, struct fscrypt_str *crypto_str)
 {
-	unsigned int olen;
-	int padding = 16;
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
+	unsigned int olen = fscrypt_fname_encrypted_size(inode, ilen);
 
-	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)
-		olen = F2FS_FNAME_CRYPTO_DIGEST_SIZE * 2;
-	/* Allocated buffer can hold one more character to null-terminate the
-	 * string */
+	if (olen < FS_FNAME_CRYPTO_DIGEST_SIZE * 2)
+		olen = FS_FNAME_CRYPTO_DIGEST_SIZE * 2;
+	/*
+	 * 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,
-			f2fs_hash_t *hash,
-			const struct f2fs_str *iname,
-			struct f2fs_str *oname)
+int fscrypt_fname_disk_to_usr(struct inode *inode,
+			u32 hash, u32 minor_hash,
+			const struct fscrypt_str *iname,
+			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)
-		return f2fs_fname_decrypt(inode, iname, oname);
+	if (iname->len < FS_CRYPTO_BLOCK_SIZE)
+		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);
-		memset(buf + 4, 0, 4);
-	} else
+		memcpy(buf, &hash, 4);
+		memcpy(buf + 4, &minor_hash, 4);
+	} else {
 		memset(buf, 0, 8);
-	memcpy(buf + 8, iname->name + ((iname->len - 17) & ~15), 16);
+	}
+	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;
-	struct f2fs_crypt_info *ci = F2FS_I(inode)->i_crypt_info;
-
-	if (is_dot_dotdot(iname)) {
+	if (fscrypt_is_dot_dotdot(iname)) {
 		oname->name[0] = '.';
 		oname->name[iname->len - 1] = '.';
 		oname->len = iname->len;
 		return oname->len;
 	}
-
-	if (ci) {
-		res = f2fs_fname_encrypt(inode, iname, oname);
-		return res;
-	}
-	/* Without a proper key, a user is not allowed to modify the filenames
+	if (inode->i_crypt_info)
+		return fname_encrypt(inode, iname, oname);
+	/*
+	 * 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 lookup, struct f2fs_filename *fname)
+int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
+			      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);
-	if (ret)
+	ret = get_crypt_info(dir);
+	if (ret && ret != -EOPNOTSUPP)
 		return ret;
-	ci = F2FS_I(dir)->i_crypt_info;
-	if (ci) {
-		ret = f2fs_fname_crypto_alloc_buffer(dir, iname->len,
-						     &fname->crypto_buf);
+
+	if (dir->i_crypt_info) {
+		ret = fscrypt_fname_alloc_buffer(dir, iname->len,
+							&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;
@@ -400,18 +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)) ||
-	    (!bigname && (iname->len > 43)))
+	if ((bigname && (iname->len != 33)) || (!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) {
@@ -421,20 +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 +1,304 @@
+/*
+ * 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 int validate_user_key(struct fscrypt_info *crypt_info,
+			struct fscrypt_context *ctx, u8 *raw_key,
+			u8 *prefix, int prefix_size)
+{
+	u8 *full_key_descriptor;
+	struct key *keyring_key;
+	struct fscrypt_key *master_key;
+	const struct user_key_payload *ukp;
+	int full_key_len = prefix_size + (FS_KEY_DESCRIPTOR_SIZE * 2) + 1;
+	int res;
+
+	full_key_descriptor = kmalloc(full_key_len, GFP_NOFS);
+	if (!full_key_descriptor)
+		return -ENOMEM;
+
+	memcpy(full_key_descriptor, prefix, prefix_size);
+	sprintf(full_key_descriptor + prefix_size,
+			"%*phN", FS_KEY_DESCRIPTOR_SIZE,
+			ctx->master_key_descriptor);
+	full_key_descriptor[full_key_len - 1] = '\0';
+	keyring_key = request_key(&key_type_logon, full_key_descriptor, NULL);
+	kfree(full_key_descriptor);
+	if (IS_ERR(keyring_key))
+		return PTR_ERR(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;
+
+	crypt_info->ci_keyring_key = keyring_key;
+	return 0;
+out:
+	key_put(keyring_key);
+	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;
+	struct fscrypt_context ctx;
+	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;
+	}
+
+	res = validate_user_key(crypt_info, &ctx, raw_key,
+			FS_KEY_DESC_PREFIX, FS_KEY_DESC_PREFIX_SIZE);
+	if (res && inode->i_sb->s_cop->key_prefix) {
+		u8 *prefix = NULL;
+		int prefix_size, res2;
+
+		prefix_size = inode->i_sb->s_cop->key_prefix(inode, &prefix);
+		res2 = validate_user_key(crypt_info, &ctx, raw_key,
+							prefix, prefix_size);
+		if (res2) {
+			if (res2 == -ENOKEY)
+				res = -ENOKEY;
+			goto out;
+		}
+	} else 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 +1,246 @@
+/*
+ * 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>
+#include <linux/mount.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 file *filp,
+				const struct fscrypt_policy *policy)
+{
+	struct inode *inode = file_inode(filp);
+	int ret;
+
+	if (!inode_owner_or_capable(inode))
+		return -EACCES;
+
+	if (policy->version != 0)
+		return -EINVAL;
+
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
+
+	if (!inode_has_encryption_context(inode)) {
+		if (!S_ISDIR(inode->i_mode))
+			ret = -EINVAL;
+		else if (!inode->i_sb->s_cop->empty_dir)
+			ret = -EOPNOTSUPP;
+		else if (!inode->i_sb->s_cop->empty_dir(inode))
+			ret = -ENOTEMPTY;
+		else
+			ret = create_encryption_context_from_policy(inode,
+								    policy);
+	} else if (!is_encryption_context_consistent_with_policy(inode,
+								 policy)) {
+		printk(KERN_WARNING
+		       "%s: Policy inconsistent with encryption context\n",
+		       __func__);
+		ret = -EINVAL;
+	}
+
+	mnt_drop_write_file(filp);
+	return ret;
+}
+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 +1,9 @@
 config F2FS_FS
 	tristate "F2FS filesystem support"
 	depends on BLOCK
+	select CRYPTO
+	select KEYS
+	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 +79,7 @@ config F2FS_FS_ENCRYPTION
 	bool "F2FS Encryption"
 	depends on F2FS_FS
 	depends on F2FS_FS_XATTR
-	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
+	select FS_ENCRYPTION
 	help
 	  Enable encryption of f2fs files and directories.  This
 	  feature is similar to ecryptfs, but it is more memory
@@ -100,3 +95,11 @@ config F2FS_IO_TRACE
 	  information and block IO patterns in the filesystem level.
 
 	  If unsure, say N.
+
+config F2FS_FAULT_INJECTION
+	bool "F2FS fault injection facility"
+	depends on F2FS_FS
+	help
+	  Test F2FS to inject faults such as ENOMEM, ENOSPC, and so on.
+
+	  If unsure, say N.

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/acl.c

@@ -109,14 +109,16 @@ fail:
 	return ERR_PTR(-EINVAL);
 }
 
-static void *f2fs_acl_to_disk(const struct posix_acl *acl, size_t *size)
+static void *f2fs_acl_to_disk(struct f2fs_sb_info *sbi,
+				const struct posix_acl *acl, size_t *size)
 {
 	struct f2fs_acl_header *f2fs_acl;
 	struct f2fs_acl_entry *entry;
 	int i;
 
-	f2fs_acl = kmalloc(sizeof(struct f2fs_acl_header) + acl->a_count *
-			sizeof(struct f2fs_acl_entry), GFP_NOFS);
+	f2fs_acl = f2fs_kmalloc(sbi, sizeof(struct f2fs_acl_header) +
+			acl->a_count * sizeof(struct f2fs_acl_entry),
+			GFP_NOFS);
 	if (!f2fs_acl)
 		return ERR_PTR(-ENOMEM);
 
@@ -175,7 +177,7 @@ static struct posix_acl *__f2fs_get_acl(struct inode *inode, int type,
 
 	retval = f2fs_getxattr(inode, name_index, "", NULL, 0, dpage);
 	if (retval > 0) {
-		value = kmalloc(retval, GFP_F2FS_ZERO);
+		value = f2fs_kmalloc(F2FS_I_SB(inode), retval, GFP_F2FS_ZERO);
 		if (!value)
 			return ERR_PTR(-ENOMEM);
 		retval = f2fs_getxattr(inode, name_index, "", value,
@@ -204,7 +206,6 @@ struct posix_acl *f2fs_get_acl(struct inode *inode, int type)
 static int __f2fs_set_acl(struct inode *inode, int type,
 			struct posix_acl *acl, struct page *ipage)
 {
-	struct f2fs_inode_info *fi = F2FS_I(inode);
 	int name_index;
 	void *value = NULL;
 	size_t size = 0;
@@ -213,11 +214,13 @@ static int __f2fs_set_acl(struct inode *inode, int type,
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS;
-		if (acl && !ipage) {
-			error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
-			if (error)
+		if (acl) {
+			error = posix_acl_equiv_mode(acl, &inode->i_mode);
+			if (error < 0)
 				return error;
-			set_acl_inode(fi, inode->i_mode);
+			set_acl_inode(inode, inode->i_mode);
+			if (error == 0)
+				acl = NULL;
 		}
 		break;
 
@@ -232,9 +235,9 @@ static int __f2fs_set_acl(struct inode *inode, int type,
 	}
 
 	if (acl) {
-		value = f2fs_acl_to_disk(acl, &size);
+		value = f2fs_acl_to_disk(F2FS_I_SB(inode), acl, &size);
 		if (IS_ERR(value)) {
-			clear_inode_flag(fi, FI_ACL_MODE);
+			clear_inode_flag(inode, FI_ACL_MODE);
 			return (int)PTR_ERR(value);
 		}
 	}
@@ -245,7 +248,7 @@ static int __f2fs_set_acl(struct inode *inode, int type,
 	if (!error)
 		set_cached_acl(inode, type, acl);
 
-	clear_inode_flag(fi, FI_ACL_MODE);
+	clear_inode_flag(inode, FI_ACL_MODE);
 	return error;
 }
 
@@ -386,6 +389,8 @@ int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage,
 	if (error)
 		return error;
 
+	f2fs_mark_inode_dirty_sync(inode);
+
 	if (default_acl) {
 		error = __f2fs_set_acl(inode, ACL_TYPE_DEFAULT, default_acl,
 				       ipage);

fs/f2fs/acl.h

@@ -37,11 +37,10 @@ struct f2fs_acl_header {
 #ifdef CONFIG_F2FS_FS_POSIX_ACL
 
 extern struct posix_acl *f2fs_get_acl(struct inode *, int);
-extern int f2fs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+extern int f2fs_set_acl(struct inode *, struct posix_acl *, int);
 extern int f2fs_init_acl(struct inode *, struct inode *, struct page *,
 							struct page *);
 #else
-#define f2fs_check_acl	NULL
 #define f2fs_get_acl	NULL
 #define f2fs_set_acl	NULL
 

fs/f2fs/checkpoint.c

@@ -26,6 +26,14 @@
 static struct kmem_cache *ino_entry_slab;
 struct kmem_cache *inode_entry_slab;
 
+void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io)
+{
+	set_ckpt_flags(sbi, CP_ERROR_FLAG);
+	sbi->sb->s_flags |= MS_RDONLY;
+	if (!end_io)
+		f2fs_flush_merged_bios(sbi);
+}
+
 /*
  * We guarantee no failure on the returned page.
  */
@@ -34,13 +42,14 @@ struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
 	struct address_space *mapping = META_MAPPING(sbi);
 	struct page *page = NULL;
 repeat:
-	page = grab_cache_page(mapping, index);
+	page = f2fs_grab_cache_page(mapping, index, false);
 	if (!page) {
 		cond_resched();
 		goto repeat;
 	}
-	f2fs_wait_on_page_writeback(page, META);
-	SetPageUptodate(page);
+	f2fs_wait_on_page_writeback(page, META, true);
+	if (!PageUptodate(page))
+		SetPageUptodate(page);
 	return page;
 }
 
@@ -56,14 +65,15 @@ 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,
 	};
 
 	if (unlikely(!is_meta))
 		fio.rw &= ~REQ_META;
 repeat:
-	page = grab_cache_page(mapping, index);
+	page = f2fs_grab_cache_page(mapping, index, false);
 	if (!page) {
 		cond_resched();
 		goto repeat;
@@ -90,7 +100,7 @@ repeat:
 	 * meta page.
 	 */
 	if (unlikely(!PageUptodate(page)))
-		f2fs_stop_checkpoint(sbi);
+		f2fs_stop_checkpoint(sbi, false);
 out:
 	return page;
 }
@@ -143,7 +153,6 @@ 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 +161,12 @@ 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 +178,25 @@ 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 = f2fs_grab_cache_page(META_MAPPING(sbi),
+						fio.new_blkaddr, false);
 		if (!page)
 			continue;
 		if (PageUptodate(page)) {
@@ -196,11 +205,13 @@ 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;
 }
 
@@ -210,7 +221,7 @@ void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index)
 	bool readahead = false;
 
 	page = find_get_page(META_MAPPING(sbi), index);
-	if (!page || (page && !PageUptodate(page)))
+	if (!page || !PageUptodate(page))
 		readahead = true;
 	f2fs_put_page(page, 0);
 
@@ -232,13 +243,17 @@ 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);
-	unlock_page(page);
 
 	if (wbc->for_reclaim)
+		f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, META, WRITE);
+
+	unlock_page(page);
+
+	if (unlikely(f2fs_cp_error(sbi)))
 		f2fs_submit_merged_bio(sbi, META, WRITE);
+
 	return 0;
 
 redirty_out:
@@ -252,13 +267,13 @@ 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 +284,7 @@ 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 +292,18 @@ 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 +315,7 @@ 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 +334,9 @@ 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 +356,8 @@ stop:
 	if (nwritten)
 		f2fs_submit_merged_bio(sbi, type, WRITE);
 
+	blk_finish_plug(&plug);
+
 	return nwritten;
 }
 
@@ -341,9 +365,10 @@ static int f2fs_set_meta_page_dirty(struct page *page)
 {
 	trace_f2fs_set_page_dirty(page, META);
 
-	SetPageUptodate(page);
+	if (!PageUptodate(page))
+		SetPageUptodate(page);
 	if (!PageDirty(page)) {
-		__set_page_dirty_nobuffers(page);
+		f2fs_set_page_dirty_nobuffers(page);
 		inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META);
 		SetPagePrivate(page);
 		f2fs_trace_pid(page);
@@ -358,6 +383,9 @@ const struct address_space_operations f2fs_meta_aops = {
 	.set_page_dirty	= f2fs_set_meta_page_dirty,
 	.invalidatepage = f2fs_invalidate_page,
 	.releasepage	= f2fs_release_page,
+#ifdef CONFIG_MIGRATION
+	.migratepage    = f2fs_migrate_page,
+#endif
 };
 
 static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
@@ -410,13 +438,13 @@ static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
 	spin_unlock(&im->ino_lock);
 }
 
-void add_dirty_inode(struct f2fs_sb_info *sbi, nid_t ino, int type)
+void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
 {
 	/* add new dirty ino entry into list */
 	__add_ino_entry(sbi, ino, type);
 }
 
-void remove_dirty_inode(struct f2fs_sb_info *sbi, nid_t ino, int type)
+void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
 {
 	/* remove dirty ino entry from list */
 	__remove_ino_entry(sbi, ino, type);
@@ -434,12 +462,12 @@ bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode)
 	return e ? true : false;
 }
 
-void release_dirty_inode(struct f2fs_sb_info *sbi)
+void release_ino_entry(struct f2fs_sb_info *sbi, bool all)
 {
 	struct ino_entry *e, *tmp;
 	int i;
 
-	for (i = APPEND_INO; i <= UPDATE_INO; i++) {
+	for (i = all ? ORPHAN_INO: APPEND_INO; i <= UPDATE_INO; i++) {
 		struct inode_management *im = &sbi->im[i];
 
 		spin_lock(&im->ino_lock);
@@ -459,6 +487,13 @@ int acquire_orphan_inode(struct f2fs_sb_info *sbi)
 	int err = 0;
 
 	spin_lock(&im->ino_lock);
+
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	if (time_to_inject(sbi, FAULT_ORPHAN)) {
+		spin_unlock(&im->ino_lock);
+		return -ENOSPC;
+	}
+#endif
 	if (unlikely(im->ino_num >= sbi->max_orphans))
 		err = -ENOSPC;
 	else
@@ -478,10 +513,11 @@ void release_orphan_inode(struct f2fs_sb_info *sbi)
 	spin_unlock(&im->ino_lock);
 }
 
-void add_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
+void add_orphan_inode(struct inode *inode)
 {
 	/* add new orphan ino entry into list */
-	__add_ino_entry(sbi, ino, ORPHAN_INO);
+	__add_ino_entry(F2FS_I_SB(inode), inode->i_ino, ORPHAN_INO);
+	update_inode_page(inode);
 }
 
 void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
@@ -493,8 +529,20 @@ void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
 static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
 {
 	struct inode *inode;
+	struct node_info ni;
+	int err = acquire_orphan_inode(sbi);
 
-	inode = f2fs_iget(sbi->sb, ino);
+	if (err) {
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+		f2fs_msg(sbi->sb, KERN_WARNING,
+				"%s: orphan failed (ino=%x), run fsck to fix.",
+				__func__, ino);
+		return err;
+	}
+
+	__add_ino_entry(sbi, ino, ORPHAN_INO);
+
+	inode = f2fs_iget_retry(sbi->sb, ino);
 	if (IS_ERR(inode)) {
 		/*
 		 * there should be a bug that we can't find the entry
@@ -508,6 +556,18 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
 
 	/* truncate all the data during iput */
 	iput(inode);
+
+	get_node_info(sbi, ino, &ni);
+
+	/* ENOMEM was fully retried in f2fs_evict_inode. */
+	if (ni.blk_addr != NULL_ADDR) {
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
+		f2fs_msg(sbi->sb, KERN_WARNING,
+			"%s: orphan failed (ino=%x), run fsck to fix.",
+				__func__, ino);
+		return -EIO;
+	}
+	__remove_ino_entry(sbi, ino, ORPHAN_INO);
 	return 0;
 }
 
@@ -516,7 +576,7 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi)
 	block_t start_blk, orphan_blocks, i, j;
 	int err;
 
-	if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG))
+	if (!is_set_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG))
 		return 0;
 
 	start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi);
@@ -540,7 +600,7 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi)
 		f2fs_put_page(page, 1);
 	}
 	/* clear Orphan Flag */
-	clear_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG);
+	clear_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG);
 	return 0;
 }
 
@@ -601,45 +661,55 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
 	}
 }
 
+static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr,
+		struct f2fs_checkpoint **cp_block, struct page **cp_page,
+		unsigned long long *version)
+{
+	unsigned long blk_size = sbi->blocksize;
+	size_t crc_offset = 0;
+	__u32 crc = 0;
+
+	*cp_page = get_meta_page(sbi, cp_addr);
+	*cp_block = (struct f2fs_checkpoint *)page_address(*cp_page);
+
+	crc_offset = le32_to_cpu((*cp_block)->checksum_offset);
+	if (crc_offset >= blk_size) {
+		f2fs_msg(sbi->sb, KERN_WARNING,
+			"invalid crc_offset: %zu", crc_offset);
+		return -EINVAL;
+	}
+
+	crc = le32_to_cpu(*((__le32 *)((unsigned char *)*cp_block
+							+ crc_offset)));
+	if (!f2fs_crc_valid(sbi, crc, *cp_block, crc_offset)) {
+		f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value");
+		return -EINVAL;
+	}
+
+	*version = cur_cp_version(*cp_block);
+	return 0;
+}
+
 static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
 				block_t cp_addr, unsigned long long *version)
 {
-	struct page *cp_page_1, *cp_page_2 = NULL;
-	unsigned long blk_size = sbi->blocksize;
-	struct f2fs_checkpoint *cp_block;
+	struct page *cp_page_1 = NULL, *cp_page_2 = NULL;
+	struct f2fs_checkpoint *cp_block = NULL;
 	unsigned long long cur_version = 0, pre_version = 0;
-	size_t crc_offset;
-	__u32 crc = 0;
+	int err;
 
-	/* Read the 1st cp block in this CP pack */
-	cp_page_1 = get_meta_page(sbi, cp_addr);
-
-	/* get the version number */
-	cp_block = (struct f2fs_checkpoint *)page_address(cp_page_1);
-	crc_offset = le32_to_cpu(cp_block->checksum_offset);
-	if (crc_offset >= blk_size)
+	err = get_checkpoint_version(sbi, cp_addr, &cp_block,
+					&cp_page_1, version);
+	if (err)
 		goto invalid_cp1;
+	pre_version = *version;
 
-	crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
-	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
-		goto invalid_cp1;
-
-	pre_version = cur_cp_version(cp_block);
-
-	/* Read the 2nd cp block in this CP pack */
 	cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1;
-	cp_page_2 = get_meta_page(sbi, cp_addr);
-
-	cp_block = (struct f2fs_checkpoint *)page_address(cp_page_2);
-	crc_offset = le32_to_cpu(cp_block->checksum_offset);
-	if (crc_offset >= blk_size)
+	err = get_checkpoint_version(sbi, cp_addr, &cp_block,
+					&cp_page_2, version);
+	if (err)
 		goto invalid_cp2;
-
-	crc = le32_to_cpu(*((__le32 *)((unsigned char *)cp_block + crc_offset)));
-	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
-		goto invalid_cp2;
-
-	cur_version = cur_cp_version(cp_block);
+	cur_version = *version;
 
 	if (cur_version == pre_version) {
 		*version = cur_version;
@@ -696,6 +766,10 @@ 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;
 
@@ -722,118 +796,94 @@ fail_no_cp:
 	return -EINVAL;
 }
 
-static int __add_dirty_inode(struct inode *inode, struct inode_entry *new)
+static void __add_dirty_inode(struct inode *inode, enum inode_type type)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	int flag = (type == DIR_INODE) ? FI_DIRTY_DIR : FI_DIRTY_FILE;
 
-	if (is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR))
-		return -EEXIST;
+	if (is_inode_flag_set(inode, flag))
+		return;
 
-	set_inode_flag(F2FS_I(inode), FI_DIRTY_DIR);
-	F2FS_I(inode)->dirty_dir = new;
-	list_add_tail(&new->list, &sbi->dir_inode_list);
-	stat_inc_dirty_dir(sbi);
-	return 0;
+	set_inode_flag(inode, flag);
+	list_add_tail(&F2FS_I(inode)->dirty_list, &sbi->inode_list[type]);
+	stat_inc_dirty_inode(sbi, type);
+}
+
+static void __remove_dirty_inode(struct inode *inode, enum inode_type type)
+{
+	int flag = (type == DIR_INODE) ? FI_DIRTY_DIR : FI_DIRTY_FILE;
+
+	if (get_dirty_pages(inode) || !is_inode_flag_set(inode, flag))
+		return;
+
+	list_del_init(&F2FS_I(inode)->dirty_list);
+	clear_inode_flag(inode, flag);
+	stat_dec_dirty_inode(F2FS_I_SB(inode), type);
 }
 
 void update_dirty_page(struct inode *inode, struct page *page)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct inode_entry *new;
-	int ret = 0;
+	enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE;
 
 	if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
 			!S_ISLNK(inode->i_mode))
 		return;
 
-	if (!S_ISDIR(inode->i_mode)) {
-		inode_inc_dirty_pages(inode);
-		goto out;
-	}
-
-	new = f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
-	new->inode = inode;
-	INIT_LIST_HEAD(&new->list);
-
-	spin_lock(&sbi->dir_inode_lock);
-	ret = __add_dirty_inode(inode, new);
+	spin_lock(&sbi->inode_lock[type]);
+	if (type != FILE_INODE || test_opt(sbi, DATA_FLUSH))
+		__add_dirty_inode(inode, type);
 	inode_inc_dirty_pages(inode);
-	spin_unlock(&sbi->dir_inode_lock);
+	spin_unlock(&sbi->inode_lock[type]);
 
-	if (ret)
-		kmem_cache_free(inode_entry_slab, new);
-out:
 	SetPagePrivate(page);
 	f2fs_trace_pid(page);
 }
 
-void add_dirty_dir_inode(struct inode *inode)
+void remove_dirty_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct inode_entry *new =
-			f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
-	int ret = 0;
+	enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE;
 
-	new->inode = inode;
-	INIT_LIST_HEAD(&new->list);
-
-	spin_lock(&sbi->dir_inode_lock);
-	ret = __add_dirty_inode(inode, new);
-	spin_unlock(&sbi->dir_inode_lock);
-
-	if (ret)
-		kmem_cache_free(inode_entry_slab, new);
-}
-
-void remove_dirty_dir_inode(struct inode *inode)
-{
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct inode_entry *entry;
-
-	if (!S_ISDIR(inode->i_mode))
+	if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
+			!S_ISLNK(inode->i_mode))
 		return;
 
-	spin_lock(&sbi->dir_inode_lock);
-	if (get_dirty_pages(inode) ||
-			!is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR)) {
-		spin_unlock(&sbi->dir_inode_lock);
+	if (type == FILE_INODE && !test_opt(sbi, DATA_FLUSH))
 		return;
-	}
 
-	entry = F2FS_I(inode)->dirty_dir;
-	list_del(&entry->list);
-	F2FS_I(inode)->dirty_dir = NULL;
-	clear_inode_flag(F2FS_I(inode), FI_DIRTY_DIR);
-	stat_dec_dirty_dir(sbi);
-	spin_unlock(&sbi->dir_inode_lock);
-	kmem_cache_free(inode_entry_slab, entry);
-
-	/* Only from the recovery routine */
-	if (is_inode_flag_set(F2FS_I(inode), FI_DELAY_IPUT)) {
-		clear_inode_flag(F2FS_I(inode), FI_DELAY_IPUT);
-		iput(inode);
-	}
+	spin_lock(&sbi->inode_lock[type]);
+	__remove_dirty_inode(inode, type);
+	spin_unlock(&sbi->inode_lock[type]);
 }
 
-void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi)
+int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
 {
 	struct list_head *head;
-	struct inode_entry *entry;
 	struct inode *inode;
+	struct f2fs_inode_info *fi;
+	bool is_dir = (type == DIR_INODE);
+
+	trace_f2fs_sync_dirty_inodes_enter(sbi->sb, is_dir,
+				get_pages(sbi, is_dir ?
+				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
 retry:
 	if (unlikely(f2fs_cp_error(sbi)))
-		return;
+		return -EIO;
 
-	spin_lock(&sbi->dir_inode_lock);
+	spin_lock(&sbi->inode_lock[type]);
 
-	head = &sbi->dir_inode_list;
+	head = &sbi->inode_list[type];
 	if (list_empty(head)) {
-		spin_unlock(&sbi->dir_inode_lock);
-		return;
+		spin_unlock(&sbi->inode_lock[type]);
+		trace_f2fs_sync_dirty_inodes_exit(sbi->sb, is_dir,
+				get_pages(sbi, is_dir ?
+				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
+		return 0;
 	}
-	entry = list_entry(head->next, struct inode_entry, list);
-	inode = igrab(entry->inode);
-	spin_unlock(&sbi->dir_inode_lock);
+	fi = list_entry(head->next, struct f2fs_inode_info, dirty_list);
+	inode = igrab(&fi->vfs_inode);
+	spin_unlock(&sbi->inode_lock[type]);
 	if (inode) {
 		filemap_fdatawrite(inode->i_mapping);
 		iput(inode);
@@ -848,6 +898,34 @@ retry:
 	goto retry;
 }
 
+int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
+{
+	struct list_head *head = &sbi->inode_list[DIRTY_META];
+	struct inode *inode;
+	struct f2fs_inode_info *fi;
+	s64 total = get_pages(sbi, F2FS_DIRTY_IMETA);
+
+	while (total--) {
+		if (unlikely(f2fs_cp_error(sbi)))
+			return -EIO;
+
+		spin_lock(&sbi->inode_lock[DIRTY_META]);
+		if (list_empty(head)) {
+			spin_unlock(&sbi->inode_lock[DIRTY_META]);
+			return 0;
+		}
+		fi = list_entry(head->next, struct f2fs_inode_info,
+							gdirty_list);
+		inode = igrab(&fi->vfs_inode);
+		spin_unlock(&sbi->inode_lock[DIRTY_META]);
+		if (inode) {
+			update_inode_page(inode);
+			iput(inode);
+		}
+	};
+	return 0;
+}
+
 /*
  * Freeze all the FS-operations for checkpoint.
  */
@@ -868,11 +946,17 @@ retry_flush_dents:
 	/* write all the dirty dentry pages */
 	if (get_pages(sbi, F2FS_DIRTY_DENTS)) {
 		f2fs_unlock_all(sbi);
-		sync_dirty_dir_inodes(sbi);
-		if (unlikely(f2fs_cp_error(sbi))) {
-			err = -EIO;
+		err = sync_dirty_inodes(sbi, DIR_INODE);
+		if (err)
+			goto out;
+		goto retry_flush_dents;
+	}
+
+	if (get_pages(sbi, F2FS_DIRTY_IMETA)) {
+		f2fs_unlock_all(sbi);
+		err = f2fs_sync_inode_meta(sbi);
+		if (err)
 			goto out;
-		}
 		goto retry_flush_dents;
 	}
 
@@ -885,10 +969,9 @@ retry_flush_nodes:
 
 	if (get_pages(sbi, F2FS_DIRTY_NODES)) {
 		up_write(&sbi->node_write);
-		sync_node_pages(sbi, 0, &wbc);
-		if (unlikely(f2fs_cp_error(sbi))) {
+		err = sync_node_pages(sbi, &wbc);
+		if (err) {
 			f2fs_unlock_all(sbi);
-			err = -EIO;
 			goto out;
 		}
 		goto retry_flush_nodes;
@@ -901,6 +984,8 @@ out:
 static void unblock_operations(struct f2fs_sb_info *sbi)
 {
 	up_write(&sbi->node_write);
+
+	build_free_nids(sbi);
 	f2fs_unlock_all(sbi);
 }
 
@@ -911,18 +996,48 @@ static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
 	for (;;) {
 		prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE);
 
-		if (!get_pages(sbi, F2FS_WRITEBACK))
+		if (!atomic_read(&sbi->nr_wb_bios))
 			break;
 
-		io_schedule();
+		io_schedule_timeout(5*HZ);
 	}
 	finish_wait(&sbi->cp_wait, &wait);
 }
 
-static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
+static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
+{
+	unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num;
+	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+
+	spin_lock(&sbi->cp_lock);
+
+	if (cpc->reason == CP_UMOUNT)
+		__set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+	else
+		__clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+
+	if (cpc->reason == CP_FASTBOOT)
+		__set_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
+	else
+		__clear_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
+
+	if (orphan_num)
+		__set_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
+	else
+		__clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
+
+	if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
+		__set_ckpt_flags(ckpt, CP_FSCK_FLAG);
+
+	/* set this flag to activate crc|cp_ver for recovery */
+	__set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG);
+
+	spin_unlock(&sbi->cp_lock);
+}
+
+static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
-	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num;
 	nid_t last_nid = nm_i->next_scan_nid;
@@ -931,21 +1046,15 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	__u32 crc32 = 0;
 	int i;
 	int cp_payload_blks = __cp_payload(sbi);
-	block_t discard_blk = NEXT_FREE_BLKADDR(sbi, curseg);
-	bool invalidate = false;
-
-	/*
-	 * This avoids to conduct wrong roll-forward operations and uses
-	 * metapages, so should be called prior to sync_meta_pages below.
-	 */
-	if (discard_next_dnode(sbi, discard_blk))
-		invalidate = true;
+	struct super_block *sb = sbi->sb;
+	struct curseg_info *seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
+	u64 kbytes_written;
 
 	/* Flush all the NAT/SIT pages */
 	while (get_pages(sbi, F2FS_DIRTY_META)) {
 		sync_meta_pages(sbi, META, LONG_MAX);
 		if (unlikely(f2fs_cp_error(sbi)))
-			return;
+			return -EIO;
 	}
 
 	next_free_nid(sbi, &last_nid);
@@ -980,10 +1089,12 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	/* 2 cp  + n data seg summary + orphan inode blocks */
 	data_sum_blocks = npages_for_summary_flush(sbi, false);
+	spin_lock(&sbi->cp_lock);
 	if (data_sum_blocks < NR_CURSEG_DATA_TYPE)
-		set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
+		__set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
 	else
-		clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
+		__clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
+	spin_unlock(&sbi->cp_lock);
 
 	orphan_blocks = GET_ORPHAN_BLOCKS(orphan_num);
 	ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks +
@@ -998,29 +1109,14 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 				cp_payload_blks + data_sum_blocks +
 				orphan_blocks);
 
-	if (cpc->reason == CP_UMOUNT)
-		set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
-	else
-		clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
-
-	if (cpc->reason == CP_FASTBOOT)
-		set_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
-	else
-		clear_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
-
-	if (orphan_num)
-		set_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
-	else
-		clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
-
-	if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
-		set_ckpt_flags(ckpt, CP_FSCK_FLAG);
+	/* update ckpt flag for checkpoint */
+	update_ckpt_flags(sbi, cpc);
 
 	/* update SIT/NAT bitmap */
 	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);
@@ -1030,7 +1126,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	/* need to wait for end_io results */
 	wait_on_all_pages_writeback(sbi);
 	if (unlikely(f2fs_cp_error(sbi)))
-		return;
+		return -EIO;
 
 	/* write out checkpoint buffer at block 0 */
 	update_meta_page(sbi, ckpt, start_blk++);
@@ -1046,6 +1142,14 @@ static void 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;
@@ -1058,14 +1162,14 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	wait_on_all_pages_writeback(sbi);
 
 	if (unlikely(f2fs_cp_error(sbi)))
-		return;
+		return -EIO;
 
-	filemap_fdatawait_range(NODE_MAPPING(sbi), 0, LONG_MAX);
-	filemap_fdatawait_range(META_MAPPING(sbi), 0, LONG_MAX);
+	filemap_fdatawait_range(NODE_MAPPING(sbi), 0, LLONG_MAX);
+	filemap_fdatawait_range(META_MAPPING(sbi), 0, LLONG_MAX);
 
 	/* update user_block_counts */
 	sbi->last_valid_block_count = sbi->total_valid_block_count;
-	sbi->alloc_valid_block_count = 0;
+	percpu_counter_set(&sbi->alloc_valid_block_count, 0);
 
 	/* Here, we only have one bio having CP pack */
 	sync_meta_pages(sbi, META_FLUSH, LONG_MAX);
@@ -1073,30 +1177,36 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	/* wait for previous submitted meta pages writeback */
 	wait_on_all_pages_writeback(sbi);
 
-	/*
-	 * invalidate meta page which is used temporarily for zeroing out
-	 * block at the end of warm node chain.
-	 */
-	if (invalidate)
-		invalidate_mapping_pages(META_MAPPING(sbi), discard_blk,
-								discard_blk);
-
-	release_dirty_inode(sbi);
+	release_ino_entry(sbi, false);
 
 	if (unlikely(f2fs_cp_error(sbi)))
-		return;
+		return -EIO;
 
 	clear_prefree_segments(sbi, cpc);
 	clear_sbi_flag(sbi, SBI_IS_DIRTY);
+	clear_sbi_flag(sbi, SBI_NEED_CP);
+
+	/*
+	 * redirty superblock if metadata like node page or inode cache is
+	 * updated during writing checkpoint.
+	 */
+	if (get_pages(sbi, F2FS_DIRTY_NODES) ||
+			get_pages(sbi, F2FS_DIRTY_IMETA))
+		set_sbi_flag(sbi, SBI_IS_DIRTY);
+
+	f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_DENTS));
+
+	return 0;
 }
 
 /*
  * We guarantee that this checkpoint procedure will not fail.
  */
-void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
+int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
 	unsigned long long ckpt_ver;
+	int err = 0;
 
 	mutex_lock(&sbi->cp_mutex);
 
@@ -1104,21 +1214,35 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 		(cpc->reason == CP_FASTBOOT || cpc->reason == CP_SYNC ||
 		(cpc->reason == CP_DISCARD && !sbi->discard_blks)))
 		goto out;
-	if (unlikely(f2fs_cp_error(sbi)))
+	if (unlikely(f2fs_cp_error(sbi))) {
+		err = -EIO;
 		goto out;
-	if (f2fs_readonly(sbi->sb))
+	}
+	if (f2fs_readonly(sbi->sb)) {
+		err = -EROFS;
 		goto out;
+	}
 
 	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "start block_ops");
 
-	if (block_operations(sbi))
+	err = block_operations(sbi);
+	if (err)
 		goto out;
 
 	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish block_ops");
 
-	f2fs_submit_merged_bio(sbi, DATA, WRITE);
-	f2fs_submit_merged_bio(sbi, NODE, WRITE);
-	f2fs_submit_merged_bio(sbi, META, WRITE);
+	f2fs_flush_merged_bios(sbi);
+
+	/* this is the case of multiple fstrims without any changes */
+	if (cpc->reason == CP_DISCARD && !is_sbi_flag_set(sbi, SBI_IS_DIRTY)) {
+		f2fs_bug_on(sbi, NM_I(sbi)->dirty_nat_cnt);
+		f2fs_bug_on(sbi, SIT_I(sbi)->dirty_sentries);
+		f2fs_bug_on(sbi, prefree_segments(sbi));
+		flush_sit_entries(sbi, cpc);
+		clear_prefree_segments(sbi, cpc);
+		unblock_operations(sbi);
+		goto out;
+	}
 
 	/*
 	 * update checkpoint pack index
@@ -1133,7 +1257,7 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	flush_sit_entries(sbi, cpc);
 
 	/* unlock all the fs_lock[] in do_checkpoint() */
-	do_checkpoint(sbi, cpc);
+	err = do_checkpoint(sbi, cpc);
 
 	unblock_operations(sbi);
 	stat_inc_cp_count(sbi->stat_info);
@@ -1143,10 +1267,11 @@ void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			"checkpoint: version = %llx", ckpt_ver);
 
 	/* do checkpoint periodically */
-	sbi->cp_expires = round_jiffies_up(jiffies + HZ * sbi->cp_interval);
+	f2fs_update_time(sbi, CP_TIME);
+	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint");
 out:
 	mutex_unlock(&sbi->cp_mutex);
-	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint");
+	return err;
 }
 
 void init_ino_entry_info(struct f2fs_sb_info *sbi)

fs/f2fs/crypto.c

@@ -1,491 +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/hash.h>
-#include <crypto/sha.h>
-#include <keys/user-type.h>
-#include <keys/encrypted-type.h>
-#include <linux/crypto.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 ablkcipher_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_ablkcipher *tfm = ci->ci_ctfm;
-	int res = 0;
-
-	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
-	if (!req) {
-		printk_ratelimited(KERN_ERR
-				"%s: crypto_request_alloc() failed\n",
-				__func__);
-		return -ENOMEM;
-	}
-	ablkcipher_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);
-	ablkcipher_request_set_crypt(req, &src, &dst, PAGE_CACHE_SIZE,
-					xts_tweak);
-	if (rw == F2FS_DECRYPT)
-		res = crypto_ablkcipher_decrypt(req);
-	else
-		res = crypto_ablkcipher_encrypt(req);
-	if (res == -EINPROGRESS || res == -EBUSY) {
-		BUG_ON(req->base.data != &ecr);
-		wait_for_completion(&ecr.completion);
-		res = ecr.res;
-	}
-	ablkcipher_request_free(req);
-	if (res) {
-		printk_ratelimited(KERN_ERR
-			"%s: crypto_ablkcipher_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/debug.c

@@ -38,23 +38,30 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->hit_rbtree = atomic64_read(&sbi->read_hit_rbtree);
 	si->hit_total = si->hit_largest + si->hit_cached + si->hit_rbtree;
 	si->total_ext = atomic64_read(&sbi->total_hit_ext);
-	si->ext_tree = sbi->total_ext_tree;
+	si->ext_tree = atomic_read(&sbi->total_ext_tree);
+	si->zombie_tree = atomic_read(&sbi->total_zombie_tree);
 	si->ext_node = atomic_read(&sbi->total_ext_node);
 	si->ndirty_node = get_pages(sbi, F2FS_DIRTY_NODES);
 	si->ndirty_dent = get_pages(sbi, F2FS_DIRTY_DENTS);
-	si->ndirty_dirs = sbi->n_dirty_dirs;
 	si->ndirty_meta = get_pages(sbi, F2FS_DIRTY_META);
+	si->ndirty_data = get_pages(sbi, F2FS_DIRTY_DATA);
+	si->ndirty_imeta = get_pages(sbi, F2FS_DIRTY_IMETA);
+	si->ndirty_dirs = sbi->ndirty_inode[DIR_INODE];
+	si->ndirty_files = sbi->ndirty_inode[FILE_INODE];
+	si->ndirty_all = sbi->ndirty_inode[DIRTY_META];
 	si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES);
-	si->wb_pages = get_pages(sbi, F2FS_WRITEBACK);
+	si->wb_bios = atomic_read(&sbi->nr_wb_bios);
 	si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg;
 	si->rsvd_segs = reserved_segments(sbi);
 	si->overp_segs = overprovision_segments(sbi);
 	si->valid_count = valid_user_blocks(sbi);
+	si->discard_blks = discard_blocks(sbi);
 	si->valid_node_count = valid_node_count(sbi);
 	si->valid_inode_count = valid_inode_count(sbi);
 	si->inline_xattr = atomic_read(&sbi->inline_xattr);
 	si->inline_inode = atomic_read(&sbi->inline_inode);
 	si->inline_dir = atomic_read(&sbi->inline_dir);
+	si->orphans = sbi->im[ORPHAN_INO].ino_num;
 	si->utilization = utilization(sbi);
 
 	si->free_segs = free_segments(sbi);
@@ -105,7 +112,7 @@ static void update_sit_info(struct f2fs_sb_info *sbi)
 
 	bimodal = 0;
 	total_vblocks = 0;
-	blks_per_sec = sbi->segs_per_sec * (1 << sbi->log_blocks_per_seg);
+	blks_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg;
 	hblks_per_sec = blks_per_sec / 2;
 	for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
 		vblocks = get_valid_blocks(sbi, segno, sbi->segs_per_sec);
@@ -140,6 +147,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 	si->base_mem = sizeof(struct f2fs_sb_info) + sbi->sb->s_blocksize;
 	si->base_mem += 2 * sizeof(struct f2fs_inode_info);
 	si->base_mem += sizeof(*sbi->ckpt);
+	si->base_mem += sizeof(struct percpu_counter) * NR_COUNT_TYPE;
 
 	/* build sm */
 	si->base_mem += sizeof(struct f2fs_sm_info);
@@ -148,7 +156,9 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 	si->base_mem += sizeof(struct sit_info);
 	si->base_mem += MAIN_SEGS(sbi) * sizeof(struct seg_entry);
 	si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi));
-	si->base_mem += 3 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi);
+	si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi);
+	if (f2fs_discard_en(sbi))
+		si->base_mem += SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi);
 	si->base_mem += SIT_VBLOCK_MAP_SIZE;
 	if (sbi->segs_per_sec > 1)
 		si->base_mem += MAIN_SECS(sbi) * sizeof(struct sec_entry);
@@ -161,7 +171,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 
 	/* build curseg */
 	si->base_mem += sizeof(struct curseg_info) * NR_CURSEG_TYPE;
-	si->base_mem += PAGE_CACHE_SIZE * NR_CURSEG_TYPE;
+	si->base_mem += PAGE_SIZE * NR_CURSEG_TYPE;
 
 	/* build dirty segmap */
 	si->base_mem += sizeof(struct dirty_seglist_info);
@@ -189,18 +199,18 @@ get_cache:
 	si->cache_mem += NM_I(sbi)->dirty_nat_cnt *
 					sizeof(struct nat_entry_set);
 	si->cache_mem += si->inmem_pages * sizeof(struct inmem_pages);
-	si->cache_mem += sbi->n_dirty_dirs * sizeof(struct inode_entry);
-	for (i = 0; i <= UPDATE_INO; i++)
+	for (i = 0; i <= ORPHAN_INO; i++)
 		si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry);
-	si->cache_mem += sbi->total_ext_tree * sizeof(struct extent_tree);
+	si->cache_mem += atomic_read(&sbi->total_ext_tree) *
+						sizeof(struct extent_tree);
 	si->cache_mem += atomic_read(&sbi->total_ext_node) *
 						sizeof(struct extent_node);
 
 	si->page_mem = 0;
 	npages = NODE_MAPPING(sbi)->nrpages;
-	si->page_mem += (unsigned long long)npages << PAGE_CACHE_SHIFT;
+	si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
 	npages = META_MAPPING(sbi)->nrpages;
-	si->page_mem += (unsigned long long)npages << PAGE_CACHE_SHIFT;
+	si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
 }
 
 static int stat_show(struct seq_file *s, void *v)
@@ -211,20 +221,24 @@ static int stat_show(struct seq_file *s, void *v)
 
 	mutex_lock(&f2fs_stat_mutex);
 	list_for_each_entry(si, &f2fs_stat_list, stat_list) {
-		char devname[BDEVNAME_SIZE];
-
 		update_general_status(si->sbi);
 
-		seq_printf(s, "\n=====[ partition info(%s). #%d ]=====\n",
-			bdevname(si->sbi->sb->s_bdev, devname), i++);
+		seq_printf(s, "\n=====[ partition info(%pg). #%d, %s]=====\n",
+			si->sbi->sb->s_bdev, i++,
+			f2fs_readonly(si->sbi->sb) ? "RO": "RW");
 		seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ",
 			   si->sit_area_segs, si->nat_area_segs);
 		seq_printf(s, "[SSA: %d] [MAIN: %d",
 			   si->ssa_area_segs, si->main_area_segs);
 		seq_printf(s, "(OverProv:%d Resv:%d)]\n\n",
 			   si->overp_segs, si->rsvd_segs);
-		seq_printf(s, "Utilization: %d%% (%d valid blocks)\n",
-			   si->utilization, si->valid_count);
+		if (test_opt(si->sbi, DISCARD))
+			seq_printf(s, "Utilization: %u%% (%u valid blocks, %u discard blocks)\n",
+				si->utilization, si->valid_count, si->discard_blks);
+		else
+			seq_printf(s, "Utilization: %u%% (%u valid blocks)\n",
+				si->utilization, si->valid_count);
+
 		seq_printf(s, "  - Node: %u (Inode: %u, ",
 			   si->valid_node_count, si->valid_inode_count);
 		seq_printf(s, "Other: %u)\n  - Data: %u\n",
@@ -236,6 +250,8 @@ static int stat_show(struct seq_file *s, void *v)
 			   si->inline_inode);
 		seq_printf(s, "  - Inline_dentry Inode: %u\n",
 			   si->inline_dir);
+		seq_printf(s, "  - Orphan Inode: %u\n",
+			   si->orphans);
 		seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n",
 			   si->main_area_segs, si->main_area_sections,
 			   si->main_area_zones);
@@ -269,7 +285,8 @@ static int stat_show(struct seq_file *s, void *v)
 			   si->dirty_count);
 		seq_printf(s, "  - Prefree: %d\n  - Free: %d (%d)\n\n",
 			   si->prefree_count, si->free_segs, si->free_secs);
-		seq_printf(s, "CP calls: %d\n", si->cp_count);
+		seq_printf(s, "CP calls: %d (BG: %d)\n",
+				si->cp_count, si->bg_cp_count);
 		seq_printf(s, "GC calls: %d (BG: %d)\n",
 			   si->call_count, si->bg_gc);
 		seq_printf(s, "  - data segments : %d (%d)\n",
@@ -290,17 +307,21 @@ static int stat_show(struct seq_file *s, void *v)
 				!si->total_ext ? 0 :
 				div64_u64(si->hit_total * 100, si->total_ext),
 				si->hit_total, si->total_ext);
-		seq_printf(s, "  - Inner Struct Count: tree: %d, node: %d\n",
-				si->ext_tree, si->ext_node);
+		seq_printf(s, "  - Inner Struct Count: tree: %d(%d), node: %d\n",
+				si->ext_tree, si->zombie_tree, si->ext_node);
 		seq_puts(s, "\nBalancing F2FS Async:\n");
-		seq_printf(s, "  - inmem: %4d, wb: %4d\n",
-			   si->inmem_pages, si->wb_pages);
-		seq_printf(s, "  - nodes: %4d in %4d\n",
+		seq_printf(s, "  - inmem: %4lld, wb_bios: %4d\n",
+			   si->inmem_pages, si->wb_bios);
+		seq_printf(s, "  - nodes: %4lld in %4d\n",
 			   si->ndirty_node, si->node_pages);
-		seq_printf(s, "  - dents: %4d in dirs:%4d\n",
-			   si->ndirty_dent, si->ndirty_dirs);
-		seq_printf(s, "  - meta: %4d in %4d\n",
+		seq_printf(s, "  - dents: %4lld in dirs:%4d (%4d)\n",
+			   si->ndirty_dent, si->ndirty_dirs, si->ndirty_all);
+		seq_printf(s, "  - datas: %4lld in files:%4d\n",
+			   si->ndirty_data, si->ndirty_files);
+		seq_printf(s, "  - meta: %4lld in %4d\n",
 			   si->ndirty_meta, si->meta_pages);
+		seq_printf(s, "  - imeta: %4lld\n",
+			   si->ndirty_imeta);
 		seq_printf(s, "  - NATs: %9d/%9d\n  - SITs: %9d/%9d\n",
 			   si->dirty_nats, si->nats, si->dirty_sits, si->sits);
 		seq_printf(s, "  - free_nids: %9d\n",
@@ -407,20 +428,23 @@ void f2fs_destroy_stats(struct f2fs_sb_info *sbi)
 	kfree(si);
 }
 
-void __init f2fs_create_root_stats(void)
+int __init f2fs_create_root_stats(void)
 {
 	struct dentry *file;
 
 	f2fs_debugfs_root = debugfs_create_dir("f2fs", NULL);
 	if (!f2fs_debugfs_root)
-		return;
+		return -ENOMEM;
 
 	file = debugfs_create_file("status", S_IRUGO, f2fs_debugfs_root,
 			NULL, &stat_fops);
 	if (!file) {
 		debugfs_remove(f2fs_debugfs_root);
 		f2fs_debugfs_root = NULL;
+		return -ENOMEM;
 	}
+
+	return 0;
 }
 
 void f2fs_destroy_root_stats(void)

fs/f2fs/dir.c

@@ -17,8 +17,8 @@
 
 static unsigned long dir_blocks(struct inode *inode)
 {
-	return ((unsigned long long) (i_size_read(inode) + PAGE_CACHE_SIZE - 1))
-							>> PAGE_CACHE_SHIFT;
+	return ((unsigned long long) (i_size_read(inode) + PAGE_SIZE - 1))
+							>> PAGE_SHIFT;
 }
 
 static unsigned int dir_buckets(unsigned int level, int dir_level)
@@ -37,7 +37,7 @@ static unsigned int bucket_blocks(unsigned int level)
 		return 4;
 }
 
-unsigned char f2fs_filetype_table[F2FS_FT_MAX] = {
+static unsigned char f2fs_filetype_table[F2FS_FT_MAX] = {
 	[F2FS_FT_UNKNOWN]	= DT_UNKNOWN,
 	[F2FS_FT_REG_FILE]	= DT_REG,
 	[F2FS_FT_DIR]		= DT_DIR,
@@ -48,7 +48,6 @@ unsigned char f2fs_filetype_table[F2FS_FT_MAX] = {
 	[F2FS_FT_SYMLINK]	= DT_LNK,
 };
 
-#define S_SHIFT 12
 static unsigned char f2fs_type_by_mode[S_IFMT >> S_SHIFT] = {
 	[S_IFREG >> S_SHIFT]	= F2FS_FT_REG_FILE,
 	[S_IFDIR >> S_SHIFT]	= F2FS_FT_DIR,
@@ -64,6 +63,13 @@ void set_de_type(struct f2fs_dir_entry *de, umode_t mode)
 	de->file_type = f2fs_type_by_mode[(mode & S_IFMT) >> S_SHIFT];
 }
 
+unsigned char get_de_type(struct f2fs_dir_entry *de)
+{
+	if (de->file_type < F2FS_FT_MAX)
+		return f2fs_filetype_table[de->file_type];
+	return DT_UNKNOWN;
+}
+
 static unsigned long dir_block_index(unsigned int level,
 				int dir_level, unsigned int idx)
 {
@@ -77,7 +83,7 @@ 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)
@@ -95,23 +101,18 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
 	else
 		kunmap(dentry_page);
 
-	/*
-	 * For the most part, it should be a bug when name_len is zero.
-	 * We stop here for figuring out where the bugs has occurred.
-	 */
-	f2fs_bug_on(F2FS_P_SB(dentry_page), d.max < 0);
 	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 f2fs_str *name = &fname->disk_name;
+	struct fscrypt_str de_name = FSTR_INIT(NULL, 0);
+	struct fscrypt_str *name = &fname->disk_name;
 
 	if (max_slots)
 		*max_slots = 0;
@@ -124,37 +125,28 @@ struct f2fs_dir_entry *find_target_dentry(struct f2fs_filename *fname,
 
 		de = &d->dentry[bit_pos];
 
-		if (de->hash_code != namehash)
-			goto not_match;
+		if (unlikely(!de->name_len)) {
+			bit_pos++;
+			continue;
+		}
 
+		/* encrypted case */
 		de_name.name = d->filename[bit_pos];
 		de_name.len = le16_to_cpu(de->name_len);
 
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-		if (unlikely(!name->name)) {
-			if (fname->usr_fname->name[0] == '_') {
-				if (de_name.len > 32 &&
-					!memcmp(de_name.name + ((de_name.len - 17) & ~15),
-						fname->crypto_buf.name + 8, 16))
-					goto found;
-				goto not_match;
-			}
-			name->name = fname->crypto_buf.name;
-			name->len = fname->crypto_buf.len;
-		}
-#endif
-		if (de_name.len == name->len &&
-				!memcmp(de_name.name, name->name, name->len))
+		/* show encrypted name */
+		if (fname->hash) {
+			if (de->hash_code == fname->hash)
+				goto found;
+		} else if (de_name.len == name->len &&
+			de->hash_code == namehash &&
+			!memcmp(de_name.name, name->name, name->len))
 			goto found;
-not_match:
+
 		if (max_slots && max_len > *max_slots)
 			*max_slots = max_len;
 		max_len = 0;
 
-		/* remain bug on condition */
-		if (unlikely(!de->name_len))
-			d->max = -1;
-
 		bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
 	}
 
@@ -167,7 +159,7 @@ 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);
@@ -180,9 +172,10 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 	int max_slots;
 	f2fs_hash_t namehash;
 
-	namehash = f2fs_dentry_hash(&name, fname);
-
-	f2fs_bug_on(F2FS_I_SB(dir), level > MAX_DIR_HASH_DEPTH);
+	if(fname->hash)
+		namehash = cpu_to_le32(fname->hash);
+	else
+		namehash = f2fs_dentry_hash(&name);
 
 	nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level);
 	nblock = bucket_blocks(level);
@@ -195,8 +188,13 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 		/* no need to allocate new dentry pages to all the indices */
 		dentry_page = find_data_page(dir, bidx);
 		if (IS_ERR(dentry_page)) {
-			room = true;
-			continue;
+			if (PTR_ERR(dentry_page) == -ENOENT) {
+				room = true;
+				continue;
+			} else {
+				*res_page = dentry_page;
+				break;
+			}
 		}
 
 		de = find_in_block(dentry_page, fname, namehash, &max_slots,
@@ -217,6 +215,44 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 	return de;
 }
 
+struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
+			struct fscrypt_name *fname, struct page **res_page)
+{
+	unsigned long npages = dir_blocks(dir);
+	struct f2fs_dir_entry *de = NULL;
+	unsigned int max_depth;
+	unsigned int level;
+
+	if (f2fs_has_inline_dentry(dir)) {
+		*res_page = NULL;
+		de = find_in_inline_dir(dir, fname, res_page);
+		goto out;
+	}
+
+	if (npages == 0) {
+		*res_page = NULL;
+		goto out;
+	}
+
+	max_depth = F2FS_I(dir)->i_current_depth;
+	if (unlikely(max_depth > MAX_DIR_HASH_DEPTH)) {
+		f2fs_msg(F2FS_I_SB(dir)->sb, KERN_WARNING,
+				"Corrupted max_depth of %lu: %u",
+				dir->i_ino, max_depth);
+		max_depth = MAX_DIR_HASH_DEPTH;
+		f2fs_i_depth_write(dir, max_depth);
+	}
+
+	for (level = 0; level < max_depth; level++) {
+		*res_page = NULL;
+		de = find_in_level(dir, level, fname, res_page);
+		if (de || IS_ERR(*res_page))
+			break;
+	}
+out:
+	return de;
+}
+
 /*
  * Find an entry in the specified directory with the wanted name.
  * It returns the page where the entry was found (as a parameter - res_page),
@@ -224,72 +260,42 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
  * Entry is guaranteed to be valid.
  */
 struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
-			struct qstr *child, struct page **res_page)
+			const struct qstr *child, struct page **res_page)
 {
-	unsigned long npages = dir_blocks(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);
-	if (err)
+	err = fscrypt_setup_filename(dir, child, 1, &fname);
+	if (err) {
+		*res_page = ERR_PTR(err);
 		return NULL;
-
-	if (f2fs_has_inline_dentry(dir)) {
-		de = find_in_inline_dir(dir, &fname, res_page);
-		goto out;
 	}
 
-	if (npages == 0)
-		goto out;
+	de = __f2fs_find_entry(dir, &fname, res_page);
 
-	max_depth = F2FS_I(dir)->i_current_depth;
-
-	for (level = 0; level < max_depth; level++) {
-		de = find_in_level(dir, level, &fname, res_page);
-		if (de)
-			break;
-	}
-out:
-	f2fs_fname_free_filename(&fname);
+	fscrypt_free_filename(&fname);
 	return de;
 }
 
 struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p)
 {
-	struct page *page;
-	struct f2fs_dir_entry *de;
-	struct f2fs_dentry_block *dentry_blk;
+	struct qstr dotdot = QSTR_INIT("..", 2);
 
-	if (f2fs_has_inline_dentry(dir))
-		return f2fs_parent_inline_dir(dir, p);
-
-	page = get_lock_data_page(dir, 0, false);
-	if (IS_ERR(page))
-		return NULL;
-
-	dentry_blk = kmap(page);
-	de = &dentry_blk->dentry[1];
-	*p = page;
-	unlock_page(page);
-	return de;
+	return f2fs_find_entry(dir, &dotdot, p);
 }
 
-ino_t f2fs_inode_by_name(struct inode *dir, struct qstr *qstr)
+ino_t f2fs_inode_by_name(struct inode *dir, const struct qstr *qstr,
+							struct page **page)
 {
 	ino_t res = 0;
 	struct f2fs_dir_entry *de;
-	struct page *page;
 
-	de = f2fs_find_entry(dir, qstr, &page);
+	de = f2fs_find_entry(dir, qstr, page);
 	if (de) {
 		res = le32_to_cpu(de->ino);
-		f2fs_dentry_kunmap(dir, page);
-		f2fs_put_page(page, 0);
+		f2fs_dentry_kunmap(dir, *page);
+		f2fs_put_page(*page, 0);
 	}
 
 	return res;
@@ -300,14 +306,14 @@ 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);
 	set_page_dirty(page);
-	dir->i_mtime = dir->i_ctime = CURRENT_TIME;
-	mark_inode_dirty(dir);
 
+	dir->i_mtime = dir->i_ctime = CURRENT_TIME;
+	f2fs_mark_inode_dirty_sync(dir);
 	f2fs_put_page(page, 1);
 }
 
@@ -315,7 +321,7 @@ 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);
@@ -345,24 +351,14 @@ 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];
-	de->name_len = cpu_to_le16(1);
-	de->hash_code = 0;
-	de->ino = cpu_to_le32(inode->i_ino);
-	memcpy(d->filename[0], ".", 1);
-	set_de_type(de, inode->i_mode);
+	/* update dirent of "." */
+	f2fs_update_dentry(inode->i_ino, inode->i_mode, d, &dot, 0, 0);
 
-	de = &d->dentry[1];
-	de->hash_code = 0;
-	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);
+	/* update dirent of ".." */
+	f2fs_update_dentry(parent->i_ino, parent->i_mode, d, &dotdot, 0, 1);
 }
 
 static int make_empty_dir(struct inode *inode,
@@ -392,32 +388,38 @@ static int make_empty_dir(struct inode *inode,
 }
 
 struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
-			const struct qstr *name, struct page *dpage)
+			const struct qstr *new_name, const struct qstr *orig_name,
+			struct page *dpage)
 {
 	struct page *page;
 	int err;
 
-	if (is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) {
+	if (is_inode_flag_set(inode, FI_NEW_INODE)) {
 		page = new_inode_page(inode);
 		if (IS_ERR(page))
 			return page;
 
 		if (S_ISDIR(inode->i_mode)) {
+			/* in order to handle error case */
+			get_page(page);
 			err = make_empty_dir(inode, dir, page);
-			if (err)
-				goto error;
+			if (err) {
+				lock_page(page);
+				goto put_error;
+			}
+			put_page(page);
 		}
 
 		err = f2fs_init_acl(inode, dir, page, dpage);
 		if (err)
 			goto put_error;
 
-		err = f2fs_init_security(inode, dir, name, page);
+		err = f2fs_init_security(inode, dir, orig_name, page);
 		if (err)
 			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;
 		}
@@ -429,14 +431,14 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
 		set_cold_node(inode, page);
 	}
 
-	if (name)
-		init_dent_inode(name, page);
+	if (new_name)
+		init_dent_inode(new_name, page);
 
 	/*
 	 * This file should be checkpointed during fsync.
 	 * We lost i_pino from now on.
 	 */
-	if (is_inode_flag_set(F2FS_I(inode), FI_INC_LINK)) {
+	if (is_inode_flag_set(inode, FI_INC_LINK)) {
 		file_lost_pino(inode);
 		/*
 		 * If link the tmpfile to alias through linkat path,
@@ -444,41 +446,33 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
 		 */
 		if (inode->i_nlink == 0)
 			remove_orphan_inode(F2FS_I_SB(dir), inode->i_ino);
-		inc_nlink(inode);
+		f2fs_i_links_write(inode, true);
 	}
 	return page;
 
 put_error:
+	clear_nlink(inode);
+	update_inode(inode, page);
 	f2fs_put_page(page, 1);
-error:
-	/* once the failed inode becomes a bad inode, i_mode is S_IFREG */
-	truncate_inode_pages(&inode->i_data, 0);
-	truncate_blocks(inode, 0, false);
-	remove_dirty_dir_inode(inode);
-	remove_inode_page(inode);
 	return ERR_PTR(err);
 }
 
 void update_parent_metadata(struct inode *dir, struct inode *inode,
 						unsigned int current_depth)
 {
-	if (inode && is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) {
-		if (S_ISDIR(inode->i_mode)) {
-			inc_nlink(dir);
-			set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
-		}
-		clear_inode_flag(F2FS_I(inode), FI_NEW_INODE);
+	if (inode && is_inode_flag_set(inode, FI_NEW_INODE)) {
+		if (S_ISDIR(inode->i_mode))
+			f2fs_i_links_write(dir, true);
+		clear_inode_flag(inode, FI_NEW_INODE);
 	}
 	dir->i_mtime = dir->i_ctime = CURRENT_TIME;
-	mark_inode_dirty(dir);
+	f2fs_mark_inode_dirty_sync(dir);
 
-	if (F2FS_I(dir)->i_current_depth != current_depth) {
-		F2FS_I(dir)->i_current_depth = current_depth;
-		set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
-	}
+	if (F2FS_I(dir)->i_current_depth != current_depth)
+		f2fs_i_depth_write(dir, current_depth);
 
-	if (inode && is_inode_flag_set(F2FS_I(inode), FI_INC_LINK))
-		clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
+	if (inode && is_inode_flag_set(inode, FI_INC_LINK))
+		clear_inode_flag(inode, FI_INC_LINK);
 }
 
 int room_for_filename(const void *bitmap, int slots, int max_slots)
@@ -515,15 +509,16 @@ 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++)
-		test_and_set_bit_le(bit_pos + i, (void *)d->bitmap);
+	for (i = 0; i < slots; i++) {
+		__set_bit_le(bit_pos + i, (void *)d->bitmap);
+		/* avoid wrong garbage data for readdir */
+		if (i)
+			(de + i)->name_len = 0;
+	}
 }
 
-/*
- * Caller should grab and release a rwsem by calling f2fs_lock_op() and
- * f2fs_unlock_op().
- */
-int __f2fs_add_link(struct inode *dir, const struct qstr *name,
+int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
+				const struct qstr *orig_name,
 				struct inode *inode, nid_t ino, umode_t mode)
 {
 	unsigned int bit_pos;
@@ -536,28 +531,11 @@ 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 qstr new_name;
-	int slots, err;
-
-	err = f2fs_fname_setup_filename(dir, name, 0, &fname);
-	if (err)
-		return err;
-
-	new_name.name = fname_name(&fname);
-	new_name.len = fname_len(&fname);
-
-	if (f2fs_has_inline_dentry(dir)) {
-		err = f2fs_add_inline_entry(dir, &new_name, inode, ino, mode);
-		if (!err || err != -EAGAIN)
-			goto out;
-		else
-			err = 0;
-	}
+	int slots, err = 0;
 
 	level = 0;
-	slots = GET_DENTRY_SLOTS(new_name.len);
-	dentry_hash = f2fs_dentry_hash(&new_name, NULL);
+	slots = GET_DENTRY_SLOTS(new_name->len);
+	dentry_hash = f2fs_dentry_hash(new_name);
 
 	current_depth = F2FS_I(dir)->i_current_depth;
 	if (F2FS_I(dir)->chash == dentry_hash) {
@@ -566,10 +544,12 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
 	}
 
 start:
-	if (unlikely(current_depth == MAX_DIR_HASH_DEPTH)) {
-		err = -ENOSPC;
-		goto out;
-	}
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	if (time_to_inject(F2FS_I_SB(dir), FAULT_DIR_DEPTH))
+		return -ENOSPC;
+#endif
+	if (unlikely(current_depth == MAX_DIR_HASH_DEPTH))
+		return -ENOSPC;
 
 	/* Increase the depth, if required */
 	if (level == current_depth)
@@ -583,10 +563,8 @@ start:
 
 	for (block = bidx; block <= (bidx + nblock - 1); block++) {
 		dentry_page = get_new_data_page(dir, NULL, block, true);
-		if (IS_ERR(dentry_page)) {
-			err = PTR_ERR(dentry_page);
-			goto out;
-		}
+		if (IS_ERR(dentry_page))
+			return PTR_ERR(dentry_page);
 
 		dentry_blk = kmap(dentry_page);
 		bit_pos = room_for_filename(&dentry_blk->dentry_bitmap,
@@ -602,11 +580,12 @@ 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);
-		page = init_inode_metadata(inode, dir, &new_name, NULL);
+		page = init_inode_metadata(inode, dir, new_name,
+						orig_name, NULL);
 		if (IS_ERR(page)) {
 			err = PTR_ERR(page);
 			goto fail;
@@ -616,14 +595,12 @@ add_dentry:
 	}
 
 	make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1);
-	f2fs_update_dentry(ino, mode, &d, &new_name, dentry_hash, bit_pos);
+	f2fs_update_dentry(ino, mode, &d, new_name, dentry_hash, bit_pos);
 
 	set_page_dirty(dentry_page);
 
 	if (inode) {
-		/* we don't need to mark_inode_dirty now */
-		F2FS_I(inode)->i_pino = dir->i_ino;
-		update_inode(inode, page);
+		f2fs_i_pino_write(inode, dir->i_ino);
 		f2fs_put_page(page, 1);
 	}
 
@@ -632,14 +609,49 @@ fail:
 	if (inode)
 		up_write(&F2FS_I(inode)->i_sem);
 
-	if (is_inode_flag_set(F2FS_I(dir), FI_UPDATE_DIR)) {
-		update_inode_page(dir);
-		clear_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
-	}
 	kunmap(dentry_page);
 	f2fs_put_page(dentry_page, 1);
-out:
-	f2fs_fname_free_filename(&fname);
+
+	return err;
+}
+
+int __f2fs_do_add_link(struct inode *dir, struct fscrypt_name *fname,
+				struct inode *inode, nid_t ino, umode_t mode)
+{
+	struct qstr new_name;
+	int err = -EAGAIN;
+
+	new_name.name = fname_name(fname);
+	new_name.len = fname_len(fname);
+
+	if (f2fs_has_inline_dentry(dir))
+		err = f2fs_add_inline_entry(dir, &new_name, fname->usr_fname,
+							inode, ino, mode);
+	if (err == -EAGAIN)
+		err = f2fs_add_regular_entry(dir, &new_name, fname->usr_fname,
+							inode, ino, mode);
+
+	f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
+	return err;
+}
+
+/*
+ * Caller should grab and release a rwsem by calling f2fs_lock_op() and
+ * f2fs_unlock_op().
+ */
+int __f2fs_add_link(struct inode *dir, const struct qstr *name,
+				struct inode *inode, nid_t ino, umode_t mode)
+{
+	struct fscrypt_name fname;
+	int err;
+
+	err = fscrypt_setup_filename(dir, name, 0, &fname);
+	if (err)
+		return err;
+
+	err = __f2fs_do_add_link(dir, &fname, inode, ino, mode);
+
+	fscrypt_free_filename(&fname);
 	return err;
 }
 
@@ -649,46 +661,39 @@ int f2fs_do_tmpfile(struct inode *inode, struct inode *dir)
 	int err = 0;
 
 	down_write(&F2FS_I(inode)->i_sem);
-	page = init_inode_metadata(inode, dir, NULL, NULL);
+	page = init_inode_metadata(inode, dir, NULL, NULL, NULL);
 	if (IS_ERR(page)) {
 		err = PTR_ERR(page);
 		goto fail;
 	}
-	/* we don't need to mark_inode_dirty now */
-	update_inode(inode, page);
 	f2fs_put_page(page, 1);
 
-	clear_inode_flag(F2FS_I(inode), FI_NEW_INODE);
+	clear_inode_flag(inode, FI_NEW_INODE);
 fail:
 	up_write(&F2FS_I(inode)->i_sem);
+	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 	return err;
 }
 
-void f2fs_drop_nlink(struct inode *dir, struct inode *inode, struct page *page)
+void f2fs_drop_nlink(struct inode *dir, struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
 
 	down_write(&F2FS_I(inode)->i_sem);
 
-	if (S_ISDIR(inode->i_mode)) {
-		drop_nlink(dir);
-		if (page)
-			update_inode(dir, page);
-		else
-			update_inode_page(dir);
-	}
+	if (S_ISDIR(inode->i_mode))
+		f2fs_i_links_write(dir, false);
 	inode->i_ctime = CURRENT_TIME;
 
-	drop_nlink(inode);
+	f2fs_i_links_write(inode, false);
 	if (S_ISDIR(inode->i_mode)) {
-		drop_nlink(inode);
-		i_size_write(inode, 0);
+		f2fs_i_links_write(inode, false);
+		f2fs_i_size_write(inode, 0);
 	}
 	up_write(&F2FS_I(inode)->i_sem);
-	update_inode_page(inode);
 
 	if (inode->i_nlink == 0)
-		add_orphan_inode(sbi, inode->i_ino);
+		add_orphan_inode(inode);
 	else
 		release_orphan_inode(sbi);
 }
@@ -705,11 +710,13 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 	int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
 	int i;
 
+	f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
+
 	if (f2fs_has_inline_dentry(dir))
 		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;
@@ -724,9 +731,10 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 	set_page_dirty(page);
 
 	dir->i_ctime = dir->i_mtime = CURRENT_TIME;
+	f2fs_mark_inode_dirty_sync(dir);
 
 	if (inode)
-		f2fs_drop_nlink(dir, inode, NULL);
+		f2fs_drop_nlink(dir, inode);
 
 	if (bit_pos == NR_DENTRY_IN_BLOCK &&
 			!truncate_hole(dir, page->index, page->index + 1)) {
@@ -777,12 +785,12 @@ 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);
 
@@ -792,10 +800,13 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 			break;
 
 		de = &d->dentry[bit_pos];
-		if (de->file_type < F2FS_FT_MAX)
-			d_type = f2fs_filetype_table[de->file_type];
-		else
-			d_type = DT_UNKNOWN;
+		if (de->name_len == 0) {
+			bit_pos++;
+			ctx->pos = start_pos + bit_pos;
+			continue;
+		}
+
+		d_type = get_de_type(de);
 
 		de_name.name = d->filename[bit_pos];
 		de_name.len = le16_to_cpu(de->name_len);
@@ -804,15 +815,9 @@ bool f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
 			int save_len = fstr->len;
 			int ret;
 
-			de_name.name = kmalloc(de_name.len, GFP_NOFS);
-			if (!de_name.name)
-				return false;
-
-			memcpy(de_name.name, d->filename[bit_pos], de_name.len);
-
-			ret = f2fs_fname_disk_to_usr(d->inode, &de->hash_code,
-							&de_name, fstr);
-			kfree(de_name.name);
+			ret = fscrypt_fname_disk_to_usr(d->inode,
+						(u32)de->hash_code, 0,
+						&de_name, fstr);
 			if (ret < 0)
 				return true;
 
@@ -839,16 +844,15 @@ 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);
-		if (err)
+		err = fscrypt_get_encryption_info(inode);
+		if (err && err != -ENOKEY)
 			return err;
 
-		err = f2fs_fname_crypto_alloc_buffer(inode, F2FS_NAME_LEN,
-								&fstr);
+		err = fscrypt_fname_alloc_buffer(inode, F2FS_NAME_LEN, &fstr);
 		if (err < 0)
 			return err;
 	}
@@ -865,36 +869,47 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 
 	for (; n < npages; n++) {
 		dentry_page = get_lock_data_page(inode, n, false);
-		if (IS_ERR(dentry_page))
-			continue;
+		if (IS_ERR(dentry_page)) {
+			err = PTR_ERR(dentry_page);
+			if (err == -ENOENT)
+				continue;
+			else
+				goto out;
+		}
 
 		dentry_blk = kmap(dentry_page);
 
 		make_dentry_ptr(inode, &d, (void *)dentry_blk, 1);
 
-		if (f2fs_fill_dentries(ctx, &d, n * NR_DENTRY_IN_BLOCK, &fstr))
-			goto stop;
+		if (f2fs_fill_dentries(ctx, &d, n * NR_DENTRY_IN_BLOCK, &fstr)) {
+			kunmap(dentry_page);
+			f2fs_put_page(dentry_page, 1);
+			break;
+		}
 
 		ctx->pos = (n + 1) * NR_DENTRY_IN_BLOCK;
 		kunmap(dentry_page);
 		f2fs_put_page(dentry_page, 1);
-		dentry_page = NULL;
-	}
-stop:
-	if (dentry_page && !IS_ERR(dentry_page)) {
-		kunmap(dentry_page);
-		f2fs_put_page(dentry_page, 1);
 	}
+	err = 0;
 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

@@ -33,10 +33,11 @@ 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);
-	et->count++;
+	atomic_inc(&et->node_cnt);
 	atomic_inc(&sbi->total_ext_node);
 	return en;
 }
@@ -45,11 +46,29 @@ static void __detach_extent_node(struct f2fs_sb_info *sbi,
 				struct extent_tree *et, struct extent_node *en)
 {
 	rb_erase(&en->rb_node, &et->root);
-	et->count--;
+	atomic_dec(&et->node_cnt);
 	atomic_dec(&sbi->total_ext_node);
 
 	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)
@@ -68,11 +87,13 @@ static struct extent_tree *__grab_extent_tree(struct inode *inode)
 		et->root = RB_ROOT;
 		et->cached_en = NULL;
 		rwlock_init(&et->lock);
-		atomic_set(&et->refcount, 0);
-		et->count = 0;
-		sbi->total_ext_tree++;
+		INIT_LIST_HEAD(&et->list);
+		atomic_set(&et->node_cnt, 0);
+		atomic_inc(&sbi->total_ext_tree);
+	} else {
+		atomic_dec(&sbi->total_zombie_tree);
+		list_del_init(&et->list);
 	}
-	atomic_inc(&et->refcount);
 	up_write(&sbi->extent_tree_lock);
 
 	/* never died until evict_inode */
@@ -127,32 +148,21 @@ 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;
-	unsigned int count = et->count;
+	unsigned int count = atomic_read(&et->node_cnt);
 
 	node = rb_first(&et->root);
 	while (node) {
 		next = rb_next(node);
 		en = rb_entry(node, struct extent_node, rb_node);
-
-		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);
-		}
+		__release_extent_node(sbi, et, en);
 		node = next;
 	}
 
-	return count - et->count;
+	return count - atomic_read(&et->node_cnt);
 }
 
 static void __drop_largest_extent(struct inode *inode,
@@ -160,38 +170,38 @@ static void __drop_largest_extent(struct inode *inode,
 {
 	struct extent_info *largest = &F2FS_I(inode)->extent_tree->largest;
 
-	if (fofs < largest->fofs + largest->len && fofs + len > largest->fofs)
+	if (fofs < largest->fofs + largest->len && fofs + len > largest->fofs) {
 		largest->len = 0;
+		f2fs_mark_inode_dirty_sync(inode);
+	}
 }
 
-void f2fs_drop_largest_extent(struct inode *inode, pgoff_t fofs)
-{
-	if (!f2fs_may_extent_tree(inode))
-		return;
-
-	__drop_largest_extent(inode, fofs, 1);
-}
-
-void f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
+/* return true, if inode page is changed */
+bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct extent_tree *et;
 	struct extent_node *en;
 	struct extent_info ei;
 
-	if (!f2fs_may_extent_tree(inode))
-		return;
+	if (!f2fs_may_extent_tree(inode)) {
+		/* drop largest extent */
+		if (i_ext && i_ext->len) {
+			i_ext->len = 0;
+			return true;
+		}
+		return false;
+	}
 
 	et = __grab_extent_tree(inode);
 
-	if (!i_ext || le32_to_cpu(i_ext->len) < F2FS_MIN_EXTENT_LEN)
-		return;
+	if (!i_ext || !i_ext->len)
+		return false;
 
-	set_extent_info(&ei, le32_to_cpu(i_ext->fofs),
-		le32_to_cpu(i_ext->blk), le32_to_cpu(i_ext->len));
+	get_extent_info(&ei, i_ext);
 
 	write_lock(&et->lock);
-	if (et->count)
+	if (atomic_read(&et->node_cnt))
 		goto out;
 
 	en = __init_extent_tree(sbi, et, &ei);
@@ -202,6 +212,7 @@ void f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
 	}
 out:
 	write_unlock(&et->lock);
+	return false;
 }
 
 static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
@@ -230,9 +241,10 @@ 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;
 	}
@@ -325,12 +337,12 @@ lookup_neighbors:
 	return en;
 }
 
-static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi,
+static struct extent_node *__try_merge_extent_node(struct inode *inode,
 				struct extent_tree *et, struct extent_info *ei,
-				struct extent_node **den,
 				struct extent_node *prev_ex,
 				struct extent_node *next_ex)
 {
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct extent_node *en = NULL;
 
 	if (prev_ex && __is_back_mergeable(ei, &prev_ex->ei)) {
@@ -340,28 +352,34 @@ 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) {
-			__detach_extent_node(sbi, et, prev_ex);
-			*den = prev_ex;
-		}
+		if (en)
+			__release_extent_node(sbi, et, 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) {
-		__try_update_largest_extent(et, en);
+	if (!en)
+		return NULL;
+
+	__try_update_largest_extent(inode, 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;
 }
 
-static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi,
+static struct extent_node *__insert_extent_tree(struct inode *inode,
 				struct extent_tree *et, struct extent_info *ei,
 				struct rb_node **insert_p,
 				struct rb_node *insert_parent)
 {
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct rb_node **p = &et->root.rb_node;
 	struct rb_node *parent = NULL;
 	struct extent_node *en = NULL;
@@ -388,8 +406,13 @@ do_insert:
 	if (!en)
 		return NULL;
 
-	__try_update_largest_extent(et, en);
+	__try_update_largest_extent(inode, 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;
 }
 
@@ -412,7 +435,7 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 
 	write_lock(&et->lock);
 
-	if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT)) {
+	if (is_inode_flag_set(inode, FI_NO_EXTENT)) {
 		write_unlock(&et->lock);
 		return false;
 	}
@@ -454,7 +477,7 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 				set_extent_info(&ei, end,
 						end - dei.fofs + dei.blk,
 						org_end - end);
-				en1 = __insert_extent_tree(sbi, et, &ei,
+				en1 = __insert_extent_tree(inode, et, &ei,
 							NULL, NULL);
 				next_en = en1;
 			} else {
@@ -475,9 +498,9 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 		}
 
 		if (parts)
-			__try_update_largest_extent(et, en);
+			__try_update_largest_extent(inode, 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
@@ -488,58 +511,28 @@ 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,
-							prev_en, next_en);
-		if (!en1)
-			en1 = __insert_extent_tree(sbi, et, &ei,
+		if (!__try_merge_extent_node(inode, et, &ei, prev_en, next_en))
+			__insert_extent_tree(inode, et, &ei,
 						insert_p, insert_parent);
 
 		/* give up extent_cache, if split and small updates happen */
 		if (dei.len >= 1 &&
 				prev.len < F2FS_MIN_EXTENT_LEN &&
 				et->largest.len < F2FS_MIN_EXTENT_LEN) {
-			et->largest.len = 0;
-			set_inode_flag(F2FS_I(inode), FI_NO_EXTENT);
+			__drop_largest_extent(inode, 0, UINT_MAX);
+			set_inode_flag(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);
+	if (is_inode_flag_set(inode, FI_NO_EXTENT))
+		__free_extent_tree(sbi, et);
 
 	write_unlock(&et->lock);
 
@@ -548,46 +541,42 @@ 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_node *en, *tmp;
-	unsigned long ino = F2FS_ROOT_INO(sbi);
-	struct radix_tree_root *root = &sbi->extent_tree_root;
-	unsigned int found;
+	struct extent_tree *et, *next;
+	struct extent_node *en;
 	unsigned int node_cnt = 0, tree_cnt = 0;
 	int remained;
 
 	if (!test_opt(sbi, EXTENT_CACHE))
 		return 0;
 
+	if (!atomic_read(&sbi->total_zombie_tree))
+		goto free_node;
+
 	if (!down_write_trylock(&sbi->extent_tree_lock))
 		goto out;
 
 	/* 1. remove unreferenced extent tree */
-	while ((found = radix_tree_gang_lookup(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->refcount)) {
-				write_lock(&et->lock);
-				node_cnt += __free_extent_tree(sbi, et, true);
-				write_unlock(&et->lock);
-
-				radix_tree_delete(root, et->ino);
-				kmem_cache_free(extent_tree_slab, et);
-				sbi->total_ext_tree--;
-				tree_cnt++;
-
-				if (node_cnt + tree_cnt >= nr_shrink)
-					goto unlock_out;
-			}
+	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);
+			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);
+		atomic_dec(&sbi->total_ext_tree);
+		atomic_dec(&sbi->total_zombie_tree);
+		tree_cnt++;
+
+		if (node_cnt + tree_cnt >= nr_shrink)
+			goto unlock_out;
+		cond_resched();
 	}
 	up_write(&sbi->extent_tree_lock);
 
+free_node:
 	/* 2. remove LRU extent entries */
 	if (!down_write_trylock(&sbi->extent_tree_lock))
 		goto out;
@@ -595,34 +584,29 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
 	remained = nr_shrink - (node_cnt + tree_cnt);
 
 	spin_lock(&sbi->extent_lock);
-	list_for_each_entry_safe(en, tmp, &sbi->extent_list, list) {
-		if (!remained--)
+	for (; remained > 0; 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);
+		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);
 
-	/*
-	 * reset ino for searching victims from beginning of global extent tree.
-	 */
-	ino = F2FS_ROOT_INO(sbi);
-
-	while ((found = radix_tree_gang_lookup(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];
-
-			write_lock(&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:
@@ -637,16 +621,29 @@ unsigned int f2fs_destroy_extent_node(struct inode *inode)
 	struct extent_tree *et = F2FS_I(inode)->extent_tree;
 	unsigned int node_cnt = 0;
 
-	if (!et)
+	if (!et || !atomic_read(&et->node_cnt))
 		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;
 }
 
+void f2fs_drop_extent_tree(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct extent_tree *et = F2FS_I(inode)->extent_tree;
+
+	set_inode_flag(inode, FI_NO_EXTENT);
+
+	write_lock(&et->lock);
+	__free_extent_tree(sbi, et);
+	__drop_largest_extent(inode, 0, UINT_MAX);
+	write_unlock(&et->lock);
+}
+
 void f2fs_destroy_extent_tree(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -656,8 +653,12 @@ void f2fs_destroy_extent_tree(struct inode *inode)
 	if (!et)
 		return;
 
-	if (inode->i_nlink && !is_bad_inode(inode) && et->count) {
-		atomic_dec(&et->refcount);
+	if (inode->i_nlink && !is_bad_inode(inode) &&
+					atomic_read(&et->node_cnt)) {
+		down_write(&sbi->extent_tree_lock);
+		list_add_tail(&et->list, &sbi->zombie_list);
+		atomic_inc(&sbi->total_zombie_tree);
+		up_write(&sbi->extent_tree_lock);
 		return;
 	}
 
@@ -666,11 +667,10 @@ void f2fs_destroy_extent_tree(struct inode *inode)
 
 	/* delete extent tree entry in radix tree */
 	down_write(&sbi->extent_tree_lock);
-	atomic_dec(&et->refcount);
-	f2fs_bug_on(sbi, atomic_read(&et->refcount) || et->count);
+	f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
 	radix_tree_delete(&sbi->extent_tree_root, inode->i_ino);
 	kmem_cache_free(extent_tree_slab, et);
-	sbi->total_ext_tree--;
+	atomic_dec(&sbi->total_ext_tree);
 	up_write(&sbi->extent_tree_lock);
 
 	F2FS_I(inode)->extent_tree = NULL;
@@ -689,20 +689,20 @@ 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), fi) +
-							dn->ofs_in_node;
-
-	if (f2fs_update_extent_tree_range(dn->inode, fofs, dn->data_blkaddr, 1))
-		sync_inode_page(dn);
+	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
+								dn->ofs_in_node;
+	f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, 1);
 }
 
 void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
@@ -712,8 +712,7 @@ void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
 	if (!f2fs_may_extent_tree(dn->inode))
 		return;
 
-	if (f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, len))
-		sync_inode_page(dn);
+	f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, len);
 }
 
 void init_extent_cache_info(struct f2fs_sb_info *sbi)
@@ -722,7 +721,9 @@ void init_extent_cache_info(struct f2fs_sb_info *sbi)
 	init_rwsem(&sbi->extent_tree_lock);
 	INIT_LIST_HEAD(&sbi->extent_list);
 	spin_lock_init(&sbi->extent_lock);
-	sbi->total_ext_tree = 0;
+	atomic_set(&sbi->total_ext_tree, 0);
+	INIT_LIST_HEAD(&sbi->zombie_list);
+	atomic_set(&sbi->total_zombie_tree, 0);
 	atomic_set(&sbi->total_ext_node, 0);
 }
 

fs/f2fs/gc.c

@@ -16,7 +16,6 @@
 #include <linux/kthread.h>
 #include <linux/delay.h>
 #include <linux/freezer.h>
-#include <linux/blkdev.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -48,6 +47,11 @@ static int gc_thread_func(void *data)
 			continue;
 		}
 
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+		if (time_to_inject(sbi, FAULT_CHECKPOINT))
+			f2fs_stop_checkpoint(sbi, false);
+#endif
+
 		/*
 		 * [GC triggering condition]
 		 * 0. GC is not conducted currently.
@@ -97,7 +101,7 @@ int start_gc_thread(struct f2fs_sb_info *sbi)
 	dev_t dev = sbi->sb->s_bdev->bd_dev;
 	int err = 0;
 
-	gc_th = kmalloc(sizeof(struct f2fs_gc_kthread), GFP_KERNEL);
+	gc_th = f2fs_kmalloc(sbi, sizeof(struct f2fs_gc_kthread), GFP_KERNEL);
 	if (!gc_th) {
 		err = -ENOMEM;
 		goto out;
@@ -173,9 +177,9 @@ static unsigned int get_max_cost(struct f2fs_sb_info *sbi,
 {
 	/* SSR allocates in a segment unit */
 	if (p->alloc_mode == SSR)
-		return 1 << sbi->log_blocks_per_seg;
+		return sbi->blocks_per_seg;
 	if (p->gc_mode == GC_GREEDY)
-		return (1 << sbi->log_blocks_per_seg) * p->ofs_unit;
+		return sbi->blocks_per_seg * p->ofs_unit;
 	else if (p->gc_mode == GC_CB)
 		return UINT_MAX;
 	else /* No other gc_mode */
@@ -246,6 +250,18 @@ 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.
@@ -259,9 +275,9 @@ 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, last_victim;
 	unsigned int last_segment = MAIN_SEGS(sbi);
-	int nsearched = 0;
+	unsigned int nsearched = 0;
 
 	mutex_lock(&dirty_i->seglist_lock);
 
@@ -269,11 +285,12 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 	select_policy(sbi, gc_type, type, &p);
 
 	p.min_segno = NULL_SEGNO;
-	p.min_cost = max_cost = get_max_cost(sbi, &p);
+	p.min_cost = get_max_cost(sbi, &p);
 
 	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)
@@ -296,27 +313,35 @@ 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;
 		}
-
-		if (nsearched++ >= p.max_search) {
-			sbi->last_victim[p.gc_mode] = segno;
+next:
+		if (nsearched >= p.max_search) {
+			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;
 		}
 	}
@@ -400,13 +425,13 @@ 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;
 	struct f2fs_summary *entry;
 	block_t start_addr;
 	int off;
+	int phase = 0;
 
 	start_addr = START_BLOCK(sbi, segno);
 
@@ -419,16 +444,24 @@ next_step:
 		struct node_info ni;
 
 		/* stop BG_GC if there is not enough free sections. */
-		if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0))
-			return 0;
+		if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0))
+			return;
 
 		if (check_valid_map(sbi, segno, off) == 0)
 			continue;
 
-		if (initial) {
+		if (phase == 0) {
+			ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1,
+							META_NAT, true);
+			continue;
+		}
+
+		if (phase == 1) {
 			ra_node_page(sbi, nid);
 			continue;
 		}
+
+		/* phase == 2 */
 		node_page = get_node_page(sbi, nid);
 		if (IS_ERR(node_page))
 			continue;
@@ -445,36 +478,12 @@ next_step:
 			continue;
 		}
 
-		/* set page dirty and write it */
-		if (gc_type == FG_GC) {
-			f2fs_wait_on_page_writeback(node_page, NODE);
-			set_page_dirty(node_page);
-		} else {
-			if (!PageWriteback(node_page))
-				set_page_dirty(node_page);
-		}
-		f2fs_put_page(node_page, 1);
+		move_node_page(node_page, gc_type);
 		stat_inc_node_blk_count(sbi, 1, gc_type);
 	}
 
-	if (initial) {
-		initial = false;
+	if (++phase < 3)
 		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;
 }
 
 /*
@@ -484,7 +493,7 @@ 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;
@@ -501,7 +510,7 @@ 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,
@@ -547,6 +556,7 @@ 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 */
@@ -568,21 +578,24 @@ 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),
-					fio.blk_addr,
-					FGP_LOCK|FGP_CREAT,
-					GFP_NOFS);
-	if (!fio.encrypted_page)
-		goto put_out;
+	allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr,
+							&sum, CURSEG_COLD_DATA);
+
+	fio.encrypted_page = pagecache_get_page(META_MAPPING(fio.sbi), newaddr,
+					FGP_LOCK | FGP_CREAT, GFP_NOFS);
+	if (!fio.encrypted_page) {
+		err = -ENOMEM;
+		goto recover_block;
+	}
 
 	err = f2fs_submit_page_bio(&fio);
 	if (err)
@@ -591,33 +604,39 @@ 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(fio.encrypted_page->mapping != META_MAPPING(fio.sbi))) {
+		err = -EIO;
 		goto put_page_out;
-	if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi)))
+	}
+	if (unlikely(!PageUptodate(fio.encrypted_page))) {
+		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);
-	allocate_data_block(fio.sbi, NULL, fio.blk_addr,
-					&fio.blk_addr, &sum, CURSEG_COLD_DATA);
+	f2fs_wait_on_page_writeback(dn.node_page, NODE, true);
+
 	fio.rw = WRITE_SYNC;
+	fio.new_blkaddr = newaddr;
 	f2fs_submit_page_mbio(&fio);
 
-	dn.data_blkaddr = fio.blk_addr;
-	set_data_blkaddr(&dn);
-	f2fs_update_extent_cache(&dn);
-	set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
+	f2fs_update_data_blkaddr(&dn, newaddr);
+	set_inode_flag(inode, FI_APPEND_WRITE);
 	if (page->index == 0)
-		set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
+		set_inode_flag(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:
@@ -645,12 +664,23 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
 			.page = page,
 			.encrypted_page = NULL,
 		};
+		bool is_dirty = PageDirty(page);
+		int err;
+
+retry:
 		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);
-		do_write_data_page(&fio);
+
+		err = do_write_data_page(&fio);
+		if (err == -ENOMEM && is_dirty) {
+			congestion_wait(BLK_RW_ASYNC, HZ/50);
+			goto retry;
+		}
+
 		clear_cold_data(page);
 	}
 out:
@@ -664,7 +694,7 @@ 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;
@@ -684,16 +714,23 @@ next_step:
 		struct node_info dni; /* dnode info for the data */
 		unsigned int ofs_in_node, nofs;
 		block_t start_bidx;
+		nid_t nid = le32_to_cpu(entry->nid);
 
 		/* stop BG_GC if there is not enough free sections. */
-		if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0))
-			return 0;
+		if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0))
+			return;
 
 		if (check_valid_map(sbi, segno, off) == 0)
 			continue;
 
 		if (phase == 0) {
-			ra_node_page(sbi, le32_to_cpu(entry->nid));
+			ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1,
+							META_NAT, true);
+			continue;
+		}
+
+		if (phase == 1) {
+			ra_node_page(sbi, nid);
 			continue;
 		}
 
@@ -701,14 +738,14 @@ next_step:
 		if (!is_alive(sbi, entry, &dni, start_addr + off, &nofs))
 			continue;
 
-		if (phase == 1) {
+		if (phase == 2) {
 			ra_node_page(sbi, dni.ino);
 			continue;
 		}
 
 		ofs_in_node = le16_to_cpu(entry->ofs_in_node);
 
-		if (phase == 2) {
+		if (phase == 3) {
 			inode = f2fs_iget(sb, dni.ino);
 			if (IS_ERR(inode) || is_bad_inode(inode))
 				continue;
@@ -720,7 +757,7 @@ 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)) {
@@ -733,30 +770,41 @@ next_step:
 			continue;
 		}
 
-		/* phase 3 */
+		/* phase 4 */
 		inode = find_gc_inode(gc_list, dni.ino);
 		if (inode) {
-			start_bidx = start_bidx_of_node(nofs, F2FS_I(inode))
+			struct f2fs_inode_info *fi = F2FS_I(inode);
+			bool locked = false;
+
+			if (S_ISREG(inode->i_mode)) {
+				if (!down_write_trylock(&fi->dio_rwsem[READ]))
+					continue;
+				if (!down_write_trylock(
+						&fi->dio_rwsem[WRITE])) {
+					up_write(&fi->dio_rwsem[READ]);
+					continue;
+				}
+				locked = true;
+			}
+
+			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);
 			else
 				move_data_page(inode, start_bidx, gc_type);
+
+			if (locked) {
+				up_write(&fi->dio_rwsem[WRITE]);
+				up_write(&fi->dio_rwsem[READ]);
+			}
+
 			stat_inc_data_blk_count(sbi, 1, gc_type);
 		}
 	}
 
-	if (++phase < 4)
+	if (++phase < 5)
 		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,
@@ -772,51 +820,84 @@ 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 sec_freed = 0;
+	unsigned char type = IS_DATASEG(get_seg_entry(sbi, segno)->type) ?
+						SUM_TYPE_DATA : SUM_TYPE_NODE;
 
-	/* read segment summary of victim */
-	sum_page = get_sum_page(sbi, segno);
+	/* readahead multi ssa blocks those have contiguous address */
+	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++) {
 
-	/*
-	 * this is to avoid deadlock:
-	 * - 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);
+		if (get_valid_blocks(sbi, segno, 1) == 0 ||
+					unlikely(f2fs_cp_error(sbi)))
+			goto next;
 
-	switch (GET_SUM_TYPE((&sum->footer))) {
-	case SUM_TYPE_NODE:
-		nfree = gc_node_segment(sbi, sum->entries, segno, gc_type);
-		break;
-	case SUM_TYPE_DATA:
-		nfree = gc_data_segment(sbi, sum->entries, gc_list,
-							segno, gc_type);
-		break;
+		/* 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);
+		f2fs_bug_on(sbi, type != GET_SUM_TYPE((&sum->footer)));
+
+		/*
+		 * this is to avoid deadlock:
+		 * - lock_page(sum_page)         - f2fs_replace_block
+		 *  - check_valid_map()            - mutex_lock(sentry_lock)
+		 *   - mutex_lock(sentry_lock)     - change_curseg()
+		 *                                  - lock_page(sum_page)
+		 */
+
+		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);
+next:
+		f2fs_put_page(sum_page, 0);
 	}
+
+	if (gc_type == FG_GC)
+		f2fs_submit_merged_bio(sbi,
+				(type == SUM_TYPE_NODE) ? NODE : DATA, WRITE);
+
 	blk_finish_plug(&plug);
 
-	stat_inc_seg_count(sbi, GET_SUM_TYPE((&sum->footer)), gc_type);
+	if (gc_type == FG_GC &&
+		get_valid_blocks(sbi, start_segno, sbi->segs_per_sec) == 0)
+		sec_freed = 1;
+
 	stat_inc_call_count(sbi->stat_info);
 
-	f2fs_put_page(sum_page, 0);
-	return nfree;
+	return sec_freed;
 }
 
 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 ret = -EINVAL;
@@ -832,46 +913,48 @@ gc_more:
 
 	if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE)))
 		goto stop;
-	if (unlikely(f2fs_cp_error(sbi)))
+	if (unlikely(f2fs_cp_error(sbi))) {
+		ret = -EIO;
 		goto stop;
+	}
 
-	if (gc_type == BG_GC && has_not_enough_free_secs(sbi, sec_freed)) {
+	if (gc_type == BG_GC && has_not_enough_free_secs(sbi, sec_freed, 0)) {
 		gc_type = FG_GC;
-		if (__get_victim(sbi, &segno, gc_type) || prefree_segments(sbi))
-			write_checkpoint(sbi, &cpc);
+		/*
+		 * 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)) {
+			ret = write_checkpoint(sbi, &cpc);
+			if (ret)
+				goto stop;
+			segno = NULL_SEGNO;
+		} else if (has_not_enough_free_secs(sbi, 0, 0)) {
+			ret = write_checkpoint(sbi, &cpc);
+			if (ret)
+				goto stop;
+		}
 	}
 
 	if (segno == NULL_SEGNO && !__get_victim(sbi, &segno, gc_type))
 		goto stop;
 	ret = 0;
 
-	/* readahead multi ssa blocks those have contiguous address */
-	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++) {
-		/*
-		 * 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)
+	if (do_garbage_collect(sbi, segno, &gc_list, gc_type) &&
+			gc_type == FG_GC)
 		sec_freed++;
 
 	if (gc_type == FG_GC)
 		sbi->cur_victim_sec = NULL_SEGNO;
 
 	if (!sync) {
-		if (has_not_enough_free_secs(sbi, sec_freed))
+		if (has_not_enough_free_secs(sbi, sec_freed, 0))
 			goto gc_more;
 
 		if (gc_type == FG_GC)
-			write_checkpoint(sbi, &cpc);
+			ret = write_checkpoint(sbi, &cpc);
 	}
 stop:
 	mutex_unlock(&sbi->gc_mutex);

fs/f2fs/gc.h

@@ -100,11 +100,3 @@ static inline bool has_enough_invalid_blocks(struct f2fs_sb_info *sbi)
 		return true;
 	return false;
 }
-
-static inline int is_idle(struct f2fs_sb_info *sbi)
-{
-	struct block_device *bdev = sbi->sb->s_bdev;
-	struct request_queue *q = bdev_get_queue(bdev);
-	struct request_list *rl = &q->root_rl;
-	return !(rl->count[BLK_RW_SYNC]) && !(rl->count[BLK_RW_ASYNC]);
-}

fs/f2fs/hash.c

@@ -70,8 +70,7 @@ static void str2hashbuf(const unsigned char *msg, size_t len,
 		*buf++ = pad;
 }
 
-f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info,
-				struct f2fs_filename *fname)
+f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info)
 {
 	__u32 hash;
 	f2fs_hash_t f2fs_hash;
@@ -80,10 +79,6 @@ f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info,
 	const unsigned char *name = name_info->name;
 	size_t len = name_info->len;
 
-	/* encrypted bigname case */
-	if (fname && !fname->disk_name.name)
-		return cpu_to_le32(fname->hash);
-
 	if (is_dot_dotdot(name_info))
 		return 0;
 

fs/f2fs/inline.c

@@ -17,9 +17,6 @@
 
 bool f2fs_may_inline_data(struct inode *inode)
 {
-	if (!test_opt(F2FS_I_SB(inode), INLINE_DATA))
-		return false;
-
 	if (f2fs_is_atomic_file(inode))
 		return false;
 
@@ -55,7 +52,7 @@ void read_inline_data(struct page *page, struct page *ipage)
 
 	f2fs_bug_on(F2FS_P_SB(page), page->index);
 
-	zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
+	zero_user_segment(page, MAX_INLINE_DATA, PAGE_SIZE);
 
 	/* Copy the whole inline data block */
 	src_addr = inline_data_addr(ipage);
@@ -63,7 +60,8 @@ void read_inline_data(struct page *page, struct page *ipage)
 	memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
 	flush_dcache_page(page);
 	kunmap_atomic(dst_addr);
-	SetPageUptodate(page);
+	if (!PageUptodate(page))
+		SetPageUptodate(page);
 }
 
 bool truncate_inline_inode(struct page *ipage, u64 from)
@@ -75,9 +73,9 @@ 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);
-
+	set_page_dirty(ipage);
 	return true;
 }
 
@@ -112,11 +110,12 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page)
 	}
 
 	if (page->index)
-		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+		zero_user_segment(page, 0, PAGE_SIZE);
 	else
 		read_inline_data(page, ipage);
 
-	SetPageUptodate(page);
+	if (!PageUptodate(page))
+		SetPageUptodate(page);
 	f2fs_put_page(ipage, 1);
 	trace_android_fs_dataread_end(inode, page_offset(page),
 				      PAGE_SIZE);
@@ -126,7 +125,6 @@ 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,
@@ -136,8 +134,6 @@ 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;
 
@@ -145,21 +141,9 @@ 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))
-		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:
+	read_inline_data(page, dn->inode_page);
 	set_page_dirty(page);
 
 	/* clear dirty state */
@@ -167,23 +151,21 @@ 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_update_extent_cache(dn);
-	f2fs_wait_on_page_writeback(page, DATA);
+	f2fs_wait_on_page_writeback(page, DATA, true);
 	if (dirty)
 		inode_dec_dirty_pages(dn->inode);
 
 	/* this converted inline_data should be recovered. */
-	set_inode_flag(F2FS_I(dn->inode), FI_APPEND_WRITE);
+	set_inode_flag(dn->inode, FI_APPEND_WRITE);
 
 	/* 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);
-	sync_inode_page(dn);
 	f2fs_put_dnode(dn);
 	return 0;
 }
@@ -195,7 +177,10 @@ int f2fs_convert_inline_inode(struct inode *inode)
 	struct page *ipage, *page;
 	int err = 0;
 
-	page = grab_cache_page(inode->i_mapping, 0);
+	if (!f2fs_has_inline_data(inode))
+		return 0;
+
+	page = f2fs_grab_cache_page(inode->i_mapping, 0, false);
 	if (!page)
 		return -ENOMEM;
 
@@ -217,6 +202,9 @@ out:
 	f2fs_unlock_op(sbi);
 
 	f2fs_put_page(page, 1);
+
+	f2fs_balance_fs(sbi, dn.node_changed);
+
 	return err;
 }
 
@@ -238,16 +226,17 @@ 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);
 	kunmap_atomic(src_addr);
+	set_page_dirty(dn.inode_page);
 
-	set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
-	set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
+	set_inode_flag(inode, FI_APPEND_WRITE);
+	set_inode_flag(inode, FI_DATA_EXIST);
 
-	sync_inode_page(&dn);
+	clear_inline_node(dn.inode_page);
 	f2fs_put_dnode(&dn);
 	return 0;
 }
@@ -276,16 +265,16 @@ 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);
 		memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
 
-		set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
-		set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
+		set_inode_flag(inode, FI_INLINE_DATA);
+		set_inode_flag(inode, FI_DATA_EXIST);
 
-		update_inode(inode, ipage);
+		set_page_dirty(ipage);
 		f2fs_put_page(ipage, 1);
 		return true;
 	}
@@ -296,7 +285,6 @@ process_inline:
 		if (!truncate_inline_inode(ipage, 0))
 			return false;
 		f2fs_clear_inline_inode(inode);
-		update_inode(inode, ipage);
 		f2fs_put_page(ipage, 1);
 	} else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) {
 		if (truncate_blocks(inode, 0, false))
@@ -307,7 +295,7 @@ 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;
@@ -318,10 +306,12 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
 	f2fs_hash_t namehash;
 
 	ipage = get_node_page(sbi, dir->i_ino);
-	if (IS_ERR(ipage))
+	if (IS_ERR(ipage)) {
+		*res_page = ipage;
 		return NULL;
+	}
 
-	namehash = f2fs_dentry_hash(&name, fname);
+	namehash = f2fs_dentry_hash(&name);
 
 	inline_dentry = inline_data_addr(ipage);
 
@@ -333,30 +323,6 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
 	else
 		f2fs_put_page(ipage, 0);
 
-	/*
-	 * For the most part, it should be a bug when name_len is zero.
-	 * We stop here for figuring out where the bugs has occurred.
-	 */
-	f2fs_bug_on(sbi, d.max < 0);
-	return de;
-}
-
-struct f2fs_dir_entry *f2fs_parent_inline_dir(struct inode *dir,
-							struct page **p)
-{
-	struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
-	struct page *ipage;
-	struct f2fs_dir_entry *de;
-	struct f2fs_inline_dentry *dentry_blk;
-
-	ipage = get_node_page(sbi, dir->i_ino);
-	if (IS_ERR(ipage))
-		return NULL;
-
-	dentry_blk = inline_data_addr(ipage);
-	de = &dentry_blk->dentry[1];
-	*p = ipage;
-	unlock_page(ipage);
 	return de;
 }
 
@@ -374,10 +340,8 @@ int make_empty_inline_dir(struct inode *inode, struct inode *parent,
 	set_page_dirty(ipage);
 
 	/* update i_size to MAX_INLINE_DATA */
-	if (i_size_read(inode) < MAX_INLINE_DATA) {
-		i_size_write(inode, MAX_INLINE_DATA);
-		set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR);
-	}
+	if (i_size_read(inode) < MAX_INLINE_DATA)
+		f2fs_i_size_write(inode, MAX_INLINE_DATA);
 	return 0;
 }
 
@@ -385,7 +349,7 @@ int make_empty_inline_dir(struct inode *inode, struct inode *parent,
  * NOTE: ipage is grabbed by caller, but if any error occurs, we should
  * release ipage in this function.
  */
-static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
+static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
 				struct f2fs_inline_dentry *inline_dentry)
 {
 	struct page *page;
@@ -393,7 +357,7 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
 	struct f2fs_dentry_block *dentry_blk;
 	int err;
 
-	page = grab_cache_page(dir->i_mapping, 0);
+	page = f2fs_grab_cache_page(dir->i_mapping, 0, false);
 	if (!page) {
 		f2fs_put_page(ipage, 1);
 		return -ENOMEM;
@@ -404,8 +368,8 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
 	if (err)
 		goto out;
 
-	f2fs_wait_on_page_writeback(page, DATA);
-	zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
+	f2fs_wait_on_page_writeback(page, DATA, true);
+	zero_user_segment(page, MAX_INLINE_DATA, PAGE_SIZE);
 
 	dentry_blk = kmap_atomic(page);
 
@@ -426,37 +390,132 @@ static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
 					NR_INLINE_DENTRY * F2FS_SLOT_LEN);
 
 	kunmap_atomic(dentry_blk);
-	SetPageUptodate(page);
+	if (!PageUptodate(page))
+		SetPageUptodate(page);
 	set_page_dirty(page);
 
 	/* clear inline dir and flag after data writeback */
 	truncate_inline_inode(ipage, 0);
 
 	stat_dec_inline_dir(dir);
-	clear_inode_flag(F2FS_I(dir), FI_INLINE_DENTRY);
+	clear_inode_flag(dir, FI_INLINE_DENTRY);
 
-	if (i_size_read(dir) < PAGE_CACHE_SIZE) {
-		i_size_write(dir, PAGE_CACHE_SIZE);
-		set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
-	}
-
-	sync_inode_page(&dn);
+	f2fs_i_depth_write(dir, 1);
+	if (i_size_read(dir) < PAGE_SIZE)
+		f2fs_i_size_write(dir, PAGE_SIZE);
 out:
 	f2fs_put_page(page, 1);
 	return err;
 }
 
-int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name,
-			struct inode *inode, nid_t ino, umode_t mode)
+static int f2fs_add_inline_entries(struct inode *dir,
+			struct f2fs_inline_dentry *inline_dentry)
+{
+	struct f2fs_dentry_ptr d;
+	unsigned long bit_pos = 0;
+	int err = 0;
+
+	make_dentry_ptr(NULL, &d, (void *)inline_dentry, 2);
+
+	while (bit_pos < d.max) {
+		struct f2fs_dir_entry *de;
+		struct qstr new_name;
+		nid_t ino;
+		umode_t fake_mode;
+
+		if (!test_bit_le(bit_pos, d.bitmap)) {
+			bit_pos++;
+			continue;
+		}
+
+		de = &d.dentry[bit_pos];
+
+		if (unlikely(!de->name_len)) {
+			bit_pos++;
+			continue;
+		}
+
+		new_name.name = d.filename[bit_pos];
+		new_name.len = de->name_len;
+
+		ino = le32_to_cpu(de->ino);
+		fake_mode = get_de_type(de) << S_SHIFT;
+
+		err = f2fs_add_regular_entry(dir, &new_name, NULL, NULL,
+							ino, fake_mode);
+		if (err)
+			goto punch_dentry_pages;
+
+		bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
+	}
+	return 0;
+punch_dentry_pages:
+	truncate_inode_pages(&dir->i_data, 0);
+	truncate_blocks(dir, 0, false);
+	remove_dirty_inode(dir);
+	return err;
+}
+
+static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage,
+				struct f2fs_inline_dentry *inline_dentry)
+{
+	struct f2fs_inline_dentry *backup_dentry;
+	int err;
+
+	backup_dentry = f2fs_kmalloc(F2FS_I_SB(dir),
+			sizeof(struct f2fs_inline_dentry), GFP_F2FS_ZERO);
+	if (!backup_dentry) {
+		f2fs_put_page(ipage, 1);
+		return -ENOMEM;
+	}
+
+	memcpy(backup_dentry, inline_dentry, MAX_INLINE_DATA);
+	truncate_inline_inode(ipage, 0);
+
+	unlock_page(ipage);
+
+	err = f2fs_add_inline_entries(dir, backup_dentry);
+	if (err)
+		goto recover;
+
+	lock_page(ipage);
+
+	stat_dec_inline_dir(dir);
+	clear_inode_flag(dir, FI_INLINE_DENTRY);
+	kfree(backup_dentry);
+	return 0;
+recover:
+	lock_page(ipage);
+	memcpy(inline_dentry, backup_dentry, MAX_INLINE_DATA);
+	f2fs_i_depth_write(dir, 0);
+	f2fs_i_size_write(dir, MAX_INLINE_DATA);
+	set_page_dirty(ipage);
+	f2fs_put_page(ipage, 1);
+
+	kfree(backup_dentry);
+	return err;
+}
+
+static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
+				struct f2fs_inline_dentry *inline_dentry)
+{
+	if (!F2FS_I(dir)->i_dir_level)
+		return f2fs_move_inline_dirents(dir, ipage, inline_dentry);
+	else
+		return f2fs_move_rehashed_dirents(dir, ipage, inline_dentry);
+}
+
+int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
+				const struct qstr *orig_name,
+				struct inode *inode, nid_t ino, umode_t mode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
 	struct page *ipage;
 	unsigned int bit_pos;
 	f2fs_hash_t name_hash;
-	size_t namelen = name->len;
 	struct f2fs_inline_dentry *dentry_blk = NULL;
 	struct f2fs_dentry_ptr d;
-	int slots = GET_DENTRY_SLOTS(namelen);
+	int slots = GET_DENTRY_SLOTS(new_name->len);
 	struct page *page = NULL;
 	int err = 0;
 
@@ -477,25 +536,27 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name,
 
 	if (inode) {
 		down_write(&F2FS_I(inode)->i_sem);
-		page = init_inode_metadata(inode, dir, name, ipage);
+		page = init_inode_metadata(inode, dir, new_name,
+						orig_name, ipage);
 		if (IS_ERR(page)) {
 			err = PTR_ERR(page);
 			goto fail;
 		}
+		if (f2fs_encrypted_inode(dir))
+			file_set_enc_name(inode);
 	}
 
-	f2fs_wait_on_page_writeback(ipage, NODE);
+	f2fs_wait_on_page_writeback(ipage, NODE, true);
 
-	name_hash = f2fs_dentry_hash(name, NULL);
+	name_hash = f2fs_dentry_hash(new_name);
 	make_dentry_ptr(NULL, &d, (void *)dentry_blk, 2);
-	f2fs_update_dentry(ino, mode, &d, name, name_hash, bit_pos);
+	f2fs_update_dentry(ino, mode, &d, new_name, name_hash, bit_pos);
 
 	set_page_dirty(ipage);
 
 	/* we don't need to mark_inode_dirty now */
 	if (inode) {
-		F2FS_I(inode)->i_pino = dir->i_ino;
-		update_inode(inode, page);
+		f2fs_i_pino_write(inode, dir->i_ino);
 		f2fs_put_page(page, 1);
 	}
 
@@ -503,11 +564,6 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *name,
 fail:
 	if (inode)
 		up_write(&F2FS_I(inode)->i_sem);
-
-	if (is_inode_flag_set(F2FS_I(dir), FI_UPDATE_DIR)) {
-		update_inode(dir, ipage);
-		clear_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
-	}
 out:
 	f2fs_put_page(ipage, 1);
 	return err;
@@ -522,22 +578,22 @@ 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;
 	for (i = 0; i < slots; i++)
-		test_and_clear_bit_le(bit_pos + i,
+		__clear_bit_le(bit_pos + i,
 				&inline_dentry->dentry_bitmap);
 
 	set_page_dirty(page);
+	f2fs_put_page(page, 1);
 
 	dir->i_ctime = dir->i_mtime = CURRENT_TIME;
+	f2fs_mark_inode_dirty_sync(dir);
 
 	if (inode)
-		f2fs_drop_nlink(dir, inode, page);
-
-	f2fs_put_page(page, 1);
+		f2fs_drop_nlink(dir, inode);
 }
 
 bool f2fs_empty_inline_dir(struct inode *dir)
@@ -565,7 +621,7 @@ 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

@@ -11,6 +11,7 @@
 #include <linux/fs.h>
 #include <linux/f2fs_fs.h>
 #include <linux/buffer_head.h>
+#include <linux/backing-dev.h>
 #include <linux/writeback.h>
 
 #include "f2fs.h"
@@ -18,6 +19,13 @@
 
 #include <trace/events/f2fs.h>
 
+void f2fs_mark_inode_dirty_sync(struct inode *inode)
+{
+	if (f2fs_inode_dirtied(inode))
+		return;
+	mark_inode_dirty_sync(inode);
+}
+
 void f2fs_set_inode_flags(struct inode *inode)
 {
 	unsigned int flags = F2FS_I(inode)->i_flags;
@@ -35,6 +43,7 @@ void f2fs_set_inode_flags(struct inode *inode)
 		new_fl |= S_DIRSYNC;
 	inode_set_flags(inode, new_fl,
 			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
+	f2fs_mark_inode_dirty_sync(inode);
 }
 
 static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
@@ -83,10 +92,10 @@ 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));
+			set_inode_flag(inode, FI_DATA_EXIST);
+			set_raw_inline(inode, F2FS_INODE(ipage));
 			set_page_dirty(ipage);
 			return;
 		}
@@ -138,9 +147,10 @@ static int do_read_inode(struct inode *inode)
 	fi->i_pino = le32_to_cpu(ri->i_pino);
 	fi->i_dir_level = ri->i_dir_level;
 
-	f2fs_init_extent_tree(inode, &ri->i_ext);
+	if (f2fs_init_extent_tree(inode, &ri->i_ext))
+		set_page_dirty(node_page);
 
-	get_inline_info(fi, ri);
+	get_inline_info(inode, ri);
 
 	/* check data exist */
 	if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode))
@@ -150,7 +160,10 @@ static int do_read_inode(struct inode *inode)
 	__get_inode_rdev(inode, ri);
 
 	if (__written_first_block(ri))
-		set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
+		set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
+
+	if (!need_inode_block_update(sbi, inode->i_ino))
+		fi->last_disk_size = inode->i_size;
 
 	f2fs_put_page(node_page, 1);
 
@@ -202,6 +215,7 @@ make_now:
 			inode->i_op = &f2fs_encrypted_symlink_inode_operations;
 		else
 			inode->i_op = &f2fs_symlink_inode_operations;
+		inode_nohighmem(inode);
 		inode->i_mapping->a_ops = &f2fs_dblock_aops;
 	} else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
 			S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
@@ -221,11 +235,27 @@ bad_inode:
 	return ERR_PTR(ret);
 }
 
-void update_inode(struct inode *inode, struct page *node_page)
+struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino)
+{
+	struct inode *inode;
+retry:
+	inode = f2fs_iget(sb, ino);
+	if (IS_ERR(inode)) {
+		if (PTR_ERR(inode) == -ENOMEM) {
+			congestion_wait(BLK_RW_ASYNC, HZ/50);
+			goto retry;
+		}
+	}
+	return inode;
+}
+
+int update_inode(struct inode *inode, struct page *node_page)
 {
 	struct f2fs_inode *ri;
 
-	f2fs_wait_on_page_writeback(node_page, NODE);
+	f2fs_inode_synced(inode);
+
+	f2fs_wait_on_page_writeback(node_page, NODE, true);
 
 	ri = F2FS_INODE(node_page);
 
@@ -242,7 +272,7 @@ void update_inode(struct inode *inode, struct page *node_page)
 							&ri->i_ext);
 	else
 		memset(&ri->i_ext, 0, sizeof(ri->i_ext));
-	set_raw_inline(F2FS_I(inode), ri);
+	set_raw_inline(inode, ri);
 
 	ri->i_atime = cpu_to_le64(inode->i_atime.tv_sec);
 	ri->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
@@ -259,15 +289,19 @@ void update_inode(struct inode *inode, struct page *node_page)
 
 	__set_inode_rdev(inode, ri);
 	set_cold_node(inode, node_page);
-	set_page_dirty(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);
 }
 
-void update_inode_page(struct inode *inode)
+int update_inode_page(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct page *node_page;
+	int ret = 0;
 retry:
 	node_page = get_node_page(sbi, inode->i_ino);
 	if (IS_ERR(node_page)) {
@@ -276,12 +310,14 @@ retry:
 			cond_resched();
 			goto retry;
 		} else if (err != -ENOENT) {
-			f2fs_stop_checkpoint(sbi);
+			f2fs_stop_checkpoint(sbi, false);
 		}
-		return;
+		f2fs_inode_synced(inode);
+		return 0;
 	}
-	update_inode(inode, node_page);
+	ret = update_inode(inode, node_page);
 	f2fs_put_page(node_page, 1);
+	return ret;
 }
 
 int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
@@ -292,16 +328,15 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
 			inode->i_ino == F2FS_META_INO(sbi))
 		return 0;
 
-	if (!is_inode_flag_set(F2FS_I(inode), FI_DIRTY_INODE))
+	if (!is_inode_flag_set(inode, FI_DIRTY_INODE))
 		return 0;
 
 	/*
 	 * We need to balance fs here to prevent from producing dirty node pages
 	 * during the urgent cleaning time when runing out of free sections.
 	 */
-	update_inode_page(inode);
-
-	f2fs_balance_fs(sbi);
+	if (update_inode_page(inode))
+		f2fs_balance_fs(sbi, true);
 	return 0;
 }
 
@@ -311,13 +346,12 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
 void f2fs_evict_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct f2fs_inode_info *fi = F2FS_I(inode);
-	nid_t xnid = fi->i_xattr_nid;
+	nid_t xnid = F2FS_I(inode)->i_xattr_nid;
 	int err = 0;
 
 	/* 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);
@@ -327,19 +361,24 @@ void f2fs_evict_inode(struct inode *inode)
 		goto out_clear;
 
 	f2fs_bug_on(sbi, get_dirty_pages(inode));
-	remove_dirty_dir_inode(inode);
+	remove_dirty_inode(inode);
 
 	f2fs_destroy_extent_tree(inode);
 
 	if (inode->i_nlink || is_bad_inode(inode))
 		goto no_delete;
 
-	sb_start_intwrite(inode->i_sb);
-	set_inode_flag(fi, FI_NO_ALLOC);
-	i_size_write(inode, 0);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	if (time_to_inject(sbi, FAULT_EVICT_INODE))
+		goto no_delete;
+#endif
 
+	sb_start_intwrite(inode->i_sb);
+	set_inode_flag(inode, FI_NO_ALLOC);
+	i_size_write(inode, 0);
+retry:
 	if (F2FS_HAS_BLOCKS(inode))
-		err = f2fs_truncate(inode, true);
+		err = f2fs_truncate(inode);
 
 	if (!err) {
 		f2fs_lock_op(sbi);
@@ -347,6 +386,14 @@ void f2fs_evict_inode(struct inode *inode)
 		f2fs_unlock_op(sbi);
 	}
 
+	/* give more chances, if ENOMEM case */
+	if (err == -ENOMEM) {
+		err = 0;
+		goto retry;
+	}
+
+	if (err)
+		update_inode_page(inode);
 	sb_end_intwrite(inode->i_sb);
 no_delete:
 	stat_dec_inline_xattr(inode);
@@ -356,36 +403,18 @@ no_delete:
 	invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino, inode->i_ino);
 	if (xnid)
 		invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid);
-	if (is_inode_flag_set(fi, FI_APPEND_WRITE))
-		add_dirty_inode(sbi, inode->i_ino, APPEND_INO);
-	if (is_inode_flag_set(fi, FI_UPDATE_WRITE))
-		add_dirty_inode(sbi, inode->i_ino, UPDATE_INO);
-	if (is_inode_flag_set(fi, FI_FREE_NID)) {
-		if (err && err != -ENOENT)
-			alloc_nid_done(sbi, inode->i_ino);
-		else
-			alloc_nid_failed(sbi, inode->i_ino);
-		clear_inode_flag(fi, FI_FREE_NID);
-	}
-
-	if (err && err != -ENOENT) {
-		if (!exist_written_data(sbi, inode->i_ino, ORPHAN_INO)) {
-			/*
-			 * get here because we failed to release resource
-			 * of inode previously, reminder our user to run fsck
-			 * for fixing.
-			 */
-			set_sbi_flag(sbi, SBI_NEED_FSCK);
-			f2fs_msg(sbi->sb, KERN_WARNING,
-				"inode (ino:%lu) resource leak, run fsck "
-				"to fix this issue!", inode->i_ino);
-		}
+	if (is_inode_flag_set(inode, FI_APPEND_WRITE))
+		add_ino_entry(sbi, inode->i_ino, APPEND_INO);
+	if (is_inode_flag_set(inode, FI_UPDATE_WRITE))
+		add_ino_entry(sbi, inode->i_ino, UPDATE_INO);
+	if (is_inode_flag_set(inode, FI_FREE_NID)) {
+		alloc_nid_failed(sbi, inode->i_ino);
+		clear_inode_flag(inode, FI_FREE_NID);
 	}
+	f2fs_bug_on(sbi, err &&
+		!exist_written_data(sbi, inode->i_ino, ORPHAN_INO));
 out_clear:
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-	if (fi->i_crypt_info)
-		f2fs_free_encryption_info(inode, fi->i_crypt_info);
-#endif
+	fscrypt_put_encryption_info(inode, NULL);
 	clear_inode(inode);
 }
 
@@ -393,37 +422,32 @@ out_clear:
 void handle_failed_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	int err = 0;
+	struct node_info ni;
 
-	clear_nlink(inode);
-	make_bad_inode(inode);
+	/* don't make bad inode, since it becomes a regular file. */
 	unlock_new_inode(inode);
 
-	i_size_write(inode, 0);
-	if (F2FS_HAS_BLOCKS(inode))
-		err = f2fs_truncate(inode, false);
-
-	if (!err)
-		err = remove_inode_page(inode);
-
 	/*
-	 * if we skip truncate_node in remove_inode_page bacause we failed
-	 * before, it's better to find another way to release resource of
-	 * this inode (e.g. valid block count, node block or nid). Here we
-	 * choose to add this inode to orphan list, so that we can call iput
-	 * for releasing in orphan recovery flow.
-	 *
 	 * Note: we should add inode to orphan list before f2fs_unlock_op()
 	 * so we can prevent losing this orphan when encoutering checkpoint
 	 * and following suddenly power-off.
 	 */
-	if (err && err != -ENOENT) {
-		err = acquire_orphan_inode(sbi);
-		if (!err)
-			add_orphan_inode(sbi, inode->i_ino);
+	get_node_info(sbi, inode->i_ino, &ni);
+
+	if (ni.blk_addr != NULL_ADDR) {
+		int err = acquire_orphan_inode(sbi);
+		if (err) {
+			set_sbi_flag(sbi, SBI_NEED_FSCK);
+			f2fs_msg(sbi->sb, KERN_WARNING,
+				"Too many orphan inodes, run fsck to fix.");
+		} else {
+			add_orphan_inode(inode);
+		}
+		alloc_nid_done(sbi, inode->i_ino);
+	} else {
+		set_inode_flag(inode, FI_FREE_NID);
 	}
 
-	set_inode_flag(F2FS_I(inode), FI_FREE_NID);
 	f2fs_unlock_op(sbi);
 
 	/* iput will drop the inode object */

fs/f2fs/namei.c

@@ -60,10 +60,14 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 	if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode))
 		f2fs_set_encrypted_inode(inode);
 
-	if (f2fs_may_inline_data(inode))
-		set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
+	set_inode_flag(inode, FI_NEW_INODE);
+
+	if (test_opt(sbi, INLINE_XATTR))
+		set_inode_flag(inode, FI_INLINE_XATTR);
+	if (test_opt(sbi, INLINE_DATA) && f2fs_may_inline_data(inode))
+		set_inode_flag(inode, FI_INLINE_DATA);
 	if (f2fs_may_inline_dentry(inode))
-		set_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY);
+		set_inode_flag(inode, FI_INLINE_DENTRY);
 
 	f2fs_init_extent_tree(inode, NULL);
 
@@ -72,14 +76,13 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 	stat_inc_inline_dir(inode);
 
 	trace_f2fs_new_inode(inode, 0);
-	mark_inode_dirty(inode);
 	return inode;
 
 fail:
 	trace_f2fs_new_inode(inode, err);
 	make_bad_inode(inode);
 	if (nid_free)
-		set_inode_flag(F2FS_I(inode), FI_FREE_NID);
+		set_inode_flag(inode, FI_FREE_NID);
 	iput(inode);
 	return ERR_PTR(err);
 }
@@ -88,18 +91,23 @@ static int is_multimedia_file(const unsigned char *s, const char *sub)
 {
 	size_t slen = strlen(s);
 	size_t sublen = strlen(sub);
+	int i;
 
 	/*
 	 * filename format of multimedia file should be defined as:
-	 * "filename + '.' + extension".
+	 * "filename + '.' + extension + (optional: '.' + temp extension)".
 	 */
 	if (slen < sublen + 2)
 		return 0;
 
-	if (s[slen - sublen - 1] != '.')
-		return 0;
+	for (i = 1; i < slen - sublen; i++) {
+		if (s[i] != '.')
+			continue;
+		if (!strncasecmp(s + i + 1, sub, sublen))
+			return 1;
+	}
 
-	return !strncasecmp(s + slen - sublen, sub, sublen);
+	return 0;
 }
 
 /*
@@ -128,8 +136,6 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	nid_t ino = 0;
 	int err;
 
-	f2fs_balance_fs(sbi);
-
 	inode = f2fs_new_inode(dir, mode);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -142,6 +148,8 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	inode->i_mapping->a_ops = &f2fs_dblock_aops;
 	ino = inode->i_ino;
 
+	f2fs_balance_fs(sbi, true);
+
 	f2fs_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
 	if (err)
@@ -169,15 +177,15 @@ 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);
+	f2fs_balance_fs(sbi, true);
 
 	inode->i_ctime = CURRENT_TIME;
 	ihold(inode);
 
-	set_inode_flag(F2FS_I(inode), FI_INC_LINK);
+	set_inode_flag(inode, FI_INC_LINK);
 	f2fs_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
 	if (err)
@@ -190,7 +198,7 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
 		f2fs_sync_fs(sbi->sb, 1);
 	return 0;
 out:
-	clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
+	clear_inode_flag(inode, FI_INC_LINK);
 	iput(inode);
 	f2fs_unlock_op(sbi);
 	return err;
@@ -199,10 +207,14 @@ out:
 struct dentry *f2fs_get_parent(struct dentry *child)
 {
 	struct qstr dotdot = QSTR_INIT("..", 2);
-	unsigned long ino = f2fs_inode_by_name(d_inode(child), &dotdot);
-	if (!ino)
+	struct page *page;
+	unsigned long ino = f2fs_inode_by_name(d_inode(child), &dotdot, &page);
+	if (!ino) {
+		if (IS_ERR(page))
+			return ERR_CAST(page);
 		return ERR_PTR(-ENOENT);
-	return d_obtain_alias(f2fs_iget(d_inode(child)->i_sb, ino));
+	}
+	return d_obtain_alias(f2fs_iget(child->d_sb, ino));
 }
 
 static int __recover_dot_dentries(struct inode *dir, nid_t pino)
@@ -214,12 +226,24 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino)
 	struct page *page;
 	int err = 0;
 
+	if (f2fs_readonly(sbi->sb)) {
+		f2fs_msg(sbi->sb, KERN_INFO,
+			"skip recovering inline_dots inode (ino:%lu, pino:%u) "
+			"in readonly mountpoint", dir->i_ino, pino);
+		return 0;
+	}
+
+	f2fs_balance_fs(sbi, true);
+
 	f2fs_lock_op(sbi);
 
 	de = f2fs_find_entry(dir, &dot, &page);
 	if (de) {
 		f2fs_dentry_kunmap(dir, page);
 		f2fs_put_page(page, 0);
+	} else if (IS_ERR(page)) {
+		err = PTR_ERR(page);
+		goto out;
 	} else {
 		err = __f2fs_add_link(dir, &dot, NULL, dir->i_ino, S_IFDIR);
 		if (err)
@@ -230,14 +254,14 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino)
 	if (de) {
 		f2fs_dentry_kunmap(dir, page);
 		f2fs_put_page(page, 0);
+	} else if (IS_ERR(page)) {
+		err = PTR_ERR(page);
 	} else {
 		err = __f2fs_add_link(dir, &dotdot, NULL, pino, S_IFDIR);
 	}
 out:
-	if (!err) {
-		clear_inode_flag(F2FS_I(dir), FI_INLINE_DOTS);
-		mark_inode_dirty(dir);
-	}
+	if (!err)
+		clear_inode_flag(dir, FI_INLINE_DOTS);
 
 	f2fs_unlock_op(sbi);
 	return err;
@@ -251,13 +275,32 @@ 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);
 
 	de = f2fs_find_entry(dir, &dentry->d_name, &page);
-	if (!de)
+	if (!de) {
+		if (IS_ERR(page))
+			return (struct dentry *)page;
 		return d_splice_alias(inode, dentry);
+	}
 
 	ino = le32_to_cpu(de->ino);
 	f2fs_dentry_kunmap(dir, page);
@@ -267,15 +310,29 @@ 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);
 }
 
@@ -288,11 +345,15 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
 	int err = -ENOENT;
 
 	trace_f2fs_unlink_enter(dir, dentry);
-	f2fs_balance_fs(sbi);
 
 	de = f2fs_find_entry(dir, &dentry->d_name, &page);
-	if (!de)
+	if (!de) {
+		if (IS_ERR(page))
+			err = PTR_ERR(page);
 		goto fail;
+	}
+
+	f2fs_balance_fs(sbi, true);
 
 	f2fs_lock_op(sbi);
 	err = acquire_orphan_inode(sbi);
@@ -305,9 +366,6 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
 	f2fs_delete_entry(de, page, dir, inode);
 	f2fs_unlock_op(sbi);
 
-	/* In order to evict this inode, we set it dirty */
-	mark_inode_dirty(inode);
-
 	if (IS_DIRSYNC(dir))
 		f2fs_sync_fs(sbi->sb, 1);
 fail:
@@ -332,16 +390,24 @@ 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;
-	char *p_str;
-	struct f2fs_str disk_link = FSTR_INIT(NULL, 0);
-	struct f2fs_encrypted_symlink_data *sd = NULL;
+	struct fscrypt_str disk_link = FSTR_INIT((char *)symname, len + 1);
+	struct fscrypt_symlink_data *sd = NULL;
 	int err;
 
-	if (len > dir->i_sb->s_blocksize)
-		return -ENAMETOOLONG;
+	if (f2fs_encrypted_inode(dir)) {
+		err = fscrypt_get_encryption_info(dir);
+		if (err)
+			return err;
 
-	f2fs_balance_fs(sbi);
+		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);
 	if (IS_ERR(inode))
@@ -351,8 +417,11 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 		inode->i_op = &f2fs_encrypted_symlink_inode_operations;
 	else
 		inode->i_op = &f2fs_symlink_inode_operations;
+	inode_nohighmem(inode);
 	inode->i_mapping->a_ops = &f2fs_dblock_aops;
 
+	f2fs_balance_fs(sbi, true);
+
 	f2fs_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
 	if (err)
@@ -360,42 +429,36 @@ 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);
-		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);
+		sd = kzalloc(disk_link.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);
-		p_str = (char *)sd;
-	} else {
-		p_len = len + 1;
-		p_str = (char *)symname;
+
+		err = fscrypt_get_encryption_info(inode);
+		if (err)
+			goto err_out;
+
+		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);
@@ -411,7 +474,8 @@ 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);
@@ -420,7 +484,6 @@ err_out:
 	}
 
 	kfree(sd);
-	f2fs_fname_crypto_free_buffer(&disk_link);
 	return err;
 out:
 	handle_failed_inode(inode);
@@ -433,8 +496,6 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	struct inode *inode;
 	int err;
 
-	f2fs_balance_fs(sbi);
-
 	inode = f2fs_new_inode(dir, S_IFDIR | mode);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -444,7 +505,9 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	inode->i_mapping->a_ops = &f2fs_dblock_aops;
 	mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO);
 
-	set_inode_flag(F2FS_I(inode), FI_INC_LINK);
+	f2fs_balance_fs(sbi, true);
+
+	set_inode_flag(inode, FI_INC_LINK);
 	f2fs_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
 	if (err)
@@ -461,7 +524,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	return 0;
 
 out_fail:
-	clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
+	clear_inode_flag(inode, FI_INC_LINK);
 	handle_failed_inode(inode);
 	return err;
 }
@@ -481,8 +544,6 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
 	struct inode *inode;
 	int err = 0;
 
-	f2fs_balance_fs(sbi);
-
 	inode = f2fs_new_inode(dir, mode);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -490,6 +551,8 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
 	init_special_inode(inode, inode->i_mode, rdev);
 	inode->i_op = &f2fs_special_inode_operations;
 
+	f2fs_balance_fs(sbi, true);
+
 	f2fs_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
 	if (err)
@@ -516,9 +579,6 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
 	struct inode *inode;
 	int err;
 
-	if (!whiteout)
-		f2fs_balance_fs(sbi);
-
 	inode = f2fs_new_inode(dir, mode);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -532,6 +592,8 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
 		inode->i_mapping->a_ops = &f2fs_dblock_aops;
 	}
 
+	f2fs_balance_fs(sbi, true);
+
 	f2fs_lock_op(sbi);
 	err = acquire_orphan_inode(sbi);
 	if (err)
@@ -545,17 +607,17 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
 	 * add this non-linked tmpfile to orphan list, in this way we could
 	 * remove all unused data of tmpfile after abnormal power-off.
 	 */
-	add_orphan_inode(sbi, inode->i_ino);
-	f2fs_unlock_op(sbi);
-
+	add_orphan_inode(inode);
 	alloc_nid_done(sbi, inode->i_ino);
 
 	if (whiteout) {
-		inode_dec_link_count(inode);
+		f2fs_i_links_write(inode, false);
 		*whiteout = inode;
 	} else {
 		d_tmpfile(dentry, inode);
 	}
+	/* link_count was changed by d_tmpfile as well. */
+	f2fs_unlock_op(sbi);
 	unlock_new_inode(inode);
 	return 0;
 
@@ -569,7 +631,7 @@ 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;
 	}
@@ -595,26 +657,29 @@ 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,
-							old_inode)) {
+			!fscrypt_has_permitted_context(new_dir, old_inode)) {
 		err = -EPERM;
 		goto out;
 	}
 
-	f2fs_balance_fs(sbi);
-
 	old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
-	if (!old_entry)
+	if (!old_entry) {
+		if (IS_ERR(old_page))
+			err = PTR_ERR(old_page);
 		goto out;
+	}
 
 	if (S_ISDIR(old_inode->i_mode)) {
-		err = -EIO;
 		old_dir_entry = f2fs_parent_dir(old_inode, &old_dir_page);
-		if (!old_dir_entry)
+		if (!old_dir_entry) {
+			if (IS_ERR(old_dir_page))
+				err = PTR_ERR(old_dir_page);
 			goto out_old;
+		}
 	}
 
 	if (flags & RENAME_WHITEOUT) {
@@ -632,8 +697,13 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		err = -ENOENT;
 		new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name,
 						&new_page);
-		if (!new_entry)
+		if (!new_entry) {
+			if (IS_ERR(new_page))
+				err = PTR_ERR(new_page);
 			goto out_whiteout;
+		}
+
+		f2fs_balance_fs(sbi, true);
 
 		f2fs_lock_op(sbi);
 
@@ -641,8 +711,9 @@ 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,
-						&new_dentry->d_name)) {
+		err = update_dent_inode(old_inode, new_inode,
+						&new_dentry->d_name);
+		if (err) {
 			release_orphan_inode(sbi);
 			goto put_out_dir;
 		}
@@ -652,20 +723,17 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		new_inode->i_ctime = CURRENT_TIME;
 		down_write(&F2FS_I(new_inode)->i_sem);
 		if (old_dir_entry)
-			drop_nlink(new_inode);
-		drop_nlink(new_inode);
+			f2fs_i_links_write(new_inode, false);
+		f2fs_i_links_write(new_inode, false);
 		up_write(&F2FS_I(new_inode)->i_sem);
 
-		mark_inode_dirty(new_inode);
-
 		if (!new_inode->i_nlink)
-			add_orphan_inode(sbi, new_inode->i_ino);
+			add_orphan_inode(new_inode);
 		else
 			release_orphan_inode(sbi);
-
-		update_inode_page(old_inode);
-		update_inode_page(new_inode);
 	} else {
+		f2fs_balance_fs(sbi, true);
+
 		f2fs_lock_op(sbi);
 
 		err = f2fs_add_link(new_dentry, old_inode);
@@ -674,9 +742,29 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			goto out_whiteout;
 		}
 
-		if (old_dir_entry) {
-			inc_nlink(new_dir);
-			update_inode_page(new_dir);
+		if (old_dir_entry)
+			f2fs_i_links_write(new_dir, true);
+
+		/*
+		 * 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 = -ENOENT;
+				if (IS_ERR(old_page))
+					err = PTR_ERR(old_page);
+				f2fs_unlock_op(sbi);
+				goto out_whiteout;
+			}
 		}
 	}
 
@@ -687,13 +775,13 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	up_write(&F2FS_I(old_inode)->i_sem);
 
 	old_inode->i_ctime = CURRENT_TIME;
-	mark_inode_dirty(old_inode);
+	f2fs_mark_inode_dirty_sync(old_inode);
 
 	f2fs_delete_entry(old_entry, old_page, old_dir, NULL);
 
 	if (whiteout) {
 		whiteout->i_state |= I_LINKABLE;
-		set_inode_flag(F2FS_I(whiteout), FI_INC_LINK);
+		set_inode_flag(whiteout, FI_INC_LINK);
 		err = f2fs_add_link(old_dentry, whiteout);
 		if (err)
 			goto put_out_dir;
@@ -705,14 +793,11 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (old_dir != new_dir && !whiteout) {
 			f2fs_set_link(old_inode, old_dir_entry,
 						old_dir_page, new_dir);
-			update_inode_page(old_inode);
 		} else {
 			f2fs_dentry_kunmap(old_inode, old_dir_page);
 			f2fs_put_page(old_dir_page, 0);
 		}
-		drop_nlink(old_dir);
-		mark_inode_dirty(old_dir);
-		update_inode_page(old_dir);
+		f2fs_i_links_write(old_dir, false);
 	}
 
 	f2fs_unlock_op(sbi);
@@ -756,39 +841,45 @@ 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) &&
-		(!f2fs_is_child_context_consistent_with_parent(new_dir,
-								old_inode) ||
-		!f2fs_is_child_context_consistent_with_parent(old_dir,
-								new_inode)))
+			(old_dir != new_dir) &&
+			(!fscrypt_has_permitted_context(new_dir, old_inode) ||
+			 !fscrypt_has_permitted_context(old_dir, new_inode)))
 		return -EPERM;
 
-	f2fs_balance_fs(sbi);
-
 	old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
-	if (!old_entry)
+	if (!old_entry) {
+		if (IS_ERR(old_page))
+			err = PTR_ERR(old_page);
 		goto out;
+	}
 
 	new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name, &new_page);
-	if (!new_entry)
+	if (!new_entry) {
+		if (IS_ERR(new_page))
+			err = PTR_ERR(new_page);
 		goto out_old;
+	}
 
 	/* prepare for updating ".." directory entry info later */
 	if (old_dir != new_dir) {
 		if (S_ISDIR(old_inode->i_mode)) {
-			err = -EIO;
 			old_dir_entry = f2fs_parent_dir(old_inode,
 							&old_dir_page);
-			if (!old_dir_entry)
+			if (!old_dir_entry) {
+				if (IS_ERR(old_dir_page))
+					err = PTR_ERR(old_dir_page);
 				goto out_new;
+			}
 		}
 
 		if (S_ISDIR(new_inode->i_mode)) {
-			err = -EIO;
 			new_dir_entry = f2fs_parent_dir(new_inode,
 							&new_dir_page);
-			if (!new_dir_entry)
+			if (!new_dir_entry) {
+				if (IS_ERR(new_dir_page))
+					err = PTR_ERR(new_dir_page);
 				goto out_old_dir;
+			}
 		}
 	}
 
@@ -807,6 +898,8 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 			goto out_new_dir;
 	}
 
+	f2fs_balance_fs(sbi, true);
+
 	f2fs_lock_op(sbi);
 
 	err = update_dent_inode(old_inode, new_inode, &new_dentry->d_name);
@@ -836,19 +929,13 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 	file_lost_pino(old_inode);
 	up_write(&F2FS_I(old_inode)->i_sem);
 
-	update_inode_page(old_inode);
-
 	old_dir->i_ctime = CURRENT_TIME;
 	if (old_nlink) {
 		down_write(&F2FS_I(old_dir)->i_sem);
-		if (old_nlink < 0)
-			drop_nlink(old_dir);
-		else
-			inc_nlink(old_dir);
+		f2fs_i_links_write(old_dir, old_nlink > 0);
 		up_write(&F2FS_I(old_dir)->i_sem);
 	}
-	mark_inode_dirty(old_dir);
-	update_inode_page(old_dir);
+	f2fs_mark_inode_dirty_sync(old_dir);
 
 	/* update directory entry info of new dir inode */
 	f2fs_set_link(new_dir, new_entry, new_page, old_inode);
@@ -857,19 +944,13 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 	file_lost_pino(new_inode);
 	up_write(&F2FS_I(new_inode)->i_sem);
 
-	update_inode_page(new_inode);
-
 	new_dir->i_ctime = CURRENT_TIME;
 	if (new_nlink) {
 		down_write(&F2FS_I(new_dir)->i_sem);
-		if (new_nlink < 0)
-			drop_nlink(new_dir);
-		else
-			inc_nlink(new_dir);
+		f2fs_i_links_write(new_dir, new_nlink > 0);
 		up_write(&F2FS_I(new_dir)->i_sem);
 	}
-	mark_inode_dirty(new_dir);
-	update_inode_page(new_dir);
+	f2fs_mark_inode_dirty_sync(new_dir);
 
 	f2fs_unlock_op(sbi);
 
@@ -922,89 +1003,85 @@ 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_follow_link(struct dentry *dentry, void **cookie)
 {
 	struct page *cpage = NULL;
 	char *caddr, *paddr = NULL;
-	struct f2fs_str cstr;
-	struct f2fs_str pstr = FSTR_INIT(NULL, 0);
+	struct fscrypt_str cstr = FSTR_INIT(NULL, 0);
+	struct fscrypt_str pstr = FSTR_INIT(NULL, 0);
+	struct fscrypt_symlink_data *sd;
 	struct inode *inode = d_inode(dentry);
-	struct f2fs_encrypted_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;
 
-	res = f2fs_get_encryption_info(inode);
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
+	res = fscrypt_get_encryption_info(inode);
 	if (res)
 		return ERR_PTR(res);
 
 	cpage = read_mapping_page(inode->i_mapping, 0, NULL);
 	if (IS_ERR(cpage))
 		return ERR_CAST(cpage);
-	caddr = kmap(cpage);
-	caddr[size] = 0;
+	caddr = page_address(cpage);
 
 	/* 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);
-	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 (cstr.name[0] == 0 && cstr.len == 0) {
+	if (unlikely(cstr.len == 0)) {
 		res = -ENOENT;
 		goto errout;
 	}
 
-	if ((cstr.len + sizeof(struct f2fs_encrypted_symlink_data) - 1) >
-								max_size) {
+	if ((cstr.len + sizeof(struct fscrypt_symlink_data) - 1) > 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);
+	/* this is broken symlink case */
+	if (unlikely(pstr.name[0] == 0)) {
+		res = -ENOENT;
+		goto errout;
+	}
 
 	paddr = pstr.name;
 
 	/* Null-terminate the name */
 	paddr[res] = '\0';
 
-	kunmap(cpage);
-	page_cache_release(cpage);
+	put_page(cpage);
 	return *cookie = paddr;
 errout:
-	kfree(cstr.name);
-	f2fs_fname_crypto_free_buffer(&pstr);
-	kunmap(cpage);
-	page_cache_release(cpage);
+	fscrypt_fname_free_buffer(&pstr);
+	put_page(cpage);
 	return ERR_PTR(res);
 }
 
 const struct inode_operations f2fs_encrypted_symlink_inode_operations = {
 	.readlink       = generic_readlink,
-	.follow_link    = f2fs_encrypted_follow_link,
-	.put_link       = kfree_put_link,
+	.follow_link	= f2fs_encrypted_follow_link,
+	.put_link	= kfree_put_link,
 	.getattr	= f2fs_getattr,
 	.setattr	= f2fs_setattr,
+#ifdef CONFIG_F2FS_FS_XATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
 	.listxattr	= f2fs_listxattr,
 	.removexattr	= generic_removexattr,
-};
 #endif
+};
 
 const struct inode_operations f2fs_dir_inode_operations = {
 	.create		= f2fs_create,

fs/f2fs/node.h

@@ -15,15 +15,21 @@
 #define	NAT_BLOCK_OFFSET(start_nid) (start_nid / NAT_ENTRY_PER_BLOCK)
 
 /* # of pages to perform synchronous readahead before building free nids */
-#define FREE_NID_PAGES 4
+#define FREE_NID_PAGES	8
+#define MAX_FREE_NIDS	(NAT_ENTRY_PER_BLOCK * FREE_NID_PAGES)
 
-#define DEF_RA_NID_PAGES	4	/* # of nid pages to be readaheaded */
+#define DEF_RA_NID_PAGES	0	/* # of nid pages to be readaheaded */
 
 /* maximum readahead size for node during getting data blocks */
 #define MAX_RA_NODE		128
 
 /* control the memory footprint threshold (10MB per 1GB ram) */
-#define DEF_RAM_THRESHOLD	10
+#define DEF_RAM_THRESHOLD	1
+
+/* control dirty nats ratio threshold (default: 10% over max nid count) */
+#define DEF_DIRTY_NAT_RATIO_THRESHOLD		10
+/* control total # of nats */
+#define DEF_NAT_CACHE_THRESHOLD			100000
 
 /* vector size for gang look-up from nat cache that consists of radix tree */
 #define NATVEC_SIZE	64
@@ -117,6 +123,17 @@ 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;
+}
+
+static inline bool excess_cached_nats(struct f2fs_sb_info *sbi)
+{
+	return NM_I(sbi)->nat_cnt >= DEF_NAT_CACHE_THRESHOLD;
+}
+
 enum mem_type {
 	FREE_NIDS,	/* indicates the free nid list */
 	NAT_ENTRIES,	/* indicates the cached nat entry */
@@ -183,7 +200,7 @@ static inline pgoff_t current_nat_addr(struct f2fs_sb_info *sbi, nid_t start)
 
 	block_addr = (pgoff_t)(nm_i->nat_blkaddr +
 		(seg_off << sbi->log_blocks_per_seg << 1) +
-		(block_off & ((1 << sbi->log_blocks_per_seg) - 1)));
+		(block_off & (sbi->blocks_per_seg - 1)));
 
 	if (f2fs_test_bit(block_off, nm_i->nat_bitmap))
 		block_addr += sbi->blocks_per_seg;
@@ -212,6 +229,37 @@ static inline void set_to_next_nat(struct f2fs_nm_info *nm_i, nid_t start_nid)
 	f2fs_change_bit(block_off, nm_i->nat_bitmap);
 }
 
+static inline nid_t ino_of_node(struct page *node_page)
+{
+	struct f2fs_node *rn = F2FS_NODE(node_page);
+	return le32_to_cpu(rn->footer.ino);
+}
+
+static inline nid_t nid_of_node(struct page *node_page)
+{
+	struct f2fs_node *rn = F2FS_NODE(node_page);
+	return le32_to_cpu(rn->footer.nid);
+}
+
+static inline unsigned int ofs_of_node(struct page *node_page)
+{
+	struct f2fs_node *rn = F2FS_NODE(node_page);
+	unsigned flag = le32_to_cpu(rn->footer.flag);
+	return flag >> OFFSET_BIT_SHIFT;
+}
+
+static inline __u64 cpver_of_node(struct page *node_page)
+{
+	struct f2fs_node *rn = F2FS_NODE(node_page);
+	return le64_to_cpu(rn->footer.cp_ver);
+}
+
+static inline block_t next_blkaddr_of_node(struct page *node_page)
+{
+	struct f2fs_node *rn = F2FS_NODE(node_page);
+	return le32_to_cpu(rn->footer.next_blkaddr);
+}
+
 static inline void fill_node_footer(struct page *page, nid_t nid,
 				nid_t ino, unsigned int ofs, bool reset)
 {
@@ -242,40 +290,30 @@ static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
 	struct f2fs_node *rn = F2FS_NODE(page);
+	size_t crc_offset = le32_to_cpu(ckpt->checksum_offset);
+	__u64 cp_ver = le64_to_cpu(ckpt->checkpoint_ver);
 
-	rn->footer.cp_ver = ckpt->checkpoint_ver;
+	if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG)) {
+		__u64 crc = le32_to_cpu(*((__le32 *)
+				((unsigned char *)ckpt + crc_offset)));
+		cp_ver |= (crc << 32);
+	}
+	rn->footer.cp_ver = cpu_to_le64(cp_ver);
 	rn->footer.next_blkaddr = cpu_to_le32(blkaddr);
 }
 
-static inline nid_t ino_of_node(struct page *node_page)
+static inline bool is_recoverable_dnode(struct page *page)
 {
-	struct f2fs_node *rn = F2FS_NODE(node_page);
-	return le32_to_cpu(rn->footer.ino);
-}
+	struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
+	size_t crc_offset = le32_to_cpu(ckpt->checksum_offset);
+	__u64 cp_ver = cur_cp_version(ckpt);
 
-static inline nid_t nid_of_node(struct page *node_page)
-{
-	struct f2fs_node *rn = F2FS_NODE(node_page);
-	return le32_to_cpu(rn->footer.nid);
-}
-
-static inline unsigned int ofs_of_node(struct page *node_page)
-{
-	struct f2fs_node *rn = F2FS_NODE(node_page);
-	unsigned flag = le32_to_cpu(rn->footer.flag);
-	return flag >> OFFSET_BIT_SHIFT;
-}
-
-static inline unsigned long long cpver_of_node(struct page *node_page)
-{
-	struct f2fs_node *rn = F2FS_NODE(node_page);
-	return le64_to_cpu(rn->footer.cp_ver);
-}
-
-static inline block_t next_blkaddr_of_node(struct page *node_page)
-{
-	struct f2fs_node *rn = F2FS_NODE(node_page);
-	return le32_to_cpu(rn->footer.next_blkaddr);
+	if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG)) {
+		__u64 crc = le32_to_cpu(*((__le32 *)
+				((unsigned char *)ckpt + crc_offset)));
+		cp_ver |= (crc << 32);
+	}
+	return cpu_to_le64(cp_ver) == cpver_of_node(page);
 }
 
 /*
@@ -317,17 +355,17 @@ static inline bool IS_DNODE(struct page *node_page)
 	return true;
 }
 
-static inline void set_nid(struct page *p, int off, nid_t nid, bool i)
+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);
 	else
 		rn->in.nid[off] = cpu_to_le32(nid);
-	set_page_dirty(p);
+	return set_page_dirty(p);
 }
 
 static inline nid_t get_nid(struct page *p, int off, bool i)
@@ -370,6 +408,21 @@ 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

@@ -49,8 +49,9 @@ static struct kmem_cache *fsync_entry_slab;
 
 bool space_for_roll_forward(struct f2fs_sb_info *sbi)
 {
-	if (sbi->last_valid_block_count + sbi->alloc_valid_block_count
-			> sbi->user_block_count)
+	s64 nalloc = percpu_counter_sum_positive(&sbi->alloc_valid_block_count);
+
+	if (sbi->last_valid_block_count + nalloc > sbi->user_block_count)
 		return false;
 	return true;
 }
@@ -67,42 +68,71 @@ static struct fsync_inode_entry *get_fsync_inode(struct list_head *head,
 	return NULL;
 }
 
-static int recover_dentry(struct inode *inode, struct page *ipage)
+static struct fsync_inode_entry *add_fsync_inode(struct f2fs_sb_info *sbi,
+					struct list_head *head, nid_t ino)
+{
+	struct inode *inode;
+	struct fsync_inode_entry *entry;
+
+	inode = f2fs_iget_retry(sbi->sb, ino);
+	if (IS_ERR(inode))
+		return ERR_CAST(inode);
+
+	entry = f2fs_kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
+	entry->inode = inode;
+	list_add_tail(&entry->list, head);
+
+	return entry;
+}
+
+static void del_fsync_inode(struct fsync_inode_entry *entry)
+{
+	iput(entry->inode);
+	list_del(&entry->list);
+	kmem_cache_free(fsync_entry_slab, entry);
+}
+
+static int recover_dentry(struct inode *inode, struct page *ipage,
+						struct list_head *dir_list)
 {
 	struct f2fs_inode *raw_inode = F2FS_INODE(ipage);
 	nid_t pino = le32_to_cpu(raw_inode->i_pino);
 	struct f2fs_dir_entry *de;
-	struct qstr name;
+	struct fscrypt_name fname;
 	struct page *page;
 	struct inode *dir, *einode;
+	struct fsync_inode_entry *entry;
 	int err = 0;
+	char *name;
 
-	dir = f2fs_iget(inode->i_sb, pino);
-	if (IS_ERR(dir)) {
-		err = PTR_ERR(dir);
-		goto out;
+	entry = get_fsync_inode(dir_list, pino);
+	if (!entry) {
+		entry = add_fsync_inode(F2FS_I_SB(inode), dir_list, pino);
+		if (IS_ERR(entry)) {
+			dir = ERR_CAST(entry);
+			err = PTR_ERR(entry);
+			goto out;
+		}
 	}
 
-	if (file_enc_name(inode)) {
-		iput(dir);
-		return 0;
-	}
+	dir = entry->inode;
 
-	name.len = le32_to_cpu(raw_inode->i_namelen);
-	name.name = raw_inode->i_name;
+	memset(&fname, 0, sizeof(struct fscrypt_name));
+	fname.disk_name.len = le32_to_cpu(raw_inode->i_namelen);
+	fname.disk_name.name = raw_inode->i_name;
 
-	if (unlikely(name.len > F2FS_NAME_LEN)) {
+	if (unlikely(fname.disk_name.len > F2FS_NAME_LEN)) {
 		WARN_ON(1);
 		err = -ENAMETOOLONG;
-		goto out_err;
+		goto out;
 	}
 retry:
-	de = f2fs_find_entry(dir, &name, &page);
+	de = __f2fs_find_entry(dir, &fname, &page);
 	if (de && inode->i_ino == le32_to_cpu(de->ino))
 		goto out_unmap_put;
 
 	if (de) {
-		einode = f2fs_iget(inode->i_sb, le32_to_cpu(de->ino));
+		einode = f2fs_iget_retry(inode->i_sb, le32_to_cpu(de->ino));
 		if (IS_ERR(einode)) {
 			WARN_ON(1);
 			err = PTR_ERR(einode);
@@ -118,29 +148,27 @@ retry:
 		f2fs_delete_entry(de, page, dir, einode);
 		iput(einode);
 		goto retry;
-	}
-	err = __f2fs_add_link(dir, &name, inode, inode->i_ino, inode->i_mode);
-	if (err)
-		goto out_err;
-
-	if (is_inode_flag_set(F2FS_I(dir), FI_DELAY_IPUT)) {
-		iput(dir);
+	} else if (IS_ERR(page)) {
+		err = PTR_ERR(page);
 	} else {
-		add_dirty_dir_inode(dir);
-		set_inode_flag(F2FS_I(dir), FI_DELAY_IPUT);
+		err = __f2fs_do_add_link(dir, &fname, inode,
+					inode->i_ino, inode->i_mode);
 	}
-
+	if (err == -ENOMEM)
+		goto retry;
 	goto out;
 
 out_unmap_put:
 	f2fs_dentry_kunmap(dir, page);
 	f2fs_put_page(page, 0);
-out_err:
-	iput(dir);
 out:
+	if (file_enc_name(inode))
+		name = "<encrypted>";
+	else
+		name = raw_inode->i_name;
 	f2fs_msg(inode->i_sb, KERN_NOTICE,
 			"%s: ino = %x, name = %s, dir = %lx, err = %d",
-			__func__, ino_of_node(ipage), raw_inode->i_name,
+			__func__, ino_of_node(ipage), name,
 			IS_ERR(dir) ? 0 : dir->i_ino, err);
 	return err;
 }
@@ -151,7 +179,7 @@ static void recover_inode(struct inode *inode, struct page *page)
 	char *name;
 
 	inode->i_mode = le16_to_cpu(raw->i_mode);
-	i_size_write(inode, le64_to_cpu(raw->i_size));
+	f2fs_i_size_write(inode, le64_to_cpu(raw->i_size));
 	inode->i_atime.tv_sec = le64_to_cpu(raw->i_mtime);
 	inode->i_ctime.tv_sec = le64_to_cpu(raw->i_ctime);
 	inode->i_mtime.tv_sec = le64_to_cpu(raw->i_mtime);
@@ -168,9 +196,34 @@ static void recover_inode(struct inode *inode, struct page *page)
 			ino_of_node(page), name);
 }
 
+static bool is_same_inode(struct inode *inode, struct page *ipage)
+{
+	struct f2fs_inode *ri = F2FS_INODE(ipage);
+	struct timespec disk;
+
+	if (!IS_INODE(ipage))
+		return true;
+
+	disk.tv_sec = le64_to_cpu(ri->i_ctime);
+	disk.tv_nsec = le32_to_cpu(ri->i_ctime_nsec);
+	if (timespec_compare(&inode->i_ctime, &disk) > 0)
+		return false;
+
+	disk.tv_sec = le64_to_cpu(ri->i_atime);
+	disk.tv_nsec = le32_to_cpu(ri->i_atime_nsec);
+	if (timespec_compare(&inode->i_atime, &disk) > 0)
+		return false;
+
+	disk.tv_sec = le64_to_cpu(ri->i_mtime);
+	disk.tv_nsec = le32_to_cpu(ri->i_mtime_nsec);
+	if (timespec_compare(&inode->i_mtime, &disk) > 0)
+		return false;
+
+	return true;
+}
+
 static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 {
-	unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
 	struct curseg_info *curseg;
 	struct page *page = NULL;
 	block_t blkaddr;
@@ -180,8 +233,6 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 	curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
 	blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
 
-	ra_meta_pages(sbi, blkaddr, 1, META_POR, true);
-
 	while (1) {
 		struct fsync_inode_entry *entry;
 
@@ -190,49 +241,41 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 
 		page = get_tmp_page(sbi, blkaddr);
 
-		if (cp_ver != cpver_of_node(page))
+		if (!is_recoverable_dnode(page))
 			break;
 
 		if (!is_fsync_dnode(page))
 			goto next;
 
 		entry = get_fsync_inode(head, ino_of_node(page));
-		if (!entry) {
+		if (entry) {
+			if (!is_same_inode(entry->inode, page))
+				goto next;
+		} else {
 			if (IS_INODE(page) && is_dent_dnode(page)) {
 				err = recover_inode_page(sbi, page);
 				if (err)
 					break;
 			}
 
-			/* add this fsync inode to the list */
-			entry = kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
-			if (!entry) {
-				err = -ENOMEM;
-				break;
-			}
 			/*
 			 * CP | dnode(F) | inode(DF)
 			 * For this case, we should not give up now.
 			 */
-			entry->inode = f2fs_iget(sbi->sb, ino_of_node(page));
-			if (IS_ERR(entry->inode)) {
-				err = PTR_ERR(entry->inode);
-				kmem_cache_free(fsync_entry_slab, entry);
+			entry = add_fsync_inode(sbi, head, ino_of_node(page));
+			if (IS_ERR(entry)) {
+				err = PTR_ERR(entry);
 				if (err == -ENOENT) {
 					err = 0;
 					goto next;
 				}
 				break;
 			}
-			list_add_tail(&entry->list, head);
 		}
 		entry->blkaddr = blkaddr;
 
-		if (IS_INODE(page)) {
-			entry->last_inode = blkaddr;
-			if (is_dent_dnode(page))
-				entry->last_dentry = blkaddr;
-		}
+		if (IS_INODE(page) && is_dent_dnode(page))
+			entry->last_dentry = blkaddr;
 next:
 		/* check next segment */
 		blkaddr = next_blkaddr_of_node(page);
@@ -248,11 +291,8 @@ static void destroy_fsync_dnodes(struct list_head *head)
 {
 	struct fsync_inode_entry *entry, *tmp;
 
-	list_for_each_entry_safe(entry, tmp, head, list) {
-		iput(entry->inode);
-		list_del(&entry->list);
-		kmem_cache_free(fsync_entry_slab, entry);
-	}
+	list_for_each_entry_safe(entry, tmp, head, list)
+		del_fsync_inode(entry);
 }
 
 static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
@@ -314,15 +354,14 @@ got_it:
 
 	if (ino != dn->inode->i_ino) {
 		/* Deallocate previous index in the node page */
-		inode = f2fs_iget(sbi->sb, ino);
+		inode = f2fs_iget_retry(sbi->sb, ino);
 		if (IS_ERR(inode))
 			return PTR_ERR(inode);
 	} else {
 		inode = dn->inode;
 	}
 
-	bidx = start_bidx_of_node(offset, F2FS_I(inode)) +
-			le16_to_cpu(sum.ofs_in_node);
+	bidx = start_bidx_of_node(offset, inode) + le16_to_cpu(sum.ofs_in_node);
 
 	/*
 	 * if inode page is locked, unlock temporarily, but its reference
@@ -357,10 +396,9 @@ 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 */
@@ -380,16 +418,21 @@ 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);
-	end = start + ADDRS_PER_PAGE(page, fi);
+	start = start_bidx_of_node(ofs_of_node(page), inode);
+	end = start + ADDRS_PER_PAGE(page, inode);
 
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
-
+retry_dn:
 	err = get_dnode_of_data(&dn, start, ALLOC_NODE);
-	if (err)
+	if (err) {
+		if (err == -ENOMEM) {
+			congestion_wait(BLK_RW_ASYNC, HZ/50);
+			goto retry_dn;
+		}
 		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));
@@ -411,14 +454,16 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 			continue;
 		}
 
+		if ((start + 1) << PAGE_SHIFT > i_size_read(inode))
+			f2fs_i_size_write(inode, (start + 1) << PAGE_SHIFT);
+
 		/*
 		 * dest is reserved block, invalidate src block
 		 * and then reserve one new block in dnode page.
 		 */
 		if (dest == NEW_ADDR) {
 			truncate_data_blocks_range(&dn, 1);
-			err = reserve_new_block(&dn);
-			f2fs_bug_on(sbi, err);
+			reserve_new_block(&dn);
 			continue;
 		}
 
@@ -427,25 +472,33 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 
 			if (src == NULL_ADDR) {
 				err = reserve_new_block(&dn);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+				while (err)
+					err = reserve_new_block(&dn);
+#endif
 				/* We should not get -ENOSPC */
 				f2fs_bug_on(sbi, err);
+				if (err)
+					goto err;
 			}
-
+retry_prev:
 			/* Check the previous node page having this index */
 			err = check_index_in_prev_nodes(sbi, dest, &dn);
-			if (err)
+			if (err) {
+				if (err == -ENOMEM) {
+					congestion_wait(BLK_RW_ASYNC, HZ/50);
+					goto retry_prev;
+				}
 				goto err;
+			}
 
 			/* write dummy data page */
 			f2fs_replace_block(sbi, &dn, src, dest,
-							ni.version, false);
+						ni.version, false, false);
 			recovered++;
 		}
 	}
 
-	if (IS_INODE(dn.node_page))
-		sync_inode_page(&dn);
-
 	copy_node_footer(dn.node_page, page);
 	fill_node_footer(dn.node_page, dn.nid, ni.ino,
 					ofs_of_node(page), false);
@@ -459,17 +512,16 @@ out:
 	return err;
 }
 
-static int recover_data(struct f2fs_sb_info *sbi,
-				struct list_head *head, int type)
+static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
+						struct list_head *dir_list)
 {
-	unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
 	struct curseg_info *curseg;
 	struct page *page = NULL;
 	int err = 0;
 	block_t blkaddr;
 
 	/* get node pages in the current segment */
-	curseg = CURSEG_I(sbi, type);
+	curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
 	blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
 
 	while (1) {
@@ -482,12 +534,12 @@ static int recover_data(struct f2fs_sb_info *sbi,
 
 		page = get_tmp_page(sbi, blkaddr);
 
-		if (cp_ver != cpver_of_node(page)) {
+		if (!is_recoverable_dnode(page)) {
 			f2fs_put_page(page, 1);
 			break;
 		}
 
-		entry = get_fsync_inode(head, ino_of_node(page));
+		entry = get_fsync_inode(inode_list, ino_of_node(page));
 		if (!entry)
 			goto next;
 		/*
@@ -495,10 +547,10 @@ static int recover_data(struct f2fs_sb_info *sbi,
 		 * In this case, we can lose the latest inode(x).
 		 * So, call recover_inode for the inode update.
 		 */
-		if (entry->last_inode == blkaddr)
+		if (IS_INODE(page))
 			recover_inode(entry->inode, page);
 		if (entry->last_dentry == blkaddr) {
-			err = recover_dentry(entry->inode, page);
+			err = recover_dentry(entry->inode, page, dir_list);
 			if (err) {
 				f2fs_put_page(page, 1);
 				break;
@@ -510,11 +562,8 @@ static int recover_data(struct f2fs_sb_info *sbi,
 			break;
 		}
 
-		if (entry->blkaddr == blkaddr) {
-			iput(entry->inode);
-			list_del(&entry->list);
-			kmem_cache_free(fsync_entry_slab, entry);
-		}
+		if (entry->blkaddr == blkaddr)
+			del_fsync_inode(entry);
 next:
 		/* check next segment */
 		blkaddr = next_blkaddr_of_node(page);
@@ -525,12 +574,14 @@ next:
 	return err;
 }
 
-int recover_fsync_data(struct f2fs_sb_info *sbi)
+int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
 	struct list_head inode_list;
+	struct list_head dir_list;
 	block_t blkaddr;
 	int err;
+	int ret = 0;
 	bool need_writecp = false;
 
 	fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry",
@@ -539,6 +590,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&inode_list);
+	INIT_LIST_HEAD(&dir_list);
 
 	/* prevent checkpoint */
 	mutex_lock(&sbi->cp_mutex);
@@ -547,25 +599,26 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
 
 	/* step #1: find fsynced inode numbers */
 	err = find_fsync_dnodes(sbi, &inode_list);
-	if (err)
+	if (err || list_empty(&inode_list))
 		goto out;
 
-	if (list_empty(&inode_list))
+	if (check_only) {
+		ret = 1;
 		goto out;
+	}
 
 	need_writecp = true;
 
 	/* step #2: recover data */
-	err = recover_data(sbi, &inode_list, CURSEG_WARM_NODE);
+	err = recover_data(sbi, &inode_list, &dir_list);
 	if (!err)
 		f2fs_bug_on(sbi, !list_empty(&inode_list));
 out:
 	destroy_fsync_dnodes(&inode_list);
-	kmem_cache_destroy(fsync_entry_slab);
 
 	/* truncate meta pages to be used by the recovery */
 	truncate_inode_pages_range(META_MAPPING(sbi),
-			(loff_t)MAIN_BLKADDR(sbi) << PAGE_CACHE_SHIFT, -1);
+			(loff_t)MAIN_BLKADDR(sbi) << PAGE_SHIFT, -1);
 
 	if (err) {
 		truncate_inode_pages_final(NODE_MAPPING(sbi));
@@ -573,31 +626,20 @@ out:
 	}
 
 	clear_sbi_flag(sbi, SBI_POR_DOING);
-	if (err) {
-		bool invalidate = false;
+	if (err)
+		set_ckpt_flags(sbi, CP_ERROR_FLAG);
+	mutex_unlock(&sbi->cp_mutex);
 
-		if (discard_next_dnode(sbi, blkaddr))
-			invalidate = true;
+	/* let's drop all the directory inodes for clean checkpoint */
+	destroy_fsync_dnodes(&dir_list);
 
-		/* Flush all the NAT/SIT pages */
-		while (get_pages(sbi, F2FS_DIRTY_META))
-			sync_meta_pages(sbi, META, LONG_MAX);
-
-		/* invalidate temporary meta page */
-		if (invalidate)
-			invalidate_mapping_pages(META_MAPPING(sbi),
-							blkaddr, blkaddr);
-
-		set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
-		mutex_unlock(&sbi->cp_mutex);
-	} else if (need_writecp) {
+	if (!err && need_writecp) {
 		struct cp_control cpc = {
 			.reason = CP_RECOVERY,
 		};
-		mutex_unlock(&sbi->cp_mutex);
-		write_checkpoint(sbi, &cpc);
-	} else {
-		mutex_unlock(&sbi->cp_mutex);
+		err = write_checkpoint(sbi, &cpc);
 	}
-	return err;
+
+	kmem_cache_destroy(fsync_entry_slab);
+	return ret ? ret: err;
 }

fs/f2fs/segment.h

@@ -16,6 +16,7 @@
 #define NULL_SECNO			((unsigned int)(~0))
 
 #define DEF_RECLAIM_PREFREE_SEGMENTS	5	/* 5% over total segments */
+#define DEF_MAX_RECLAIM_PREFREE_SEGMENTS	4096	/* 8GB in maximum */
 
 /* L: Logical segment # in volume, R: Relative segment # in main area */
 #define GET_L2R_SEGNO(free_i, segno)	(segno - free_i->start_segno)
@@ -158,16 +159,17 @@ struct victim_sel_policy {
 };
 
 struct seg_entry {
-	unsigned short valid_blocks;	/* # of valid blocks */
+	unsigned int type:6;		/* segment type like CURSEG_XXX_TYPE */
+	unsigned int valid_blocks:10;	/* # of valid blocks */
+	unsigned int ckpt_valid_blocks:10;	/* # of valid blocks last cp */
+	unsigned int padding:6;		/* padding */
 	unsigned char *cur_valid_map;	/* validity bitmap of blocks */
 	/*
 	 * # of valid blocks and the validity bitmap stored in the the last
 	 * checkpoint pack. This information is used by the SSR mode.
 	 */
-	unsigned short ckpt_valid_blocks;
-	unsigned char *ckpt_valid_map;
+	unsigned char *ckpt_valid_map;	/* validity bitmap of blocks last cp */
 	unsigned char *discard_map;
-	unsigned char type;		/* segment type like CURSEG_XXX_TYPE */
 	unsigned long long mtime;	/* modification time of the segment */
 };
 
@@ -183,7 +185,7 @@ 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 +193,7 @@ 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 +260,8 @@ 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 */
@@ -466,20 +471,27 @@ static inline bool need_SSR(struct f2fs_sb_info *sbi)
 {
 	int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
 	int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
+
+	if (test_opt(sbi, LFS))
+		return false;
+
 	return free_sections(sbi) <= (node_secs + 2 * dent_secs +
 						reserved_sections(sbi) + 1);
 }
 
-static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed)
+static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi,
+					int freed, int needed)
 {
 	int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
 	int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
 
+	node_secs += get_blocktype_secs(sbi, F2FS_DIRTY_IMETA);
+
 	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
 		return false;
 
-	return (free_sections(sbi) + freed) <= (node_secs + 2 * dent_secs +
-						reserved_sections(sbi));
+	return (free_sections(sbi) + freed) <=
+		(node_secs + 2 * dent_secs + reserved_sections(sbi) + needed);
 }
 
 static inline bool excess_prefree_segs(struct f2fs_sb_info *sbi)
@@ -527,6 +539,9 @@ static inline bool need_inplace_update(struct inode *inode)
 	if (S_ISDIR(inode->i_mode) || f2fs_is_atomic_file(inode))
 		return false;
 
+	if (test_opt(sbi, LFS))
+		return false;
+
 	if (policy & (0x1 << F2FS_IPU_FORCE))
 		return true;
 	if (policy & (0x1 << F2FS_IPU_SSR) && need_SSR(sbi))
@@ -540,7 +555,7 @@ static inline bool need_inplace_update(struct inode *inode)
 
 	/* this is only set during fdatasync */
 	if (policy & (0x1 << F2FS_IPU_FSYNC) &&
-			is_inode_flag_set(F2FS_I(inode), FI_NEED_IPU))
+			is_inode_flag_set(inode, FI_NEED_IPU))
 		return true;
 
 	return false;
@@ -573,8 +588,8 @@ static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno)
 
 static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr)
 {
-	f2fs_bug_on(sbi, blk_addr < SEG0_BLKADDR(sbi)
-					|| blk_addr >= MAX_BLKADDR(sbi));
+	BUG_ON(blk_addr < SEG0_BLKADDR(sbi)
+			|| blk_addr >= MAX_BLKADDR(sbi));
 }
 
 /*
@@ -702,9 +717,9 @@ static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type)
 	if (type == DATA)
 		return sbi->blocks_per_seg;
 	else if (type == NODE)
-		return 3 * sbi->blocks_per_seg;
+		return 8 * sbi->blocks_per_seg;
 	else if (type == META)
-		return MAX_BIO_BLOCKS(sbi);
+		return 8 * MAX_BIO_BLOCKS(sbi);
 	else
 		return 0;
 }
@@ -722,10 +737,8 @@ static inline long nr_pages_to_write(struct f2fs_sb_info *sbi, int type,
 
 	nr_to_write = wbc->nr_to_write;
 
-	if (type == DATA)
-		desired = 4096;
-	else if (type == NODE)
-		desired = 3 * max_hw_blocks(sbi);
+	if (type == NODE)
+		desired = 2 * max_hw_blocks(sbi);
 	else
 		desired = MAX_BIO_BLOCKS(sbi);
 

fs/f2fs/shrinker.c

@@ -13,6 +13,7 @@
 #include <linux/f2fs_fs.h>
 
 #include "f2fs.h"
+#include "node.h"
 
 static LIST_HEAD(f2fs_list);
 static DEFINE_SPINLOCK(f2fs_list_lock);
@@ -25,14 +26,15 @@ static unsigned long __count_nat_entries(struct f2fs_sb_info *sbi)
 
 static unsigned long __count_free_nids(struct f2fs_sb_info *sbi)
 {
-	if (NM_I(sbi)->fcnt > NAT_ENTRY_PER_BLOCK)
-		return NM_I(sbi)->fcnt - NAT_ENTRY_PER_BLOCK;
+	if (NM_I(sbi)->fcnt > MAX_FREE_NIDS)
+		return NM_I(sbi)->fcnt - MAX_FREE_NIDS;
 	return 0;
 }
 
 static unsigned long __count_extent_cache(struct f2fs_sb_info *sbi)
 {
-	return sbi->total_ext_tree + atomic_read(&sbi->total_ext_node);
+	return atomic_read(&sbi->total_zombie_tree) +
+				atomic_read(&sbi->total_ext_node);
 }
 
 unsigned long f2fs_shrink_count(struct shrinker *shrink,

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

@@ -151,7 +151,7 @@ static int f2fs_xattr_advise_set(const struct xattr_handler *handler,
 		return -EINVAL;
 
 	F2FS_I(inode)->i_advise |= *(char *)value;
-	mark_inode_dirty(inode);
+	f2fs_mark_inode_dirty_sync(inode);
 	return 0;
 }
 
@@ -264,18 +264,20 @@ static struct f2fs_xattr_entry *__find_xattr(void *base_addr, int index,
 	return entry;
 }
 
-static void *read_all_xattrs(struct inode *inode, struct page *ipage)
+static int read_all_xattrs(struct inode *inode, struct page *ipage,
+							void **base_addr)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct f2fs_xattr_header *header;
 	size_t size = PAGE_SIZE, inline_size = 0;
 	void *txattr_addr;
+	int err;
 
 	inline_size = inline_xattr_size(inode);
 
 	txattr_addr = kzalloc(inline_size + size, GFP_F2FS_ZERO);
 	if (!txattr_addr)
-		return NULL;
+		return -ENOMEM;
 
 	/* read from inline xattr */
 	if (inline_size) {
@@ -286,8 +288,10 @@ static void *read_all_xattrs(struct inode *inode, struct page *ipage)
 			inline_addr = inline_xattr_addr(ipage);
 		} else {
 			page = get_node_page(sbi, inode->i_ino);
-			if (IS_ERR(page))
+			if (IS_ERR(page)) {
+				err = PTR_ERR(page);
 				goto fail;
+			}
 			inline_addr = inline_xattr_addr(page);
 		}
 		memcpy(txattr_addr, inline_addr, inline_size);
@@ -301,8 +305,10 @@ static void *read_all_xattrs(struct inode *inode, struct page *ipage)
 
 		/* The inode already has an extended attribute block. */
 		xpage = get_node_page(sbi, F2FS_I(inode)->i_xattr_nid);
-		if (IS_ERR(xpage))
+		if (IS_ERR(xpage)) {
+			err = PTR_ERR(xpage);
 			goto fail;
+		}
 
 		xattr_addr = page_address(xpage);
 		memcpy(txattr_addr + inline_size, xattr_addr, PAGE_SIZE);
@@ -316,10 +322,11 @@ static void *read_all_xattrs(struct inode *inode, struct page *ipage)
 		header->h_magic = cpu_to_le32(F2FS_XATTR_MAGIC);
 		header->h_refcount = cpu_to_le32(1);
 	}
-	return txattr_addr;
+	*base_addr = txattr_addr;
+	return 0;
 fail:
 	kzfree(txattr_addr);
-	return NULL;
+	return err;
 }
 
 static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
@@ -345,7 +352,8 @@ 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);
+			set_page_dirty(ipage);
 		} else {
 			page = get_node_page(sbi, inode->i_ino);
 			if (IS_ERR(page)) {
@@ -353,7 +361,7 @@ 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);
@@ -374,7 +382,7 @@ 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);
@@ -412,9 +420,9 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name,
 	if (len > F2FS_NAME_LEN)
 		return -ERANGE;
 
-	base_addr = read_all_xattrs(inode, ipage);
-	if (!base_addr)
-		return -ENOMEM;
+	error = read_all_xattrs(inode, ipage, &base_addr);
+	if (error)
+		return error;
 
 	entry = __find_xattr(base_addr, index, len, name);
 	if (IS_XATTR_LAST_ENTRY(entry)) {
@@ -448,9 +456,9 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
 	int error = 0;
 	size_t rest = buffer_size;
 
-	base_addr = read_all_xattrs(inode, NULL);
-	if (!base_addr)
-		return -ENOMEM;
+	error = read_all_xattrs(inode, NULL, &base_addr);
+	if (error)
+		return error;
 
 	list_for_each_xattr(entry, base_addr) {
 		const struct xattr_handler *handler =
@@ -481,13 +489,12 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 			const char *name, const void *value, size_t size,
 			struct page *ipage, int flags)
 {
-	struct f2fs_inode_info *fi = F2FS_I(inode);
 	struct f2fs_xattr_entry *here, *last;
 	void *base_addr;
 	int found, newsize;
 	size_t len;
 	__u32 new_hsize;
-	int error = -ENOMEM;
+	int error = 0;
 
 	if (name == NULL)
 		return -EINVAL;
@@ -503,9 +510,9 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 	if (size > MAX_VALUE_LEN(inode))
 		return -E2BIG;
 
-	base_addr = read_all_xattrs(inode, ipage);
-	if (!base_addr)
-		goto exit;
+	error = read_all_xattrs(inode, ipage, &base_addr);
+	if (error)
+		return error;
 
 	/* find entry with wanted name. */
 	here = __find_xattr(base_addr, index, len, name);
@@ -538,7 +545,7 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 			free = free + ENTRY_SIZE(here);
 
 		if (unlikely(free < newsize)) {
-			error = -ENOSPC;
+			error = -E2BIG;
 			goto exit;
 		}
 	}
@@ -566,7 +573,6 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 		 * Before we come here, old entry is removed.
 		 * We just write new entry.
 		 */
-		memset(last, 0, newsize);
 		last->e_name_index = index;
 		last->e_name_len = len;
 		memcpy(last->e_name, name, len);
@@ -580,19 +586,17 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 	if (error)
 		goto exit;
 
-	if (is_inode_flag_set(fi, FI_ACL_MODE)) {
-		inode->i_mode = fi->i_acl_mode;
+	if (is_inode_flag_set(inode, FI_ACL_MODE)) {
+		inode->i_mode = F2FS_I(inode)->i_acl_mode;
 		inode->i_ctime = CURRENT_TIME;
-		clear_inode_flag(fi, FI_ACL_MODE);
+		clear_inode_flag(inode, FI_ACL_MODE);
 	}
 	if (index == F2FS_XATTR_INDEX_ENCRYPTION &&
 			!strcmp(name, F2FS_XATTR_NAME_ENCRYPTION_CONTEXT))
 		f2fs_set_encrypted_inode(inode);
-
-	if (ipage)
-		update_inode(inode, ipage);
-	else
-		update_inode_page(inode);
+	f2fs_mark_inode_dirty_sync(inode);
+	if (!error && S_ISDIR(inode->i_mode))
+		set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_CP);
 exit:
 	kzfree(base_addr);
 	return error;
@@ -609,7 +613,7 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name,
 	if (ipage)
 		return __f2fs_setxattr(inode, index, name, value,
 						size, ipage, flags);
-	f2fs_balance_fs(sbi);
+	f2fs_balance_fs(sbi, true);
 
 	f2fs_lock_op(sbi);
 	/* protect xattr_ver */
@@ -618,5 +622,6 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name,
 	up_write(&F2FS_I(inode)->i_sem);
 	f2fs_unlock_op(sbi);
 
+	f2fs_update_time(sbi, REQ_TIME);
 	return err;
 }

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

@@ -229,6 +229,7 @@ struct dentry_operations {
 #define DCACHE_MAY_FREE			0x00800000
 #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 */
 #define DCACHE_OP_REAL			0x08000000
 
 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 */
@@ -51,6 +51,7 @@
 #define MAX_ACTIVE_DATA_LOGS	8
 
 #define VERSION_LEN	256
+#define MAX_VOLUME_NAME		512
 
 /*
  * For superblock
@@ -84,7 +85,7 @@ struct f2fs_super_block {
 	__le32 node_ino;		/* node inode number */
 	__le32 meta_ino;		/* meta inode number */
 	__u8 uuid[16];			/* 128-bit uuid for volume */
-	__le16 volume_name[512];	/* volume name */
+	__le16 volume_name[MAX_VOLUME_NAME];	/* volume name */
 	__le32 extension_count;		/* # of extensions below */
 	__u8 extension_list[F2FS_MAX_EXTENSION][8];	/* extension array */
 	__le32 cp_payload;
@@ -99,6 +100,7 @@ struct f2fs_super_block {
 /*
  * For checkpoint
  */
+#define CP_CRC_RECOVERY_FLAG	0x00000040
 #define CP_FASTBOOT_FLAG	0x00000020
 #define CP_FSCK_FLAG		0x00000010
 #define CP_ERROR_FLAG		0x00000008
@@ -169,12 +171,12 @@ 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)	\
-	(IS_INODE(page) ? ADDRS_PER_INODE(fi) : ADDRS_PER_BLOCK)
+#define ADDRS_PER_PAGE(page, inode)	\
+	(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)
@@ -261,7 +263,7 @@ struct f2fs_node {
 /*
  * For NAT entries
  */
-#define NAT_ENTRY_PER_BLOCK (PAGE_CACHE_SIZE / sizeof(struct f2fs_nat_entry))
+#define NAT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_nat_entry))
 
 struct f2fs_nat_entry {
 	__u8 version;		/* latest version of cached nat entry */
@@ -281,7 +283,7 @@ struct f2fs_nat_block {
  * Not allow to change this.
  */
 #define SIT_VBLOCK_MAP_SIZE 64
-#define SIT_ENTRY_PER_BLOCK (PAGE_CACHE_SIZE / sizeof(struct f2fs_sit_entry))
+#define SIT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_sit_entry))
 
 /*
  * F2FS uses 4 bytes to represent block address. As a result, supported size of
@@ -350,7 +352,7 @@ 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 -\
@@ -363,6 +365,12 @@ 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
@@ -392,18 +400,28 @@ struct sit_journal {
 	__u8 reserved[SIT_JOURNAL_RESERVED];
 } __packed;
 
-/* 4KB-sized summary block structure */
-struct f2fs_summary_block {
-	struct f2fs_summary entries[ENTRIES_IN_SUM];
+struct f2fs_extra_info {
+	__le64 kbytes_written;
+	__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;
 
@@ -497,4 +515,6 @@ enum {
 	F2FS_FT_MAX
 };
 
+#define S_SHIFT 12
+
 #endif  /* _LINUX_F2FS_FS_H */

include/linux/fs.h

@@ -52,6 +52,8 @@ 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);
@@ -677,6 +679,9 @@ 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 */
 };
 
@@ -1337,6 +1342,8 @@ 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 +1,435 @@
+/*
+ * 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 (*key_prefix)(struct inode *, u8 **);
+	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 *, gfp_t);
+extern void fscrypt_release_ctx(struct fscrypt_ctx *);
+extern struct page *fscrypt_encrypt_page(struct inode *, struct page *, gfp_t);
+extern int fscrypt_decrypt_page(struct page *);
+extern 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 file *, 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,
+							gfp_t f)
+{
+	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, gfp_t f)
+{
+	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 file *f,
+				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" })
 
@@ -693,28 +694,32 @@ TRACE_EVENT(f2fs_direct_IO_exit,
 		__entry->ret)
 );
 
-TRACE_EVENT(f2fs_reserve_new_block,
+TRACE_EVENT(f2fs_reserve_new_blocks,
 
-	TP_PROTO(struct inode *inode, nid_t nid, unsigned int ofs_in_node),
+	TP_PROTO(struct inode *inode, nid_t nid, unsigned int ofs_in_node,
+							blkcnt_t count),
 
-	TP_ARGS(inode, nid, ofs_in_node),
+	TP_ARGS(inode, nid, ofs_in_node, count),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(nid_t, nid)
 		__field(unsigned int, ofs_in_node)
+		__field(blkcnt_t, count)
 	),
 
 	TP_fast_assign(
 		__entry->dev	= inode->i_sb->s_dev;
 		__entry->nid	= nid;
 		__entry->ofs_in_node = ofs_in_node;
+		__entry->count = count;
 	),
 
-	TP_printk("dev = (%d,%d), nid = %u, ofs_in_node = %u",
+	TP_printk("dev = (%d,%d), nid = %u, ofs_in_node = %u, count = %llu",
 		show_dev(__entry),
 		(unsigned int)__entry->nid,
-		__entry->ofs_in_node)
+		__entry->ofs_in_node,
+		(unsigned long long)__entry->count)
 );
 
 DECLARE_EVENT_CLASS(f2fs__submit_page_bio,
@@ -727,7 +732,8 @@ 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 +742,18 @@ 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))
 );
@@ -1265,6 +1273,44 @@ TRACE_EVENT(f2fs_destroy_extent_tree,
 		__entry->node_cnt)
 );
 
+DECLARE_EVENT_CLASS(f2fs_sync_dirty_inodes,
+
+	TP_PROTO(struct super_block *sb, int type, s64 count),
+
+	TP_ARGS(sb, type, count),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(int, type)
+		__field(s64, count)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= sb->s_dev;
+		__entry->type	= type;
+		__entry->count	= count;
+	),
+
+	TP_printk("dev = (%d,%d), %s, dirty count = %lld",
+		show_dev(__entry),
+		show_file_type(__entry->type),
+		__entry->count)
+);
+
+DEFINE_EVENT(f2fs_sync_dirty_inodes, f2fs_sync_dirty_inodes_enter,
+
+	TP_PROTO(struct super_block *sb, int type, s64 count),
+
+	TP_ARGS(sb, type, count)
+);
+
+DEFINE_EVENT(f2fs_sync_dirty_inodes, f2fs_sync_dirty_inodes_exit,
+
+	TP_PROTO(struct super_block *sb, int type, s64 count),
+
+	TP_ARGS(sb, type, count)
+);
+
 #endif /* _TRACE_F2FS_H */
 
  /* This part must be outside protection */

include/uapi/linux/fs.h

@@ -172,6 +172,24 @@ struct inodes_stat_t {
 #define FS_IOC32_GETVERSION		_IOR('v', 1, int)
 #define FS_IOC32_SETVERSION		_IOW('v', 2, int)
 
+/*
+ * 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)
  */