update twrp defconfig,disable NTFS drivers

original patch: jcadduono/android_kernel_samsung_universal8890/commit/e3c2fe84c96c350db4dbcf545a9e247d0525bb43

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -74,3 +74,41 @@ Date:		March 2014
 Contact:	"Jaegeuk Kim" <jaegeuk.kim@samsung.com>
 Description:
 		 Controls the memory footprint used by f2fs.
+
+What:		/sys/fs/f2fs/<disk>/trim_sections
+Date:		February 2015
+Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:
+		 Controls the trimming rate in batch mode.
+
+What:		/sys/fs/f2fs/<disk>/cp_interval
+Date:		October 2015
+Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:
+		 Controls the checkpoint timing.
+
+What:		/sys/fs/f2fs/<disk>/idle_interval
+Date:		January 2016
+Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:
+		 Controls the idle timing.
+
+What:		/sys/fs/f2fs/<disk>/ra_nid_pages
+Date:		October 2015
+Contact:	"Chao Yu" <chao2.yu@samsung.com>
+Description:
+		 Controls the count of nid pages to be readaheaded.
+
+What:		/sys/fs/f2fs/<disk>/dirty_nats_ratio
+Date:		January 2016
+Contact:	"Chao Yu" <chao2.yu@samsung.com>
+Description:
+		 Controls dirty nat entries ratio threshold, if current
+		 ratio exceeds configured threshold, checkpoint will
+		 be triggered for flushing dirty nat entries.
+
+What:		/sys/fs/f2fs/<disk>/lifetime_write_kbytes
+Date:		January 2016
+Contact:	"Shuoran Liu" <liushuoran@huawei.com>
+Description:
+		 Shows total written kbytes issued to disk.

Documentation/filesystems/f2fs.txt

@@ -106,7 +106,11 @@ background_gc=%s       Turn on/off cleaning operations, namely garbage
                        Default value for this option is on. So garbage
                        collection is on by default.
 disable_roll_forward   Disable the roll-forward recovery routine
-discard                Issue discard/TRIM commands when a segment is cleaned.
+norecovery             Disable the roll-forward recovery routine, mounted read-
+                       only (i.e., -o ro,disable_roll_forward)
+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.
@@ -131,6 +135,22 @@ nobarrier              This option can be used if underlying storage guarantees
 		       If this option is set, no cache_flush commands are issued
 		       but f2fs still guarantees the write ordering of all the
 		       data writes.
+fastboot               This option is used when a system wants to reduce mount
+                       time as much as possible, even though normal performance
+		       can be sacrificed.
+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         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

Makefile

@@ -621,9 +621,10 @@ all: vmlinux
 include $(srctree)/arch/$(SRCARCH)/Makefile
 
 KBUILD_CFLAGS	+= $(call cc-option,-fno-delete-null-pointer-checks,)
+KBUILD_CFLAGS	+= $(call cc-disable-warning,maybe-uninitialized,)
 
 ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
-KBUILD_CFLAGS	+= -Os $(call cc-disable-warning,maybe-uninitialized,)
+KBUILD_CFLAGS	+= -Os
 else
 KBUILD_CFLAGS	+= -O2
 endif

drivers/gpu/msm/adreno_a5xx.c

@@ -1,4 +1,4 @@
-/* Copyright (c) 2014-2015, The Linux Foundation. All rights reserved.
+/* Copyright (c) 2014-2016, The Linux Foundation. All rights reserved.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 and
@@ -379,6 +379,10 @@ static int a5xx_preemption_pre_ibsubmit(
 		*cmds++ = 0;
 	}
 
+	/* Enable CP_CONTEXT_SWITCH_YIELD packets in the IB2s */
+	*cmds++ = cp_type7_packet(CP_YIELD_ENABLE, 1);
+	*cmds++ = 2;
+
 	return cmds - cmds_orig;
 }
 

drivers/gpu/msm/adreno_ringbuffer.c

@@ -1,4 +1,4 @@
-/* Copyright (c) 2002,2007-2015, The Linux Foundation. All rights reserved.
+/* Copyright (c) 2002,2007-2016, The Linux Foundation. All rights reserved.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 and
@@ -584,7 +584,7 @@ adreno_ringbuffer_addcmds(struct adreno_ringbuffer *rb,
 
 	if (gpudev->preemption_pre_ibsubmit &&
 				adreno_is_preemption_enabled(adreno_dev))
-		total_sizedwords += 20;
+		total_sizedwords += 22;
 
 	if (gpudev->preemption_post_ibsubmit &&
 				adreno_is_preemption_enabled(adreno_dev))

drivers/gpu/msm/kgsl_sharedmem.c

@@ -685,6 +685,10 @@ _kgsl_sharedmem_page_alloc(struct kgsl_memdesc *memdesc,
 	unsigned int align;
 	unsigned int step = ((VMALLOC_END - VMALLOC_START)/8) >> PAGE_SHIFT;
 
+	size = PAGE_ALIGN(size);
+	if (size == 0 || size > UINT_MAX)
+		return -EINVAL;
+
 	align = (memdesc->flags & KGSL_MEMALIGN_MASK) >> KGSL_MEMALIGN_SHIFT;
 
 	page_size = get_page_size(size, align);

drivers/gpu/msm/kgsl_sync.c

@@ -1,4 +1,4 @@
-/* Copyright (c) 2012-2015, The Linux Foundation. All rights reserved.
+/* Copyright (c) 2012-2016, The Linux Foundation. All rights reserved.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 and
@@ -474,22 +474,22 @@ long kgsl_ioctl_syncsource_create(struct kgsl_device_private *dev_priv,
 		goto out;
 	}
 
+	kref_init(&syncsource->refcount);
+	syncsource->private = private;
+
 	idr_preload(GFP_KERNEL);
 	spin_lock(&private->syncsource_lock);
 	id = idr_alloc(&private->syncsource_idr, syncsource, 1, 0, GFP_NOWAIT);
-	spin_unlock(&private->syncsource_lock);
-	idr_preload_end();
 
 	if (id > 0) {
-		kref_init(&syncsource->refcount);
 		syncsource->id = id;
-		syncsource->private = private;
-
 		param->id = id;
 		ret = 0;
 	} else {
 		ret = id;
 	}
+	spin_unlock(&private->syncsource_lock);
+	idr_preload_end();
 
 out:
 	if (ret) {
@@ -548,25 +548,23 @@ long kgsl_ioctl_syncsource_destroy(struct kgsl_device_private *dev_priv,
 {
 	struct kgsl_syncsource_destroy *param = data;
 	struct kgsl_syncsource *syncsource = NULL;
-	struct kgsl_process_private *private;
+	struct kgsl_process_private *private = dev_priv->process_priv;
 
-	syncsource = kgsl_syncsource_get(dev_priv->process_priv,
-				     param->id);
+	spin_lock(&private->syncsource_lock);
+	syncsource = idr_find(&private->syncsource_idr, param->id);
+
+	if (syncsource) {
+		idr_remove(&private->syncsource_idr, param->id);
+		syncsource->id = 0;
+	}
+
+	spin_unlock(&private->syncsource_lock);
 
 	if (syncsource == NULL)
 		return -EINVAL;
 
-	private = syncsource->private;
-
-	spin_lock(&private->syncsource_lock);
-	idr_remove(&private->syncsource_idr, param->id);
-	syncsource->id = 0;
-	spin_unlock(&private->syncsource_lock);
-
 	/* put reference from syncsource creation */
 	kgsl_syncsource_put(syncsource);
-	/* put reference from getting the syncsource above */
-	kgsl_syncsource_put(syncsource);
 	return 0;
 }
 

drivers/nfc/pn547.c

@@ -661,7 +661,10 @@ long pn547_dev_ioctl(struct file *filp,
 					}
 				}
 				if (!(current_state & P61_STATE_WIRED))
+				{
 					gpio_set_value(pn547_dev->ese_pwr_req, 0);
+					msleep(60);
+				}
 
 				pn547_dev->spi_ven_enabled = false;
 
@@ -676,6 +679,7 @@ long pn547_dev_ioctl(struct file *filp,
 				if (!(current_state & P61_STATE_WIRED))
 				{
 					gpio_set_value(pn547_dev->ese_pwr_req, 0);
+					msleep(60);
 				}
 				/*If JCOP3.2 or 3.3 for handling triple mode protection signal NFC service */
 				else
@@ -715,7 +719,7 @@ long pn547_dev_ioctl(struct file *filp,
 					}
 				}
 				gpio_set_value(pn547_dev->ese_pwr_req, 0);
-				msleep(10);
+				msleep(60);
 				gpio_set_value(pn547_dev->ese_pwr_req, 1);
 				msleep(10);
 			} else {
@@ -827,7 +831,10 @@ long pn547_dev_ioctl(struct file *filp,
             if (current_state & P61_STATE_WIRED){
                 p61_update_access_state(pn547_dev, P61_STATE_WIRED, false);
                 if((current_state & (P61_STATE_SPI|P61_STATE_SPI_PRIO)) == 0)
+				{
                     gpio_set_value(pn547_dev->ese_pwr_req, 0);
+					msleep(60);
+				}
 			} else {
                 pr_err("%s : P61_SET_WIRED_ACCESS - failed, current_state = %x \n",
 						__func__, pn547_dev->p61_current_state);
@@ -839,6 +846,7 @@ long pn547_dev_ioctl(struct file *filp,
 		{
 			pr_info("%s : P61_ESE_GPIO_LOW  \n", __func__);
 			gpio_set_value(pn547_dev->ese_pwr_req, 0);
+			msleep(60);
 		}
 		else if(arg == 3)
 		{

drivers/usb/gadget/android.c

@@ -2591,7 +2591,7 @@ static int mass_storage_function_init(struct android_usb_function *f,
 	}
 
 #ifdef CONFIG_USB_ANDROID_SAMSUNG_COMPOSITE
-	fsg_mod_data.cdrom[0] = true;
+	fsg_mod_data.cdrom[0] = false;
 	fsg_mod_data.ro[0] = false;
 	fsg_mod_data.removable[0] = true;
 #else

fs/Kconfig

@@ -62,6 +62,8 @@ 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

@@ -28,6 +28,7 @@ obj-$(CONFIG_SIGNALFD)		+= signalfd.o
 obj-$(CONFIG_TIMERFD)		+= timerfd.o
 obj-$(CONFIG_EVENTFD)		+= eventfd.o
 obj-$(CONFIG_AIO)               += aio.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/aio.c

@@ -1354,11 +1354,16 @@ static ssize_t aio_setup_single_vector(struct kiocb *kiocb,
 				       unsigned long *nr_segs,
 				       struct iovec *iovec)
 {
-	if (unlikely(!access_ok(!rw, buf, kiocb->ki_nbytes)))
+	size_t len = kiocb->ki_nbytes;
+
+	if (len > MAX_RW_COUNT)
+		len = MAX_RW_COUNT;
+
+	if (unlikely(!access_ok(!rw, buf, len)))
 		return -EFAULT;
 
 	iovec->iov_base = buf;
-	iovec->iov_len = kiocb->ki_nbytes;
+	iovec->iov_len = len;
 	*nr_segs = 1;
 	return 0;
 }

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 +1,567 @@
+/*
+ * 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/crypto.h>
+#include <linux/ecryptfs.h>
+#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>
+
+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 ablkcipher_request *req = NULL;
+	DECLARE_FS_COMPLETION_RESULT(ecr);
+	struct scatterlist dst, src;
+	struct fscrypt_info *ci = inode->i_crypt_info;
+	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+	int res = 0;
+
+	req = ablkcipher_request_alloc(tfm, gfp_flags);
+	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,
+		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_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 == FS_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 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_CACHE_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);
+		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

@@ -0,0 +1,427 @@
+/*
+ * This contains functions for filename crypto management
+ *
+ * Copyright (C) 2015, Google, Inc.
+ * Copyright (C) 2015, Motorola Mobility
+ *
+ * Written by Uday Savagaonkar, 2014.
+ * 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/scatterlist.h>
+#include <linux/ratelimit.h>
+#include <linux/fscrypto.h>
+
+static u32 size_round_up(size_t size, size_t blksize)
+{
+	return ((size + blksize - 1) / blksize) * blksize;
+}
+
+/**
+ * dir_crypt_complete() -
+ */
+static void dir_crypt_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);
+}
+
+/**
+ * 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 fname_encrypt(struct inode *inode,
+			const struct qstr *iname, struct fscrypt_str *oname)
+{
+	u32 ciphertext_len;
+	struct ablkcipher_request *req = NULL;
+	DECLARE_FS_COMPLETION_RESULT(ecr);
+	struct fscrypt_info *ci = inode->i_crypt_info;
+	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+	int res = 0;
+	char iv[FS_CRYPTO_BLOCK_SIZE];
+	struct scatterlist src_sg, dst_sg;
+	int padding = 4 << (ci->ci_flags & FS_POLICY_FLAGS_PAD_MASK);
+	char *workbuf, buf[32], *alloc_buf = NULL;
+	unsigned lim;
+
+	lim = inode->i_sb->s_cop->max_namelen(inode);
+	if (iname->len <= 0 || iname->len > lim)
+		return -EIO;
+
+	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)) {
+		workbuf = buf;
+	} else {
+		alloc_buf = kmalloc(ciphertext_len, GFP_NOFS);
+		if (!alloc_buf)
+			return -ENOMEM;
+		workbuf = alloc_buf;
+	}
+
+	/* Allocate request */
+	req = ablkcipher_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,
+			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+			dir_crypt_complete, &ecr);
+
+	/* Copy the input */
+	memcpy(workbuf, iname->name, iname->len);
+	if (iname->len < ciphertext_len)
+		memset(workbuf + iname->len, 0, ciphertext_len - iname->len);
+
+	/* Initialize IV */
+	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);
+	if (res == -EINPROGRESS || res == -EBUSY) {
+		wait_for_completion(&ecr.completion);
+		res = ecr.res;
+	}
+	kfree(alloc_buf);
+	ablkcipher_request_free(req);
+	if (res < 0)
+		printk_ratelimited(KERN_ERR
+				"%s: Error (error code %d)\n", __func__, res);
+
+	oname->len = ciphertext_len;
+	return res;
+}
+
+/*
+ * 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 fname_decrypt(struct inode *inode,
+				const struct fscrypt_str *iname,
+				struct fscrypt_str *oname)
+{
+	struct ablkcipher_request *req = NULL;
+	DECLARE_FS_COMPLETION_RESULT(ecr);
+	struct scatterlist src_sg, dst_sg;
+	struct fscrypt_info *ci = inode->i_crypt_info;
+	struct crypto_ablkcipher *tfm = ci->ci_ctfm;
+	int res = 0;
+	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);
+	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,
+		dir_crypt_complete, &ecr);
+
+	/* Initialize IV */
+	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);
+	if (res == -EINPROGRESS || res == -EBUSY) {
+		wait_for_completion(&ecr.completion);
+		res = ecr.res;
+	}
+	ablkcipher_request_free(req);
+	if (res < 0) {
+		printk_ratelimited(KERN_ERR
+				"%s: Error (error code %d)\n", __func__, res);
+		return res;
+	}
+
+	oname->len = strnlen(oname->name, iname->len);
+	return oname->len;
+}
+
+static const char *lookup_table =
+	"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,";
+
+/**
+ * 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.
+ */
+static int digest_encode(const char *src, int len, char *dst)
+{
+	int i = 0, bits = 0, ac = 0;
+	char *cp = dst;
+
+	while (i < len) {
+		ac += (((unsigned char) src[i]) << bits);
+		bits += 8;
+		do {
+			*cp++ = lookup_table[ac & 0x3f];
+			ac >>= 6;
+			bits -= 6;
+		} while (bits >= 6);
+		i++;
+	}
+	if (bits)
+		*cp++ = lookup_table[ac & 0x3f];
+	return cp - dst;
+}
+
+static int digest_decode(const char *src, int len, char *dst)
+{
+	int i = 0, bits = 0, ac = 0;
+	const char *p;
+	char *cp = dst;
+
+	while (i < len) {
+		p = strchr(lookup_table, src[i]);
+		if (p == NULL || src[i] == 0)
+			return -2;
+		ac += (p - lookup_table) << bits;
+		bits += 6;
+		if (bits >= 8) {
+			*cp++ = ac & 0xff;
+			ac >>= 8;
+			bits -= 8;
+		}
+		i++;
+	}
+	if (ac)
+		return -1;
+	return cp - dst;
+}
+
+u32 fscrypt_fname_encrypted_size(struct inode *inode, u32 ilen)
+{
+	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);
+
+/**
+ * fscrypt_fname_crypto_alloc_obuff() -
+ *
+ * Allocates an output buffer that is sufficient for the crypto operation
+ * specified by the context and the direction.
+ */
+int fscrypt_fname_alloc_buffer(struct inode *inode,
+				u32 ilen, struct fscrypt_str *crypto_str)
+{
+	unsigned int olen = fscrypt_fname_encrypted_size(inode, ilen);
+
+	crypto_str->len = olen;
+	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);
+
+/**
+ * fscrypt_fname_crypto_free_buffer() -
+ *
+ * Frees the buffer allocated for crypto operation.
+ */
+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);
+
+/**
+ * fscrypt_fname_disk_to_usr() - converts a filename from disk space to user
+ * space
+ */
+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 (fscrypt_is_dot_dotdot(&qname)) {
+		oname->name[0] = '.';
+		oname->name[iname->len - 1] = '.';
+		oname->len = iname->len;
+		return oname->len;
+	}
+
+	if (iname->len < FS_CRYPTO_BLOCK_SIZE)
+		return -EUCLEAN;
+
+	if (inode->i_crypt_info)
+		return fname_decrypt(inode, iname, oname);
+
+	if (iname->len <= FS_FNAME_CRYPTO_DIGEST_SIZE) {
+		ret = digest_encode(iname->name, iname->len, oname->name);
+		oname->len = ret;
+		return ret;
+	}
+	if (hash) {
+		memcpy(buf, &hash, 4);
+		memcpy(buf + 4, &minor_hash, 4);
+	} else {
+		memset(buf, 0, 8);
+	}
+	memcpy(buf + 8, iname->name + iname->len - 16, 16);
+	oname->name[0] = '_';
+	ret = digest_encode(buf, 24, oname->name + 1);
+	oname->len = ret + 1;
+	return ret + 1;
+}
+EXPORT_SYMBOL(fscrypt_fname_disk_to_usr);
+
+/**
+ * fscrypt_fname_usr_to_disk() - converts a filename from user space to disk
+ * space
+ */
+int fscrypt_fname_usr_to_disk(struct inode *inode,
+			const struct qstr *iname,
+			struct fscrypt_str *oname)
+{
+	if (fscrypt_is_dot_dotdot(iname)) {
+		oname->name[0] = '.';
+		oname->name[iname->len - 1] = '.';
+		oname->len = iname->len;
+		return oname->len;
+	}
+	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
+	 */
+	return -EACCES;
+}
+EXPORT_SYMBOL(fscrypt_fname_usr_to_disk);
+
+int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
+			      int lookup, struct fscrypt_name *fname)
+{
+	int ret = 0, bigname = 0;
+
+	memset(fname, 0, sizeof(struct fscrypt_name));
+	fname->usr_fname = 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 = get_crypt_info(dir);
+	if (ret && ret != -EOPNOTSUPP)
+		return ret;
+
+	if (dir->i_crypt_info) {
+		ret = fscrypt_fname_alloc_buffer(dir, iname->len,
+							&fname->crypto_buf);
+		if (ret < 0)
+			return ret;
+		ret = fname_encrypt(dir, iname, &fname->crypto_buf);
+		if (ret < 0)
+			goto errout;
+		fname->disk_name.name = fname->crypto_buf.name;
+		fname->disk_name.len = fname->crypto_buf.len;
+		return 0;
+	}
+	if (!lookup)
+		return -EACCES;
+
+	/*
+	 * 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)))
+		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) {
+		ret = -ENOENT;
+		goto errout;
+	}
+	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:
+	fscrypt_fname_free_buffer(&fname->crypto_buf);
+	return ret;
+}
+EXPORT_SYMBOL(fscrypt_setup_filename);
+
+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 +1,310 @@
+/*
+ * 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 <crypto/hash.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 ablkcipher_request *req = NULL;
+	DECLARE_FS_COMPLETION_RESULT(ecr);
+	struct scatterlist src_sg, dst_sg;
+	struct crypto_ablkcipher *tfm = crypto_alloc_ablkcipher("ecb(aes)", 0,
+								0);
+
+	if (IS_ERR(tfm)) {
+		res = PTR_ERR(tfm);
+		tfm = NULL;
+		goto out;
+	}
+	crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_REQ_WEAK_KEY);
+	req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+	if (!req) {
+		res = -ENOMEM;
+		goto out;
+	}
+	ablkcipher_request_set_callback(req,
+			CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+			derive_crypt_complete, &ecr);
+	res = crypto_ablkcipher_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);
+	ablkcipher_request_set_crypt(req, &src_sg, &dst_sg,
+					FS_AES_256_XTS_KEY_SIZE, NULL);
+	res = crypto_ablkcipher_encrypt(req);
+	if (res == -EINPROGRESS || res == -EBUSY) {
+		wait_for_completion(&ecr.completion);
+		res = ecr.res;
+	}
+out:
+	if (req)
+		ablkcipher_request_free(req);
+	if (tfm)
+		crypto_free_ablkcipher(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 = ((struct user_key_payload *)keyring_key->payload.data);
+	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;
+
+	if (ci->ci_keyring_key)
+		key_put(ci->ci_keyring_key);
+	crypto_free_ablkcipher(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_ablkcipher *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_ablkcipher(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_ablkcipher_clear_flags(ctfm, ~0);
+	crypto_tfm_set_flags(crypto_ablkcipher_tfm(ctfm),
+					CRYPTO_TFM_REQ_WEAK_KEY);
+	res = crypto_ablkcipher_setkey(ctfm, raw_key, fscrypt_key_size(mode));
+	if (res)
+		goto out;
+
+	memzero_explicit(raw_key, sizeof(raw_key));
+	if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) != NULL) {
+		put_crypt_info(crypt_info);
+		goto retry;
+	}
+	return 0;
+
+out:
+	if (res == -ENOKEY)
+		res = 0;
+	put_crypt_info(crypt_info);
+	memzero_explicit(raw_key, sizeof(raw_key));
+	return res;
+}
+
+void fscrypt_put_encryption_info(struct inode *inode, struct fscrypt_info *ci)
+{
+	struct fscrypt_info *prev;
+
+	if (ci == NULL)
+		ci = ACCESS_ONCE(inode->i_crypt_info);
+	if (ci == NULL)
+		return;
+
+	prev = cmpxchg(&inode->i_crypt_info, ci, NULL);
+	if (prev != ci)
+		return;
+
+	put_crypt_info(ci);
+}
+EXPORT_SYMBOL(fscrypt_put_encryption_info);
+
+int fscrypt_get_encryption_info(struct inode *inode)
+{
+	struct fscrypt_info *ci = inode->i_crypt_info;
+
+	if (!ci ||
+		(ci->ci_keyring_key &&
+		 (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
+					       (1 << KEY_FLAG_REVOKED) |
+					       (1 << KEY_FLAG_DEAD)))))
+		return get_crypt_info(inode);
+	return 0;
+}
+EXPORT_SYMBOL(fscrypt_get_encryption_info);

fs/crypto/policy.c

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

fs/ecryptfs/inode.c

@@ -48,6 +48,34 @@
 #include "ecryptfs_dlp.h"
 #endif
 
+/* Do not directly use this function. Use ECRYPTFS_OVERRIDE_CRED() instead. */
+const struct cred * ecryptfs_override_fsids(uid_t fsuid, gid_t fsgid)
+{
+	struct cred * cred; 
+	const struct cred * old_cred; 
+
+	cred = prepare_creds(); 
+	if (!cred) 
+		return NULL; 
+
+	cred->fsuid = make_kuid(current_user_ns(), fsuid);
+	cred->fsgid = make_kgid(current_user_ns(), fsgid);
+
+	old_cred = override_creds(cred); 
+
+	return old_cred; 
+}
+
+/* Do not directly use this function, use REVERT_CRED() instead. */
+void ecryptfs_revert_fsids(const struct cred * old_cred)
+{
+	const struct cred * cur_cred; 
+
+	cur_cred = current->cred; 
+	revert_creds(old_cred); 
+	put_cred(cur_cred); 
+}
+
 #ifndef CONFIG_SDP
 static struct dentry *lock_parent(struct dentry *dentry)
 {
@@ -490,8 +518,6 @@ static int ecryptfs_lookup_interpose(struct dentry *dentry,
 	dentry_info->lower_path.dentry = lower_dentry;
 
 	if (!lower_dentry->d_inode) {
-		/* We want to add because we couldn't find in lower */
-		d_add(dentry, NULL);
 		return 0;
 	}
 	inode = __ecryptfs_get_inode(lower_inode, dir_inode->i_sb);

fs/f2fs/Kconfig

@@ -1,6 +1,8 @@
 config F2FS_FS
-	tristate "F2FS filesystem support (EXPERIMENTAL)"
+	tristate "F2FS filesystem support"
 	depends on BLOCK
+	select CRYPTO
+	select CRYPTO_CRC32
 	help
 	  F2FS is based on Log-structured File System (LFS), which supports
 	  versatile "flash-friendly" features. The design has been focused on
@@ -45,7 +47,7 @@ config F2FS_FS_POSIX_ACL
 	default y
 	help
 	  Posix Access Control Lists (ACLs) support permissions for users and
-	  gourps beyond the owner/group/world scheme.
+	  groups beyond the owner/group/world scheme.
 
 	  To learn more about Access Control Lists, visit the POSIX ACLs for
 	  Linux website <http://acl.bestbits.at/>.
@@ -71,3 +73,32 @@ config F2FS_CHECK_FS
 	  Enables BUG_ONs which check the filesystem consistency in runtime.
 
 	  If you want to improve the performance, say N.
+
+config F2FS_FS_ENCRYPTION
+	bool "F2FS Encryption"
+	depends on F2FS_FS
+	depends on F2FS_FS_XATTR
+	select FS_ENCRYPTION
+	help
+	  Enable encryption of f2fs 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.
+
+config F2FS_IO_TRACE
+	bool "F2FS IO tracer"
+	depends on F2FS_FS
+	depends on FUNCTION_TRACER
+	help
+	  F2FS IO trace is based on a function trace, which gathers process
+	  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

@@ -2,6 +2,8 @@ obj-$(CONFIG_F2FS_FS) += f2fs.o
 
 f2fs-y		:= dir.o file.o inode.o namei.o hash.o super.o inline.o
 f2fs-y		+= checkpoint.o gc.o data.o node.o segment.o recovery.o
+f2fs-y		+= shrinker.o extent_cache.o
 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

fs/f2fs/acl.c

@@ -62,7 +62,7 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size)
 	if (count == 0)
 		return NULL;
 
-	acl = posix_acl_alloc(count, GFP_KERNEL);
+	acl = posix_acl_alloc(count, GFP_NOFS);
 	if (!acl)
 		return ERR_PTR(-ENOMEM);
 
@@ -115,8 +115,8 @@ static void *f2fs_acl_to_disk(const struct posix_acl *acl, size_t *size)
 	struct f2fs_acl_entry *entry;
 	int i;
 
-	f2fs_acl = kmalloc(sizeof(struct f2fs_acl_header) + acl->a_count *
-			sizeof(struct f2fs_acl_entry), GFP_KERNEL);
+	f2fs_acl = f2fs_kmalloc(sizeof(struct f2fs_acl_header) + acl->a_count *
+			sizeof(struct f2fs_acl_entry), GFP_NOFS);
 	if (!f2fs_acl)
 		return ERR_PTR(-ENOMEM);
 
@@ -162,7 +162,8 @@ fail:
 	return ERR_PTR(-EINVAL);
 }
 
-struct posix_acl *f2fs_get_acl(struct inode *inode, int type)
+static struct posix_acl *__f2fs_get_acl(struct inode *inode, int type,
+						struct page *dpage)
 {
 	int name_index = F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT;
 	void *value = NULL;
@@ -172,12 +173,13 @@ struct posix_acl *f2fs_get_acl(struct inode *inode, int type)
 	if (type == ACL_TYPE_ACCESS)
 		name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS;
 
-	retval = f2fs_getxattr(inode, name_index, "", NULL, 0);
+	retval = f2fs_getxattr(inode, name_index, "", NULL, 0, dpage);
 	if (retval > 0) {
-		value = kmalloc(retval, GFP_F2FS_ZERO);
+		value = f2fs_kmalloc(retval, GFP_F2FS_ZERO);
 		if (!value)
 			return ERR_PTR(-ENOMEM);
-		retval = f2fs_getxattr(inode, name_index, "", value, retval);
+		retval = f2fs_getxattr(inode, name_index, "", value,
+							retval, dpage);
 	}
 
 	if (retval > 0)
@@ -188,16 +190,17 @@ struct posix_acl *f2fs_get_acl(struct inode *inode, int type)
 		acl = ERR_PTR(retval);
 	kfree(value);
 
-	if (!IS_ERR(acl))
-		set_cached_acl(inode, type, acl);
-
 	return acl;
 }
 
+struct posix_acl *f2fs_get_acl(struct inode *inode, int type)
+{
+	return __f2fs_get_acl(inode, type, NULL);
+}
+
 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;
@@ -210,7 +213,7 @@ static int __f2fs_set_acl(struct inode *inode, int type,
 			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;
 		}
@@ -229,7 +232,7 @@ static int __f2fs_set_acl(struct inode *inode, int type,
 	if (acl) {
 		value = f2fs_acl_to_disk(acl, &size);
 		if (IS_ERR(value)) {
-			cond_clear_inode_flag(fi, FI_ACL_MODE);
+			clear_inode_flag(inode, FI_ACL_MODE);
 			return (int)PTR_ERR(value);
 		}
 	}
@@ -240,7 +243,7 @@ static int __f2fs_set_acl(struct inode *inode, int type,
 	if (!error)
 		set_cached_acl(inode, type, acl);
 
-	cond_clear_inode_flag(fi, FI_ACL_MODE);
+	clear_inode_flag(inode, FI_ACL_MODE);
 	return error;
 }
 
@@ -249,22 +252,147 @@ int f2fs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	return __f2fs_set_acl(inode, type, acl, NULL);
 }
 
-int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage)
+/*
+ * Most part of f2fs_acl_clone, f2fs_acl_create_masq, f2fs_acl_create
+ * are copied from posix_acl.c
+ */
+static struct posix_acl *f2fs_acl_clone(const struct posix_acl *acl,
+							gfp_t flags)
 {
-	struct posix_acl *default_acl, *acl;
+	struct posix_acl *clone = NULL;
+
+	if (acl) {
+		int size = sizeof(struct posix_acl) + acl->a_count *
+				sizeof(struct posix_acl_entry);
+		clone = kmemdup(acl, size, flags);
+		if (clone)
+			atomic_set(&clone->a_refcount, 1);
+	}
+	return clone;
+}
+
+static int f2fs_acl_create_masq(struct posix_acl *acl, umode_t *mode_p)
+{
+	struct posix_acl_entry *pa, *pe;
+	struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL;
+	umode_t mode = *mode_p;
+	int not_equiv = 0;
+
+	/* assert(atomic_read(acl->a_refcount) == 1); */
+
+	FOREACH_ACL_ENTRY(pa, acl, pe) {
+		switch(pa->e_tag) {
+		case ACL_USER_OBJ:
+			pa->e_perm &= (mode >> 6) | ~S_IRWXO;
+			mode &= (pa->e_perm << 6) | ~S_IRWXU;
+			break;
+
+		case ACL_USER:
+		case ACL_GROUP:
+			not_equiv = 1;
+			break;
+
+		case ACL_GROUP_OBJ:
+			group_obj = pa;
+			break;
+
+		case ACL_OTHER:
+			pa->e_perm &= mode | ~S_IRWXO;
+			mode &= pa->e_perm | ~S_IRWXO;
+			break;
+
+		case ACL_MASK:
+			mask_obj = pa;
+			not_equiv = 1;
+			break;
+
+		default:
+			return -EIO;
+		}
+	}
+
+	if (mask_obj) {
+		mask_obj->e_perm &= (mode >> 3) | ~S_IRWXO;
+		mode &= (mask_obj->e_perm << 3) | ~S_IRWXG;
+	} else {
+		if (!group_obj)
+			return -EIO;
+		group_obj->e_perm &= (mode >> 3) | ~S_IRWXO;
+		mode &= (group_obj->e_perm << 3) | ~S_IRWXG;
+	}
+
+	*mode_p = (*mode_p & ~S_IRWXUGO) | mode;
+        return not_equiv;
+}
+
+static int f2fs_acl_create(struct inode *dir, umode_t *mode,
+		struct posix_acl **default_acl, struct posix_acl **acl,
+		struct page *dpage)
+{
+	struct posix_acl *p;
+	struct posix_acl *clone;
+	int ret;
+
+	*acl = NULL;
+	*default_acl = NULL;
+
+	if (S_ISLNK(*mode) || !IS_POSIXACL(dir))
+		return 0;
+
+	p = __f2fs_get_acl(dir, ACL_TYPE_DEFAULT, dpage);
+	if (!p || p == ERR_PTR(-EOPNOTSUPP)) {
+		*mode &= ~current_umask();
+		return 0;
+	}
+	if (IS_ERR(p))
+		return PTR_ERR(p);
+
+	clone = f2fs_acl_clone(p, GFP_NOFS);
+	if (!clone)
+		goto no_mem;
+
+	ret = f2fs_acl_create_masq(clone, mode);
+	if (ret < 0)
+		goto no_mem_clone;
+
+	if (ret == 0)
+		posix_acl_release(clone);
+	else
+		*acl = clone;
+
+	if (!S_ISDIR(*mode))
+		posix_acl_release(p);
+	else
+		*default_acl = p;
+
+	return 0;
+
+no_mem_clone:
+	posix_acl_release(clone);
+no_mem:
+	posix_acl_release(p);
+	return -ENOMEM;
+}
+
+int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage,
+							struct page *dpage)
+{
+	struct posix_acl *default_acl = NULL, *acl = NULL;
 	int error = 0;
 
-	error = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl);
+	error = f2fs_acl_create(dir, &inode->i_mode, &default_acl, &acl, dpage);
 	if (error)
 		return error;
 
+	f2fs_mark_inode_dirty_sync(inode);
+
 	if (default_acl) {
 		error = __f2fs_set_acl(inode, ACL_TYPE_DEFAULT, default_acl,
 				       ipage);
 		posix_acl_release(default_acl);
 	}
 	if (acl) {
-		if (error)
+		if (!error)
 			error = __f2fs_set_acl(inode, ACL_TYPE_ACCESS, acl,
 					       ipage);
 		posix_acl_release(acl);

fs/f2fs/acl.h

@@ -37,15 +37,16 @@ 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_init_acl(struct inode *, struct inode *, struct page *);
+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
 
 static inline int f2fs_init_acl(struct inode *inode, struct inode *dir,
-							struct page *page)
+				struct page *ipage, struct page *dpage)
 {
 	return 0;
 }

fs/f2fs/debug.c

@@ -33,19 +33,33 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	int i;
 
 	/* validation check of the segment numbers */
-	si->hit_ext = sbi->read_hit_ext;
-	si->total_ext = sbi->total_hit_ext;
+	si->hit_largest = atomic64_read(&sbi->read_hit_largest);
+	si->hit_cached = atomic64_read(&sbi->read_hit_cached);
+	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 = 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_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_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->valid_node_count = valid_node_count(sbi);
 	si->valid_inode_count = valid_inode_count(sbi);
-	si->inline_inode = sbi->inline_inode;
+	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);
@@ -55,7 +69,9 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->node_pages = NODE_MAPPING(sbi)->nrpages;
 	si->meta_pages = META_MAPPING(sbi)->nrpages;
 	si->nats = NM_I(sbi)->nat_cnt;
-	si->sits = SIT_I(sbi)->dirty_sentries;
+	si->dirty_nats = NM_I(sbi)->dirty_nat_cnt;
+	si->sits = MAIN_SEGS(sbi);
+	si->dirty_sits = SIT_I(sbi)->dirty_sentries;
 	si->fnids = NM_I(sbi)->fcnt;
 	si->bg_gc = sbi->bg_gc;
 	si->util_free = (int)(free_user_blocks(sbi) >> sbi->log_blocks_per_seg)
@@ -77,6 +93,8 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 		si->segment_count[i] = sbi->segment_count[i];
 		si->block_count[i] = sbi->block_count[i];
 	}
+
+	si->inplace_count = atomic_read(&sbi->inplace_count);
 }
 
 /*
@@ -85,13 +103,14 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 static void update_sit_info(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_stat_info *si = F2FS_STAT(sbi);
-	unsigned int blks_per_sec, hblks_per_sec, total_vblocks, bimodal, dist;
+	unsigned long long blks_per_sec, hblks_per_sec, total_vblocks;
+	unsigned long long bimodal, dist;
 	unsigned int segno, vblocks;
 	int ndirty = 0;
 
 	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);
@@ -103,10 +122,10 @@ static void update_sit_info(struct f2fs_sb_info *sbi)
 			ndirty++;
 		}
 	}
-	dist = MAIN_SECS(sbi) * hblks_per_sec * hblks_per_sec / 100;
-	si->bimodal = bimodal / dist;
+	dist = div_u64(MAIN_SECS(sbi) * hblks_per_sec * hblks_per_sec, 100);
+	si->bimodal = div64_u64(bimodal, dist);
 	if (si->dirty_count)
-		si->avg_vblocks = total_vblocks / ndirty;
+		si->avg_vblocks = div_u64(total_vblocks, ndirty);
 	else
 		si->avg_vblocks = 0;
 }
@@ -118,6 +137,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_stat_info *si = F2FS_STAT(sbi);
 	unsigned npages;
+	int i;
 
 	if (si->base_mem)
 		goto get_cache;
@@ -125,6 +145,7 @@ 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);
@@ -133,7 +154,8 @@ 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 += 2 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi);
+	si->base_mem += 3 * 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);
 	si->base_mem += __bitmap_size(sbi, SIT_BITMAP);
@@ -145,7 +167,7 @@ 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);
@@ -156,19 +178,35 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 	si->base_mem += sizeof(struct f2fs_nm_info);
 	si->base_mem += __bitmap_size(sbi, NAT_BITMAP);
 
-	/* build gc */
-	si->base_mem += sizeof(struct f2fs_gc_kthread);
-
 get_cache:
+	si->cache_mem = 0;
+
+	/* build gc */
+	if (sbi->gc_thread)
+		si->cache_mem += sizeof(struct f2fs_gc_kthread);
+
+	/* build merge flush thread */
+	if (SM_I(sbi)->cmd_control_info)
+		si->cache_mem += sizeof(struct flush_cmd_control);
+
 	/* free nids */
-	si->cache_mem = NM_I(sbi)->fcnt;
-	si->cache_mem += NM_I(sbi)->nat_cnt;
+	si->cache_mem += NM_I(sbi)->fcnt * sizeof(struct free_nid);
+	si->cache_mem += NM_I(sbi)->nat_cnt * sizeof(struct nat_entry);
+	si->cache_mem += NM_I(sbi)->dirty_nat_cnt *
+					sizeof(struct nat_entry_set);
+	si->cache_mem += si->inmem_pages * sizeof(struct inmem_pages);
+	for (i = 0; i <= ORPHAN_INO; i++)
+		si->cache_mem += sbi->im[i].ino_num * sizeof(struct ino_entry);
+	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->cache_mem += npages << PAGE_CACHE_SHIFT;
+	si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
 	npages = META_MAPPING(sbi)->nrpages;
-	si->cache_mem += npages << PAGE_CACHE_SHIFT;
-	si->cache_mem += sbi->n_orphans * sizeof(struct ino_entry);
-	si->cache_mem += sbi->n_dirty_dirs * sizeof(struct dir_inode_entry);
+	si->page_mem += (unsigned long long)npages << PAGE_SHIFT;
 }
 
 static int stat_show(struct seq_file *s, void *v)
@@ -183,8 +221,9 @@ static int stat_show(struct seq_file *s, void *v)
 
 		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(%s). #%d, %s]=====\n",
+			bdevname(si->sbi->sb->s_bdev, devname), 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",
@@ -198,8 +237,14 @@ static int stat_show(struct seq_file *s, void *v)
 		seq_printf(s, "Other: %u)\n  - Data: %u\n",
 			   si->valid_node_count - si->valid_inode_count,
 			   si->valid_count - si->valid_node_count);
+		seq_printf(s, "  - Inline_xattr Inode: %u\n",
+			   si->inline_xattr);
 		seq_printf(s, "  - Inline_data Inode: %u\n",
 			   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);
@@ -233,25 +278,43 @@ 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\n", si->data_segs);
-		seq_printf(s, "  - node segments : %d\n", si->node_segs);
-		seq_printf(s, "Try to move %d blocks\n", si->tot_blks);
-		seq_printf(s, "  - data blocks : %d\n", si->data_blks);
-		seq_printf(s, "  - node blocks : %d\n", si->node_blks);
-		seq_printf(s, "\nExtent Hit Ratio: %d / %d\n",
-			   si->hit_ext, si->total_ext);
+		seq_printf(s, "  - data segments : %d (%d)\n",
+				si->data_segs, si->bg_data_segs);
+		seq_printf(s, "  - node segments : %d (%d)\n",
+				si->node_segs, si->bg_node_segs);
+		seq_printf(s, "Try to move %d blocks (BG: %d)\n", si->tot_blks,
+				si->bg_data_blks + si->bg_node_blks);
+		seq_printf(s, "  - data blocks : %d (%d)\n", si->data_blks,
+				si->bg_data_blks);
+		seq_printf(s, "  - node blocks : %d (%d)\n", si->node_blks,
+				si->bg_node_blks);
+		seq_puts(s, "\nExtent Cache:\n");
+		seq_printf(s, "  - Hit Count: L1-1:%llu L1-2:%llu L2:%llu\n",
+				si->hit_largest, si->hit_cached,
+				si->hit_rbtree);
+		seq_printf(s, "  - Hit Ratio: %llu%% (%llu / %llu)\n",
+				!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(%d), node: %d\n",
+				si->ext_tree, si->zombie_tree, si->ext_node);
 		seq_puts(s, "\nBalancing F2FS Async:\n");
-		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, "  - NATs: %9d\n  - SITs: %9d\n",
-			   si->nats, si->sits);
+		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",
 			   si->fnids);
 		seq_puts(s, "\nDistribution of User Blocks:");
@@ -269,6 +332,7 @@ static int stat_show(struct seq_file *s, void *v)
 		for (j = 0; j < si->util_free; j++)
 			seq_putc(s, '-');
 		seq_puts(s, "]\n\n");
+		seq_printf(s, "IPU: %u blocks\n", si->inplace_count);
 		seq_printf(s, "SSR: %u blocks in %u segments\n",
 			   si->block_count[SSR], si->segment_count[SSR]);
 		seq_printf(s, "LFS: %u blocks in %u segments\n",
@@ -281,9 +345,14 @@ static int stat_show(struct seq_file *s, void *v)
 
 		/* memory footprint */
 		update_mem_info(si->sbi);
-		seq_printf(s, "\nMemory: %u KB = static: %u + cached: %u\n",
-				(si->base_mem + si->cache_mem) >> 10,
-				si->base_mem >> 10, si->cache_mem >> 10);
+		seq_printf(s, "\nMemory: %llu KB\n",
+			(si->base_mem + si->cache_mem + si->page_mem) >> 10);
+		seq_printf(s, "  - static: %llu KB\n",
+				si->base_mem >> 10);
+		seq_printf(s, "  - cached: %llu KB\n",
+				si->cache_mem >> 10);
+		seq_printf(s, "  - paged : %llu KB\n",
+				si->page_mem >> 10);
 	}
 	mutex_unlock(&f2fs_stat_mutex);
 	return 0;
@@ -321,6 +390,16 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
 	si->sbi = sbi;
 	sbi->stat_info = si;
 
+	atomic64_set(&sbi->total_hit_ext, 0);
+	atomic64_set(&sbi->read_hit_rbtree, 0);
+	atomic64_set(&sbi->read_hit_largest, 0);
+	atomic64_set(&sbi->read_hit_cached, 0);
+
+	atomic_set(&sbi->inline_xattr, 0);
+	atomic_set(&sbi->inline_inode, 0);
+	atomic_set(&sbi->inline_dir, 0);
+	atomic_set(&sbi->inplace_count, 0);
+
 	mutex_lock(&f2fs_stat_mutex);
 	list_add_tail(&si->stat_list, &f2fs_stat_list);
 	mutex_unlock(&f2fs_stat_mutex);
@@ -339,20 +418,23 @@ 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/extent_cache.c

@@ -0,0 +1,749 @@
+/*
+ * f2fs extent cache support
+ *
+ * Copyright (c) 2015 Motorola Mobility
+ * Copyright (c) 2015 Samsung Electronics
+ * Authors: Jaegeuk Kim <jaegeuk@kernel.org>
+ *          Chao Yu <chao2.yu@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/fs.h>
+#include <linux/f2fs_fs.h>
+
+#include "f2fs.h"
+#include "node.h"
+#include <trace/events/f2fs.h>
+
+static struct kmem_cache *extent_tree_slab;
+static struct kmem_cache *extent_node_slab;
+
+static struct extent_node *__attach_extent_node(struct f2fs_sb_info *sbi,
+				struct extent_tree *et, struct extent_info *ei,
+				struct rb_node *parent, struct rb_node **p)
+{
+	struct extent_node *en;
+
+	en = kmem_cache_alloc(extent_node_slab, GFP_ATOMIC);
+	if (!en)
+		return NULL;
+
+	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);
+	atomic_inc(&et->node_cnt);
+	atomic_inc(&sbi->total_ext_node);
+	return en;
+}
+
+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);
+	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)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct extent_tree *et;
+	nid_t ino = inode->i_ino;
+
+	down_write(&sbi->extent_tree_lock);
+	et = radix_tree_lookup(&sbi->extent_tree_root, ino);
+	if (!et) {
+		et = f2fs_kmem_cache_alloc(extent_tree_slab, GFP_NOFS);
+		f2fs_radix_tree_insert(&sbi->extent_tree_root, ino, et);
+		memset(et, 0, sizeof(struct extent_tree));
+		et->ino = ino;
+		et->root = RB_ROOT;
+		et->cached_en = NULL;
+		rwlock_init(&et->lock);
+		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);
+	}
+	up_write(&sbi->extent_tree_lock);
+
+	/* never died until evict_inode */
+	F2FS_I(inode)->extent_tree = et;
+
+	return et;
+}
+
+static struct extent_node *__lookup_extent_tree(struct f2fs_sb_info *sbi,
+				struct extent_tree *et, unsigned int fofs)
+{
+	struct rb_node *node = et->root.rb_node;
+	struct extent_node *en = et->cached_en;
+
+	if (en) {
+		struct extent_info *cei = &en->ei;
+
+		if (cei->fofs <= fofs && cei->fofs + cei->len > fofs) {
+			stat_inc_cached_node_hit(sbi);
+			return en;
+		}
+	}
+
+	while (node) {
+		en = rb_entry(node, struct extent_node, rb_node);
+
+		if (fofs < en->ei.fofs) {
+			node = node->rb_left;
+		} else if (fofs >= en->ei.fofs + en->ei.len) {
+			node = node->rb_right;
+		} else {
+			stat_inc_rbtree_node_hit(sbi);
+			return en;
+		}
+	}
+	return NULL;
+}
+
+static struct extent_node *__init_extent_tree(struct f2fs_sb_info *sbi,
+				struct extent_tree *et, struct extent_info *ei)
+{
+	struct rb_node **p = &et->root.rb_node;
+	struct extent_node *en;
+
+	en = __attach_extent_node(sbi, et, ei, NULL, p);
+	if (!en)
+		return NULL;
+
+	et->largest = en->ei;
+	et->cached_en = en;
+	return en;
+}
+
+static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,
+					struct extent_tree *et)
+{
+	struct rb_node *node, *next;
+	struct extent_node *en;
+	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);
+		__release_extent_node(sbi, et, en);
+		node = next;
+	}
+
+	return count - atomic_read(&et->node_cnt);
+}
+
+static void __drop_largest_extent(struct inode *inode,
+					pgoff_t fofs, unsigned int len)
+{
+	struct extent_info *largest = &F2FS_I(inode)->extent_tree->largest;
+
+	if (fofs < largest->fofs + largest->len && fofs + len > largest->fofs) {
+		largest->len = 0;
+		f2fs_mark_inode_dirty_sync(inode);
+	}
+}
+
+/* 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)) {
+		/* 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 || !i_ext->len)
+		return false;
+
+	get_extent_info(&ei, i_ext);
+
+	write_lock(&et->lock);
+	if (atomic_read(&et->node_cnt))
+		goto out;
+
+	en = __init_extent_tree(sbi, et, &ei);
+	if (en) {
+		spin_lock(&sbi->extent_lock);
+		list_add_tail(&en->list, &sbi->extent_list);
+		spin_unlock(&sbi->extent_lock);
+	}
+out:
+	write_unlock(&et->lock);
+	return false;
+}
+
+static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
+							struct extent_info *ei)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct extent_tree *et = F2FS_I(inode)->extent_tree;
+	struct extent_node *en;
+	bool ret = false;
+
+	f2fs_bug_on(sbi, !et);
+
+	trace_f2fs_lookup_extent_tree_start(inode, pgofs);
+
+	read_lock(&et->lock);
+
+	if (et->largest.fofs <= pgofs &&
+			et->largest.fofs + et->largest.len > pgofs) {
+		*ei = et->largest;
+		ret = true;
+		stat_inc_largest_node_hit(sbi);
+		goto out;
+	}
+
+	en = __lookup_extent_tree(sbi, et, pgofs);
+	if (en) {
+		*ei = en->ei;
+		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);
+		ret = true;
+	}
+out:
+	stat_inc_total_hit(sbi);
+	read_unlock(&et->lock);
+
+	trace_f2fs_lookup_extent_tree_end(inode, pgofs, ei);
+	return ret;
+}
+
+
+/*
+ * lookup extent at @fofs, if hit, return the extent
+ * if not, return NULL and
+ * @prev_ex: extent before fofs
+ * @next_ex: extent after fofs
+ * @insert_p: insert point for new extent at fofs
+ * in order to simpfy the insertion after.
+ * tree must stay unchanged between lookup and insertion.
+ */
+static struct extent_node *__lookup_extent_tree_ret(struct extent_tree *et,
+				unsigned int fofs,
+				struct extent_node **prev_ex,
+				struct extent_node **next_ex,
+				struct rb_node ***insert_p,
+				struct rb_node **insert_parent)
+{
+	struct rb_node **pnode = &et->root.rb_node;
+	struct rb_node *parent = NULL, *tmp_node;
+	struct extent_node *en = et->cached_en;
+
+	*insert_p = NULL;
+	*insert_parent = NULL;
+	*prev_ex = NULL;
+	*next_ex = NULL;
+
+	if (RB_EMPTY_ROOT(&et->root))
+		return NULL;
+
+	if (en) {
+		struct extent_info *cei = &en->ei;
+
+		if (cei->fofs <= fofs && cei->fofs + cei->len > fofs)
+			goto lookup_neighbors;
+	}
+
+	while (*pnode) {
+		parent = *pnode;
+		en = rb_entry(*pnode, struct extent_node, rb_node);
+
+		if (fofs < en->ei.fofs)
+			pnode = &(*pnode)->rb_left;
+		else if (fofs >= en->ei.fofs + en->ei.len)
+			pnode = &(*pnode)->rb_right;
+		else
+			goto lookup_neighbors;
+	}
+
+	*insert_p = pnode;
+	*insert_parent = parent;
+
+	en = rb_entry(parent, struct extent_node, rb_node);
+	tmp_node = parent;
+	if (parent && fofs > en->ei.fofs)
+		tmp_node = rb_next(parent);
+	*next_ex = tmp_node ?
+		rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
+
+	tmp_node = parent;
+	if (parent && fofs < en->ei.fofs)
+		tmp_node = rb_prev(parent);
+	*prev_ex = tmp_node ?
+		rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
+	return NULL;
+
+lookup_neighbors:
+	if (fofs == en->ei.fofs) {
+		/* lookup prev node for merging backward later */
+		tmp_node = rb_prev(&en->rb_node);
+		*prev_ex = tmp_node ?
+			rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
+	}
+	if (fofs == en->ei.fofs + en->ei.len - 1) {
+		/* lookup next node for merging frontward later */
+		tmp_node = rb_next(&en->rb_node);
+		*next_ex = tmp_node ?
+			rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
+	}
+	return en;
+}
+
+static struct extent_node *__try_merge_extent_node(struct inode *inode,
+				struct extent_tree *et, struct extent_info *ei,
+				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)) {
+		prev_ex->ei.len += ei->len;
+		ei = &prev_ex->ei;
+		en = prev_ex;
+	}
+
+	if (next_ex && __is_front_mergeable(ei, &next_ex->ei)) {
+		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)
+		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 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;
+
+	if (insert_p && insert_parent) {
+		parent = insert_parent;
+		p = insert_p;
+		goto do_insert;
+	}
+
+	while (*p) {
+		parent = *p;
+		en = rb_entry(parent, struct extent_node, rb_node);
+
+		if (ei->fofs < en->ei.fofs)
+			p = &(*p)->rb_left;
+		else if (ei->fofs >= en->ei.fofs + en->ei.len)
+			p = &(*p)->rb_right;
+		else
+			f2fs_bug_on(sbi, 1);
+	}
+do_insert:
+	en = __attach_extent_node(sbi, et, ei, parent, p);
+	if (!en)
+		return NULL;
+
+	__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;
+}
+
+static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
+				pgoff_t fofs, block_t blkaddr, unsigned int len)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct extent_tree *et = F2FS_I(inode)->extent_tree;
+	struct extent_node *en = NULL, *en1 = NULL;
+	struct extent_node *prev_en = NULL, *next_en = NULL;
+	struct extent_info ei, dei, prev;
+	struct rb_node **insert_p = NULL, *insert_parent = NULL;
+	unsigned int end = fofs + len;
+	unsigned int pos = (unsigned int)fofs;
+
+	if (!et)
+		return false;
+
+	trace_f2fs_update_extent_tree_range(inode, fofs, blkaddr, len);
+
+	write_lock(&et->lock);
+
+	if (is_inode_flag_set(inode, FI_NO_EXTENT)) {
+		write_unlock(&et->lock);
+		return false;
+	}
+
+	prev = et->largest;
+	dei.len = 0;
+
+	/*
+	 * drop largest extent before lookup, in case it's already
+	 * been shrunk from extent tree
+	 */
+	__drop_largest_extent(inode, fofs, len);
+
+	/* 1. lookup first extent node in range [fofs, fofs + len - 1] */
+	en = __lookup_extent_tree_ret(et, fofs, &prev_en, &next_en,
+					&insert_p, &insert_parent);
+	if (!en)
+		en = next_en;
+
+	/* 2. invlidate all extent nodes in range [fofs, fofs + len - 1] */
+	while (en && en->ei.fofs < end) {
+		unsigned int org_end;
+		int parts = 0;	/* # of parts current extent split into */
+
+		next_en = en1 = NULL;
+
+		dei = en->ei;
+		org_end = dei.fofs + dei.len;
+		f2fs_bug_on(sbi, pos >= org_end);
+
+		if (pos > dei.fofs &&	pos - dei.fofs >= F2FS_MIN_EXTENT_LEN) {
+			en->ei.len = pos - en->ei.fofs;
+			prev_en = en;
+			parts = 1;
+		}
+
+		if (end < org_end && org_end - end >= F2FS_MIN_EXTENT_LEN) {
+			if (parts) {
+				set_extent_info(&ei, end,
+						end - dei.fofs + dei.blk,
+						org_end - end);
+				en1 = __insert_extent_tree(inode, et, &ei,
+							NULL, NULL);
+				next_en = en1;
+			} else {
+				en->ei.fofs = end;
+				en->ei.blk += end - dei.fofs;
+				en->ei.len -= end - dei.fofs;
+				next_en = en;
+			}
+			parts++;
+		}
+
+		if (!next_en) {
+			struct rb_node *node = rb_next(&en->rb_node);
+
+			next_en = node ?
+				rb_entry(node, struct extent_node, rb_node)
+				: NULL;
+		}
+
+		if (parts)
+			__try_update_largest_extent(inode, et, en);
+		else
+			__release_extent_node(sbi, et, en);
+
+		/*
+		 * if original extent is split into zero or two parts, extent
+		 * tree has been altered by deletion or insertion, therefore
+		 * invalidate pointers regard to tree.
+		 */
+		if (parts != 1) {
+			insert_p = NULL;
+			insert_parent = NULL;
+		}
+		en = next_en;
+	}
+
+	/* 3. update extent in extent cache */
+	if (blkaddr) {
+
+		set_extent_info(&ei, fofs, blkaddr, len);
+		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) {
+			__drop_largest_extent(inode, 0, UINT_MAX);
+			set_inode_flag(inode, FI_NO_EXTENT);
+		}
+	}
+
+	if (is_inode_flag_set(inode, FI_NO_EXTENT))
+		__free_extent_tree(sbi, et);
+
+	write_unlock(&et->lock);
+
+	return !__is_extent_same(&prev, &et->largest);
+}
+
+unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
+{
+	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 */
+	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;
+
+	remained = nr_shrink - (node_cnt + tree_cnt);
+
+	spin_lock(&sbi->extent_lock);
+	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);
+
+unlock_out:
+	up_write(&sbi->extent_tree_lock);
+out:
+	trace_f2fs_shrink_extent_tree(sbi, node_cnt, tree_cnt);
+
+	return node_cnt + tree_cnt;
+}
+
+unsigned int f2fs_destroy_extent_node(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct extent_tree *et = F2FS_I(inode)->extent_tree;
+	unsigned int node_cnt = 0;
+
+	if (!et || !atomic_read(&et->node_cnt))
+		return 0;
+
+	write_lock(&et->lock);
+	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);
+	struct extent_tree *et = F2FS_I(inode)->extent_tree;
+	unsigned int node_cnt = 0;
+
+	if (!et)
+		return;
+
+	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;
+	}
+
+	/* free all extent info belong to this extent tree */
+	node_cnt = f2fs_destroy_extent_node(inode);
+
+	/* delete extent tree entry in radix tree */
+	down_write(&sbi->extent_tree_lock);
+	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);
+	atomic_dec(&sbi->total_ext_tree);
+	up_write(&sbi->extent_tree_lock);
+
+	F2FS_I(inode)->extent_tree = NULL;
+
+	trace_f2fs_destroy_extent_tree(inode, node_cnt);
+}
+
+bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
+					struct extent_info *ei)
+{
+	if (!f2fs_may_extent_tree(inode))
+		return false;
+
+	return f2fs_lookup_extent_tree(inode, pgofs, ei);
+}
+
+void f2fs_update_extent_cache(struct dnode_of_data *dn)
+{
+	pgoff_t fofs;
+	block_t blkaddr;
+
+	if (!f2fs_may_extent_tree(dn->inode))
+		return;
+
+	if (dn->data_blkaddr == NEW_ADDR)
+		blkaddr = NULL_ADDR;
+	else
+		blkaddr = dn->data_blkaddr;
+
+	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
+								dn->ofs_in_node;
+	f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, 1);
+}
+
+void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
+				pgoff_t fofs, block_t blkaddr, unsigned int len)
+
+{
+	if (!f2fs_may_extent_tree(dn->inode))
+		return;
+
+	f2fs_update_extent_tree_range(dn->inode, fofs, blkaddr, len);
+}
+
+void init_extent_cache_info(struct f2fs_sb_info *sbi)
+{
+	INIT_RADIX_TREE(&sbi->extent_tree_root, GFP_NOIO);
+	init_rwsem(&sbi->extent_tree_lock);
+	INIT_LIST_HEAD(&sbi->extent_list);
+	spin_lock_init(&sbi->extent_lock);
+	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);
+}
+
+int __init create_extent_cache(void)
+{
+	extent_tree_slab = f2fs_kmem_cache_create("f2fs_extent_tree",
+			sizeof(struct extent_tree));
+	if (!extent_tree_slab)
+		return -ENOMEM;
+	extent_node_slab = f2fs_kmem_cache_create("f2fs_extent_node",
+			sizeof(struct extent_node));
+	if (!extent_node_slab) {
+		kmem_cache_destroy(extent_tree_slab);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void destroy_extent_cache(void)
+{
+	kmem_cache_destroy(extent_node_slab);
+	kmem_cache_destroy(extent_tree_slab);
+}

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"
@@ -24,8 +23,6 @@
 #include "gc.h"
 #include <trace/events/f2fs.h>
 
-static struct kmem_cache *winode_slab;
-
 static int gc_thread_func(void *data)
 {
 	struct f2fs_sb_info *sbi = data;
@@ -46,7 +43,7 @@ static int gc_thread_func(void *data)
 			break;
 
 		if (sbi->sb->s_writers.frozen >= SB_FREEZE_WRITE) {
-			wait_ms = increase_sleep_time(gc_th, wait_ms);
+			increase_sleep_time(gc_th, &wait_ms);
 			continue;
 		}
 
@@ -67,22 +64,25 @@ static int gc_thread_func(void *data)
 			continue;
 
 		if (!is_idle(sbi)) {
-			wait_ms = increase_sleep_time(gc_th, wait_ms);
+			increase_sleep_time(gc_th, &wait_ms);
 			mutex_unlock(&sbi->gc_mutex);
 			continue;
 		}
 
 		if (has_enough_invalid_blocks(sbi))
-			wait_ms = decrease_sleep_time(gc_th, wait_ms);
+			decrease_sleep_time(gc_th, &wait_ms);
 		else
-			wait_ms = increase_sleep_time(gc_th, wait_ms);
+			increase_sleep_time(gc_th, &wait_ms);
 
 		stat_inc_bggc_count(sbi);
 
 		/* if return value is not zero, no victim was selected */
-		if (f2fs_gc(sbi))
+		if (f2fs_gc(sbi, test_opt(sbi, FORCE_FG_GC)))
 			wait_ms = gc_th->no_gc_sleep_time;
 
+		trace_f2fs_background_gc(sbi->sb, wait_ms,
+				prefree_segments(sbi), free_segments(sbi));
+
 		/* balancing f2fs's metadata periodically */
 		f2fs_balance_fs_bg(sbi);
 
@@ -96,9 +96,7 @@ int start_gc_thread(struct f2fs_sb_info *sbi)
 	dev_t dev = sbi->sb->s_bdev->bd_dev;
 	int err = 0;
 
-	if (!test_opt(sbi, BG_GC))
-		goto out;
-	gc_th = kmalloc(sizeof(struct f2fs_gc_kthread), GFP_KERNEL);
+	gc_th = f2fs_kmalloc(sizeof(struct f2fs_gc_kthread), GFP_KERNEL);
 	if (!gc_th) {
 		err = -ENOMEM;
 		goto out;
@@ -174,9 +172,9 @@ 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 */
@@ -247,6 +245,18 @@ static inline unsigned int get_gc_cost(struct f2fs_sb_info *sbi,
 		return get_cb_cost(sbi, segno);
 }
 
+static unsigned int count_bits(const unsigned long *addr,
+				unsigned int offset, unsigned int len)
+{
+	unsigned int end = offset + len, sum = 0;
+
+	while (offset < end) {
+		if (test_bit(offset++, addr))
+			++sum;
+	}
+	return sum;
+}
+
 /*
  * This function is called from two paths.
  * One is garbage collection and the other is SSR segment selection.
@@ -260,8 +270,9 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 {
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	struct victim_sel_policy p;
-	unsigned int secno, max_cost;
-	int nsearched = 0;
+	unsigned int secno, max_cost, last_victim;
+	unsigned int last_segment = MAIN_SEGS(sbi);
+	unsigned int nsearched = 0;
 
 	mutex_lock(&dirty_i->seglist_lock);
 
@@ -271,6 +282,10 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 	p.min_segno = NULL_SEGNO;
 	p.min_cost = max_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)
@@ -281,9 +296,10 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 		unsigned long cost;
 		unsigned int segno;
 
-		segno = find_next_bit(p.dirty_segmap, MAIN_SEGS(sbi), p.offset);
-		if (segno >= MAIN_SEGS(sbi)) {
+		segno = find_next_bit(p.dirty_segmap, last_segment, p.offset);
+		if (segno >= last_segment) {
 			if (sbi->last_victim[p.gc_mode]) {
+				last_segment = sbi->last_victim[p.gc_mode];
 				sbi->last_victim[p.gc_mode] = 0;
 				p.offset = 0;
 				continue;
@@ -292,27 +308,35 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 		}
 
 		p.offset = segno + p.ofs_unit;
-		if (p.ofs_unit > 1)
+		if (p.ofs_unit > 1) {
 			p.offset -= segno % p.ofs_unit;
+			nsearched += count_bits(p.dirty_segmap,
+						p.offset - p.ofs_unit,
+						p.ofs_unit);
+		} else {
+			nsearched++;
+		}
+
 
 		secno = GET_SECNO(sbi, segno);
 
 		if (sec_usage_check(sbi, secno))
-			continue;
+			goto next;
 		if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap))
-			continue;
+			goto next;
 
 		cost = get_gc_cost(sbi, segno, &p);
 
 		if (p.min_cost > cost) {
 			p.min_segno = segno;
 			p.min_cost = cost;
-		} else if (unlikely(cost == max_cost)) {
-			continue;
 		}
-
-		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;
 		}
 	}
@@ -331,6 +355,7 @@ got_it:
 				sbi->cur_victim_sec,
 				prefree_segments(sbi), free_segments(sbi));
 	}
+out:
 	mutex_unlock(&dirty_i->seglist_lock);
 
 	return (p.min_segno == NULL_SEGNO) ? 0 : 1;
@@ -340,37 +365,39 @@ static const struct victim_selection default_v_ops = {
 	.get_victim = get_victim_by_default,
 };
 
-static struct inode *find_gc_inode(nid_t ino, struct list_head *ilist)
+static struct inode *find_gc_inode(struct gc_inode_list *gc_list, nid_t ino)
 {
 	struct inode_entry *ie;
 
-	list_for_each_entry(ie, ilist, list)
-		if (ie->inode->i_ino == ino)
-			return ie->inode;
+	ie = radix_tree_lookup(&gc_list->iroot, ino);
+	if (ie)
+		return ie->inode;
 	return NULL;
 }
 
-static void add_gc_inode(struct inode *inode, struct list_head *ilist)
+static void add_gc_inode(struct gc_inode_list *gc_list, struct inode *inode)
 {
 	struct inode_entry *new_ie;
 
-	if (inode == find_gc_inode(inode->i_ino, ilist)) {
+	if (inode == find_gc_inode(gc_list, inode->i_ino)) {
 		iput(inode);
 		return;
 	}
-
-	new_ie = f2fs_kmem_cache_alloc(winode_slab, GFP_NOFS);
+	new_ie = f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
 	new_ie->inode = inode;
-	list_add_tail(&new_ie->list, ilist);
+
+	f2fs_radix_tree_insert(&gc_list->iroot, inode->i_ino, new_ie);
+	list_add_tail(&new_ie->list, &gc_list->ilist);
 }
 
-static void put_gc_inode(struct list_head *ilist)
+static void put_gc_inode(struct gc_inode_list *gc_list)
 {
 	struct inode_entry *ie, *next_ie;
-	list_for_each_entry_safe(ie, next_ie, ilist, list) {
+	list_for_each_entry_safe(ie, next_ie, &gc_list->ilist, list) {
+		radix_tree_delete(&gc_list->iroot, ie->inode->i_ino);
 		iput(ie->inode);
 		list_del(&ie->list);
-		kmem_cache_free(winode_slab, ie);
+		kmem_cache_free(inode_entry_slab, ie);
 	}
 }
 
@@ -398,14 +425,18 @@ static void gc_node_segment(struct f2fs_sb_info *sbi,
 {
 	bool initial = true;
 	struct f2fs_summary *entry;
+	block_t start_addr;
 	int off;
 
+	start_addr = START_BLOCK(sbi, segno);
+
 next_step:
 	entry = sum;
 
 	for (off = 0; off < sbi->blocks_per_seg; off++, entry++) {
 		nid_t nid = le32_to_cpu(entry->nid);
 		struct page *node_page;
+		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))
@@ -428,38 +459,20 @@ 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);
+		get_node_info(sbi, nid, &ni);
+		if (ni.blk_addr != start_addr + off) {
+			f2fs_put_page(node_page, 1);
+			continue;
 		}
-		f2fs_put_page(node_page, 1);
-		stat_inc_node_blk_count(sbi, 1);
+
+		move_node_page(node_page, gc_type);
+		stat_inc_node_blk_count(sbi, 1, gc_type);
 	}
 
 	if (initial) {
 		initial = false;
 		goto next_step;
 	}
-
-	if (gc_type == FG_GC) {
-		struct writeback_control wbc = {
-			.sync_mode = WB_SYNC_ALL,
-			.nr_to_write = LONG_MAX,
-			.for_reclaim = 0,
-		};
-		sync_node_pages(sbi, 0, &wbc);
-
-		/*
-		 * In the case of FG_GC, it'd be better to reclaim this victim
-		 * completely.
-		 */
-		if (get_valid_blocks(sbi, segno, 1) != 0)
-			goto next_step;
-	}
 }
 
 /*
@@ -469,7 +482,7 @@ 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;
@@ -486,10 +499,10 @@ 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 int check_dnode(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
+static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 		struct node_info *dni, block_t blkaddr, unsigned int *nofs)
 {
 	struct page *node_page;
@@ -502,13 +515,13 @@ static int check_dnode(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 
 	node_page = get_node_page(sbi, nid);
 	if (IS_ERR(node_page))
-		return 0;
+		return false;
 
 	get_node_info(sbi, nid, dni);
 
 	if (sum->version != dni->version) {
 		f2fs_put_page(node_page, 1);
-		return 0;
+		return false;
 	}
 
 	*nofs = ofs_of_node(node_page);
@@ -516,16 +529,116 @@ static int check_dnode(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 	f2fs_put_page(node_page, 1);
 
 	if (source_blkaddr != blkaddr)
-		return 0;
-	return 1;
+		return false;
+	return true;
 }
 
-static void move_data_page(struct inode *inode, struct page *page, int gc_type)
+static void move_encrypted_block(struct inode *inode, block_t bidx)
 {
 	struct f2fs_io_info fio = {
+		.sbi = F2FS_I_SB(inode),
 		.type = DATA,
-		.rw = WRITE_SYNC,
+		.rw = READ_SYNC,
+		.encrypted_page = NULL,
 	};
+	struct dnode_of_data dn;
+	struct f2fs_summary sum;
+	struct node_info ni;
+	struct page *page;
+	block_t newaddr;
+	int err;
+
+	/* do not read out */
+	page = f2fs_grab_cache_page(inode->i_mapping, bidx, false);
+	if (!page)
+		return;
+
+	set_new_dnode(&dn, inode, NULL, NULL, 0);
+	err = get_dnode_of_data(&dn, bidx, LOOKUP_NODE);
+	if (err)
+		goto out;
+
+	if (unlikely(dn.data_blkaddr == NULL_ADDR)) {
+		ClearPageUptodate(page);
+		goto put_out;
+	}
+
+	/*
+	 * 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, 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.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr;
+
+	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)
+		goto put_page_out;
+
+	/* write page */
+	lock_page(fio.encrypted_page);
+
+	if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi))) {
+		err = -EIO;
+		goto put_page_out;
+	}
+	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, 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, true);
+
+	fio.rw = WRITE_SYNC;
+	fio.new_blkaddr = newaddr;
+	f2fs_submit_page_mbio(&fio);
+
+	f2fs_update_data_blkaddr(&dn, newaddr);
+	set_inode_flag(inode, FI_APPEND_WRITE);
+	if (page->index == 0)
+		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:
+	f2fs_put_page(page, 1);
+}
+
+static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
+{
+	struct page *page;
+
+	page = get_lock_data_page(inode, bidx, true);
+	if (IS_ERR(page))
+		return;
 
 	if (gc_type == BG_GC) {
 		if (PageWriteback(page))
@@ -533,12 +646,30 @@ static void move_data_page(struct inode *inode, struct page *page, int gc_type)
 		set_page_dirty(page);
 		set_cold_data(page);
 	} else {
-		f2fs_wait_on_page_writeback(page, DATA);
+		struct f2fs_io_info fio = {
+			.sbi = F2FS_I_SB(inode),
+			.type = DATA,
+			.rw = WRITE_SYNC,
+			.page = page,
+			.encrypted_page = NULL,
+		};
+		bool is_dirty = PageDirty(page);
+		int err;
 
+retry:
+		set_page_dirty(page);
+		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(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:
@@ -553,7 +684,7 @@ out:
  * the victim data block is ignored.
  */
 static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
-		struct list_head *ilist, unsigned int segno, int gc_type)
+		struct gc_inode_list *gc_list, unsigned int segno, int gc_type)
 {
 	struct super_block *sb = sbi->sb;
 	struct f2fs_summary *entry;
@@ -586,7 +717,7 @@ next_step:
 		}
 
 		/* Get an inode by ino with checking validity */
-		if (check_dnode(sbi, entry, &dni, start_addr + off, &nofs) == 0)
+		if (!is_alive(sbi, entry, &dni, start_addr + off, &nofs))
 			continue;
 
 		if (phase == 1) {
@@ -601,141 +732,217 @@ next_step:
 			if (IS_ERR(inode) || is_bad_inode(inode))
 				continue;
 
-			start_bidx = start_bidx_of_node(nofs, F2FS_I(inode));
+			/* if encrypted inode, let's go phase 3 */
+			if (f2fs_encrypted_inode(inode) &&
+						S_ISREG(inode->i_mode)) {
+				add_gc_inode(gc_list, inode);
+				continue;
+			}
 
-			data_page = find_data_page(inode,
-					start_bidx + ofs_in_node, false);
-			if (IS_ERR(data_page))
-				goto next_iput;
+			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)) {
+				iput(inode);
+				continue;
+			}
 
 			f2fs_put_page(data_page, 0);
-			add_gc_inode(inode, ilist);
-		} else {
-			inode = find_gc_inode(dni.ino, ilist);
-			if (inode) {
-				start_bidx = start_bidx_of_node(nofs,
-								F2FS_I(inode));
-				data_page = get_lock_data_page(inode,
-						start_bidx + ofs_in_node);
-				if (IS_ERR(data_page))
-					continue;
-				move_data_page(inode, data_page, gc_type);
-				stat_inc_data_blk_count(sbi, 1);
-			}
+			add_gc_inode(gc_list, inode);
+			continue;
+		}
+
+		/* phase 3 */
+		inode = find_gc_inode(gc_list, dni.ino);
+		if (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);
 		}
-		continue;
-next_iput:
-		iput(inode);
 	}
 
 	if (++phase < 4)
 		goto next_step;
-
-	if (gc_type == FG_GC) {
-		f2fs_submit_merged_bio(sbi, DATA, WRITE);
-
-		/*
-		 * In the case of FG_GC, it'd be better to reclaim this victim
-		 * completely.
-		 */
-		if (get_valid_blocks(sbi, segno, 1) != 0) {
-			phase = 2;
-			goto next_step;
-		}
-	}
 }
 
 static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim,
-						int gc_type, int type)
+			int gc_type)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
 	int ret;
+
 	mutex_lock(&sit_i->sentry_lock);
-	ret = DIRTY_I(sbi)->v_ops->get_victim(sbi, victim, gc_type, type, LFS);
+	ret = DIRTY_I(sbi)->v_ops->get_victim(sbi, victim, gc_type,
+					      NO_CHECK_TYPE, LFS);
 	mutex_unlock(&sit_i->sentry_lock);
 	return ret;
 }
 
-static void do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int segno,
-				struct list_head *ilist, int gc_type)
+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;
-
-	/* read segment summary of victim */
-	sum_page = get_sum_page(sbi, segno);
-
-	blk_start_plug(&plug);
-
-	sum = page_address(sum_page);
-
-	switch (GET_SUM_TYPE((&sum->footer))) {
-	case SUM_TYPE_NODE:
-		gc_node_segment(sbi, sum->entries, segno, gc_type);
-		break;
-	case SUM_TYPE_DATA:
-		gc_data_segment(sbi, sum->entries, ilist, segno, gc_type);
-		break;
-	}
-	blk_finish_plug(&plug);
-
-	stat_inc_seg_count(sbi, GET_SUM_TYPE((&sum->footer)));
-	stat_inc_call_count(sbi->stat_info);
-
-	f2fs_put_page(sum_page, 1);
-}
-
-int f2fs_gc(struct f2fs_sb_info *sbi)
-{
-	struct list_head ilist;
-	unsigned int segno, i;
-	int gc_type = BG_GC;
-	int nfree = 0;
-	int ret = -1;
-	struct cp_control cpc = {
-		.reason = CP_SYNC,
-	};
-
-	INIT_LIST_HEAD(&ilist);
-gc_more:
-	if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE)))
-		goto stop;
-	if (unlikely(f2fs_cp_error(sbi)))
-		goto stop;
-
-	if (gc_type == BG_GC && has_not_enough_free_secs(sbi, nfree)) {
-		gc_type = FG_GC;
-		write_checkpoint(sbi, &cpc);
-	}
-
-	if (!__get_victim(sbi, &segno, gc_type, NO_CHECK_TYPE))
-		goto stop;
-	ret = 0;
+	unsigned int segno = start_segno;
+	unsigned int end_segno = start_segno + sbi->segs_per_sec;
+	int seg_freed = 0;
+	unsigned char type = IS_DATASEG(get_seg_entry(sbi, segno)->type) ?
+						SUM_TYPE_DATA : SUM_TYPE_NODE;
 
 	/* 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);
+		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++)
-		do_garbage_collect(sbi, segno + i, &ilist, gc_type);
-
-	if (gc_type == FG_GC) {
-		sbi->cur_victim_sec = NULL_SEGNO;
-		nfree++;
-		WARN_ON(get_valid_blocks(sbi, segno, sbi->segs_per_sec));
+	/* reference all summary page */
+	while (segno < end_segno) {
+		sum_page = get_sum_page(sbi, segno++);
+		unlock_page(sum_page);
 	}
 
-	if (has_not_enough_free_secs(sbi, nfree))
-		goto gc_more;
+	blk_start_plug(&plug);
+
+	for (segno = start_segno; segno < end_segno; segno++) {
+
+		if (get_valid_blocks(sbi, segno, 1) == 0)
+			continue;
+
+		/* 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);
+
+		f2fs_put_page(sum_page, 0);
+	}
 
 	if (gc_type == FG_GC)
-		write_checkpoint(sbi, &cpc);
+		f2fs_submit_merged_bio(sbi,
+				(type == SUM_TYPE_NODE) ? NODE : DATA, WRITE);
+
+	blk_finish_plug(&plug);
+
+	if (gc_type == FG_GC) {
+		while (start_segno < end_segno)
+			if (get_valid_blocks(sbi, start_segno++, 1) == 0)
+				seg_freed++;
+	}
+
+	stat_inc_call_count(sbi->stat_info);
+
+	return seg_freed;
+}
+
+int f2fs_gc(struct f2fs_sb_info *sbi, bool sync)
+{
+	unsigned int segno;
+	int gc_type = sync ? FG_GC : BG_GC;
+	int sec_freed = 0, seg_freed;
+	int ret = -EINVAL;
+	struct cp_control cpc;
+	struct gc_inode_list gc_list = {
+		.ilist = LIST_HEAD_INIT(gc_list.ilist),
+		.iroot = RADIX_TREE_INIT(GFP_NOFS),
+	};
+
+	cpc.reason = __get_cp_reason(sbi);
+gc_more:
+	segno = NULL_SEGNO;
+
+	if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE)))
+		goto stop;
+	if (unlikely(f2fs_cp_error(sbi))) {
+		ret = -EIO;
+		goto stop;
+	}
+
+	if (gc_type == BG_GC && has_not_enough_free_secs(sbi, sec_freed)) {
+		gc_type = FG_GC;
+		/*
+		 * If there is no victim and no prefree segment but still not
+		 * enough free sections, we should flush dent/node blocks and do
+		 * garbage collections.
+		 */
+		if (__get_victim(sbi, &segno, gc_type) ||
+						prefree_segments(sbi)) {
+			write_checkpoint(sbi, &cpc);
+			segno = NULL_SEGNO;
+		} else if (has_not_enough_free_secs(sbi, 0)) {
+			write_checkpoint(sbi, &cpc);
+		}
+	}
+
+	if (segno == NULL_SEGNO && !__get_victim(sbi, &segno, gc_type))
+		goto stop;
+	ret = 0;
+
+	seg_freed = do_garbage_collect(sbi, segno, &gc_list, gc_type);
+
+	if (gc_type == FG_GC && seg_freed == sbi->segs_per_sec)
+		sec_freed++;
+
+	if (gc_type == FG_GC)
+		sbi->cur_victim_sec = NULL_SEGNO;
+
+	if (!sync) {
+		if (has_not_enough_free_secs(sbi, sec_freed))
+			goto gc_more;
+
+		if (gc_type == FG_GC)
+			write_checkpoint(sbi, &cpc);
+	}
 stop:
 	mutex_unlock(&sbi->gc_mutex);
 
-	put_gc_inode(&ilist);
+	put_gc_inode(&gc_list);
+
+	if (sync)
+		ret = sec_freed ? 0 : -EAGAIN;
 	return ret;
 }
 
@@ -743,17 +950,3 @@ void build_gc_manager(struct f2fs_sb_info *sbi)
 {
 	DIRTY_I(sbi)->v_ops = &default_v_ops;
 }
-
-int __init create_gc_caches(void)
-{
-	winode_slab = f2fs_kmem_cache_create("f2fs_gc_inodes",
-			sizeof(struct inode_entry));
-	if (!winode_slab)
-		return -ENOMEM;
-	return 0;
-}
-
-void destroy_gc_caches(void)
-{
-	kmem_cache_destroy(winode_slab);
-}

fs/f2fs/gc.h

@@ -35,9 +35,9 @@ struct f2fs_gc_kthread {
 	unsigned int gc_idle;
 };
 
-struct inode_entry {
-	struct list_head list;
-	struct inode *inode;
+struct gc_inode_list {
+	struct list_head ilist;
+	struct radix_tree_root iroot;
 };
 
 /*
@@ -64,26 +64,26 @@ static inline block_t limit_free_user_blocks(struct f2fs_sb_info *sbi)
 	return (long)(reclaimable_user_blocks * LIMIT_FREE_BLOCK) / 100;
 }
 
-static inline long increase_sleep_time(struct f2fs_gc_kthread *gc_th, long wait)
+static inline void increase_sleep_time(struct f2fs_gc_kthread *gc_th,
+								long *wait)
 {
-	if (wait == gc_th->no_gc_sleep_time)
-		return wait;
+	if (*wait == gc_th->no_gc_sleep_time)
+		return;
 
-	wait += gc_th->min_sleep_time;
-	if (wait > gc_th->max_sleep_time)
-		wait = gc_th->max_sleep_time;
-	return wait;
+	*wait += gc_th->min_sleep_time;
+	if (*wait > gc_th->max_sleep_time)
+		*wait = gc_th->max_sleep_time;
 }
 
-static inline long decrease_sleep_time(struct f2fs_gc_kthread *gc_th, long wait)
+static inline void decrease_sleep_time(struct f2fs_gc_kthread *gc_th,
+								long *wait)
 {
-	if (wait == gc_th->no_gc_sleep_time)
-		wait = gc_th->max_sleep_time;
+	if (*wait == gc_th->no_gc_sleep_time)
+		*wait = gc_th->max_sleep_time;
 
-	wait -= gc_th->min_sleep_time;
-	if (wait <= gc_th->min_sleep_time)
-		wait = gc_th->min_sleep_time;
-	return wait;
+	*wait -= gc_th->min_sleep_time;
+	if (*wait <= gc_th->min_sleep_time)
+		*wait = gc_th->min_sleep_time;
 }
 
 static inline bool has_enough_invalid_blocks(struct f2fs_sb_info *sbi)
@@ -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

@@ -79,8 +79,7 @@ f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info)
 	const unsigned char *name = name_info->name;
 	size_t len = name_info->len;
 
-	if ((len <= 2) && (name[0] == '.') &&
-		(name[1] == '.' || name[1] == '\0'))
+	if (is_dot_dotdot(name_info))
 		return 0;
 
 	/* Initialize the default seed for the hash checksum functions */

fs/f2fs/inline.c

@@ -12,38 +12,75 @@
 #include <linux/f2fs_fs.h>
 
 #include "f2fs.h"
+#include "node.h"
 
-bool f2fs_may_inline(struct inode *inode)
+bool f2fs_may_inline_data(struct inode *inode)
 {
-	block_t nr_blocks;
-	loff_t i_size;
-
-	if (!test_opt(F2FS_I_SB(inode), INLINE_DATA))
-		return false;
-
 	if (f2fs_is_atomic_file(inode))
 		return false;
 
-	nr_blocks = F2FS_I(inode)->i_xattr_nid ? 3 : 2;
-	if (inode->i_blocks > nr_blocks)
+	if (!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode))
 		return false;
 
-	i_size = i_size_read(inode);
-	if (i_size > MAX_INLINE_DATA)
+	if (i_size_read(inode) > MAX_INLINE_DATA)
 		return false;
 
+	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
+		return false;
+
+	return true;
+}
+
+bool f2fs_may_inline_dentry(struct inode *inode)
+{
+	if (!test_opt(F2FS_I_SB(inode), INLINE_DENTRY))
+		return false;
+
+	if (!S_ISDIR(inode->i_mode))
+		return false;
+
+	return true;
+}
+
+void read_inline_data(struct page *page, struct page *ipage)
+{
+	void *src_addr, *dst_addr;
+
+	if (PageUptodate(page))
+		return;
+
+	f2fs_bug_on(F2FS_P_SB(page), page->index);
+
+	zero_user_segment(page, MAX_INLINE_DATA, PAGE_SIZE);
+
+	/* Copy the whole inline data block */
+	src_addr = inline_data_addr(ipage);
+	dst_addr = kmap_atomic(page);
+	memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
+	flush_dcache_page(page);
+	kunmap_atomic(dst_addr);
+	if (!PageUptodate(page))
+		SetPageUptodate(page);
+}
+
+bool truncate_inline_inode(struct page *ipage, u64 from)
+{
+	void *addr;
+
+	if (from >= MAX_INLINE_DATA)
+		return false;
+
+	addr = inline_data_addr(ipage);
+
+	f2fs_wait_on_page_writeback(ipage, NODE, true);
+	memset(addr + from, 0, MAX_INLINE_DATA - from);
+	set_page_dirty(ipage);
 	return true;
 }
 
 int f2fs_read_inline_data(struct inode *inode, struct page *page)
 {
 	struct page *ipage;
-	void *src_addr, *dst_addr;
-
-	if (page->index) {
-		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
-		goto out;
-	}
 
 	ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
 	if (IS_ERR(ipage)) {
@@ -51,112 +88,111 @@ int f2fs_read_inline_data(struct inode *inode, struct page *page)
 		return PTR_ERR(ipage);
 	}
 
-	zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
+	if (!f2fs_has_inline_data(inode)) {
+		f2fs_put_page(ipage, 1);
+		return -EAGAIN;
+	}
 
-	/* Copy the whole inline data block */
-	src_addr = inline_data_addr(ipage);
-	dst_addr = kmap(page);
-	memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
-	kunmap(page);
+	if (page->index)
+		zero_user_segment(page, 0, PAGE_SIZE);
+	else
+		read_inline_data(page, ipage);
+
+	if (!PageUptodate(page))
+		SetPageUptodate(page);
 	f2fs_put_page(ipage, 1);
-
-out:
-	SetPageUptodate(page);
 	unlock_page(page);
-
 	return 0;
 }
 
-static int __f2fs_convert_inline_data(struct inode *inode, struct page *page)
+int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 {
-	int err = 0;
-	struct page *ipage;
-	struct dnode_of_data dn;
-	void *src_addr, *dst_addr;
-	block_t new_blk_addr;
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct f2fs_io_info fio = {
+		.sbi = F2FS_I_SB(dn->inode),
 		.type = DATA,
 		.rw = WRITE_SYNC | REQ_PRIO,
+		.page = page,
+		.encrypted_page = NULL,
 	};
+	int dirty, err;
+
+	if (!f2fs_exist_data(dn->inode))
+		goto clear_out;
+
+	err = f2fs_reserve_block(dn, 0);
+	if (err)
+		return err;
+
+	f2fs_bug_on(F2FS_P_SB(page), PageWriteback(page));
+
+	read_inline_data(page, dn->inode_page);
+	set_page_dirty(page);
+
+	/* clear dirty state */
+	dirty = clear_page_dirty_for_io(page);
+
+	/* write data page to try to make data consistent */
+	set_page_writeback(page);
+	fio.old_blkaddr = dn->data_blkaddr;
+	write_data_page(dn, &fio);
+	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(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);
+	f2fs_put_dnode(dn);
+	return 0;
+}
+
+int f2fs_convert_inline_inode(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct dnode_of_data dn;
+	struct page *ipage, *page;
+	int err = 0;
+
+	if (!f2fs_has_inline_data(inode))
+		return 0;
+
+	page = f2fs_grab_cache_page(inode->i_mapping, 0, false);
+	if (!page)
+		return -ENOMEM;
 
 	f2fs_lock_op(sbi);
+
 	ipage = get_node_page(sbi, inode->i_ino);
 	if (IS_ERR(ipage)) {
 		err = PTR_ERR(ipage);
 		goto out;
 	}
 
-	/* someone else converted inline_data already */
-	if (!f2fs_has_inline_data(inode))
-		goto out;
+	set_new_dnode(&dn, inode, ipage, ipage, 0);
 
-	/*
-	 * i_addr[0] is not used for inline data,
-	 * so reserving new block will not destroy inline data
-	 */
-	set_new_dnode(&dn, inode, ipage, NULL, 0);
-	err = f2fs_reserve_block(&dn, 0);
-	if (err)
-		goto out;
+	if (f2fs_has_inline_data(inode))
+		err = f2fs_convert_inline_page(&dn, page);
 
-	f2fs_wait_on_page_writeback(page, DATA);
-	zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
-
-	/* Copy the whole inline data block */
-	src_addr = inline_data_addr(ipage);
-	dst_addr = kmap(page);
-	memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
-	kunmap(page);
-	SetPageUptodate(page);
-
-	/* write data page to try to make data consistent */
-	set_page_writeback(page);
-	write_data_page(page, &dn, &new_blk_addr, &fio);
-	update_extent_cache(new_blk_addr, &dn);
-	f2fs_wait_on_page_writeback(page, DATA);
-
-	/* clear inline data and flag after data writeback */
-	zero_user_segment(ipage, INLINE_DATA_OFFSET,
-				 INLINE_DATA_OFFSET + MAX_INLINE_DATA);
-	clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
-	stat_dec_inline_inode(inode);
-
-	sync_inode_page(&dn);
 	f2fs_put_dnode(&dn);
 out:
 	f2fs_unlock_op(sbi);
+
+	f2fs_put_page(page, 1);
+
+	f2fs_balance_fs(sbi, dn.node_changed);
+
 	return err;
 }
 
-int f2fs_convert_inline_data(struct inode *inode, pgoff_t to_size,
-						struct page *page)
-{
-	struct page *new_page = page;
-	int err;
-
-	if (!f2fs_has_inline_data(inode))
-		return 0;
-	else if (to_size <= MAX_INLINE_DATA)
-		return 0;
-
-	if (!page || page->index != 0) {
-		new_page = grab_cache_page(inode->i_mapping, 0);
-		if (!new_page)
-			return -ENOMEM;
-	}
-
-	err = __f2fs_convert_inline_data(inode, new_page);
-	if (!page || page->index != 0)
-		f2fs_put_page(new_page, 1);
-	return err;
-}
-
-int f2fs_write_inline_data(struct inode *inode,
-				struct page *page, unsigned size)
+int f2fs_write_inline_data(struct inode *inode, struct page *page)
 {
 	void *src_addr, *dst_addr;
-	struct page *ipage;
 	struct dnode_of_data dn;
 	int err;
 
@@ -164,49 +200,29 @@ int f2fs_write_inline_data(struct inode *inode,
 	err = get_dnode_of_data(&dn, 0, LOOKUP_NODE);
 	if (err)
 		return err;
-	ipage = dn.inode_page;
 
-	f2fs_wait_on_page_writeback(ipage, NODE);
-	zero_user_segment(ipage, INLINE_DATA_OFFSET,
-				 INLINE_DATA_OFFSET + MAX_INLINE_DATA);
-	src_addr = kmap(page);
-	dst_addr = inline_data_addr(ipage);
-	memcpy(dst_addr, src_addr, size);
-	kunmap(page);
-
-	/* Release the first data block if it is allocated */
 	if (!f2fs_has_inline_data(inode)) {
-		truncate_data_blocks_range(&dn, 1);
-		set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
-		stat_inc_inline_inode(inode);
+		f2fs_put_dnode(&dn);
+		return -EAGAIN;
 	}
 
-	set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
-	sync_inode_page(&dn);
+	f2fs_bug_on(F2FS_I_SB(inode), page->index);
+
+	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(inode, FI_APPEND_WRITE);
+	set_inode_flag(inode, FI_DATA_EXIST);
+
+	clear_inline_node(dn.inode_page);
 	f2fs_put_dnode(&dn);
-
 	return 0;
 }
 
-void truncate_inline_data(struct inode *inode, u64 from)
-{
-	struct page *ipage;
-
-	if (from >= MAX_INLINE_DATA)
-		return;
-
-	ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
-	if (IS_ERR(ipage))
-		return;
-
-	f2fs_wait_on_page_writeback(ipage, NODE);
-
-	zero_user_segment(ipage, INLINE_DATA_OFFSET + from,
-				INLINE_DATA_OFFSET + MAX_INLINE_DATA);
-	set_page_dirty(ipage);
-	f2fs_put_page(ipage, 1);
-}
-
 bool recover_inline_data(struct inode *inode, struct page *npage)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -231,12 +247,16 @@ 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);
-		update_inode(inode, ipage);
+
+		set_inode_flag(inode, FI_INLINE_DATA);
+		set_inode_flag(inode, FI_DATA_EXIST);
+
+		set_page_dirty(ipage);
 		f2fs_put_page(ipage, 1);
 		return true;
 	}
@@ -244,16 +264,398 @@ process_inline:
 	if (f2fs_has_inline_data(inode)) {
 		ipage = get_node_page(sbi, inode->i_ino);
 		f2fs_bug_on(sbi, IS_ERR(ipage));
-		f2fs_wait_on_page_writeback(ipage, NODE);
-		zero_user_segment(ipage, INLINE_DATA_OFFSET,
-				 INLINE_DATA_OFFSET + MAX_INLINE_DATA);
-		clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
-		update_inode(inode, ipage);
+		if (!truncate_inline_inode(ipage, 0))
+			return false;
+		f2fs_clear_inline_inode(inode);
 		f2fs_put_page(ipage, 1);
 	} else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) {
-		truncate_blocks(inode, 0, false);
-		set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
+		if (truncate_blocks(inode, 0, false))
+			return false;
 		goto process_inline;
 	}
 	return false;
 }
+
+struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
+			struct fscrypt_name *fname, struct page **res_page)
+{
+	struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb);
+	struct f2fs_inline_dentry *inline_dentry;
+	struct qstr name = FSTR_TO_QSTR(&fname->disk_name);
+	struct f2fs_dir_entry *de;
+	struct f2fs_dentry_ptr d;
+	struct page *ipage;
+	f2fs_hash_t namehash;
+
+	ipage = get_node_page(sbi, dir->i_ino);
+	if (IS_ERR(ipage)) {
+		*res_page = ipage;
+		return NULL;
+	}
+
+	namehash = f2fs_dentry_hash(&name);
+
+	inline_dentry = inline_data_addr(ipage);
+
+	make_dentry_ptr(NULL, &d, (void *)inline_dentry, 2);
+	de = find_target_dentry(fname, namehash, NULL, &d);
+	unlock_page(ipage);
+	if (de)
+		*res_page = ipage;
+	else
+		f2fs_put_page(ipage, 0);
+
+	return de;
+}
+
+int make_empty_inline_dir(struct inode *inode, struct inode *parent,
+							struct page *ipage)
+{
+	struct f2fs_inline_dentry *dentry_blk;
+	struct f2fs_dentry_ptr d;
+
+	dentry_blk = inline_data_addr(ipage);
+
+	make_dentry_ptr(NULL, &d, (void *)dentry_blk, 2);
+	do_make_empty_dir(inode, parent, &d);
+
+	set_page_dirty(ipage);
+
+	/* update i_size to MAX_INLINE_DATA */
+	if (i_size_read(inode) < MAX_INLINE_DATA)
+		f2fs_i_size_write(inode, MAX_INLINE_DATA);
+	return 0;
+}
+
+/*
+ * NOTE: ipage is grabbed by caller, but if any error occurs, we should
+ * release ipage in this function.
+ */
+static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
+				struct f2fs_inline_dentry *inline_dentry)
+{
+	struct page *page;
+	struct dnode_of_data dn;
+	struct f2fs_dentry_block *dentry_blk;
+	int err;
+
+	page = f2fs_grab_cache_page(dir->i_mapping, 0, false);
+	if (!page) {
+		f2fs_put_page(ipage, 1);
+		return -ENOMEM;
+	}
+
+	set_new_dnode(&dn, dir, ipage, NULL, 0);
+	err = f2fs_reserve_block(&dn, 0);
+	if (err)
+		goto out;
+
+	f2fs_wait_on_page_writeback(page, DATA, true);
+	zero_user_segment(page, MAX_INLINE_DATA, PAGE_SIZE);
+
+	dentry_blk = kmap_atomic(page);
+
+	/* copy data from inline dentry block to new dentry block */
+	memcpy(dentry_blk->dentry_bitmap, inline_dentry->dentry_bitmap,
+					INLINE_DENTRY_BITMAP_SIZE);
+	memset(dentry_blk->dentry_bitmap + INLINE_DENTRY_BITMAP_SIZE, 0,
+			SIZE_OF_DENTRY_BITMAP - INLINE_DENTRY_BITMAP_SIZE);
+	/*
+	 * we do not need to zero out remainder part of dentry and filename
+	 * field, since we have used bitmap for marking the usage status of
+	 * them, besides, we can also ignore copying/zeroing reserved space
+	 * of dentry block, because them haven't been used so far.
+	 */
+	memcpy(dentry_blk->dentry, inline_dentry->dentry,
+			sizeof(struct f2fs_dir_entry) * NR_INLINE_DENTRY);
+	memcpy(dentry_blk->filename, inline_dentry->filename,
+					NR_INLINE_DENTRY * F2FS_SLOT_LEN);
+
+	kunmap_atomic(dentry_blk);
+	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(dir, FI_INLINE_DENTRY);
+
+	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;
+}
+
+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,
+							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(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 *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);
+	struct page *page = NULL;
+	int err = 0;
+
+	ipage = get_node_page(sbi, dir->i_ino);
+	if (IS_ERR(ipage))
+		return PTR_ERR(ipage);
+
+	dentry_blk = inline_data_addr(ipage);
+	bit_pos = room_for_filename(&dentry_blk->dentry_bitmap,
+						slots, NR_INLINE_DENTRY);
+	if (bit_pos >= NR_INLINE_DENTRY) {
+		err = f2fs_convert_inline_dir(dir, ipage, dentry_blk);
+		if (err)
+			return err;
+		err = -EAGAIN;
+		goto out;
+	}
+
+	if (inode) {
+		down_write(&F2FS_I(inode)->i_sem);
+		page = init_inode_metadata(inode, dir, name, ipage);
+		if (IS_ERR(page)) {
+			err = PTR_ERR(page);
+			goto fail;
+		}
+	}
+
+	f2fs_wait_on_page_writeback(ipage, NODE, true);
+
+	name_hash = f2fs_dentry_hash(name);
+	make_dentry_ptr(NULL, &d, (void *)dentry_blk, 2);
+	f2fs_update_dentry(ino, mode, &d, name, name_hash, bit_pos);
+
+	set_page_dirty(ipage);
+
+	/* we don't need to mark_inode_dirty now */
+	if (inode) {
+		f2fs_i_pino_write(inode, dir->i_ino);
+		f2fs_put_page(page, 1);
+	}
+
+	update_parent_metadata(dir, inode, 0);
+fail:
+	if (inode)
+		up_write(&F2FS_I(inode)->i_sem);
+out:
+	f2fs_put_page(ipage, 1);
+	return err;
+}
+
+void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page,
+					struct inode *dir, struct inode *inode)
+{
+	struct f2fs_inline_dentry *inline_dentry;
+	int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
+	unsigned int bit_pos;
+	int i;
+
+	lock_page(page);
+	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,
+				&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);
+}
+
+bool f2fs_empty_inline_dir(struct inode *dir)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
+	struct page *ipage;
+	unsigned int bit_pos = 2;
+	struct f2fs_inline_dentry *dentry_blk;
+
+	ipage = get_node_page(sbi, dir->i_ino);
+	if (IS_ERR(ipage))
+		return false;
+
+	dentry_blk = inline_data_addr(ipage);
+	bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
+					NR_INLINE_DENTRY,
+					bit_pos);
+
+	f2fs_put_page(ipage, 1);
+
+	if (bit_pos < NR_INLINE_DENTRY)
+		return false;
+
+	return true;
+}
+
+int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
+				struct fscrypt_str *fstr)
+{
+	struct inode *inode = file_inode(file);
+	struct f2fs_inline_dentry *inline_dentry = NULL;
+	struct page *ipage = NULL;
+	struct f2fs_dentry_ptr d;
+
+	if (ctx->pos == NR_INLINE_DENTRY)
+		return 0;
+
+	ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
+	if (IS_ERR(ipage))
+		return PTR_ERR(ipage);
+
+	inline_dentry = inline_data_addr(ipage);
+
+	make_dentry_ptr(inode, &d, (void *)inline_dentry, 2);
+
+	if (!f2fs_fill_dentries(ctx, &d, 0, fstr))
+		ctx->pos = NR_INLINE_DENTRY;
+
+	f2fs_put_page(ipage, 1);
+	return 0;
+}
+
+int f2fs_inline_data_fiemap(struct inode *inode,
+		struct fiemap_extent_info *fieinfo, __u64 start, __u64 len)
+{
+	__u64 byteaddr, ilen;
+	__u32 flags = FIEMAP_EXTENT_DATA_INLINE | FIEMAP_EXTENT_NOT_ALIGNED |
+		FIEMAP_EXTENT_LAST;
+	struct node_info ni;
+	struct page *ipage;
+	int err = 0;
+
+	ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
+	if (IS_ERR(ipage))
+		return PTR_ERR(ipage);
+
+	if (!f2fs_has_inline_data(inode)) {
+		err = -EAGAIN;
+		goto out;
+	}
+
+	ilen = min_t(size_t, MAX_INLINE_DATA, i_size_read(inode));
+	if (start >= ilen)
+		goto out;
+	if (start + len < ilen)
+		ilen = start + len;
+	ilen -= start;
+
+	get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni);
+	byteaddr = (__u64)ni.blk_addr << inode->i_sb->s_blocksize_bits;
+	byteaddr += (char *)inline_data_addr(ipage) - (char *)F2FS_INODE(ipage);
+	err = fiemap_fill_next_extent(fieinfo, start, byteaddr, ilen, flags);
+out:
+	f2fs_put_page(ipage, 1);
+	return err;
+}

fs/f2fs/inode.c

@@ -12,13 +12,19 @@
 #include <linux/f2fs_fs.h>
 #include <linux/buffer_head.h>
 #include <linux/writeback.h>
-#include <linux/bitops.h>
 
 #include "f2fs.h"
 #include "node.h"
 
 #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;
@@ -34,8 +40,9 @@ void f2fs_set_inode_flags(struct inode *inode)
 		new_fl |= S_NOATIME;
 	if (flags & FS_DIRSYNC_FL)
 		new_fl |= S_DIRSYNC;
-	set_mask_bits(&inode->i_flags,
-			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC, new_fl);
+	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)
@@ -51,6 +58,15 @@ static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
 	}
 }
 
+static bool __written_first_block(struct f2fs_inode *ri)
+{
+	block_t addr = le32_to_cpu(ri->i_addr[0]);
+
+	if (addr != NEW_ADDR && addr != NULL_ADDR)
+		return true;
+	return false;
+}
+
 static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
 {
 	if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
@@ -67,6 +83,25 @@ static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
 	}
 }
 
+static void __recover_inline_status(struct inode *inode, struct page *ipage)
+{
+	void *inline_data = inline_data_addr(ipage);
+	__le32 *start = inline_data;
+	__le32 *end = start + MAX_INLINE_DATA / sizeof(__le32);
+
+	while (start < end) {
+		if (*start++) {
+			f2fs_wait_on_page_writeback(ipage, NODE, true);
+
+			set_inode_flag(inode, FI_DATA_EXIST);
+			set_raw_inline(inode, F2FS_INODE(ipage));
+			set_page_dirty(ipage);
+			return;
+		}
+	}
+	return;
+}
+
 static int do_read_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -111,13 +146,30 @@ 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;
 
-	get_extent_info(&fi->ext, ri->i_ext);
-	get_inline_info(fi, ri);
+	if (f2fs_init_extent_tree(inode, &ri->i_ext))
+		set_page_dirty(node_page);
+
+	get_inline_info(inode, ri);
+
+	/* check data exist */
+	if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode))
+		__recover_inline_status(inode, node_page);
 
 	/* get rdev by using inline_info */
 	__get_inode_rdev(inode, ri);
 
+	if (__written_first_block(ri))
+		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);
+
+	stat_inc_inline_xattr(inode);
+	stat_inc_inline_inode(inode);
+	stat_inc_inline_dir(inode);
+
 	return 0;
 }
 
@@ -156,9 +208,13 @@ make_now:
 		inode->i_op = &f2fs_dir_inode_operations;
 		inode->i_fop = &f2fs_dir_operations;
 		inode->i_mapping->a_ops = &f2fs_dblock_aops;
-		mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_ZERO);
+		mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO);
 	} else if (S_ISLNK(inode->i_mode)) {
-		inode->i_op = &f2fs_symlink_inode_operations;
+		if (f2fs_encrypted_inode(inode))
+			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)) {
@@ -178,11 +234,13 @@ bad_inode:
 	return ERR_PTR(ret);
 }
 
-void update_inode(struct inode *inode, struct page *node_page)
+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);
 
@@ -193,8 +251,13 @@ void update_inode(struct inode *inode, struct page *node_page)
 	ri->i_links = cpu_to_le32(inode->i_nlink);
 	ri->i_size = cpu_to_le64(i_size_read(inode));
 	ri->i_blocks = cpu_to_le64(inode->i_blocks);
-	set_raw_extent(&F2FS_I(inode)->ext, &ri->i_ext);
-	set_raw_inline(F2FS_I(inode), ri);
+
+	if (F2FS_I(inode)->extent_tree)
+		set_raw_extent(&F2FS_I(inode)->extent_tree->largest,
+							&ri->i_ext);
+	else
+		memset(&ri->i_ext, 0, sizeof(ri->i_ext));
+	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);
@@ -211,15 +274,19 @@ 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)) {
@@ -228,12 +295,14 @@ 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)
@@ -244,20 +313,15 @@ 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 lock here to prevent from producing dirty node pages
+	 * We need to balance fs here to prevent from producing dirty node pages
 	 * during the urgent cleaning time when runing out of free sections.
 	 */
-	f2fs_lock_op(sbi);
-	update_inode_page(inode);
-	f2fs_unlock_op(sbi);
-
-	if (wbc)
-		f2fs_balance_fs(sbi);
-
+	if (update_inode_page(inode))
+		f2fs_balance_fs(sbi, true);
 	return 0;
 }
 
@@ -268,46 +332,74 @@ void f2fs_evict_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	nid_t xnid = F2FS_I(inode)->i_xattr_nid;
+	int err = 0;
 
 	/* some remained atomic pages should discarded */
-	if (f2fs_is_atomic_file(inode) || f2fs_is_volatile_file(inode))
-		commit_inmem_pages(inode, true);
+	if (f2fs_is_atomic_file(inode))
+		drop_inmem_pages(inode);
 
 	trace_f2fs_evict_inode(inode);
-	truncate_inode_pages_final(&inode->i_data);
+	truncate_inode_pages(&inode->i_data, 0);
 
 	if (inode->i_ino == F2FS_NODE_INO(sbi) ||
 			inode->i_ino == F2FS_META_INO(sbi))
 		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;
 
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	if (time_to_inject(FAULT_EVICT_INODE))
+		goto no_delete;
+#endif
+
 	sb_start_intwrite(inode->i_sb);
-	set_inode_flag(F2FS_I(inode), FI_NO_ALLOC);
+	set_inode_flag(inode, FI_NO_ALLOC);
 	i_size_write(inode, 0);
-
+retry:
 	if (F2FS_HAS_BLOCKS(inode))
-		f2fs_truncate(inode);
+		err = f2fs_truncate(inode);
 
-	f2fs_lock_op(sbi);
-	remove_inode_page(inode);
-	stat_dec_inline_inode(inode);
-	f2fs_unlock_op(sbi);
+	if (!err) {
+		f2fs_lock_op(sbi);
+		err = remove_inode_page(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);
+	stat_dec_inline_dir(inode);
+	stat_dec_inline_inode(inode);
+
 	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(F2FS_I(inode), FI_APPEND_WRITE))
-		add_dirty_inode(sbi, inode->i_ino, APPEND_INO);
-	if (is_inode_flag_set(F2FS_I(inode), FI_UPDATE_WRITE))
-		add_dirty_inode(sbi, inode->i_ino, UPDATE_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:
+	fscrypt_put_encryption_info(inode, NULL);
 	clear_inode(inode);
 }
 
@@ -315,19 +407,32 @@ out_clear:
 void handle_failed_inode(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	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))
-		f2fs_truncate(inode);
+	/*
+	 * 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.
+	 */
+	get_node_info(sbi, inode->i_ino, &ni);
 
-	remove_inode_page(inode);
-	stat_dec_inline_inode(inode);
+	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);
+	}
 
-	alloc_nid_failed(sbi, inode->i_ino);
 	f2fs_unlock_op(sbi);
 
 	/* iput will drop the inode object */

fs/f2fs/node.h

@@ -14,21 +14,38 @@
 /* node block offset on the NAT area dedicated to the given start node id */
 #define	NAT_BLOCK_OFFSET(start_nid) (start_nid / NAT_ENTRY_PER_BLOCK)
 
-/* # of pages to perform readahead before building free nids */
-#define FREE_NID_PAGES 4
+/* # of pages to perform synchronous readahead before building free nids */
+#define FREE_NID_PAGES	8
+#define MAX_FREE_NIDS	(NAT_ENTRY_PER_BLOCK * FREE_NID_PAGES)
+
+#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
+#define SETVEC_SIZE	32
 
 /* return value for read_node_page */
 #define LOCKED_PAGE	1
 
+/* For flag in struct node_info */
+enum {
+	IS_CHECKPOINTED,	/* is it checkpointed before? */
+	HAS_FSYNCED_INODE,	/* is the inode fsynced before? */
+	HAS_LAST_FSYNC,		/* has the latest node fsync mark? */
+	IS_DIRTY,		/* this nat entry is dirty? */
+};
+
 /*
  * For node information
  */
@@ -37,18 +54,11 @@ struct node_info {
 	nid_t ino;		/* inode number of the node's owner */
 	block_t	blk_addr;	/* block address of the node */
 	unsigned char version;	/* version of the node */
-};
-
-enum {
-	IS_CHECKPOINTED,	/* is it checkpointed before? */
-	HAS_FSYNCED_INODE,	/* is the inode fsynced before? */
-	HAS_LAST_FSYNC,		/* has the latest node fsync mark? */
-	IS_DIRTY,		/* this nat entry is dirty? */
+	unsigned char flag;	/* for node information bits */
 };
 
 struct nat_entry {
 	struct list_head list;	/* for clean or dirty nat list */
-	unsigned char flag;	/* for node information bits */
 	struct node_info ni;	/* in-memory node information */
 };
 
@@ -63,20 +73,30 @@ struct nat_entry {
 
 #define inc_node_version(version)	(++version)
 
+static inline void copy_node_info(struct node_info *dst,
+						struct node_info *src)
+{
+	dst->nid = src->nid;
+	dst->ino = src->ino;
+	dst->blk_addr = src->blk_addr;
+	dst->version = src->version;
+	/* should not copy flag here */
+}
+
 static inline void set_nat_flag(struct nat_entry *ne,
 				unsigned int type, bool set)
 {
 	unsigned char mask = 0x01 << type;
 	if (set)
-		ne->flag |= mask;
+		ne->ni.flag |= mask;
 	else
-		ne->flag &= ~mask;
+		ne->ni.flag &= ~mask;
 }
 
 static inline bool get_nat_flag(struct nat_entry *ne, unsigned int type)
 {
 	unsigned char mask = 0x01 << type;
-	return ne->flag & mask;
+	return ne->ni.flag & mask;
 }
 
 static inline void nat_reset_flag(struct nat_entry *ne)
@@ -103,10 +123,24 @@ 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 */
-	DIRTY_DENTS	/* indicates dirty dentry pages */
+	DIRTY_DENTS,	/* indicates dirty dentry pages */
+	INO_ENTRIES,	/* indicates inode entries */
+	EXTENT_CACHE,	/* indicates extent cache */
+	BASE_CHECK,	/* check kernel status */
 };
 
 struct nat_entry_set {
@@ -166,7 +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;
@@ -192,21 +226,26 @@ static inline void set_to_next_nat(struct f2fs_nm_info *nm_i, nid_t start_nid)
 {
 	unsigned int block_off = NAT_BLOCK_OFFSET(start_nid);
 
-	if (f2fs_test_bit(block_off, nm_i->nat_bitmap))
-		f2fs_clear_bit(block_off, nm_i->nat_bitmap);
-	else
-		f2fs_set_bit(block_off, nm_i->nat_bitmap);
+	f2fs_change_bit(block_off, nm_i->nat_bitmap);
 }
 
 static inline void fill_node_footer(struct page *page, nid_t nid,
 				nid_t ino, unsigned int ofs, bool reset)
 {
 	struct f2fs_node *rn = F2FS_NODE(page);
+	unsigned int old_flag = 0;
+
 	if (reset)
 		memset(rn, 0, sizeof(*rn));
+	else
+		old_flag = le32_to_cpu(rn->footer.flag);
+
 	rn->footer.nid = cpu_to_le32(nid);
 	rn->footer.ino = cpu_to_le32(ino);
-	rn->footer.flag = cpu_to_le32(ofs << OFFSET_BIT_SHIFT);
+
+	/* should remain old flag bits such as COLD_BIT_SHIFT */
+	rn->footer.flag = cpu_to_le32((ofs << OFFSET_BIT_SHIFT) |
+					(old_flag & OFFSET_BIT_MASK));
 }
 
 static inline void copy_node_footer(struct page *dst, struct page *src)
@@ -295,17 +334,17 @@ 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)
@@ -323,28 +362,6 @@ static inline nid_t get_nid(struct page *p, int off, bool i)
  *  - Mark cold node blocks in their node footer
  *  - Mark cold data pages in page cache
  */
-static inline int is_file(struct inode *inode, int type)
-{
-	return F2FS_I(inode)->i_advise & type;
-}
-
-static inline void set_file(struct inode *inode, int type)
-{
-	F2FS_I(inode)->i_advise |= type;
-}
-
-static inline void clear_file(struct inode *inode, int type)
-{
-	F2FS_I(inode)->i_advise &= ~type;
-}
-
-#define file_is_cold(inode)	is_file(inode, FADVISE_COLD_BIT)
-#define file_wrong_pino(inode)	is_file(inode, FADVISE_LOST_PINO_BIT)
-#define file_set_cold(inode)	set_file(inode, FADVISE_COLD_BIT)
-#define file_lost_pino(inode)	set_file(inode, FADVISE_LOST_PINO_BIT)
-#define file_clear_cold(inode)	clear_file(inode, FADVISE_COLD_BIT)
-#define file_got_pino(inode)	clear_file(inode, FADVISE_LOST_PINO_BIT)
-
 static inline int is_cold_data(struct page *page)
 {
 	return PageChecked(page);
@@ -370,6 +387,21 @@ 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;
 }
@@ -67,7 +68,30 @@ 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 list_head *head,
+							struct inode *inode)
+{
+	struct fsync_inode_entry *entry;
+
+	entry = kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
+	if (!entry)
+		return NULL;
+
+	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);
@@ -75,28 +99,43 @@ static int recover_dentry(struct inode *inode, struct page *ipage)
 	struct qstr name;
 	struct page *page;
 	struct inode *dir, *einode;
+	struct fsync_inode_entry *entry;
 	int err = 0;
 
-	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) {
+		dir = f2fs_iget(inode->i_sb, pino);
+		if (IS_ERR(dir)) {
+			err = PTR_ERR(dir);
+			goto out;
+		}
+
+		entry = add_fsync_inode(dir_list, dir);
+		if (!entry) {
+			err = -ENOMEM;
+			iput(dir);
+			goto out;
+		}
 	}
 
+	dir = entry->inode;
+
+	if (file_enc_name(inode))
+		return 0;
+
 	name.len = le32_to_cpu(raw_inode->i_namelen);
 	name.name = raw_inode->i_name;
 
 	if (unlikely(name.len > F2FS_NAME_LEN)) {
 		WARN_ON(1);
 		err = -ENAMETOOLONG;
-		goto out_err;
+		goto out;
 	}
 retry:
 	de = f2fs_find_entry(dir, &name, &page);
-	if (de && inode->i_ino == le32_to_cpu(de->ino)) {
-		clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
+	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));
 		if (IS_ERR(einode)) {
@@ -111,28 +150,20 @@ retry:
 			iput(einode);
 			goto out_unmap_put;
 		}
-		f2fs_delete_entry(de, page, einode);
+		f2fs_delete_entry(de, page, dir, einode);
 		iput(einode);
 		goto retry;
-	}
-	err = __f2fs_add_link(dir, &name, inode);
-	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_add_link(dir, &name, inode,
+					inode->i_ino, inode->i_mode);
 	}
-
 	goto out;
 
 out_unmap_put:
-	kunmap(page);
+	f2fs_dentry_kunmap(dir, page);
 	f2fs_put_page(page, 0);
-out_err:
-	iput(dir);
 out:
 	f2fs_msg(inode->i_sb, KERN_NOTICE,
 			"%s: ino = %x, name = %s, dir = %lx, err = %d",
@@ -144,9 +175,10 @@ out:
 static void recover_inode(struct inode *inode, struct page *page)
 {
 	struct f2fs_inode *raw = F2FS_INODE(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);
@@ -154,14 +186,46 @@ static void recover_inode(struct inode *inode, struct page *page)
 	inode->i_ctime.tv_nsec = le32_to_cpu(raw->i_ctime_nsec);
 	inode->i_mtime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec);
 
+	if (file_enc_name(inode))
+		name = "<encrypted>";
+	else
+		name = F2FS_INODE(page)->i_name;
+
 	f2fs_msg(inode->i_sb, KERN_NOTICE, "recover_inode: ino = %x, name = %s",
-			ino_of_node(page), F2FS_INODE(page)->i_name);
+			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 inode *inode;
 	struct page *page = NULL;
 	block_t blkaddr;
 	int err = 0;
@@ -173,10 +237,10 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 	while (1) {
 		struct fsync_inode_entry *entry;
 
-		if (blkaddr < MAIN_BLKADDR(sbi) || blkaddr >= MAX_BLKADDR(sbi))
+		if (!is_valid_blkaddr(sbi, blkaddr, META_POR))
 			return 0;
 
-		page = get_meta_page_ra(sbi, blkaddr);
+		page = get_tmp_page(sbi, blkaddr);
 
 		if (cp_ver != cpver_of_node(page))
 			break;
@@ -186,9 +250,8 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 
 		entry = get_fsync_inode(head, ino_of_node(page));
 		if (entry) {
-			if (IS_INODE(page) && is_dent_dnode(page))
-				set_inode_flag(F2FS_I(entry->inode),
-							FI_INC_LINK);
+			if (!is_same_inode(entry->inode, page))
+				goto next;
 		} else {
 			if (IS_INODE(page) && is_dent_dnode(page)) {
 				err = recover_inode_page(sbi, page);
@@ -196,37 +259,38 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 					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);
-				if (err == -ENOENT)
+			inode = f2fs_iget(sbi->sb, ino_of_node(page));
+			if (IS_ERR(inode)) {
+				err = PTR_ERR(inode);
+				if (err == -ENOENT) {
+					err = 0;
 					goto next;
+				}
+				break;
+			}
+
+			/* add this fsync inode to the list */
+			entry = add_fsync_inode(head, inode);
+			if (!entry) {
+				err = -ENOMEM;
+				iput(inode);
 				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);
 		f2fs_put_page(page, 1);
+
+		ra_meta_pages_cond(sbi, blkaddr);
 	}
 	f2fs_put_page(page, 1);
 	return err;
@@ -236,11 +300,8 @@ 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,
@@ -252,6 +313,7 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
 	struct f2fs_summary_block *sum_node;
 	struct f2fs_summary sum;
 	struct page *sum_page, *node_page;
+	struct dnode_of_data tdn = *dn;
 	nid_t ino, nid;
 	struct inode *inode;
 	unsigned int offset;
@@ -279,17 +341,15 @@ got_it:
 	/* Use the locked dnode page and inode */
 	nid = le32_to_cpu(sum.nid);
 	if (dn->inode->i_ino == nid) {
-		struct dnode_of_data tdn = *dn;
 		tdn.nid = nid;
+		if (!dn->inode_page_locked)
+			lock_page(dn->inode_page);
 		tdn.node_page = dn->inode_page;
 		tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node);
-		truncate_data_blocks_range(&tdn, 1);
-		return 0;
+		goto truncate_out;
 	} else if (dn->nid == nid) {
-		struct dnode_of_data tdn = *dn;
 		tdn.ofs_in_node = le16_to_cpu(sum.ofs_in_node);
-		truncate_data_blocks_range(&tdn, 1);
-		return 0;
+		goto truncate_out;
 	}
 
 	/* Get the node page */
@@ -310,38 +370,54 @@ got_it:
 		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 (ino != dn->inode->i_ino) {
-		truncate_hole(inode, bidx, bidx + 1);
+	/*
+	 * if inode page is locked, unlock temporarily, but its reference
+	 * count keeps alive.
+	 */
+	if (ino == dn->inode->i_ino && dn->inode_page_locked)
+		unlock_page(dn->inode_page);
+
+	set_new_dnode(&tdn, inode, NULL, NULL, 0);
+	if (get_dnode_of_data(&tdn, bidx, LOOKUP_NODE))
+		goto out;
+
+	if (tdn.data_blkaddr == blkaddr)
+		truncate_data_blocks_range(&tdn, 1);
+
+	f2fs_put_dnode(&tdn);
+out:
+	if (ino != dn->inode->i_ino)
 		iput(inode);
-	} else {
-		struct dnode_of_data tdn;
-		set_new_dnode(&tdn, inode, dn->inode_page, NULL, 0);
-		if (get_dnode_of_data(&tdn, bidx, LOOKUP_NODE))
-			return 0;
-		if (tdn.data_blkaddr != NULL_ADDR)
-			truncate_data_blocks_range(&tdn, 1);
-		f2fs_put_page(tdn.node_page, 1);
-	}
+	else if (dn->inode_page_locked)
+		lock_page(dn->inode_page);
+	return 0;
+
+truncate_out:
+	if (datablock_addr(tdn.node_page, tdn.ofs_in_node) == blkaddr)
+		truncate_data_blocks_range(&tdn, 1);
+	if (dn->inode->i_ino == nid && !dn->inode_page_locked)
+		unlock_page(dn->inode_page);
 	return 0;
 }
 
 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 f2fs_summary sum;
 	struct node_info ni;
+	unsigned int start, end;
 	int err = 0, recovered = 0;
 
 	/* step 1: recover xattr */
 	if (IS_INODE(page)) {
 		recover_inline_xattr(inode, page);
 	} else if (f2fs_has_xattr_block(ofs_of_node(page))) {
+		/*
+		 * Deprecated; xattr blocks should be found from cold log.
+		 * But, we should remain this for backward compatibility.
+		 */
 		recover_xattr_data(inode, page, blkaddr);
 		goto out;
 	}
@@ -351,36 +427,63 @@ 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);
-
-	f2fs_lock_op(sbi);
+	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);
 
 	err = get_dnode_of_data(&dn, start, ALLOC_NODE);
-	if (err) {
-		f2fs_unlock_op(sbi);
+	if (err)
 		goto out;
-	}
 
-	f2fs_wait_on_page_writeback(dn.node_page, NODE);
+	f2fs_wait_on_page_writeback(dn.node_page, NODE, true);
 
 	get_node_info(sbi, dn.nid, &ni);
 	f2fs_bug_on(sbi, ni.ino != ino_of_node(page));
 	f2fs_bug_on(sbi, ofs_of_node(dn.node_page) != ofs_of_node(page));
 
-	for (; start < end; start++) {
+	for (; start < end; start++, dn.ofs_in_node++) {
 		block_t src, dest;
 
 		src = datablock_addr(dn.node_page, dn.ofs_in_node);
 		dest = datablock_addr(page, dn.ofs_in_node);
 
-		if (src != dest && dest != NEW_ADDR && dest != NULL_ADDR) {
+		/* skip recovering if dest is the same as src */
+		if (src == dest)
+			continue;
+
+		/* dest is invalid, just invalidate src block */
+		if (dest == NULL_ADDR) {
+			truncate_data_blocks_range(&dn, 1);
+			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);
+			reserve_new_block(&dn);
+			continue;
+		}
+
+		/* dest is valid block, try to recover from src to dest */
+		if (is_valid_blkaddr(sbi, dest, META_POR)) {
+
 			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;
 			}
 
 			/* Check the previous node page having this index */
@@ -388,28 +491,19 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 			if (err)
 				goto err;
 
-			set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version);
-
 			/* write dummy data page */
-			recover_data_page(sbi, NULL, &sum, src, dest);
-			update_extent_cache(dest, &dn);
+			f2fs_replace_block(sbi, &dn, src, dest,
+						ni.version, false, false);
 			recovered++;
 		}
-		dn.ofs_in_node++;
 	}
 
-	/* write node page in place */
-	set_summary(&sum, dn.nid, 0, 0);
-	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);
 	set_page_dirty(dn.node_page);
 err:
 	f2fs_put_dnode(&dn);
-	f2fs_unlock_op(sbi);
 out:
 	f2fs_msg(sbi->sb, KERN_NOTICE,
 		"recover_data: ino = %lx, recovered = %d blocks, err = %d",
@@ -417,8 +511,8 @@ 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;
@@ -427,23 +521,25 @@ static int recover_data(struct f2fs_sb_info *sbi,
 	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) {
 		struct fsync_inode_entry *entry;
 
-		if (blkaddr < MAIN_BLKADDR(sbi) || blkaddr >= MAX_BLKADDR(sbi))
+		if (!is_valid_blkaddr(sbi, blkaddr, META_POR))
 			break;
 
-		page = get_meta_page_ra(sbi, blkaddr);
+		ra_meta_pages_cond(sbi, blkaddr);
+
+		page = get_tmp_page(sbi, blkaddr);
 
 		if (cp_ver != cpver_of_node(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;
 		/*
@@ -451,10 +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;
@@ -466,11 +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);
@@ -481,12 +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",
@@ -495,58 +590,74 @@ int recover_fsync_data(struct f2fs_sb_info *sbi)
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&inode_list);
-
-	/* step #1: find fsynced inode numbers */
-	sbi->por_doing = true;
+	INIT_LIST_HEAD(&dir_list);
 
 	/* prevent checkpoint */
 	mutex_lock(&sbi->cp_mutex);
 
 	blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
 
+	/* 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),
-			MAIN_BLKADDR(sbi) << PAGE_CACHE_SHIFT, -1);
+			(loff_t)MAIN_BLKADDR(sbi) << PAGE_SHIFT, -1);
 
 	if (err) {
-		truncate_inode_pages_final(NODE_MAPPING(sbi));
-		truncate_inode_pages_final(META_MAPPING(sbi));
+		truncate_inode_pages(NODE_MAPPING(sbi), 0);
+		truncate_inode_pages(META_MAPPING(sbi), 0);
 	}
 
-	sbi->por_doing = false;
+	clear_sbi_flag(sbi, SBI_POR_DOING);
 	if (err) {
-		discard_next_dnode(sbi, blkaddr);
+		bool invalidate = false;
+
+		if (test_opt(sbi, LFS)) {
+			update_meta_page(sbi, NULL, blkaddr);
+			invalidate = true;
+		} else if (discard_next_dnode(sbi, blkaddr)) {
+			invalidate = true;
+		}
 
 		/* 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) {
 		struct cp_control cpc = {
-			.reason = CP_SYNC,
+			.reason = CP_RECOVERY,
 		};
 		mutex_unlock(&sbi->cp_mutex);
-		write_checkpoint(sbi, &cpc);
+		err = write_checkpoint(sbi, &cpc);
 	} else {
 		mutex_unlock(&sbi->cp_mutex);
 	}
-	return err;
+
+	destroy_fsync_dnodes(&dir_list);
+	kmem_cache_destroy(fsync_entry_slab);
+	return ret ? ret: err;
 }

fs/f2fs/segment.h

@@ -15,6 +15,7 @@
 #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)
@@ -136,10 +137,12 @@ enum {
 /*
  * BG_GC means the background cleaning job.
  * FG_GC means the on-demand cleaning job.
+ * FORCE_FG_GC means on-demand cleaning job in background.
  */
 enum {
 	BG_GC = 0,
-	FG_GC
+	FG_GC,
+	FORCE_FG_GC,
 };
 
 /* for a function parameter to select a victim segment */
@@ -155,15 +158,17 @@ 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 type;		/* segment type like CURSEG_XXX_TYPE */
+	unsigned char *ckpt_valid_map;	/* validity bitmap of blocks last cp */
+	unsigned char *discard_map;
 	unsigned long long mtime;	/* modification time of the segment */
 };
 
@@ -175,9 +180,19 @@ struct segment_allocation {
 	void (*allocate_segment)(struct f2fs_sb_info *, int, bool);
 };
 
+/*
+ * 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		((unsigned long)-1)
+
+#define IS_ATOMIC_WRITTEN_PAGE(page)			\
+		(page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE)
+
 struct inmem_pages {
 	struct list_head list;
 	struct page *page;
+	block_t old_addr;		/* for revoking when fail to commit */
 };
 
 struct sit_info {
@@ -189,6 +204,7 @@ struct sit_info {
 	char *sit_bitmap;		/* SIT bitmap pointer */
 	unsigned int bitmap_size;	/* SIT bitmap size */
 
+	unsigned long *tmp_map;			/* bitmap for temporal use */
 	unsigned long *dirty_sentries_bitmap;	/* bitmap for dirty sentries */
 	unsigned int dirty_sentries;		/* # of dirty sentries */
 	unsigned int sents_per_block;		/* # of SIT entries per block */
@@ -207,7 +223,7 @@ struct free_segmap_info {
 	unsigned int start_segno;	/* start segment number logically */
 	unsigned int free_segments;	/* # of free segments */
 	unsigned int free_sections;	/* # of free sections */
-	rwlock_t segmap_lock;		/* free segmap lock */
+	spinlock_t segmap_lock;		/* free segmap lock */
 	unsigned long *free_segmap;	/* free segment bitmap */
 	unsigned long *free_secmap;	/* free section bitmap */
 };
@@ -243,6 +259,8 @@ 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 */
@@ -318,9 +336,9 @@ static inline unsigned int find_next_inuse(struct free_segmap_info *free_i,
 		unsigned int max, unsigned int segno)
 {
 	unsigned int ret;
-	read_lock(&free_i->segmap_lock);
+	spin_lock(&free_i->segmap_lock);
 	ret = find_next_bit(free_i->free_segmap, max, segno);
-	read_unlock(&free_i->segmap_lock);
+	spin_unlock(&free_i->segmap_lock);
 	return ret;
 }
 
@@ -331,16 +349,17 @@ static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
 	unsigned int start_segno = secno * sbi->segs_per_sec;
 	unsigned int next;
 
-	write_lock(&free_i->segmap_lock);
+	spin_lock(&free_i->segmap_lock);
 	clear_bit(segno, free_i->free_segmap);
 	free_i->free_segments++;
 
-	next = find_next_bit(free_i->free_segmap, MAIN_SEGS(sbi), start_segno);
+	next = find_next_bit(free_i->free_segmap,
+			start_segno + sbi->segs_per_sec, start_segno);
 	if (next >= start_segno + sbi->segs_per_sec) {
 		clear_bit(secno, free_i->free_secmap);
 		free_i->free_sections++;
 	}
-	write_unlock(&free_i->segmap_lock);
+	spin_unlock(&free_i->segmap_lock);
 }
 
 static inline void __set_inuse(struct f2fs_sb_info *sbi,
@@ -362,7 +381,7 @@ static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
 	unsigned int start_segno = secno * sbi->segs_per_sec;
 	unsigned int next;
 
-	write_lock(&free_i->segmap_lock);
+	spin_lock(&free_i->segmap_lock);
 	if (test_and_clear_bit(segno, free_i->free_segmap)) {
 		free_i->free_segments++;
 
@@ -373,7 +392,7 @@ static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
 				free_i->free_sections++;
 		}
 	}
-	write_unlock(&free_i->segmap_lock);
+	spin_unlock(&free_i->segmap_lock);
 }
 
 static inline void __set_test_and_inuse(struct f2fs_sb_info *sbi,
@@ -381,13 +400,13 @@ static inline void __set_test_and_inuse(struct f2fs_sb_info *sbi,
 {
 	struct free_segmap_info *free_i = FREE_I(sbi);
 	unsigned int secno = segno / sbi->segs_per_sec;
-	write_lock(&free_i->segmap_lock);
+	spin_lock(&free_i->segmap_lock);
 	if (!test_and_set_bit(segno, free_i->free_segmap)) {
 		free_i->free_segments--;
 		if (!test_and_set_bit(secno, free_i->free_secmap))
 			free_i->free_sections--;
 	}
-	write_unlock(&free_i->segmap_lock);
+	spin_unlock(&free_i->segmap_lock);
 }
 
 static inline void get_sit_bitmap(struct f2fs_sb_info *sbi,
@@ -451,6 +470,10 @@ 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);
 }
@@ -460,7 +483,9 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed)
 	int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
 	int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
 
-	if (unlikely(sbi->por_doing))
+	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 +
@@ -512,6 +537,9 @@ 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))
@@ -525,7 +553,7 @@ 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;
@@ -551,16 +579,15 @@ static inline unsigned short curseg_blkoff(struct f2fs_sb_info *sbi, int type)
 	return curseg->next_blkoff;
 }
 
-#ifdef CONFIG_F2FS_CHECK_FS
 static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno)
 {
-	BUG_ON(segno > TOTAL_SEGS(sbi) - 1);
+	f2fs_bug_on(sbi, segno > TOTAL_SEGS(sbi) - 1);
 }
 
 static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr)
 {
-	BUG_ON(blk_addr < SEG0_BLKADDR(sbi));
-	BUG_ON(blk_addr >= MAX_BLKADDR(sbi));
+	f2fs_bug_on(sbi, blk_addr < SEG0_BLKADDR(sbi)
+					|| blk_addr >= MAX_BLKADDR(sbi));
 }
 
 /*
@@ -569,16 +596,11 @@ static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr)
 static inline void check_block_count(struct f2fs_sb_info *sbi,
 		int segno, struct f2fs_sit_entry *raw_sit)
 {
+#ifdef CONFIG_F2FS_CHECK_FS
 	bool is_valid  = test_bit_le(0, raw_sit->valid_map) ? true : false;
 	int valid_blocks = 0;
 	int cur_pos = 0, next_pos;
 
-	/* check segment usage */
-	BUG_ON(GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg);
-
-	/* check boundary of a given segment number */
-	BUG_ON(segno > TOTAL_SEGS(sbi) - 1);
-
 	/* check bitmap with valid block count */
 	do {
 		if (is_valid) {
@@ -594,35 +616,11 @@ static inline void check_block_count(struct f2fs_sb_info *sbi,
 		is_valid = !is_valid;
 	} while (cur_pos < sbi->blocks_per_seg);
 	BUG_ON(GET_SIT_VBLOCKS(raw_sit) != valid_blocks);
-}
-#else
-static inline void check_seg_range(struct f2fs_sb_info *sbi, unsigned int segno)
-{
-	if (segno > TOTAL_SEGS(sbi) - 1)
-		sbi->need_fsck = true;
-}
-
-static inline void verify_block_addr(struct f2fs_sb_info *sbi, block_t blk_addr)
-{
-	if (blk_addr < SEG0_BLKADDR(sbi) || blk_addr >= MAX_BLKADDR(sbi))
-		sbi->need_fsck = true;
-}
-
-/*
- * Summary block is always treated as an invalid block
- */
-static inline void check_block_count(struct f2fs_sb_info *sbi,
-		int segno, struct f2fs_sit_entry *raw_sit)
-{
-	/* check segment usage */
-	if (GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg)
-		sbi->need_fsck = true;
-
-	/* check boundary of a given segment number */
-	if (segno > TOTAL_SEGS(sbi) - 1)
-		sbi->need_fsck = true;
-}
 #endif
+	/* check segment usage, and check boundary of a given segment number */
+	f2fs_bug_on(sbi, GET_SIT_VBLOCKS(raw_sit) > sbi->blocks_per_seg
+					|| segno > TOTAL_SEGS(sbi) - 1);
+}
 
 static inline pgoff_t current_sit_addr(struct f2fs_sb_info *sbi,
 						unsigned int start)
@@ -657,10 +655,7 @@ static inline void set_to_next_sit(struct sit_info *sit_i, unsigned int start)
 {
 	unsigned int block_off = SIT_BLOCK_OFFSET(start);
 
-	if (f2fs_test_bit(block_off, sit_i->sit_bitmap))
-		f2fs_clear_bit(block_off, sit_i->sit_bitmap);
-	else
-		f2fs_set_bit(block_off, sit_i->sit_bitmap);
+	f2fs_change_bit(block_off, sit_i->sit_bitmap);
 }
 
 static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi)
@@ -714,12 +709,15 @@ static inline unsigned int max_hw_blocks(struct f2fs_sb_info *sbi)
  */
 static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type)
 {
+	if (sbi->sb->s_bdi->dirty_exceeded)
+		return 0;
+
 	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;
 }
@@ -737,10 +735,8 @@ 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

@@ -0,0 +1,141 @@
+/*
+ * f2fs shrinker support
+ *   the basic infra was copied from fs/ubifs/shrinker.c
+ *
+ * Copyright (c) 2015 Motorola Mobility
+ * Copyright (c) 2015 Jaegeuk Kim <jaegeuk@kernel.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/fs.h>
+#include <linux/f2fs_fs.h>
+
+#include "f2fs.h"
+#include "node.h"
+
+static LIST_HEAD(f2fs_list);
+static DEFINE_SPINLOCK(f2fs_list_lock);
+static unsigned int shrinker_run_no;
+
+static unsigned long __count_nat_entries(struct f2fs_sb_info *sbi)
+{
+	return NM_I(sbi)->nat_cnt - NM_I(sbi)->dirty_nat_cnt;
+}
+
+static unsigned long __count_free_nids(struct f2fs_sb_info *sbi)
+{
+	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 atomic_read(&sbi->total_zombie_tree) +
+				atomic_read(&sbi->total_ext_node);
+}
+
+unsigned long f2fs_shrink_count(struct shrinker *shrink,
+				struct shrink_control *sc)
+{
+	struct f2fs_sb_info *sbi;
+	struct list_head *p;
+	unsigned long count = 0;
+
+	spin_lock(&f2fs_list_lock);
+	p = f2fs_list.next;
+	while (p != &f2fs_list) {
+		sbi = list_entry(p, struct f2fs_sb_info, s_list);
+
+		/* stop f2fs_put_super */
+		if (!mutex_trylock(&sbi->umount_mutex)) {
+			p = p->next;
+			continue;
+		}
+		spin_unlock(&f2fs_list_lock);
+
+		/* count extent cache entries */
+		count += __count_extent_cache(sbi);
+
+		/* shrink clean nat cache entries */
+		count += __count_nat_entries(sbi);
+
+		/* count free nids cache entries */
+		count += __count_free_nids(sbi);
+
+		spin_lock(&f2fs_list_lock);
+		p = p->next;
+		mutex_unlock(&sbi->umount_mutex);
+	}
+	spin_unlock(&f2fs_list_lock);
+	return count;
+}
+
+unsigned long f2fs_shrink_scan(struct shrinker *shrink,
+				struct shrink_control *sc)
+{
+	unsigned long nr = sc->nr_to_scan;
+	struct f2fs_sb_info *sbi;
+	struct list_head *p;
+	unsigned int run_no;
+	unsigned long freed = 0;
+
+	spin_lock(&f2fs_list_lock);
+	do {
+		run_no = ++shrinker_run_no;
+	} while (run_no == 0);
+	p = f2fs_list.next;
+	while (p != &f2fs_list) {
+		sbi = list_entry(p, struct f2fs_sb_info, s_list);
+
+		if (sbi->shrinker_run_no == run_no)
+			break;
+
+		/* stop f2fs_put_super */
+		if (!mutex_trylock(&sbi->umount_mutex)) {
+			p = p->next;
+			continue;
+		}
+		spin_unlock(&f2fs_list_lock);
+
+		sbi->shrinker_run_no = run_no;
+
+		/* shrink extent cache entries */
+		freed += f2fs_shrink_extent_tree(sbi, nr >> 1);
+
+		/* shrink clean nat cache entries */
+		if (freed < nr)
+			freed += try_to_free_nats(sbi, nr - freed);
+
+		/* shrink free nids cache entries */
+		if (freed < nr)
+			freed += try_to_free_nids(sbi, nr - freed);
+
+		spin_lock(&f2fs_list_lock);
+		p = p->next;
+		list_move_tail(&sbi->s_list, &f2fs_list);
+		mutex_unlock(&sbi->umount_mutex);
+		if (freed >= nr)
+			break;
+	}
+	spin_unlock(&f2fs_list_lock);
+	return freed;
+}
+
+void f2fs_join_shrinker(struct f2fs_sb_info *sbi)
+{
+	spin_lock(&f2fs_list_lock);
+	list_add_tail(&sbi->s_list, &f2fs_list);
+	spin_unlock(&f2fs_list_lock);
+}
+
+void f2fs_leave_shrinker(struct f2fs_sb_info *sbi)
+{
+	f2fs_shrink_extent_tree(sbi, __count_extent_cache(sbi));
+
+	spin_lock(&f2fs_list_lock);
+	list_del(&sbi->s_list);
+	spin_unlock(&f2fs_list_lock);
+}

fs/f2fs/trace.c

@@ -0,0 +1,161 @@
+/*
+ * f2fs IO tracer
+ *
+ * Copyright (c) 2014 Motorola Mobility
+ * Copyright (c) 2014 Jaegeuk Kim <jaegeuk@kernel.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/fs.h>
+#include <linux/f2fs_fs.h>
+#include <linux/sched.h>
+#include <linux/radix-tree.h>
+
+#include "f2fs.h"
+#include "trace.h"
+
+static RADIX_TREE(pids, GFP_ATOMIC);
+static spinlock_t pids_lock;
+static struct last_io_info last_io;
+
+static inline void __print_last_io(void)
+{
+	if (!last_io.len)
+		return;
+
+	trace_printk("%3x:%3x %4x %-16s %2x %5x %12x %4x\n",
+			last_io.major, last_io.minor,
+			last_io.pid, "----------------",
+			last_io.type,
+			last_io.fio.rw,
+			last_io.fio.new_blkaddr,
+			last_io.len);
+	memset(&last_io, 0, sizeof(last_io));
+}
+
+static int __file_type(struct inode *inode, pid_t pid)
+{
+	if (f2fs_is_atomic_file(inode))
+		return __ATOMIC_FILE;
+	else if (f2fs_is_volatile_file(inode))
+		return __VOLATILE_FILE;
+	else if (S_ISDIR(inode->i_mode))
+		return __DIR_FILE;
+	else if (inode->i_ino == F2FS_NODE_INO(F2FS_I_SB(inode)))
+		return __NODE_FILE;
+	else if (inode->i_ino == F2FS_META_INO(F2FS_I_SB(inode)))
+		return __META_FILE;
+	else if (pid)
+		return __NORMAL_FILE;
+	else
+		return __MISC_FILE;
+}
+
+void f2fs_trace_pid(struct page *page)
+{
+	struct inode *inode = page->mapping->host;
+	pid_t pid = task_pid_nr(current);
+	void *p;
+
+	page->private = pid;
+
+	if (radix_tree_preload(GFP_NOFS))
+		return;
+
+	spin_lock(&pids_lock);
+	p = radix_tree_lookup(&pids, pid);
+	if (p == current)
+		goto out;
+	if (p)
+		radix_tree_delete(&pids, pid);
+
+	f2fs_radix_tree_insert(&pids, pid, current);
+
+	trace_printk("%3x:%3x %4x %-16s\n",
+			MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev),
+			pid, current->comm);
+out:
+	spin_unlock(&pids_lock);
+	radix_tree_preload_end();
+}
+
+void f2fs_trace_ios(struct f2fs_io_info *fio, int flush)
+{
+	struct inode *inode;
+	pid_t pid;
+	int major, minor;
+
+	if (flush) {
+		__print_last_io();
+		return;
+	}
+
+	inode = fio->page->mapping->host;
+	pid = page_private(fio->page);
+
+	major = MAJOR(inode->i_sb->s_dev);
+	minor = MINOR(inode->i_sb->s_dev);
+
+	if (last_io.major == major && last_io.minor == minor &&
+			last_io.pid == pid &&
+			last_io.type == __file_type(inode, pid) &&
+			last_io.fio.rw == fio->rw &&
+			last_io.fio.new_blkaddr + last_io.len ==
+							fio->new_blkaddr) {
+		last_io.len++;
+		return;
+	}
+
+	__print_last_io();
+
+	last_io.major = major;
+	last_io.minor = minor;
+	last_io.pid = pid;
+	last_io.type = __file_type(inode, pid);
+	last_io.fio = *fio;
+	last_io.len = 1;
+	return;
+}
+
+void f2fs_build_trace_ios(void)
+{
+	spin_lock_init(&pids_lock);
+}
+
+#define PIDVEC_SIZE	128
+static unsigned int gang_lookup_pids(pid_t *results, unsigned long first_index,
+							unsigned int max_items)
+{
+	struct radix_tree_iter iter;
+	void **slot;
+	unsigned int ret = 0;
+
+	if (unlikely(!max_items))
+		return 0;
+
+	radix_tree_for_each_slot(slot, &pids, &iter, first_index) {
+		results[ret] = iter.index;
+		if (++ret == PIDVEC_SIZE)
+			break;
+	}
+	return ret;
+}
+
+void f2fs_destroy_trace_ios(void)
+{
+	pid_t pid[PIDVEC_SIZE];
+	pid_t next_pid = 0;
+	unsigned int found;
+
+	spin_lock(&pids_lock);
+	while ((found = gang_lookup_pids(pid, next_pid, PIDVEC_SIZE))) {
+		unsigned idx;
+
+		next_pid = pid[found - 1] + 1;
+		for (idx = 0; idx < found; idx++)
+			radix_tree_delete(&pids, pid[idx]);
+	}
+	spin_unlock(&pids_lock);
+}

fs/f2fs/trace.h

@@ -0,0 +1,46 @@
+/*
+ * f2fs IO tracer
+ *
+ * Copyright (c) 2014 Motorola Mobility
+ * Copyright (c) 2014 Jaegeuk Kim <jaegeuk@kernel.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __F2FS_TRACE_H__
+#define __F2FS_TRACE_H__
+
+#ifdef CONFIG_F2FS_IO_TRACE
+#include <trace/events/f2fs.h>
+
+enum file_type {
+	__NORMAL_FILE,
+	__DIR_FILE,
+	__NODE_FILE,
+	__META_FILE,
+	__ATOMIC_FILE,
+	__VOLATILE_FILE,
+	__MISC_FILE,
+};
+
+struct last_io_info {
+	int major, minor;
+	pid_t pid;
+	enum file_type type;
+	struct f2fs_io_info fio;
+	block_t len;
+};
+
+extern void f2fs_trace_pid(struct page *);
+extern void f2fs_trace_ios(struct f2fs_io_info *, int);
+extern void f2fs_build_trace_ios(void);
+extern void f2fs_destroy_trace_ios(void);
+#else
+#define f2fs_trace_pid(p)
+#define f2fs_trace_ios(i, n)
+#define f2fs_build_trace_ios()
+#define f2fs_destroy_trace_ios()
+
+#endif
+#endif /* __F2FS_TRACE_H__ */

fs/f2fs/xattr.c

@@ -83,7 +83,7 @@ static int f2fs_xattr_generic_get(struct dentry *dentry, const char *name,
 	}
 	if (strcmp(name, "") == 0)
 		return -EINVAL;
-	return f2fs_getxattr(dentry->d_inode, type, name, buffer, size);
+	return f2fs_getxattr(d_inode(dentry), type, name, buffer, size, NULL);
 }
 
 static int f2fs_xattr_generic_set(struct dentry *dentry, const char *name,
@@ -108,7 +108,7 @@ static int f2fs_xattr_generic_set(struct dentry *dentry, const char *name,
 	if (strcmp(name, "") == 0)
 		return -EINVAL;
 
-	return f2fs_setxattr(dentry->d_inode, type, name,
+	return f2fs_setxattr(d_inode(dentry), type, name,
 					value, size, NULL, flags);
 }
 
@@ -130,19 +130,20 @@ static size_t f2fs_xattr_advise_list(struct dentry *dentry, char *list,
 static int f2fs_xattr_advise_get(struct dentry *dentry, const char *name,
 		void *buffer, size_t size, int type)
 {
-	struct inode *inode = dentry->d_inode;
+	struct inode *inode = d_inode(dentry);
 
 	if (strcmp(name, "") != 0)
 		return -EINVAL;
 
-	*((char *)buffer) = F2FS_I(inode)->i_advise;
+	if (buffer)
+		*((char *)buffer) = F2FS_I(inode)->i_advise;
 	return sizeof(char);
 }
 
 static int f2fs_xattr_advise_set(struct dentry *dentry, const char *name,
 		const void *value, size_t size, int flags, int type)
 {
-	struct inode *inode = dentry->d_inode;
+	struct inode *inode = d_inode(dentry);
 
 	if (strcmp(name, "") != 0)
 		return -EINVAL;
@@ -152,6 +153,7 @@ static int f2fs_xattr_advise_set(struct dentry *dentry, const char *name,
 		return -EINVAL;
 
 	F2FS_I(inode)->i_advise |= *(char *)value;
+	f2fs_mark_inode_dirty_sync(inode);
 	return 0;
 }
 
@@ -345,7 +347,8 @@ 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 +356,7 @@ 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 +377,7 @@ 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);
@@ -398,7 +401,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 }
 
 int f2fs_getxattr(struct inode *inode, int index, const char *name,
-		void *buffer, size_t buffer_size)
+		void *buffer, size_t buffer_size, struct page *ipage)
 {
 	struct f2fs_xattr_entry *entry;
 	void *base_addr;
@@ -412,7 +415,7 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name,
 	if (len > F2FS_NAME_LEN)
 		return -ERANGE;
 
-	base_addr = read_all_xattrs(inode, NULL);
+	base_addr = read_all_xattrs(inode, ipage);
 	if (!base_addr)
 		return -ENOMEM;
 
@@ -442,7 +445,7 @@ cleanup:
 
 ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
 {
-	struct inode *inode = dentry->d_inode;
+	struct inode *inode = d_inode(dentry);
 	struct f2fs_xattr_entry *entry;
 	void *base_addr;
 	int error = 0;
@@ -481,13 +484,12 @@ 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;
@@ -497,12 +499,15 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 
 	len = strlen(name);
 
-	if (len > F2FS_NAME_LEN || size > MAX_VALUE_LEN(inode))
+	if (len > F2FS_NAME_LEN)
 		return -ERANGE;
 
+	if (size > MAX_VALUE_LEN(inode))
+		return -E2BIG;
+
 	base_addr = read_all_xattrs(inode, ipage);
 	if (!base_addr)
-		goto exit;
+		return -ENOMEM;
 
 	/* find entry with wanted name. */
 	here = __find_xattr(base_addr, index, len, name);
@@ -535,7 +540,7 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 			free = free + ENTRY_SIZE(here);
 
 		if (unlikely(free < newsize)) {
-			error = -ENOSPC;
+			error = -E2BIG;
 			goto exit;
 		}
 	}
@@ -563,7 +568,6 @@ 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);
@@ -577,16 +581,15 @@ 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 (ipage)
-		update_inode(inode, ipage);
-	else
-		update_inode_page(inode);
+	if (index == F2FS_XATTR_INDEX_ENCRYPTION &&
+			!strcmp(name, F2FS_XATTR_NAME_ENCRYPTION_CONTEXT))
+		f2fs_set_encrypted_inode(inode);
+	f2fs_mark_inode_dirty_sync(inode);
 exit:
 	kzfree(base_addr);
 	return error;
@@ -603,7 +606,7 @@ 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 */
@@ -612,5 +615,6 @@ 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

@@ -35,6 +35,10 @@
 #define F2FS_XATTR_INDEX_LUSTRE			5
 #define F2FS_XATTR_INDEX_SECURITY		6
 #define F2FS_XATTR_INDEX_ADVISE			7
+/* Should be same as EXT4_XATTR_INDEX_ENCRYPTION */
+#define F2FS_XATTR_INDEX_ENCRYPTION		9
+
+#define F2FS_XATTR_NAME_ENCRYPTION_CONTEXT	"c"
 
 struct f2fs_xattr_header {
 	__le32  h_magic;        /* magic number for identification */
@@ -115,18 +119,21 @@ extern const struct xattr_handler *f2fs_xattr_handlers[];
 
 extern int f2fs_setxattr(struct inode *, int, const char *,
 				const void *, size_t, struct page *, int);
-extern int f2fs_getxattr(struct inode *, int, const char *, void *, size_t);
+extern int f2fs_getxattr(struct inode *, int, const char *, void *,
+						size_t, struct page *);
 extern ssize_t f2fs_listxattr(struct dentry *, char *, size_t);
 #else
 
 #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;
 }
 static inline int f2fs_getxattr(struct inode *inode, int index,
-		const char *name, void *buffer, size_t buffer_size)
+			const char *name, void *buffer,
+			size_t buffer_size, struct page *dpage)
 {
 	return -EOPNOTSUPP;
 }

fs/sdfat/blkdev.c

@@ -75,7 +75,9 @@ s32 bdev_check_bdi_valid(struct super_block *sb)
 			fsi->prev_eio |= SDFAT_EIO_BDI;
 			sdfat_log_msg(sb, KERN_ERR, "%s: block device is "
 				"eliminated.(bdi:%p)", __func__, sb->s_bdi);
+#ifdef CONFIG_SDFAT_DEBUG
 			sdfat_debug_warn_on(1);
+#endif
 		}
 		return -ENXIO;
 	}
@@ -130,7 +132,9 @@ s32 bdev_mread(struct super_block *sb, u32 secno, struct buffer_head **bh, u32 n
 	if(!(fsi->prev_eio & SDFAT_EIO_READ)) {
 		fsi->prev_eio |= SDFAT_EIO_READ;
 		sdfat_log_msg(sb, KERN_ERR, "%s: No bh. I/O error.", __func__);
+#ifdef CONFIG_SDFAT_DEBUG
 		sdfat_debug_warn_on(1);
+#endif
 	}
 
 	return -EIO;
@@ -187,7 +191,9 @@ no_bh:
 	if(!(fsi->prev_eio & SDFAT_EIO_WRITE)) {
 		fsi->prev_eio |= SDFAT_EIO_WRITE;
 		sdfat_log_msg(sb, KERN_ERR, "%s: No bh. I/O error.", __func__);
+#ifdef CONFIG_SDFAT_DEBUG
 		sdfat_debug_warn_on(1);
+#endif
 	}
 
 	return -EIO;

include/linux/dcache.h

@@ -223,6 +223,8 @@ struct dentry_operations {
 
 #define DCACHE_MAY_FREE			0x00800000
 
+#define DCACHE_ENCRYPTED_WITH_KEY	0x04000000 /* dir is encrypted with a valid key */
+
 extern seqlock_t rename_lock;
 
 /*
@@ -468,4 +470,61 @@ static inline unsigned long vfs_pressure_ratio(unsigned long val)
 {
 	return mult_frac(val, sysctl_vfs_cache_pressure, 100);
 }
+
+/**
+ * d_inode - Get the actual inode of this dentry
+ * @dentry: The dentry to query
+ *
+ * This is the helper normal filesystems should use to get at their own inodes
+ * in their own dentries and ignore the layering superimposed upon them.
+ */
+static inline struct inode *d_inode(const struct dentry *dentry)
+{
+	return dentry->d_inode;
+}
+
+/**
+ * d_inode_rcu - Get the actual inode of this dentry with ACCESS_ONCE()
+ * @dentry: The dentry to query
+ *
+ * This is the helper normal filesystems should use to get at their own inodes
+ * in their own dentries and ignore the layering superimposed upon them.
+ */
+static inline struct inode *d_inode_rcu(const struct dentry *dentry)
+{
+	return ACCESS_ONCE(dentry->d_inode);
+}
+
+/**
+ * d_backing_inode - Get upper or lower inode we should be using
+ * @upper: The upper layer
+ *
+ * This is the helper that should be used to get at the inode that will be used
+ * if this dentry were to be opened as a file.  The inode may be on the upper
+ * dentry or it may be on a lower dentry pinned by the upper.
+ *
+ * Normal filesystems should not use this to access their own inodes.
+ */
+static inline struct inode *d_backing_inode(const struct dentry *upper)
+{
+	struct inode *inode = upper->d_inode;
+
+	return inode;
+}
+
+/**
+ * d_backing_dentry - Get upper or lower dentry we should be using
+ * @upper: The upper layer
+ *
+ * This is the helper that should be used to get the dentry of the inode that
+ * will be used if this dentry were opened as a file.  It may be the upper
+ * dentry or it may be a lower dentry pinned by the upper.
+ *
+ * Normal filesystems should not use this to access their own dentries.
+ */
+static inline struct dentry *d_backing_dentry(struct dentry *upper)
+{
+	return upper;
+}
+
 #endif	/* __LINUX_DCACHE_H */

include/linux/f2fs_fs.h

@@ -19,12 +19,16 @@
 #define F2FS_MAX_LOG_SECTOR_SIZE	12	/* 12 bits for 4096 bytes */
 #define F2FS_LOG_SECTORS_PER_BLOCK	3	/* log number for sector/blk */
 #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 */
 
+#define F2FS_BYTES_TO_BLK(bytes)	((bytes) >> F2FS_BLKSIZE_BITS)
+#define F2FS_BLK_TO_BYTES(blk)		((blk) << F2FS_BLKSIZE_BITS)
+
 /* 0, 1(node nid), 2(meta nid) are reserved node id */
 #define F2FS_RESERVED_NODE_NUM		3
 
@@ -33,7 +37,8 @@
 #define F2FS_META_INO(sbi)	(sbi->meta_ino_num)
 
 /* This flag is used by node and meta inodes, and by recovery */
-#define GFP_F2FS_ZERO	(GFP_NOFS | __GFP_ZERO)
+#define GFP_F2FS_ZERO		(GFP_NOFS | __GFP_ZERO)
+#define GFP_F2FS_HIGH_ZERO	(GFP_NOFS | __GFP_ZERO | __GFP_HIGHMEM)
 
 /*
  * For further optimization on multi-head logs, on-disk layout supports maximum
@@ -45,6 +50,9 @@
 #define MAX_ACTIVE_NODE_LOGS	8
 #define MAX_ACTIVE_DATA_LOGS	8
 
+#define VERSION_LEN	256
+#define MAX_VOLUME_NAME		512
+
 /*
  * For superblock
  */
@@ -77,15 +85,22 @@ 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;
+	__u8 version[VERSION_LEN];	/* the kernel version */
+	__u8 init_version[VERSION_LEN];	/* the initial kernel version */
+	__le32 feature;			/* defined features */
+	__u8 encryption_level;		/* versioning level for encryption */
+	__u8 encrypt_pw_salt[16];	/* Salt used for string2key algorithm */
+	__u8 reserved[871];		/* valid reserved region */
 } __packed;
 
 /*
  * For checkpoint
  */
+#define CP_FASTBOOT_FLAG	0x00000020
 #define CP_FSCK_FLAG		0x00000010
 #define CP_ERROR_FLAG		0x00000008
 #define CP_COMPACT_SUM_FLAG	0x00000004
@@ -147,7 +162,7 @@ struct f2fs_orphan_block {
  */
 struct f2fs_extent {
 	__le32 fofs;		/* start file offset of the extent */
-	__le32 blk_addr;	/* start block address of the extent */
+	__le32 blk;		/* start block address of the extent */
 	__le32 len;		/* lengh of the extent */
 } __packed;
 
@@ -155,12 +170,12 @@ struct f2fs_extent {
 #define F2FS_INLINE_XATTR_ADDRS	50	/* 200 bytes for inline xattrs */
 #define DEF_ADDRS_PER_INODE	923	/* Address Pointers in an Inode */
 #define DEF_NIDS_PER_INODE	5	/* Node IDs in an Inode */
-#define ADDRS_PER_INODE(fi)	addrs_per_inode(fi)
+#define ADDRS_PER_INODE(inode)	addrs_per_inode(inode)
 #define ADDRS_PER_BLOCK		1018	/* Address Pointers in a Direct Block */
 #define NIDS_PER_BLOCK		1018	/* Node IDs in an Indirect Block */
 
-#define ADDRS_PER_PAGE(page, fi)	\
-	(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)
@@ -170,14 +185,13 @@ struct f2fs_extent {
 
 #define F2FS_INLINE_XATTR	0x01	/* file inline xattr flag */
 #define F2FS_INLINE_DATA	0x02	/* file inline data flag */
+#define F2FS_INLINE_DENTRY	0x04	/* file inline dentry flag */
+#define F2FS_DATA_EXIST		0x08	/* file inline data exist flag */
+#define F2FS_INLINE_DOTS	0x10	/* file having implicit dot dentries */
 
 #define MAX_INLINE_DATA		(sizeof(__le32) * (DEF_ADDRS_PER_INODE - \
 						F2FS_INLINE_XATTR_ADDRS - 1))
 
-#define INLINE_DATA_OFFSET	(PAGE_CACHE_SIZE - sizeof(struct node_footer) -\
-				sizeof(__le32) * (DEF_ADDRS_PER_INODE + \
-				DEF_NIDS_PER_INODE - 1))
-
 struct f2fs_inode {
 	__le16 i_mode;			/* file mode */
 	__u8 i_advise;			/* file hints */
@@ -225,6 +239,8 @@ enum {
 	OFFSET_BIT_SHIFT
 };
 
+#define OFFSET_BIT_MASK		(0x07)	/* (0x01 << OFFSET_BIT_SHIFT) - 1 */
+
 struct node_footer {
 	__le32 nid;		/* node id */
 	__le32 ino;		/* inode nunmber */
@@ -329,7 +345,7 @@ struct f2fs_summary {
 
 struct summary_footer {
 	unsigned char entry_type;	/* SUM_TYPE_XXX */
-	__u32 check_sum;		/* summary checksum */
+	__le32 check_sum;		/* summary checksum */
 } __packed;
 
 #define SUM_JOURNAL_SIZE	(F2FS_BLKSIZE - SUM_FOOTER_SIZE -\
@@ -342,6 +358,12 @@ struct summary_footer {
 				sizeof(struct sit_journal_entry))
 #define SIT_JOURNAL_RESERVED	((SUM_JOURNAL_SIZE - 2) %\
 				sizeof(struct sit_journal_entry))
+
+/* Reserved area should make size of f2fs_extra_info equals to
+ * that of nat_journal and sit_journal.
+ */
+#define EXTRA_INFO_RESERVED	(SUM_JOURNAL_SIZE - 2 - 8)
+
 /*
  * frequently updated NAT/SIT entries can be stored in the spare area in
  * summary blocks
@@ -371,18 +393,28 @@ 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;
 
@@ -402,15 +434,25 @@ typedef __le32	f2fs_hash_t;
 
 #define GET_DENTRY_SLOTS(x)	((x + F2FS_SLOT_LEN - 1) >> F2FS_SLOT_LEN_BITS)
 
-/* the number of dentry in a block */
-#define NR_DENTRY_IN_BLOCK	214
-
 /* MAX level for dir lookup */
 #define MAX_DIR_HASH_DEPTH	63
 
 /* MAX buckets in one level of dir */
 #define MAX_DIR_BUCKETS		(1 << ((MAX_DIR_HASH_DEPTH / 2) - 1))
 
+/*
+ * space utilization of regular dentry and inline dentry
+ *		regular dentry			inline dentry
+ * bitmap	1 * 27 = 27			1 * 23 = 23
+ * reserved	1 * 3 = 3			1 * 7 = 7
+ * dentry	11 * 214 = 2354			11 * 182 = 2002
+ * filename	8 * 214 = 1712			8 * 182 = 1456
+ * total	4096				3488
+ *
+ * Note: there are more reserved space in inline dentry than in regular
+ * dentry, when converting inline dentry we should handle this carefully.
+ */
+#define NR_DENTRY_IN_BLOCK	214	/* the number of dentry in a block */
 #define SIZE_OF_DIR_ENTRY	11	/* by byte */
 #define SIZE_OF_DENTRY_BITMAP	((NR_DENTRY_IN_BLOCK + BITS_PER_BYTE - 1) / \
 					BITS_PER_BYTE)
@@ -435,6 +477,24 @@ struct f2fs_dentry_block {
 	__u8 filename[NR_DENTRY_IN_BLOCK][F2FS_SLOT_LEN];
 } __packed;
 
+/* for inline dir */
+#define NR_INLINE_DENTRY	(MAX_INLINE_DATA * BITS_PER_BYTE / \
+				((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \
+				BITS_PER_BYTE + 1))
+#define INLINE_DENTRY_BITMAP_SIZE	((NR_INLINE_DENTRY + \
+					BITS_PER_BYTE - 1) / BITS_PER_BYTE)
+#define INLINE_RESERVED_SIZE	(MAX_INLINE_DATA - \
+				((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \
+				NR_INLINE_DENTRY + INLINE_DENTRY_BITMAP_SIZE))
+
+/* inline directory entry structure */
+struct f2fs_inline_dentry {
+	__u8 dentry_bitmap[INLINE_DENTRY_BITMAP_SIZE];
+	__u8 reserved[INLINE_RESERVED_SIZE];
+	struct f2fs_dir_entry dentry[NR_INLINE_DENTRY];
+	__u8 filename[NR_INLINE_DENTRY][F2FS_SLOT_LEN];
+} __packed;
+
 /* file types used in inode_info->flags */
 enum {
 	F2FS_FT_UNKNOWN,
@@ -448,4 +508,6 @@ enum {
 	F2FS_FT_MAX
 };
 
+#define S_SHIFT 12
+
 #endif  /* _LINUX_F2FS_FS_H */

include/linux/fs.h

@@ -49,6 +49,8 @@ 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);
@@ -641,6 +643,10 @@ struct inode {
 	struct hlist_head	i_fsnotify_marks;
 #endif
 
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+	struct fscrypt_info	*i_crypt_info;
+#endif
+
 	void			*i_private; /* fs or device private pointer */
 };
 
@@ -1236,6 +1242,9 @@ struct super_block {
 	const struct xattr_handler **s_xattr;
 
 	struct list_head	s_inodes;	/* all inodes */
+
+	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 <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_ablkcipher *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 inode *,
+					const struct fscrypt_policy *);
+extern int fscrypt_get_policy(struct inode *, struct fscrypt_policy *);
+extern int fscrypt_has_permitted_context(struct inode *, struct inode *);
+extern int fscrypt_inherit_context(struct inode *, struct inode *,
+					void *, bool);
+/* keyinfo.c */
+extern int get_crypt_info(struct inode *);
+extern int fscrypt_get_encryption_info(struct inode *);
+extern void fscrypt_put_encryption_info(struct inode *, struct fscrypt_info *);
+
+/* fname.c */
+extern int fscrypt_setup_filename(struct inode *, const struct qstr *,
+				int lookup, struct fscrypt_name *);
+extern void fscrypt_free_filename(struct fscrypt_name *);
+extern u32 fscrypt_fname_encrypted_size(struct inode *, u32);
+extern int fscrypt_fname_alloc_buffer(struct inode *, u32,
+				struct fscrypt_str *);
+extern void fscrypt_fname_free_buffer(struct fscrypt_str *);
+extern int fscrypt_fname_disk_to_usr(struct inode *, u32, u32,
+			const struct fscrypt_str *, struct fscrypt_str *);
+extern int fscrypt_fname_usr_to_disk(struct inode *, const struct qstr *,
+			struct fscrypt_str *);
+#endif
+
+/* crypto.c */
+static inline struct fscrypt_ctx *fscrypt_notsupp_get_ctx(struct inode *i,
+							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 inode *i,
+				const struct fscrypt_policy *p)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int fscrypt_notsupp_get_policy(struct inode *i,
+				struct fscrypt_policy *p)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int fscrypt_notsupp_has_permitted_context(struct inode *p,
+				struct inode *i)
+{
+	return 0;
+}
+
+static inline int fscrypt_notsupp_inherit_context(struct inode *p,
+				struct inode *i, void *v, bool b)
+{
+	return -EOPNOTSUPP;
+}
+
+/* keyinfo.c */
+static inline int fscrypt_notsupp_get_encryption_info(struct inode *i)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void fscrypt_notsupp_put_encryption_info(struct inode *i,
+					struct fscrypt_info *f)
+{
+	return;
+}
+
+ /* fname.c */
+static inline int fscrypt_notsupp_setup_filename(struct inode *dir,
+			const struct qstr *iname,
+			int lookup, struct fscrypt_name *fname)
+{
+	if (dir->i_sb->s_cop->is_encrypted(dir))
+		return -EOPNOTSUPP;
+
+	memset(fname, 0, sizeof(struct fscrypt_name));
+	fname->usr_fname = iname;
+	fname->disk_name.name = (unsigned char *)iname->name;
+	fname->disk_name.len = iname->len;
+	return 0;
+}
+
+static inline void fscrypt_notsupp_free_filename(struct fscrypt_name *fname)
+{
+	return;
+}
+
+static inline u32 fscrypt_notsupp_fname_encrypted_size(struct inode *i, u32 s)
+{
+	/* never happens */
+	WARN_ON(1);
+	return 0;
+}
+
+static inline int fscrypt_notsupp_fname_alloc_buffer(struct inode *inode,
+				u32 ilen, struct fscrypt_str *crypto_str)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void fscrypt_notsupp_fname_free_buffer(struct fscrypt_str *c)
+{
+	return;
+}
+
+static inline int fscrypt_notsupp_fname_disk_to_usr(struct inode *inode,
+			u32 hash, u32 minor_hash,
+			const struct fscrypt_str *iname,
+			struct fscrypt_str *oname)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int fscrypt_notsupp_fname_usr_to_disk(struct inode *inode,
+			const struct qstr *iname,
+			struct fscrypt_str *oname)
+{
+	return -EOPNOTSUPP;
+}
+#endif	/* _LINUX_FSCRYPTO_H */

include/trace/events/f2fs.h

@@ -14,7 +14,12 @@
 		{ NODE,		"NODE" },				\
 		{ DATA,		"DATA" },				\
 		{ META,		"META" },				\
-		{ META_FLUSH,	"META_FLUSH" })
+		{ META_FLUSH,	"META_FLUSH" },				\
+		{ INMEM,	"INMEM" },				\
+		{ INMEM_DROP,	"INMEM_DROP" },				\
+		{ INMEM_REVOKE,	"INMEM_REVOKE" },			\
+		{ IPU,		"IN-PLACE" },				\
+		{ OPU,		"OUT-OF-PLACE" })
 
 #define F2FS_BIO_MASK(t)	(t & (READA | WRITE_FLUSH_FUA))
 #define F2FS_BIO_EXTRA_MASK(t)	(t & (REQ_META | REQ_PRIO))
@@ -72,10 +77,13 @@
 #define show_cpreason(type)						\
 	__print_symbolic(type,						\
 		{ CP_UMOUNT,	"Umount" },				\
+		{ CP_FASTBOOT,	"Fastboot" },				\
 		{ CP_SYNC,	"Sync" },				\
+		{ CP_RECOVERY,	"Recovery" },				\
 		{ CP_DISCARD,	"Discard" })
 
 struct victim_sel_policy;
+struct f2fs_map_blocks;
 
 DECLARE_EVENT_CLASS(f2fs__inode,
 
@@ -148,14 +156,14 @@ DEFINE_EVENT(f2fs__inode, f2fs_sync_file_enter,
 
 TRACE_EVENT(f2fs_sync_file_exit,
 
-	TP_PROTO(struct inode *inode, bool need_cp, int datasync, int ret),
+	TP_PROTO(struct inode *inode, int need_cp, int datasync, int ret),
 
 	TP_ARGS(inode, need_cp, datasync, ret),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(ino_t,	ino)
-		__field(bool,	need_cp)
+		__field(int,	need_cp)
 		__field(int,	datasync)
 		__field(int,	ret)
 	),
@@ -190,7 +198,7 @@ TRACE_EVENT(f2fs_sync_fs,
 
 	TP_fast_assign(
 		__entry->dev	= sb->s_dev;
-		__entry->dirty	= F2FS_SB(sb)->s_dirty;
+		__entry->dirty	= is_sbi_flag_set(F2FS_SB(sb), SBI_IS_DIRTY);
 		__entry->wait	= wait;
 	),
 
@@ -440,71 +448,66 @@ TRACE_EVENT(f2fs_truncate_partial_nodes,
 		__entry->err)
 );
 
-TRACE_EVENT_CONDITION(f2fs_submit_page_bio,
+TRACE_EVENT(f2fs_map_blocks,
+	TP_PROTO(struct inode *inode, struct f2fs_map_blocks *map, int ret),
 
-	TP_PROTO(struct page *page, sector_t blkaddr, int type),
-
-	TP_ARGS(page, blkaddr, type),
-
-	TP_CONDITION(page->mapping),
+	TP_ARGS(inode, map, ret),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(ino_t,	ino)
-		__field(pgoff_t,	index)
-		__field(sector_t,	blkaddr)
-		__field(int,	type)
-	),
-
-	TP_fast_assign(
-		__entry->dev		= page->mapping->host->i_sb->s_dev;
-		__entry->ino		= page->mapping->host->i_ino;
-		__entry->index		= page->index;
-		__entry->blkaddr	= blkaddr;
-		__entry->type		= type;
-	),
-
-	TP_printk("dev = (%d,%d), ino = %lu, page_index = 0x%lx, "
-		"blkaddr = 0x%llx, bio_type = %s%s",
-		show_dev_ino(__entry),
-		(unsigned long)__entry->index,
-		(unsigned long long)__entry->blkaddr,
-		show_bio_type(__entry->type))
-);
-
-TRACE_EVENT(f2fs_get_data_block,
-	TP_PROTO(struct inode *inode, sector_t iblock,
-				struct buffer_head *bh, int ret),
-
-	TP_ARGS(inode, iblock, bh, ret),
-
-	TP_STRUCT__entry(
-		__field(dev_t,	dev)
-		__field(ino_t,	ino)
-		__field(sector_t,	iblock)
-		__field(sector_t,	bh_start)
-		__field(size_t,	bh_size)
+		__field(block_t,	m_lblk)
+		__field(block_t,	m_pblk)
+		__field(unsigned int,	m_len)
 		__field(int,	ret)
 	),
 
 	TP_fast_assign(
 		__entry->dev		= inode->i_sb->s_dev;
 		__entry->ino		= inode->i_ino;
-		__entry->iblock		= iblock;
-		__entry->bh_start	= bh->b_blocknr;
-		__entry->bh_size	= bh->b_size;
+		__entry->m_lblk		= map->m_lblk;
+		__entry->m_pblk		= map->m_pblk;
+		__entry->m_len		= map->m_len;
 		__entry->ret		= ret;
 	),
 
 	TP_printk("dev = (%d,%d), ino = %lu, file offset = %llu, "
-		"start blkaddr = 0x%llx, len = 0x%llx bytes, err = %d",
+		"start blkaddr = 0x%llx, len = 0x%llx, err = %d",
 		show_dev_ino(__entry),
-		(unsigned long long)__entry->iblock,
-		(unsigned long long)__entry->bh_start,
-		(unsigned long long)__entry->bh_size,
+		(unsigned long long)__entry->m_lblk,
+		(unsigned long long)__entry->m_pblk,
+		(unsigned long long)__entry->m_len,
 		__entry->ret)
 );
 
+TRACE_EVENT(f2fs_background_gc,
+
+	TP_PROTO(struct super_block *sb, long wait_ms,
+			unsigned int prefree, unsigned int free),
+
+	TP_ARGS(sb, wait_ms, prefree, free),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(long,	wait_ms)
+		__field(unsigned int,	prefree)
+		__field(unsigned int,	free)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= sb->s_dev;
+		__entry->wait_ms	= wait_ms;
+		__entry->prefree	= prefree;
+		__entry->free		= free;
+	),
+
+	TP_printk("dev = (%d,%d), wait_ms = %ld, prefree = %u, free = %u",
+		show_dev(__entry),
+		__entry->wait_ms,
+		__entry->prefree,
+		__entry->free)
+);
+
 TRACE_EVENT(f2fs_get_victim,
 
 	TP_PROTO(struct super_block *sb, int type, int gc_type,
@@ -656,35 +659,94 @@ 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,
+
+	TP_PROTO(struct page *page, struct f2fs_io_info *fio),
+
+	TP_ARGS(page, fio),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(ino_t, ino)
+		__field(pgoff_t, index)
+		__field(block_t, old_blkaddr)
+		__field(block_t, new_blkaddr)
+		__field(int, rw)
+		__field(int, type)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= page->mapping->host->i_sb->s_dev;
+		__entry->ino		= page->mapping->host->i_ino;
+		__entry->index		= page->index;
+		__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, "
+		"oldaddr = 0x%llx, newaddr = 0x%llx rw = %s%s, type = %s",
+		show_dev_ino(__entry),
+		(unsigned long)__entry->index,
+		(unsigned long long)__entry->old_blkaddr,
+		(unsigned long long)__entry->new_blkaddr,
+		show_bio_type(__entry->rw),
+		show_block_type(__entry->type))
+);
+
+DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_bio,
+
+	TP_PROTO(struct page *page, struct f2fs_io_info *fio),
+
+	TP_ARGS(page, fio),
+
+	TP_CONDITION(page->mapping)
+);
+
+DEFINE_EVENT_CONDITION(f2fs__submit_page_bio, f2fs_submit_page_mbio,
+
+	TP_PROTO(struct page *page, struct f2fs_io_info *fio),
+
+	TP_ARGS(page, fio),
+
+	TP_CONDITION(page->mapping)
 );
 
 DECLARE_EVENT_CLASS(f2fs__submit_bio,
 
-	TP_PROTO(struct super_block *sb, int rw, int type, struct bio *bio),
+	TP_PROTO(struct super_block *sb, struct f2fs_io_info *fio,
+						struct bio *bio),
 
-	TP_ARGS(sb, rw, type, bio),
+	TP_ARGS(sb, fio, bio),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
@@ -696,8 +758,8 @@ DECLARE_EVENT_CLASS(f2fs__submit_bio,
 
 	TP_fast_assign(
 		__entry->dev		= sb->s_dev;
-		__entry->rw		= rw;
-		__entry->type		= type;
+		__entry->rw		= fio->rw;
+		__entry->type		= fio->type;
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->size		= bio->bi_iter.bi_size;
 	),
@@ -712,18 +774,20 @@ DECLARE_EVENT_CLASS(f2fs__submit_bio,
 
 DEFINE_EVENT_CONDITION(f2fs__submit_bio, f2fs_submit_write_bio,
 
-	TP_PROTO(struct super_block *sb, int rw, int type, struct bio *bio),
+	TP_PROTO(struct super_block *sb, struct f2fs_io_info *fio,
+							struct bio *bio),
 
-	TP_ARGS(sb, rw, type, bio),
+	TP_ARGS(sb, fio, bio),
 
 	TP_CONDITION(bio)
 );
 
 DEFINE_EVENT_CONDITION(f2fs__submit_bio, f2fs_submit_read_bio,
 
-	TP_PROTO(struct super_block *sb, int rw, int type, struct bio *bio),
+	TP_PROTO(struct super_block *sb, struct f2fs_io_info *fio,
+							struct bio *bio),
 
-	TP_ARGS(sb, rw, type, bio),
+	TP_ARGS(sb, fio, bio),
 
 	TP_CONDITION(bio)
 );
@@ -831,6 +895,13 @@ DEFINE_EVENT(f2fs__page, f2fs_writepage,
 	TP_ARGS(page, type)
 );
 
+DEFINE_EVENT(f2fs__page, f2fs_do_write_data_page,
+
+	TP_PROTO(struct page *page, int type),
+
+	TP_ARGS(page, type)
+);
+
 DEFINE_EVENT(f2fs__page, f2fs_readpage,
 
 	TP_PROTO(struct page *page, int type),
@@ -852,6 +923,20 @@ DEFINE_EVENT(f2fs__page, f2fs_vm_page_mkwrite,
 	TP_ARGS(page, type)
 );
 
+DEFINE_EVENT(f2fs__page, f2fs_register_inmem_page,
+
+	TP_PROTO(struct page *page, int type),
+
+	TP_ARGS(page, type)
+);
+
+DEFINE_EVENT(f2fs__page, f2fs_commit_inmem_page,
+
+	TP_PROTO(struct page *page, int type),
+
+	TP_ARGS(page, type)
+);
+
 TRACE_EVENT(f2fs_writepages,
 
 	TP_PROTO(struct inode *inode, struct writeback_control *wbc, int type),
@@ -916,36 +1001,30 @@ TRACE_EVENT(f2fs_writepages,
 		__entry->for_sync)
 );
 
-TRACE_EVENT(f2fs_submit_page_mbio,
+TRACE_EVENT(f2fs_readpages,
 
-	TP_PROTO(struct page *page, int rw, int type, block_t blk_addr),
+	TP_PROTO(struct inode *inode, struct page *page, unsigned int nrpage),
 
-	TP_ARGS(page, rw, type, blk_addr),
+	TP_ARGS(inode, page, nrpage),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(ino_t,	ino)
-		__field(int, rw)
-		__field(int, type)
-		__field(pgoff_t, index)
-		__field(block_t, block)
+		__field(pgoff_t,	start)
+		__field(unsigned int,	nrpage)
 	),
 
 	TP_fast_assign(
-		__entry->dev	= page->mapping->host->i_sb->s_dev;
-		__entry->ino	= page->mapping->host->i_ino;
-		__entry->rw	= rw;
-		__entry->type	= type;
-		__entry->index	= page->index;
-		__entry->block	= blk_addr;
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->start	= page->index;
+		__entry->nrpage	= nrpage;
 	),
 
-	TP_printk("dev = (%d,%d), ino = %lu, %s%s, %s, index = %lu, blkaddr = 0x%llx",
+	TP_printk("dev = (%d,%d), ino = %lu, start = %lu nrpage = %u",
 		show_dev_ino(__entry),
-		show_bio_type(__entry->rw),
-		show_block_type(__entry->type),
-		(unsigned long)__entry->index,
-		(unsigned long long)__entry->block)
+		(unsigned long)__entry->start,
+		__entry->nrpage)
 );
 
 TRACE_EVENT(f2fs_write_checkpoint,
@@ -998,14 +1077,15 @@ TRACE_EVENT(f2fs_issue_discard,
 
 TRACE_EVENT(f2fs_issue_flush,
 
-	TP_PROTO(struct super_block *sb, bool nobarrier, bool flush_merge),
+	TP_PROTO(struct super_block *sb, unsigned int nobarrier,
+					unsigned int flush_merge),
 
 	TP_ARGS(sb, nobarrier, flush_merge),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
-		__field(bool, nobarrier)
-		__field(bool, flush_merge)
+		__field(unsigned int, nobarrier)
+		__field(unsigned int, flush_merge)
 	),
 
 	TP_fast_assign(
@@ -1019,6 +1099,183 @@ TRACE_EVENT(f2fs_issue_flush,
 		__entry->nobarrier ? "skip (nobarrier)" : "issue",
 		__entry->flush_merge ? " with flush_merge" : "")
 );
+
+TRACE_EVENT(f2fs_lookup_extent_tree_start,
+
+	TP_PROTO(struct inode *inode, unsigned int pgofs),
+
+	TP_ARGS(inode, pgofs),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(unsigned int, pgofs)
+	),
+
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->pgofs = pgofs;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u",
+		show_dev_ino(__entry),
+		__entry->pgofs)
+);
+
+TRACE_EVENT_CONDITION(f2fs_lookup_extent_tree_end,
+
+	TP_PROTO(struct inode *inode, unsigned int pgofs,
+						struct extent_info *ei),
+
+	TP_ARGS(inode, pgofs, ei),
+
+	TP_CONDITION(ei),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(unsigned int, pgofs)
+		__field(unsigned int, fofs)
+		__field(u32, blk)
+		__field(unsigned int, len)
+	),
+
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->pgofs = pgofs;
+		__entry->fofs = ei->fofs;
+		__entry->blk = ei->blk;
+		__entry->len = ei->len;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u, "
+		"ext_info(fofs: %u, blk: %u, len: %u)",
+		show_dev_ino(__entry),
+		__entry->pgofs,
+		__entry->fofs,
+		__entry->blk,
+		__entry->len)
+);
+
+TRACE_EVENT(f2fs_update_extent_tree_range,
+
+	TP_PROTO(struct inode *inode, unsigned int pgofs, block_t blkaddr,
+						unsigned int len),
+
+	TP_ARGS(inode, pgofs, blkaddr, len),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(unsigned int, pgofs)
+		__field(u32, blk)
+		__field(unsigned int, len)
+	),
+
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->pgofs = pgofs;
+		__entry->blk = blkaddr;
+		__entry->len = len;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u, "
+					"blkaddr = %u, len = %u",
+		show_dev_ino(__entry),
+		__entry->pgofs,
+		__entry->blk,
+		__entry->len)
+);
+
+TRACE_EVENT(f2fs_shrink_extent_tree,
+
+	TP_PROTO(struct f2fs_sb_info *sbi, unsigned int node_cnt,
+						unsigned int tree_cnt),
+
+	TP_ARGS(sbi, node_cnt, tree_cnt),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(unsigned int, node_cnt)
+		__field(unsigned int, tree_cnt)
+	),
+
+	TP_fast_assign(
+		__entry->dev = sbi->sb->s_dev;
+		__entry->node_cnt = node_cnt;
+		__entry->tree_cnt = tree_cnt;
+	),
+
+	TP_printk("dev = (%d,%d), shrunk: node_cnt = %u, tree_cnt = %u",
+		show_dev(__entry),
+		__entry->node_cnt,
+		__entry->tree_cnt)
+);
+
+TRACE_EVENT(f2fs_destroy_extent_tree,
+
+	TP_PROTO(struct inode *inode, unsigned int node_cnt),
+
+	TP_ARGS(inode, node_cnt),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(unsigned int, node_cnt)
+	),
+
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->node_cnt = node_cnt;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, destroyed: node_cnt = %u",
+		show_dev_ino(__entry),
+		__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_IOC_INVAL_MAPPING		_IO('f', 13)
 
+/*
+ * 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)
  */

mm/mmap.c

@@ -633,6 +633,7 @@ void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * immediately update the gap to the correct value. Finally we
 	 * rebalance the rbtree after all augmented values have been set.
 	 */
+	smp_mb();
 	rb_link_node(&vma->vm_rb, rb_parent, rb_link);
 	vma->rb_subtree_gap = 0;
 	vma_gap_update(vma);

net/netfilter/xt_qtaguid.c

@@ -1935,7 +1935,7 @@ static int qtaguid_ctrl_proc_show(struct seq_file *m, void *v)
 			);
 		f_count = atomic_long_read(
 			&sock_tag_entry->socket->file->f_count);
-		seq_printf(m, "sock=%p tag=0x%llx (uid=%u) pid=%u "
+		seq_printf(m, "sock=%pK tag=0x%llx (uid=%u) pid=%u "
 			   "f_count=%lu\n",
 			   sock_tag_entry->sk,
 			   sock_tag_entry->tag, uid,

scripts/fips_crypto_utils.c

@@ -13,83 +13,83 @@
 
 #include <stdio.h>
 #include <stdlib.h>
- 
-int main (int argc, char **argv)
+#include <string.h>
+
+#define SHA256_DIGEST_SIZE 32
+
+/*  
+ * Given a vmlinux file, overwrites bytes at given offset with hmac bytes, available in 
+ * hmac file.
+ * Return 0, if Success
+ *       -1, if Error
+ */
+int
+update_crypto_hmac (const char * vmlinux_path, const char * hmac_path, unsigned long offset)
 {
-	if (argc < 2)
+	FILE * vmlinux_fp = NULL;
+	FILE * hmac_fp = NULL;
+	int i = 0, j = 0;
+	unsigned char hmac[SHA256_DIGEST_SIZE];
+
+	if (!vmlinux_path || !hmac_path || !offset)
 	{
-		printf ("\nUsage : \n");
-		printf ("fips_crypto_utils -u vmlinux_file hmac_file offset");
-		printf ("fips_crypto_utils -g vmlinux_file section_name offset size out_file");
-		printf ("\n");
+		printf ("FIPS update_crypto_hmac : Invalid Params");
 		return -1;
 	}
 
-	if (!strcmp ("-u", argv[1]))
+	vmlinux_fp  = fopen (vmlinux_path, "r+b");
+	if (!vmlinux_fp)
 	{
-		unsigned long offset = 0;
-		unsigned char * vmlinux_file = NULL;
-		unsigned char * hmac_file    = NULL;
+		printf ("Unable to open vmlinux file ");
+		return -1;
+	}	
 
-		if (argc != 5)
-		{
-			printf ("\nUsage : \n");
-			printf ("fips_crypto_utils -u vmlinux_file hmac_file offset");
-			printf ("\n");
-			return -1;
-		}
-		
-		vmlinux_file = argv[2];
-		hmac_file    = argv[3];
-		offset       = atol(argv[4]);
-		
-		if (!vmlinux_file || !hmac_file || !offset)
-		{
-			printf ("./fips_crypto_utils -u vmlinux_file hmac_file offset");
-			return -1;
-		}
+	hmac_fp = fopen (hmac_path, "rb"); 
 
-		return update_crypto_hmac (vmlinux_file, hmac_file, offset);
-	}
-	else if (!strcmp ("-g", argv[1]))
+	if (!hmac_fp)
 	{
-		const char * in_file      = NULL;
-		const char * section_name = NULL;
-		unsigned long offset      = 0;
-		unsigned long size        = 0;
-		const char * out_file     = NULL;
+		printf ("Unable to open hmac file ");
+		fclose (vmlinux_fp);
+		return -1;
+	}	
 
-		if (argc != 7)
-		{
-			printf ("\nUsage : \n");
-			printf ("./fips_crypto_utils -g vmlinux_file section_name offset size out_file");
-			printf ("\n");
-			return -1;
-		}
-
-		in_file      = argv[2];
-		section_name = argv[3];
-		offset       = atol(argv[4]);
-		size         = atol(argv[5]);
-		out_file     = argv[6];
-
-		if (!in_file || !section_name || !offset || !size || !out_file)
-		{
-			printf ("./fips_crypto_utils -g vmlinux_file section_name offset size out_file");
-			return -1;
-		}
-
-		return collect_crypto_bytes (in_file, section_name, offset, size, out_file);
-	}
-	else
+	if (SHA256_DIGEST_SIZE != fread (&hmac, sizeof(unsigned char), SHA256_DIGEST_SIZE, hmac_fp)) 
 	{
-		printf ("\nUsage : \n");
-		printf ("fips_crypto_utils -u vmlinux_file hmac_file offset");
-		printf ("fips_crypto_utils -g vmlinux_file section_name offset size out_file");
-		printf ("\n");
+		printf ("Unable to read %d bytes from hmac file", SHA256_DIGEST_SIZE);
+		fclose (hmac_fp);
+		fclose (vmlinux_fp);
+		return -1;
 	}
 
-	return -1;
+#if 0
+	printf ("Hash : ");
+	for (i = 0; i < sizeof(hmac); i++)
+		printf ("%02x ", hmac[i]);
+	printf ("\n");
+
+	printf ("Offset : %ld", offset);
+#endif
+
+	if (fseek (vmlinux_fp, offset, SEEK_SET) != 0 )
+	{
+		printf ("Unable to seek into vmlinux file.");
+		fclose (hmac_fp);
+		fclose (vmlinux_fp);
+		return -1;
+	}
+
+	if (SHA256_DIGEST_SIZE !=  fwrite (hmac, sizeof(unsigned char), SHA256_DIGEST_SIZE, vmlinux_fp))
+	{
+		printf ("Unable to write %d byte into vmlinux", SHA256_DIGEST_SIZE);
+		fclose (hmac_fp);
+		fclose (vmlinux_fp);
+		return -1;
+	}
+
+	fclose (vmlinux_fp);
+	fclose (hmac_fp);
+
+	return 0;
 }
 
 /*
@@ -175,80 +175,85 @@ collect_crypto_bytes (const char * in_file, const char * section_name, unsigned
 	return 0;
 }
 
-
-#define SHA256_DIGEST_SIZE 32
-
-/*  
- * Given a vmlinux file, overwrites bytes at given offset with hmac bytes, available in 
- * hmac file.
- * Return 0, if Success
- *       -1, if Error
- */
-int
-update_crypto_hmac (const char * vmlinux_path, const char * hmac_path, unsigned long offset)
+int main (int argc, char **argv)
 {
-	FILE * vmlinux_fp = NULL;
-	FILE * hmac_fp = NULL;
-	int i = 0, j = 0;
-	unsigned char hmac[SHA256_DIGEST_SIZE];
-
-	if (!vmlinux_path || !hmac_path || !offset)
+	if (argc < 2)
 	{
-		printf ("FIPS update_crypto_hmac : Invalid Params");
+		printf ("\nUsage : \n");
+		printf ("fips_crypto_utils -u vmlinux_file hmac_file offset");
+		printf ("fips_crypto_utils -g vmlinux_file section_name offset size out_file");
+		printf ("\n");
 		return -1;
 	}
 
-	vmlinux_fp  = fopen (vmlinux_path, "r+b");
-	if (!vmlinux_fp)
+	if (!strcmp ("-u", argv[1]))
 	{
-		printf ("Unable to open vmlinux file ");
-		return -1;
-	}	
+		unsigned long offset = 0;
+		unsigned char * vmlinux_file = NULL;
+		unsigned char * hmac_file    = NULL;
 
-	hmac_fp = fopen (hmac_path, "rb"); 
+		if (argc != 5)
+		{
+			printf ("\nUsage : \n");
+			printf ("fips_crypto_utils -u vmlinux_file hmac_file offset");
+			printf ("\n");
+			return -1;
+		}
+		
+		vmlinux_file = argv[2];
+		hmac_file    = argv[3];
+		offset       = atol(argv[4]);
+		
+		if (!vmlinux_file || !hmac_file || !offset)
+		{
+			printf ("./fips_crypto_utils -u vmlinux_file hmac_file offset");
+			return -1;
+		}
 
-	if (!hmac_fp)
+		return update_crypto_hmac (vmlinux_file, hmac_file, offset);
+	}
+	else if (!strcmp ("-g", argv[1]))
 	{
-		printf ("Unable to open hmac file ");
-		fclose (vmlinux_fp);
-		return -1;
-	}	
+		const char * in_file      = NULL;
+		const char * section_name = NULL;
+		unsigned long offset      = 0;
+		unsigned long size        = 0;
+		const char * out_file     = NULL;
 
-	if (SHA256_DIGEST_SIZE != fread (&hmac, sizeof(unsigned char), SHA256_DIGEST_SIZE, hmac_fp)) 
+		if (argc != 7)
+		{
+			printf ("\nUsage : \n");
+			printf ("./fips_crypto_utils -g vmlinux_file section_name offset size out_file");
+			printf ("\n");
+			return -1;
+		}
+
+		in_file      = argv[2];
+		section_name = argv[3];
+		offset       = atol(argv[4]);
+		size         = atol(argv[5]);
+		out_file     = argv[6];
+
+		if (!in_file || !section_name || !offset || !size || !out_file)
+		{
+			printf ("./fips_crypto_utils -g vmlinux_file section_name offset size out_file");
+			return -1;
+		}
+
+		return collect_crypto_bytes (in_file, section_name, offset, size, out_file);
+	}
+	else
 	{
-		printf ("Unable to read %d bytes from hmac file", SHA256_DIGEST_SIZE);
-		fclose (hmac_fp);
-		fclose (vmlinux_fp);
-		return -1;
+		printf ("\nUsage : \n");
+		printf ("fips_crypto_utils -u vmlinux_file hmac_file offset");
+		printf ("fips_crypto_utils -g vmlinux_file section_name offset size out_file");
+		printf ("\n");
 	}
 
-#if 0
-	printf ("Hash : ");
-	for (i = 0; i < sizeof(hmac); i++)
-		printf ("%02x ", hmac[i]);
-	printf ("\n");
+	return -1;
+}
 
-	printf ("Offset : %ld", offset);
-#endif
 
-	if (fseek (vmlinux_fp, offset, SEEK_SET) != 0 )
-	{
-		printf ("Unable to seek into vmlinux file.");
-		fclose (hmac_fp);
-		fclose (vmlinux_fp);
-		return -1;
-	}
 
-	if (SHA256_DIGEST_SIZE !=  fwrite (hmac, sizeof(unsigned char), SHA256_DIGEST_SIZE, vmlinux_fp))
-	{
-		printf ("Unable to write %d byte into vmlinux", SHA256_DIGEST_SIZE);
-		fclose (hmac_fp);
-		fclose (vmlinux_fp);
-		return -1;
-	}
 
-	fclose (vmlinux_fp);
-	fclose (hmac_fp);
 
-	return 0;
-}

security/selinux/hooks.c

@@ -512,6 +512,7 @@ static int selinux_is_sblabel_mnt(struct super_block *sb)
 		!strcmp(sb->s_type->name, "sysfs") ||
 		!strcmp(sb->s_type->name, "pstore") ||
 		!strcmp(sb->s_type->name, "debugfs") ||
+		!strcmp(sb->s_type->name, "f2fs") ||
 		!strcmp(sb->s_type->name, "rootfs");
 }
 

sound/core/timer.c

@@ -215,11 +215,13 @@ static void snd_timer_check_master(struct snd_timer_instance *master)
 		    slave->slave_id == master->slave_id) {
 			list_move_tail(&slave->open_list, &master->slave_list_head);
 			spin_lock_irq(&slave_active_lock);
+			spin_lock(&master->timer->lock);
 			slave->master = master;
 			slave->timer = master->timer;
 			if (slave->flags & SNDRV_TIMER_IFLG_RUNNING)
 				list_add_tail(&slave->active_list,
 					      &master->slave_active_head);
+			spin_unlock(&master->timer->lock);
 			spin_unlock_irq(&slave_active_lock);
 		}
 	}
@@ -346,15 +348,18 @@ int snd_timer_close(struct snd_timer_instance *timeri)
 		    timer->hw.close)
 			timer->hw.close(timer);
 		/* remove slave links */
+		spin_lock_irq(&slave_active_lock);
+		spin_lock(&timer->lock);
 		list_for_each_entry_safe(slave, tmp, &timeri->slave_list_head,
 					 open_list) {
-			spin_lock_irq(&slave_active_lock);
-			_snd_timer_stop(slave, 1, SNDRV_TIMER_EVENT_RESOLUTION);
 			list_move_tail(&slave->open_list, &snd_timer_slave_list);
 			slave->master = NULL;
 			slave->timer = NULL;
-			spin_unlock_irq(&slave_active_lock);
+			list_del_init(&slave->ack_list);
+			list_del_init(&slave->active_list);
 		}
+		spin_unlock(&timer->lock);
+		spin_unlock_irq(&slave_active_lock);
 		mutex_unlock(&register_mutex);
 	}
  out:
@@ -441,9 +446,12 @@ static int snd_timer_start_slave(struct snd_timer_instance *timeri)
 
 	spin_lock_irqsave(&slave_active_lock, flags);
 	timeri->flags |= SNDRV_TIMER_IFLG_RUNNING;
-	if (timeri->master)
+	if (timeri->master && timeri->timer) {
+		spin_lock(&timeri->timer->lock);
 		list_add_tail(&timeri->active_list,
 			      &timeri->master->slave_active_head);
+		spin_unlock(&timeri->timer->lock);
+	}
 	spin_unlock_irqrestore(&slave_active_lock, flags);
 	return 1; /* delayed start */
 }
@@ -489,6 +497,8 @@ static int _snd_timer_stop(struct snd_timer_instance * timeri,
 		if (!keep_flag) {
 			spin_lock_irqsave(&slave_active_lock, flags);
 			timeri->flags &= ~SNDRV_TIMER_IFLG_RUNNING;
+			list_del_init(&timeri->ack_list);
+			list_del_init(&timeri->active_list);
 			spin_unlock_irqrestore(&slave_active_lock, flags);
 		}
 		goto __end;

sound/soc/msm/qdsp6v2/msm-ds2-dap-config.c

@@ -1,4 +1,4 @@
-/* Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
+/* Copyright (c) 2013-2016, The Linux Foundation. All rights reserved.
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 and
 * only version 2 as published by the Free Software Foundation.
@@ -1356,7 +1356,11 @@ static int msm_ds2_dap_handle_commands(u32 cmd, void *arg)
 	int ret  = 0, port_id = 0;
 	int32_t data;
 	struct dolby_param_data *dolby_data = (struct dolby_param_data *)arg;
-	get_user(data, &dolby_data->data[0]);
+	if (get_user(data, &dolby_data->data[0])) {
+		pr_debug("%s error getting data\n", __func__);
+		ret = -EFAULT;
+		goto end;
+	}
 
 	pr_debug("%s: param_id %d,be_id %d,device_id 0x%x,length %d,data %d\n",
 		 __func__, dolby_data->param_id, dolby_data->be_id,
@@ -1471,11 +1475,23 @@ static int msm_ds2_dap_set_param(u32 cmd, void *arg)
 			goto end;
 		}
 
+		off = ds2_dap_params_offset[idx];
+		if ((dolby_data->length <= 0) ||
+			(dolby_data->length > TOTAL_LENGTH_DS2_PARAM - off)) {
+			pr_err("%s: invalid length %d at idx %d\n",
+				__func__, dolby_data->length, idx);
+			rc = -EINVAL;
+			goto end;
+		}
+
 		/* cache the parameters */
 		ds2_dap_params[cdev].dap_params_modified[idx] += 1;
 		for (j = 0; j <  dolby_data->length; j++) {
-			off = ds2_dap_params_offset[idx];
-			get_user(data, &dolby_data->data[j]);
+			if (get_user(data, &dolby_data->data[j])) {
+				pr_debug("%s:error getting data\n", __func__);
+				rc = -EFAULT;
+				goto end;
+			}
 			ds2_dap_params[cdev].params_val[off + j] = data;
 				pr_debug("%s:off %d,val[i/p:o/p]-[%d / %d]\n",
 					 __func__, off, data,