fscrypt,f2fs: catch up fscrypt and f2fs-stable/v3.18 having v4.12-rc1
This patch adds fs/crypto and updates fs/f2fs towards v4.12-rc1, cherry-picked
from f2fs-stable/linux-3.18.y.
Changes include:
Merge branch 'linux-3.18.y' of git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable into linux-3.18.y
f2fs: switch to using fscrypt_match_name()
fscrypt: introduce helper function for filename matching
fscrypt: fix context consistency check when key(s) unavailable
fscrypt: Move key structure and constants to uapi
fscrypt: remove unnecessary checks for NULL operations
fscrypt: eliminate ->prepare_context() operation
fscrypt: remove broken support for detecting keyring key revocation
fscrypt: avoid collisions when presenting long encrypted filenames
f2fs: check entire encrypted bigname when finding a dentry
f2fs: sync f2fs_lookup() with ext4_lookup()
f2fs: fix a mount fail for wrong next_scan_nid
f2fs: relocate inode_{,un}lock in F2FS_IOC_SETFLAGS
f2fs: show available_nids in f2fs/status
f2fs: flush dirty nats periodically
f2fs: introduce CP_TRIMMED_FLAG to avoid unneeded discard
f2fs: allow cpc->reason to indicate more than one reason
...
Change-Id: Iae7ac8d2aa890f6b15a4d20e625af1ccc5480848
Signed-off-by: Jaegeuk Kim <jaegeuk@google.com>
diff --git a/fs/Kconfig b/fs/Kconfig
index 0fcd3a0..874e1c4 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -61,6 +61,8 @@
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"
diff --git a/fs/Makefile b/fs/Makefile
index 340227e..f67fb07 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -28,6 +28,7 @@
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-$(CONFIG_BINFMT_AOUT) += binfmt_aout.o
diff --git a/fs/crypto/Kconfig b/fs/crypto/Kconfig
new file mode 100644
index 0000000..92348fa
--- /dev/null
+++ b/fs/crypto/Kconfig
@@ -0,0 +1,18 @@
+config FS_ENCRYPTION
+ tristate "FS Encryption (Per-file encryption)"
+ depends on BLOCK
+ select CRYPTO
+ select CRYPTO_AES
+ select CRYPTO_CBC
+ select CRYPTO_ECB
+ select CRYPTO_XTS
+ select CRYPTO_CTS
+ select CRYPTO_CTR
+ select CRYPTO_SHA256
+ select KEYS
+ select ENCRYPTED_KEYS
+ help
+ Enable encryption of files and directories. This
+ feature is similar to ecryptfs, but it is more memory
+ efficient since it avoids caching the encrypted and
+ decrypted pages in the page cache.
diff --git a/fs/crypto/Makefile b/fs/crypto/Makefile
new file mode 100644
index 0000000..9f6607f
--- /dev/null
+++ b/fs/crypto/Makefile
@@ -0,0 +1,4 @@
+obj-$(CONFIG_FS_ENCRYPTION) += fscrypto.o
+
+fscrypto-y := crypto.o fname.o policy.o keyinfo.o
+fscrypto-$(CONFIG_BLOCK) += bio.o
diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c
new file mode 100644
index 0000000..a91ed46
--- /dev/null
+++ b/fs/crypto/bio.c
@@ -0,0 +1,143 @@
+/*
+ * This contains encryption functions for per-file encryption.
+ *
+ * Copyright (C) 2015, Google, Inc.
+ * Copyright (C) 2015, Motorola Mobility
+ *
+ * Written by Michael Halcrow, 2014.
+ *
+ * Filename encryption additions
+ * Uday Savagaonkar, 2014
+ * Encryption policy handling additions
+ * Ildar Muslukhov, 2014
+ * Add fscrypt_pullback_bio_page()
+ * Jaegeuk Kim, 2015.
+ *
+ * This has not yet undergone a rigorous security audit.
+ *
+ * The usage of AES-XTS should conform to recommendations in NIST
+ * Special Publication 800-38E and IEEE P1619/D16.
+ */
+
+#include <linux/pagemap.h>
+#include <linux/module.h>
+#include <linux/bio.h>
+#include <linux/namei.h>
+#include "fscrypt_private.h"
+
+/*
+ * 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->mapping->host, page,
+ PAGE_SIZE, 0, page->index);
+
+ 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);
+
+int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
+ sector_t pblk, unsigned int len)
+{
+ struct fscrypt_ctx *ctx;
+ struct page *ciphertext_page = NULL;
+ struct bio *bio;
+ int ret, err = 0;
+
+ BUG_ON(inode->i_sb->s_blocksize != PAGE_SIZE);
+
+ ctx = fscrypt_get_ctx(inode, GFP_NOFS);
+ if (IS_ERR(ctx))
+ return PTR_ERR(ctx);
+
+ ciphertext_page = fscrypt_alloc_bounce_page(ctx, GFP_NOWAIT);
+ if (IS_ERR(ciphertext_page)) {
+ err = PTR_ERR(ciphertext_page);
+ goto errout;
+ }
+
+ while (len--) {
+ err = fscrypt_do_page_crypto(inode, FS_ENCRYPT, lblk,
+ ZERO_PAGE(0), ciphertext_page,
+ PAGE_SIZE, 0, 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);
+ bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+ 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(0, bio);
+ bio_put(bio);
+ if (err)
+ goto errout;
+ lblk++;
+ pblk++;
+ }
+ err = 0;
+errout:
+ fscrypt_release_ctx(ctx);
+ return err;
+}
+EXPORT_SYMBOL(fscrypt_zeroout_range);
diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
new file mode 100644
index 0000000..2100bc8
--- /dev/null
+++ b/fs/crypto/crypto.c
@@ -0,0 +1,483 @@
+/*
+ * This contains encryption functions for per-file encryption.
+ *
+ * Copyright (C) 2015, Google, Inc.
+ * Copyright (C) 2015, Motorola Mobility
+ *
+ * Written by Michael Halcrow, 2014.
+ *
+ * Filename encryption additions
+ * Uday Savagaonkar, 2014
+ * Encryption policy handling additions
+ * Ildar Muslukhov, 2014
+ * Add fscrypt_pullback_bio_page()
+ * Jaegeuk Kim, 2015.
+ *
+ * This has not yet undergone a rigorous security audit.
+ *
+ * The usage of AES-XTS should conform to recommendations in NIST
+ * Special Publication 800-38E and IEEE P1619/D16.
+ */
+
+#include <linux/pagemap.h>
+#include <linux/mempool.h>
+#include <linux/module.h>
+#include <linux/scatterlist.h>
+#include <linux/ratelimit.h>
+#include <linux/dcache.h>
+#include <linux/namei.h>
+#include "fscrypt_private.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);
+
+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_CTX_HAS_BOUNCE_BUFFER_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(const 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_CTX_HAS_BOUNCE_BUFFER_FL;
+ return ctx;
+}
+EXPORT_SYMBOL(fscrypt_get_ctx);
+
+/**
+ * page_crypt_complete() - completion callback for page crypto
+ * @req: The asynchronous cipher request context
+ * @res: The result of the cipher operation
+ */
+static void page_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);
+}
+
+int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw,
+ u64 lblk_num, struct page *src_page,
+ struct page *dest_page, unsigned int len,
+ unsigned int offs, gfp_t gfp_flags)
+{
+ struct {
+ __le64 index;
+ u8 padding[FS_XTS_TWEAK_SIZE - sizeof(__le64)];
+ } xts_tweak;
+ 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;
+
+ BUG_ON(len == 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,
+ page_crypt_complete, &ecr);
+
+ BUILD_BUG_ON(sizeof(xts_tweak) != FS_XTS_TWEAK_SIZE);
+ xts_tweak.index = cpu_to_le64(lblk_num);
+ memset(xts_tweak.padding, 0, sizeof(xts_tweak.padding));
+
+ sg_init_table(&dst, 1);
+ sg_set_page(&dst, dest_page, len, offs);
+ sg_init_table(&src, 1);
+ sg_set_page(&src, src_page, len, offs);
+ ablkcipher_request_set_crypt(req, &src, &dst, len, &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;
+}
+
+struct page *fscrypt_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_CTX_HAS_BOUNCE_BUFFER_FL;
+ return ctx->w.bounce_page;
+}
+
+/**
+ * fscypt_encrypt_page() - Encrypts a page
+ * @inode: The inode for which the encryption should take place
+ * @page: The page to encrypt. Must be locked for bounce-page
+ * encryption.
+ * @len: Length of data to encrypt in @page and encrypted
+ * data in returned page.
+ * @offs: Offset of data within @page and returned
+ * page holding encrypted data.
+ * @lblk_num: Logical block number. This must be unique for multiple
+ * calls with same inode, except when overwriting
+ * previously written data.
+ * @gfp_flags: The gfp flag for memory allocation
+ *
+ * Encrypts @page using the ctx encryption context. Performs encryption
+ * either in-place or into a newly allocated bounce page.
+ * Called on the page write path.
+ *
+ * Bounce page allocation is the default.
+ * In this case, the contents of @page are encrypted and stored in an
+ * allocated bounce page. @page has to be locked and the caller must call
+ * fscrypt_restore_control_page() on the returned ciphertext page to
+ * release the bounce buffer and the encryption context.
+ *
+ * In-place encryption is used by setting the FS_CFLG_OWN_PAGES flag in
+ * fscrypt_operations. Here, the input-page is returned with its content
+ * encrypted.
+ *
+ * Return: A page with the encrypted content on success. Else, an
+ * error value or NULL.
+ */
+struct page *fscrypt_encrypt_page(const struct inode *inode,
+ struct page *page,
+ unsigned int len,
+ unsigned int offs,
+ u64 lblk_num, gfp_t gfp_flags)
+
+{
+ struct fscrypt_ctx *ctx;
+ struct page *ciphertext_page = page;
+ int err;
+
+ BUG_ON(len % FS_CRYPTO_BLOCK_SIZE != 0);
+
+ if (inode->i_sb->s_cop->flags & FS_CFLG_OWN_PAGES) {
+ /* with inplace-encryption we just encrypt the page */
+ err = fscrypt_do_page_crypto(inode, FS_ENCRYPT, lblk_num, page,
+ ciphertext_page, len, offs,
+ gfp_flags);
+ if (err)
+ return ERR_PTR(err);
+
+ return ciphertext_page;
+ }
+
+ BUG_ON(!PageLocked(page));
+
+ ctx = fscrypt_get_ctx(inode, gfp_flags);
+ if (IS_ERR(ctx))
+ return (struct page *)ctx;
+
+ /* The encryption operation will require a bounce page. */
+ ciphertext_page = fscrypt_alloc_bounce_page(ctx, gfp_flags);
+ if (IS_ERR(ciphertext_page))
+ goto errout;
+
+ ctx->w.control_page = page;
+ err = fscrypt_do_page_crypto(inode, FS_ENCRYPT, lblk_num,
+ page, ciphertext_page, len, offs,
+ 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);
+
+/**
+ * fscrypt_decrypt_page() - Decrypts a page in-place
+ * @inode: The corresponding inode for the page to decrypt.
+ * @page: The page to decrypt. Must be locked in case
+ * it is a writeback page (FS_CFLG_OWN_PAGES unset).
+ * @len: Number of bytes in @page to be decrypted.
+ * @offs: Start of data in @page.
+ * @lblk_num: Logical block number.
+ *
+ * Decrypts page in-place using the ctx encryption context.
+ *
+ * Called from the read completion callback.
+ *
+ * Return: Zero on success, non-zero otherwise.
+ */
+int fscrypt_decrypt_page(const struct inode *inode, struct page *page,
+ unsigned int len, unsigned int offs, u64 lblk_num)
+{
+ if (!(inode->i_sb->s_cop->flags & FS_CFLG_OWN_PAGES))
+ BUG_ON(!PageLocked(page));
+
+ return fscrypt_do_page_crypto(inode, FS_DECRYPT, lblk_num, page, page,
+ len, offs, GFP_NOFS);
+}
+EXPORT_SYMBOL(fscrypt_decrypt_page);
+
+/*
+ * 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;
+ 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;
+ }
+
+ /* 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 = (d_inode(dir)->i_crypt_info != 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);
+
+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.
+ * @cop_flags: fscrypt operations flags
+ *
+ * We only call this when we start accessing encrypted files, since it
+ * results in memory getting allocated that wouldn't otherwise be used.
+ *
+ * Return: Zero on success, non-zero otherwise.
+ */
+int fscrypt_initialize(unsigned int cop_flags)
+{
+ int i, res = -ENOMEM;
+
+ /*
+ * No need to allocate a bounce page pool if there already is one or
+ * this FS won't use it.
+ */
+ if (cop_flags & FS_CFLG_OWN_PAGES || fscrypt_bounce_page_pool)
+ return 0;
+
+ mutex_lock(&fscrypt_init_mutex);
+ 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;
+}
+
+/**
+ * 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");
diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
new file mode 100644
index 0000000..17905ce
--- /dev/null
+++ b/fs/crypto/fname.c
@@ -0,0 +1,464 @@
+/*
+ * 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 <linux/scatterlist.h>
+#include <linux/ratelimit.h>
+#include "fscrypt_private.h"
+
+/**
+ * fname_crypt_complete() - completion callback for filename crypto
+ * @req: The asynchronous cipher request context
+ * @res: The result of the cipher operation
+ */
+static void fname_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() - encrypt a filename
+ *
+ * The caller must have allocated sufficient memory for the @oname string.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int fname_encrypt(struct inode *inode,
+ const struct qstr *iname, struct fscrypt_str *oname)
+{
+ 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 sg;
+ int padding = 4 << (ci->ci_flags & FS_POLICY_FLAGS_PAD_MASK);
+ unsigned int lim;
+ unsigned int cryptlen;
+
+ lim = inode->i_sb->s_cop->max_namelen(inode);
+ if (iname->len <= 0 || iname->len > lim)
+ return -EIO;
+
+ /*
+ * Copy the filename to the output buffer for encrypting in-place and
+ * pad it with the needed number of NUL bytes.
+ */
+ cryptlen = max_t(unsigned int, iname->len, FS_CRYPTO_BLOCK_SIZE);
+ cryptlen = round_up(cryptlen, padding);
+ cryptlen = min(cryptlen, lim);
+ memcpy(oname->name, iname->name, iname->len);
+ memset(oname->name + iname->len, 0, cryptlen - iname->len);
+
+ /* Initialize the IV */
+ memset(iv, 0, FS_CRYPTO_BLOCK_SIZE);
+
+ /* Set up the encryption request */
+ req = ablkcipher_request_alloc(tfm, GFP_NOFS);
+ if (!req) {
+ printk_ratelimited(KERN_ERR
+ "%s: ablkcipher_request_alloc() failed\n", __func__);
+ return -ENOMEM;
+ }
+ ablkcipher_request_set_callback(req,
+ CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
+ fname_crypt_complete, &ecr);
+ sg_init_one(&sg, oname->name, cryptlen);
+ ablkcipher_request_set_crypt(req, &sg, &sg, cryptlen, iv);
+
+ /* Do the encryption */
+ res = crypto_ablkcipher_encrypt(req);
+ if (res == -EINPROGRESS || res == -EBUSY) {
+ /* Request is being completed asynchronously; wait for it */
+ 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 = cryptlen;
+ return 0;
+}
+
+/**
+ * fname_decrypt() - decrypt a filename
+ *
+ * The caller must have allocated sufficient memory for the @oname string.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+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,
+ fname_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 0;
+}
+
+static const char *lookup_table =
+ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,";
+
+#define BASE64_CHARS(nbytes) DIV_ROUND_UP((nbytes) * 4, 3)
+
+/**
+ * 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(const 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);
+ ilen = max(ilen, (u32)FS_CRYPTO_BLOCK_SIZE);
+ return 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(const struct inode *inode,
+ u32 ilen, struct fscrypt_str *crypto_str)
+{
+ u32 olen = fscrypt_fname_encrypted_size(inode, ilen);
+ const u32 max_encoded_len =
+ max_t(u32, BASE64_CHARS(FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE),
+ 1 + BASE64_CHARS(sizeof(struct fscrypt_digested_name)));
+
+ crypto_str->len = olen;
+ olen = max(olen, max_encoded_len);
+
+ /*
+ * 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
+ *
+ * The caller must have allocated sufficient memory for the @oname string.
+ *
+ * If the key is available, we'll decrypt the disk name; otherwise, we'll encode
+ * it for presentation. Short names are directly base64-encoded, while long
+ * names are encoded in fscrypt_digested_name format.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+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);
+ struct fscrypt_digested_name digested_name;
+
+ if (fscrypt_is_dot_dotdot(&qname)) {
+ oname->name[0] = '.';
+ oname->name[iname->len - 1] = '.';
+ oname->len = iname->len;
+ return 0;
+ }
+
+ if (iname->len < FS_CRYPTO_BLOCK_SIZE)
+ return -EUCLEAN;
+
+ if (inode->i_crypt_info)
+ return fname_decrypt(inode, iname, oname);
+
+ if (iname->len <= FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE) {
+ oname->len = digest_encode(iname->name, iname->len,
+ oname->name);
+ return 0;
+ }
+ if (hash) {
+ digested_name.hash = hash;
+ digested_name.minor_hash = minor_hash;
+ } else {
+ digested_name.hash = 0;
+ digested_name.minor_hash = 0;
+ }
+ memcpy(digested_name.digest,
+ FSCRYPT_FNAME_DIGEST(iname->name, iname->len),
+ FSCRYPT_FNAME_DIGEST_SIZE);
+ oname->name[0] = '_';
+ oname->len = 1 + digest_encode((const char *)&digested_name,
+ sizeof(digested_name), oname->name + 1);
+ return 0;
+}
+EXPORT_SYMBOL(fscrypt_fname_disk_to_usr);
+
+/**
+ * fscrypt_fname_usr_to_disk() - converts a filename from user space to disk
+ * space
+ *
+ * The caller must have allocated sufficient memory for the @oname string.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+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 0;
+ }
+ 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 -ENOKEY;
+}
+EXPORT_SYMBOL(fscrypt_fname_usr_to_disk);
+
+/**
+ * fscrypt_setup_filename() - prepare to search a possibly encrypted directory
+ * @dir: the directory that will be searched
+ * @iname: the user-provided filename being searched for
+ * @lookup: 1 if we're allowed to proceed without the key because it's
+ * ->lookup() or we're finding the dir_entry for deletion; 0 if we cannot
+ * proceed without the key because we're going to create the dir_entry.
+ * @fname: the filename information to be filled in
+ *
+ * Given a user-provided filename @iname, this function sets @fname->disk_name
+ * to the name that would be stored in the on-disk directory entry, if possible.
+ * If the directory is unencrypted this is simply @iname. Else, if we have the
+ * directory's encryption key, then @iname is the plaintext, so we encrypt it to
+ * get the disk_name.
+ *
+ * Else, for keyless @lookup operations, @iname is the presented ciphertext, so
+ * we decode it to get either the ciphertext disk_name (for short names) or the
+ * fscrypt_digested_name (for long names). Non-@lookup operations will be
+ * impossible in this case, so we fail them with ENOKEY.
+ *
+ * If successful, fscrypt_free_filename() must be called later to clean up.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
+ int lookup, struct fscrypt_name *fname)
+{
+ int ret;
+ int digested;
+
+ 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 = fscrypt_get_encryption_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)
+ return ret;
+ ret = fname_encrypt(dir, iname, &fname->crypto_buf);
+ if (ret)
+ goto errout;
+ fname->disk_name.name = fname->crypto_buf.name;
+ fname->disk_name.len = fname->crypto_buf.len;
+ return 0;
+ }
+ if (!lookup)
+ return -ENOKEY;
+
+ /*
+ * We don't have the key and we are doing a lookup; decode the
+ * user-supplied name
+ */
+ if (iname->name[0] == '_') {
+ if (iname->len !=
+ 1 + BASE64_CHARS(sizeof(struct fscrypt_digested_name)))
+ return -ENOENT;
+ digested = 1;
+ } else {
+ if (iname->len >
+ BASE64_CHARS(FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE))
+ return -ENOENT;
+ digested = 0;
+ }
+
+ fname->crypto_buf.name =
+ kmalloc(max_t(size_t, FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE,
+ sizeof(struct fscrypt_digested_name)),
+ GFP_KERNEL);
+ if (fname->crypto_buf.name == NULL)
+ return -ENOMEM;
+
+ ret = digest_decode(iname->name + digested, iname->len - digested,
+ fname->crypto_buf.name);
+ if (ret < 0) {
+ ret = -ENOENT;
+ goto errout;
+ }
+ fname->crypto_buf.len = ret;
+ if (digested) {
+ const struct fscrypt_digested_name *n =
+ (const void *)fname->crypto_buf.name;
+ fname->hash = n->hash;
+ fname->minor_hash = n->minor_hash;
+ } 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);
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
new file mode 100644
index 0000000..1bc34d98
--- /dev/null
+++ b/fs/crypto/fscrypt_private.h
@@ -0,0 +1,115 @@
+/*
+ * fscrypt_private.h
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * This contains encryption key functions.
+ *
+ * Written by Michael Halcrow, Ildar Muslukhov, and Uday Savagaonkar, 2015.
+ */
+
+#ifndef _FSCRYPT_PRIVATE_H
+#define _FSCRYPT_PRIVATE_H
+
+#include <linux/fscrypt_supp.h>
+
+/* 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_KEY_DERIVATION_NONCE_SIZE 16
+
+/**
+ * Encryption context for inode
+ *
+ * Protector format:
+ * 1 byte: Protector format (1 = this version)
+ * 1 byte: File contents encryption mode
+ * 1 byte: File names encryption mode
+ * 1 byte: Flags
+ * 8 bytes: Master Key descriptor
+ * 16 bytes: Encryption Key derivation nonce
+ */
+struct fscrypt_context {
+ u8 format;
+ u8 contents_encryption_mode;
+ u8 filenames_encryption_mode;
+ u8 flags;
+ u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
+ u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE];
+} __packed;
+
+#define FS_ENCRYPTION_CONTEXT_FORMAT_V1 1
+
+/*
+ * A pointer to this structure is stored in the file system's in-core
+ * representation of an inode.
+ */
+struct fscrypt_info {
+ u8 ci_data_mode;
+ u8 ci_filename_mode;
+ u8 ci_flags;
+ struct crypto_ablkcipher *ci_ctfm;
+ u8 ci_master_key[FS_KEY_DESCRIPTOR_SIZE];
+};
+
+typedef enum {
+ FS_DECRYPT = 0,
+ FS_ENCRYPT,
+} fscrypt_direction_t;
+
+#define FS_CTX_REQUIRES_FREE_ENCRYPT_FL 0x00000001
+#define FS_CTX_HAS_BOUNCE_BUFFER_FL 0x00000002
+
+struct fscrypt_completion_result {
+ struct completion completion;
+ int res;
+};
+
+#define DECLARE_FS_COMPLETION_RESULT(ecr) \
+ struct fscrypt_completion_result ecr = { \
+ COMPLETION_INITIALIZER_ONSTACK((ecr).completion), 0 }
+
+static inline void inode_lock(struct inode *inode)
+{
+ mutex_lock(&inode->i_mutex);
+}
+
+static inline void inode_unlock(struct inode *inode)
+{
+ mutex_unlock(&inode->i_mutex);
+}
+
+static inline const struct user_key_payload *user_key_payload(const struct key *key)
+{
+ return (struct user_key_payload *)rcu_dereference_key(key);
+}
+
+/* bio stuffs */
+#define REQ_OP_READ READ
+#define REQ_OP_WRITE WRITE
+#define bio_op(bio) ((bio)->bi_rw & 1)
+
+static inline void bio_set_op_attrs(struct bio *bio, unsigned op,
+ unsigned op_flags)
+{
+ bio->bi_rw = op | op_flags;
+}
+
+/* crypto.c */
+extern int fscrypt_initialize(unsigned int cop_flags);
+extern struct workqueue_struct *fscrypt_read_workqueue;
+extern int fscrypt_do_page_crypto(const struct inode *inode,
+ fscrypt_direction_t rw, u64 lblk_num,
+ struct page *src_page,
+ struct page *dest_page,
+ unsigned int len, unsigned int offs,
+ gfp_t gfp_flags);
+extern struct page *fscrypt_alloc_bounce_page(struct fscrypt_ctx *ctx,
+ gfp_t gfp_flags);
+
+#endif /* _FSCRYPT_PRIVATE_H */
diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c
new file mode 100644
index 0000000..995003c
--- /dev/null
+++ b/fs/crypto/keyinfo.c
@@ -0,0 +1,297 @@
+/*
+ * 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/user-type.h>
+#include <linux/scatterlist.h>
+#include "fscrypt_private.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,
+ const char *prefix)
+{
+ char *description;
+ struct key *keyring_key;
+ struct fscrypt_key *master_key;
+ const struct user_key_payload *ukp;
+ int prefix_size = strlen(prefix);
+ int full_key_len = prefix_size + (FS_KEY_DESCRIPTOR_SIZE * 2) + 1;
+ int res;
+
+ /* FIXME: 3.18 causes kernel panic.
+ description = kasprintf(GFP_NOFS, "%s%*phN", prefix,
+ FS_KEY_DESCRIPTOR_SIZE,
+ ctx->master_key_descriptor);
+ */
+ description = kmalloc(full_key_len, GFP_NOFS);
+ if (!description)
+ return -ENOMEM;
+
+ memcpy(description, prefix, prefix_size);
+ sprintf(description + prefix_size,
+ "%*phN", FS_KEY_DESCRIPTOR_SIZE,
+ ctx->master_key_descriptor);
+ description[full_key_len - 1] = '\0';
+
+ keyring_key = request_key(&key_type_logon, description, NULL);
+ kfree(description);
+ if (IS_ERR(keyring_key))
+ return PTR_ERR(keyring_key);
+ down_read(&keyring_key->sem);
+
+ if (keyring_key->type != &key_type_logon) {
+ printk_once(KERN_WARNING
+ "%s: key type must be logon\n", __func__);
+ res = -ENOKEY;
+ goto out;
+ }
+ ukp = user_key_payload(keyring_key);
+ if (ukp->datalen != sizeof(struct fscrypt_key)) {
+ res = -EINVAL;
+ 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;
+ goto out;
+ }
+ res = derive_key_aes(ctx->nonce, master_key->raw, raw_key);
+out:
+ up_read(&keyring_key->sem);
+ key_put(keyring_key);
+ return res;
+}
+
+static int determine_cipher_type(struct fscrypt_info *ci, struct inode *inode,
+ const char **cipher_str_ret, int *keysize_ret)
+{
+ if (S_ISREG(inode->i_mode)) {
+ if (ci->ci_data_mode == FS_ENCRYPTION_MODE_AES_256_XTS) {
+ *cipher_str_ret = "xts(aes)";
+ *keysize_ret = FS_AES_256_XTS_KEY_SIZE;
+ return 0;
+ }
+ pr_warn_once("fscrypto: unsupported contents encryption mode "
+ "%d for inode %lu\n",
+ ci->ci_data_mode, inode->i_ino);
+ return -ENOKEY;
+ }
+
+ if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) {
+ if (ci->ci_filename_mode == FS_ENCRYPTION_MODE_AES_256_CTS) {
+ *cipher_str_ret = "cts(cbc(aes))";
+ *keysize_ret = FS_AES_256_CTS_KEY_SIZE;
+ return 0;
+ }
+ pr_warn_once("fscrypto: unsupported filenames encryption mode "
+ "%d for inode %lu\n",
+ ci->ci_filename_mode, inode->i_ino);
+ return -ENOKEY;
+ }
+
+ pr_warn_once("fscrypto: unsupported file type %d for inode %lu\n",
+ (inode->i_mode & S_IFMT), inode->i_ino);
+ return -ENOKEY;
+}
+
+static void put_crypt_info(struct fscrypt_info *ci)
+{
+ if (!ci)
+ return;
+
+ crypto_free_ablkcipher(ci->ci_ctfm);
+ kmem_cache_free(fscrypt_info_cachep, ci);
+}
+
+int fscrypt_get_encryption_info(struct inode *inode)
+{
+ struct fscrypt_info *crypt_info;
+ struct fscrypt_context ctx;
+ struct crypto_ablkcipher *ctfm;
+ const char *cipher_str;
+ int keysize;
+ u8 *raw_key = NULL;
+ int res;
+
+ if (inode->i_crypt_info)
+ return 0;
+
+ res = fscrypt_initialize(inode->i_sb->s_cop->flags);
+ if (res)
+ return res;
+
+ res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+ if (res < 0) {
+ if (!fscrypt_dummy_context_enabled(inode) ||
+ inode->i_sb->s_cop->is_encrypted(inode))
+ return res;
+ /* Fake up a context for an unencrypted directory */
+ memset(&ctx, 0, sizeof(ctx));
+ ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1;
+ ctx.contents_encryption_mode = FS_ENCRYPTION_MODE_AES_256_XTS;
+ ctx.filenames_encryption_mode = FS_ENCRYPTION_MODE_AES_256_CTS;
+ memset(ctx.master_key_descriptor, 0x42, FS_KEY_DESCRIPTOR_SIZE);
+ } else if (res != sizeof(ctx)) {
+ return -EINVAL;
+ }
+
+ if (ctx.format != FS_ENCRYPTION_CONTEXT_FORMAT_V1)
+ return -EINVAL;
+
+ if (ctx.flags & ~FS_POLICY_FLAGS_VALID)
+ return -EINVAL;
+
+ 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;
+ memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor,
+ sizeof(crypt_info->ci_master_key));
+
+ res = determine_cipher_type(crypt_info, inode, &cipher_str, &keysize);
+ if (res)
+ goto out;
+
+ /*
+ * This cannot be a stack buffer because it is passed to the scatterlist
+ * crypto API as part of key derivation.
+ */
+ res = -ENOMEM;
+ raw_key = kmalloc(FS_MAX_KEY_SIZE, GFP_NOFS);
+ if (!raw_key)
+ goto out;
+
+ res = validate_user_key(crypt_info, &ctx, raw_key, FS_KEY_DESC_PREFIX);
+ if (res && inode->i_sb->s_cop->key_prefix) {
+ int res2 = validate_user_key(crypt_info, &ctx, raw_key,
+ inode->i_sb->s_cop->key_prefix);
+ if (res2) {
+ if (res2 == -ENOKEY)
+ res = -ENOKEY;
+ goto out;
+ }
+ } else if (res) {
+ goto out;
+ }
+ 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_ablkcipher_set_flags(ctfm, CRYPTO_TFM_REQ_WEAK_KEY);
+ res = crypto_ablkcipher_setkey(ctfm, raw_key, keysize);
+ if (res)
+ goto out;
+
+ if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) == NULL)
+ crypt_info = NULL;
+out:
+ if (res == -ENOKEY)
+ res = 0;
+ put_crypt_info(crypt_info);
+ kzfree(raw_key);
+ return res;
+}
+EXPORT_SYMBOL(fscrypt_get_encryption_info);
+
+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);
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
new file mode 100644
index 0000000..210976e
--- /dev/null
+++ b/fs/crypto/policy.c
@@ -0,0 +1,269 @@
+/*
+ * 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/mount.h>
+#include "fscrypt_private.h"
+
+/*
+ * check whether an encryption policy is consistent with an encryption context
+ */
+static bool is_encryption_context_consistent_with_policy(
+ const struct fscrypt_context *ctx,
+ const struct fscrypt_policy *policy)
+{
+ 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;
+
+ 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))
+ return -EINVAL;
+
+ if (!fscrypt_valid_filenames_enc_mode(
+ 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_ioctl_set_policy(struct file *filp, const void __user *arg)
+{
+ struct fscrypt_policy policy;
+ struct inode *inode = file_inode(filp);
+ int ret;
+ struct fscrypt_context ctx;
+
+ if (copy_from_user(&policy, arg, sizeof(policy)))
+ return -EFAULT;
+
+ if (!inode_owner_or_capable(inode))
+ return -EACCES;
+
+ if (policy.version != 0)
+ return -EINVAL;
+
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ inode_lock(inode);
+
+ ret = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+ if (ret == -ENODATA) {
+ if (!S_ISDIR(inode->i_mode))
+ ret = -ENOTDIR;
+ else if (!inode->i_sb->s_cop->empty_dir(inode))
+ ret = -ENOTEMPTY;
+ else
+ ret = create_encryption_context_from_policy(inode,
+ &policy);
+ } else if (ret == sizeof(ctx) &&
+ is_encryption_context_consistent_with_policy(&ctx,
+ &policy)) {
+ /* The file already uses the same encryption policy. */
+ ret = 0;
+ } else if (ret >= 0 || ret == -ERANGE) {
+ /* The file already uses a different encryption policy. */
+ ret = -EEXIST;
+ }
+
+ inode_unlock(inode);
+
+ mnt_drop_write_file(filp);
+ return ret;
+}
+EXPORT_SYMBOL(fscrypt_ioctl_set_policy);
+
+int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct fscrypt_context ctx;
+ struct fscrypt_policy policy;
+ int res;
+
+ if (!inode->i_sb->s_cop->is_encrypted(inode))
+ return -ENODATA;
+
+ res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+ if (res < 0 && res != -ERANGE)
+ return res;
+ if (res != sizeof(ctx))
+ return -EINVAL;
+ 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);
+
+ if (copy_to_user(arg, &policy, sizeof(policy)))
+ return -EFAULT;
+ return 0;
+}
+EXPORT_SYMBOL(fscrypt_ioctl_get_policy);
+
+/**
+ * fscrypt_has_permitted_context() - is a file's encryption policy permitted
+ * within its directory?
+ *
+ * @parent: inode for parent directory
+ * @child: inode for file being looked up, opened, or linked into @parent
+ *
+ * Filesystems must call this before permitting access to an inode in a
+ * situation where the parent directory is encrypted (either before allowing
+ * ->lookup() to succeed, or for a regular file before allowing it to be opened)
+ * and before any operation that involves linking an inode into an encrypted
+ * directory, including link, rename, and cross rename. It enforces the
+ * constraint that within a given encrypted directory tree, all files use the
+ * same encryption policy. The pre-access check is needed to detect potentially
+ * malicious offline violations of this constraint, while the link and rename
+ * checks are needed to prevent online violations of this constraint.
+ *
+ * Return: 1 if permitted, 0 if forbidden. If forbidden, the caller must fail
+ * the filesystem operation with EPERM.
+ */
+int fscrypt_has_permitted_context(struct inode *parent, struct inode *child)
+{
+ const struct fscrypt_operations *cops = parent->i_sb->s_cop;
+ const struct fscrypt_info *parent_ci, *child_ci;
+ struct fscrypt_context parent_ctx, child_ctx;
+ int res;
+
+ /* No restrictions on file types which are never encrypted */
+ if (!S_ISREG(child->i_mode) && !S_ISDIR(child->i_mode) &&
+ !S_ISLNK(child->i_mode))
+ return 1;
+
+ /* No restrictions if the parent directory is unencrypted */
+ if (!cops->is_encrypted(parent))
+ return 1;
+
+ /* Encrypted directories must not contain unencrypted files */
+ if (!cops->is_encrypted(child))
+ return 0;
+
+ /*
+ * Both parent and child are encrypted, so verify they use the same
+ * encryption policy. Compare the fscrypt_info structs if the keys are
+ * available, otherwise retrieve and compare the fscrypt_contexts.
+ *
+ * Note that the fscrypt_context retrieval will be required frequently
+ * when accessing an encrypted directory tree without the key.
+ * Performance-wise this is not a big deal because we already don't
+ * really optimize for file access without the key (to the extent that
+ * such access is even possible), given that any attempted access
+ * already causes a fscrypt_context retrieval and keyring search.
+ *
+ * In any case, if an unexpected error occurs, fall back to "forbidden".
+ */
+
+ 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 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);
+ }
+
+ res = cops->get_context(parent, &parent_ctx, sizeof(parent_ctx));
+ if (res != sizeof(parent_ctx))
+ return 0;
+
+ res = cops->get_context(child, &child_ctx, sizeof(child_ctx));
+ if (res != sizeof(child_ctx))
+ return 0;
+
+ return memcmp(parent_ctx.master_key_descriptor,
+ child_ctx.master_key_descriptor,
+ FS_KEY_DESCRIPTOR_SIZE) == 0 &&
+ (parent_ctx.contents_encryption_mode ==
+ child_ctx.contents_encryption_mode) &&
+ (parent_ctx.filenames_encryption_mode ==
+ child_ctx.filenames_encryption_mode) &&
+ (parent_ctx.flags == child_ctx.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 if true
+ *
+ * Return: 0 on success, -errno on failure
+ */
+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;
+
+ 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;
+ 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);
diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig
index 736a348..378c221 100644
--- a/fs/f2fs/Kconfig
+++ b/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 @@
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 @@
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.
diff --git a/fs/f2fs/Makefile b/fs/f2fs/Makefile
index 2e35da1..ca949ea 100644
--- a/fs/f2fs/Makefile
+++ b/fs/f2fs/Makefile
@@ -2,6 +2,8 @@
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
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index f12d5c5..8f48769 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -62,7 +62,7 @@
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);
@@ -109,14 +109,16 @@
return ERR_PTR(-EINVAL);
}
-static void *f2fs_acl_to_disk(const struct posix_acl *acl, size_t *size)
+static void *f2fs_acl_to_disk(struct f2fs_sb_info *sbi,
+ const struct posix_acl *acl, size_t *size)
{
struct f2fs_acl_header *f2fs_acl;
struct f2fs_acl_entry *entry;
int i;
- f2fs_acl = kmalloc(sizeof(struct f2fs_acl_header) + acl->a_count *
- sizeof(struct f2fs_acl_entry), GFP_KERNEL);
+ f2fs_acl = f2fs_kmalloc(sbi, sizeof(struct f2fs_acl_header) +
+ acl->a_count * sizeof(struct f2fs_acl_entry),
+ GFP_NOFS);
if (!f2fs_acl)
return ERR_PTR(-ENOMEM);
@@ -162,7 +164,8 @@
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 +175,13 @@
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(F2FS_I_SB(inode), 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 +192,17 @@
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 +215,7 @@
error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
if (error)
return error;
- set_acl_inode(fi, inode->i_mode);
+ set_acl_inode(inode, inode->i_mode);
}
break;
@@ -225,9 +230,9 @@
}
if (acl) {
- value = f2fs_acl_to_disk(acl, &size);
+ value = f2fs_acl_to_disk(F2FS_I_SB(inode), 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);
}
}
@@ -238,7 +243,7 @@
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;
}
@@ -247,22 +252,147 @@
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, true);
+
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);
diff --git a/fs/f2fs/acl.h b/fs/f2fs/acl.h
index e086465..2c68518 100644
--- a/fs/f2fs/acl.h
+++ b/fs/f2fs/acl.h
@@ -37,15 +37,15 @@
#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;
}
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index dd10a03..b39de99 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -20,10 +20,19 @@
#include "f2fs.h"
#include "node.h"
#include "segment.h"
+#include "trace.h"
#include <trace/events/f2fs.h>
static struct kmem_cache *ino_entry_slab;
-static struct kmem_cache *inode_entry_slab;
+struct kmem_cache *inode_entry_slab;
+
+void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io)
+{
+ set_ckpt_flags(sbi, CP_ERROR_FLAG);
+ sbi->sb->s_flags |= MS_RDONLY;
+ if (!end_io)
+ f2fs_flush_merged_bios(sbi);
+}
/*
* We guarantee no failure on the returned page.
@@ -33,25 +42,39 @@
struct address_space *mapping = META_MAPPING(sbi);
struct page *page = NULL;
repeat:
- page = grab_cache_page(mapping, index);
+ page = f2fs_grab_cache_page(mapping, index, false);
if (!page) {
cond_resched();
goto repeat;
}
- f2fs_wait_on_page_writeback(page, META);
- SetPageUptodate(page);
+ f2fs_wait_on_page_writeback(page, META, true);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
return page;
}
/*
* We guarantee no failure on the returned page.
*/
-struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
+static struct page *__get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index,
+ bool is_meta)
{
struct address_space *mapping = META_MAPPING(sbi);
struct page *page;
+ struct f2fs_io_info fio = {
+ .sbi = sbi,
+ .type = META,
+ .op = REQ_OP_READ,
+ .op_flags = REQ_META | REQ_PRIO,
+ .old_blkaddr = index,
+ .new_blkaddr = index,
+ .encrypted_page = NULL,
+ };
+
+ if (unlikely(!is_meta))
+ fio.op_flags &= ~REQ_META;
repeat:
- page = grab_cache_page(mapping, index);
+ page = f2fs_grab_cache_page(mapping, index, false);
if (!page) {
cond_resched();
goto repeat;
@@ -59,101 +82,124 @@
if (PageUptodate(page))
goto out;
- if (f2fs_submit_page_bio(sbi, page, index,
- READ_SYNC | REQ_META | REQ_PRIO))
+ fio.page = page;
+
+ if (f2fs_submit_page_bio(&fio)) {
+ f2fs_put_page(page, 1);
goto repeat;
+ }
lock_page(page);
if (unlikely(page->mapping != mapping)) {
f2fs_put_page(page, 1);
goto repeat;
}
+
+ /*
+ * if there is any IO error when accessing device, make our filesystem
+ * readonly and make sure do not write checkpoint with non-uptodate
+ * meta page.
+ */
+ if (unlikely(!PageUptodate(page)))
+ f2fs_stop_checkpoint(sbi, false);
out:
+ mark_page_accessed(page);
return page;
}
-struct page *get_meta_page_ra(struct f2fs_sb_info *sbi, pgoff_t index)
+struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
{
- bool readahead = false;
- struct page *page;
-
- page = find_get_page(META_MAPPING(sbi), index);
- if (!page || (page && !PageUptodate(page)))
- readahead = true;
- f2fs_put_page(page, 0);
-
- if (readahead)
- ra_meta_pages(sbi, index, MAX_BIO_BLOCKS(sbi), META_POR);
- return get_meta_page(sbi, index);
+ return __get_meta_page(sbi, index, true);
}
-static inline block_t get_max_meta_blks(struct f2fs_sb_info *sbi, int type)
+/* for POR only */
+struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index)
+{
+ return __get_meta_page(sbi, index, false);
+}
+
+bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type)
{
switch (type) {
case META_NAT:
- return NM_I(sbi)->max_nid / NAT_ENTRY_PER_BLOCK;
+ break;
case META_SIT:
- return SIT_BLK_CNT(sbi);
+ if (unlikely(blkaddr >= SIT_BLK_CNT(sbi)))
+ return false;
+ break;
case META_SSA:
+ if (unlikely(blkaddr >= MAIN_BLKADDR(sbi) ||
+ blkaddr < SM_I(sbi)->ssa_blkaddr))
+ return false;
+ break;
case META_CP:
- return 0;
+ if (unlikely(blkaddr >= SIT_I(sbi)->sit_base_addr ||
+ blkaddr < __start_cp_addr(sbi)))
+ return false;
+ break;
case META_POR:
- return MAX_BLKADDR(sbi);
+ if (unlikely(blkaddr >= MAX_BLKADDR(sbi) ||
+ blkaddr < MAIN_BLKADDR(sbi)))
+ return false;
+ break;
default:
BUG();
}
+
+ return true;
}
/*
* Readahead CP/NAT/SIT/SSA pages
*/
-int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type)
+int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
+ int type, bool sync)
{
- block_t prev_blk_addr = 0;
struct page *page;
block_t blkno = start;
- block_t max_blks = get_max_meta_blks(sbi, type);
-
struct f2fs_io_info fio = {
+ .sbi = sbi,
.type = META,
- .rw = READ_SYNC | REQ_META | REQ_PRIO
+ .op = REQ_OP_READ,
+ .op_flags = sync ? (REQ_META | REQ_PRIO) : REQ_RAHEAD,
+ .encrypted_page = NULL,
};
+ struct blk_plug plug;
+ if (unlikely(type == META_POR))
+ fio.op_flags &= ~REQ_META;
+
+ blk_start_plug(&plug);
for (; nrpages-- > 0; blkno++) {
- block_t blk_addr;
+
+ if (!is_valid_blkaddr(sbi, blkno, type))
+ goto out;
switch (type) {
case META_NAT:
- /* get nat block addr */
- if (unlikely(blkno >= max_blks))
+ if (unlikely(blkno >=
+ NAT_BLOCK_OFFSET(NM_I(sbi)->max_nid)))
blkno = 0;
- blk_addr = current_nat_addr(sbi,
+ /* get nat block addr */
+ fio.new_blkaddr = current_nat_addr(sbi,
blkno * NAT_ENTRY_PER_BLOCK);
break;
case META_SIT:
/* get sit block addr */
- if (unlikely(blkno >= max_blks))
- goto out;
- blk_addr = current_sit_addr(sbi,
+ fio.new_blkaddr = current_sit_addr(sbi,
blkno * SIT_ENTRY_PER_BLOCK);
- if (blkno != start && prev_blk_addr + 1 != blk_addr)
- goto out;
- prev_blk_addr = blk_addr;
break;
case META_SSA:
case META_CP:
case META_POR:
- if (unlikely(blkno >= max_blks))
- goto out;
- if (unlikely(blkno < SEG0_BLKADDR(sbi)))
- goto out;
- blk_addr = blkno;
+ fio.new_blkaddr = blkno;
break;
default:
BUG();
}
- page = grab_cache_page(META_MAPPING(sbi), blk_addr);
+ page = f2fs_grab_cache_page(META_MAPPING(sbi),
+ fio.new_blkaddr, false);
if (!page)
continue;
if (PageUptodate(page)) {
@@ -161,14 +207,31 @@
continue;
}
- f2fs_submit_page_mbio(sbi, page, blk_addr, &fio);
+ fio.page = page;
+ fio.old_blkaddr = fio.new_blkaddr;
+ f2fs_submit_page_mbio(&fio);
f2fs_put_page(page, 0);
}
out:
f2fs_submit_merged_bio(sbi, META, READ);
+ blk_finish_plug(&plug);
return blkno - start;
}
+void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index)
+{
+ struct page *page;
+ bool readahead = false;
+
+ page = find_get_page(META_MAPPING(sbi), index);
+ if (!page || !PageUptodate(page))
+ readahead = true;
+ f2fs_put_page(page, 0);
+
+ if (readahead)
+ ra_meta_pages(sbi, index, BIO_MAX_PAGES, META_POR, true);
+}
+
static int f2fs_write_meta_page(struct page *page,
struct writeback_control *wbc)
{
@@ -176,17 +239,25 @@
trace_f2fs_writepage(page, META);
- if (unlikely(sbi->por_doing))
+ if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto redirty_out;
- if (wbc->for_reclaim)
+ if (wbc->for_reclaim && page->index < GET_SUM_BLOCK(sbi, 0))
goto redirty_out;
if (unlikely(f2fs_cp_error(sbi)))
goto redirty_out;
- f2fs_wait_on_page_writeback(page, META);
write_meta_page(sbi, page);
dec_page_count(sbi, F2FS_DIRTY_META);
+
+ if (wbc->for_reclaim)
+ f2fs_submit_merged_bio_cond(sbi, page->mapping->host,
+ 0, page->index, META, WRITE);
+
unlock_page(page);
+
+ if (unlikely(f2fs_cp_error(sbi)))
+ f2fs_submit_merged_bio(sbi, META, WRITE);
+
return 0;
redirty_out:
@@ -200,15 +271,16 @@
struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
long diff, written;
- trace_f2fs_writepages(mapping->host, wbc, META);
-
/* collect a number of dirty meta pages and write together */
if (wbc->for_kupdate ||
get_pages(sbi, F2FS_DIRTY_META) < nr_pages_to_skip(sbi, META))
goto skip_write;
- /* if mounting is failed, skip writing node pages */
- mutex_lock(&sbi->cp_mutex);
+ /* if locked failed, cp will flush dirty pages instead */
+ if (!mutex_trylock(&sbi->cp_mutex))
+ goto skip_write;
+
+ trace_f2fs_writepages(mapping->host, wbc, META);
diff = nr_pages_to_write(sbi, META, wbc);
written = sync_meta_pages(sbi, META, wbc->nr_to_write);
mutex_unlock(&sbi->cp_mutex);
@@ -217,6 +289,7 @@
skip_write:
wbc->pages_skipped += get_pages(sbi, F2FS_DIRTY_META);
+ trace_f2fs_writepages(mapping->host, wbc, META);
return 0;
}
@@ -224,15 +297,18 @@
long nr_to_write)
{
struct address_space *mapping = META_MAPPING(sbi);
- pgoff_t index = 0, end = LONG_MAX;
+ pgoff_t index = 0, end = ULONG_MAX, prev = ULONG_MAX;
struct pagevec pvec;
long nwritten = 0;
struct writeback_control wbc = {
.for_reclaim = 0,
};
+ struct blk_plug plug;
pagevec_init(&pvec, 0);
+ blk_start_plug(&plug);
+
while (index <= end) {
int i, nr_pages;
nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
@@ -244,6 +320,13 @@
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
+ if (prev == ULONG_MAX)
+ prev = page->index - 1;
+ if (nr_to_write != LONG_MAX && page->index != prev + 1) {
+ pagevec_release(&pvec);
+ goto stop;
+ }
+
lock_page(page);
if (unlikely(page->mapping != mapping)) {
@@ -256,24 +339,30 @@
goto continue_unlock;
}
+ f2fs_wait_on_page_writeback(page, META, true);
+
+ BUG_ON(PageWriteback(page));
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
- if (f2fs_write_meta_page(page, &wbc)) {
+ if (mapping->a_ops->writepage(page, &wbc)) {
unlock_page(page);
break;
}
nwritten++;
+ prev = page->index;
if (unlikely(nwritten >= nr_to_write))
break;
}
pagevec_release(&pvec);
cond_resched();
}
-
+stop:
if (nwritten)
f2fs_submit_merged_bio(sbi, type, WRITE);
+ blk_finish_plug(&plug);
+
return nwritten;
}
@@ -281,10 +370,13 @@
{
trace_f2fs_set_page_dirty(page, META);
- SetPageUptodate(page);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
if (!PageDirty(page)) {
- __set_page_dirty_nobuffers(page);
+ f2fs_set_page_dirty_nobuffers(page);
inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_META);
+ SetPagePrivate(page);
+ f2fs_trace_pid(page);
return 1;
}
return 0;
@@ -294,59 +386,70 @@
.writepage = f2fs_write_meta_page,
.writepages = f2fs_write_meta_pages,
.set_page_dirty = f2fs_set_meta_page_dirty,
+ .invalidatepage = f2fs_invalidate_page,
+ .releasepage = f2fs_release_page,
+#ifdef CONFIG_F2FS_MIGRATION
+ .migratepage = f2fs_migrate_page,
+#endif
};
static void __add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
{
- struct ino_entry *e;
-retry:
- spin_lock(&sbi->ino_lock[type]);
+ struct inode_management *im = &sbi->im[type];
+ struct ino_entry *e, *tmp;
- e = radix_tree_lookup(&sbi->ino_root[type], ino);
+ tmp = f2fs_kmem_cache_alloc(ino_entry_slab, GFP_NOFS);
+retry:
+ radix_tree_preload(GFP_NOFS | __GFP_NOFAIL);
+
+ spin_lock(&im->ino_lock);
+ e = radix_tree_lookup(&im->ino_root, ino);
if (!e) {
- e = kmem_cache_alloc(ino_entry_slab, GFP_ATOMIC);
- if (!e) {
- spin_unlock(&sbi->ino_lock[type]);
- goto retry;
- }
- if (radix_tree_insert(&sbi->ino_root[type], ino, e)) {
- spin_unlock(&sbi->ino_lock[type]);
- kmem_cache_free(ino_entry_slab, e);
+ e = tmp;
+ if (radix_tree_insert(&im->ino_root, ino, e)) {
+ spin_unlock(&im->ino_lock);
+ radix_tree_preload_end();
goto retry;
}
memset(e, 0, sizeof(struct ino_entry));
e->ino = ino;
- list_add_tail(&e->list, &sbi->ino_list[type]);
+ list_add_tail(&e->list, &im->ino_list);
+ if (type != ORPHAN_INO)
+ im->ino_num++;
}
- spin_unlock(&sbi->ino_lock[type]);
+ spin_unlock(&im->ino_lock);
+ radix_tree_preload_end();
+
+ if (e != tmp)
+ kmem_cache_free(ino_entry_slab, tmp);
}
static void __remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
{
+ struct inode_management *im = &sbi->im[type];
struct ino_entry *e;
- spin_lock(&sbi->ino_lock[type]);
- e = radix_tree_lookup(&sbi->ino_root[type], ino);
+ spin_lock(&im->ino_lock);
+ e = radix_tree_lookup(&im->ino_root, ino);
if (e) {
list_del(&e->list);
- radix_tree_delete(&sbi->ino_root[type], ino);
- if (type == ORPHAN_INO)
- sbi->n_orphans--;
- spin_unlock(&sbi->ino_lock[type]);
+ radix_tree_delete(&im->ino_root, ino);
+ im->ino_num--;
+ spin_unlock(&im->ino_lock);
kmem_cache_free(ino_entry_slab, e);
return;
}
- spin_unlock(&sbi->ino_lock[type]);
+ spin_unlock(&im->ino_lock);
}
-void add_dirty_inode(struct f2fs_sb_info *sbi, nid_t ino, int type)
+void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
{
/* add new dirty ino entry into list */
__add_ino_entry(sbi, ino, type);
}
-void remove_dirty_inode(struct f2fs_sb_info *sbi, nid_t ino, int type)
+void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type)
{
/* remove dirty ino entry from list */
__remove_ino_entry(sbi, ino, type);
@@ -355,55 +458,72 @@
/* mode should be APPEND_INO or UPDATE_INO */
bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode)
{
+ struct inode_management *im = &sbi->im[mode];
struct ino_entry *e;
- spin_lock(&sbi->ino_lock[mode]);
- e = radix_tree_lookup(&sbi->ino_root[mode], ino);
- spin_unlock(&sbi->ino_lock[mode]);
+
+ spin_lock(&im->ino_lock);
+ e = radix_tree_lookup(&im->ino_root, ino);
+ spin_unlock(&im->ino_lock);
return e ? true : false;
}
-void release_dirty_inode(struct f2fs_sb_info *sbi)
+void release_ino_entry(struct f2fs_sb_info *sbi, bool all)
{
struct ino_entry *e, *tmp;
int i;
- for (i = APPEND_INO; i <= UPDATE_INO; i++) {
- spin_lock(&sbi->ino_lock[i]);
- list_for_each_entry_safe(e, tmp, &sbi->ino_list[i], list) {
+ for (i = all ? ORPHAN_INO: APPEND_INO; i <= UPDATE_INO; i++) {
+ struct inode_management *im = &sbi->im[i];
+
+ spin_lock(&im->ino_lock);
+ list_for_each_entry_safe(e, tmp, &im->ino_list, list) {
list_del(&e->list);
- radix_tree_delete(&sbi->ino_root[i], e->ino);
+ radix_tree_delete(&im->ino_root, e->ino);
kmem_cache_free(ino_entry_slab, e);
+ im->ino_num--;
}
- spin_unlock(&sbi->ino_lock[i]);
+ spin_unlock(&im->ino_lock);
}
}
int acquire_orphan_inode(struct f2fs_sb_info *sbi)
{
+ struct inode_management *im = &sbi->im[ORPHAN_INO];
int err = 0;
- spin_lock(&sbi->ino_lock[ORPHAN_INO]);
- if (unlikely(sbi->n_orphans >= sbi->max_orphans))
+ spin_lock(&im->ino_lock);
+
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(sbi, FAULT_ORPHAN)) {
+ spin_unlock(&im->ino_lock);
+ f2fs_show_injection_info(FAULT_ORPHAN);
+ return -ENOSPC;
+ }
+#endif
+ if (unlikely(im->ino_num >= sbi->max_orphans))
err = -ENOSPC;
else
- sbi->n_orphans++;
- spin_unlock(&sbi->ino_lock[ORPHAN_INO]);
+ im->ino_num++;
+ spin_unlock(&im->ino_lock);
return err;
}
void release_orphan_inode(struct f2fs_sb_info *sbi)
{
- spin_lock(&sbi->ino_lock[ORPHAN_INO]);
- f2fs_bug_on(sbi, sbi->n_orphans == 0);
- sbi->n_orphans--;
- spin_unlock(&sbi->ino_lock[ORPHAN_INO]);
+ struct inode_management *im = &sbi->im[ORPHAN_INO];
+
+ spin_lock(&im->ino_lock);
+ f2fs_bug_on(sbi, im->ino_num == 0);
+ im->ino_num--;
+ spin_unlock(&im->ino_lock);
}
-void add_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
+void add_orphan_inode(struct inode *inode)
{
/* add new orphan ino entry into list */
- __add_ino_entry(sbi, ino, ORPHAN_INO);
+ __add_ino_entry(F2FS_I_SB(inode), inode->i_ino, ORPHAN_INO);
+ update_inode_page(inode);
}
void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
@@ -412,46 +532,82 @@
__remove_ino_entry(sbi, ino, ORPHAN_INO);
}
-static void recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
+static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
{
- struct inode *inode = f2fs_iget(sbi->sb, ino);
- f2fs_bug_on(sbi, IS_ERR(inode));
+ struct inode *inode;
+ struct node_info ni;
+ int err = acquire_orphan_inode(sbi);
+
+ if (err) {
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "%s: orphan failed (ino=%x), run fsck to fix.",
+ __func__, ino);
+ return err;
+ }
+
+ __add_ino_entry(sbi, ino, ORPHAN_INO);
+
+ inode = f2fs_iget_retry(sbi->sb, ino);
+ if (IS_ERR(inode)) {
+ /*
+ * there should be a bug that we can't find the entry
+ * to orphan inode.
+ */
+ f2fs_bug_on(sbi, PTR_ERR(inode) == -ENOENT);
+ return PTR_ERR(inode);
+ }
+
clear_nlink(inode);
/* truncate all the data during iput */
iput(inode);
+
+ get_node_info(sbi, ino, &ni);
+
+ /* ENOMEM was fully retried in f2fs_evict_inode. */
+ if (ni.blk_addr != NULL_ADDR) {
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "%s: orphan failed (ino=%x) by kernel, retry mount.",
+ __func__, ino);
+ return -EIO;
+ }
+ __remove_ino_entry(sbi, ino, ORPHAN_INO);
+ return 0;
}
-void recover_orphan_inodes(struct f2fs_sb_info *sbi)
+int recover_orphan_inodes(struct f2fs_sb_info *sbi)
{
- block_t start_blk, orphan_blkaddr, i, j;
+ block_t start_blk, orphan_blocks, i, j;
+ int err;
- if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG))
- return;
+ if (!is_set_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG))
+ return 0;
- sbi->por_doing = true;
+ start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi);
+ orphan_blocks = __start_sum_addr(sbi) - 1 - __cp_payload(sbi);
- start_blk = __start_cp_addr(sbi) + 1 +
- le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
- orphan_blkaddr = __start_sum_addr(sbi) - 1;
+ ra_meta_pages(sbi, start_blk, orphan_blocks, META_CP, true);
- ra_meta_pages(sbi, start_blk, orphan_blkaddr, META_CP);
-
- for (i = 0; i < orphan_blkaddr; i++) {
+ for (i = 0; i < orphan_blocks; i++) {
struct page *page = get_meta_page(sbi, start_blk + i);
struct f2fs_orphan_block *orphan_blk;
orphan_blk = (struct f2fs_orphan_block *)page_address(page);
for (j = 0; j < le32_to_cpu(orphan_blk->entry_count); j++) {
nid_t ino = le32_to_cpu(orphan_blk->ino[j]);
- recover_orphan_inode(sbi, ino);
+ err = recover_orphan_inode(sbi, ino);
+ if (err) {
+ f2fs_put_page(page, 1);
+ return err;
+ }
}
f2fs_put_page(page, 1);
}
/* clear Orphan Flag */
- clear_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG);
- sbi->por_doing = false;
- return;
+ clear_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG);
+ return 0;
}
static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
@@ -459,28 +615,28 @@
struct list_head *head;
struct f2fs_orphan_block *orphan_blk = NULL;
unsigned int nentries = 0;
- unsigned short index;
- unsigned short orphan_blocks =
- (unsigned short)GET_ORPHAN_BLOCKS(sbi->n_orphans);
+ unsigned short index = 1;
+ unsigned short orphan_blocks;
struct page *page = NULL;
struct ino_entry *orphan = NULL;
+ struct inode_management *im = &sbi->im[ORPHAN_INO];
- for (index = 0; index < orphan_blocks; index++)
- grab_meta_page(sbi, start_blk + index);
+ orphan_blocks = GET_ORPHAN_BLOCKS(im->ino_num);
- index = 1;
- spin_lock(&sbi->ino_lock[ORPHAN_INO]);
- head = &sbi->ino_list[ORPHAN_INO];
+ /*
+ * we don't need to do spin_lock(&im->ino_lock) here, since all the
+ * orphan inode operations are covered under f2fs_lock_op().
+ * And, spin_lock should be avoided due to page operations below.
+ */
+ head = &im->ino_list;
/* loop for each orphan inode entry and write them in Jornal block */
list_for_each_entry(orphan, head, list) {
if (!page) {
- page = find_get_page(META_MAPPING(sbi), start_blk++);
- f2fs_bug_on(sbi, !page);
+ page = grab_meta_page(sbi, start_blk++);
orphan_blk =
(struct f2fs_orphan_block *)page_address(page);
memset(orphan_blk, 0, sizeof(*orphan_blk));
- f2fs_put_page(page, 0);
}
orphan_blk->ino[nentries++] = cpu_to_le32(orphan->ino);
@@ -509,49 +665,56 @@
set_page_dirty(page);
f2fs_put_page(page, 1);
}
+}
- spin_unlock(&sbi->ino_lock[ORPHAN_INO]);
+static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr,
+ struct f2fs_checkpoint **cp_block, struct page **cp_page,
+ unsigned long long *version)
+{
+ unsigned long blk_size = sbi->blocksize;
+ size_t crc_offset = 0;
+ __u32 crc = 0;
+
+ *cp_page = get_meta_page(sbi, cp_addr);
+ *cp_block = (struct f2fs_checkpoint *)page_address(*cp_page);
+
+ crc_offset = le32_to_cpu((*cp_block)->checksum_offset);
+ if (crc_offset > (blk_size - sizeof(__le32))) {
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "invalid crc_offset: %zu", crc_offset);
+ return -EINVAL;
+ }
+
+ crc = cur_cp_crc(*cp_block);
+ if (!f2fs_crc_valid(sbi, crc, *cp_block, crc_offset)) {
+ f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value");
+ return -EINVAL;
+ }
+
+ *version = cur_cp_version(*cp_block);
+ return 0;
}
static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
block_t cp_addr, unsigned long long *version)
{
- struct page *cp_page_1, *cp_page_2 = NULL;
- unsigned long blk_size = sbi->blocksize;
- struct f2fs_checkpoint *cp_block;
+ struct page *cp_page_1 = NULL, *cp_page_2 = NULL;
+ struct f2fs_checkpoint *cp_block = NULL;
unsigned long long cur_version = 0, pre_version = 0;
- size_t crc_offset;
- __u32 crc = 0;
+ int err;
- /* Read the 1st cp block in this CP pack */
- cp_page_1 = get_meta_page(sbi, cp_addr);
-
- /* get the version number */
- cp_block = (struct f2fs_checkpoint *)page_address(cp_page_1);
- crc_offset = le32_to_cpu(cp_block->checksum_offset);
- if (crc_offset >= blk_size)
+ err = get_checkpoint_version(sbi, cp_addr, &cp_block,
+ &cp_page_1, version);
+ if (err)
goto invalid_cp1;
+ pre_version = *version;
- crc = le32_to_cpu(*((__u32 *)((unsigned char *)cp_block + crc_offset)));
- if (!f2fs_crc_valid(crc, cp_block, crc_offset))
- goto invalid_cp1;
-
- pre_version = cur_cp_version(cp_block);
-
- /* Read the 2nd cp block in this CP pack */
cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1;
- cp_page_2 = get_meta_page(sbi, cp_addr);
-
- cp_block = (struct f2fs_checkpoint *)page_address(cp_page_2);
- crc_offset = le32_to_cpu(cp_block->checksum_offset);
- if (crc_offset >= blk_size)
+ err = get_checkpoint_version(sbi, cp_addr, &cp_block,
+ &cp_page_2, version);
+ if (err)
goto invalid_cp2;
-
- crc = le32_to_cpu(*((__u32 *)((unsigned char *)cp_block + crc_offset)));
- if (!f2fs_crc_valid(crc, cp_block, crc_offset))
- goto invalid_cp2;
-
- cur_version = cur_cp_version(cp_block);
+ cur_version = *version;
if (cur_version == pre_version) {
*version = cur_version;
@@ -573,7 +736,7 @@
unsigned long blk_size = sbi->blocksize;
unsigned long long cp1_version = 0, cp2_version = 0;
unsigned long long cp_start_blk_no;
- unsigned int cp_blks = 1 + le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
+ unsigned int cp_blks = 1 + __cp_payload(sbi);
block_t cp_blk_no;
int i;
@@ -608,6 +771,15 @@
cp_block = (struct f2fs_checkpoint *)page_address(cur_page);
memcpy(sbi->ckpt, cp_block, blk_size);
+ /* Sanity checking of checkpoint */
+ if (sanity_check_ckpt(sbi))
+ goto free_fail_no_cp;
+
+ if (cur_page == cp1)
+ sbi->cur_cp_pack = 1;
+ else
+ sbi->cur_cp_pack = 2;
+
if (cp_blks <= 1)
goto done;
@@ -629,118 +801,104 @@
f2fs_put_page(cp2, 1);
return 0;
+free_fail_no_cp:
+ f2fs_put_page(cp1, 1);
+ f2fs_put_page(cp2, 1);
fail_no_cp:
kfree(sbi->ckpt);
return -EINVAL;
}
-static int __add_dirty_inode(struct inode *inode, struct dir_inode_entry *new)
+static void __add_dirty_inode(struct inode *inode, enum inode_type type)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ int flag = (type == DIR_INODE) ? FI_DIRTY_DIR : FI_DIRTY_FILE;
- if (is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR))
- return -EEXIST;
+ if (is_inode_flag_set(inode, flag))
+ return;
- set_inode_flag(F2FS_I(inode), FI_DIRTY_DIR);
- F2FS_I(inode)->dirty_dir = new;
- list_add_tail(&new->list, &sbi->dir_inode_list);
- stat_inc_dirty_dir(sbi);
- return 0;
+ set_inode_flag(inode, flag);
+ if (!f2fs_is_volatile_file(inode))
+ list_add_tail(&F2FS_I(inode)->dirty_list,
+ &sbi->inode_list[type]);
+ stat_inc_dirty_inode(sbi, type);
+}
+
+static void __remove_dirty_inode(struct inode *inode, enum inode_type type)
+{
+ int flag = (type == DIR_INODE) ? FI_DIRTY_DIR : FI_DIRTY_FILE;
+
+ if (get_dirty_pages(inode) || !is_inode_flag_set(inode, flag))
+ return;
+
+ list_del_init(&F2FS_I(inode)->dirty_list);
+ clear_inode_flag(inode, flag);
+ stat_dec_dirty_inode(F2FS_I_SB(inode), type);
}
void update_dirty_page(struct inode *inode, struct page *page)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct dir_inode_entry *new;
- int ret = 0;
+ enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE;
- if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode))
+ if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
+ !S_ISLNK(inode->i_mode))
return;
- if (!S_ISDIR(inode->i_mode)) {
- inode_inc_dirty_pages(inode);
- goto out;
- }
-
- new = f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
- new->inode = inode;
- INIT_LIST_HEAD(&new->list);
-
- spin_lock(&sbi->dir_inode_lock);
- ret = __add_dirty_inode(inode, new);
+ spin_lock(&sbi->inode_lock[type]);
+ if (type != FILE_INODE || test_opt(sbi, DATA_FLUSH))
+ __add_dirty_inode(inode, type);
inode_inc_dirty_pages(inode);
- spin_unlock(&sbi->dir_inode_lock);
+ spin_unlock(&sbi->inode_lock[type]);
- if (ret)
- kmem_cache_free(inode_entry_slab, new);
-out:
SetPagePrivate(page);
+ f2fs_trace_pid(page);
}
-void add_dirty_dir_inode(struct inode *inode)
+void remove_dirty_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct dir_inode_entry *new =
- f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
- int ret = 0;
+ enum inode_type type = S_ISDIR(inode->i_mode) ? DIR_INODE : FILE_INODE;
- new->inode = inode;
- INIT_LIST_HEAD(&new->list);
-
- spin_lock(&sbi->dir_inode_lock);
- ret = __add_dirty_inode(inode, new);
- spin_unlock(&sbi->dir_inode_lock);
-
- if (ret)
- kmem_cache_free(inode_entry_slab, new);
-}
-
-void remove_dirty_dir_inode(struct inode *inode)
-{
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct dir_inode_entry *entry;
-
- if (!S_ISDIR(inode->i_mode))
+ if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
+ !S_ISLNK(inode->i_mode))
return;
- spin_lock(&sbi->dir_inode_lock);
- if (get_dirty_pages(inode) ||
- !is_inode_flag_set(F2FS_I(inode), FI_DIRTY_DIR)) {
- spin_unlock(&sbi->dir_inode_lock);
+ if (type == FILE_INODE && !test_opt(sbi, DATA_FLUSH))
return;
- }
- entry = F2FS_I(inode)->dirty_dir;
- list_del(&entry->list);
- F2FS_I(inode)->dirty_dir = NULL;
- clear_inode_flag(F2FS_I(inode), FI_DIRTY_DIR);
- stat_dec_dirty_dir(sbi);
- spin_unlock(&sbi->dir_inode_lock);
- kmem_cache_free(inode_entry_slab, entry);
-
- /* Only from the recovery routine */
- if (is_inode_flag_set(F2FS_I(inode), FI_DELAY_IPUT)) {
- clear_inode_flag(F2FS_I(inode), FI_DELAY_IPUT);
- iput(inode);
- }
+ spin_lock(&sbi->inode_lock[type]);
+ __remove_dirty_inode(inode, type);
+ spin_unlock(&sbi->inode_lock[type]);
}
-void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi)
+int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
{
struct list_head *head;
- struct dir_inode_entry *entry;
struct inode *inode;
-retry:
- spin_lock(&sbi->dir_inode_lock);
+ struct f2fs_inode_info *fi;
+ bool is_dir = (type == DIR_INODE);
- head = &sbi->dir_inode_list;
+ trace_f2fs_sync_dirty_inodes_enter(sbi->sb, is_dir,
+ get_pages(sbi, is_dir ?
+ F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
+retry:
+ if (unlikely(f2fs_cp_error(sbi)))
+ return -EIO;
+
+ spin_lock(&sbi->inode_lock[type]);
+
+ head = &sbi->inode_list[type];
if (list_empty(head)) {
- spin_unlock(&sbi->dir_inode_lock);
- return;
+ spin_unlock(&sbi->inode_lock[type]);
+ trace_f2fs_sync_dirty_inodes_exit(sbi->sb, is_dir,
+ get_pages(sbi, is_dir ?
+ F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
+ return 0;
}
- entry = list_entry(head->next, struct dir_inode_entry, list);
- inode = igrab(entry->inode);
- spin_unlock(&sbi->dir_inode_lock);
+ fi = list_first_entry(head, struct f2fs_inode_info, dirty_list);
+ inode = igrab(&fi->vfs_inode);
+ spin_unlock(&sbi->inode_lock[type]);
if (inode) {
filemap_fdatawrite(inode->i_mapping);
iput(inode);
@@ -750,10 +908,56 @@
* wribacking dentry pages in the freeing inode.
*/
f2fs_submit_merged_bio(sbi, DATA, WRITE);
+ cond_resched();
}
goto retry;
}
+int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
+{
+ struct list_head *head = &sbi->inode_list[DIRTY_META];
+ struct inode *inode;
+ struct f2fs_inode_info *fi;
+ s64 total = get_pages(sbi, F2FS_DIRTY_IMETA);
+
+ while (total--) {
+ if (unlikely(f2fs_cp_error(sbi)))
+ return -EIO;
+
+ spin_lock(&sbi->inode_lock[DIRTY_META]);
+ if (list_empty(head)) {
+ spin_unlock(&sbi->inode_lock[DIRTY_META]);
+ return 0;
+ }
+ fi = list_first_entry(head, struct f2fs_inode_info,
+ gdirty_list);
+ inode = igrab(&fi->vfs_inode);
+ spin_unlock(&sbi->inode_lock[DIRTY_META]);
+ if (inode) {
+ sync_inode_metadata(inode, 0);
+
+ /* it's on eviction */
+ if (is_inode_flag_set(inode, FI_DIRTY_INODE))
+ update_inode_page(inode);
+ iput(inode);
+ }
+ };
+ return 0;
+}
+
+static void __prepare_cp_block(struct f2fs_sb_info *sbi)
+{
+ struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ nid_t last_nid = nm_i->next_scan_nid;
+
+ next_free_nid(sbi, &last_nid);
+ ckpt->valid_block_count = cpu_to_le64(valid_user_blocks(sbi));
+ ckpt->valid_node_count = cpu_to_le32(valid_node_count(sbi));
+ ckpt->valid_inode_count = cpu_to_le32(valid_inode_count(sbi));
+ ckpt->next_free_nid = cpu_to_le32(last_nid);
+}
+
/*
* Freeze all the FS-operations for checkpoint.
*/
@@ -774,31 +978,50 @@
/* write all the dirty dentry pages */
if (get_pages(sbi, F2FS_DIRTY_DENTS)) {
f2fs_unlock_all(sbi);
- sync_dirty_dir_inodes(sbi);
- if (unlikely(f2fs_cp_error(sbi))) {
- err = -EIO;
+ err = sync_dirty_inodes(sbi, DIR_INODE);
+ if (err)
goto out;
- }
+ cond_resched();
goto retry_flush_dents;
}
/*
* POR: we should ensure that there are no dirty node pages
- * until finishing nat/sit flush.
+ * until finishing nat/sit flush. inode->i_blocks can be updated.
*/
+ down_write(&sbi->node_change);
+
+ if (get_pages(sbi, F2FS_DIRTY_IMETA)) {
+ up_write(&sbi->node_change);
+ f2fs_unlock_all(sbi);
+ err = f2fs_sync_inode_meta(sbi);
+ if (err)
+ goto out;
+ cond_resched();
+ goto retry_flush_dents;
+ }
+
retry_flush_nodes:
down_write(&sbi->node_write);
if (get_pages(sbi, F2FS_DIRTY_NODES)) {
up_write(&sbi->node_write);
- sync_node_pages(sbi, 0, &wbc);
- if (unlikely(f2fs_cp_error(sbi))) {
+ err = sync_node_pages(sbi, &wbc);
+ if (err) {
+ up_write(&sbi->node_change);
f2fs_unlock_all(sbi);
- err = -EIO;
goto out;
}
+ cond_resched();
goto retry_flush_nodes;
}
+
+ /*
+ * sbi->node_change is used only for AIO write_begin path which produces
+ * dirty node blocks and some checkpoint values by block allocation.
+ */
+ __prepare_cp_block(sbi);
+ up_write(&sbi->node_change);
out:
blk_finish_plug(&plug);
return err;
@@ -817,49 +1040,79 @@
for (;;) {
prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE);
- if (!get_pages(sbi, F2FS_WRITEBACK))
+ if (!get_pages(sbi, F2FS_WB_CP_DATA))
break;
- io_schedule();
+ io_schedule_timeout(5*HZ);
}
finish_wait(&sbi->cp_wait, &wait);
}
-static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
+static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
+{
+ unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num;
+ struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+
+ spin_lock(&sbi->cp_lock);
+
+ if ((cpc->reason & CP_UMOUNT) &&
+ le32_to_cpu(ckpt->cp_pack_total_block_count) >
+ sbi->blocks_per_seg - NM_I(sbi)->nat_bits_blocks)
+ disable_nat_bits(sbi, false);
+
+ if (cpc->reason & CP_TRIMMED)
+ __set_ckpt_flags(ckpt, CP_TRIMMED_FLAG);
+
+ if (cpc->reason & CP_UMOUNT)
+ __set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+ else
+ __clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+
+ if (cpc->reason & CP_FASTBOOT)
+ __set_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
+ else
+ __clear_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
+
+ if (orphan_num)
+ __set_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
+ else
+ __clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
+
+ if (is_sbi_flag_set(sbi, SBI_NEED_FSCK))
+ __set_ckpt_flags(ckpt, CP_FSCK_FLAG);
+
+ /* set this flag to activate crc|cp_ver for recovery */
+ __set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG);
+
+ spin_unlock(&sbi->cp_lock);
+}
+
+static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
- struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
struct f2fs_nm_info *nm_i = NM_I(sbi);
- nid_t last_nid = nm_i->next_scan_nid;
+ unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num;
block_t start_blk;
- struct page *cp_page;
unsigned int data_sum_blocks, orphan_blocks;
__u32 crc32 = 0;
- void *kaddr;
int i;
- int cp_payload_blks = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
-
- /*
- * This avoids to conduct wrong roll-forward operations and uses
- * metapages, so should be called prior to sync_meta_pages below.
- */
- discard_next_dnode(sbi, NEXT_FREE_BLKADDR(sbi, curseg));
+ int cp_payload_blks = __cp_payload(sbi);
+ struct super_block *sb = sbi->sb;
+ struct curseg_info *seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
+ u64 kbytes_written;
/* Flush all the NAT/SIT pages */
while (get_pages(sbi, F2FS_DIRTY_META)) {
sync_meta_pages(sbi, META, LONG_MAX);
if (unlikely(f2fs_cp_error(sbi)))
- return;
+ return -EIO;
}
- next_free_nid(sbi, &last_nid);
-
/*
* modify checkpoint
* version number is already updated
*/
ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi));
- ckpt->valid_block_count = cpu_to_le64(valid_user_blocks(sbi));
ckpt->free_segment_count = cpu_to_le32(free_segments(sbi));
for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) {
ckpt->cur_node_segno[i] =
@@ -878,136 +1131,189 @@
curseg_alloc_type(sbi, i + CURSEG_HOT_DATA);
}
- ckpt->valid_node_count = cpu_to_le32(valid_node_count(sbi));
- ckpt->valid_inode_count = cpu_to_le32(valid_inode_count(sbi));
- ckpt->next_free_nid = cpu_to_le32(last_nid);
-
/* 2 cp + n data seg summary + orphan inode blocks */
- data_sum_blocks = npages_for_summary_flush(sbi);
+ data_sum_blocks = npages_for_summary_flush(sbi, false);
+ spin_lock(&sbi->cp_lock);
if (data_sum_blocks < NR_CURSEG_DATA_TYPE)
- set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
+ __set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
else
- clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
+ __clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
+ spin_unlock(&sbi->cp_lock);
- orphan_blocks = GET_ORPHAN_BLOCKS(sbi->n_orphans);
+ orphan_blocks = GET_ORPHAN_BLOCKS(orphan_num);
ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks +
orphan_blocks);
- if (cpc->reason == CP_UMOUNT) {
- set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+ if (__remain_node_summaries(cpc->reason))
ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS+
cp_payload_blks + data_sum_blocks +
orphan_blocks + NR_CURSEG_NODE_TYPE);
- } else {
- clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
+ else
ckpt->cp_pack_total_block_count = cpu_to_le32(F2FS_CP_PACKS +
cp_payload_blks + data_sum_blocks +
orphan_blocks);
- }
- if (sbi->n_orphans)
- set_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
- else
- clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
-
- if (sbi->need_fsck)
- set_ckpt_flags(ckpt, CP_FSCK_FLAG);
+ /* update ckpt flag for checkpoint */
+ update_ckpt_flags(sbi, cpc);
/* update SIT/NAT bitmap */
get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP));
get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP));
- crc32 = f2fs_crc32(ckpt, le32_to_cpu(ckpt->checksum_offset));
+ crc32 = f2fs_crc32(sbi, ckpt, le32_to_cpu(ckpt->checksum_offset));
*((__le32 *)((unsigned char *)ckpt +
le32_to_cpu(ckpt->checksum_offset)))
= cpu_to_le32(crc32);
- start_blk = __start_cp_addr(sbi);
+ start_blk = __start_cp_next_addr(sbi);
- /* write out checkpoint buffer at block 0 */
- cp_page = grab_meta_page(sbi, start_blk++);
- kaddr = page_address(cp_page);
- memcpy(kaddr, ckpt, (1 << sbi->log_blocksize));
- set_page_dirty(cp_page);
- f2fs_put_page(cp_page, 1);
+ /* write nat bits */
+ if (enabled_nat_bits(sbi, cpc)) {
+ __u64 cp_ver = cur_cp_version(ckpt);
+ block_t blk;
- for (i = 1; i < 1 + cp_payload_blks; i++) {
- cp_page = grab_meta_page(sbi, start_blk++);
- kaddr = page_address(cp_page);
- memcpy(kaddr, (char *)ckpt + i * F2FS_BLKSIZE,
- (1 << sbi->log_blocksize));
- set_page_dirty(cp_page);
- f2fs_put_page(cp_page, 1);
+ cp_ver |= ((__u64)crc32 << 32);
+ *(__le64 *)nm_i->nat_bits = cpu_to_le64(cp_ver);
+
+ blk = start_blk + sbi->blocks_per_seg - nm_i->nat_bits_blocks;
+ for (i = 0; i < nm_i->nat_bits_blocks; i++)
+ update_meta_page(sbi, nm_i->nat_bits +
+ (i << F2FS_BLKSIZE_BITS), blk + i);
+
+ /* Flush all the NAT BITS pages */
+ while (get_pages(sbi, F2FS_DIRTY_META)) {
+ sync_meta_pages(sbi, META, LONG_MAX);
+ if (unlikely(f2fs_cp_error(sbi)))
+ return -EIO;
+ }
}
- if (sbi->n_orphans) {
+ /* need to wait for end_io results */
+ wait_on_all_pages_writeback(sbi);
+ if (unlikely(f2fs_cp_error(sbi)))
+ return -EIO;
+
+ /* write out checkpoint buffer at block 0 */
+ update_meta_page(sbi, ckpt, start_blk++);
+
+ for (i = 1; i < 1 + cp_payload_blks; i++)
+ update_meta_page(sbi, (char *)ckpt + i * F2FS_BLKSIZE,
+ start_blk++);
+
+ if (orphan_num) {
write_orphan_inodes(sbi, start_blk);
start_blk += orphan_blocks;
}
write_data_summaries(sbi, start_blk);
start_blk += data_sum_blocks;
- if (cpc->reason == CP_UMOUNT) {
+
+ /* Record write statistics in the hot node summary */
+ kbytes_written = sbi->kbytes_written;
+ if (sb->s_bdev->bd_part)
+ kbytes_written += BD_PART_WRITTEN(sbi);
+
+ seg_i->journal->info.kbytes_written = cpu_to_le64(kbytes_written);
+
+ if (__remain_node_summaries(cpc->reason)) {
write_node_summaries(sbi, start_blk);
start_blk += NR_CURSEG_NODE_TYPE;
}
/* writeout checkpoint block */
- cp_page = grab_meta_page(sbi, start_blk);
- kaddr = page_address(cp_page);
- memcpy(kaddr, ckpt, (1 << sbi->log_blocksize));
- set_page_dirty(cp_page);
- f2fs_put_page(cp_page, 1);
+ update_meta_page(sbi, ckpt, start_blk);
/* wait for previous submitted node/meta pages writeback */
wait_on_all_pages_writeback(sbi);
if (unlikely(f2fs_cp_error(sbi)))
- return;
+ return -EIO;
- filemap_fdatawait_range(NODE_MAPPING(sbi), 0, LONG_MAX);
- filemap_fdatawait_range(META_MAPPING(sbi), 0, LONG_MAX);
+ filemap_fdatawait_range(NODE_MAPPING(sbi), 0, LLONG_MAX);
+ filemap_fdatawait_range(META_MAPPING(sbi), 0, LLONG_MAX);
/* update user_block_counts */
sbi->last_valid_block_count = sbi->total_valid_block_count;
- sbi->alloc_valid_block_count = 0;
+ percpu_counter_set(&sbi->alloc_valid_block_count, 0);
/* Here, we only have one bio having CP pack */
sync_meta_pages(sbi, META_FLUSH, LONG_MAX);
- release_dirty_inode(sbi);
+ /* wait for previous submitted meta pages writeback */
+ wait_on_all_pages_writeback(sbi);
+
+ release_ino_entry(sbi, false);
if (unlikely(f2fs_cp_error(sbi)))
- return;
+ return -EIO;
- clear_prefree_segments(sbi);
- F2FS_RESET_SB_DIRT(sbi);
+ clear_sbi_flag(sbi, SBI_IS_DIRTY);
+ clear_sbi_flag(sbi, SBI_NEED_CP);
+ __set_cp_next_pack(sbi);
+
+ /*
+ * redirty superblock if metadata like node page or inode cache is
+ * updated during writing checkpoint.
+ */
+ if (get_pages(sbi, F2FS_DIRTY_NODES) ||
+ get_pages(sbi, F2FS_DIRTY_IMETA))
+ set_sbi_flag(sbi, SBI_IS_DIRTY);
+
+ f2fs_bug_on(sbi, get_pages(sbi, F2FS_DIRTY_DENTS));
+
+ return 0;
}
/*
* We guarantee that this checkpoint procedure will not fail.
*/
-void write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
+int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
unsigned long long ckpt_ver;
-
- trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "start block_ops");
+ int err = 0;
mutex_lock(&sbi->cp_mutex);
- if (!sbi->s_dirty && cpc->reason != CP_DISCARD)
+ if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) &&
+ ((cpc->reason & CP_FASTBOOT) || (cpc->reason & CP_SYNC) ||
+ ((cpc->reason & CP_DISCARD) && !sbi->discard_blks)))
goto out;
- if (unlikely(f2fs_cp_error(sbi)))
+ if (unlikely(f2fs_cp_error(sbi))) {
+ err = -EIO;
goto out;
- if (block_operations(sbi))
+ }
+ if (f2fs_readonly(sbi->sb)) {
+ err = -EROFS;
+ goto out;
+ }
+
+ trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "start block_ops");
+
+ err = block_operations(sbi);
+ if (err)
goto out;
trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish block_ops");
- f2fs_submit_merged_bio(sbi, DATA, WRITE);
- f2fs_submit_merged_bio(sbi, NODE, WRITE);
- f2fs_submit_merged_bio(sbi, META, WRITE);
+ f2fs_flush_merged_bios(sbi);
+
+ /* this is the case of multiple fstrims without any changes */
+ if (cpc->reason & CP_DISCARD) {
+ if (!exist_trim_candidates(sbi, cpc)) {
+ unblock_operations(sbi);
+ goto out;
+ }
+
+ if (NM_I(sbi)->dirty_nat_cnt == 0 &&
+ SIT_I(sbi)->dirty_sentries == 0 &&
+ prefree_segments(sbi) == 0) {
+ flush_sit_entries(sbi, cpc);
+ clear_prefree_segments(sbi, cpc);
+ unblock_operations(sbi);
+ goto out;
+ }
+ }
/*
* update checkpoint pack index
@@ -1018,17 +1324,29 @@
ckpt->checkpoint_ver = cpu_to_le64(++ckpt_ver);
/* write cached NAT/SIT entries to NAT/SIT area */
- flush_nat_entries(sbi);
+ flush_nat_entries(sbi, cpc);
flush_sit_entries(sbi, cpc);
/* unlock all the fs_lock[] in do_checkpoint() */
- do_checkpoint(sbi, cpc);
+ err = do_checkpoint(sbi, cpc);
+ if (err)
+ release_discard_addrs(sbi);
+ else
+ clear_prefree_segments(sbi, cpc);
unblock_operations(sbi);
stat_inc_cp_count(sbi->stat_info);
+
+ if (cpc->reason & CP_RECOVERY)
+ f2fs_msg(sbi->sb, KERN_NOTICE,
+ "checkpoint: version = %llx", ckpt_ver);
+
+ /* do checkpoint periodically */
+ f2fs_update_time(sbi, CP_TIME);
+ trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint");
out:
mutex_unlock(&sbi->cp_mutex);
- trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish checkpoint");
+ return err;
}
void init_ino_entry_info(struct f2fs_sb_info *sbi)
@@ -1036,20 +1354,17 @@
int i;
for (i = 0; i < MAX_INO_ENTRY; i++) {
- INIT_RADIX_TREE(&sbi->ino_root[i], GFP_ATOMIC);
- spin_lock_init(&sbi->ino_lock[i]);
- INIT_LIST_HEAD(&sbi->ino_list[i]);
+ struct inode_management *im = &sbi->im[i];
+
+ INIT_RADIX_TREE(&im->ino_root, GFP_ATOMIC);
+ spin_lock_init(&im->ino_lock);
+ INIT_LIST_HEAD(&im->ino_list);
+ im->ino_num = 0;
}
- /*
- * considering 512 blocks in a segment 8 blocks are needed for cp
- * and log segment summaries. Remaining blocks are used to keep
- * orphan entries with the limitation one reserved segment
- * for cp pack we can have max 1020*504 orphan entries
- */
- sbi->n_orphans = 0;
sbi->max_orphans = (sbi->blocks_per_seg - F2FS_CP_PACKS -
- NR_CURSEG_TYPE) * F2FS_ORPHANS_PER_BLOCK;
+ NR_CURSEG_TYPE - __cp_payload(sbi)) *
+ F2FS_ORPHANS_PER_BLOCK;
}
int __init create_checkpoint_caches(void)
@@ -1058,8 +1373,8 @@
sizeof(struct ino_entry));
if (!ino_entry_slab)
return -ENOMEM;
- inode_entry_slab = f2fs_kmem_cache_create("f2fs_dirty_dir_entry",
- sizeof(struct dir_inode_entry));
+ inode_entry_slab = f2fs_kmem_cache_create("f2fs_inode_entry",
+ sizeof(struct inode_entry));
if (!inode_entry_slab) {
kmem_cache_destroy(ino_entry_slab);
return -ENOMEM;
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 5d09ea57..dd97cbe 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -15,26 +15,69 @@
#include <linux/aio.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
+#include <linux/pagevec.h>
#include <linux/blkdev.h>
#include <linux/bio.h>
#include <linux/prefetch.h>
+#include <linux/uio.h>
+#include <linux/mm.h>
+#include <linux/memcontrol.h>
+#include <linux/cleancache.h>
#include "f2fs.h"
#include "node.h"
#include "segment.h"
+#include "trace.h"
#include <trace/events/f2fs.h>
#include <trace/events/android_fs.h>
+static bool __is_cp_guaranteed(struct page *page)
+{
+ struct address_space *mapping = page->mapping;
+ struct inode *inode;
+ struct f2fs_sb_info *sbi;
+
+ if (!mapping)
+ return false;
+
+ inode = mapping->host;
+ sbi = F2FS_I_SB(inode);
+
+ if (inode->i_ino == F2FS_META_INO(sbi) ||
+ inode->i_ino == F2FS_NODE_INO(sbi) ||
+ S_ISDIR(inode->i_mode) ||
+ is_cold_data(page))
+ return true;
+ return false;
+}
+
static void f2fs_read_end_io(struct bio *bio, int err)
{
struct bio_vec *bvec;
int i;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(F2FS_P_SB(bio->bi_io_vec->bv_page), FAULT_IO)) {
+ f2fs_show_injection_info(FAULT_IO);
+ err = -EIO;
+ }
+#endif
+
+ if (f2fs_bio_encrypted(bio)) {
+ if (err) {
+ fscrypt_release_ctx(bio->bi_private);
+ } else {
+ fscrypt_decrypt_bio_pages(bio->bi_private, bio);
+ return;
+ }
+ }
+
bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
if (!err) {
- SetPageUptodate(page);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
} else {
ClearPageUptodate(page);
SetPageError(page);
@@ -52,29 +95,77 @@
bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
+ enum count_type type = WB_DATA_TYPE(page);
+
+ if (IS_DUMMY_WRITTEN_PAGE(page)) {
+ set_page_private(page, (unsigned long)NULL);
+ ClearPagePrivate(page);
+ unlock_page(page);
+ mempool_free(page, sbi->write_io_dummy);
+
+ if (unlikely(err))
+ f2fs_stop_checkpoint(sbi, true);
+ continue;
+ }
+
+ fscrypt_pullback_bio_page(&page, true);
if (unlikely(err)) {
- set_page_dirty(page);
set_bit(AS_EIO, &page->mapping->flags);
- f2fs_stop_checkpoint(sbi);
+ f2fs_stop_checkpoint(sbi, true);
}
+ dec_page_count(sbi, type);
+ clear_cold_data(page);
end_page_writeback(page);
- dec_page_count(sbi, F2FS_WRITEBACK);
}
-
- if (sbi->wait_io) {
- complete(sbi->wait_io);
- sbi->wait_io = NULL;
- }
-
- if (!get_pages(sbi, F2FS_WRITEBACK) &&
- !list_empty(&sbi->cp_wait.task_list))
+ if (!get_pages(sbi, F2FS_WB_CP_DATA) &&
+ wq_has_sleeper(&sbi->cp_wait))
wake_up(&sbi->cp_wait);
bio_put(bio);
}
/*
+ * Return true, if pre_bio's bdev is same as its target device.
+ */
+struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
+ block_t blk_addr, struct bio *bio)
+{
+ struct block_device *bdev = sbi->sb->s_bdev;
+ int i;
+
+ for (i = 0; i < sbi->s_ndevs; i++) {
+ if (FDEV(i).start_blk <= blk_addr &&
+ FDEV(i).end_blk >= blk_addr) {
+ blk_addr -= FDEV(i).start_blk;
+ bdev = FDEV(i).bdev;
+ break;
+ }
+ }
+ if (bio) {
+ bio->bi_bdev = bdev;
+ bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blk_addr);
+ }
+ return bdev;
+}
+
+int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr)
+{
+ int i;
+
+ for (i = 0; i < sbi->s_ndevs; i++)
+ if (FDEV(i).start_blk <= blkaddr && FDEV(i).end_blk >= blkaddr)
+ return i;
+ return 0;
+}
+
+static bool __same_bdev(struct f2fs_sb_info *sbi,
+ block_t blk_addr, struct bio *bio)
+{
+ return f2fs_target_device(sbi, blk_addr, NULL) == bio->bi_bdev;
+}
+
+/*
* Low-level block read/write IO operations.
*/
static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
@@ -82,52 +173,127 @@
{
struct bio *bio;
- /* No failure on bio allocation */
- bio = bio_alloc(GFP_NOIO, npages);
+ bio = f2fs_bio_alloc(npages);
- bio->bi_bdev = sbi->sb->s_bdev;
- bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blk_addr);
+ f2fs_target_device(sbi, blk_addr, bio);
bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io;
- bio->bi_private = sbi;
+ bio->bi_private = is_read ? NULL : sbi;
return bio;
}
+static inline void __submit_bio(struct f2fs_sb_info *sbi,
+ struct bio *bio, enum page_type type)
+{
+ if (!is_read_io(bio_op(bio))) {
+ unsigned int start;
+
+ if (f2fs_sb_mounted_blkzoned(sbi->sb) &&
+ current->plug && (type == DATA || type == NODE))
+ blk_finish_plug(current->plug);
+
+ if (type != DATA && type != NODE)
+ goto submit_io;
+
+ start = bio->bi_iter.bi_size >> F2FS_BLKSIZE_BITS;
+ start %= F2FS_IO_SIZE(sbi);
+
+ if (start == 0)
+ goto submit_io;
+
+ /* fill dummy pages */
+ for (; start < F2FS_IO_SIZE(sbi); start++) {
+ struct page *page =
+ mempool_alloc(sbi->write_io_dummy,
+ GFP_NOIO | __GFP_ZERO | __GFP_NOFAIL);
+ f2fs_bug_on(sbi, !page);
+
+ SetPagePrivate(page);
+ set_page_private(page, (unsigned long)DUMMY_WRITTEN_PAGE);
+ lock_page(page);
+ if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE)
+ f2fs_bug_on(sbi, 1);
+ }
+ /*
+ * In the NODE case, we lose next block address chain. So, we
+ * need to do checkpoint in f2fs_sync_file.
+ */
+ if (type == NODE)
+ set_sbi_flag(sbi, SBI_NEED_CP);
+ }
+submit_io:
+ if (is_read_io(bio_op(bio)))
+ trace_f2fs_submit_read_bio(sbi->sb, type, bio);
+ else
+ trace_f2fs_submit_write_bio(sbi->sb, type, bio);
+ submit_bio(0, bio);
+}
+
static void __submit_merged_bio(struct f2fs_bio_info *io)
{
struct f2fs_io_info *fio = &io->fio;
- int rw;
if (!io->bio)
return;
- rw = fio->rw;
+ bio_set_op_attrs(io->bio, fio->op, fio->op_flags);
- if (is_read_io(rw)) {
- trace_f2fs_submit_read_bio(io->sbi->sb, rw,
- fio->type, io->bio);
- submit_bio(rw, io->bio);
- } else {
- trace_f2fs_submit_write_bio(io->sbi->sb, rw,
- fio->type, io->bio);
- /*
- * META_FLUSH is only from the checkpoint procedure, and we
- * should wait this metadata bio for FS consistency.
- */
- if (fio->type == META_FLUSH) {
- DECLARE_COMPLETION_ONSTACK(wait);
- io->sbi->wait_io = &wait;
- submit_bio(rw, io->bio);
- wait_for_completion(&wait);
- } else {
- submit_bio(rw, io->bio);
- }
- }
+ if (is_read_io(fio->op))
+ trace_f2fs_prepare_read_bio(io->sbi->sb, fio->type, io->bio);
+ else
+ trace_f2fs_prepare_write_bio(io->sbi->sb, fio->type, io->bio);
+ __submit_bio(io->sbi, io->bio, fio->type);
io->bio = NULL;
}
-void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
+static bool __has_merged_page(struct f2fs_bio_info *io,
+ struct inode *inode, nid_t ino, pgoff_t idx)
+{
+ struct bio_vec *bvec;
+ struct page *target;
+ int i;
+
+ if (!io->bio)
+ return false;
+
+ if (!inode && !ino)
+ return true;
+
+ bio_for_each_segment_all(bvec, io->bio, i) {
+
+ if (bvec->bv_page->mapping)
+ target = bvec->bv_page;
+ else
+ target = fscrypt_control_page(bvec->bv_page);
+
+ if (idx != target->index)
+ continue;
+
+ if (inode && inode == target->mapping->host)
+ return true;
+ if (ino && ino == ino_of_node(target))
+ return true;
+ }
+
+ return false;
+}
+
+static bool has_merged_page(struct f2fs_sb_info *sbi, struct inode *inode,
+ nid_t ino, pgoff_t idx, enum page_type type)
+{
+ enum page_type btype = PAGE_TYPE_OF_BIO(type);
+ struct f2fs_bio_info *io = &sbi->write_io[btype];
+ bool ret;
+
+ down_read(&io->io_rwsem);
+ ret = __has_merged_page(io, inode, ino, idx);
+ up_read(&io->io_rwsem);
+ return ret;
+}
+
+static void __f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
+ struct inode *inode, nid_t ino, pgoff_t idx,
enum page_type type, int rw)
{
enum page_type btype = PAGE_TYPE_OF_BIO(type);
@@ -137,79 +303,137 @@
down_write(&io->io_rwsem);
+ if (!__has_merged_page(io, inode, ino, idx))
+ goto out;
+
/* change META to META_FLUSH in the checkpoint procedure */
if (type >= META_FLUSH) {
io->fio.type = META_FLUSH;
- if (test_opt(sbi, NOBARRIER))
- io->fio.rw = WRITE_FLUSH | REQ_META | REQ_PRIO;
- else
- io->fio.rw = WRITE_FLUSH_FUA | REQ_META | REQ_PRIO;
+ io->fio.op = REQ_OP_WRITE;
+ io->fio.op_flags = REQ_META | REQ_PRIO;
+ if (!test_opt(sbi, NOBARRIER))
+ io->fio.op_flags |= WRITE_FLUSH | REQ_FUA;
}
__submit_merged_bio(io);
+out:
up_write(&io->io_rwsem);
}
+void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, enum page_type type,
+ int rw)
+{
+ __f2fs_submit_merged_bio(sbi, NULL, 0, 0, type, rw);
+}
+
+void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *sbi,
+ struct inode *inode, nid_t ino, pgoff_t idx,
+ enum page_type type, int rw)
+{
+ if (has_merged_page(sbi, inode, ino, idx, type))
+ __f2fs_submit_merged_bio(sbi, inode, ino, idx, type, rw);
+}
+
+void f2fs_flush_merged_bios(struct f2fs_sb_info *sbi)
+{
+ f2fs_submit_merged_bio(sbi, DATA, WRITE);
+ f2fs_submit_merged_bio(sbi, NODE, WRITE);
+ f2fs_submit_merged_bio(sbi, META, WRITE);
+}
+
/*
* Fill the locked page with data located in the block address.
- * Return unlocked page.
+ * A caller needs to unlock the page on failure.
*/
-int f2fs_submit_page_bio(struct f2fs_sb_info *sbi, struct page *page,
- block_t blk_addr, int rw)
+int f2fs_submit_page_bio(struct f2fs_io_info *fio)
{
struct bio *bio;
+ struct page *page = fio->encrypted_page ?
+ fio->encrypted_page : fio->page;
- trace_f2fs_submit_page_bio(page, blk_addr, rw);
+ trace_f2fs_submit_page_bio(page, fio);
+ f2fs_trace_ios(fio, 0);
/* Allocate a new bio */
- bio = __bio_alloc(sbi, blk_addr, 1, is_read_io(rw));
+ bio = __bio_alloc(fio->sbi, fio->new_blkaddr, 1, is_read_io(fio->op));
- if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) {
+ if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
bio_put(bio);
- f2fs_put_page(page, 1);
return -EFAULT;
}
+ bio_set_op_attrs(bio, fio->op, fio->op_flags);
- submit_bio(rw, bio);
+ __submit_bio(fio->sbi, bio, fio->type);
+
+ if (!is_read_io(fio->op))
+ inc_page_count(fio->sbi, WB_DATA_TYPE(fio->page));
return 0;
}
-void f2fs_submit_page_mbio(struct f2fs_sb_info *sbi, struct page *page,
- block_t blk_addr, struct f2fs_io_info *fio)
+int f2fs_submit_page_mbio(struct f2fs_io_info *fio)
{
+ struct f2fs_sb_info *sbi = fio->sbi;
enum page_type btype = PAGE_TYPE_OF_BIO(fio->type);
struct f2fs_bio_info *io;
- bool is_read = is_read_io(fio->rw);
+ bool is_read = is_read_io(fio->op);
+ struct page *bio_page;
+ int err = 0;
io = is_read ? &sbi->read_io : &sbi->write_io[btype];
- verify_block_addr(sbi, blk_addr);
+ if (fio->old_blkaddr != NEW_ADDR)
+ verify_block_addr(sbi, fio->old_blkaddr);
+ verify_block_addr(sbi, fio->new_blkaddr);
+
+ bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page;
+
+ /* set submitted = 1 as a return value */
+ fio->submitted = 1;
+
+ if (!is_read)
+ inc_page_count(sbi, WB_DATA_TYPE(bio_page));
down_write(&io->io_rwsem);
- if (!is_read)
- inc_page_count(sbi, F2FS_WRITEBACK);
-
- if (io->bio && (io->last_block_in_bio != blk_addr - 1 ||
- io->fio.rw != fio->rw))
+ if (io->bio && (io->last_block_in_bio != fio->new_blkaddr - 1 ||
+ (io->fio.op != fio->op || io->fio.op_flags != fio->op_flags) ||
+ !__same_bdev(sbi, fio->new_blkaddr, io->bio)))
__submit_merged_bio(io);
alloc_new:
if (io->bio == NULL) {
- int bio_blocks = MAX_BIO_BLOCKS(sbi);
-
- io->bio = __bio_alloc(sbi, blk_addr, bio_blocks, is_read);
+ if ((fio->type == DATA || fio->type == NODE) &&
+ fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) {
+ err = -EAGAIN;
+ if (!is_read)
+ dec_page_count(sbi, WB_DATA_TYPE(bio_page));
+ goto out_fail;
+ }
+ io->bio = __bio_alloc(sbi, fio->new_blkaddr,
+ BIO_MAX_PAGES, is_read);
io->fio = *fio;
}
- if (bio_add_page(io->bio, page, PAGE_CACHE_SIZE, 0) <
- PAGE_CACHE_SIZE) {
+ if (bio_add_page(io->bio, bio_page, PAGE_SIZE, 0) <
+ PAGE_SIZE) {
__submit_merged_bio(io);
goto alloc_new;
}
- io->last_block_in_bio = blk_addr;
-
+ io->last_block_in_bio = fio->new_blkaddr;
+ f2fs_trace_ios(fio, 0);
+out_fail:
up_write(&io->io_rwsem);
- trace_f2fs_submit_page_mbio(page, fio->rw, fio->type, blk_addr);
+ trace_f2fs_submit_page_mbio(fio->page, fio);
+ return err;
+}
+
+static void __set_data_blkaddr(struct dnode_of_data *dn)
+{
+ struct f2fs_node *rn = F2FS_NODE(dn->node_page);
+ __le32 *addr_array;
+
+ /* Get physical address of data block */
+ addr_array = blkaddr_in_node(rn);
+ addr_array[dn->ofs_in_node] = cpu_to_le32(dn->data_blkaddr);
}
/*
@@ -218,49 +442,70 @@
* ->node_page
* update block addresses in the node page
*/
-static void __set_data_blkaddr(struct dnode_of_data *dn, block_t new_addr)
+void set_data_blkaddr(struct dnode_of_data *dn)
{
- struct f2fs_node *rn;
- __le32 *addr_array;
- struct page *node_page = dn->node_page;
- unsigned int ofs_in_node = dn->ofs_in_node;
-
- f2fs_wait_on_page_writeback(node_page, NODE);
-
- rn = F2FS_NODE(node_page);
-
- /* Get physical address of data block */
- addr_array = blkaddr_in_node(rn);
- addr_array[ofs_in_node] = cpu_to_le32(new_addr);
- set_page_dirty(node_page);
+ f2fs_wait_on_page_writeback(dn->node_page, NODE, true);
+ __set_data_blkaddr(dn);
+ if (set_page_dirty(dn->node_page))
+ dn->node_changed = true;
}
-int reserve_new_block(struct dnode_of_data *dn)
+void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr)
+{
+ dn->data_blkaddr = blkaddr;
+ set_data_blkaddr(dn);
+ f2fs_update_extent_cache(dn);
+}
+
+/* dn->ofs_in_node will be returned with up-to-date last block pointer */
+int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
- if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
+ if (!count)
+ return 0;
+
+ if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
return -EPERM;
- if (unlikely(!inc_valid_block_count(sbi, dn->inode, 1)))
+ if (unlikely(!inc_valid_block_count(sbi, dn->inode, &count)))
return -ENOSPC;
- trace_f2fs_reserve_new_block(dn->inode, dn->nid, dn->ofs_in_node);
+ trace_f2fs_reserve_new_blocks(dn->inode, dn->nid,
+ dn->ofs_in_node, count);
- __set_data_blkaddr(dn, NEW_ADDR);
- dn->data_blkaddr = NEW_ADDR;
- mark_inode_dirty(dn->inode);
- sync_inode_page(dn);
+ f2fs_wait_on_page_writeback(dn->node_page, NODE, true);
+
+ for (; count > 0; dn->ofs_in_node++) {
+ block_t blkaddr =
+ datablock_addr(dn->node_page, dn->ofs_in_node);
+ if (blkaddr == NULL_ADDR) {
+ dn->data_blkaddr = NEW_ADDR;
+ __set_data_blkaddr(dn);
+ count--;
+ }
+ }
+
+ if (set_page_dirty(dn->node_page))
+ dn->node_changed = true;
return 0;
}
+/* Should keep dn->ofs_in_node unchanged */
+int reserve_new_block(struct dnode_of_data *dn)
+{
+ unsigned int ofs_in_node = dn->ofs_in_node;
+ int ret;
+
+ ret = reserve_new_blocks(dn, 1);
+ dn->ofs_in_node = ofs_in_node;
+ return ret;
+}
+
int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index)
{
bool need_put = dn->inode_page ? false : true;
int err;
- /* if inode_page exists, index should be zero */
- f2fs_bug_on(F2FS_I_SB(dn->inode), !need_put && index);
-
err = get_dnode_of_data(dn, index, ALLOC_NODE);
if (err)
return err;
@@ -272,174 +517,110 @@
return err;
}
-static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
- struct buffer_head *bh_result)
+int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index)
{
- struct f2fs_inode_info *fi = F2FS_I(inode);
- pgoff_t start_fofs, end_fofs;
- block_t start_blkaddr;
+ struct extent_info ei = {0,0,0};
+ struct inode *inode = dn->inode;
- if (is_inode_flag_set(fi, FI_NO_EXTENT))
- return 0;
-
- read_lock(&fi->ext.ext_lock);
- if (fi->ext.len == 0) {
- read_unlock(&fi->ext.ext_lock);
+ if (f2fs_lookup_extent_cache(inode, index, &ei)) {
+ dn->data_blkaddr = ei.blk + index - ei.fofs;
return 0;
}
- stat_inc_total_hit(inode->i_sb);
-
- start_fofs = fi->ext.fofs;
- end_fofs = fi->ext.fofs + fi->ext.len - 1;
- start_blkaddr = fi->ext.blk_addr;
-
- if (pgofs >= start_fofs && pgofs <= end_fofs) {
- unsigned int blkbits = inode->i_sb->s_blocksize_bits;
- size_t count;
-
- clear_buffer_new(bh_result);
- map_bh(bh_result, inode->i_sb,
- start_blkaddr + pgofs - start_fofs);
- count = end_fofs - pgofs + 1;
- if (count < (UINT_MAX >> blkbits))
- bh_result->b_size = (count << blkbits);
- else
- bh_result->b_size = UINT_MAX;
-
- stat_inc_read_hit(inode->i_sb);
- read_unlock(&fi->ext.ext_lock);
- return 1;
- }
- read_unlock(&fi->ext.ext_lock);
- return 0;
+ return f2fs_reserve_block(dn, index);
}
-void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn)
-{
- struct f2fs_inode_info *fi = F2FS_I(dn->inode);
- pgoff_t fofs, start_fofs, end_fofs;
- block_t start_blkaddr, end_blkaddr;
- int need_update = true;
-
- f2fs_bug_on(F2FS_I_SB(dn->inode), blk_addr == NEW_ADDR);
- fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
- dn->ofs_in_node;
-
- /* Update the page address in the parent node */
- __set_data_blkaddr(dn, blk_addr);
-
- if (is_inode_flag_set(fi, FI_NO_EXTENT))
- return;
-
- write_lock(&fi->ext.ext_lock);
-
- start_fofs = fi->ext.fofs;
- end_fofs = fi->ext.fofs + fi->ext.len - 1;
- start_blkaddr = fi->ext.blk_addr;
- end_blkaddr = fi->ext.blk_addr + fi->ext.len - 1;
-
- /* Drop and initialize the matched extent */
- if (fi->ext.len == 1 && fofs == start_fofs)
- fi->ext.len = 0;
-
- /* Initial extent */
- if (fi->ext.len == 0) {
- if (blk_addr != NULL_ADDR) {
- fi->ext.fofs = fofs;
- fi->ext.blk_addr = blk_addr;
- fi->ext.len = 1;
- }
- goto end_update;
- }
-
- /* Front merge */
- if (fofs == start_fofs - 1 && blk_addr == start_blkaddr - 1) {
- fi->ext.fofs--;
- fi->ext.blk_addr--;
- fi->ext.len++;
- goto end_update;
- }
-
- /* Back merge */
- if (fofs == end_fofs + 1 && blk_addr == end_blkaddr + 1) {
- fi->ext.len++;
- goto end_update;
- }
-
- /* Split the existing extent */
- if (fi->ext.len > 1 &&
- fofs >= start_fofs && fofs <= end_fofs) {
- if ((end_fofs - fofs) < (fi->ext.len >> 1)) {
- fi->ext.len = fofs - start_fofs;
- } else {
- fi->ext.fofs = fofs + 1;
- fi->ext.blk_addr = start_blkaddr +
- fofs - start_fofs + 1;
- fi->ext.len -= fofs - start_fofs + 1;
- }
- } else {
- need_update = false;
- }
-
- /* Finally, if the extent is very fragmented, let's drop the cache. */
- if (fi->ext.len < F2FS_MIN_EXTENT_LEN) {
- fi->ext.len = 0;
- set_inode_flag(fi, FI_NO_EXTENT);
- need_update = true;
- }
-end_update:
- write_unlock(&fi->ext.ext_lock);
- if (need_update)
- sync_inode_page(dn);
- return;
-}
-
-struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
+struct page *get_read_data_page(struct inode *inode, pgoff_t index,
+ int op_flags, bool for_write)
{
struct address_space *mapping = inode->i_mapping;
struct dnode_of_data dn;
struct page *page;
+ struct extent_info ei = {0,0,0};
int err;
+ struct f2fs_io_info fio = {
+ .sbi = F2FS_I_SB(inode),
+ .type = DATA,
+ .op = REQ_OP_READ,
+ .op_flags = op_flags,
+ .encrypted_page = NULL,
+ };
+
+ if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
+ return read_mapping_page(mapping, index, NULL);
+
+ page = f2fs_grab_cache_page(mapping, index, for_write);
+ if (!page)
+ return ERR_PTR(-ENOMEM);
+
+ if (f2fs_lookup_extent_cache(inode, index, &ei)) {
+ dn.data_blkaddr = ei.blk + index - ei.fofs;
+ goto got_it;
+ }
+
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
+ if (err)
+ goto put_err;
+ f2fs_put_dnode(&dn);
+
+ if (unlikely(dn.data_blkaddr == NULL_ADDR)) {
+ err = -ENOENT;
+ goto put_err;
+ }
+got_it:
+ if (PageUptodate(page)) {
+ unlock_page(page);
+ return page;
+ }
+
+ /*
+ * A new dentry page is allocated but not able to be written, since its
+ * new inode page couldn't be allocated due to -ENOSPC.
+ * In such the case, its blkaddr can be remained as NEW_ADDR.
+ * see, f2fs_add_link -> get_new_data_page -> init_inode_metadata.
+ */
+ if (dn.data_blkaddr == NEW_ADDR) {
+ zero_user_segment(page, 0, PAGE_SIZE);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
+ unlock_page(page);
+ return page;
+ }
+
+ fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr;
+ fio.page = page;
+ err = f2fs_submit_page_bio(&fio);
+ if (err)
+ goto put_err;
+ return page;
+
+put_err:
+ f2fs_put_page(page, 1);
+ return ERR_PTR(err);
+}
+
+struct page *find_data_page(struct inode *inode, pgoff_t index)
+{
+ struct address_space *mapping = inode->i_mapping;
+ struct page *page;
page = find_get_page(mapping, index);
if (page && PageUptodate(page))
return page;
f2fs_put_page(page, 0);
- set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
- if (err)
- return ERR_PTR(err);
- f2fs_put_dnode(&dn);
-
- if (dn.data_blkaddr == NULL_ADDR)
- return ERR_PTR(-ENOENT);
-
- /* By fallocate(), there is no cached page, but with NEW_ADDR */
- if (unlikely(dn.data_blkaddr == NEW_ADDR))
- return ERR_PTR(-EINVAL);
-
- page = grab_cache_page(mapping, index);
- if (!page)
- return ERR_PTR(-ENOMEM);
-
- if (PageUptodate(page)) {
- unlock_page(page);
+ page = get_read_data_page(inode, index, 0, false);
+ if (IS_ERR(page))
return page;
- }
- err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, dn.data_blkaddr,
- sync ? READ_SYNC : READA);
- if (err)
- return ERR_PTR(err);
+ if (PageUptodate(page))
+ return page;
- if (sync) {
- wait_on_page_locked(page);
- if (unlikely(!PageUptodate(page))) {
- f2fs_put_page(page, 0);
- return ERR_PTR(-EIO);
- }
+ wait_on_page_locked(page);
+ if (unlikely(!PageUptodate(page))) {
+ f2fs_put_page(page, 0);
+ return ERR_PTR(-EIO);
}
return page;
}
@@ -449,60 +630,26 @@
* Because, the callers, functions in dir.c and GC, should be able to know
* whether this page exists or not.
*/
-struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
+struct page *get_lock_data_page(struct inode *inode, pgoff_t index,
+ bool for_write)
{
struct address_space *mapping = inode->i_mapping;
- struct dnode_of_data dn;
struct page *page;
- int err;
-
repeat:
- page = grab_cache_page(mapping, index);
- if (!page)
- return ERR_PTR(-ENOMEM);
-
- set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
- if (err) {
- f2fs_put_page(page, 1);
- return ERR_PTR(err);
- }
- f2fs_put_dnode(&dn);
-
- if (unlikely(dn.data_blkaddr == NULL_ADDR)) {
- f2fs_put_page(page, 1);
- return ERR_PTR(-ENOENT);
- }
-
- if (PageUptodate(page))
+ page = get_read_data_page(inode, index, 0, for_write);
+ if (IS_ERR(page))
return page;
- /*
- * A new dentry page is allocated but not able to be written, since its
- * new inode page couldn't be allocated due to -ENOSPC.
- * In such the case, its blkaddr can be remained as NEW_ADDR.
- * see, f2fs_add_link -> get_new_data_page -> init_inode_metadata.
- */
- if (dn.data_blkaddr == NEW_ADDR) {
- zero_user_segment(page, 0, PAGE_CACHE_SIZE);
- SetPageUptodate(page);
- return page;
- }
-
- err = f2fs_submit_page_bio(F2FS_I_SB(inode), page,
- dn.data_blkaddr, READ_SYNC);
- if (err)
- return ERR_PTR(err);
-
+ /* wait for read completion */
lock_page(page);
- if (unlikely(!PageUptodate(page))) {
- f2fs_put_page(page, 1);
- return ERR_PTR(-EIO);
- }
if (unlikely(page->mapping != mapping)) {
f2fs_put_page(page, 1);
goto repeat;
}
+ if (unlikely(!PageUptodate(page))) {
+ f2fs_put_page(page, 1);
+ return ERR_PTR(-EIO);
+ }
return page;
}
@@ -512,7 +659,8 @@
*
* Also, caller should grab and release a rwsem by calling f2fs_lock_op() and
* f2fs_unlock_op().
- * Note that, ipage is set only by make_empty_dir.
+ * Note that, ipage is set only by make_empty_dir, and if any error occur,
+ * ipage should be released by this function.
*/
struct page *get_new_data_page(struct inode *inode,
struct page *ipage, pgoff_t index, bool new_i_size)
@@ -522,235 +670,616 @@
struct dnode_of_data dn;
int err;
+ page = f2fs_grab_cache_page(mapping, index, true);
+ if (!page) {
+ /*
+ * before exiting, we should make sure ipage will be released
+ * if any error occur.
+ */
+ f2fs_put_page(ipage, 1);
+ return ERR_PTR(-ENOMEM);
+ }
+
set_new_dnode(&dn, inode, ipage, NULL, 0);
err = f2fs_reserve_block(&dn, index);
- if (err)
+ if (err) {
+ f2fs_put_page(page, 1);
return ERR_PTR(err);
-repeat:
- page = grab_cache_page(mapping, index);
- if (!page) {
- err = -ENOMEM;
- goto put_err;
}
+ if (!ipage)
+ f2fs_put_dnode(&dn);
if (PageUptodate(page))
- return page;
+ goto got_it;
if (dn.data_blkaddr == NEW_ADDR) {
- zero_user_segment(page, 0, PAGE_CACHE_SIZE);
- SetPageUptodate(page);
+ zero_user_segment(page, 0, PAGE_SIZE);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
} else {
- err = f2fs_submit_page_bio(F2FS_I_SB(inode), page,
- dn.data_blkaddr, READ_SYNC);
- if (err)
- goto put_err;
+ f2fs_put_page(page, 1);
- lock_page(page);
- if (unlikely(!PageUptodate(page))) {
- f2fs_put_page(page, 1);
- err = -EIO;
- goto put_err;
- }
- if (unlikely(page->mapping != mapping)) {
- f2fs_put_page(page, 1);
- goto repeat;
- }
+ /* if ipage exists, blkaddr should be NEW_ADDR */
+ f2fs_bug_on(F2FS_I_SB(inode), ipage);
+ page = get_lock_data_page(inode, index, true);
+ if (IS_ERR(page))
+ return page;
}
-
- if (new_i_size &&
- i_size_read(inode) < ((index + 1) << PAGE_CACHE_SHIFT)) {
- i_size_write(inode, ((index + 1) << PAGE_CACHE_SHIFT));
- /* Only the directory inode sets new_i_size */
- set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR);
- }
+got_it:
+ if (new_i_size && i_size_read(inode) <
+ ((loff_t)(index + 1) << PAGE_SHIFT))
+ f2fs_i_size_write(inode, ((loff_t)(index + 1) << PAGE_SHIFT));
return page;
-
-put_err:
- f2fs_put_dnode(&dn);
- return ERR_PTR(err);
}
static int __allocate_data_block(struct dnode_of_data *dn)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
- struct f2fs_inode_info *fi = F2FS_I(dn->inode);
struct f2fs_summary sum;
- block_t new_blkaddr;
struct node_info ni;
pgoff_t fofs;
- int type;
+ blkcnt_t count = 1;
- if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
+ if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
return -EPERM;
- if (unlikely(!inc_valid_block_count(sbi, dn->inode, 1)))
+
+ dn->data_blkaddr = datablock_addr(dn->node_page, dn->ofs_in_node);
+ if (dn->data_blkaddr == NEW_ADDR)
+ goto alloc;
+
+ if (unlikely(!inc_valid_block_count(sbi, dn->inode, &count)))
return -ENOSPC;
- __set_data_blkaddr(dn, NEW_ADDR);
- dn->data_blkaddr = NEW_ADDR;
-
+alloc:
get_node_info(sbi, dn->nid, &ni);
set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
- type = CURSEG_WARM_DATA;
-
- allocate_data_block(sbi, NULL, NULL_ADDR, &new_blkaddr, &sum, type);
-
- /* direct IO doesn't use extent cache to maximize the performance */
- set_inode_flag(F2FS_I(dn->inode), FI_NO_EXTENT);
- update_extent_cache(new_blkaddr, dn);
- clear_inode_flag(F2FS_I(dn->inode), FI_NO_EXTENT);
+ allocate_data_block(sbi, NULL, dn->data_blkaddr, &dn->data_blkaddr,
+ &sum, CURSEG_WARM_DATA);
+ set_data_blkaddr(dn);
/* update i_size */
- fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
+ fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) +
dn->ofs_in_node;
- if (i_size_read(dn->inode) < ((fofs + 1) << PAGE_CACHE_SHIFT))
- i_size_write(dn->inode, ((fofs + 1) << PAGE_CACHE_SHIFT));
-
- dn->data_blkaddr = new_blkaddr;
+ if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_SHIFT))
+ f2fs_i_size_write(dn->inode,
+ ((loff_t)(fofs + 1) << PAGE_SHIFT));
return 0;
}
+static inline bool __force_buffered_io(struct inode *inode, int rw)
+{
+ return ((f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) ||
+ (rw == WRITE && test_opt(F2FS_I_SB(inode), LFS)) ||
+ F2FS_I_SB(inode)->s_ndevs);
+}
+
+int f2fs_preallocate_blocks(struct inode *inode, loff_t pos,
+ size_t count, bool dio)
+{
+ struct f2fs_map_blocks map;
+ int err = 0;
+
+ map.m_lblk = F2FS_BLK_ALIGN(pos);
+ map.m_len = F2FS_BYTES_TO_BLK(pos + count);
+ if (map.m_len > map.m_lblk)
+ map.m_len -= map.m_lblk;
+ else
+ map.m_len = 0;
+
+ map.m_next_pgofs = NULL;
+
+ if (dio) {
+ err = f2fs_convert_inline_inode(inode);
+ if (err)
+ return err;
+ return f2fs_map_blocks(inode, &map, 1,
+ __force_buffered_io(inode, WRITE) ?
+ F2FS_GET_BLOCK_PRE_AIO :
+ F2FS_GET_BLOCK_PRE_DIO);
+ }
+ if (pos + count > MAX_INLINE_DATA) {
+ err = f2fs_convert_inline_inode(inode);
+ if (err)
+ return err;
+ }
+ if (!f2fs_has_inline_data(inode))
+ return f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
+ return err;
+}
+
+static inline void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock)
+{
+ if (flag == F2FS_GET_BLOCK_PRE_AIO) {
+ if (lock)
+ down_read(&sbi->node_change);
+ else
+ up_read(&sbi->node_change);
+ } else {
+ if (lock)
+ f2fs_lock_op(sbi);
+ else
+ f2fs_unlock_op(sbi);
+ }
+}
+
/*
- * get_data_block() now supported readahead/bmap/rw direct_IO with mapped bh.
+ * f2fs_map_blocks() now supported readahead/bmap/rw direct_IO with
+ * f2fs_map_blocks structure.
* If original data blocks are allocated, then give them to blockdev.
* Otherwise,
* a. preallocate requested block addresses
* b. do not use extent cache for better performance
* c. give the block addresses to blockdev
*/
-static int __get_data_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create, bool fiemap)
+int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
+ int create, int flag)
{
- unsigned int blkbits = inode->i_sb->s_blocksize_bits;
- unsigned maxblocks = bh_result->b_size >> blkbits;
+ unsigned int maxblocks = map->m_len;
struct dnode_of_data dn;
- int mode = create ? ALLOC_NODE : LOOKUP_NODE_RA;
- pgoff_t pgofs, end_offset;
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ int mode = create ? ALLOC_NODE : LOOKUP_NODE;
+ pgoff_t pgofs, end_offset, end;
int err = 0, ofs = 1;
- bool allocated = false;
+ unsigned int ofs_in_node, last_ofs_in_node;
+ blkcnt_t prealloc;
+ struct extent_info ei = {0,0,0};
+ block_t blkaddr;
- /* Get the page offset from the block offset(iblock) */
- pgofs = (pgoff_t)(iblock >> (PAGE_CACHE_SHIFT - blkbits));
+ if (!maxblocks)
+ return 0;
- if (check_extent_cache(inode, pgofs, bh_result))
+ map->m_len = 0;
+ map->m_flags = 0;
+
+ /* it only supports block size == page size */
+ pgofs = (pgoff_t)map->m_lblk;
+ end = pgofs + maxblocks;
+
+ if (!create && f2fs_lookup_extent_cache(inode, pgofs, &ei)) {
+ map->m_pblk = ei.blk + pgofs - ei.fofs;
+ map->m_len = min((pgoff_t)maxblocks, ei.fofs + ei.len - pgofs);
+ map->m_flags = F2FS_MAP_MAPPED;
goto out;
-
- if (create) {
- f2fs_balance_fs(F2FS_I_SB(inode));
- f2fs_lock_op(F2FS_I_SB(inode));
}
+next_dnode:
+ if (create)
+ __do_map_lock(sbi, flag, true);
+
/* When reading holes, we need its node page */
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, pgofs, mode);
if (err) {
- if (err == -ENOENT)
+ if (flag == F2FS_GET_BLOCK_BMAP)
+ map->m_pblk = 0;
+ if (err == -ENOENT) {
err = 0;
+ if (map->m_next_pgofs)
+ *map->m_next_pgofs =
+ get_next_page_offset(&dn, pgofs);
+ }
goto unlock_out;
}
- if (dn.data_blkaddr == NEW_ADDR && !fiemap)
- goto put_out;
- if (dn.data_blkaddr != NULL_ADDR) {
- map_bh(bh_result, inode->i_sb, dn.data_blkaddr);
- } else if (create) {
- err = __allocate_data_block(&dn);
- if (err)
- goto put_out;
- allocated = true;
- map_bh(bh_result, inode->i_sb, dn.data_blkaddr);
- } else {
- goto put_out;
+ prealloc = 0;
+ last_ofs_in_node = ofs_in_node = dn.ofs_in_node;
+ end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
+
+next_block:
+ blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
+
+ if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) {
+ if (create) {
+ if (unlikely(f2fs_cp_error(sbi))) {
+ err = -EIO;
+ goto sync_out;
+ }
+ if (flag == F2FS_GET_BLOCK_PRE_AIO) {
+ if (blkaddr == NULL_ADDR) {
+ prealloc++;
+ last_ofs_in_node = dn.ofs_in_node;
+ }
+ } else {
+ err = __allocate_data_block(&dn);
+ if (!err)
+ set_inode_flag(inode, FI_APPEND_WRITE);
+ }
+ if (err)
+ goto sync_out;
+ map->m_flags |= F2FS_MAP_NEW;
+ blkaddr = dn.data_blkaddr;
+ } else {
+ if (flag == F2FS_GET_BLOCK_BMAP) {
+ map->m_pblk = 0;
+ goto sync_out;
+ }
+ if (flag == F2FS_GET_BLOCK_FIEMAP &&
+ blkaddr == NULL_ADDR) {
+ if (map->m_next_pgofs)
+ *map->m_next_pgofs = pgofs + 1;
+ }
+ if (flag != F2FS_GET_BLOCK_FIEMAP ||
+ blkaddr != NEW_ADDR)
+ goto sync_out;
+ }
}
- end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
- bh_result->b_size = (((size_t)1) << blkbits);
+ if (flag == F2FS_GET_BLOCK_PRE_AIO)
+ goto skip;
+
+ if (map->m_len == 0) {
+ /* preallocated unwritten block should be mapped for fiemap. */
+ if (blkaddr == NEW_ADDR)
+ map->m_flags |= F2FS_MAP_UNWRITTEN;
+ map->m_flags |= F2FS_MAP_MAPPED;
+
+ map->m_pblk = blkaddr;
+ map->m_len = 1;
+ } else if ((map->m_pblk != NEW_ADDR &&
+ blkaddr == (map->m_pblk + ofs)) ||
+ (map->m_pblk == NEW_ADDR && blkaddr == NEW_ADDR) ||
+ flag == F2FS_GET_BLOCK_PRE_DIO) {
+ ofs++;
+ map->m_len++;
+ } else {
+ goto sync_out;
+ }
+
+skip:
dn.ofs_in_node++;
pgofs++;
-get_next:
- if (dn.ofs_in_node >= end_offset) {
- if (allocated)
- sync_inode_page(&dn);
- allocated = false;
- f2fs_put_dnode(&dn);
+ /* preallocate blocks in batch for one dnode page */
+ if (flag == F2FS_GET_BLOCK_PRE_AIO &&
+ (pgofs == end || dn.ofs_in_node == end_offset)) {
- set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, pgofs, mode);
- if (err) {
- if (err == -ENOENT)
- err = 0;
- goto unlock_out;
+ dn.ofs_in_node = ofs_in_node;
+ err = reserve_new_blocks(&dn, prealloc);
+ if (err)
+ goto sync_out;
+
+ map->m_len += dn.ofs_in_node - ofs_in_node;
+ if (prealloc && dn.ofs_in_node != last_ofs_in_node + 1) {
+ err = -ENOSPC;
+ goto sync_out;
}
- if (dn.data_blkaddr == NEW_ADDR && !fiemap)
- goto put_out;
-
- end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+ dn.ofs_in_node = end_offset;
}
- if (maxblocks > (bh_result->b_size >> blkbits)) {
- block_t blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
- if (blkaddr == NULL_ADDR && create) {
- err = __allocate_data_block(&dn);
- if (err)
- goto sync_out;
- allocated = true;
- blkaddr = dn.data_blkaddr;
- }
- /* Give more consecutive addresses for the readahead */
- if (blkaddr == (bh_result->b_blocknr + ofs)) {
- ofs++;
- dn.ofs_in_node++;
- pgofs++;
- bh_result->b_size += (((size_t)1) << blkbits);
- goto get_next;
- }
+ if (pgofs >= end)
+ goto sync_out;
+ else if (dn.ofs_in_node < end_offset)
+ goto next_block;
+
+ f2fs_put_dnode(&dn);
+
+ if (create) {
+ __do_map_lock(sbi, flag, false);
+ f2fs_balance_fs(sbi, dn.node_changed);
}
+ goto next_dnode;
+
sync_out:
- if (allocated)
- sync_inode_page(&dn);
-put_out:
f2fs_put_dnode(&dn);
unlock_out:
- if (create)
- f2fs_unlock_op(F2FS_I_SB(inode));
+ if (create) {
+ __do_map_lock(sbi, flag, false);
+ f2fs_balance_fs(sbi, dn.node_changed);
+ }
out:
- trace_f2fs_get_data_block(inode, iblock, bh_result, err);
+ trace_f2fs_map_blocks(inode, map, err);
+ return err;
+}
+
+static int __get_data_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh, int create, int flag,
+ pgoff_t *next_pgofs)
+{
+ struct f2fs_map_blocks map;
+ int err;
+
+ map.m_lblk = iblock;
+ map.m_len = bh->b_size >> inode->i_blkbits;
+ map.m_next_pgofs = next_pgofs;
+
+ err = f2fs_map_blocks(inode, &map, create, flag);
+ if (!err) {
+ map_bh(bh, inode->i_sb, map.m_pblk);
+ bh->b_state = (bh->b_state & ~F2FS_MAP_FLAGS) | map.m_flags;
+ bh->b_size = (u64)map.m_len << inode->i_blkbits;
+ }
return err;
}
static int get_data_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
+ struct buffer_head *bh_result, int create, int flag,
+ pgoff_t *next_pgofs)
{
- return __get_data_block(inode, iblock, bh_result, create, false);
+ return __get_data_block(inode, iblock, bh_result, create,
+ flag, next_pgofs);
}
-static int get_data_block_fiemap(struct inode *inode, sector_t iblock,
+static int get_data_block_dio(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
- return __get_data_block(inode, iblock, bh_result, create, true);
+ return __get_data_block(inode, iblock, bh_result, create,
+ F2FS_GET_BLOCK_DIO, NULL);
+}
+
+static int get_data_block_bmap(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
+{
+ /* Block number less than F2FS MAX BLOCKS */
+ if (unlikely(iblock >= F2FS_I_SB(inode)->max_file_blocks))
+ return -EFBIG;
+
+ return __get_data_block(inode, iblock, bh_result, create,
+ F2FS_GET_BLOCK_BMAP, NULL);
+}
+
+static inline sector_t logical_to_blk(struct inode *inode, loff_t offset)
+{
+ return (offset >> inode->i_blkbits);
+}
+
+static inline loff_t blk_to_logical(struct inode *inode, sector_t blk)
+{
+ return (blk << inode->i_blkbits);
}
int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len)
{
- return generic_block_fiemap(inode, fieinfo,
- start, len, get_data_block_fiemap);
+ struct buffer_head map_bh;
+ sector_t start_blk, last_blk;
+ pgoff_t next_pgofs;
+ u64 logical = 0, phys = 0, size = 0;
+ u32 flags = 0;
+ int ret = 0;
+
+ ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
+ if (ret)
+ return ret;
+
+ if (f2fs_has_inline_data(inode)) {
+ ret = f2fs_inline_data_fiemap(inode, fieinfo, start, len);
+ if (ret != -EAGAIN)
+ return ret;
+ }
+
+ inode_lock(inode);
+
+ if (logical_to_blk(inode, len) == 0)
+ len = blk_to_logical(inode, 1);
+
+ start_blk = logical_to_blk(inode, start);
+ last_blk = logical_to_blk(inode, start + len - 1);
+
+next:
+ memset(&map_bh, 0, sizeof(struct buffer_head));
+ map_bh.b_size = len;
+
+ ret = get_data_block(inode, start_blk, &map_bh, 0,
+ F2FS_GET_BLOCK_FIEMAP, &next_pgofs);
+ if (ret)
+ goto out;
+
+ /* HOLE */
+ if (!buffer_mapped(&map_bh)) {
+ start_blk = next_pgofs;
+
+ if (blk_to_logical(inode, start_blk) < blk_to_logical(inode,
+ F2FS_I_SB(inode)->max_file_blocks))
+ goto prep_next;
+
+ flags |= FIEMAP_EXTENT_LAST;
+ }
+
+ if (size) {
+ if (f2fs_encrypted_inode(inode))
+ flags |= FIEMAP_EXTENT_DATA_ENCRYPTED;
+
+ ret = fiemap_fill_next_extent(fieinfo, logical,
+ phys, size, flags);
+ }
+
+ if (start_blk > last_blk || ret)
+ goto out;
+
+ logical = blk_to_logical(inode, start_blk);
+ phys = blk_to_logical(inode, map_bh.b_blocknr);
+ size = map_bh.b_size;
+ flags = 0;
+ if (buffer_unwritten(&map_bh))
+ flags = FIEMAP_EXTENT_UNWRITTEN;
+
+ start_blk += logical_to_blk(inode, size);
+
+prep_next:
+ cond_resched();
+ if (fatal_signal_pending(current))
+ ret = -EINTR;
+ else
+ goto next;
+out:
+ if (ret == 1)
+ ret = 0;
+
+ inode_unlock(inode);
+ return ret;
+}
+
+static struct bio *f2fs_grab_bio(struct inode *inode, block_t blkaddr,
+ unsigned nr_pages)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct fscrypt_ctx *ctx = NULL;
+ struct bio *bio;
+
+ if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
+ ctx = fscrypt_get_ctx(inode, GFP_NOFS);
+ if (IS_ERR(ctx))
+ return ERR_CAST(ctx);
+
+ /* wait the page to be moved by cleaning */
+ f2fs_wait_on_encrypted_page_writeback(sbi, blkaddr);
+ }
+
+ bio = bio_alloc(GFP_KERNEL, min_t(int, nr_pages, BIO_MAX_PAGES));
+ if (!bio) {
+ if (ctx)
+ fscrypt_release_ctx(ctx);
+ return ERR_PTR(-ENOMEM);
+ }
+ f2fs_target_device(sbi, blkaddr, bio);
+ bio->bi_end_io = f2fs_read_end_io;
+ bio->bi_private = ctx;
+
+ return bio;
+}
+
+/*
+ * This function was originally taken from fs/mpage.c, and customized for f2fs.
+ * Major change was from block_size == page_size in f2fs by default.
+ */
+static int f2fs_mpage_readpages(struct address_space *mapping,
+ struct list_head *pages, struct page *page,
+ unsigned nr_pages)
+{
+ struct bio *bio = NULL;
+ unsigned page_idx;
+ sector_t last_block_in_bio = 0;
+ struct inode *inode = mapping->host;
+ const unsigned blkbits = inode->i_blkbits;
+ const unsigned blocksize = 1 << blkbits;
+ sector_t block_in_file;
+ sector_t last_block;
+ sector_t last_block_in_file;
+ sector_t block_nr;
+ struct f2fs_map_blocks map;
+
+ map.m_pblk = 0;
+ map.m_lblk = 0;
+ map.m_len = 0;
+ map.m_flags = 0;
+ map.m_next_pgofs = NULL;
+
+ for (page_idx = 0; nr_pages; page_idx++, nr_pages--) {
+
+ if (pages) {
+ page = list_last_entry(pages, struct page, lru);
+
+ prefetchw(&page->flags);
+ list_del(&page->lru);
+ if (add_to_page_cache_lru(page, mapping,
+ page->index, GFP_KERNEL))
+ goto next_page;
+ }
+
+ block_in_file = (sector_t)page->index;
+ last_block = block_in_file + nr_pages;
+ last_block_in_file = (i_size_read(inode) + blocksize - 1) >>
+ blkbits;
+ if (last_block > last_block_in_file)
+ last_block = last_block_in_file;
+
+ /*
+ * Map blocks using the previous result first.
+ */
+ if ((map.m_flags & F2FS_MAP_MAPPED) &&
+ block_in_file > map.m_lblk &&
+ block_in_file < (map.m_lblk + map.m_len))
+ goto got_it;
+
+ /*
+ * Then do more f2fs_map_blocks() calls until we are
+ * done with this page.
+ */
+ map.m_flags = 0;
+
+ if (block_in_file < last_block) {
+ map.m_lblk = block_in_file;
+ map.m_len = last_block - block_in_file;
+
+ if (f2fs_map_blocks(inode, &map, 0,
+ F2FS_GET_BLOCK_READ))
+ goto set_error_page;
+ }
+got_it:
+ if ((map.m_flags & F2FS_MAP_MAPPED)) {
+ block_nr = map.m_pblk + block_in_file - map.m_lblk;
+ SetPageMappedToDisk(page);
+
+ if (!PageUptodate(page) && !cleancache_get_page(page)) {
+ SetPageUptodate(page);
+ goto confused;
+ }
+ } else {
+ zero_user_segment(page, 0, PAGE_SIZE);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
+ unlock_page(page);
+ goto next_page;
+ }
+
+ /*
+ * This page will go to BIO. Do we need to send this
+ * BIO off first?
+ */
+ if (bio && (last_block_in_bio != block_nr - 1 ||
+ !__same_bdev(F2FS_I_SB(inode), block_nr, bio))) {
+submit_and_realloc:
+ __submit_bio(F2FS_I_SB(inode), bio, DATA);
+ bio = NULL;
+ }
+ if (bio == NULL) {
+ bio = f2fs_grab_bio(inode, block_nr, nr_pages);
+ if (IS_ERR(bio)) {
+ bio = NULL;
+ goto set_error_page;
+ }
+ bio_set_op_attrs(bio, REQ_OP_READ, 0);
+ }
+
+ if (bio_add_page(bio, page, blocksize, 0) < blocksize)
+ goto submit_and_realloc;
+
+ last_block_in_bio = block_nr;
+ goto next_page;
+set_error_page:
+ SetPageError(page);
+ zero_user_segment(page, 0, PAGE_SIZE);
+ unlock_page(page);
+ goto next_page;
+confused:
+ if (bio) {
+ __submit_bio(F2FS_I_SB(inode), bio, DATA);
+ bio = NULL;
+ }
+ unlock_page(page);
+next_page:
+ if (pages)
+ put_page(page);
+ }
+ BUG_ON(pages && !list_empty(pages));
+ if (bio)
+ __submit_bio(F2FS_I_SB(inode), bio, DATA);
+ return 0;
}
static int f2fs_read_data_page(struct file *file, struct page *page)
{
struct inode *inode = page->mapping->host;
- int ret;
+ int ret = -EAGAIN;
trace_f2fs_readpage(page, DATA);
/* If the file has inline data, try to read it directly */
if (f2fs_has_inline_data(inode))
ret = f2fs_read_inline_data(inode, page);
- else
- ret = mpage_readpage(page, get_data_block);
-
+ if (ret == -EAGAIN)
+ ret = f2fs_mpage_readpages(page->mapping, NULL, page, 1);
return ret;
}
@@ -759,30 +1288,105 @@
struct list_head *pages, unsigned nr_pages)
{
struct inode *inode = file->f_mapping->host;
+ struct page *page = list_last_entry(pages, struct page, lru);
+
+ trace_f2fs_readpages(inode, page, nr_pages);
/* If the file has inline data, skip readpages */
if (f2fs_has_inline_data(inode))
return 0;
- return mpage_readpages(mapping, pages, nr_pages, get_data_block);
+ return f2fs_mpage_readpages(mapping, pages, NULL, nr_pages);
}
-int do_write_data_page(struct page *page, struct f2fs_io_info *fio)
+static int encrypt_one_page(struct f2fs_io_info *fio)
{
+ struct inode *inode = fio->page->mapping->host;
+ gfp_t gfp_flags = GFP_NOFS;
+
+ if (!f2fs_encrypted_inode(inode) || !S_ISREG(inode->i_mode))
+ return 0;
+
+ /* wait for GCed encrypted page writeback */
+ f2fs_wait_on_encrypted_page_writeback(fio->sbi, fio->old_blkaddr);
+
+retry_encrypt:
+ fio->encrypted_page = fscrypt_encrypt_page(inode, fio->page,
+ PAGE_SIZE, 0, fio->page->index, gfp_flags);
+ if (!IS_ERR(fio->encrypted_page))
+ return 0;
+
+ /* flush pending IOs and wait for a while in the ENOMEM case */
+ if (PTR_ERR(fio->encrypted_page) == -ENOMEM) {
+ f2fs_flush_merged_bios(fio->sbi);
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ gfp_flags |= __GFP_NOFAIL;
+ goto retry_encrypt;
+ }
+ return PTR_ERR(fio->encrypted_page);
+}
+
+static inline bool need_inplace_update(struct f2fs_io_info *fio)
+{
+ struct inode *inode = fio->page->mapping->host;
+
+ if (S_ISDIR(inode->i_mode) || f2fs_is_atomic_file(inode))
+ return false;
+ if (is_cold_data(fio->page))
+ return false;
+ if (IS_ATOMIC_WRITTEN_PAGE(fio->page))
+ return false;
+
+ return need_inplace_update_policy(inode, fio);
+}
+
+static inline bool valid_ipu_blkaddr(struct f2fs_io_info *fio)
+{
+ if (fio->old_blkaddr == NEW_ADDR)
+ return false;
+ if (fio->old_blkaddr == NULL_ADDR)
+ return false;
+ return true;
+}
+
+int do_write_data_page(struct f2fs_io_info *fio)
+{
+ struct page *page = fio->page;
struct inode *inode = page->mapping->host;
- block_t old_blkaddr, new_blkaddr;
struct dnode_of_data dn;
+ struct extent_info ei = {0,0,0};
+ bool ipu_force = false;
int err = 0;
set_new_dnode(&dn, inode, NULL, NULL, 0);
+ if (need_inplace_update(fio) &&
+ f2fs_lookup_extent_cache(inode, page->index, &ei)) {
+ fio->old_blkaddr = ei.blk + page->index - ei.fofs;
+
+ if (valid_ipu_blkaddr(fio)) {
+ ipu_force = true;
+ fio->need_lock = false;
+ goto got_it;
+ }
+ }
+
+ if (fio->need_lock)
+ f2fs_lock_op(fio->sbi);
+
err = get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
if (err)
- return err;
+ goto out;
- old_blkaddr = dn.data_blkaddr;
+ fio->old_blkaddr = dn.data_blkaddr;
/* This page is already truncated */
- if (old_blkaddr == NULL_ADDR)
+ if (fio->old_blkaddr == NULL_ADDR) {
+ ClearPageUptodate(page);
+ goto out_writepage;
+ }
+got_it:
+ err = encrypt_one_page(fio);
+ if (err)
goto out_writepage;
set_page_writeback(page);
@@ -791,35 +1395,52 @@
* If current allocation needs SSR,
* it had better in-place writes for updated data.
*/
- if (unlikely(old_blkaddr != NEW_ADDR &&
- !is_cold_data(page) &&
- need_inplace_update(inode))) {
- rewrite_data_page(page, old_blkaddr, fio);
- set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE);
- } else {
- write_data_page(page, &dn, &new_blkaddr, fio);
- update_extent_cache(new_blkaddr, &dn);
- set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
+ if (ipu_force || (valid_ipu_blkaddr(fio) && need_inplace_update(fio))) {
+ f2fs_put_dnode(&dn);
+ if (fio->need_lock)
+ f2fs_unlock_op(fio->sbi);
+ err = rewrite_data_page(fio);
+ trace_f2fs_do_write_data_page(fio->page, IPU);
+ set_inode_flag(inode, FI_UPDATE_WRITE);
+ return err;
}
+
+ /* LFS mode write path */
+ write_data_page(&dn, fio);
+ trace_f2fs_do_write_data_page(page, OPU);
+ set_inode_flag(inode, FI_APPEND_WRITE);
+ if (page->index == 0)
+ set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
out_writepage:
f2fs_put_dnode(&dn);
+out:
+ if (fio->need_lock)
+ f2fs_unlock_op(fio->sbi);
return err;
}
-static int f2fs_write_data_page(struct page *page,
- struct writeback_control *wbc)
+static int __write_data_page(struct page *page, bool *submitted,
+ struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
loff_t i_size = i_size_read(inode);
const pgoff_t end_index = ((unsigned long long) i_size)
- >> PAGE_CACHE_SHIFT;
+ >> PAGE_SHIFT;
+ loff_t psize = (page->index + 1) << PAGE_SHIFT;
unsigned offset = 0;
bool need_balance_fs = false;
int err = 0;
struct f2fs_io_info fio = {
+ .sbi = sbi,
.type = DATA,
- .rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE,
+ .op = REQ_OP_WRITE,
+ .op_flags = wbc_to_write_flags(wbc),
+ .old_blkaddr = NULL_ADDR,
+ .page = page,
+ .encrypted_page = NULL,
+ .submitted = false,
+ .need_lock = true,
};
trace_f2fs_writepage(page, DATA);
@@ -831,66 +1452,238 @@
* If the offset is out-of-range of file size,
* this page does not have to be written to disk.
*/
- offset = i_size & (PAGE_CACHE_SIZE - 1);
+ offset = i_size & (PAGE_SIZE - 1);
if ((page->index >= end_index + 1) || !offset)
goto out;
- zero_user_segment(page, offset, PAGE_CACHE_SIZE);
+ zero_user_segment(page, offset, PAGE_SIZE);
write:
- if (unlikely(sbi->por_doing))
+ if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
goto redirty_out;
-
- /* Dentry blocks are controlled by checkpoint */
- if (S_ISDIR(inode->i_mode)) {
- if (unlikely(f2fs_cp_error(sbi)))
- goto redirty_out;
- err = do_write_data_page(page, &fio);
- goto done;
- }
+ if (f2fs_is_drop_cache(inode))
+ goto out;
+ /* we should not write 0'th page having journal header */
+ if (f2fs_is_volatile_file(inode) && (!page->index ||
+ (!wbc->for_reclaim &&
+ available_free_memory(sbi, BASE_CHECK))))
+ goto redirty_out;
/* we should bypass data pages to proceed the kworkder jobs */
if (unlikely(f2fs_cp_error(sbi))) {
- SetPageError(page);
- unlock_page(page);
+ mapping_set_error(page->mapping, -EIO);
goto out;
}
+ /* Dentry blocks are controlled by checkpoint */
+ if (S_ISDIR(inode->i_mode)) {
+ fio.need_lock = false;
+ err = do_write_data_page(&fio);
+ goto done;
+ }
+
if (!wbc->for_reclaim)
need_balance_fs = true;
- else if (has_not_enough_free_secs(sbi, 0))
+ else if (has_not_enough_free_secs(sbi, 0, 0))
goto redirty_out;
-
- f2fs_lock_op(sbi);
- if (f2fs_has_inline_data(inode) || f2fs_may_inline(inode))
- err = f2fs_write_inline_data(inode, page, offset);
else
- err = do_write_data_page(page, &fio);
- f2fs_unlock_op(sbi);
+ set_inode_flag(inode, FI_HOT_DATA);
+
+ err = -EAGAIN;
+ if (f2fs_has_inline_data(inode)) {
+ err = f2fs_write_inline_data(inode, page);
+ if (!err)
+ goto out;
+ }
+
+ if (err == -EAGAIN)
+ err = do_write_data_page(&fio);
+ if (F2FS_I(inode)->last_disk_size < psize)
+ F2FS_I(inode)->last_disk_size = psize;
+
done:
if (err && err != -ENOENT)
goto redirty_out;
- clear_cold_data(page);
out:
inode_dec_dirty_pages(inode);
+ if (err)
+ ClearPageUptodate(page);
+
+ if (wbc->for_reclaim) {
+ f2fs_submit_merged_bio_cond(sbi, inode, 0, page->index,
+ DATA, WRITE);
+ clear_inode_flag(inode, FI_HOT_DATA);
+ remove_dirty_inode(inode);
+ submitted = NULL;
+ }
+
unlock_page(page);
- if (need_balance_fs)
- f2fs_balance_fs(sbi);
- if (wbc->for_reclaim)
+ if (!S_ISDIR(inode->i_mode))
+ f2fs_balance_fs(sbi, need_balance_fs);
+
+ if (unlikely(f2fs_cp_error(sbi))) {
f2fs_submit_merged_bio(sbi, DATA, WRITE);
+ submitted = NULL;
+ }
+
+ if (submitted)
+ *submitted = fio.submitted;
+
return 0;
redirty_out:
redirty_page_for_writepage(wbc, page);
- return AOP_WRITEPAGE_ACTIVATE;
+ if (!err)
+ return AOP_WRITEPAGE_ACTIVATE;
+ unlock_page(page);
+ return err;
}
-static int __f2fs_writepage(struct page *page, struct writeback_control *wbc,
- void *data)
+static int f2fs_write_data_page(struct page *page,
+ struct writeback_control *wbc)
{
- struct address_space *mapping = data;
- int ret = mapping->a_ops->writepage(page, wbc);
- mapping_set_error(mapping, ret);
+ return __write_data_page(page, NULL, wbc);
+}
+
+/*
+ * This function was copied from write_cche_pages from mm/page-writeback.c.
+ * The major change is making write step of cold data page separately from
+ * warm/hot data page.
+ */
+static int f2fs_write_cache_pages(struct address_space *mapping,
+ struct writeback_control *wbc)
+{
+ int ret = 0;
+ int done = 0;
+ struct pagevec pvec;
+ int nr_pages;
+ pgoff_t uninitialized_var(writeback_index);
+ pgoff_t index;
+ pgoff_t end; /* Inclusive */
+ pgoff_t done_index;
+ pgoff_t last_idx = ULONG_MAX;
+ int cycled;
+ int range_whole = 0;
+ int tag;
+
+ pagevec_init(&pvec, 0);
+
+ if (get_dirty_pages(mapping->host) <=
+ SM_I(F2FS_M_SB(mapping))->min_hot_blocks)
+ set_inode_flag(mapping->host, FI_HOT_DATA);
+ else
+ clear_inode_flag(mapping->host, FI_HOT_DATA);
+
+ if (wbc->range_cyclic) {
+ writeback_index = mapping->writeback_index; /* prev offset */
+ index = writeback_index;
+ if (index == 0)
+ cycled = 1;
+ else
+ cycled = 0;
+ end = -1;
+ } else {
+ index = wbc->range_start >> PAGE_SHIFT;
+ end = wbc->range_end >> PAGE_SHIFT;
+ if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
+ range_whole = 1;
+ cycled = 1; /* ignore range_cyclic tests */
+ }
+ if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
+ tag = PAGECACHE_TAG_TOWRITE;
+ else
+ tag = PAGECACHE_TAG_DIRTY;
+retry:
+ if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
+ tag_pages_for_writeback(mapping, index, end);
+ done_index = index;
+ while (!done && (index <= end)) {
+ int i;
+
+ nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
+ min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1);
+ if (nr_pages == 0)
+ break;
+
+ for (i = 0; i < nr_pages; i++) {
+ struct page *page = pvec.pages[i];
+ bool submitted = false;
+
+ if (page->index > end) {
+ done = 1;
+ break;
+ }
+
+ done_index = page->index;
+
+ lock_page(page);
+
+ if (unlikely(page->mapping != mapping)) {
+continue_unlock:
+ unlock_page(page);
+ continue;
+ }
+
+ if (!PageDirty(page)) {
+ /* someone wrote it for us */
+ goto continue_unlock;
+ }
+
+ if (PageWriteback(page)) {
+ if (wbc->sync_mode != WB_SYNC_NONE)
+ f2fs_wait_on_page_writeback(page,
+ DATA, true);
+ else
+ goto continue_unlock;
+ }
+
+ BUG_ON(PageWriteback(page));
+ if (!clear_page_dirty_for_io(page))
+ goto continue_unlock;
+
+ ret = __write_data_page(page, &submitted, wbc);
+ if (unlikely(ret)) {
+ /*
+ * keep nr_to_write, since vfs uses this to
+ * get # of written pages.
+ */
+ if (ret == AOP_WRITEPAGE_ACTIVATE) {
+ unlock_page(page);
+ ret = 0;
+ continue;
+ }
+ done_index = page->index + 1;
+ done = 1;
+ break;
+ } else if (submitted) {
+ last_idx = page->index;
+ }
+
+ /* give a priority to WB_SYNC threads */
+ if ((atomic_read(&F2FS_M_SB(mapping)->wb_sync_req) ||
+ --wbc->nr_to_write <= 0) &&
+ wbc->sync_mode == WB_SYNC_NONE) {
+ done = 1;
+ break;
+ }
+ }
+ pagevec_release(&pvec);
+ cond_resched();
+ }
+
+ if (!cycled && !done) {
+ cycled = 1;
+ index = 0;
+ end = writeback_index - 1;
+ goto retry;
+ }
+ if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
+ mapping->writeback_index = done_index;
+
+ if (last_idx != ULONG_MAX)
+ f2fs_submit_merged_bio_cond(F2FS_M_SB(mapping), mapping->host,
+ 0, last_idx, DATA, WRITE);
+
return ret;
}
@@ -899,62 +1692,155 @@
{
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- bool locked = false;
+ struct blk_plug plug;
int ret;
- long diff;
-
- trace_f2fs_writepages(mapping->host, wbc, DATA);
/* deal with chardevs and other special file */
if (!mapping->a_ops->writepage)
return 0;
+ /* skip writing if there is no dirty page in this inode */
+ if (!get_dirty_pages(inode) && wbc->sync_mode == WB_SYNC_NONE)
+ return 0;
+
if (S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_NONE &&
get_dirty_pages(inode) < nr_pages_to_skip(sbi, DATA) &&
available_free_memory(sbi, DIRTY_DENTS))
goto skip_write;
- diff = nr_pages_to_write(sbi, DATA, wbc);
+ /* skip writing during file defragment */
+ if (is_inode_flag_set(inode, FI_DO_DEFRAG))
+ goto skip_write;
- if (!S_ISDIR(inode->i_mode)) {
- mutex_lock(&sbi->writepages);
- locked = true;
- }
- ret = write_cache_pages(mapping, wbc, __f2fs_writepage, mapping);
- if (locked)
- mutex_unlock(&sbi->writepages);
+ /* during POR, we don't need to trigger writepage at all. */
+ if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+ goto skip_write;
- f2fs_submit_merged_bio(sbi, DATA, WRITE);
+ trace_f2fs_writepages(mapping->host, wbc, DATA);
- remove_dirty_dir_inode(inode);
+ /* to avoid spliting IOs due to mixed WB_SYNC_ALL and WB_SYNC_NONE */
+ if (wbc->sync_mode == WB_SYNC_ALL)
+ atomic_inc(&sbi->wb_sync_req);
+ else if (atomic_read(&sbi->wb_sync_req))
+ goto skip_write;
- wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff);
+ blk_start_plug(&plug);
+ ret = f2fs_write_cache_pages(mapping, wbc);
+ blk_finish_plug(&plug);
+
+ if (wbc->sync_mode == WB_SYNC_ALL)
+ atomic_dec(&sbi->wb_sync_req);
+ /*
+ * if some pages were truncated, we cannot guarantee its mapping->host
+ * to detect pending bios.
+ */
+
+ remove_dirty_inode(inode);
return ret;
skip_write:
wbc->pages_skipped += get_dirty_pages(inode);
+ trace_f2fs_writepages(mapping->host, wbc, DATA);
return 0;
}
static void f2fs_write_failed(struct address_space *mapping, loff_t to)
{
struct inode *inode = mapping->host;
+ loff_t i_size = i_size_read(inode);
- if (to > inode->i_size) {
- truncate_pagecache(inode, inode->i_size);
- truncate_blocks(inode, inode->i_size, true);
+ if (to > i_size) {
+ truncate_pagecache(inode, i_size);
+ truncate_blocks(inode, i_size, true);
}
}
+static int prepare_write_begin(struct f2fs_sb_info *sbi,
+ struct page *page, loff_t pos, unsigned len,
+ block_t *blk_addr, bool *node_changed)
+{
+ struct inode *inode = page->mapping->host;
+ pgoff_t index = page->index;
+ struct dnode_of_data dn;
+ struct page *ipage;
+ bool locked = false;
+ struct extent_info ei = {0,0,0};
+ int err = 0;
+
+ /*
+ * we already allocated all the blocks, so we don't need to get
+ * the block addresses when there is no need to fill the page.
+ */
+ if (!f2fs_has_inline_data(inode) && len == PAGE_SIZE)
+ return 0;
+
+ if (f2fs_has_inline_data(inode) ||
+ (pos & PAGE_MASK) >= i_size_read(inode)) {
+ __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true);
+ locked = true;
+ }
+restart:
+ /* check inline_data */
+ ipage = get_node_page(sbi, inode->i_ino);
+ if (IS_ERR(ipage)) {
+ err = PTR_ERR(ipage);
+ goto unlock_out;
+ }
+
+ set_new_dnode(&dn, inode, ipage, ipage, 0);
+
+ if (f2fs_has_inline_data(inode)) {
+ if (pos + len <= MAX_INLINE_DATA) {
+ read_inline_data(page, ipage);
+ set_inode_flag(inode, FI_DATA_EXIST);
+ if (inode->i_nlink)
+ set_inline_node(ipage);
+ } else {
+ err = f2fs_convert_inline_page(&dn, page);
+ if (err)
+ goto out;
+ if (dn.data_blkaddr == NULL_ADDR)
+ err = f2fs_get_block(&dn, index);
+ }
+ } else if (locked) {
+ err = f2fs_get_block(&dn, index);
+ } else {
+ if (f2fs_lookup_extent_cache(inode, index, &ei)) {
+ dn.data_blkaddr = ei.blk + index - ei.fofs;
+ } else {
+ /* hole case */
+ err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
+ if (err || dn.data_blkaddr == NULL_ADDR) {
+ f2fs_put_dnode(&dn);
+ __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO,
+ true);
+ locked = true;
+ goto restart;
+ }
+ }
+ }
+
+ /* convert_inline_page can make node_changed */
+ *blk_addr = dn.data_blkaddr;
+ *node_changed = dn.node_changed;
+out:
+ f2fs_put_dnode(&dn);
+unlock_out:
+ if (locked)
+ __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false);
+ return err;
+}
+
static int f2fs_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
struct inode *inode = mapping->host;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct page *page;
- pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT;
- struct dnode_of_data dn;
+ struct page *page = NULL;
+ pgoff_t index = ((unsigned long long) pos) >> PAGE_SHIFT;
+ bool need_balance = false;
+ block_t blkaddr = NULL_ADDR;
int err = 0;
if (trace_android_fs_datawrite_start_enabled()) {
@@ -969,85 +1855,93 @@
}
trace_f2fs_write_begin(inode, pos, len, flags);
- f2fs_balance_fs(sbi);
+ /*
+ * We should check this at this moment to avoid deadlock on inode page
+ * and #0 page. The locking rule for inline_data conversion should be:
+ * lock_page(page #0) -> lock_page(inode_page)
+ */
+ if (index != 0) {
+ err = f2fs_convert_inline_inode(inode);
+ if (err)
+ goto fail;
+ }
repeat:
- err = f2fs_convert_inline_data(inode, pos + len, NULL);
- if (err)
- goto fail;
-
- page = grab_cache_page_write_begin(mapping, index, flags);
+ /*
+ * Do not use grab_cache_page_write_begin() to avoid deadlock due to
+ * wait_for_stable_page. Will wait that below with our IO control.
+ */
+ page = grab_cache_page(mapping, index);
if (!page) {
err = -ENOMEM;
goto fail;
}
- /* to avoid latency during memory pressure */
- unlock_page(page);
-
*pagep = page;
- if (f2fs_has_inline_data(inode) && (pos + len) <= MAX_INLINE_DATA)
- goto inline_data;
-
- f2fs_lock_op(sbi);
- set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = f2fs_reserve_block(&dn, index);
- f2fs_unlock_op(sbi);
- if (err) {
- f2fs_put_page(page, 0);
+ err = prepare_write_begin(sbi, page, pos, len,
+ &blkaddr, &need_balance);
+ if (err)
goto fail;
- }
-inline_data:
- lock_page(page);
- if (unlikely(page->mapping != mapping)) {
- f2fs_put_page(page, 1);
- goto repeat;
- }
- f2fs_wait_on_page_writeback(page, DATA);
-
- if ((len == PAGE_CACHE_SIZE) || PageUptodate(page))
- return 0;
-
- if ((pos & PAGE_CACHE_MASK) >= i_size_read(inode)) {
- unsigned start = pos & (PAGE_CACHE_SIZE - 1);
- unsigned end = start + len;
-
- /* Reading beyond i_size is simple: memset to zero */
- zero_user_segments(page, 0, start, end, PAGE_CACHE_SIZE);
- goto out;
- }
-
- if (f2fs_has_inline_data(inode)) {
- err = f2fs_read_inline_data(inode, page);
- if (err) {
- page_cache_release(page);
- goto fail;
- }
- } else if (dn.data_blkaddr == NEW_ADDR) {
- zero_user_segment(page, 0, PAGE_CACHE_SIZE);
- } else {
- err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr,
- READ_SYNC);
- if (err)
- goto fail;
-
+ if (need_balance && has_not_enough_free_secs(sbi, 0, 0)) {
+ unlock_page(page);
+ f2fs_balance_fs(sbi, true);
lock_page(page);
- if (unlikely(!PageUptodate(page))) {
- f2fs_put_page(page, 1);
- err = -EIO;
- goto fail;
- }
- if (unlikely(page->mapping != mapping)) {
+ if (page->mapping != mapping) {
+ /* The page got truncated from under us */
f2fs_put_page(page, 1);
goto repeat;
}
}
-out:
- SetPageUptodate(page);
- clear_cold_data(page);
+
+ f2fs_wait_on_page_writeback(page, DATA, false);
+
+ /* wait for GCed encrypted page writeback */
+ if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
+ f2fs_wait_on_encrypted_page_writeback(sbi, blkaddr);
+
+ if (len == PAGE_SIZE || PageUptodate(page))
+ return 0;
+
+ if (!(pos & (PAGE_SIZE - 1)) && (pos + len) >= i_size_read(inode)) {
+ zero_user_segment(page, len, PAGE_SIZE);
+ return 0;
+ }
+
+ if (blkaddr == NEW_ADDR) {
+ zero_user_segment(page, 0, PAGE_SIZE);
+ SetPageUptodate(page);
+ } else {
+ struct bio *bio;
+
+ bio = f2fs_grab_bio(inode, blkaddr, 1);
+ if (IS_ERR(bio)) {
+ err = PTR_ERR(bio);
+ goto fail;
+ }
+ bio->bi_rw = REQ_OP_READ;
+ if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
+ bio_put(bio);
+ err = -EFAULT;
+ goto fail;
+ }
+
+ __submit_bio(sbi, bio, DATA);
+
+ lock_page(page);
+ if (unlikely(page->mapping != mapping)) {
+ f2fs_put_page(page, 1);
+ goto repeat;
+ }
+ if (unlikely(!PageUptodate(page))) {
+ err = -EIO;
+ goto fail;
+ }
+ }
return 0;
+
fail:
+ f2fs_put_page(page, 1);
f2fs_write_failed(mapping, pos + len);
return err;
}
@@ -1062,29 +1956,35 @@
trace_android_fs_datawrite_end(inode, pos, len);
trace_f2fs_write_end(inode, pos, len, copied);
- if (f2fs_is_atomic_file(inode) || f2fs_is_volatile_file(inode))
- register_inmem_page(inode, page);
- else
- set_page_dirty(page);
-
- if (pos + copied > i_size_read(inode)) {
- i_size_write(inode, pos + copied);
- mark_inode_dirty(inode);
- update_inode_page(inode);
+ /*
+ * This should be come from len == PAGE_SIZE, and we expect copied
+ * should be PAGE_SIZE. Otherwise, we treat it with zero copied and
+ * let generic_perform_write() try to copy data again through copied=0.
+ */
+ if (!PageUptodate(page)) {
+ if (unlikely(copied != len))
+ copied = 0;
+ else
+ SetPageUptodate(page);
}
+ if (!copied)
+ goto unlock_out;
+ set_page_dirty(page);
+
+ if (pos + copied > i_size_read(inode))
+ f2fs_i_size_write(inode, pos + copied);
+unlock_out:
f2fs_put_page(page, 1);
+ f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return copied;
}
-static int check_direct_IO(struct inode *inode, int rw,
- struct iov_iter *iter, loff_t offset)
+static int check_direct_IO(struct inode *inode, struct iov_iter *iter,
+ loff_t offset)
{
unsigned blocksize_mask = inode->i_sb->s_blocksize - 1;
- if (rw == READ)
- return 0;
-
if (offset & blocksize_mask)
return -EINVAL;
@@ -1094,20 +1994,19 @@
return 0;
}
-static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
- struct iov_iter *iter, loff_t offset)
+static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
+ loff_t offset)
{
- struct file *file = iocb->ki_filp;
- struct address_space *mapping = file->f_mapping;
+ struct address_space *mapping = iocb->ki_filp->f_mapping;
struct inode *inode = mapping->host;
size_t count = iov_iter_count(iter);
int err;
- /* Let buffer I/O handle the inline data case. */
- if (f2fs_has_inline_data(inode))
- return 0;
+ err = check_direct_IO(inode, iter, offset);
+ if (err)
+ return err;
- if (check_direct_IO(inode, rw, iter, offset))
+ if (__force_buffered_io(inode, rw))
return 0;
if (trace_android_fs_dataread_start_enabled() && (rw == READ)) {
@@ -1133,9 +2032,16 @@
trace_f2fs_direct_IO_enter(inode, offset, count, rw);
- err = blockdev_direct_IO(rw, iocb, inode, iter, offset, get_data_block);
- if (err < 0 && (rw & WRITE))
- f2fs_write_failed(mapping, offset + count);
+ down_read(&F2FS_I(inode)->dio_rwsem[rw]);
+ err = blockdev_direct_IO(rw, iocb, inode, iter, offset, get_data_block_dio);
+ up_read(&F2FS_I(inode)->dio_rwsem[rw]);
+
+ if (rw & WRITE) {
+ if (err > 0)
+ set_inode_flag(inode, FI_UPDATE_WRITE);
+ else if (err < 0)
+ f2fs_write_failed(mapping, offset + count);
+ }
trace_f2fs_direct_IO_exit(inode, offset, count, rw, err);
@@ -1147,25 +2053,77 @@
return err;
}
-static void f2fs_invalidate_data_page(struct page *page, unsigned int offset,
- unsigned int length)
+void f2fs_invalidate_page(struct page *page, unsigned int offset,
+ unsigned int length)
{
struct inode *inode = page->mapping->host;
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- if (offset % PAGE_CACHE_SIZE || length != PAGE_CACHE_SIZE)
+ if (inode->i_ino >= F2FS_ROOT_INO(sbi) &&
+ (offset % PAGE_SIZE || length != PAGE_SIZE))
return;
- if (PageDirty(page))
- inode_dec_dirty_pages(inode);
+ if (PageDirty(page)) {
+ if (inode->i_ino == F2FS_META_INO(sbi)) {
+ dec_page_count(sbi, F2FS_DIRTY_META);
+ } else if (inode->i_ino == F2FS_NODE_INO(sbi)) {
+ dec_page_count(sbi, F2FS_DIRTY_NODES);
+ } else {
+ inode_dec_dirty_pages(inode);
+ remove_dirty_inode(inode);
+ }
+ }
+
+ /* This is atomic written page, keep Private */
+ if (IS_ATOMIC_WRITTEN_PAGE(page))
+ return drop_inmem_page(inode, page);
+
+ set_page_private(page, 0);
ClearPagePrivate(page);
}
-static int f2fs_release_data_page(struct page *page, gfp_t wait)
+int f2fs_release_page(struct page *page, gfp_t wait)
{
+ /* If this is dirty page, keep PagePrivate */
+ if (PageDirty(page))
+ return 0;
+
+ /* This is atomic written page, keep Private */
+ if (IS_ATOMIC_WRITTEN_PAGE(page))
+ return 0;
+
+ set_page_private(page, 0);
ClearPagePrivate(page);
return 1;
}
+/*
+ * This was copied from __set_page_dirty_buffers which gives higher performance
+ * in very high speed storages. (e.g., pmem)
+ */
+void f2fs_set_page_dirty_nobuffers(struct page *page)
+{
+ struct address_space *mapping = page->mapping;
+ unsigned long flags;
+
+ if (unlikely(!mapping))
+ return;
+
+ spin_lock(&mapping->private_lock);
+ SetPageDirty(page);
+ spin_unlock(&mapping->private_lock);
+
+ spin_lock_irqsave(&mapping->tree_lock, flags);
+ WARN_ON_ONCE(!PageUptodate(page));
+ account_page_dirtied(page, mapping);
+ radix_tree_tag_set(&mapping->page_tree,
+ page_index(page), PAGECACHE_TAG_DIRTY);
+ spin_unlock_irqrestore(&mapping->tree_lock, flags);
+
+ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+ return;
+}
+
static int f2fs_set_data_page_dirty(struct page *page)
{
struct address_space *mapping = page->mapping;
@@ -1173,11 +2131,23 @@
trace_f2fs_set_page_dirty(page, DATA);
- SetPageUptodate(page);
- mark_inode_dirty(inode);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
+
+ if (f2fs_is_atomic_file(inode) && !f2fs_is_commit_atomic_write(inode)) {
+ if (!IS_ATOMIC_WRITTEN_PAGE(page)) {
+ register_inmem_page(inode, page);
+ return 1;
+ }
+ /*
+ * Previously, this page has been registered, we just
+ * return here.
+ */
+ return 0;
+ }
if (!PageDirty(page)) {
- __set_page_dirty_nobuffers(page);
+ f2fs_set_page_dirty_nobuffers(page);
update_dirty_page(inode, page);
return 1;
}
@@ -1191,9 +2161,65 @@
if (f2fs_has_inline_data(inode))
return 0;
- return generic_block_bmap(mapping, block, get_data_block);
+ /* make sure allocating whole blocks */
+ if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
+ filemap_write_and_wait(mapping);
+
+ return generic_block_bmap(mapping, block, get_data_block_bmap);
}
+#ifdef CONFIG_F2FS_MIGRATION
+#include <linux/migrate.h>
+
+int f2fs_migrate_page(struct address_space *mapping,
+ struct page *newpage, struct page *page, enum migrate_mode mode)
+{
+ int rc, extra_count;
+ struct f2fs_inode_info *fi = F2FS_I(mapping->host);
+ bool atomic_written = IS_ATOMIC_WRITTEN_PAGE(page);
+
+ BUG_ON(PageWriteback(page));
+
+ /* migrating an atomic written page is safe with the inmem_lock hold */
+ if (atomic_written && !mutex_trylock(&fi->inmem_lock))
+ return -EAGAIN;
+
+ /*
+ * A reference is expected if PagePrivate set when move mapping,
+ * however F2FS breaks this for maintaining dirty page counts when
+ * truncating pages. So here adjusting the 'extra_count' make it work.
+ */
+ extra_count = (atomic_written ? 1 : 0) - page_has_private(page);
+ rc = migrate_page_move_mapping(mapping, newpage,
+ page, NULL, mode, extra_count);
+ if (rc != MIGRATEPAGE_SUCCESS) {
+ if (atomic_written)
+ mutex_unlock(&fi->inmem_lock);
+ return rc;
+ }
+
+ if (atomic_written) {
+ struct inmem_pages *cur;
+ list_for_each_entry(cur, &fi->inmem_pages, list)
+ if (cur->page == page) {
+ cur->page = newpage;
+ break;
+ }
+ mutex_unlock(&fi->inmem_lock);
+ put_page(page);
+ get_page(newpage);
+ }
+
+ if (PagePrivate(page))
+ SetPagePrivate(newpage);
+ set_page_private(newpage, page_private(page));
+
+ migrate_page_copy(newpage, page);
+
+ return MIGRATEPAGE_SUCCESS;
+}
+#endif
+
const struct address_space_operations f2fs_dblock_aops = {
.readpage = f2fs_read_data_page,
.readpages = f2fs_read_data_pages,
@@ -1202,8 +2228,11 @@
.write_begin = f2fs_write_begin,
.write_end = f2fs_write_end,
.set_page_dirty = f2fs_set_data_page_dirty,
- .invalidatepage = f2fs_invalidate_data_page,
- .releasepage = f2fs_release_data_page,
+ .invalidatepage = f2fs_invalidate_page,
+ .releasepage = f2fs_release_page,
.direct_IO = f2fs_direct_IO,
.bmap = f2fs_bmap,
+#ifdef CONFIG_F2FS_MIGRATION
+ .migratepage = f2fs_migrate_page,
+#endif
};
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 8e53d80..629c570 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -33,19 +33,57 @@
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_imeta = get_pages(sbi, F2FS_DIRTY_IMETA);
+ si->ndirty_dirs = sbi->ndirty_inode[DIR_INODE];
+ si->ndirty_files = sbi->ndirty_inode[FILE_INODE];
+ si->ndirty_all = sbi->ndirty_inode[DIRTY_META];
+ si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES);
+ si->aw_cnt = atomic_read(&sbi->aw_cnt);
+ si->vw_cnt = atomic_read(&sbi->vw_cnt);
+ si->max_aw_cnt = atomic_read(&sbi->max_aw_cnt);
+ si->max_vw_cnt = atomic_read(&sbi->max_vw_cnt);
+ si->nr_wb_cp_data = get_pages(sbi, F2FS_WB_CP_DATA);
+ si->nr_wb_data = get_pages(sbi, F2FS_WB_DATA);
+ if (SM_I(sbi) && SM_I(sbi)->fcc_info) {
+ si->nr_flushed =
+ atomic_read(&SM_I(sbi)->fcc_info->issued_flush);
+ si->nr_flushing =
+ atomic_read(&SM_I(sbi)->fcc_info->issing_flush);
+ }
+ if (SM_I(sbi) && SM_I(sbi)->dcc_info) {
+ si->nr_discarded =
+ atomic_read(&SM_I(sbi)->dcc_info->issued_discard);
+ si->nr_discarding =
+ atomic_read(&SM_I(sbi)->dcc_info->issing_discard);
+ si->nr_discard_cmd =
+ atomic_read(&SM_I(sbi)->dcc_info->discard_cmd_cnt);
+ si->undiscard_blks = SM_I(sbi)->dcc_info->undiscard_blks;
+ }
si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg;
si->rsvd_segs = reserved_segments(sbi);
si->overp_segs = overprovision_segments(sbi);
si->valid_count = valid_user_blocks(sbi);
+ si->discard_blks = discard_blocks(sbi);
si->valid_node_count = valid_node_count(sbi);
si->valid_inode_count = valid_inode_count(sbi);
- si->inline_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->append = sbi->im[APPEND_INO].ino_num;
+ si->update = sbi->im[UPDATE_INO].ino_num;
+ si->orphans = sbi->im[ORPHAN_INO].ino_num;
si->utilization = utilization(sbi);
si->free_segs = free_segments(sbi);
@@ -55,8 +93,12 @@
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->fnids = NM_I(sbi)->fcnt;
+ si->dirty_nats = NM_I(sbi)->dirty_nat_cnt;
+ si->sits = MAIN_SEGS(sbi);
+ si->dirty_sits = SIT_I(sbi)->dirty_sentries;
+ si->free_nids = NM_I(sbi)->nid_cnt[FREE_NID_LIST];
+ si->avail_nids = NM_I(sbi)->available_nids;
+ si->alloc_nids = NM_I(sbi)->nid_cnt[ALLOC_NID_LIST];
si->bg_gc = sbi->bg_gc;
si->util_free = (int)(free_user_blocks(sbi) >> sbi->log_blocks_per_seg)
* 100 / (int)(sbi->user_block_count >> sbi->log_blocks_per_seg)
@@ -69,14 +111,16 @@
for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_NODE; i++) {
struct curseg_info *curseg = CURSEG_I(sbi, i);
si->curseg[i] = curseg->segno;
- si->cursec[i] = curseg->segno / sbi->segs_per_sec;
- si->curzone[i] = si->cursec[i] / sbi->secs_per_zone;
+ si->cursec[i] = GET_SEC_FROM_SEG(sbi, curseg->segno);
+ si->curzone[i] = GET_ZONE_FROM_SEC(sbi, si->cursec[i]);
}
for (i = 0; i < 2; i++) {
si->segment_count[i] = sbi->segment_count[i];
si->block_count[i] = sbi->block_count[i];
}
+
+ si->inplace_count = atomic_read(&sbi->inplace_count);
}
/*
@@ -85,16 +129,17 @@
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 = BLKS_PER_SEC(sbi);
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);
+ vblocks = get_valid_blocks(sbi, segno, true);
dist = abs(vblocks - hblks_per_sec);
bimodal += dist * dist;
@@ -103,10 +148,10 @@
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;
}
@@ -118,13 +163,19 @@
{
struct f2fs_stat_info *si = F2FS_STAT(sbi);
unsigned npages;
+ int i;
if (si->base_mem)
goto get_cache;
- si->base_mem = sizeof(struct f2fs_sb_info) + sbi->sb->s_blocksize;
+ /* build stat */
+ si->base_mem = sizeof(struct f2fs_stat_info);
+
+ /* build superblock */
+ 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);
@@ -134,6 +185,9 @@
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);
+ if (f2fs_discard_en(sbi))
+ si->base_mem += SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi);
+ si->base_mem += SIT_VBLOCK_MAP_SIZE;
if (sbi->segs_per_sec > 1)
si->base_mem += MAIN_SECS(sbi) * sizeof(struct sec_entry);
si->base_mem += __bitmap_size(sbi, SIT_BITMAP);
@@ -145,7 +199,7 @@
/* 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);
@@ -155,20 +209,47 @@
/* build nm */
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);
+ si->base_mem += (NM_I(sbi)->nat_bits_blocks << F2FS_BLKSIZE_BITS);
+ si->base_mem += NM_I(sbi)->nat_blocks * NAT_ENTRY_BITMAP_SIZE;
+ si->base_mem += NM_I(sbi)->nat_blocks / 8;
+ si->base_mem += NM_I(sbi)->nat_blocks * sizeof(unsigned short);
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)->fcc_info)
+ si->cache_mem += sizeof(struct flush_cmd_control);
+ if (SM_I(sbi)->dcc_info) {
+ si->cache_mem += sizeof(struct discard_cmd_control);
+ si->cache_mem += sizeof(struct discard_cmd) *
+ atomic_read(&SM_I(sbi)->dcc_info->discard_cmd_cnt);
+ }
+
/* free nids */
- si->cache_mem = NM_I(sbi)->fcnt;
- si->cache_mem += NM_I(sbi)->nat_cnt;
+ si->cache_mem += (NM_I(sbi)->nid_cnt[FREE_NID_LIST] +
+ NM_I(sbi)->nid_cnt[ALLOC_NID_LIST]) *
+ 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)
@@ -183,23 +264,35 @@
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",
si->ssa_area_segs, si->main_area_segs);
seq_printf(s, "(OverProv:%d Resv:%d)]\n\n",
si->overp_segs, si->rsvd_segs);
- seq_printf(s, "Utilization: %d%% (%d valid blocks)\n",
- si->utilization, si->valid_count);
+ if (test_opt(si->sbi, DISCARD))
+ seq_printf(s, "Utilization: %u%% (%u valid blocks, %u discard blocks)\n",
+ si->utilization, si->valid_count, si->discard_blks);
+ else
+ seq_printf(s, "Utilization: %u%% (%u valid blocks)\n",
+ si->utilization, si->valid_count);
+
seq_printf(s, " - Node: %u (Inode: %u, ",
si->valid_node_count, si->valid_inode_count);
seq_printf(s, "Other: %u)\n - Data: %u\n",
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/Append/Update Inode: %u, %u, %u\n",
+ si->orphans, si->append, si->update);
seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n",
si->main_area_segs, si->main_area_sections,
si->main_area_zones);
@@ -233,27 +326,55 @@
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, " - IO (CP: %4d, Data: %4d, Flush: (%4d %4d), "
+ "Discard: (%4d %4d)) cmd: %4d undiscard:%4u\n",
+ si->nr_wb_cp_data, si->nr_wb_data,
+ si->nr_flushing, si->nr_flushed,
+ si->nr_discarding, si->nr_discarded,
+ si->nr_discard_cmd, si->undiscard_blks);
+ seq_printf(s, " - inmem: %4d, atomic IO: %4d (Max. %4d), "
+ "volatile IO: %4d (Max. %4d)\n",
+ si->inmem_pages, si->aw_cnt, si->max_aw_cnt,
+ si->vw_cnt, si->max_vw_cnt);
seq_printf(s, " - nodes: %4d 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, " - dents: %4d in dirs:%4d (%4d)\n",
+ si->ndirty_dent, si->ndirty_dirs, si->ndirty_all);
+ seq_printf(s, " - datas: %4d in files:%4d\n",
+ si->ndirty_data, si->ndirty_files);
seq_printf(s, " - meta: %4d 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, " - free_nids: %9d\n",
- si->fnids);
+ seq_printf(s, " - imeta: %4d\n",
+ si->ndirty_imeta);
+ seq_printf(s, " - NATs: %9d/%9d\n - SITs: %9d/%9d\n",
+ si->dirty_nats, si->nats, si->dirty_sits, si->sits);
+ seq_printf(s, " - free_nids: %9d/%9d\n - alloc_nids: %9d\n",
+ si->free_nids, si->avail_nids, si->alloc_nids);
seq_puts(s, "\nDistribution of User Blocks:");
seq_puts(s, " [ valid | invalid | free ]\n");
seq_puts(s, " [");
@@ -269,6 +390,7 @@
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 +403,14 @@
/* 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;
@@ -322,6 +449,21 @@
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);
+
+ atomic_set(&sbi->aw_cnt, 0);
+ atomic_set(&sbi->vw_cnt, 0);
+ atomic_set(&sbi->max_aw_cnt, 0);
+ atomic_set(&sbi->max_vw_cnt, 0);
+
mutex_lock(&f2fs_stat_mutex);
list_add_tail(&si->stat_list, &f2fs_stat_list);
mutex_unlock(&f2fs_stat_mutex);
@@ -340,20 +482,23 @@
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)
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index b54f871..f0333d1 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -17,8 +17,8 @@
static unsigned long dir_blocks(struct inode *inode)
{
- return ((unsigned long long) (i_size_read(inode) + PAGE_CACHE_SIZE - 1))
- >> PAGE_CACHE_SHIFT;
+ return ((unsigned long long) (i_size_read(inode) + PAGE_SIZE - 1))
+ >> PAGE_SHIFT;
}
static unsigned int dir_buckets(unsigned int level, int dir_level)
@@ -48,7 +48,6 @@
[F2FS_FT_SYMLINK] = DT_LNK,
};
-#define S_SHIFT 12
static unsigned char f2fs_type_by_mode[S_IFMT >> S_SHIFT] = {
[S_IFREG >> S_SHIFT] = F2FS_FT_REG_FILE,
[S_IFDIR >> S_SHIFT] = F2FS_FT_DIR,
@@ -59,12 +58,18 @@
[S_IFLNK >> S_SHIFT] = F2FS_FT_SYMLINK,
};
-static void set_de_type(struct f2fs_dir_entry *de, struct inode *inode)
+void set_de_type(struct f2fs_dir_entry *de, umode_t mode)
{
- umode_t mode = inode->i_mode;
de->file_type = f2fs_type_by_mode[(mode & S_IFMT) >> S_SHIFT];
}
+unsigned char get_de_type(struct f2fs_dir_entry *de)
+{
+ if (de->file_type < F2FS_FT_MAX)
+ return f2fs_filetype_table[de->file_type];
+ return DT_UNKNOWN;
+}
+
static unsigned long dir_block_index(unsigned int level,
int dir_level, unsigned int idx)
{
@@ -77,81 +82,85 @@
return bidx;
}
-static bool early_match_name(size_t namelen, f2fs_hash_t namehash,
- struct f2fs_dir_entry *de)
+static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
+ struct fscrypt_name *fname,
+ f2fs_hash_t namehash,
+ int *max_slots,
+ struct page **res_page)
{
- if (le16_to_cpu(de->name_len) != namelen)
- return false;
+ struct f2fs_dentry_block *dentry_blk;
+ struct f2fs_dir_entry *de;
+ struct f2fs_dentry_ptr d;
- if (de->hash_code != namehash)
- return false;
+ dentry_blk = (struct f2fs_dentry_block *)kmap(dentry_page);
- return true;
+ make_dentry_ptr_block(NULL, &d, dentry_blk);
+ de = find_target_dentry(fname, namehash, max_slots, &d);
+ if (de)
+ *res_page = dentry_page;
+ else
+ kunmap(dentry_page);
+
+ return de;
}
-static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
- struct qstr *name, int *max_slots,
- f2fs_hash_t namehash, struct page **res_page)
+struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname,
+ f2fs_hash_t namehash, int *max_slots,
+ struct f2fs_dentry_ptr *d)
{
struct f2fs_dir_entry *de;
unsigned long bit_pos = 0;
- struct f2fs_dentry_block *dentry_blk = kmap(dentry_page);
- const void *dentry_bits = &dentry_blk->dentry_bitmap;
int max_len = 0;
- while (bit_pos < NR_DENTRY_IN_BLOCK) {
- if (!test_bit_le(bit_pos, dentry_bits)) {
- if (bit_pos == 0)
- max_len = 1;
- else if (!test_bit_le(bit_pos - 1, dentry_bits))
- max_len++;
+ if (max_slots)
+ *max_slots = 0;
+ while (bit_pos < d->max) {
+ if (!test_bit_le(bit_pos, d->bitmap)) {
+ bit_pos++;
+ max_len++;
+ continue;
+ }
+
+ de = &d->dentry[bit_pos];
+
+ if (unlikely(!de->name_len)) {
bit_pos++;
continue;
}
- de = &dentry_blk->dentry[bit_pos];
- if (early_match_name(name->len, namehash, de)) {
- if (!memcmp(dentry_blk->filename[bit_pos],
- name->name,
- name->len)) {
- *res_page = dentry_page;
- goto found;
- }
- }
- if (max_len > *max_slots) {
- *max_slots = max_len;
- max_len = 0;
- }
- /*
- * For the most part, it should be a bug when name_len is zero.
- * We stop here for figuring out where the bugs has occurred.
- */
- f2fs_bug_on(F2FS_P_SB(dentry_page), !de->name_len);
+ if (de->hash_code == namehash &&
+ fscrypt_match_name(fname, d->filename[bit_pos],
+ le16_to_cpu(de->name_len)))
+ goto found;
+
+ if (max_slots && max_len > *max_slots)
+ *max_slots = max_len;
+ max_len = 0;
bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
}
de = NULL;
- kunmap(dentry_page);
found:
- if (max_len > *max_slots)
+ if (max_slots && max_len > *max_slots)
*max_slots = max_len;
return de;
}
static struct f2fs_dir_entry *find_in_level(struct inode *dir,
- unsigned int level, struct qstr *name,
- f2fs_hash_t namehash, struct page **res_page)
+ unsigned int level,
+ struct fscrypt_name *fname,
+ struct page **res_page)
{
- int s = GET_DENTRY_SLOTS(name->len);
+ struct qstr name = FSTR_TO_QSTR(&fname->disk_name);
+ int s = GET_DENTRY_SLOTS(name.len);
unsigned int nbucket, nblock;
unsigned int bidx, end_block;
struct page *dentry_page;
struct f2fs_dir_entry *de = NULL;
bool room = false;
- int max_slots = 0;
-
- f2fs_bug_on(F2FS_I_SB(dir), level > MAX_DIR_HASH_DEPTH);
+ int max_slots;
+ f2fs_hash_t namehash = f2fs_dentry_hash(&name, fname);
nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level);
nblock = bucket_blocks(level);
@@ -162,14 +171,19 @@
for (; bidx < end_block; bidx++) {
/* no need to allocate new dentry pages to all the indices */
- dentry_page = find_data_page(dir, bidx, true);
+ dentry_page = find_data_page(dir, bidx);
if (IS_ERR(dentry_page)) {
- room = true;
- continue;
+ if (PTR_ERR(dentry_page) == -ENOENT) {
+ room = true;
+ continue;
+ } else {
+ *res_page = dentry_page;
+ break;
+ }
}
- de = find_in_block(dentry_page, name, &max_slots,
- namehash, res_page);
+ de = find_in_block(dentry_page, fname, namehash, &max_slots,
+ res_page);
if (de)
break;
@@ -186,6 +200,47 @@
return de;
}
+struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
+ struct fscrypt_name *fname, struct page **res_page)
+{
+ unsigned long npages = dir_blocks(dir);
+ struct f2fs_dir_entry *de = NULL;
+ unsigned int max_depth;
+ unsigned int level;
+
+ if (f2fs_has_inline_dentry(dir)) {
+ *res_page = NULL;
+ de = find_in_inline_dir(dir, fname, res_page);
+ goto out;
+ }
+
+ if (npages == 0) {
+ *res_page = NULL;
+ goto out;
+ }
+
+ max_depth = F2FS_I(dir)->i_current_depth;
+ if (unlikely(max_depth > MAX_DIR_HASH_DEPTH)) {
+ f2fs_msg(F2FS_I_SB(dir)->sb, KERN_WARNING,
+ "Corrupted max_depth of %lu: %u",
+ dir->i_ino, max_depth);
+ max_depth = MAX_DIR_HASH_DEPTH;
+ f2fs_i_depth_write(dir, max_depth);
+ }
+
+ for (level = 0; level < max_depth; level++) {
+ *res_page = NULL;
+ de = find_in_level(dir, level, fname, res_page);
+ if (de || IS_ERR(*res_page))
+ break;
+ }
+out:
+ /* This is to increase the speed of f2fs_create */
+ if (!de)
+ F2FS_I(dir)->task = current;
+ return de;
+}
+
/*
* Find an entry in the specified directory with the wanted name.
* It returns the page where the entry was found (as a parameter - res_page),
@@ -195,60 +250,43 @@
struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
struct qstr *child, struct page **res_page)
{
- unsigned long npages = dir_blocks(dir);
struct f2fs_dir_entry *de = NULL;
- f2fs_hash_t name_hash;
- unsigned int max_depth;
- unsigned int level;
+ struct fscrypt_name fname;
+ int err;
- if (npages == 0)
+ err = fscrypt_setup_filename(dir, child, 1, &fname);
+ if (err) {
+ if (err == -ENOENT)
+ *res_page = NULL;
+ else
+ *res_page = ERR_PTR(err);
return NULL;
-
- *res_page = NULL;
-
- name_hash = f2fs_dentry_hash(child);
- max_depth = F2FS_I(dir)->i_current_depth;
-
- for (level = 0; level < max_depth; level++) {
- de = find_in_level(dir, level, child, name_hash, res_page);
- if (de)
- break;
}
- if (!de && F2FS_I(dir)->chash != name_hash) {
- F2FS_I(dir)->chash = name_hash;
- F2FS_I(dir)->clevel = level - 1;
- }
+
+ de = __f2fs_find_entry(dir, &fname, res_page);
+
+ fscrypt_free_filename(&fname);
return de;
}
struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p)
{
- struct page *page;
- struct f2fs_dir_entry *de;
- struct f2fs_dentry_block *dentry_blk;
+ struct qstr dotdot = QSTR_INIT("..", 2);
- page = get_lock_data_page(dir, 0);
- if (IS_ERR(page))
- return NULL;
-
- dentry_blk = kmap(page);
- de = &dentry_blk->dentry[1];
- *p = page;
- unlock_page(page);
- return de;
+ return f2fs_find_entry(dir, &dotdot, p);
}
-ino_t f2fs_inode_by_name(struct inode *dir, struct qstr *qstr)
+ino_t f2fs_inode_by_name(struct inode *dir, struct qstr *qstr,
+ struct page **page)
{
ino_t res = 0;
struct f2fs_dir_entry *de;
- struct page *page;
- de = f2fs_find_entry(dir, qstr, &page);
+ de = f2fs_find_entry(dir, qstr, page);
if (de) {
res = le32_to_cpu(de->ino);
- kunmap(page);
- f2fs_put_page(page, 0);
+ f2fs_dentry_kunmap(dir, *page);
+ f2fs_put_page(*page, 0);
}
return res;
@@ -257,15 +295,16 @@
void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
struct page *page, struct inode *inode)
{
+ enum page_type type = f2fs_has_inline_dentry(dir) ? NODE : DATA;
lock_page(page);
- f2fs_wait_on_page_writeback(page, DATA);
+ f2fs_wait_on_page_writeback(page, type, true);
de->ino = cpu_to_le32(inode->i_ino);
- set_de_type(de, inode);
- kunmap(page);
+ set_de_type(de, inode->i_mode);
+ f2fs_dentry_kunmap(dir, page);
set_page_dirty(page);
- dir->i_mtime = dir->i_ctime = CURRENT_TIME;
- mark_inode_dirty(dir);
+ dir->i_mtime = dir->i_ctime = current_time(dir);
+ f2fs_mark_inode_dirty_sync(dir, false);
f2fs_put_page(page, 1);
}
@@ -273,7 +312,7 @@
{
struct f2fs_inode *ri;
- f2fs_wait_on_page_writeback(ipage, NODE);
+ f2fs_wait_on_page_writeback(ipage, NODE, true);
/* copy name info. to this inode page */
ri = F2FS_INODE(ipage);
@@ -282,18 +321,17 @@
set_page_dirty(ipage);
}
-int update_dent_inode(struct inode *inode, const struct qstr *name)
+void do_make_empty_dir(struct inode *inode, struct inode *parent,
+ struct f2fs_dentry_ptr *d)
{
- struct page *page;
+ struct qstr dot = QSTR_INIT(".", 1);
+ struct qstr dotdot = QSTR_INIT("..", 2);
- page = get_node_page(F2FS_I_SB(inode), inode->i_ino);
- if (IS_ERR(page))
- return PTR_ERR(page);
+ /* update dirent of "." */
+ f2fs_update_dentry(inode->i_ino, inode->i_mode, d, &dot, 0, 0);
- init_dent_inode(name, page);
- f2fs_put_page(page, 1);
-
- return 0;
+ /* update dirent of ".." */
+ f2fs_update_dentry(parent->i_ino, parent->i_mode, d, &dotdot, 0, 1);
}
static int make_empty_dir(struct inode *inode,
@@ -301,31 +339,20 @@
{
struct page *dentry_page;
struct f2fs_dentry_block *dentry_blk;
- struct f2fs_dir_entry *de;
+ struct f2fs_dentry_ptr d;
+
+ if (f2fs_has_inline_dentry(inode))
+ return make_empty_inline_dir(inode, parent, page);
dentry_page = get_new_data_page(inode, page, 0, true);
if (IS_ERR(dentry_page))
return PTR_ERR(dentry_page);
-
dentry_blk = kmap_atomic(dentry_page);
- de = &dentry_blk->dentry[0];
- de->name_len = cpu_to_le16(1);
- de->hash_code = 0;
- de->ino = cpu_to_le32(inode->i_ino);
- memcpy(dentry_blk->filename[0], ".", 1);
- set_de_type(de, inode);
+ make_dentry_ptr_block(NULL, &d, dentry_blk);
+ do_make_empty_dir(inode, parent, &d);
- de = &dentry_blk->dentry[1];
- de->hash_code = 0;
- de->name_len = cpu_to_le16(2);
- de->ino = cpu_to_le32(parent->i_ino);
- memcpy(dentry_blk->filename[1], "..", 2);
- set_de_type(de, inode);
-
- test_and_set_bit_le(0, &dentry_blk->dentry_bitmap);
- test_and_set_bit_le(1, &dentry_blk->dentry_bitmap);
kunmap_atomic(dentry_blk);
set_page_dirty(dentry_page);
@@ -333,30 +360,42 @@
return 0;
}
-static struct page *init_inode_metadata(struct inode *inode,
- struct inode *dir, const struct qstr *name)
+struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
+ const struct qstr *new_name, const struct qstr *orig_name,
+ struct page *dpage)
{
struct page *page;
int err;
- if (is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) {
+ if (is_inode_flag_set(inode, FI_NEW_INODE)) {
page = new_inode_page(inode);
if (IS_ERR(page))
return page;
if (S_ISDIR(inode->i_mode)) {
+ /* in order to handle error case */
+ get_page(page);
err = make_empty_dir(inode, dir, page);
- if (err)
- goto error;
+ if (err) {
+ lock_page(page);
+ goto put_error;
+ }
+ put_page(page);
}
- err = f2fs_init_acl(inode, dir, page);
+ err = f2fs_init_acl(inode, dir, page, dpage);
if (err)
goto put_error;
- err = f2fs_init_security(inode, dir, name, page);
+ err = f2fs_init_security(inode, dir, orig_name, page);
if (err)
goto put_error;
+
+ if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode)) {
+ err = fscrypt_inherit_context(dir, inode, page, false);
+ if (err)
+ goto put_error;
+ }
} else {
page = get_node_page(F2FS_I_SB(dir), inode->i_ino);
if (IS_ERR(page))
@@ -365,14 +404,17 @@
set_cold_node(inode, page);
}
- if (name)
- init_dent_inode(name, page);
+ if (new_name) {
+ init_dent_inode(new_name, page);
+ if (f2fs_encrypted_inode(dir))
+ file_set_enc_name(inode);
+ }
/*
* This file should be checkpointed during fsync.
* We lost i_pino from now on.
*/
- if (is_inode_flag_set(F2FS_I(inode), FI_INC_LINK)) {
+ if (is_inode_flag_set(inode, FI_INC_LINK)) {
file_lost_pino(inode);
/*
* If link the tmpfile to alias through linkat path,
@@ -380,91 +422,97 @@
*/
if (inode->i_nlink == 0)
remove_orphan_inode(F2FS_I_SB(dir), inode->i_ino);
- inc_nlink(inode);
+ f2fs_i_links_write(inode, true);
}
return page;
put_error:
+ clear_nlink(inode);
+ update_inode(inode, page);
f2fs_put_page(page, 1);
-error:
- /* once the failed inode becomes a bad inode, i_mode is S_IFREG */
- truncate_inode_pages(&inode->i_data, 0);
- truncate_blocks(inode, 0, false);
- remove_dirty_dir_inode(inode);
- remove_inode_page(inode);
return ERR_PTR(err);
}
-static void update_parent_metadata(struct inode *dir, struct inode *inode,
+void update_parent_metadata(struct inode *dir, struct inode *inode,
unsigned int current_depth)
{
- if (is_inode_flag_set(F2FS_I(inode), FI_NEW_INODE)) {
- if (S_ISDIR(inode->i_mode)) {
- inc_nlink(dir);
- set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
- }
- clear_inode_flag(F2FS_I(inode), FI_NEW_INODE);
+ if (inode && is_inode_flag_set(inode, FI_NEW_INODE)) {
+ if (S_ISDIR(inode->i_mode))
+ f2fs_i_links_write(dir, true);
+ clear_inode_flag(inode, FI_NEW_INODE);
}
- dir->i_mtime = dir->i_ctime = CURRENT_TIME;
- mark_inode_dirty(dir);
+ dir->i_mtime = dir->i_ctime = current_time(dir);
+ f2fs_mark_inode_dirty_sync(dir, false);
- if (F2FS_I(dir)->i_current_depth != current_depth) {
- F2FS_I(dir)->i_current_depth = current_depth;
- set_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
- }
+ if (F2FS_I(dir)->i_current_depth != current_depth)
+ f2fs_i_depth_write(dir, current_depth);
- if (is_inode_flag_set(F2FS_I(inode), FI_INC_LINK))
- clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
+ if (inode && is_inode_flag_set(inode, FI_INC_LINK))
+ clear_inode_flag(inode, FI_INC_LINK);
}
-static int room_for_filename(struct f2fs_dentry_block *dentry_blk, int slots)
+int room_for_filename(const void *bitmap, int slots, int max_slots)
{
int bit_start = 0;
int zero_start, zero_end;
next:
- zero_start = find_next_zero_bit_le(&dentry_blk->dentry_bitmap,
- NR_DENTRY_IN_BLOCK,
- bit_start);
- if (zero_start >= NR_DENTRY_IN_BLOCK)
- return NR_DENTRY_IN_BLOCK;
+ zero_start = find_next_zero_bit_le(bitmap, max_slots, bit_start);
+ if (zero_start >= max_slots)
+ return max_slots;
- zero_end = find_next_bit_le(&dentry_blk->dentry_bitmap,
- NR_DENTRY_IN_BLOCK,
- zero_start);
+ zero_end = find_next_bit_le(bitmap, max_slots, zero_start);
if (zero_end - zero_start >= slots)
return zero_start;
bit_start = zero_end + 1;
- if (zero_end + 1 >= NR_DENTRY_IN_BLOCK)
- return NR_DENTRY_IN_BLOCK;
+ if (zero_end + 1 >= max_slots)
+ return max_slots;
goto next;
}
-/*
- * Caller should grab and release a rwsem by calling f2fs_lock_op() and
- * f2fs_unlock_op().
- */
-int __f2fs_add_link(struct inode *dir, const struct qstr *name,
- struct inode *inode)
+void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
+ const struct qstr *name, f2fs_hash_t name_hash,
+ unsigned int bit_pos)
+{
+ struct f2fs_dir_entry *de;
+ int slots = GET_DENTRY_SLOTS(name->len);
+ int i;
+
+ de = &d->dentry[bit_pos];
+ de->hash_code = name_hash;
+ de->name_len = cpu_to_le16(name->len);
+ memcpy(d->filename[bit_pos], name->name, name->len);
+ de->ino = cpu_to_le32(ino);
+ set_de_type(de, mode);
+ for (i = 0; i < slots; i++) {
+ __set_bit_le(bit_pos + i, (void *)d->bitmap);
+ /* avoid wrong garbage data for readdir */
+ if (i)
+ (de + i)->name_len = 0;
+ }
+}
+
+int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
+ const struct qstr *orig_name,
+ struct inode *inode, nid_t ino, umode_t mode)
{
unsigned int bit_pos;
unsigned int level;
unsigned int current_depth;
unsigned long bidx, block;
f2fs_hash_t dentry_hash;
- struct f2fs_dir_entry *de;
unsigned int nbucket, nblock;
- size_t namelen = name->len;
struct page *dentry_page = NULL;
struct f2fs_dentry_block *dentry_blk = NULL;
- int slots = GET_DENTRY_SLOTS(namelen);
- struct page *page;
- int err = 0;
- int i;
+ struct f2fs_dentry_ptr d;
+ struct page *page = NULL;
+ int slots, err = 0;
- dentry_hash = f2fs_dentry_hash(name);
level = 0;
+ slots = GET_DENTRY_SLOTS(new_name->len);
+ dentry_hash = f2fs_dentry_hash(new_name, NULL);
+
current_depth = F2FS_I(dir)->i_current_depth;
if (F2FS_I(dir)->chash == dentry_hash) {
level = F2FS_I(dir)->clevel;
@@ -472,6 +520,12 @@
}
start:
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(F2FS_I_SB(dir), FAULT_DIR_DEPTH)) {
+ f2fs_show_injection_info(FAULT_DIR_DEPTH);
+ return -ENOSPC;
+ }
+#endif
if (unlikely(current_depth == MAX_DIR_HASH_DEPTH))
return -ENOSPC;
@@ -491,7 +545,8 @@
return PTR_ERR(dentry_page);
dentry_blk = kmap(dentry_page);
- bit_pos = room_for_filename(dentry_blk, slots);
+ bit_pos = room_for_filename(&dentry_blk->dentry_bitmap,
+ slots, NR_DENTRY_IN_BLOCK);
if (bit_pos < NR_DENTRY_IN_BLOCK)
goto add_dentry;
@@ -503,39 +558,96 @@
++level;
goto start;
add_dentry:
- f2fs_wait_on_page_writeback(dentry_page, DATA);
+ f2fs_wait_on_page_writeback(dentry_page, DATA, true);
- down_write(&F2FS_I(inode)->i_sem);
- page = init_inode_metadata(inode, dir, name);
- if (IS_ERR(page)) {
- err = PTR_ERR(page);
- goto fail;
+ if (inode) {
+ down_write(&F2FS_I(inode)->i_sem);
+ page = init_inode_metadata(inode, dir, new_name,
+ orig_name, NULL);
+ if (IS_ERR(page)) {
+ err = PTR_ERR(page);
+ goto fail;
+ }
}
- de = &dentry_blk->dentry[bit_pos];
- de->hash_code = dentry_hash;
- de->name_len = cpu_to_le16(namelen);
- memcpy(dentry_blk->filename[bit_pos], name->name, name->len);
- de->ino = cpu_to_le32(inode->i_ino);
- set_de_type(de, inode);
- for (i = 0; i < slots; i++)
- test_and_set_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap);
+
+ make_dentry_ptr_block(NULL, &d, dentry_blk);
+ f2fs_update_dentry(ino, mode, &d, new_name, dentry_hash, bit_pos);
+
set_page_dirty(dentry_page);
- /* we don't need to mark_inode_dirty now */
- F2FS_I(inode)->i_pino = dir->i_ino;
- update_inode(inode, page);
- f2fs_put_page(page, 1);
+ if (inode) {
+ f2fs_i_pino_write(inode, dir->i_ino);
+ f2fs_put_page(page, 1);
+ }
update_parent_metadata(dir, inode, current_depth);
fail:
- up_write(&F2FS_I(inode)->i_sem);
+ if (inode)
+ up_write(&F2FS_I(inode)->i_sem);
- if (is_inode_flag_set(F2FS_I(dir), FI_UPDATE_DIR)) {
- update_inode_page(dir);
- clear_inode_flag(F2FS_I(dir), FI_UPDATE_DIR);
- }
kunmap(dentry_page);
f2fs_put_page(dentry_page, 1);
+
+ return err;
+}
+
+int __f2fs_do_add_link(struct inode *dir, struct fscrypt_name *fname,
+ struct inode *inode, nid_t ino, umode_t mode)
+{
+ struct qstr new_name;
+ int err = -EAGAIN;
+
+ new_name.name = fname_name(fname);
+ new_name.len = fname_len(fname);
+
+ if (f2fs_has_inline_dentry(dir))
+ err = f2fs_add_inline_entry(dir, &new_name, fname->usr_fname,
+ inode, ino, mode);
+ if (err == -EAGAIN)
+ err = f2fs_add_regular_entry(dir, &new_name, fname->usr_fname,
+ inode, ino, mode);
+
+ f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
+ return err;
+}
+
+/*
+ * Caller should grab and release a rwsem by calling f2fs_lock_op() and
+ * f2fs_unlock_op().
+ */
+int __f2fs_add_link(struct inode *dir, const struct qstr *name,
+ struct inode *inode, nid_t ino, umode_t mode)
+{
+ struct fscrypt_name fname;
+ struct page *page = NULL;
+ struct f2fs_dir_entry *de = NULL;
+ int err;
+
+ err = fscrypt_setup_filename(dir, name, 0, &fname);
+ if (err)
+ return err;
+
+ /*
+ * An immature stakable filesystem shows a race condition between lookup
+ * and create. If we have same task when doing lookup and create, it's
+ * definitely fine as expected by VFS normally. Otherwise, let's just
+ * verify on-disk dentry one more time, which guarantees filesystem
+ * consistency more.
+ */
+ if (current != F2FS_I(dir)->task) {
+ de = __f2fs_find_entry(dir, &fname, &page);
+ F2FS_I(dir)->task = NULL;
+ }
+ if (de) {
+ f2fs_dentry_kunmap(dir, page);
+ f2fs_put_page(page, 0);
+ err = -EEXIST;
+ } else if (IS_ERR(page)) {
+ err = PTR_ERR(page);
+ } else {
+ err = __f2fs_do_add_link(dir, &fname, inode, ino, mode);
+ }
+ fscrypt_free_filename(&fname);
return err;
}
@@ -545,41 +657,67 @@
int err = 0;
down_write(&F2FS_I(inode)->i_sem);
- page = init_inode_metadata(inode, dir, NULL);
+ page = init_inode_metadata(inode, dir, NULL, NULL, NULL);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto fail;
}
- /* we don't need to mark_inode_dirty now */
- update_inode(inode, page);
f2fs_put_page(page, 1);
- clear_inode_flag(F2FS_I(inode), FI_NEW_INODE);
+ clear_inode_flag(inode, FI_NEW_INODE);
fail:
up_write(&F2FS_I(inode)->i_sem);
+ f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return err;
}
+void f2fs_drop_nlink(struct inode *dir, struct inode *inode)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
+
+ down_write(&F2FS_I(inode)->i_sem);
+
+ if (S_ISDIR(inode->i_mode))
+ f2fs_i_links_write(dir, false);
+ inode->i_ctime = current_time(inode);
+
+ f2fs_i_links_write(inode, false);
+ if (S_ISDIR(inode->i_mode)) {
+ f2fs_i_links_write(inode, false);
+ f2fs_i_size_write(inode, 0);
+ }
+ up_write(&F2FS_I(inode)->i_sem);
+
+ if (inode->i_nlink == 0)
+ add_orphan_inode(inode);
+ else
+ release_orphan_inode(sbi);
+}
+
/*
* It only removes the dentry from the dentry page, corresponding name
* entry in name page does not need to be touched during deletion.
*/
void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
- struct inode *inode)
+ struct inode *dir, struct inode *inode)
{
struct f2fs_dentry_block *dentry_blk;
unsigned int bit_pos;
- struct inode *dir = page->mapping->host;
int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len));
int i;
+ f2fs_update_time(F2FS_I_SB(dir), REQ_TIME);
+
+ if (f2fs_has_inline_dentry(dir))
+ return f2fs_delete_inline_entry(dentry, page, dir, inode);
+
lock_page(page);
- f2fs_wait_on_page_writeback(page, DATA);
+ f2fs_wait_on_page_writeback(page, DATA, true);
dentry_blk = page_address(page);
bit_pos = dentry - dentry_blk->dentry;
for (i = 0; i < slots; i++)
- test_and_clear_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap);
+ __clear_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap);
/* Let's check and deallocate this dentry page */
bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
@@ -588,37 +726,19 @@
kunmap(page); /* kunmap - pair of f2fs_find_entry */
set_page_dirty(page);
- dir->i_ctime = dir->i_mtime = CURRENT_TIME;
+ dir->i_ctime = dir->i_mtime = current_time(dir);
+ f2fs_mark_inode_dirty_sync(dir, false);
- if (inode) {
- struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
+ if (inode)
+ f2fs_drop_nlink(dir, inode);
- down_write(&F2FS_I(inode)->i_sem);
-
- if (S_ISDIR(inode->i_mode)) {
- drop_nlink(dir);
- update_inode_page(dir);
- }
- inode->i_ctime = CURRENT_TIME;
- drop_nlink(inode);
- if (S_ISDIR(inode->i_mode)) {
- drop_nlink(inode);
- i_size_write(inode, 0);
- }
- up_write(&F2FS_I(inode)->i_sem);
- update_inode_page(inode);
-
- if (inode->i_nlink == 0)
- add_orphan_inode(sbi, inode->i_ino);
- else
- release_orphan_inode(sbi);
- }
-
- if (bit_pos == NR_DENTRY_IN_BLOCK) {
- truncate_hole(dir, page->index, page->index + 1);
+ if (bit_pos == NR_DENTRY_IN_BLOCK &&
+ !truncate_hole(dir, page->index, page->index + 1)) {
clear_page_dirty_for_io(page);
+ ClearPagePrivate(page);
ClearPageUptodate(page);
inode_dec_dirty_pages(dir);
+ remove_dirty_inode(dir);
}
f2fs_put_page(page, 1);
}
@@ -628,11 +748,14 @@
unsigned long bidx;
struct page *dentry_page;
unsigned int bit_pos;
- struct f2fs_dentry_block *dentry_blk;
+ struct f2fs_dentry_block *dentry_blk;
unsigned long nblock = dir_blocks(dir);
+ if (f2fs_has_inline_dentry(dir))
+ return f2fs_empty_inline_dir(dir);
+
for (bidx = 0; bidx < nblock; bidx++) {
- dentry_page = get_lock_data_page(dir, bidx);
+ dentry_page = get_lock_data_page(dir, bidx, false);
if (IS_ERR(dentry_page)) {
if (PTR_ERR(dentry_page) == -ENOENT)
continue;
@@ -640,7 +763,6 @@
return false;
}
-
dentry_blk = kmap_atomic(dentry_page);
if (bidx == 0)
bit_pos = 2;
@@ -659,19 +781,83 @@
return true;
}
+int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
+ unsigned int start_pos, struct fscrypt_str *fstr)
+{
+ unsigned char d_type = DT_UNKNOWN;
+ unsigned int bit_pos;
+ struct f2fs_dir_entry *de = NULL;
+ struct fscrypt_str de_name = FSTR_INIT(NULL, 0);
+
+ bit_pos = ((unsigned long)ctx->pos % d->max);
+
+ while (bit_pos < d->max) {
+ bit_pos = find_next_bit_le(d->bitmap, d->max, bit_pos);
+ if (bit_pos >= d->max)
+ break;
+
+ de = &d->dentry[bit_pos];
+ if (de->name_len == 0) {
+ bit_pos++;
+ ctx->pos = start_pos + bit_pos;
+ continue;
+ }
+
+ d_type = get_de_type(de);
+
+ de_name.name = d->filename[bit_pos];
+ de_name.len = le16_to_cpu(de->name_len);
+
+ if (f2fs_encrypted_inode(d->inode)) {
+ int save_len = fstr->len;
+ int err;
+
+ err = fscrypt_fname_disk_to_usr(d->inode,
+ (u32)de->hash_code, 0,
+ &de_name, fstr);
+ if (err)
+ return err;
+
+ de_name = *fstr;
+ fstr->len = save_len;
+ }
+
+ if (!dir_emit(ctx, de_name.name, de_name.len,
+ le32_to_cpu(de->ino), d_type))
+ return 1;
+
+ bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
+ ctx->pos = start_pos + bit_pos;
+ }
+ return 0;
+}
+
static int f2fs_readdir(struct file *file, struct dir_context *ctx)
{
struct inode *inode = file_inode(file);
unsigned long npages = dir_blocks(inode);
- unsigned int bit_pos = 0;
struct f2fs_dentry_block *dentry_blk = NULL;
- struct f2fs_dir_entry *de = NULL;
struct page *dentry_page = NULL;
struct file_ra_state *ra = &file->f_ra;
unsigned int n = ((unsigned long)ctx->pos / NR_DENTRY_IN_BLOCK);
- unsigned char d_type = DT_UNKNOWN;
+ struct f2fs_dentry_ptr d;
+ struct fscrypt_str fstr = FSTR_INIT(NULL, 0);
+ int err = 0;
- bit_pos = ((unsigned long)ctx->pos % NR_DENTRY_IN_BLOCK);
+ if (f2fs_encrypted_inode(inode)) {
+ err = fscrypt_get_encryption_info(inode);
+ if (err && err != -ENOKEY)
+ return err;
+
+ err = fscrypt_fname_alloc_buffer(inode, F2FS_NAME_LEN, &fstr);
+ if (err < 0)
+ return err;
+ }
+
+ if (f2fs_has_inline_dentry(inode)) {
+ err = f2fs_read_inline_dir(file, ctx, &fstr);
+ goto out;
+ }
/* readahead for multi pages of dir */
if (npages - n > 1 && !ra_has_index(ra, n))
@@ -679,44 +865,42 @@
min(npages - n, (pgoff_t)MAX_DIR_RA_PAGES));
for (; n < npages; n++) {
- dentry_page = get_lock_data_page(inode, n);
- if (IS_ERR(dentry_page))
- continue;
+ dentry_page = get_lock_data_page(inode, n, false);
+ if (IS_ERR(dentry_page)) {
+ err = PTR_ERR(dentry_page);
+ if (err == -ENOENT) {
+ err = 0;
+ continue;
+ } else {
+ goto out;
+ }
+ }
dentry_blk = kmap(dentry_page);
- while (bit_pos < NR_DENTRY_IN_BLOCK) {
- bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
- NR_DENTRY_IN_BLOCK,
- bit_pos);
- if (bit_pos >= NR_DENTRY_IN_BLOCK)
- break;
- de = &dentry_blk->dentry[bit_pos];
- if (de->file_type < F2FS_FT_MAX)
- d_type = f2fs_filetype_table[de->file_type];
- else
- d_type = DT_UNKNOWN;
- if (!dir_emit(ctx,
- dentry_blk->filename[bit_pos],
- le16_to_cpu(de->name_len),
- le32_to_cpu(de->ino), d_type))
- goto stop;
+ make_dentry_ptr_block(inode, &d, dentry_blk);
- bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
- ctx->pos = n * NR_DENTRY_IN_BLOCK + bit_pos;
+ err = f2fs_fill_dentries(ctx, &d,
+ n * NR_DENTRY_IN_BLOCK, &fstr);
+ if (err) {
+ kunmap(dentry_page);
+ f2fs_put_page(dentry_page, 1);
+ break;
}
- bit_pos = 0;
+
ctx->pos = (n + 1) * NR_DENTRY_IN_BLOCK;
kunmap(dentry_page);
f2fs_put_page(dentry_page, 1);
- dentry_page = NULL;
}
-stop:
- if (dentry_page && !IS_ERR(dentry_page)) {
- kunmap(dentry_page);
- f2fs_put_page(dentry_page, 1);
- }
+out:
+ fscrypt_fname_free_buffer(&fstr);
+ return err < 0 ? err : 0;
+}
+static int f2fs_dir_open(struct inode *inode, struct file *filp)
+{
+ if (f2fs_encrypted_inode(inode))
+ return fscrypt_get_encryption_info(inode) ? -EACCES : 0;
return 0;
}
@@ -725,5 +909,9 @@
.read = generic_read_dir,
.iterate = f2fs_readdir,
.fsync = f2fs_sync_file,
+ .open = f2fs_dir_open,
.unlocked_ioctl = f2fs_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = f2fs_compat_ioctl,
+#endif
};
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
new file mode 100644
index 0000000..2f98d70
--- /dev/null
+++ b/fs/f2fs/extent_cache.c
@@ -0,0 +1,809 @@
+/*
+ * 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 rb_entry *__lookup_rb_tree_fast(struct rb_entry *cached_re,
+ unsigned int ofs)
+{
+ if (cached_re) {
+ if (cached_re->ofs <= ofs &&
+ cached_re->ofs + cached_re->len > ofs) {
+ return cached_re;
+ }
+ }
+ return NULL;
+}
+
+static struct rb_entry *__lookup_rb_tree_slow(struct rb_root *root,
+ unsigned int ofs)
+{
+ struct rb_node *node = root->rb_node;
+ struct rb_entry *re;
+
+ while (node) {
+ re = rb_entry(node, struct rb_entry, rb_node);
+
+ if (ofs < re->ofs)
+ node = node->rb_left;
+ else if (ofs >= re->ofs + re->len)
+ node = node->rb_right;
+ else
+ return re;
+ }
+ return NULL;
+}
+
+struct rb_entry *__lookup_rb_tree(struct rb_root *root,
+ struct rb_entry *cached_re, unsigned int ofs)
+{
+ struct rb_entry *re;
+
+ re = __lookup_rb_tree_fast(cached_re, ofs);
+ if (!re)
+ return __lookup_rb_tree_slow(root, ofs);
+
+ return re;
+}
+
+struct rb_node **__lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
+ struct rb_root *root, struct rb_node **parent,
+ unsigned int ofs)
+{
+ struct rb_node **p = &root->rb_node;
+ struct rb_entry *re;
+
+ while (*p) {
+ *parent = *p;
+ re = rb_entry(*parent, struct rb_entry, rb_node);
+
+ if (ofs < re->ofs)
+ p = &(*p)->rb_left;
+ else if (ofs >= re->ofs + re->len)
+ p = &(*p)->rb_right;
+ else
+ f2fs_bug_on(sbi, 1);
+ }
+
+ return p;
+}
+
+/*
+ * lookup rb entry in position of @ofs in rb-tree,
+ * if hit, return the entry, otherwise, return NULL
+ * @prev_ex: extent before ofs
+ * @next_ex: extent after ofs
+ * @insert_p: insert point for new extent at ofs
+ * in order to simpfy the insertion after.
+ * tree must stay unchanged between lookup and insertion.
+ */
+struct rb_entry *__lookup_rb_tree_ret(struct rb_root *root,
+ struct rb_entry *cached_re,
+ unsigned int ofs,
+ struct rb_entry **prev_entry,
+ struct rb_entry **next_entry,
+ struct rb_node ***insert_p,
+ struct rb_node **insert_parent,
+ bool force)
+{
+ struct rb_node **pnode = &root->rb_node;
+ struct rb_node *parent = NULL, *tmp_node;
+ struct rb_entry *re = cached_re;
+
+ *insert_p = NULL;
+ *insert_parent = NULL;
+ *prev_entry = NULL;
+ *next_entry = NULL;
+
+ if (RB_EMPTY_ROOT(root))
+ return NULL;
+
+ if (re) {
+ if (re->ofs <= ofs && re->ofs + re->len > ofs)
+ goto lookup_neighbors;
+ }
+
+ while (*pnode) {
+ parent = *pnode;
+ re = rb_entry(*pnode, struct rb_entry, rb_node);
+
+ if (ofs < re->ofs)
+ pnode = &(*pnode)->rb_left;
+ else if (ofs >= re->ofs + re->len)
+ pnode = &(*pnode)->rb_right;
+ else
+ goto lookup_neighbors;
+ }
+
+ *insert_p = pnode;
+ *insert_parent = parent;
+
+ re = rb_entry(parent, struct rb_entry, rb_node);
+ tmp_node = parent;
+ if (parent && ofs > re->ofs)
+ tmp_node = rb_next(parent);
+ *next_entry = rb_entry_safe(tmp_node, struct rb_entry, rb_node);
+
+ tmp_node = parent;
+ if (parent && ofs < re->ofs)
+ tmp_node = rb_prev(parent);
+ *prev_entry = rb_entry_safe(tmp_node, struct rb_entry, rb_node);
+ return NULL;
+
+lookup_neighbors:
+ if (ofs == re->ofs || force) {
+ /* lookup prev node for merging backward later */
+ tmp_node = rb_prev(&re->rb_node);
+ *prev_entry = rb_entry_safe(tmp_node, struct rb_entry, rb_node);
+ }
+ if (ofs == re->ofs + re->len - 1 || force) {
+ /* lookup next node for merging frontward later */
+ tmp_node = rb_next(&re->rb_node);
+ *next_entry = rb_entry_safe(tmp_node, struct rb_entry, rb_node);
+ }
+ return re;
+}
+
+bool __check_rb_tree_consistence(struct f2fs_sb_info *sbi,
+ struct rb_root *root)
+{
+#ifdef CONFIG_F2FS_CHECK_FS
+ struct rb_node *cur = rb_first(root), *next;
+ struct rb_entry *cur_re, *next_re;
+
+ if (!cur)
+ return true;
+
+ while (cur) {
+ next = rb_next(cur);
+ if (!next)
+ return true;
+
+ cur_re = rb_entry(cur, struct rb_entry, rb_node);
+ next_re = rb_entry(next, struct rb_entry, rb_node);
+
+ if (cur_re->ofs + cur_re->len > next_re->ofs) {
+ f2fs_msg(sbi->sb, KERN_INFO, "inconsistent rbtree, "
+ "cur(%u, %u) next(%u, %u)",
+ cur_re->ofs, cur_re->len,
+ next_re->ofs, next_re->len);
+ return false;
+ }
+
+ cur = next;
+ }
+#endif
+ return true;
+}
+
+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;
+
+ mutex_lock(&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);
+ }
+ mutex_unlock(&sbi->extent_tree_lock);
+
+ /* never died until evict_inode */
+ F2FS_I(inode)->extent_tree = et;
+
+ return et;
+}
+
+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, true);
+ }
+}
+
+/* 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 = (struct extent_node *)__lookup_rb_tree(&et->root,
+ (struct rb_entry *)et->cached_en, pgofs);
+ if (!en)
+ goto out;
+
+ if (en == et->cached_en)
+ stat_inc_cached_node_hit(sbi);
+ else
+ stat_inc_rbtree_node_hit(sbi);
+
+ *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;
+}
+
+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)) {
+ next_ex->ei.fofs = ei->fofs;
+ next_ex->ei.blk = ei->blk;
+ next_ex->ei.len += ei->len;
+ if (en)
+ __release_extent_node(sbi, et, prev_ex);
+
+ 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;
+ }
+
+ p = __lookup_rb_tree_for_insert(sbi, &et->root, &parent, ei->fofs);
+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 void 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;
+
+ 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;
+ }
+
+ 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 = (struct extent_node *)__lookup_rb_tree_ret(&et->root,
+ (struct rb_entry *)et->cached_en, fofs,
+ (struct rb_entry **)&prev_en,
+ (struct rb_entry **)&next_en,
+ &insert_p, &insert_parent, false);
+ 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 = rb_entry_safe(node, struct extent_node,
+ rb_node);
+ }
+
+ 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);
+}
+
+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 (!mutex_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();
+ }
+ mutex_unlock(&sbi->extent_tree_lock);
+
+free_node:
+ /* 2. remove LRU extent entries */
+ if (!mutex_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:
+ mutex_unlock(&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)) {
+ mutex_lock(&sbi->extent_tree_lock);
+ list_add_tail(&et->list, &sbi->zombie_list);
+ atomic_inc(&sbi->total_zombie_tree);
+ mutex_unlock(&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 */
+ mutex_lock(&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);
+ mutex_unlock(&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);
+ mutex_init(&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);
+}
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 8171e80..208689f 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -19,6 +19,16 @@
#include <linux/magic.h>
#include <linux/kobject.h>
#include <linux/sched.h>
+#include <linux/vmalloc.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+#include <linux/fscrypt_supp.h>
+#else
+#include <linux/fscrypt_notsupp.h>
+#endif
+#include <crypto/hash.h>
+#include <linux/writeback.h>
#ifdef CONFIG_F2FS_CHECK_FS
#define f2fs_bug_on(sbi, condition) BUG_ON(condition)
@@ -28,10 +38,34 @@
do { \
if (unlikely(condition)) { \
WARN_ON(1); \
- sbi->need_fsck = true; \
+ set_sbi_flag(sbi, SBI_NEED_FSCK); \
} \
} while (0)
-#define f2fs_down_write(x, y) down_write(x)
+#endif
+
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+enum {
+ FAULT_KMALLOC,
+ FAULT_PAGE_ALLOC,
+ FAULT_ALLOC_NID,
+ FAULT_ORPHAN,
+ FAULT_BLOCK,
+ FAULT_DIR_DEPTH,
+ FAULT_EVICT_INODE,
+ FAULT_TRUNCATE,
+ FAULT_IO,
+ FAULT_CHECKPOINT,
+ FAULT_MAX,
+};
+
+struct f2fs_fault_info {
+ atomic_t inject_ops;
+ unsigned int inject_rate;
+ unsigned int inject_type;
+};
+
+extern char *fault_name[FAULT_MAX];
+#define IS_FAULT_SET(fi, type) ((fi)->inject_type & (1 << (type)))
#endif
/*
@@ -46,12 +80,20 @@
#define F2FS_MOUNT_DISABLE_EXT_IDENTIFY 0x00000040
#define F2FS_MOUNT_INLINE_XATTR 0x00000080
#define F2FS_MOUNT_INLINE_DATA 0x00000100
-#define F2FS_MOUNT_FLUSH_MERGE 0x00000200
-#define F2FS_MOUNT_NOBARRIER 0x00000400
+#define F2FS_MOUNT_INLINE_DENTRY 0x00000200
+#define F2FS_MOUNT_FLUSH_MERGE 0x00000400
+#define F2FS_MOUNT_NOBARRIER 0x00000800
+#define F2FS_MOUNT_FASTBOOT 0x00001000
+#define F2FS_MOUNT_EXTENT_CACHE 0x00002000
+#define F2FS_MOUNT_FORCE_FG_GC 0x00004000
+#define F2FS_MOUNT_DATA_FLUSH 0x00008000
+#define F2FS_MOUNT_FAULT_INJECTION 0x00010000
+#define F2FS_MOUNT_ADAPTIVE 0x00020000
+#define F2FS_MOUNT_LFS 0x00040000
-#define clear_opt(sbi, option) (sbi->mount_opt.opt &= ~F2FS_MOUNT_##option)
-#define set_opt(sbi, option) (sbi->mount_opt.opt |= F2FS_MOUNT_##option)
-#define test_opt(sbi, option) (sbi->mount_opt.opt & F2FS_MOUNT_##option)
+#define clear_opt(sbi, option) ((sbi)->mount_opt.opt &= ~F2FS_MOUNT_##option)
+#define set_opt(sbi, option) ((sbi)->mount_opt.opt |= F2FS_MOUNT_##option)
+#define test_opt(sbi, option) ((sbi)->mount_opt.opt & F2FS_MOUNT_##option)
#define ver_after(a, b) (typecheck(unsigned long long, a) && \
typecheck(unsigned long long, b) && \
@@ -67,25 +109,111 @@
unsigned int opt;
};
-#define CRCPOLY_LE 0xedb88320
+#define F2FS_FEATURE_ENCRYPT 0x0001
+#define F2FS_FEATURE_BLKZONED 0x0002
-static inline __u32 f2fs_crc32(void *buf, size_t len)
+#define F2FS_HAS_FEATURE(sb, mask) \
+ ((F2FS_SB(sb)->raw_super->feature & cpu_to_le32(mask)) != 0)
+#define F2FS_SET_FEATURE(sb, mask) \
+ (F2FS_SB(sb)->raw_super->feature |= cpu_to_le32(mask))
+#define F2FS_CLEAR_FEATURE(sb, mask) \
+ (F2FS_SB(sb)->raw_super->feature &= ~cpu_to_le32(mask))
+
+/* bio stuffs */
+#define REQ_OP_READ READ
+#define REQ_OP_WRITE WRITE
+#define bio_op(bio) ((bio)->bi_rw & 1)
+
+static inline void bio_set_op_attrs(struct bio *bio, unsigned op,
+ unsigned op_flags)
{
- unsigned char *p = (unsigned char *)buf;
- __u32 crc = F2FS_SUPER_MAGIC;
- int i;
-
- while (len--) {
- crc ^= *p++;
- for (i = 0; i < 8; i++)
- crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0);
- }
- return crc;
+ bio->bi_rw = op | op_flags;
}
-static inline bool f2fs_crc_valid(__u32 blk_crc, void *buf, size_t buf_size)
+static inline int wbc_to_write_flags(struct writeback_control *wbc)
{
- return f2fs_crc32(buf, buf_size) == blk_crc;
+ if (wbc->sync_mode == WB_SYNC_ALL)
+ return REQ_SYNC;
+ return 0;
+}
+
+static inline void inode_lock(struct inode *inode)
+{
+ mutex_lock(&inode->i_mutex);
+}
+
+static inline int inode_trylock(struct inode *inode)
+{
+ return mutex_trylock(&inode->i_mutex);
+}
+
+static inline void inode_unlock(struct inode *inode)
+{
+ mutex_unlock(&inode->i_mutex);
+}
+
+#define rb_entry_safe(ptr, type, member) \
+ ({ typeof(ptr) ____ptr = (ptr); \
+ ____ptr ? rb_entry(____ptr, type, member) : NULL; \
+ })
+
+#define list_last_entry(ptr, type, member) \
+ list_entry((ptr)->prev, type, member)
+
+#define list_first_entry(ptr, type, member) \
+ list_entry((ptr)->next, type, member)
+
+/**
+ * wq_has_sleeper - check if there are any waiting processes
+ * @wq: wait queue head
+ *
+ * Returns true if wq has waiting processes
+ *
+ * Please refer to the comment for waitqueue_active.
+ */
+static inline bool wq_has_sleeper(wait_queue_head_t *wq)
+{
+ /*
+ * We need to be sure we are in sync with the
+ * add_wait_queue modifications to the wait queue.
+ *
+ * This memory barrier should be paired with one on the
+ * waiting side.
+ */
+ smp_mb();
+ return waitqueue_active(wq);
+}
+
+static inline struct dentry *file_dentry(const struct file *file)
+{
+ return file->f_path.dentry;
+}
+
+static inline void inode_nohighmem(struct inode *inode)
+{
+ mapping_set_gfp_mask(inode->i_mapping, GFP_USER);
+}
+
+/**
+ * current_time - Return FS time
+ * @inode: inode.
+ *
+ * Return the current time truncated to the time granularity supported by
+ * the fs.
+ *
+ * Note that inode and inode->sb cannot be NULL.
+ * Otherwise, the function warns and returns time without truncation.
+ */
+static inline struct timespec current_time(struct inode *inode)
+{
+ struct timespec now = current_kernel_time();
+
+ if (unlikely(!inode->i_sb)) {
+ WARN(1, "current_time() called with uninitialized super_block in the inode");
+ return now;
+ }
+
+ return timespec_trunc(now, inode->i_sb->s_time_gran);
}
/*
@@ -96,11 +224,22 @@
SIT_BITMAP
};
-enum {
- CP_UMOUNT,
- CP_SYNC,
- CP_DISCARD,
-};
+#define CP_UMOUNT 0x00000001
+#define CP_FASTBOOT 0x00000002
+#define CP_SYNC 0x00000004
+#define CP_RECOVERY 0x00000008
+#define CP_DISCARD 0x00000010
+#define CP_TRIMMED 0x00000020
+
+#define DEF_BATCHED_TRIM_SECTIONS 2048
+#define BATCHED_TRIM_SEGMENTS(sbi) \
+ (GET_SEG_FROM_SEC(sbi, SM_I(sbi)->trim_sections))
+#define BATCHED_TRIM_BLOCKS(sbi) \
+ (BATCHED_TRIM_SEGMENTS(sbi) << (sbi)->log_blocks_per_seg)
+#define MAX_DISCARD_BLOCKS(sbi) BLKS_PER_SEC(sbi)
+#define DISCARD_ISSUE_RATE 8
+#define DEF_CP_INTERVAL 60 /* 60 secs */
+#define DEF_IDLE_INTERVAL 5 /* 5 secs */
struct cp_control {
int reason;
@@ -134,17 +273,69 @@
nid_t ino; /* inode number */
};
-/* for the list of directory inodes */
-struct dir_inode_entry {
+/* for the list of inodes to be GCed */
+struct inode_entry {
struct list_head list; /* list head */
struct inode *inode; /* vfs inode pointer */
};
-/* for the list of blockaddresses to be discarded */
+/* for the bitmap indicate blocks to be discarded */
struct discard_entry {
struct list_head list; /* list head */
- block_t blkaddr; /* block address to be discarded */
- int len; /* # of consecutive blocks of the discard */
+ block_t start_blkaddr; /* start blockaddr of current segment */
+ unsigned char discard_map[SIT_VBLOCK_MAP_SIZE]; /* segment discard bitmap */
+};
+
+/* max discard pend list number */
+#define MAX_PLIST_NUM 512
+#define plist_idx(blk_num) ((blk_num) >= MAX_PLIST_NUM ? \
+ (MAX_PLIST_NUM - 1) : (blk_num - 1))
+
+enum {
+ D_PREP,
+ D_SUBMIT,
+ D_DONE,
+};
+
+struct discard_info {
+ block_t lstart; /* logical start address */
+ block_t len; /* length */
+ block_t start; /* actual start address in dev */
+};
+
+struct discard_cmd {
+ struct rb_node rb_node; /* rb node located in rb-tree */
+ union {
+ struct {
+ block_t lstart; /* logical start address */
+ block_t len; /* length */
+ block_t start; /* actual start address in dev */
+ };
+ struct discard_info di; /* discard info */
+
+ };
+ struct list_head list; /* command list */
+ struct completion wait; /* compleation */
+ struct block_device *bdev; /* bdev */
+ unsigned short ref; /* reference count */
+ unsigned char state; /* state */
+ int error; /* bio error */
+};
+
+struct discard_cmd_control {
+ struct task_struct *f2fs_issue_discard; /* discard thread */
+ struct list_head entry_list; /* 4KB discard entry list */
+ struct list_head pend_list[MAX_PLIST_NUM];/* store pending entries */
+ struct list_head wait_list; /* store on-flushing entries */
+ wait_queue_head_t discard_wait_queue; /* waiting queue for wake-up */
+ struct mutex cmd_lock;
+ unsigned int nr_discards; /* # of discards in the list */
+ unsigned int max_discards; /* max. discards to be issued */
+ unsigned int undiscard_blks; /* # of undiscard blocks */
+ atomic_t issued_discard; /* # of issued discard */
+ atomic_t issing_discard; /* # of issing discard */
+ atomic_t discard_cmd_cnt; /* # of cached cmd count */
+ struct rb_root root; /* root of discard rb-tree */
};
/* for the list of fsync inodes, used only during recovery */
@@ -153,40 +344,41 @@
struct inode *inode; /* vfs inode pointer */
block_t blkaddr; /* block address locating the last fsync */
block_t last_dentry; /* block address locating the last dentry */
- block_t last_inode; /* block address locating the last inode */
};
-#define nats_in_cursum(sum) (le16_to_cpu(sum->n_nats))
-#define sits_in_cursum(sum) (le16_to_cpu(sum->n_sits))
+#define nats_in_cursum(jnl) (le16_to_cpu((jnl)->n_nats))
+#define sits_in_cursum(jnl) (le16_to_cpu((jnl)->n_sits))
-#define nat_in_journal(sum, i) (sum->nat_j.entries[i].ne)
-#define nid_in_journal(sum, i) (sum->nat_j.entries[i].nid)
-#define sit_in_journal(sum, i) (sum->sit_j.entries[i].se)
-#define segno_in_journal(sum, i) (sum->sit_j.entries[i].segno)
+#define nat_in_journal(jnl, i) ((jnl)->nat_j.entries[i].ne)
+#define nid_in_journal(jnl, i) ((jnl)->nat_j.entries[i].nid)
+#define sit_in_journal(jnl, i) ((jnl)->sit_j.entries[i].se)
+#define segno_in_journal(jnl, i) ((jnl)->sit_j.entries[i].segno)
-#define MAX_NAT_JENTRIES(sum) (NAT_JOURNAL_ENTRIES - nats_in_cursum(sum))
-#define MAX_SIT_JENTRIES(sum) (SIT_JOURNAL_ENTRIES - sits_in_cursum(sum))
+#define MAX_NAT_JENTRIES(jnl) (NAT_JOURNAL_ENTRIES - nats_in_cursum(jnl))
+#define MAX_SIT_JENTRIES(jnl) (SIT_JOURNAL_ENTRIES - sits_in_cursum(jnl))
-static inline int update_nats_in_cursum(struct f2fs_summary_block *rs, int i)
+static inline int update_nats_in_cursum(struct f2fs_journal *journal, int i)
{
- int before = nats_in_cursum(rs);
- rs->n_nats = cpu_to_le16(before + i);
+ int before = nats_in_cursum(journal);
+
+ journal->n_nats = cpu_to_le16(before + i);
return before;
}
-static inline int update_sits_in_cursum(struct f2fs_summary_block *rs, int i)
+static inline int update_sits_in_cursum(struct f2fs_journal *journal, int i)
{
- int before = sits_in_cursum(rs);
- rs->n_sits = cpu_to_le16(before + i);
+ int before = sits_in_cursum(journal);
+
+ journal->n_sits = cpu_to_le16(before + i);
return before;
}
-static inline bool __has_cursum_space(struct f2fs_summary_block *sum, int size,
- int type)
+static inline bool __has_cursum_space(struct f2fs_journal *journal,
+ int size, int type)
{
if (type == NAT_JOURNAL)
- return size <= MAX_NAT_JENTRIES(sum);
- return size <= MAX_SIT_JENTRIES(sum);
+ return size <= MAX_NAT_JENTRIES(journal);
+ return size <= MAX_SIT_JENTRIES(journal);
}
/*
@@ -194,23 +386,95 @@
*/
#define F2FS_IOC_GETFLAGS FS_IOC_GETFLAGS
#define F2FS_IOC_SETFLAGS FS_IOC_SETFLAGS
+#define F2FS_IOC_GETVERSION FS_IOC_GETVERSION
#define F2FS_IOCTL_MAGIC 0xf5
#define F2FS_IOC_START_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 1)
#define F2FS_IOC_COMMIT_ATOMIC_WRITE _IO(F2FS_IOCTL_MAGIC, 2)
#define F2FS_IOC_START_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 3)
+#define F2FS_IOC_RELEASE_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 4)
+#define F2FS_IOC_ABORT_VOLATILE_WRITE _IO(F2FS_IOCTL_MAGIC, 5)
+#define F2FS_IOC_GARBAGE_COLLECT _IOW(F2FS_IOCTL_MAGIC, 6, __u32)
+#define F2FS_IOC_WRITE_CHECKPOINT _IO(F2FS_IOCTL_MAGIC, 7)
+#define F2FS_IOC_DEFRAGMENT _IOWR(F2FS_IOCTL_MAGIC, 8, \
+ struct f2fs_defragment)
+#define F2FS_IOC_MOVE_RANGE _IOWR(F2FS_IOCTL_MAGIC, 9, \
+ struct f2fs_move_range)
+#define F2FS_IOC_FLUSH_DEVICE _IOW(F2FS_IOCTL_MAGIC, 10, \
+ struct f2fs_flush_device)
+
+#define F2FS_IOC_SET_ENCRYPTION_POLICY FS_IOC_SET_ENCRYPTION_POLICY
+#define F2FS_IOC_GET_ENCRYPTION_POLICY FS_IOC_GET_ENCRYPTION_POLICY
+#define F2FS_IOC_GET_ENCRYPTION_PWSALT FS_IOC_GET_ENCRYPTION_PWSALT
+
+/*
+ * should be same as XFS_IOC_GOINGDOWN.
+ * Flags for going down operation used by FS_IOC_GOINGDOWN
+ */
+#define F2FS_IOC_SHUTDOWN _IOR('X', 125, __u32) /* Shutdown */
+#define F2FS_GOING_DOWN_FULLSYNC 0x0 /* going down with full sync */
+#define F2FS_GOING_DOWN_METASYNC 0x1 /* going down with metadata */
+#define F2FS_GOING_DOWN_NOSYNC 0x2 /* going down */
+#define F2FS_GOING_DOWN_METAFLUSH 0x3 /* going down with meta flush */
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/*
* ioctl commands in 32 bit emulation
*/
-#define F2FS_IOC32_GETFLAGS FS_IOC32_GETFLAGS
-#define F2FS_IOC32_SETFLAGS FS_IOC32_SETFLAGS
+#define F2FS_IOC32_GETFLAGS FS_IOC32_GETFLAGS
+#define F2FS_IOC32_SETFLAGS FS_IOC32_SETFLAGS
+#define F2FS_IOC32_GETVERSION FS_IOC32_GETVERSION
#endif
+struct f2fs_defragment {
+ u64 start;
+ u64 len;
+};
+
+struct f2fs_move_range {
+ u32 dst_fd; /* destination fd */
+ u64 pos_in; /* start position in src_fd */
+ u64 pos_out; /* start position in dst_fd */
+ u64 len; /* size to move */
+};
+
+struct f2fs_flush_device {
+ u32 dev_num; /* device number to flush */
+ u32 segments; /* # of segments to flush */
+};
+
/*
* For INODE and NODE manager
*/
+/* for directory operations */
+struct f2fs_dentry_ptr {
+ struct inode *inode;
+ const void *bitmap;
+ struct f2fs_dir_entry *dentry;
+ __u8 (*filename)[F2FS_SLOT_LEN];
+ int max;
+};
+
+static inline void make_dentry_ptr_block(struct inode *inode,
+ struct f2fs_dentry_ptr *d, struct f2fs_dentry_block *t)
+{
+ d->inode = inode;
+ d->max = NR_DENTRY_IN_BLOCK;
+ d->bitmap = &t->dentry_bitmap;
+ d->dentry = t->dentry;
+ d->filename = t->filename;
+}
+
+static inline void make_dentry_ptr_inline(struct inode *inode,
+ struct f2fs_dentry_ptr *d, struct f2fs_inline_dentry *t)
+{
+ d->inode = inode;
+ d->max = NR_INLINE_DENTRY;
+ d->bitmap = &t->dentry_bitmap;
+ d->dentry = t->dentry;
+ d->filename = t->filename;
+}
+
/*
* XATTR_NODE_OFFSET stores xattrs to one node block per file keeping -1
* as its node offset to distinguish from index node blocks.
@@ -227,25 +491,105 @@
*/
};
-#define F2FS_LINK_MAX 32000 /* maximum link count per file */
+#define F2FS_LINK_MAX 0xffffffff /* maximum link count per file */
#define MAX_DIR_RA_PAGES 4 /* maximum ra pages of dir */
+/* vector size for gang look-up from extent cache that consists of radix tree */
+#define EXT_TREE_VEC_SIZE 64
+
/* for in-memory extent cache entry */
-#define F2FS_MIN_EXTENT_LEN 16 /* minimum extent length */
+#define F2FS_MIN_EXTENT_LEN 64 /* minimum extent length */
+
+/* number of extent info in extent cache we try to shrink */
+#define EXTENT_CACHE_SHRINK_NUMBER 128
+
+struct rb_entry {
+ struct rb_node rb_node; /* rb node located in rb-tree */
+ unsigned int ofs; /* start offset of the entry */
+ unsigned int len; /* length of the entry */
+};
struct extent_info {
- rwlock_t ext_lock; /* rwlock for consistency */
- unsigned int fofs; /* start offset in a file */
- u32 blk_addr; /* start block address of the extent */
- unsigned int len; /* length of the extent */
+ unsigned int fofs; /* start offset in a file */
+ unsigned int len; /* length of the extent */
+ u32 blk; /* start block address of the extent */
};
+struct extent_node {
+ struct rb_node rb_node;
+ union {
+ struct {
+ unsigned int fofs;
+ unsigned int len;
+ u32 blk;
+ };
+ struct extent_info ei; /* extent info */
+
+ };
+ struct list_head list; /* node in global extent list of sbi */
+ struct extent_tree *et; /* extent tree pointer */
+};
+
+struct extent_tree {
+ nid_t ino; /* inode number */
+ struct rb_root root; /* root of extent info rb-tree */
+ struct extent_node *cached_en; /* recently accessed extent node */
+ struct extent_info largest; /* largested extent info */
+ struct list_head list; /* to be used by sbi->zombie_list */
+ rwlock_t lock; /* protect extent info rb-tree */
+ atomic_t node_cnt; /* # of extent node in rb-tree*/
+};
+
+/*
+ * This structure is taken from ext4_map_blocks.
+ *
+ * Note that, however, f2fs uses NEW and MAPPED flags for f2fs_map_blocks().
+ */
+#define F2FS_MAP_NEW (1 << BH_New)
+#define F2FS_MAP_MAPPED (1 << BH_Mapped)
+#define F2FS_MAP_UNWRITTEN (1 << BH_Unwritten)
+#define F2FS_MAP_FLAGS (F2FS_MAP_NEW | F2FS_MAP_MAPPED |\
+ F2FS_MAP_UNWRITTEN)
+
+struct f2fs_map_blocks {
+ block_t m_pblk;
+ block_t m_lblk;
+ unsigned int m_len;
+ unsigned int m_flags;
+ pgoff_t *m_next_pgofs; /* point next possible non-hole pgofs */
+};
+
+/* for flag in get_data_block */
+#define F2FS_GET_BLOCK_READ 0
+#define F2FS_GET_BLOCK_DIO 1
+#define F2FS_GET_BLOCK_FIEMAP 2
+#define F2FS_GET_BLOCK_BMAP 3
+#define F2FS_GET_BLOCK_PRE_DIO 4
+#define F2FS_GET_BLOCK_PRE_AIO 5
+
/*
* i_advise uses FADVISE_XXX_BIT. We can add additional hints later.
*/
#define FADVISE_COLD_BIT 0x01
#define FADVISE_LOST_PINO_BIT 0x02
+#define FADVISE_ENCRYPT_BIT 0x04
+#define FADVISE_ENC_NAME_BIT 0x08
+#define FADVISE_KEEP_SIZE_BIT 0x10
+
+#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)
+#define file_is_encrypt(inode) is_file(inode, FADVISE_ENCRYPT_BIT)
+#define file_set_encrypt(inode) set_file(inode, FADVISE_ENCRYPT_BIT)
+#define file_clear_encrypt(inode) clear_file(inode, FADVISE_ENCRYPT_BIT)
+#define file_enc_name(inode) is_file(inode, FADVISE_ENC_NAME_BIT)
+#define file_set_enc_name(inode) set_file(inode, FADVISE_ENC_NAME_BIT)
+#define file_keep_isize(inode) is_file(inode, FADVISE_KEEP_SIZE_BIT)
+#define file_set_keep_isize(inode) set_file(inode, FADVISE_KEEP_SIZE_BIT)
#define DEF_DIR_LEVEL 0
@@ -264,59 +608,133 @@
atomic_t dirty_pages; /* # of dirty pages */
f2fs_hash_t chash; /* hash value of given file name */
unsigned int clevel; /* maximum level of given file name */
+ struct task_struct *task; /* lookup and create consistency */
nid_t i_xattr_nid; /* node id that contains xattrs */
- unsigned long long xattr_ver; /* cp version of xattr modification */
- struct extent_info ext; /* in-memory extent cache entry */
- struct dir_inode_entry *dirty_dir; /* the pointer of dirty dir */
+ loff_t last_disk_size; /* lastly written file size */
+ struct list_head dirty_list; /* dirty list for dirs and files */
+ struct list_head gdirty_list; /* linked in global dirty list */
struct list_head inmem_pages; /* inmemory pages managed by f2fs */
struct mutex inmem_lock; /* lock for inmemory pages */
+ struct extent_tree *extent_tree; /* cached extent_tree entry */
+ struct rw_semaphore dio_rwsem[2];/* avoid racing between dio and gc */
};
static inline void get_extent_info(struct extent_info *ext,
- struct f2fs_extent i_ext)
+ struct f2fs_extent *i_ext)
{
- write_lock(&ext->ext_lock);
- ext->fofs = le32_to_cpu(i_ext.fofs);
- ext->blk_addr = le32_to_cpu(i_ext.blk_addr);
- ext->len = le32_to_cpu(i_ext.len);
- write_unlock(&ext->ext_lock);
+ ext->fofs = le32_to_cpu(i_ext->fofs);
+ ext->blk = le32_to_cpu(i_ext->blk);
+ ext->len = le32_to_cpu(i_ext->len);
}
static inline void set_raw_extent(struct extent_info *ext,
struct f2fs_extent *i_ext)
{
- read_lock(&ext->ext_lock);
i_ext->fofs = cpu_to_le32(ext->fofs);
- i_ext->blk_addr = cpu_to_le32(ext->blk_addr);
+ i_ext->blk = cpu_to_le32(ext->blk);
i_ext->len = cpu_to_le32(ext->len);
- read_unlock(&ext->ext_lock);
}
+static inline void set_extent_info(struct extent_info *ei, unsigned int fofs,
+ u32 blk, unsigned int len)
+{
+ ei->fofs = fofs;
+ ei->blk = blk;
+ ei->len = len;
+}
+
+static inline bool __is_discard_mergeable(struct discard_info *back,
+ struct discard_info *front)
+{
+ return back->lstart + back->len == front->lstart;
+}
+
+static inline bool __is_discard_back_mergeable(struct discard_info *cur,
+ struct discard_info *back)
+{
+ return __is_discard_mergeable(back, cur);
+}
+
+static inline bool __is_discard_front_mergeable(struct discard_info *cur,
+ struct discard_info *front)
+{
+ return __is_discard_mergeable(cur, front);
+}
+
+static inline bool __is_extent_mergeable(struct extent_info *back,
+ struct extent_info *front)
+{
+ return (back->fofs + back->len == front->fofs &&
+ back->blk + back->len == front->blk);
+}
+
+static inline bool __is_back_mergeable(struct extent_info *cur,
+ struct extent_info *back)
+{
+ return __is_extent_mergeable(back, cur);
+}
+
+static inline bool __is_front_mergeable(struct extent_info *cur,
+ struct extent_info *front)
+{
+ return __is_extent_mergeable(cur, front);
+}
+
+extern void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync);
+static inline void __try_update_largest_extent(struct inode *inode,
+ struct extent_tree *et, struct extent_node *en)
+{
+ if (en->ei.len > et->largest.len) {
+ et->largest = en->ei;
+ f2fs_mark_inode_dirty_sync(inode, true);
+ }
+}
+
+enum nid_list {
+ FREE_NID_LIST,
+ ALLOC_NID_LIST,
+ MAX_NID_LIST,
+};
+
struct f2fs_nm_info {
block_t nat_blkaddr; /* base disk address of NAT */
nid_t max_nid; /* maximum possible node ids */
- nid_t available_nids; /* maximum available node ids */
+ nid_t available_nids; /* # of available node ids */
nid_t next_scan_nid; /* the next nid to be scanned */
unsigned int ram_thresh; /* control the memory footprint */
+ unsigned int ra_nid_pages; /* # of nid pages to be readaheaded */
+ unsigned int dirty_nats_ratio; /* control dirty nats ratio threshold */
/* NAT cache management */
struct radix_tree_root nat_root;/* root of the nat entry cache */
struct radix_tree_root nat_set_root;/* root of the nat set cache */
- rwlock_t nat_tree_lock; /* protect nat_tree_lock */
+ struct rw_semaphore nat_tree_lock; /* protect nat_tree_lock */
struct list_head nat_entries; /* cached nat entry list (clean) */
unsigned int nat_cnt; /* the # of cached nat entries */
unsigned int dirty_nat_cnt; /* total num of nat entries in set */
+ unsigned int nat_blocks; /* # of nat blocks */
/* free node ids management */
struct radix_tree_root free_nid_root;/* root of the free_nid cache */
- struct list_head free_nid_list; /* a list for free nids */
- spinlock_t free_nid_list_lock; /* protect free nid list */
- unsigned int fcnt; /* the number of free node id */
+ struct list_head nid_list[MAX_NID_LIST];/* lists for free nids */
+ unsigned int nid_cnt[MAX_NID_LIST]; /* the number of free node id */
+ spinlock_t nid_list_lock; /* protect nid lists ops */
struct mutex build_lock; /* lock for build free nids */
+ unsigned char (*free_nid_bitmap)[NAT_ENTRY_BITMAP_SIZE];
+ unsigned char *nat_block_bitmap;
+ unsigned short *free_nid_count; /* free nid count of NAT block */
/* for checkpoint */
char *nat_bitmap; /* NAT bitmap pointer */
+
+ unsigned int nat_bits_blocks; /* # of nat bits blocks */
+ unsigned char *nat_bits; /* NAT bits blocks */
+ unsigned char *full_nat_bits; /* full NAT pages */
+ unsigned char *empty_nat_bits; /* empty NAT pages */
+#ifdef CONFIG_F2FS_CHECK_FS
+ char *nat_bitmap_mir; /* NAT bitmap mirror */
+#endif
int bitmap_size; /* bitmap size */
};
@@ -332,6 +750,9 @@
nid_t nid; /* node id of the direct node block */
unsigned int ofs_in_node; /* data offset in the node page */
bool inode_page_locked; /* inode page is locked or not */
+ bool node_changed; /* is node block changed */
+ char cur_level; /* level of hole node page */
+ char max_level; /* level of current page located */
block_t data_blkaddr; /* block address of the node block */
};
@@ -369,7 +790,7 @@
CURSEG_HOT_NODE, /* direct node blocks of directory files */
CURSEG_WARM_NODE, /* direct node blocks of normal files */
CURSEG_COLD_NODE, /* indirect node blocks */
- NO_CHECK_TYPE
+ NO_CHECK_TYPE,
};
struct flush_cmd {
@@ -381,6 +802,8 @@
struct flush_cmd_control {
struct task_struct *f2fs_issue_flush; /* flush thread */
wait_queue_head_t flush_wait_queue; /* waiting queue for wake-up */
+ atomic_t issued_flush; /* # of issued flushes */
+ atomic_t issing_flush; /* # of issing flushes */
struct llist_head issue_list; /* list for command issue */
struct llist_node *dispatch_list; /* list for command dispatch */
};
@@ -403,20 +826,21 @@
/* a threshold to reclaim prefree segments */
unsigned int rec_prefree_segments;
- /* for small discard management */
- struct list_head discard_list; /* 4KB discard list */
- int nr_discards; /* # of discards in the list */
- int max_discards; /* max. discards to be issued */
+ /* for batched trimming */
+ unsigned int trim_sections; /* # of sections to trim */
struct list_head sit_entry_set; /* sit entry set list */
unsigned int ipu_policy; /* in-place-update policy */
unsigned int min_ipu_util; /* in-place-update threshold */
unsigned int min_fsync_blocks; /* threshold for fsync */
+ unsigned int min_hot_blocks; /* threshold for hot block allocation */
/* for flush command control */
- struct flush_cmd_control *cmd_control_info;
+ struct flush_cmd_control *fcc_info;
+ /* for discard command control */
+ struct discard_cmd_control *dcc_info;
};
/*
@@ -428,11 +852,16 @@
* f2fs monitors the number of several block types such as on-writeback,
* dirty dentry blocks, dirty node blocks, and dirty meta blocks.
*/
+#define WB_DATA_TYPE(p) (__is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA)
enum count_type {
- F2FS_WRITEBACK,
F2FS_DIRTY_DENTS,
+ F2FS_DIRTY_DATA,
F2FS_DIRTY_NODES,
F2FS_DIRTY_META,
+ F2FS_INMEM_PAGES,
+ F2FS_DIRTY_IMETA,
+ F2FS_WB_CP_DATA,
+ F2FS_WB_DATA,
NR_COUNT_TYPE,
};
@@ -454,14 +883,28 @@
META,
NR_PAGE_TYPE,
META_FLUSH,
+ INMEM, /* the below types are used by tracepoints only. */
+ INMEM_DROP,
+ INMEM_INVALIDATE,
+ INMEM_REVOKE,
+ IPU,
+ OPU,
};
struct f2fs_io_info {
+ struct f2fs_sb_info *sbi; /* f2fs_sb_info pointer */
enum page_type type; /* contains DATA/NODE/META/META_FLUSH */
- int rw; /* contains R/RS/W/WS with REQ_META/REQ_PRIO */
+ int op; /* contains REQ_OP_ */
+ int op_flags; /* req_flag_bits */
+ block_t new_blkaddr; /* new block address to be written */
+ block_t old_blkaddr; /* old block address before Cow */
+ struct page *page; /* page to be written */
+ struct page *encrypted_page; /* encrypted page */
+ bool submitted; /* indicate IO submission */
+ bool need_lock; /* indicate we need to lock cp_rwsem */
};
-#define is_read_io(rw) (((rw) & 1) == READ)
+#define is_read_io(rw) ((rw) == READ)
struct f2fs_bio_info {
struct f2fs_sb_info *sbi; /* f2fs superblock */
struct bio *bio; /* bios to merge */
@@ -470,13 +913,62 @@
struct rw_semaphore io_rwsem; /* blocking op for bio */
};
+#define FDEV(i) (sbi->devs[i])
+#define RDEV(i) (raw_super->devs[i])
+struct f2fs_dev_info {
+ struct block_device *bdev;
+ char path[MAX_PATH_LEN];
+ unsigned int total_segments;
+ block_t start_blk;
+ block_t end_blk;
+#ifdef CONFIG_BLK_DEV_ZONED
+ unsigned int nr_blkz; /* Total number of zones */
+ u8 *blkz_type; /* Array of zones type */
+#endif
+};
+
+enum inode_type {
+ DIR_INODE, /* for dirty dir inode */
+ FILE_INODE, /* for dirty regular/symlink inode */
+ DIRTY_META, /* for all dirtied inode metadata */
+ NR_INODE_TYPE,
+};
+
+/* for inner inode cache management */
+struct inode_management {
+ struct radix_tree_root ino_root; /* ino entry array */
+ spinlock_t ino_lock; /* for ino entry lock */
+ struct list_head ino_list; /* inode list head */
+ unsigned long ino_num; /* number of entries */
+};
+
+/* For s_flag in struct f2fs_sb_info */
+enum {
+ SBI_IS_DIRTY, /* dirty flag for checkpoint */
+ SBI_IS_CLOSE, /* specify unmounting */
+ SBI_NEED_FSCK, /* need fsck.f2fs to fix */
+ SBI_POR_DOING, /* recovery is doing or not */
+ SBI_NEED_SB_WRITE, /* need to recover superblock */
+ SBI_NEED_CP, /* need to checkpoint */
+};
+
+enum {
+ CP_TIME,
+ REQ_TIME,
+ MAX_TIME,
+};
+
struct f2fs_sb_info {
struct super_block *sb; /* pointer to VFS super block */
struct proc_dir_entry *s_proc; /* proc entry */
- struct buffer_head *raw_super_buf; /* buffer head of raw sb */
struct f2fs_super_block *raw_super; /* raw super block pointer */
- int s_dirty; /* dirty flag for checkpoint */
- bool need_fsck; /* need fsck.f2fs to fix */
+ int valid_super_block; /* valid super block no */
+ unsigned long s_flag; /* flags for sbi */
+
+#ifdef CONFIG_BLK_DEV_ZONED
+ unsigned int blocks_per_blkz; /* F2FS blocks per zone */
+ unsigned int log_blocks_per_blkz; /* log2 F2FS blocks per zone */
+#endif
/* for node-related operations */
struct f2fs_nm_info *nm_info; /* node manager */
@@ -488,30 +980,41 @@
/* for bio operations */
struct f2fs_bio_info read_io; /* for read bios */
struct f2fs_bio_info write_io[NR_PAGE_TYPE]; /* for write bios */
- struct completion *wait_io; /* for completion bios */
+ struct mutex wio_mutex[NODE + 1]; /* bio ordering for NODE/DATA */
+ int write_io_size_bits; /* Write IO size bits */
+ mempool_t *write_io_dummy; /* Dummy pages */
/* for checkpoint */
struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */
+ int cur_cp_pack; /* remain current cp pack */
+ spinlock_t cp_lock; /* for flag in ckpt */
struct inode *meta_inode; /* cache meta blocks */
struct mutex cp_mutex; /* checkpoint procedure lock */
struct rw_semaphore cp_rwsem; /* blocking FS operations */
struct rw_semaphore node_write; /* locking node writes */
- struct mutex writepages; /* mutex for writepages() */
- bool por_doing; /* recovery is doing or not */
+ struct rw_semaphore node_change; /* locking node change */
wait_queue_head_t cp_wait;
+ unsigned long last_time[MAX_TIME]; /* to store time in jiffies */
+ long interval_time[MAX_TIME]; /* to store thresholds */
- /* for inode management */
- struct radix_tree_root ino_root[MAX_INO_ENTRY]; /* ino entry array */
- spinlock_t ino_lock[MAX_INO_ENTRY]; /* for ino entry lock */
- struct list_head ino_list[MAX_INO_ENTRY]; /* inode list head */
+ struct inode_management im[MAX_INO_ENTRY]; /* manage inode cache */
/* for orphan inode, use 0'th array */
- unsigned int n_orphans; /* # of orphan inodes */
unsigned int max_orphans; /* max orphan inodes */
- /* for directory inode management */
- struct list_head dir_inode_list; /* dir inode list */
- spinlock_t dir_inode_lock; /* for dir inode list lock */
+ /* for inode management */
+ struct list_head inode_list[NR_INODE_TYPE]; /* dirty inode list */
+ spinlock_t inode_lock[NR_INODE_TYPE]; /* for dirty inode list lock */
+
+ /* for extent tree cache */
+ struct radix_tree_root extent_tree_root;/* cache extent cache entries */
+ struct mutex extent_tree_lock; /* locking extent radix tree */
+ struct list_head extent_list; /* lru list for shrinker */
+ spinlock_t extent_lock; /* locking extent lru list */
+ atomic_t total_ext_tree; /* extent tree count */
+ struct list_head zombie_list; /* extent zombie tree list */
+ atomic_t total_zombie_tree; /* extent zombie tree count */
+ atomic_t total_ext_node; /* extent info count */
/* basic filesystem units */
unsigned int log_sectors_per_block; /* log2 sectors per block */
@@ -527,16 +1030,26 @@
unsigned int total_sections; /* total section count */
unsigned int total_node_count; /* total node block count */
unsigned int total_valid_node_count; /* valid node block count */
- unsigned int total_valid_inode_count; /* valid inode count */
+ loff_t max_file_blocks; /* max block index of file */
int active_logs; /* # of active logs */
int dir_level; /* directory level */
block_t user_block_count; /* # of user blocks */
block_t total_valid_block_count; /* # of valid blocks */
- block_t alloc_valid_block_count; /* # of allocated blocks */
+ block_t discard_blks; /* discard command candidats */
block_t last_valid_block_count; /* for recovery */
u32 s_next_generation; /* for NFS support */
- atomic_t nr_pages[NR_COUNT_TYPE]; /* # of pages, see count_type */
+
+ /* # of pages, see count_type */
+ atomic_t nr_pages[NR_COUNT_TYPE];
+ /* # of allocated blocks */
+ struct percpu_counter alloc_valid_block_count;
+
+ /* writeback control */
+ atomic_t wb_sync_req; /* count # of WB_SYNC threads */
+
+ /* valid inode count */
+ struct percpu_counter total_valid_inode_count;
struct f2fs_mount_info mount_opt; /* mount options */
@@ -545,6 +1058,9 @@
struct f2fs_gc_kthread *gc_thread; /* GC thread */
unsigned int cur_victim_sec; /* current victim section num */
+ /* threshold for converting bg victims for fg */
+ u64 fggc_threshold;
+
/* maximum # of trials to find a victim segment for SSR and GC */
unsigned int max_victim_search;
@@ -556,22 +1072,129 @@
struct f2fs_stat_info *stat_info; /* FS status information */
unsigned int segment_count[2]; /* # of allocated segments */
unsigned int block_count[2]; /* # of allocated blocks */
- int total_hit_ext, read_hit_ext; /* extent cache hit ratio */
- int inline_inode; /* # of inline_data inodes */
+ atomic_t inplace_count; /* # of inplace update */
+ atomic64_t total_hit_ext; /* # of lookup extent cache */
+ atomic64_t read_hit_rbtree; /* # of hit rbtree extent node */
+ atomic64_t read_hit_largest; /* # of hit largest extent node */
+ atomic64_t read_hit_cached; /* # of hit cached extent node */
+ atomic_t inline_xattr; /* # of inline_xattr inodes */
+ atomic_t inline_inode; /* # of inline_data inodes */
+ atomic_t inline_dir; /* # of inline_dentry inodes */
+ atomic_t aw_cnt; /* # of atomic writes */
+ atomic_t vw_cnt; /* # of volatile writes */
+ atomic_t max_aw_cnt; /* max # of atomic writes */
+ atomic_t max_vw_cnt; /* max # of volatile writes */
int bg_gc; /* background gc calls */
- unsigned int n_dirty_dirs; /* # of dir inodes */
+ unsigned int ndirty_inode[NR_INODE_TYPE]; /* # of dirty inodes */
#endif
- unsigned int last_victim[2]; /* last victim segment # */
spinlock_t stat_lock; /* lock for stat operations */
/* For sysfs suppport */
struct kobject s_kobj;
struct completion s_kobj_unregister;
+
+ /* For shrinker support */
+ struct list_head s_list;
+ int s_ndevs; /* number of devices */
+ struct f2fs_dev_info *devs; /* for device list */
+ struct mutex umount_mutex;
+ unsigned int shrinker_run_no;
+
+ /* For write statistics */
+ u64 sectors_written_start;
+ u64 kbytes_written;
+
+ /* Reference to checksum algorithm driver via cryptoapi */
+ struct crypto_shash *s_chksum_driver;
+
+ /* For fault injection */
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ struct f2fs_fault_info fault_info;
+#endif
};
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+#define f2fs_show_injection_info(type) \
+ printk("%sF2FS-fs : inject %s in %s of %pF\n", \
+ KERN_INFO, fault_name[type], \
+ __func__, __builtin_return_address(0))
+static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
+{
+ struct f2fs_fault_info *ffi = &sbi->fault_info;
+
+ if (!ffi->inject_rate)
+ return false;
+
+ if (!IS_FAULT_SET(ffi, type))
+ return false;
+
+ atomic_inc(&ffi->inject_ops);
+ if (atomic_read(&ffi->inject_ops) >= ffi->inject_rate) {
+ atomic_set(&ffi->inject_ops, 0);
+ return true;
+ }
+ return false;
+}
+#endif
+
+/* For write statistics. Suppose sector size is 512 bytes,
+ * and the return value is in kbytes. s is of struct f2fs_sb_info.
+ */
+#define BD_PART_WRITTEN(s) \
+(((u64)part_stat_read((s)->sb->s_bdev->bd_part, sectors[1]) - \
+ (s)->sectors_written_start) >> 1)
+
+static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type)
+{
+ sbi->last_time[type] = jiffies;
+}
+
+static inline bool f2fs_time_over(struct f2fs_sb_info *sbi, int type)
+{
+ struct timespec ts = {sbi->interval_time[type], 0};
+ unsigned long interval = timespec_to_jiffies(&ts);
+
+ return time_after(jiffies, sbi->last_time[type] + interval);
+}
+
+static inline bool 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;
+
+ if (rl->count[BLK_RW_SYNC] || rl->count[BLK_RW_ASYNC])
+ return 0;
+
+ return f2fs_time_over(sbi, REQ_TIME);
+}
+
/*
* Inline functions
*/
+static inline u32 f2fs_crc32(struct f2fs_sb_info *sbi, const void *address,
+ unsigned int length)
+{
+ SHASH_DESC_ON_STACK(shash, sbi->s_chksum_driver);
+ u32 *ctx = (u32 *)shash_desc_ctx(shash);
+ int err;
+
+ shash->tfm = sbi->s_chksum_driver;
+ shash->flags = 0;
+ *ctx = F2FS_SUPER_MAGIC;
+
+ err = crypto_shash_update(shash, address, length);
+ BUG_ON(err);
+
+ return *ctx;
+}
+
+static inline bool f2fs_crc_valid(struct f2fs_sb_info *sbi, __u32 blk_crc,
+ void *buf, size_t buf_size)
+{
+ return f2fs_crc32(sbi, buf, buf_size) == blk_crc;
+}
+
static inline struct f2fs_inode_info *F2FS_I(struct inode *inode)
{
return container_of(inode, struct f2fs_inode_info, vfs_inode);
@@ -652,14 +1275,19 @@
return sbi->node_inode->i_mapping;
}
-static inline void F2FS_SET_SB_DIRT(struct f2fs_sb_info *sbi)
+static inline bool is_sbi_flag_set(struct f2fs_sb_info *sbi, unsigned int type)
{
- sbi->s_dirty = 1;
+ return test_bit(type, &sbi->s_flag);
}
-static inline void F2FS_RESET_SB_DIRT(struct f2fs_sb_info *sbi)
+static inline void set_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type)
{
- sbi->s_dirty = 0;
+ set_bit(type, &sbi->s_flag);
+}
+
+static inline void clear_sbi_flag(struct f2fs_sb_info *sbi, unsigned int type)
+{
+ clear_bit(type, &sbi->s_flag);
}
static inline unsigned long long cur_cp_version(struct f2fs_checkpoint *cp)
@@ -667,26 +1295,77 @@
return le64_to_cpu(cp->checkpoint_ver);
}
-static inline bool is_set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
+static inline __u64 cur_cp_crc(struct f2fs_checkpoint *cp)
+{
+ size_t crc_offset = le32_to_cpu(cp->checksum_offset);
+ return le32_to_cpu(*((__le32 *)((unsigned char *)cp + crc_offset)));
+}
+
+static inline bool __is_set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
{
unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags);
+
return ckpt_flags & f;
}
-static inline void set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
+static inline bool is_set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
{
- unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags);
+ return __is_set_ckpt_flags(F2FS_CKPT(sbi), f);
+}
+
+static inline void __set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
+{
+ unsigned int ckpt_flags;
+
+ ckpt_flags = le32_to_cpu(cp->ckpt_flags);
ckpt_flags |= f;
cp->ckpt_flags = cpu_to_le32(ckpt_flags);
}
-static inline void clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
+static inline void set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
{
- unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags);
+ spin_lock(&sbi->cp_lock);
+ __set_ckpt_flags(F2FS_CKPT(sbi), f);
+ spin_unlock(&sbi->cp_lock);
+}
+
+static inline void __clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
+{
+ unsigned int ckpt_flags;
+
+ ckpt_flags = le32_to_cpu(cp->ckpt_flags);
ckpt_flags &= (~f);
cp->ckpt_flags = cpu_to_le32(ckpt_flags);
}
+static inline void clear_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
+{
+ spin_lock(&sbi->cp_lock);
+ __clear_ckpt_flags(F2FS_CKPT(sbi), f);
+ spin_unlock(&sbi->cp_lock);
+}
+
+static inline void disable_nat_bits(struct f2fs_sb_info *sbi, bool lock)
+{
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+
+ if (lock)
+ spin_lock(&sbi->cp_lock);
+ __clear_ckpt_flags(F2FS_CKPT(sbi), CP_NAT_BITS_FLAG);
+ kfree(NM_I(sbi)->nat_bits);
+ NM_I(sbi)->nat_bits = NULL;
+ if (lock)
+ spin_unlock(&sbi->cp_lock);
+}
+
+static inline bool enabled_nat_bits(struct f2fs_sb_info *sbi,
+ struct cp_control *cpc)
+{
+ bool set = is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG);
+
+ return (cpc) ? (cpc->reason & CP_UMOUNT) && set : set;
+}
+
static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
{
down_read(&sbi->cp_rwsem);
@@ -699,7 +1378,7 @@
static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
{
- f2fs_down_write(&sbi->cp_rwsem, &sbi->cp_mutex);
+ down_write(&sbi->cp_rwsem);
}
static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
@@ -707,6 +1386,28 @@
up_write(&sbi->cp_rwsem);
}
+static inline int __get_cp_reason(struct f2fs_sb_info *sbi)
+{
+ int reason = CP_SYNC;
+
+ if (test_opt(sbi, FASTBOOT))
+ reason = CP_FASTBOOT;
+ if (is_sbi_flag_set(sbi, SBI_IS_CLOSE))
+ reason = CP_UMOUNT;
+ return reason;
+}
+
+static inline bool __remain_node_summaries(int reason)
+{
+ return (reason & (CP_UMOUNT | CP_FASTBOOT));
+}
+
+static inline bool __exist_node_summaries(struct f2fs_sb_info *sbi)
+{
+ return (is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG) ||
+ is_set_ckpt_flags(sbi, CP_FASTBOOT_FLAG));
+}
+
/*
* Check whether the given nid is within node id range.
*/
@@ -737,22 +1438,39 @@
return ofs == XATTR_NODE_OFFSET;
}
+static inline void f2fs_i_blocks_write(struct inode *, blkcnt_t, bool);
static inline bool inc_valid_block_count(struct f2fs_sb_info *sbi,
- struct inode *inode, blkcnt_t count)
+ struct inode *inode, blkcnt_t *count)
{
- block_t valid_block_count;
+ blkcnt_t diff;
- spin_lock(&sbi->stat_lock);
- valid_block_count =
- sbi->total_valid_block_count + (block_t)count;
- if (unlikely(valid_block_count > sbi->user_block_count)) {
- spin_unlock(&sbi->stat_lock);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(sbi, FAULT_BLOCK)) {
+ f2fs_show_injection_info(FAULT_BLOCK);
return false;
}
- inode->i_blocks += count;
- sbi->total_valid_block_count = valid_block_count;
- sbi->alloc_valid_block_count += (block_t)count;
+#endif
+ /*
+ * let's increase this in prior to actual block count change in order
+ * for f2fs_sync_file to avoid data races when deciding checkpoint.
+ */
+ percpu_counter_add(&sbi->alloc_valid_block_count, (*count));
+
+ spin_lock(&sbi->stat_lock);
+ sbi->total_valid_block_count += (block_t)(*count);
+ if (unlikely(sbi->total_valid_block_count > sbi->user_block_count)) {
+ diff = sbi->total_valid_block_count - sbi->user_block_count;
+ *count -= diff;
+ sbi->total_valid_block_count = sbi->user_block_count;
+ if (!*count) {
+ spin_unlock(&sbi->stat_lock);
+ percpu_counter_sub(&sbi->alloc_valid_block_count, diff);
+ return false;
+ }
+ }
spin_unlock(&sbi->stat_lock);
+
+ f2fs_i_blocks_write(inode, *count, true);
return true;
}
@@ -763,22 +1481,27 @@
spin_lock(&sbi->stat_lock);
f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count);
f2fs_bug_on(sbi, inode->i_blocks < count);
- inode->i_blocks -= count;
sbi->total_valid_block_count -= (block_t)count;
spin_unlock(&sbi->stat_lock);
+ f2fs_i_blocks_write(inode, count, false);
}
static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
{
atomic_inc(&sbi->nr_pages[count_type]);
- F2FS_SET_SB_DIRT(sbi);
+
+ if (count_type == F2FS_DIRTY_DATA || count_type == F2FS_INMEM_PAGES ||
+ count_type == F2FS_WB_CP_DATA || count_type == F2FS_WB_DATA)
+ return;
+
+ set_sbi_flag(sbi, SBI_IS_DIRTY);
}
static inline void inode_inc_dirty_pages(struct inode *inode)
{
atomic_inc(&F2FS_I(inode)->dirty_pages);
- if (S_ISDIR(inode->i_mode))
- inc_page_count(F2FS_I_SB(inode), F2FS_DIRTY_DENTS);
+ inc_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
+ F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
}
static inline void dec_page_count(struct f2fs_sb_info *sbi, int count_type)
@@ -788,16 +1511,16 @@
static inline void inode_dec_dirty_pages(struct inode *inode)
{
- if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode))
+ if (!S_ISDIR(inode->i_mode) && !S_ISREG(inode->i_mode) &&
+ !S_ISLNK(inode->i_mode))
return;
atomic_dec(&F2FS_I(inode)->dirty_pages);
-
- if (S_ISDIR(inode->i_mode))
- dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_DENTS);
+ dec_page_count(F2FS_I_SB(inode), S_ISDIR(inode->i_mode) ?
+ F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA);
}
-static inline int get_pages(struct f2fs_sb_info *sbi, int count_type)
+static inline s64 get_pages(struct f2fs_sb_info *sbi, int count_type)
{
return atomic_read(&sbi->nr_pages[count_type]);
}
@@ -809,10 +1532,11 @@
static inline int get_blocktype_secs(struct f2fs_sb_info *sbi, int block_type)
{
- unsigned int pages_per_sec = sbi->segs_per_sec *
- (1 << sbi->log_blocks_per_seg);
- return ((get_pages(sbi, block_type) + pages_per_sec - 1)
- >> sbi->log_blocks_per_seg) / sbi->segs_per_sec;
+ unsigned int pages_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg;
+ unsigned int segs = (get_pages(sbi, block_type) + pages_per_sec - 1) >>
+ sbi->log_blocks_per_seg;
+
+ return segs / sbi->segs_per_sec;
}
static inline block_t valid_user_blocks(struct f2fs_sb_info *sbi)
@@ -820,6 +1544,11 @@
return sbi->total_valid_block_count;
}
+static inline block_t discard_blocks(struct f2fs_sb_info *sbi)
+{
+ return sbi->discard_blks;
+}
+
static inline unsigned long __bitmap_size(struct f2fs_sb_info *sbi, int flag)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
@@ -833,12 +1562,17 @@
return 0;
}
+static inline block_t __cp_payload(struct f2fs_sb_info *sbi)
+{
+ return le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload);
+}
+
static inline void *__bitmap_ptr(struct f2fs_sb_info *sbi, int flag)
{
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
int offset;
- if (le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_payload) > 0) {
+ if (__cp_payload(sbi) > 0) {
if (flag == NAT_BITMAP)
return &ckpt->sit_nat_version_bitmap;
else
@@ -852,22 +1586,27 @@
static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi)
{
- block_t start_addr;
- struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
- unsigned long long ckpt_version = cur_cp_version(ckpt);
+ block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
- start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
-
- /*
- * odd numbered checkpoint should at cp segment 0
- * and even segment must be at cp segment 1
- */
- if (!(ckpt_version & 1))
+ if (sbi->cur_cp_pack == 2)
start_addr += sbi->blocks_per_seg;
-
return start_addr;
}
+static inline block_t __start_cp_next_addr(struct f2fs_sb_info *sbi)
+{
+ block_t start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
+
+ if (sbi->cur_cp_pack == 1)
+ start_addr += sbi->blocks_per_seg;
+ return start_addr;
+}
+
+static inline void __set_cp_next_pack(struct f2fs_sb_info *sbi)
+{
+ sbi->cur_cp_pack = (sbi->cur_cp_pack == 1) ? 2 : 1;
+}
+
static inline block_t __start_sum_addr(struct f2fs_sb_info *sbi)
{
return le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum);
@@ -894,13 +1633,13 @@
}
if (inode)
- inode->i_blocks++;
+ f2fs_i_blocks_write(inode, 1, true);
- sbi->alloc_valid_block_count++;
sbi->total_valid_node_count++;
sbi->total_valid_block_count++;
spin_unlock(&sbi->stat_lock);
+ percpu_counter_inc(&sbi->alloc_valid_block_count);
return true;
}
@@ -913,7 +1652,7 @@
f2fs_bug_on(sbi, !sbi->total_valid_node_count);
f2fs_bug_on(sbi, !inode->i_blocks);
- inode->i_blocks--;
+ f2fs_i_blocks_write(inode, 1, false);
sbi->total_valid_node_count--;
sbi->total_valid_block_count--;
@@ -927,23 +1666,46 @@
static inline void inc_valid_inode_count(struct f2fs_sb_info *sbi)
{
- spin_lock(&sbi->stat_lock);
- f2fs_bug_on(sbi, sbi->total_valid_inode_count == sbi->total_node_count);
- sbi->total_valid_inode_count++;
- spin_unlock(&sbi->stat_lock);
+ percpu_counter_inc(&sbi->total_valid_inode_count);
}
static inline void dec_valid_inode_count(struct f2fs_sb_info *sbi)
{
- spin_lock(&sbi->stat_lock);
- f2fs_bug_on(sbi, !sbi->total_valid_inode_count);
- sbi->total_valid_inode_count--;
- spin_unlock(&sbi->stat_lock);
+ percpu_counter_dec(&sbi->total_valid_inode_count);
}
-static inline unsigned int valid_inode_count(struct f2fs_sb_info *sbi)
+static inline s64 valid_inode_count(struct f2fs_sb_info *sbi)
{
- return sbi->total_valid_inode_count;
+ return percpu_counter_sum_positive(&sbi->total_valid_inode_count);
+}
+
+static inline struct page *f2fs_grab_cache_page(struct address_space *mapping,
+ pgoff_t index, bool for_write)
+{
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ struct page *page = find_lock_page(mapping, index);
+
+ if (page)
+ return page;
+
+ if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC)) {
+ f2fs_show_injection_info(FAULT_PAGE_ALLOC);
+ return NULL;
+ }
+#endif
+ if (!for_write)
+ return grab_cache_page(mapping, index);
+ return grab_cache_page_write_begin(mapping, index, AOP_FLAG_NOFS);
+}
+
+static inline void f2fs_copy_page(struct page *src, struct page *dst)
+{
+ char *src_kaddr = kmap(src);
+ char *dst_kaddr = kmap(dst);
+
+ memcpy(dst_kaddr, src_kaddr, PAGE_SIZE);
+ kunmap(dst);
+ kunmap(src);
}
static inline void f2fs_put_page(struct page *page, int unlock)
@@ -955,7 +1717,7 @@
f2fs_bug_on(F2FS_P_SB(page), !PageLocked(page));
unlock_page(page);
}
- page_cache_release(page);
+ put_page(page);
}
static inline void f2fs_put_dnode(struct dnode_of_data *dn)
@@ -978,21 +1740,37 @@
gfp_t flags)
{
void *entry;
-retry:
- entry = kmem_cache_alloc(cachep, flags);
- if (!entry) {
- cond_resched();
- goto retry;
- }
+ entry = kmem_cache_alloc(cachep, flags);
+ if (!entry)
+ entry = kmem_cache_alloc(cachep, flags | __GFP_NOFAIL);
return entry;
}
+static inline struct bio *f2fs_bio_alloc(int npages)
+{
+ struct bio *bio;
+
+ /* No failure on bio allocation */
+ bio = bio_alloc(GFP_NOIO, npages);
+ if (!bio)
+ bio = bio_alloc(GFP_NOIO | __GFP_NOFAIL, npages);
+ return bio;
+}
+
+static inline void f2fs_radix_tree_insert(struct radix_tree_root *root,
+ unsigned long index, void *item)
+{
+ while (radix_tree_insert(root, index, item))
+ cond_resched();
+}
+
#define RAW_IS_INODE(p) ((p)->footer.nid == (p)->footer.ino)
static inline bool IS_INODE(struct page *page)
{
struct f2fs_node *p = F2FS_NODE(page);
+
return RAW_IS_INODE(p);
}
@@ -1006,6 +1784,7 @@
{
struct f2fs_node *raw_node;
__le32 *addr_array;
+
raw_node = F2FS_NODE(node_page);
addr_array = blkaddr_in_node(raw_node);
return le32_to_cpu(addr_array[offset]);
@@ -1020,7 +1799,25 @@
return mask & *addr;
}
-static inline int f2fs_set_bit(unsigned int nr, char *addr)
+static inline void f2fs_set_bit(unsigned int nr, char *addr)
+{
+ int mask;
+
+ addr += (nr >> 3);
+ mask = 1 << (7 - (nr & 0x07));
+ *addr |= mask;
+}
+
+static inline void f2fs_clear_bit(unsigned int nr, char *addr)
+{
+ int mask;
+
+ addr += (nr >> 3);
+ mask = 1 << (7 - (nr & 0x07));
+ *addr &= ~mask;
+}
+
+static inline int f2fs_test_and_set_bit(unsigned int nr, char *addr)
{
int mask;
int ret;
@@ -1032,7 +1829,7 @@
return ret;
}
-static inline int f2fs_clear_bit(unsigned int nr, char *addr)
+static inline int f2fs_test_and_clear_bit(unsigned int nr, char *addr)
{
int mask;
int ret;
@@ -1044,86 +1841,179 @@
return ret;
}
+static inline void f2fs_change_bit(unsigned int nr, char *addr)
+{
+ int mask;
+
+ addr += (nr >> 3);
+ mask = 1 << (7 - (nr & 0x07));
+ *addr ^= mask;
+}
+
/* used for f2fs_inode_info->flags */
enum {
FI_NEW_INODE, /* indicate newly allocated inode */
FI_DIRTY_INODE, /* indicate inode is dirty or not */
+ FI_AUTO_RECOVER, /* indicate inode is recoverable */
FI_DIRTY_DIR, /* indicate directory has dirty pages */
FI_INC_LINK, /* need to increment i_nlink */
FI_ACL_MODE, /* indicate acl mode */
FI_NO_ALLOC, /* should not allocate any blocks */
- FI_UPDATE_DIR, /* should update inode block for consistency */
- FI_DELAY_IPUT, /* used for the recovery */
+ FI_FREE_NID, /* free allocated nide */
FI_NO_EXTENT, /* not to use the extent cache */
FI_INLINE_XATTR, /* used for inline xattr */
FI_INLINE_DATA, /* used for inline data*/
+ FI_INLINE_DENTRY, /* used for inline dentry */
FI_APPEND_WRITE, /* inode has appended data */
FI_UPDATE_WRITE, /* inode has in-place-update data */
FI_NEED_IPU, /* used for ipu per file */
FI_ATOMIC_FILE, /* indicate atomic file */
+ FI_ATOMIC_COMMIT, /* indicate the state of atomical committing */
FI_VOLATILE_FILE, /* indicate volatile file */
+ FI_FIRST_BLOCK_WRITTEN, /* indicate #0 data block was written */
+ FI_DROP_CACHE, /* drop dirty page cache */
+ FI_DATA_EXIST, /* indicate data exists */
+ FI_INLINE_DOTS, /* indicate inline dot dentries */
+ FI_DO_DEFRAG, /* indicate defragment is running */
+ FI_DIRTY_FILE, /* indicate regular/symlink has dirty pages */
+ FI_HOT_DATA, /* indicate file is hot */
};
-static inline void set_inode_flag(struct f2fs_inode_info *fi, int flag)
+static inline void __mark_inode_dirty_flag(struct inode *inode,
+ int flag, bool set)
{
- if (!test_bit(flag, &fi->flags))
- set_bit(flag, &fi->flags);
-}
-
-static inline int is_inode_flag_set(struct f2fs_inode_info *fi, int flag)
-{
- return test_bit(flag, &fi->flags);
-}
-
-static inline void clear_inode_flag(struct f2fs_inode_info *fi, int flag)
-{
- if (test_bit(flag, &fi->flags))
- clear_bit(flag, &fi->flags);
-}
-
-static inline void set_acl_inode(struct f2fs_inode_info *fi, umode_t mode)
-{
- fi->i_acl_mode = mode;
- set_inode_flag(fi, FI_ACL_MODE);
-}
-
-static inline int cond_clear_inode_flag(struct f2fs_inode_info *fi, int flag)
-{
- if (is_inode_flag_set(fi, FI_ACL_MODE)) {
- clear_inode_flag(fi, FI_ACL_MODE);
- return 1;
+ switch (flag) {
+ case FI_INLINE_XATTR:
+ case FI_INLINE_DATA:
+ case FI_INLINE_DENTRY:
+ if (set)
+ return;
+ case FI_DATA_EXIST:
+ case FI_INLINE_DOTS:
+ f2fs_mark_inode_dirty_sync(inode, true);
}
- return 0;
}
-static inline void get_inline_info(struct f2fs_inode_info *fi,
- struct f2fs_inode *ri)
+static inline void set_inode_flag(struct inode *inode, int flag)
{
- if (ri->i_inline & F2FS_INLINE_XATTR)
- set_inode_flag(fi, FI_INLINE_XATTR);
- if (ri->i_inline & F2FS_INLINE_DATA)
- set_inode_flag(fi, FI_INLINE_DATA);
+ if (!test_bit(flag, &F2FS_I(inode)->flags))
+ set_bit(flag, &F2FS_I(inode)->flags);
+ __mark_inode_dirty_flag(inode, flag, true);
}
-static inline void set_raw_inline(struct f2fs_inode_info *fi,
- struct f2fs_inode *ri)
+static inline int is_inode_flag_set(struct inode *inode, int flag)
+{
+ return test_bit(flag, &F2FS_I(inode)->flags);
+}
+
+static inline void clear_inode_flag(struct inode *inode, int flag)
+{
+ if (test_bit(flag, &F2FS_I(inode)->flags))
+ clear_bit(flag, &F2FS_I(inode)->flags);
+ __mark_inode_dirty_flag(inode, flag, false);
+}
+
+static inline void set_acl_inode(struct inode *inode, umode_t mode)
+{
+ F2FS_I(inode)->i_acl_mode = mode;
+ set_inode_flag(inode, FI_ACL_MODE);
+ f2fs_mark_inode_dirty_sync(inode, false);
+}
+
+static inline void f2fs_i_links_write(struct inode *inode, bool inc)
+{
+ if (inc)
+ inc_nlink(inode);
+ else
+ drop_nlink(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
+}
+
+static inline void f2fs_i_blocks_write(struct inode *inode,
+ blkcnt_t diff, bool add)
+{
+ bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE);
+ bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER);
+
+ inode->i_blocks = add ? inode->i_blocks + diff :
+ inode->i_blocks - diff;
+ f2fs_mark_inode_dirty_sync(inode, true);
+ if (clean || recover)
+ set_inode_flag(inode, FI_AUTO_RECOVER);
+}
+
+static inline void f2fs_i_size_write(struct inode *inode, loff_t i_size)
+{
+ bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE);
+ bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER);
+
+ if (i_size_read(inode) == i_size)
+ return;
+
+ i_size_write(inode, i_size);
+ f2fs_mark_inode_dirty_sync(inode, true);
+ if (clean || recover)
+ set_inode_flag(inode, FI_AUTO_RECOVER);
+}
+
+static inline void f2fs_i_depth_write(struct inode *inode, unsigned int depth)
+{
+ F2FS_I(inode)->i_current_depth = depth;
+ f2fs_mark_inode_dirty_sync(inode, true);
+}
+
+static inline void f2fs_i_xnid_write(struct inode *inode, nid_t xnid)
+{
+ F2FS_I(inode)->i_xattr_nid = xnid;
+ f2fs_mark_inode_dirty_sync(inode, true);
+}
+
+static inline void f2fs_i_pino_write(struct inode *inode, nid_t pino)
+{
+ F2FS_I(inode)->i_pino = pino;
+ f2fs_mark_inode_dirty_sync(inode, true);
+}
+
+static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri)
+{
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+
+ if (ri->i_inline & F2FS_INLINE_XATTR)
+ set_bit(FI_INLINE_XATTR, &fi->flags);
+ if (ri->i_inline & F2FS_INLINE_DATA)
+ set_bit(FI_INLINE_DATA, &fi->flags);
+ if (ri->i_inline & F2FS_INLINE_DENTRY)
+ set_bit(FI_INLINE_DENTRY, &fi->flags);
+ if (ri->i_inline & F2FS_DATA_EXIST)
+ set_bit(FI_DATA_EXIST, &fi->flags);
+ if (ri->i_inline & F2FS_INLINE_DOTS)
+ set_bit(FI_INLINE_DOTS, &fi->flags);
+}
+
+static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri)
{
ri->i_inline = 0;
- if (is_inode_flag_set(fi, FI_INLINE_XATTR))
+ if (is_inode_flag_set(inode, FI_INLINE_XATTR))
ri->i_inline |= F2FS_INLINE_XATTR;
- if (is_inode_flag_set(fi, FI_INLINE_DATA))
+ if (is_inode_flag_set(inode, FI_INLINE_DATA))
ri->i_inline |= F2FS_INLINE_DATA;
+ if (is_inode_flag_set(inode, FI_INLINE_DENTRY))
+ ri->i_inline |= F2FS_INLINE_DENTRY;
+ if (is_inode_flag_set(inode, FI_DATA_EXIST))
+ ri->i_inline |= F2FS_DATA_EXIST;
+ if (is_inode_flag_set(inode, FI_INLINE_DOTS))
+ ri->i_inline |= F2FS_INLINE_DOTS;
}
static inline int f2fs_has_inline_xattr(struct inode *inode)
{
- return is_inode_flag_set(F2FS_I(inode), FI_INLINE_XATTR);
+ return is_inode_flag_set(inode, FI_INLINE_XATTR);
}
-static inline unsigned int addrs_per_inode(struct f2fs_inode_info *fi)
+static inline unsigned int addrs_per_inode(struct inode *inode)
{
- if (f2fs_has_inline_xattr(&fi->vfs_inode))
+ if (f2fs_has_inline_xattr(inode))
return DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS;
return DEF_ADDRS_PER_INODE;
}
@@ -1131,6 +2021,7 @@
static inline void *inline_xattr_addr(struct page *page)
{
struct f2fs_inode *ri = F2FS_INODE(page);
+
return (void *)&(ri->i_addr[DEF_ADDRS_PER_INODE -
F2FS_INLINE_XATTR_ADDRS]);
}
@@ -1145,25 +2036,97 @@
static inline int f2fs_has_inline_data(struct inode *inode)
{
- return is_inode_flag_set(F2FS_I(inode), FI_INLINE_DATA);
+ return is_inode_flag_set(inode, FI_INLINE_DATA);
+}
+
+static inline int f2fs_exist_data(struct inode *inode)
+{
+ return is_inode_flag_set(inode, FI_DATA_EXIST);
+}
+
+static inline int f2fs_has_inline_dots(struct inode *inode)
+{
+ return is_inode_flag_set(inode, FI_INLINE_DOTS);
}
static inline bool f2fs_is_atomic_file(struct inode *inode)
{
- return is_inode_flag_set(F2FS_I(inode), FI_ATOMIC_FILE);
+ return is_inode_flag_set(inode, FI_ATOMIC_FILE);
+}
+
+static inline bool f2fs_is_commit_atomic_write(struct inode *inode)
+{
+ return is_inode_flag_set(inode, FI_ATOMIC_COMMIT);
}
static inline bool f2fs_is_volatile_file(struct inode *inode)
{
- return is_inode_flag_set(F2FS_I(inode), FI_VOLATILE_FILE);
+ return is_inode_flag_set(inode, FI_VOLATILE_FILE);
+}
+
+static inline bool f2fs_is_first_block_written(struct inode *inode)
+{
+ return is_inode_flag_set(inode, FI_FIRST_BLOCK_WRITTEN);
+}
+
+static inline bool f2fs_is_drop_cache(struct inode *inode)
+{
+ return is_inode_flag_set(inode, FI_DROP_CACHE);
}
static inline void *inline_data_addr(struct page *page)
{
struct f2fs_inode *ri = F2FS_INODE(page);
+
return (void *)&(ri->i_addr[1]);
}
+static inline int f2fs_has_inline_dentry(struct inode *inode)
+{
+ return is_inode_flag_set(inode, FI_INLINE_DENTRY);
+}
+
+static inline void f2fs_dentry_kunmap(struct inode *dir, struct page *page)
+{
+ if (!f2fs_has_inline_dentry(dir))
+ kunmap(page);
+}
+
+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;
+ f2fs_mark_inode_dirty_sync(inode, true);
+}
+
+static inline void clear_file(struct inode *inode, int type)
+{
+ F2FS_I(inode)->i_advise &= ~type;
+ f2fs_mark_inode_dirty_sync(inode, true);
+}
+
+static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync)
+{
+ if (dsync) {
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ bool ret;
+
+ spin_lock(&sbi->inode_lock[DIRTY_META]);
+ ret = list_empty(&F2FS_I(inode)->gdirty_list);
+ spin_unlock(&sbi->inode_lock[DIRTY_META]);
+ return ret;
+ }
+ if (!is_inode_flag_set(inode, FI_AUTO_RECOVER) ||
+ file_keep_isize(inode) ||
+ i_size_read(inode) & PAGE_MASK)
+ return false;
+ return F2FS_I(inode)->last_disk_size == i_size_read(inode);
+}
+
static inline int f2fs_readonly(struct super_block *sb)
{
return sb->s_flags & MS_RDONLY;
@@ -1171,50 +2134,94 @@
static inline bool f2fs_cp_error(struct f2fs_sb_info *sbi)
{
- return is_set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
+ return is_set_ckpt_flags(sbi, CP_ERROR_FLAG);
}
-static inline void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi)
+static inline bool is_dot_dotdot(const struct qstr *str)
{
- set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
- sbi->sb->s_flags |= MS_RDONLY;
+ 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 bool f2fs_may_extent_tree(struct inode *inode)
+{
+ mode_t mode = inode->i_mode;
+
+ if (!test_opt(F2FS_I_SB(inode), EXTENT_CACHE) ||
+ is_inode_flag_set(inode, FI_NO_EXTENT))
+ return false;
+
+ return S_ISREG(mode);
+}
+
+static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
+ size_t size, gfp_t flags)
+{
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(sbi, FAULT_KMALLOC)) {
+ f2fs_show_injection_info(FAULT_KMALLOC);
+ return NULL;
+ }
+#endif
+ return kmalloc(size, flags);
+}
+
+static inline void *f2fs_kvmalloc(size_t size, gfp_t flags)
+{
+ void *ret;
+
+ ret = kmalloc(size, flags | __GFP_NOWARN);
+ if (!ret)
+ ret = __vmalloc(size, flags, PAGE_KERNEL);
+ return ret;
+}
+
+static inline void *f2fs_kvzalloc(size_t size, gfp_t flags)
+{
+ void *ret;
+
+ ret = kzalloc(size, flags | __GFP_NOWARN);
+ if (!ret)
+ ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL);
+ return ret;
}
#define get_inode_mode(i) \
- ((is_inode_flag_set(F2FS_I(i), FI_ACL_MODE)) ? \
+ ((is_inode_flag_set(i, FI_ACL_MODE)) ? \
(F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
-/* get offset of first page in next direct node */
-#define PGOFS_OF_NEXT_DNODE(pgofs, fi) \
- ((pgofs < ADDRS_PER_INODE(fi)) ? ADDRS_PER_INODE(fi) : \
- (pgofs - ADDRS_PER_INODE(fi) + ADDRS_PER_BLOCK) / \
- ADDRS_PER_BLOCK * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi))
-
/*
* file.c
*/
-int f2fs_sync_file(struct file *, loff_t, loff_t, int);
-void truncate_data_blocks(struct dnode_of_data *);
-int truncate_blocks(struct inode *, u64, bool);
-void f2fs_truncate(struct inode *);
-int f2fs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
-int f2fs_setattr(struct dentry *, struct iattr *);
-int truncate_hole(struct inode *, pgoff_t, pgoff_t);
-int truncate_data_blocks_range(struct dnode_of_data *, int);
-long f2fs_ioctl(struct file *, unsigned int, unsigned long);
-long f2fs_compat_ioctl(struct file *, unsigned int, unsigned long);
+int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
+void truncate_data_blocks(struct dnode_of_data *dn);
+int truncate_blocks(struct inode *inode, u64 from, bool lock);
+int f2fs_truncate(struct inode *inode);
+int f2fs_getattr(struct vfsmount *mnt, struct dentry *dentry,
+ struct kstat *stat);
+int f2fs_setattr(struct dentry *dentry, struct iattr *attr);
+int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end);
+int truncate_data_blocks_range(struct dnode_of_data *dn, int count);
+long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
+long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
/*
* inode.c
*/
-void f2fs_set_inode_flags(struct inode *);
-struct inode *f2fs_iget(struct super_block *, unsigned long);
-int try_to_free_nats(struct f2fs_sb_info *, int);
-void update_inode(struct inode *, struct page *);
-void update_inode_page(struct inode *);
-int f2fs_write_inode(struct inode *, struct writeback_control *);
-void f2fs_evict_inode(struct inode *);
-void handle_failed_inode(struct inode *);
+void f2fs_set_inode_flags(struct inode *inode);
+struct inode *f2fs_iget(struct super_block *sb, unsigned long ino);
+struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino);
+int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink);
+int update_inode(struct inode *inode, struct page *node_page);
+int update_inode_page(struct inode *inode);
+int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc);
+void f2fs_evict_inode(struct inode *inode);
+void handle_failed_inode(struct inode *inode);
/*
* namei.c
@@ -1224,36 +2231,68 @@
/*
* dir.c
*/
-struct f2fs_dir_entry *f2fs_find_entry(struct inode *, struct qstr *,
- struct page **);
-struct f2fs_dir_entry *f2fs_parent_dir(struct inode *, struct page **);
-ino_t f2fs_inode_by_name(struct inode *, struct qstr *);
-void f2fs_set_link(struct inode *, struct f2fs_dir_entry *,
- struct page *, struct inode *);
-int update_dent_inode(struct inode *, const struct qstr *);
-int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *);
-void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *);
-int f2fs_do_tmpfile(struct inode *, struct inode *);
-int f2fs_make_empty(struct inode *, struct inode *);
-bool f2fs_empty_dir(struct inode *);
+void set_de_type(struct f2fs_dir_entry *de, umode_t mode);
+unsigned char get_de_type(struct f2fs_dir_entry *de);
+struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname,
+ f2fs_hash_t namehash, int *max_slots,
+ struct f2fs_dentry_ptr *d);
+int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
+ unsigned int start_pos, struct fscrypt_str *fstr);
+void do_make_empty_dir(struct inode *inode, struct inode *parent,
+ struct f2fs_dentry_ptr *d);
+struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
+ const struct qstr *new_name,
+ const struct qstr *orig_name, struct page *dpage);
+void update_parent_metadata(struct inode *dir, struct inode *inode,
+ unsigned int current_depth);
+int room_for_filename(const void *bitmap, int slots, int max_slots);
+void f2fs_drop_nlink(struct inode *dir, struct inode *inode);
+struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
+ struct fscrypt_name *fname, struct page **res_page);
+struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
+ struct qstr *child, struct page **res_page);
+struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p);
+ino_t f2fs_inode_by_name(struct inode *dir, struct qstr *qstr,
+ struct page **page);
+void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
+ struct page *page, struct inode *inode);
+void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
+ const struct qstr *name, f2fs_hash_t name_hash,
+ unsigned int bit_pos);
+int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
+ const struct qstr *orig_name,
+ struct inode *inode, nid_t ino, umode_t mode);
+int __f2fs_do_add_link(struct inode *dir, struct fscrypt_name *fname,
+ struct inode *inode, nid_t ino, umode_t mode);
+int __f2fs_add_link(struct inode *dir, const struct qstr *name,
+ struct inode *inode, nid_t ino, umode_t mode);
+void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
+ struct inode *dir, struct inode *inode);
+int f2fs_do_tmpfile(struct inode *inode, struct inode *dir);
+bool f2fs_empty_dir(struct inode *dir);
static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
{
- return __f2fs_add_link(dentry->d_parent->d_inode, &dentry->d_name,
- inode);
+ return __f2fs_add_link(d_inode(dentry->d_parent), &dentry->d_name,
+ inode, inode->i_ino, inode->i_mode);
}
/*
* super.c
*/
-int f2fs_sync_fs(struct super_block *, int);
+int f2fs_inode_dirtied(struct inode *inode, bool sync);
+void f2fs_inode_synced(struct inode *inode);
+int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover);
+int f2fs_sync_fs(struct super_block *sb, int sync);
extern __printf(3, 4)
-void f2fs_msg(struct super_block *, const char *, const char *, ...);
+void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...);
+int sanity_check_ckpt(struct f2fs_sb_info *sbi);
/*
* hash.c
*/
-f2fs_hash_t f2fs_dentry_hash(const struct qstr *);
+f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info,
+ struct fscrypt_name *fname);
/*
* node.c
@@ -1261,136 +2300,186 @@
struct dnode_of_data;
struct node_info;
-bool available_free_memory(struct f2fs_sb_info *, int);
-bool is_checkpointed_node(struct f2fs_sb_info *, nid_t);
-bool has_fsynced_inode(struct f2fs_sb_info *, nid_t);
-bool need_inode_block_update(struct f2fs_sb_info *, nid_t);
-void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *);
-int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int);
-int truncate_inode_blocks(struct inode *, pgoff_t);
-int truncate_xattr_node(struct inode *, struct page *);
-int wait_on_node_pages_writeback(struct f2fs_sb_info *, nid_t);
-void remove_inode_page(struct inode *);
-struct page *new_inode_page(struct inode *);
-struct page *new_node_page(struct dnode_of_data *, unsigned int, struct page *);
-void ra_node_page(struct f2fs_sb_info *, nid_t);
-struct page *get_node_page(struct f2fs_sb_info *, pgoff_t);
-struct page *get_node_page_ra(struct page *, int);
-void sync_inode_page(struct dnode_of_data *);
-int sync_node_pages(struct f2fs_sb_info *, nid_t, struct writeback_control *);
-bool alloc_nid(struct f2fs_sb_info *, nid_t *);
-void alloc_nid_done(struct f2fs_sb_info *, nid_t);
-void alloc_nid_failed(struct f2fs_sb_info *, nid_t);
-void recover_inline_xattr(struct inode *, struct page *);
-void recover_xattr_data(struct inode *, struct page *, block_t);
-int recover_inode_page(struct f2fs_sb_info *, struct page *);
-int restore_node_summary(struct f2fs_sb_info *, unsigned int,
- struct f2fs_summary_block *);
-void flush_nat_entries(struct f2fs_sb_info *);
-int build_node_manager(struct f2fs_sb_info *);
-void destroy_node_manager(struct f2fs_sb_info *);
+bool available_free_memory(struct f2fs_sb_info *sbi, int type);
+int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid);
+bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid);
+bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino);
+void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni);
+pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs);
+int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode);
+int truncate_inode_blocks(struct inode *inode, pgoff_t from);
+int truncate_xattr_node(struct inode *inode, struct page *page);
+int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino);
+int remove_inode_page(struct inode *inode);
+struct page *new_inode_page(struct inode *inode);
+struct page *new_node_page(struct dnode_of_data *dn,
+ unsigned int ofs, struct page *ipage);
+void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid);
+struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid);
+struct page *get_node_page_ra(struct page *parent, int start);
+void move_node_page(struct page *node_page, int gc_type);
+int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
+ struct writeback_control *wbc, bool atomic);
+int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc);
+void build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount);
+bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid);
+void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid);
+void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid);
+int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink);
+void recover_inline_xattr(struct inode *inode, struct page *page);
+int recover_xattr_data(struct inode *inode, struct page *page,
+ block_t blkaddr);
+int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page);
+int restore_node_summary(struct f2fs_sb_info *sbi,
+ unsigned int segno, struct f2fs_summary_block *sum);
+void flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+int build_node_manager(struct f2fs_sb_info *sbi);
+void destroy_node_manager(struct f2fs_sb_info *sbi);
int __init create_node_manager_caches(void);
void destroy_node_manager_caches(void);
/*
* segment.c
*/
-void register_inmem_page(struct inode *, struct page *);
-void commit_inmem_pages(struct inode *, bool);
-void f2fs_balance_fs(struct f2fs_sb_info *);
-void f2fs_balance_fs_bg(struct f2fs_sb_info *);
-int f2fs_issue_flush(struct f2fs_sb_info *);
-int create_flush_cmd_control(struct f2fs_sb_info *);
-void destroy_flush_cmd_control(struct f2fs_sb_info *);
-void invalidate_blocks(struct f2fs_sb_info *, block_t);
-void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t);
-void clear_prefree_segments(struct f2fs_sb_info *);
-void release_discard_addrs(struct f2fs_sb_info *);
-void discard_next_dnode(struct f2fs_sb_info *, block_t);
-int npages_for_summary_flush(struct f2fs_sb_info *);
-void allocate_new_segments(struct f2fs_sb_info *);
-int f2fs_trim_fs(struct f2fs_sb_info *, struct fstrim_range *);
-struct page *get_sum_page(struct f2fs_sb_info *, unsigned int);
-void write_meta_page(struct f2fs_sb_info *, struct page *);
-void write_node_page(struct f2fs_sb_info *, struct page *,
- struct f2fs_io_info *, unsigned int, block_t, block_t *);
-void write_data_page(struct page *, struct dnode_of_data *, block_t *,
- struct f2fs_io_info *);
-void rewrite_data_page(struct page *, block_t, struct f2fs_io_info *);
-void recover_data_page(struct f2fs_sb_info *, struct page *,
- struct f2fs_summary *, block_t, block_t);
-void allocate_data_block(struct f2fs_sb_info *, struct page *,
- block_t, block_t *, struct f2fs_summary *, int);
-void f2fs_wait_on_page_writeback(struct page *, enum page_type);
-void write_data_summaries(struct f2fs_sb_info *, block_t);
-void write_node_summaries(struct f2fs_sb_info *, block_t);
-int lookup_journal_in_cursum(struct f2fs_summary_block *,
- int, unsigned int, int);
-void flush_sit_entries(struct f2fs_sb_info *, struct cp_control *);
-int build_segment_manager(struct f2fs_sb_info *);
-void destroy_segment_manager(struct f2fs_sb_info *);
+void register_inmem_page(struct inode *inode, struct page *page);
+void drop_inmem_pages(struct inode *inode);
+void drop_inmem_page(struct inode *inode, struct page *page);
+int commit_inmem_pages(struct inode *inode);
+void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need);
+void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi);
+int f2fs_issue_flush(struct f2fs_sb_info *sbi);
+int create_flush_cmd_control(struct f2fs_sb_info *sbi);
+void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free);
+void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr);
+bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr);
+void refresh_sit_entry(struct f2fs_sb_info *sbi, block_t old, block_t new);
+void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi);
+void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+void release_discard_addrs(struct f2fs_sb_info *sbi);
+int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
+void allocate_new_segments(struct f2fs_sb_info *sbi);
+int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range);
+bool exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno);
+void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr);
+void write_meta_page(struct f2fs_sb_info *sbi, struct page *page);
+void write_node_page(unsigned int nid, struct f2fs_io_info *fio);
+void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio);
+int rewrite_data_page(struct f2fs_io_info *fio);
+void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
+ block_t old_blkaddr, block_t new_blkaddr,
+ bool recover_curseg, bool recover_newaddr);
+void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
+ block_t old_addr, block_t new_addr,
+ unsigned char version, bool recover_curseg,
+ bool recover_newaddr);
+void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
+ block_t old_blkaddr, block_t *new_blkaddr,
+ struct f2fs_summary *sum, int type);
+void f2fs_wait_on_page_writeback(struct page *page,
+ enum page_type type, bool ordered);
+void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi,
+ block_t blkaddr);
+void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
+void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
+int lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
+ unsigned int val, int alloc);
+void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+int build_segment_manager(struct f2fs_sb_info *sbi);
+void destroy_segment_manager(struct f2fs_sb_info *sbi);
int __init create_segment_manager_caches(void);
void destroy_segment_manager_caches(void);
/*
* checkpoint.c
*/
-struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t);
-struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t);
-struct page *get_meta_page_ra(struct f2fs_sb_info *, pgoff_t);
-int ra_meta_pages(struct f2fs_sb_info *, block_t, int, int);
-long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long);
-void add_dirty_inode(struct f2fs_sb_info *, nid_t, int type);
-void remove_dirty_inode(struct f2fs_sb_info *, nid_t, int type);
-void release_dirty_inode(struct f2fs_sb_info *);
-bool exist_written_data(struct f2fs_sb_info *, nid_t, int);
-int acquire_orphan_inode(struct f2fs_sb_info *);
-void release_orphan_inode(struct f2fs_sb_info *);
-void add_orphan_inode(struct f2fs_sb_info *, nid_t);
-void remove_orphan_inode(struct f2fs_sb_info *, nid_t);
-void recover_orphan_inodes(struct f2fs_sb_info *);
-int get_valid_checkpoint(struct f2fs_sb_info *);
-void update_dirty_page(struct inode *, struct page *);
-void add_dirty_dir_inode(struct inode *);
-void remove_dirty_dir_inode(struct inode *);
-void sync_dirty_dir_inodes(struct f2fs_sb_info *);
-void write_checkpoint(struct f2fs_sb_info *, struct cp_control *);
-void init_ino_entry_info(struct f2fs_sb_info *);
+void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io);
+struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
+struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
+struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index);
+bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type);
+int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
+ int type, bool sync);
+void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index);
+long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
+ long nr_to_write);
+void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
+void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
+void release_ino_entry(struct f2fs_sb_info *sbi, bool all);
+bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode);
+int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi);
+int acquire_orphan_inode(struct f2fs_sb_info *sbi);
+void release_orphan_inode(struct f2fs_sb_info *sbi);
+void add_orphan_inode(struct inode *inode);
+void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino);
+int recover_orphan_inodes(struct f2fs_sb_info *sbi);
+int get_valid_checkpoint(struct f2fs_sb_info *sbi);
+void update_dirty_page(struct inode *inode, struct page *page);
+void remove_dirty_inode(struct inode *inode);
+int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type);
+int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+void init_ino_entry_info(struct f2fs_sb_info *sbi);
int __init create_checkpoint_caches(void);
void destroy_checkpoint_caches(void);
/*
* data.c
*/
-void f2fs_submit_merged_bio(struct f2fs_sb_info *, enum page_type, int);
-int f2fs_submit_page_bio(struct f2fs_sb_info *, struct page *, block_t, int);
-void f2fs_submit_page_mbio(struct f2fs_sb_info *, struct page *, block_t,
- struct f2fs_io_info *);
-int reserve_new_block(struct dnode_of_data *);
-int f2fs_reserve_block(struct dnode_of_data *, pgoff_t);
-void update_extent_cache(block_t, struct dnode_of_data *);
-struct page *find_data_page(struct inode *, pgoff_t, bool);
-struct page *get_lock_data_page(struct inode *, pgoff_t);
-struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool);
-int do_write_data_page(struct page *, struct f2fs_io_info *);
-int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64);
+void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, enum page_type type,
+ int rw);
+void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *sbi,
+ struct inode *inode, nid_t ino, pgoff_t idx,
+ enum page_type type, int rw);
+void f2fs_flush_merged_bios(struct f2fs_sb_info *sbi);
+int f2fs_submit_page_bio(struct f2fs_io_info *fio);
+int f2fs_submit_page_mbio(struct f2fs_io_info *fio);
+struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
+ block_t blk_addr, struct bio *bio);
+int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr);
+void set_data_blkaddr(struct dnode_of_data *dn);
+void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr);
+int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count);
+int reserve_new_block(struct dnode_of_data *dn);
+int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index);
+int f2fs_preallocate_blocks(struct inode *inode, loff_t pos,
+ size_t count, bool dio);
+int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index);
+struct page *get_read_data_page(struct inode *inode, pgoff_t index,
+ int op_flags, bool for_write);
+struct page *find_data_page(struct inode *inode, pgoff_t index);
+struct page *get_lock_data_page(struct inode *inode, pgoff_t index,
+ bool for_write);
+struct page *get_new_data_page(struct inode *inode,
+ struct page *ipage, pgoff_t index, bool new_i_size);
+int do_write_data_page(struct f2fs_io_info *fio);
+int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
+ int create, int flag);
+int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len);
+void f2fs_set_page_dirty_nobuffers(struct page *page);
+void f2fs_invalidate_page(struct page *page, unsigned int offset,
+ unsigned int length);
+int f2fs_release_page(struct page *page, gfp_t wait);
+#ifdef CONFIG_MIGRATION
+int f2fs_migrate_page(struct address_space *mapping, struct page *newpage,
+ struct page *page, enum migrate_mode mode);
+#endif
/*
* gc.c
*/
-int start_gc_thread(struct f2fs_sb_info *);
-void stop_gc_thread(struct f2fs_sb_info *);
-block_t start_bidx_of_node(unsigned int, struct f2fs_inode_info *);
-int f2fs_gc(struct f2fs_sb_info *);
-void build_gc_manager(struct f2fs_sb_info *);
-int __init create_gc_caches(void);
-void destroy_gc_caches(void);
+int start_gc_thread(struct f2fs_sb_info *sbi);
+void stop_gc_thread(struct f2fs_sb_info *sbi);
+block_t start_bidx_of_node(unsigned int node_ofs, struct inode *inode);
+int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background,
+ unsigned int segno);
+void build_gc_manager(struct f2fs_sb_info *sbi);
/*
* recovery.c
*/
-int recover_fsync_data(struct f2fs_sb_info *);
-bool space_for_roll_forward(struct f2fs_sb_info *);
+int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only);
+bool space_for_roll_forward(struct f2fs_sb_info *sbi);
/*
* debug.c
@@ -1401,26 +2490,39 @@
struct f2fs_sb_info *sbi;
int all_area_segs, sit_area_segs, nat_area_segs, ssa_area_segs;
int main_area_segs, main_area_sections, main_area_zones;
- int hit_ext, total_ext;
- int ndirty_node, ndirty_dent, ndirty_dirs, ndirty_meta;
- int nats, sits, fnids;
+ unsigned long long hit_largest, hit_cached, hit_rbtree;
+ unsigned long long hit_total, total_ext;
+ int ext_tree, zombie_tree, ext_node;
+ int ndirty_node, ndirty_dent, ndirty_meta, ndirty_data, ndirty_imeta;
+ int inmem_pages;
+ unsigned int ndirty_dirs, ndirty_files, ndirty_all;
+ int nats, dirty_nats, sits, dirty_sits;
+ int free_nids, avail_nids, alloc_nids;
int total_count, utilization;
- int bg_gc, inline_inode;
- unsigned int valid_count, valid_node_count, valid_inode_count;
+ int bg_gc, nr_wb_cp_data, nr_wb_data;
+ int nr_flushing, nr_flushed, nr_discarding, nr_discarded;
+ int nr_discard_cmd;
+ unsigned int undiscard_blks;
+ int inline_xattr, inline_inode, inline_dir, append, update, orphans;
+ int aw_cnt, max_aw_cnt, vw_cnt, max_vw_cnt;
+ unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks;
unsigned int bimodal, avg_vblocks;
int util_free, util_valid, util_invalid;
int rsvd_segs, overp_segs;
int dirty_count, node_pages, meta_pages;
- int prefree_count, call_count, cp_count;
+ int prefree_count, call_count, cp_count, bg_cp_count;
int tot_segs, node_segs, data_segs, free_segs, free_secs;
+ int bg_node_segs, bg_data_segs;
int tot_blks, data_blks, node_blks;
+ int bg_data_blks, bg_node_blks;
int curseg[NR_CURSEG_TYPE];
int cursec[NR_CURSEG_TYPE];
int curzone[NR_CURSEG_TYPE];
unsigned int segment_count[2];
unsigned int block_count[2];
- unsigned base_mem, cache_mem;
+ unsigned int inplace_count;
+ unsigned long long base_mem, cache_mem, page_mem;
};
static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
@@ -1429,79 +2531,143 @@
}
#define stat_inc_cp_count(si) ((si)->cp_count++)
+#define stat_inc_bg_cp_count(si) ((si)->bg_cp_count++)
#define stat_inc_call_count(si) ((si)->call_count++)
#define stat_inc_bggc_count(sbi) ((sbi)->bg_gc++)
-#define stat_inc_dirty_dir(sbi) ((sbi)->n_dirty_dirs++)
-#define stat_dec_dirty_dir(sbi) ((sbi)->n_dirty_dirs--)
-#define stat_inc_total_hit(sb) ((F2FS_SB(sb))->total_hit_ext++)
-#define stat_inc_read_hit(sb) ((F2FS_SB(sb))->read_hit_ext++)
+#define stat_inc_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]++)
+#define stat_dec_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]--)
+#define stat_inc_total_hit(sbi) (atomic64_inc(&(sbi)->total_hit_ext))
+#define stat_inc_rbtree_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_rbtree))
+#define stat_inc_largest_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_largest))
+#define stat_inc_cached_node_hit(sbi) (atomic64_inc(&(sbi)->read_hit_cached))
+#define stat_inc_inline_xattr(inode) \
+ do { \
+ if (f2fs_has_inline_xattr(inode)) \
+ (atomic_inc(&F2FS_I_SB(inode)->inline_xattr)); \
+ } while (0)
+#define stat_dec_inline_xattr(inode) \
+ do { \
+ if (f2fs_has_inline_xattr(inode)) \
+ (atomic_dec(&F2FS_I_SB(inode)->inline_xattr)); \
+ } while (0)
#define stat_inc_inline_inode(inode) \
do { \
if (f2fs_has_inline_data(inode)) \
- ((F2FS_I_SB(inode))->inline_inode++); \
+ (atomic_inc(&F2FS_I_SB(inode)->inline_inode)); \
} while (0)
#define stat_dec_inline_inode(inode) \
do { \
if (f2fs_has_inline_data(inode)) \
- ((F2FS_I_SB(inode))->inline_inode--); \
+ (atomic_dec(&F2FS_I_SB(inode)->inline_inode)); \
} while (0)
-
+#define stat_inc_inline_dir(inode) \
+ do { \
+ if (f2fs_has_inline_dentry(inode)) \
+ (atomic_inc(&F2FS_I_SB(inode)->inline_dir)); \
+ } while (0)
+#define stat_dec_inline_dir(inode) \
+ do { \
+ if (f2fs_has_inline_dentry(inode)) \
+ (atomic_dec(&F2FS_I_SB(inode)->inline_dir)); \
+ } while (0)
#define stat_inc_seg_type(sbi, curseg) \
((sbi)->segment_count[(curseg)->alloc_type]++)
#define stat_inc_block_count(sbi, curseg) \
((sbi)->block_count[(curseg)->alloc_type]++)
-
-#define stat_inc_seg_count(sbi, type) \
+#define stat_inc_inplace_blocks(sbi) \
+ (atomic_inc(&(sbi)->inplace_count))
+#define stat_inc_atomic_write(inode) \
+ (atomic_inc(&F2FS_I_SB(inode)->aw_cnt))
+#define stat_dec_atomic_write(inode) \
+ (atomic_dec(&F2FS_I_SB(inode)->aw_cnt))
+#define stat_update_max_atomic_write(inode) \
+ do { \
+ int cur = atomic_read(&F2FS_I_SB(inode)->aw_cnt); \
+ int max = atomic_read(&F2FS_I_SB(inode)->max_aw_cnt); \
+ if (cur > max) \
+ atomic_set(&F2FS_I_SB(inode)->max_aw_cnt, cur); \
+ } while (0)
+#define stat_inc_volatile_write(inode) \
+ (atomic_inc(&F2FS_I_SB(inode)->vw_cnt))
+#define stat_dec_volatile_write(inode) \
+ (atomic_dec(&F2FS_I_SB(inode)->vw_cnt))
+#define stat_update_max_volatile_write(inode) \
+ do { \
+ int cur = atomic_read(&F2FS_I_SB(inode)->vw_cnt); \
+ int max = atomic_read(&F2FS_I_SB(inode)->max_vw_cnt); \
+ if (cur > max) \
+ atomic_set(&F2FS_I_SB(inode)->max_vw_cnt, cur); \
+ } while (0)
+#define stat_inc_seg_count(sbi, type, gc_type) \
do { \
struct f2fs_stat_info *si = F2FS_STAT(sbi); \
- (si)->tot_segs++; \
- if (type == SUM_TYPE_DATA) \
+ si->tot_segs++; \
+ if ((type) == SUM_TYPE_DATA) { \
si->data_segs++; \
- else \
+ si->bg_data_segs += (gc_type == BG_GC) ? 1 : 0; \
+ } else { \
si->node_segs++; \
+ si->bg_node_segs += (gc_type == BG_GC) ? 1 : 0; \
+ } \
} while (0)
#define stat_inc_tot_blk_count(si, blks) \
- (si->tot_blks += (blks))
+ ((si)->tot_blks += (blks))
-#define stat_inc_data_blk_count(sbi, blks) \
+#define stat_inc_data_blk_count(sbi, blks, gc_type) \
do { \
struct f2fs_stat_info *si = F2FS_STAT(sbi); \
stat_inc_tot_blk_count(si, blks); \
si->data_blks += (blks); \
+ si->bg_data_blks += ((gc_type) == BG_GC) ? (blks) : 0; \
} while (0)
-#define stat_inc_node_blk_count(sbi, blks) \
+#define stat_inc_node_blk_count(sbi, blks, gc_type) \
do { \
struct f2fs_stat_info *si = F2FS_STAT(sbi); \
stat_inc_tot_blk_count(si, blks); \
si->node_blks += (blks); \
+ si->bg_node_blks += ((gc_type) == BG_GC) ? (blks) : 0; \
} while (0)
-int f2fs_build_stats(struct f2fs_sb_info *);
-void f2fs_destroy_stats(struct f2fs_sb_info *);
-void __init f2fs_create_root_stats(void);
+int f2fs_build_stats(struct f2fs_sb_info *sbi);
+void f2fs_destroy_stats(struct f2fs_sb_info *sbi);
+int __init f2fs_create_root_stats(void);
void f2fs_destroy_root_stats(void);
#else
-#define stat_inc_cp_count(si)
-#define stat_inc_call_count(si)
-#define stat_inc_bggc_count(si)
-#define stat_inc_dirty_dir(sbi)
-#define stat_dec_dirty_dir(sbi)
-#define stat_inc_total_hit(sb)
-#define stat_inc_read_hit(sb)
-#define stat_inc_inline_inode(inode)
-#define stat_dec_inline_inode(inode)
-#define stat_inc_seg_type(sbi, curseg)
-#define stat_inc_block_count(sbi, curseg)
-#define stat_inc_seg_count(si, type)
-#define stat_inc_tot_blk_count(si, blks)
-#define stat_inc_data_blk_count(si, blks)
-#define stat_inc_node_blk_count(sbi, blks)
+#define stat_inc_cp_count(si) do { } while (0)
+#define stat_inc_bg_cp_count(si) do { } while (0)
+#define stat_inc_call_count(si) do { } while (0)
+#define stat_inc_bggc_count(si) do { } while (0)
+#define stat_inc_dirty_inode(sbi, type) do { } while (0)
+#define stat_dec_dirty_inode(sbi, type) do { } while (0)
+#define stat_inc_total_hit(sb) do { } while (0)
+#define stat_inc_rbtree_node_hit(sb) do { } while (0)
+#define stat_inc_largest_node_hit(sbi) do { } while (0)
+#define stat_inc_cached_node_hit(sbi) do { } while (0)
+#define stat_inc_inline_xattr(inode) do { } while (0)
+#define stat_dec_inline_xattr(inode) do { } while (0)
+#define stat_inc_inline_inode(inode) do { } while (0)
+#define stat_dec_inline_inode(inode) do { } while (0)
+#define stat_inc_inline_dir(inode) do { } while (0)
+#define stat_dec_inline_dir(inode) do { } while (0)
+#define stat_inc_atomic_write(inode) do { } while (0)
+#define stat_dec_atomic_write(inode) do { } while (0)
+#define stat_update_max_atomic_write(inode) do { } while (0)
+#define stat_inc_volatile_write(inode) do { } while (0)
+#define stat_dec_volatile_write(inode) do { } while (0)
+#define stat_update_max_volatile_write(inode) do { } while (0)
+#define stat_inc_seg_type(sbi, curseg) do { } while (0)
+#define stat_inc_block_count(sbi, curseg) do { } while (0)
+#define stat_inc_inplace_blocks(sbi) do { } while (0)
+#define stat_inc_seg_count(sbi, type, gc_type) do { } while (0)
+#define stat_inc_tot_blk_count(si, blks) do { } while (0)
+#define stat_inc_data_blk_count(sbi, blks, gc_type) do { } while (0)
+#define stat_inc_node_blk_count(sbi, blks, gc_type) do { } while (0)
static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; }
static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { }
-static inline void __init f2fs_create_root_stats(void) { }
+static inline int __init f2fs_create_root_stats(void) { return 0; }
static inline void f2fs_destroy_root_stats(void) { }
#endif
@@ -1513,15 +2679,151 @@
extern const struct address_space_operations f2fs_meta_aops;
extern const struct inode_operations f2fs_dir_inode_operations;
extern const struct inode_operations f2fs_symlink_inode_operations;
+extern const struct inode_operations f2fs_encrypted_symlink_inode_operations;
extern const struct inode_operations f2fs_special_inode_operations;
+extern struct kmem_cache *inode_entry_slab;
/*
* inline.c
*/
-bool f2fs_may_inline(struct inode *);
-int f2fs_read_inline_data(struct inode *, struct page *);
-int f2fs_convert_inline_data(struct inode *, pgoff_t, struct page *);
-int f2fs_write_inline_data(struct inode *, struct page *, unsigned int);
-void truncate_inline_data(struct inode *, u64);
-bool recover_inline_data(struct inode *, struct page *);
+bool f2fs_may_inline_data(struct inode *inode);
+bool f2fs_may_inline_dentry(struct inode *inode);
+void read_inline_data(struct page *page, struct page *ipage);
+void truncate_inline_inode(struct inode *inode, struct page *ipage, u64 from);
+int f2fs_read_inline_data(struct inode *inode, struct page *page);
+int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page);
+int f2fs_convert_inline_inode(struct inode *inode);
+int f2fs_write_inline_data(struct inode *inode, struct page *page);
+bool recover_inline_data(struct inode *inode, struct page *npage);
+struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
+ struct fscrypt_name *fname, struct page **res_page);
+int make_empty_inline_dir(struct inode *inode, struct inode *parent,
+ struct page *ipage);
+int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
+ const struct qstr *orig_name,
+ struct inode *inode, nid_t ino, umode_t mode);
+void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page,
+ struct inode *dir, struct inode *inode);
+bool f2fs_empty_inline_dir(struct inode *dir);
+int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
+ struct fscrypt_str *fstr);
+int f2fs_inline_data_fiemap(struct inode *inode,
+ struct fiemap_extent_info *fieinfo,
+ __u64 start, __u64 len);
+
+/*
+ * shrinker.c
+ */
+unsigned long f2fs_shrink_count(struct shrinker *shrink,
+ struct shrink_control *sc);
+unsigned long f2fs_shrink_scan(struct shrinker *shrink,
+ struct shrink_control *sc);
+void f2fs_join_shrinker(struct f2fs_sb_info *sbi);
+void f2fs_leave_shrinker(struct f2fs_sb_info *sbi);
+
+/*
+ * extent_cache.c
+ */
+struct rb_entry *__lookup_rb_tree(struct rb_root *root,
+ struct rb_entry *cached_re, unsigned int ofs);
+struct rb_node **__lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
+ struct rb_root *root, struct rb_node **parent,
+ unsigned int ofs);
+struct rb_entry *__lookup_rb_tree_ret(struct rb_root *root,
+ struct rb_entry *cached_re, unsigned int ofs,
+ struct rb_entry **prev_entry, struct rb_entry **next_entry,
+ struct rb_node ***insert_p, struct rb_node **insert_parent,
+ bool force);
+bool __check_rb_tree_consistence(struct f2fs_sb_info *sbi,
+ struct rb_root *root);
+unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink);
+bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext);
+void f2fs_drop_extent_tree(struct inode *inode);
+unsigned int f2fs_destroy_extent_node(struct inode *inode);
+void f2fs_destroy_extent_tree(struct inode *inode);
+bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
+ struct extent_info *ei);
+void f2fs_update_extent_cache(struct dnode_of_data *dn);
+void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
+ pgoff_t fofs, block_t blkaddr, unsigned int len);
+void init_extent_cache_info(struct f2fs_sb_info *sbi);
+int __init create_extent_cache(void);
+void destroy_extent_cache(void);
+
+/*
+ * crypto support
+ */
+static inline bool f2fs_encrypted_inode(struct inode *inode)
+{
+ return file_is_encrypt(inode);
+}
+
+static inline void f2fs_set_encrypted_inode(struct inode *inode)
+{
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ file_set_encrypt(inode);
+#endif
+}
+
+static inline bool f2fs_bio_encrypted(struct bio *bio)
+{
+ return bio->bi_private != NULL;
+}
+
+static inline int f2fs_sb_has_crypto(struct super_block *sb)
+{
+ return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_ENCRYPT);
+}
+
+static inline int f2fs_sb_mounted_blkzoned(struct super_block *sb)
+{
+ return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_BLKZONED);
+}
+
+#ifdef CONFIG_BLK_DEV_ZONED
+static inline int get_blkz_type(struct f2fs_sb_info *sbi,
+ struct block_device *bdev, block_t blkaddr)
+{
+ unsigned int zno = blkaddr >> sbi->log_blocks_per_blkz;
+ int i;
+
+ for (i = 0; i < sbi->s_ndevs; i++)
+ if (FDEV(i).bdev == bdev)
+ return FDEV(i).blkz_type[zno];
+ return -EINVAL;
+}
+#endif
+
+static inline bool f2fs_discard_en(struct f2fs_sb_info *sbi)
+{
+ struct request_queue *q = bdev_get_queue(sbi->sb->s_bdev);
+
+ return blk_queue_discard(q) || f2fs_sb_mounted_blkzoned(sbi->sb);
+}
+
+static inline void set_opt_mode(struct f2fs_sb_info *sbi, unsigned int mt)
+{
+ clear_opt(sbi, ADAPTIVE);
+ clear_opt(sbi, LFS);
+
+ switch (mt) {
+ case F2FS_MOUNT_ADAPTIVE:
+ set_opt(sbi, ADAPTIVE);
+ break;
+ case F2FS_MOUNT_LFS:
+ set_opt(sbi, LFS);
+ break;
+ }
+}
+
+static inline bool f2fs_may_encrypt(struct inode *inode)
+{
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+ mode_t mode = inode->i_mode;
+
+ return (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode));
+#else
+ return 0;
+#endif
+}
#endif
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 8e68bb6..5e8ea49 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -20,12 +20,18 @@
#include <linux/uaccess.h>
#include <linux/mount.h>
#include <linux/pagevec.h>
+#include <linux/random.h>
+#include <linux/aio.h>
+#include <linux/uuid.h>
+#include <linux/file.h>
#include "f2fs.h"
#include "node.h"
#include "segment.h"
#include "xattr.h"
#include "acl.h"
+#include "gc.h"
+#include "trace.h"
#include <trace/events/f2fs.h>
static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
@@ -37,22 +43,22 @@
struct dnode_of_data dn;
int err;
- f2fs_balance_fs(sbi);
-
sb_start_pagefault(inode->i_sb);
- /* force to convert with normal data indices */
- err = f2fs_convert_inline_data(inode, MAX_INLINE_DATA + 1, page);
- if (err)
- goto out;
+ f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
/* block allocation */
f2fs_lock_op(sbi);
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = f2fs_reserve_block(&dn, page->index);
- f2fs_unlock_op(sbi);
- if (err)
+ if (err) {
+ f2fs_unlock_op(sbi);
goto out;
+ }
+ f2fs_put_dnode(&dn);
+ f2fs_unlock_op(sbi);
+
+ f2fs_balance_fs(sbi, dn.node_changed);
file_update_time(vma->vm_file);
lock_page(page);
@@ -71,20 +77,28 @@
goto mapped;
/* page is wholly or partially inside EOF */
- if (((page->index + 1) << PAGE_CACHE_SHIFT) > i_size_read(inode)) {
+ if (((loff_t)(page->index + 1) << PAGE_SHIFT) >
+ i_size_read(inode)) {
unsigned offset;
- offset = i_size_read(inode) & ~PAGE_CACHE_MASK;
- zero_user_segment(page, offset, PAGE_CACHE_SIZE);
+ offset = i_size_read(inode) & ~PAGE_MASK;
+ zero_user_segment(page, offset, PAGE_SIZE);
}
set_page_dirty(page);
- SetPageUptodate(page);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
trace_f2fs_vm_page_mkwrite(page, DATA);
mapped:
/* fill the page */
- f2fs_wait_on_page_writeback(page, DATA);
+ f2fs_wait_on_page_writeback(page, DATA, false);
+
+ /* wait for GCed encrypted page writeback */
+ if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
+ f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr);
+
out:
sb_end_pagefault(inode->i_sb);
+ f2fs_update_time(sbi, REQ_TIME);
return block_page_mkwrite_return(err);
}
@@ -92,7 +106,6 @@
.fault = filemap_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = f2fs_vm_page_mkwrite,
- .remap_pages = generic_file_remap_pages,
};
static int get_parent_ino(struct inode *inode, nid_t *pino)
@@ -105,11 +118,6 @@
if (!dentry)
return 0;
- if (update_dent_inode(inode, &dentry->d_name)) {
- dput(dentry);
- return 0;
- }
-
*pino = parent_ino(dentry);
dput(dentry);
return 1;
@@ -122,22 +130,51 @@
if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1)
need_cp = true;
+ else if (is_sbi_flag_set(sbi, SBI_NEED_CP))
+ need_cp = true;
else if (file_wrong_pino(inode))
need_cp = true;
else if (!space_for_roll_forward(sbi))
need_cp = true;
else if (!is_checkpointed_node(sbi, F2FS_I(inode)->i_pino))
need_cp = true;
- else if (F2FS_I(inode)->xattr_ver == cur_cp_version(F2FS_CKPT(sbi)))
+ else if (test_opt(sbi, FASTBOOT))
+ need_cp = true;
+ else if (sbi->active_logs == 2)
need_cp = true;
return need_cp;
}
-int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
+static bool need_inode_page_update(struct f2fs_sb_info *sbi, nid_t ino)
+{
+ struct page *i = find_get_page(NODE_MAPPING(sbi), ino);
+ bool ret = false;
+ /* But we need to avoid that there are some inode updates */
+ if ((i && PageDirty(i)) || need_inode_block_update(sbi, ino))
+ ret = true;
+ f2fs_put_page(i, 0);
+ return ret;
+}
+
+static void try_to_fix_pino(struct inode *inode)
+{
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ nid_t pino;
+
+ down_write(&fi->i_sem);
+ if (file_wrong_pino(inode) && inode->i_nlink == 1 &&
+ get_parent_ino(inode, &pino)) {
+ f2fs_i_pino_write(inode, pino);
+ file_got_pino(inode);
+ }
+ up_write(&fi->i_sem);
+}
+
+static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end,
+ int datasync, bool atomic)
{
struct inode *inode = file->f_mapping->host;
- struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t ino = inode->i_ino;
int ret = 0;
@@ -154,96 +191,100 @@
trace_f2fs_sync_file_enter(inode);
/* if fdatasync is triggered, let's do in-place-update */
- if (get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
- set_inode_flag(fi, FI_NEED_IPU);
+ if (datasync || get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
+ set_inode_flag(inode, FI_NEED_IPU);
ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
- clear_inode_flag(fi, FI_NEED_IPU);
+ clear_inode_flag(inode, FI_NEED_IPU);
if (ret) {
trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
return ret;
}
+ /* if the inode is dirty, let's recover all the time */
+ if (!f2fs_skip_inode_update(inode, datasync)) {
+ f2fs_write_inode(inode, NULL);
+ goto go_write;
+ }
+
/*
* if there is no written data, don't waste time to write recovery info.
*/
- if (!is_inode_flag_set(fi, FI_APPEND_WRITE) &&
+ if (!is_inode_flag_set(inode, FI_APPEND_WRITE) &&
!exist_written_data(sbi, ino, APPEND_INO)) {
- struct page *i = find_get_page(NODE_MAPPING(sbi), ino);
- /* But we need to avoid that there are some inode updates */
- if ((i && PageDirty(i)) || need_inode_block_update(sbi, ino)) {
- f2fs_put_page(i, 0);
+ /* it may call write_inode just prior to fsync */
+ if (need_inode_page_update(sbi, ino))
goto go_write;
- }
- f2fs_put_page(i, 0);
- if (is_inode_flag_set(fi, FI_UPDATE_WRITE) ||
+ if (is_inode_flag_set(inode, FI_UPDATE_WRITE) ||
exist_written_data(sbi, ino, UPDATE_INO))
goto flush_out;
goto out;
}
go_write:
- /* guarantee free sections for fsync */
- f2fs_balance_fs(sbi);
-
/*
* Both of fdatasync() and fsync() are able to be recovered from
* sudden-power-off.
*/
- down_read(&fi->i_sem);
+ down_read(&F2FS_I(inode)->i_sem);
need_cp = need_do_checkpoint(inode);
- up_read(&fi->i_sem);
+ up_read(&F2FS_I(inode)->i_sem);
if (need_cp) {
- nid_t pino;
-
/* all the dirty node pages should be flushed for POR */
ret = f2fs_sync_fs(inode->i_sb, 1);
- down_write(&fi->i_sem);
- F2FS_I(inode)->xattr_ver = 0;
- if (file_wrong_pino(inode) && inode->i_nlink == 1 &&
- get_parent_ino(inode, &pino)) {
- F2FS_I(inode)->i_pino = pino;
- file_got_pino(inode);
- up_write(&fi->i_sem);
- mark_inode_dirty_sync(inode);
- ret = f2fs_write_inode(inode, NULL);
- if (ret)
- goto out;
- } else {
- up_write(&fi->i_sem);
- }
- } else {
-sync_nodes:
- sync_node_pages(sbi, ino, &wbc);
-
- if (need_inode_block_update(sbi, ino)) {
- mark_inode_dirty_sync(inode);
- ret = f2fs_write_inode(inode, NULL);
- if (ret)
- goto out;
- goto sync_nodes;
- }
-
- ret = wait_on_node_pages_writeback(sbi, ino);
- if (ret)
- goto out;
-
- /* once recovery info is written, don't need to tack this */
- remove_dirty_inode(sbi, ino, APPEND_INO);
- clear_inode_flag(fi, FI_APPEND_WRITE);
-flush_out:
- remove_dirty_inode(sbi, ino, UPDATE_INO);
- clear_inode_flag(fi, FI_UPDATE_WRITE);
- ret = f2fs_issue_flush(F2FS_I_SB(inode));
+ /*
+ * We've secured consistency through sync_fs. Following pino
+ * will be used only for fsynced inodes after checkpoint.
+ */
+ try_to_fix_pino(inode);
+ clear_inode_flag(inode, FI_APPEND_WRITE);
+ clear_inode_flag(inode, FI_UPDATE_WRITE);
+ goto out;
}
+sync_nodes:
+ ret = fsync_node_pages(sbi, inode, &wbc, atomic);
+ if (ret)
+ goto out;
+
+ /* if cp_error was enabled, we should avoid infinite loop */
+ if (unlikely(f2fs_cp_error(sbi))) {
+ ret = -EIO;
+ goto out;
+ }
+
+ if (need_inode_block_update(sbi, ino)) {
+ f2fs_mark_inode_dirty_sync(inode, true);
+ f2fs_write_inode(inode, NULL);
+ goto sync_nodes;
+ }
+
+ ret = wait_on_node_pages_writeback(sbi, ino);
+ if (ret)
+ goto out;
+
+ /* once recovery info is written, don't need to tack this */
+ remove_ino_entry(sbi, ino, APPEND_INO);
+ clear_inode_flag(inode, FI_APPEND_WRITE);
+flush_out:
+ remove_ino_entry(sbi, ino, UPDATE_INO);
+ clear_inode_flag(inode, FI_UPDATE_WRITE);
+ if (!atomic)
+ ret = f2fs_issue_flush(sbi);
+ f2fs_update_time(sbi, REQ_TIME);
out:
trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
+ f2fs_trace_ios(NULL, 1);
return ret;
}
+int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
+{
+ return f2fs_do_sync_file(file, start, end, datasync, false);
+}
+
static pgoff_t __get_first_dirty_index(struct address_space *mapping,
pgoff_t pgofs, int whence)
{
@@ -257,7 +298,7 @@
pagevec_init(&pvec, 0);
nr_pages = pagevec_lookup_tag(&pvec, mapping, &pgofs,
PAGECACHE_TAG_DIRTY, 1);
- pgofs = nr_pages ? pvec.pages[0]->index : LONG_MAX;
+ pgofs = nr_pages ? pvec.pages[0]->index : ULONG_MAX;
pagevec_release(&pvec);
return pgofs;
}
@@ -289,45 +330,44 @@
loff_t isize;
int err = 0;
- mutex_lock(&inode->i_mutex);
+ inode_lock(inode);
isize = i_size_read(inode);
if (offset >= isize)
goto fail;
/* handle inline data case */
- if (f2fs_has_inline_data(inode)) {
+ if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) {
if (whence == SEEK_HOLE)
data_ofs = isize;
goto found;
}
- pgofs = (pgoff_t)(offset >> PAGE_CACHE_SHIFT);
+ pgofs = (pgoff_t)(offset >> PAGE_SHIFT);
dirty = __get_first_dirty_index(inode->i_mapping, pgofs, whence);
- for (; data_ofs < isize; data_ofs = pgofs << PAGE_CACHE_SHIFT) {
+ for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_SHIFT) {
set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE_RA);
+ err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE);
if (err && err != -ENOENT) {
goto fail;
} else if (err == -ENOENT) {
/* direct node does not exists */
if (whence == SEEK_DATA) {
- pgofs = PGOFS_OF_NEXT_DNODE(pgofs,
- F2FS_I(inode));
+ pgofs = get_next_page_offset(&dn, pgofs);
continue;
} else {
goto found;
}
}
- end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+ end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
/* find data/hole in dnode block */
for (; dn.ofs_in_node < end_offset;
dn.ofs_in_node++, pgofs++,
- data_ofs = pgofs << PAGE_CACHE_SHIFT) {
+ data_ofs = (loff_t)pgofs << PAGE_SHIFT) {
block_t blkaddr;
blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
@@ -344,10 +384,10 @@
found:
if (whence == SEEK_HOLE && data_ofs > isize)
data_ofs = isize;
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
return vfs_setpos(file, data_ofs, maxbytes);
fail:
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
return -ENXIO;
}
@@ -374,16 +414,54 @@
static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
+ struct inode *inode = file_inode(file);
+ int err;
+
+ if (f2fs_encrypted_inode(inode)) {
+ err = fscrypt_get_encryption_info(inode);
+ if (err)
+ return 0;
+ if (!f2fs_encrypted_inode(inode))
+ return -ENOKEY;
+ }
+
+ /* we don't need to use inline_data strictly */
+ err = f2fs_convert_inline_inode(inode);
+ if (err)
+ return err;
+
file_accessed(file);
vma->vm_ops = &f2fs_file_vm_ops;
return 0;
}
+static int f2fs_file_open(struct inode *inode, struct file *filp)
+{
+ int ret = generic_file_open(inode, filp);
+ struct dentry *dir;
+
+ if (!ret && f2fs_encrypted_inode(inode)) {
+ ret = fscrypt_get_encryption_info(inode);
+ if (ret)
+ return -EACCES;
+ if (!fscrypt_has_encryption_key(inode))
+ return -ENOKEY;
+ }
+ dir = dget_parent(file_dentry(filp));
+ if (f2fs_encrypted_inode(d_inode(dir)) &&
+ !fscrypt_has_permitted_context(d_inode(dir), inode)) {
+ dput(dir);
+ return -EPERM;
+ }
+ dput(dir);
+ return ret;
+}
+
int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
{
- int nr_free = 0, ofs = dn->ofs_in_node;
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct f2fs_node *raw_node;
+ int nr_free = 0, ofs = dn->ofs_in_node, len = count;
__le32 *addr;
raw_node = F2FS_NODE(dn->node_page);
@@ -394,17 +472,28 @@
if (blkaddr == NULL_ADDR)
continue;
- update_extent_cache(NULL_ADDR, dn);
+ dn->data_blkaddr = NULL_ADDR;
+ set_data_blkaddr(dn);
invalidate_blocks(sbi, blkaddr);
+ if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page))
+ clear_inode_flag(dn->inode, FI_FIRST_BLOCK_WRITTEN);
nr_free++;
}
+
if (nr_free) {
+ pgoff_t fofs;
+ /*
+ * once we invalidate valid blkaddr in range [ofs, ofs + count],
+ * we will invalidate all blkaddr in the whole range.
+ */
+ fofs = start_bidx_of_node(ofs_of_node(dn->node_page),
+ dn->inode) + ofs;
+ f2fs_update_extent_cache_range(dn, fofs, 0, len);
dec_valid_block_count(sbi, dn->inode, nr_free);
- set_page_dirty(dn->node_page);
- sync_inode_page(dn);
}
dn->ofs_in_node = ofs;
+ f2fs_update_time(sbi, REQ_TIME);
trace_f2fs_truncate_data_blocks_range(dn->inode, dn->nid,
dn->ofs_in_node, nr_free);
return nr_free;
@@ -415,32 +504,36 @@
truncate_data_blocks_range(dn, ADDRS_PER_BLOCK);
}
-static void truncate_partial_data_page(struct inode *inode, u64 from)
+static int truncate_partial_data_page(struct inode *inode, u64 from,
+ bool cache_only)
{
- unsigned offset = from & (PAGE_CACHE_SIZE - 1);
+ unsigned offset = from & (PAGE_SIZE - 1);
+ pgoff_t index = from >> PAGE_SHIFT;
+ struct address_space *mapping = inode->i_mapping;
struct page *page;
- if (f2fs_has_inline_data(inode))
- return truncate_inline_data(inode, from);
+ if (!offset && !cache_only)
+ return 0;
- if (!offset)
- return;
+ if (cache_only) {
+ page = find_lock_page(mapping, index);
+ if (page && PageUptodate(page))
+ goto truncate_out;
+ f2fs_put_page(page, 1);
+ return 0;
+ }
- page = find_data_page(inode, from >> PAGE_CACHE_SHIFT, false);
+ page = get_lock_data_page(inode, index, true);
if (IS_ERR(page))
- return;
-
- lock_page(page);
- if (unlikely(!PageUptodate(page) ||
- page->mapping != inode->i_mapping))
- goto out;
-
- f2fs_wait_on_page_writeback(page, DATA);
- zero_user(page, offset, PAGE_CACHE_SIZE - offset);
- set_page_dirty(page);
-
-out:
+ return PTR_ERR(page) == -ENOENT ? 0 : PTR_ERR(page);
+truncate_out:
+ f2fs_wait_on_page_writeback(page, DATA, true);
+ zero_user(page, offset, PAGE_SIZE - offset);
+ if (!cache_only || !f2fs_encrypted_inode(inode) ||
+ !S_ISREG(inode->i_mode))
+ set_page_dirty(page);
f2fs_put_page(page, 1);
+ return 0;
}
int truncate_blocks(struct inode *inode, u64 from, bool lock)
@@ -450,30 +543,41 @@
struct dnode_of_data dn;
pgoff_t free_from;
int count = 0, err = 0;
+ struct page *ipage;
+ bool truncate_page = false;
trace_f2fs_truncate_blocks_enter(inode, from);
- if (f2fs_has_inline_data(inode))
- goto done;
+ free_from = (pgoff_t)F2FS_BYTES_TO_BLK(from + blocksize - 1);
- free_from = (pgoff_t)
- ((from + blocksize - 1) >> (sbi->log_blocksize));
+ if (free_from >= sbi->max_file_blocks)
+ goto free_partial;
if (lock)
f2fs_lock_op(sbi);
- set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE);
+ ipage = get_node_page(sbi, inode->i_ino);
+ if (IS_ERR(ipage)) {
+ err = PTR_ERR(ipage);
+ goto out;
+ }
+
+ if (f2fs_has_inline_data(inode)) {
+ truncate_inline_inode(inode, ipage, from);
+ f2fs_put_page(ipage, 1);
+ truncate_page = true;
+ goto out;
+ }
+
+ set_new_dnode(&dn, inode, ipage, NULL, 0);
+ err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE_RA);
if (err) {
if (err == -ENOENT)
goto free_next;
- if (lock)
- f2fs_unlock_op(sbi);
- trace_f2fs_truncate_blocks_exit(inode, err);
- return err;
+ goto out;
}
- count = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
+ count = ADDRS_PER_PAGE(dn.node_page, inode);
count -= dn.ofs_in_node;
f2fs_bug_on(sbi, count < 0);
@@ -486,34 +590,54 @@
f2fs_put_dnode(&dn);
free_next:
err = truncate_inode_blocks(inode, free_from);
+out:
if (lock)
f2fs_unlock_op(sbi);
-done:
+free_partial:
/* lastly zero out the first data page */
- truncate_partial_data_page(inode, from);
+ if (!err)
+ err = truncate_partial_data_page(inode, from, truncate_page);
trace_f2fs_truncate_blocks_exit(inode, err);
return err;
}
-void f2fs_truncate(struct inode *inode)
+int f2fs_truncate(struct inode *inode)
{
+ int err;
+
if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
S_ISLNK(inode->i_mode)))
- return;
+ return 0;
trace_f2fs_truncate(inode);
- if (!truncate_blocks(inode, i_size_read(inode), true)) {
- inode->i_mtime = inode->i_ctime = CURRENT_TIME;
- mark_inode_dirty(inode);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(F2FS_I_SB(inode), FAULT_TRUNCATE)) {
+ f2fs_show_injection_info(FAULT_TRUNCATE);
+ return -EIO;
}
+#endif
+ /* we should check inline_data size */
+ if (!f2fs_may_inline_data(inode)) {
+ err = f2fs_convert_inline_inode(inode);
+ if (err)
+ return err;
+ }
+
+ err = truncate_blocks(inode, i_size_read(inode), true);
+ if (err)
+ return err;
+
+ inode->i_mtime = inode->i_ctime = current_time(inode);
+ f2fs_mark_inode_dirty_sync(inode, false);
+ return 0;
}
int f2fs_getattr(struct vfsmount *mnt,
struct dentry *dentry, struct kstat *stat)
{
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
generic_fillattr(inode, stat);
stat->blocks <<= 3;
return 0;
@@ -522,7 +646,6 @@
#ifdef CONFIG_F2FS_FS_POSIX_ACL
static void __setattr_copy(struct inode *inode, const struct iattr *attr)
{
- struct f2fs_inode_info *fi = F2FS_I(inode);
unsigned int ia_valid = attr->ia_valid;
if (ia_valid & ATTR_UID)
@@ -543,7 +666,7 @@
if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
mode &= ~S_ISGID;
- set_acl_inode(fi, mode);
+ set_acl_inode(inode, mode);
}
}
#else
@@ -552,43 +675,59 @@
int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
{
- struct inode *inode = dentry->d_inode;
- struct f2fs_inode_info *fi = F2FS_I(inode);
+ struct inode *inode = d_inode(dentry);
int err;
+ bool size_changed = false;
err = inode_change_ok(inode, attr);
if (err)
return err;
if (attr->ia_valid & ATTR_SIZE) {
- err = f2fs_convert_inline_data(inode, attr->ia_size, NULL);
- if (err)
- return err;
+ if (f2fs_encrypted_inode(inode) &&
+ fscrypt_get_encryption_info(inode))
+ return -EACCES;
- if (attr->ia_size != i_size_read(inode)) {
+ if (attr->ia_size <= i_size_read(inode)) {
truncate_setsize(inode, attr->ia_size);
- f2fs_truncate(inode);
- f2fs_balance_fs(F2FS_I_SB(inode));
+ err = f2fs_truncate(inode);
+ if (err)
+ return err;
} else {
/*
- * giving a chance to truncate blocks past EOF which
- * are fallocated with FALLOC_FL_KEEP_SIZE.
+ * do not trim all blocks after i_size if target size is
+ * larger than i_size.
*/
- f2fs_truncate(inode);
+ truncate_setsize(inode, attr->ia_size);
+
+ /* should convert inline inode here */
+ if (!f2fs_may_inline_data(inode)) {
+ err = f2fs_convert_inline_inode(inode);
+ if (err)
+ return err;
+ }
+ inode->i_mtime = inode->i_ctime = current_time(inode);
}
+
+ size_changed = true;
}
__setattr_copy(inode, attr);
if (attr->ia_valid & ATTR_MODE) {
err = posix_acl_chmod(inode, get_inode_mode(inode));
- if (err || is_inode_flag_set(fi, FI_ACL_MODE)) {
- inode->i_mode = fi->i_acl_mode;
- clear_inode_flag(fi, FI_ACL_MODE);
+ if (err || is_inode_flag_set(inode, FI_ACL_MODE)) {
+ inode->i_mode = F2FS_I(inode)->i_acl_mode;
+ clear_inode_flag(inode, FI_ACL_MODE);
}
}
- mark_inode_dirty(inode);
+ /* file size may changed here */
+ f2fs_mark_inode_dirty_sync(inode, size_changed);
+
+ /* inode change will produce dirty node pages flushed by checkpoint */
+ f2fs_balance_fs(F2FS_I_SB(inode), true);
+
return err;
}
@@ -606,48 +745,58 @@
.fiemap = f2fs_fiemap,
};
-static void fill_zero(struct inode *inode, pgoff_t index,
+static int fill_zero(struct inode *inode, pgoff_t index,
loff_t start, loff_t len)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct page *page;
if (!len)
- return;
+ return 0;
- f2fs_balance_fs(sbi);
+ f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
page = get_new_data_page(inode, NULL, index, false);
f2fs_unlock_op(sbi);
- if (!IS_ERR(page)) {
- f2fs_wait_on_page_writeback(page, DATA);
- zero_user(page, start, len);
- set_page_dirty(page);
- f2fs_put_page(page, 1);
- }
+ if (IS_ERR(page))
+ return PTR_ERR(page);
+
+ f2fs_wait_on_page_writeback(page, DATA, true);
+ zero_user(page, start, len);
+ set_page_dirty(page);
+ f2fs_put_page(page, 1);
+ return 0;
}
int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
{
- pgoff_t index;
int err;
- for (index = pg_start; index < pg_end; index++) {
+ while (pg_start < pg_end) {
struct dnode_of_data dn;
+ pgoff_t end_offset, count;
set_new_dnode(&dn, inode, NULL, NULL, 0);
- err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
+ err = get_dnode_of_data(&dn, pg_start, LOOKUP_NODE);
if (err) {
- if (err == -ENOENT)
+ if (err == -ENOENT) {
+ pg_start++;
continue;
+ }
return err;
}
- if (dn.data_blkaddr != NULL_ADDR)
- truncate_data_blocks_range(&dn, 1);
+ end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
+ count = min(end_offset - dn.ofs_in_node, pg_end - pg_start);
+
+ f2fs_bug_on(F2FS_I_SB(inode), count == 0 || count > end_offset);
+
+ truncate_data_blocks_range(&dn, count);
f2fs_put_dnode(&dn);
+
+ pg_start += count;
}
return 0;
}
@@ -656,44 +805,45 @@
{
pgoff_t pg_start, pg_end;
loff_t off_start, off_end;
- int ret = 0;
+ int ret;
- if (!S_ISREG(inode->i_mode))
- return -EOPNOTSUPP;
-
- /* skip punching hole beyond i_size */
- if (offset >= inode->i_size)
- return ret;
-
- ret = f2fs_convert_inline_data(inode, MAX_INLINE_DATA + 1, NULL);
+ ret = f2fs_convert_inline_inode(inode);
if (ret)
return ret;
- pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT;
- pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT;
+ pg_start = ((unsigned long long) offset) >> PAGE_SHIFT;
+ pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT;
- off_start = offset & (PAGE_CACHE_SIZE - 1);
- off_end = (offset + len) & (PAGE_CACHE_SIZE - 1);
+ off_start = offset & (PAGE_SIZE - 1);
+ off_end = (offset + len) & (PAGE_SIZE - 1);
if (pg_start == pg_end) {
- fill_zero(inode, pg_start, off_start,
+ ret = fill_zero(inode, pg_start, off_start,
off_end - off_start);
+ if (ret)
+ return ret;
} else {
- if (off_start)
- fill_zero(inode, pg_start++, off_start,
- PAGE_CACHE_SIZE - off_start);
- if (off_end)
- fill_zero(inode, pg_end, 0, off_end);
+ if (off_start) {
+ ret = fill_zero(inode, pg_start++, off_start,
+ PAGE_SIZE - off_start);
+ if (ret)
+ return ret;
+ }
+ if (off_end) {
+ ret = fill_zero(inode, pg_end, 0, off_end);
+ if (ret)
+ return ret;
+ }
if (pg_start < pg_end) {
struct address_space *mapping = inode->i_mapping;
loff_t blk_start, blk_end;
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- f2fs_balance_fs(sbi);
+ f2fs_balance_fs(sbi, true);
- blk_start = pg_start << PAGE_CACHE_SHIFT;
- blk_end = pg_end << PAGE_CACHE_SHIFT;
+ blk_start = (loff_t)pg_start << PAGE_SHIFT;
+ blk_end = (loff_t)pg_end << PAGE_SHIFT;
truncate_inode_pages_range(mapping, blk_start,
blk_end - 1);
@@ -706,92 +856,599 @@
return ret;
}
-static int expand_inode_data(struct inode *inode, loff_t offset,
- loff_t len, int mode)
+static int __read_out_blkaddrs(struct inode *inode, block_t *blkaddr,
+ int *do_replace, pgoff_t off, pgoff_t len)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct dnode_of_data dn;
+ int ret, done, i;
+
+next_dnode:
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ ret = get_dnode_of_data(&dn, off, LOOKUP_NODE_RA);
+ if (ret && ret != -ENOENT) {
+ return ret;
+ } else if (ret == -ENOENT) {
+ if (dn.max_level == 0)
+ return -ENOENT;
+ done = min((pgoff_t)ADDRS_PER_BLOCK - dn.ofs_in_node, len);
+ blkaddr += done;
+ do_replace += done;
+ goto next;
+ }
+
+ done = min((pgoff_t)ADDRS_PER_PAGE(dn.node_page, inode) -
+ dn.ofs_in_node, len);
+ for (i = 0; i < done; i++, blkaddr++, do_replace++, dn.ofs_in_node++) {
+ *blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
+ if (!is_checkpointed_data(sbi, *blkaddr)) {
+
+ if (test_opt(sbi, LFS)) {
+ f2fs_put_dnode(&dn);
+ return -ENOTSUPP;
+ }
+
+ /* do not invalidate this block address */
+ f2fs_update_data_blkaddr(&dn, NULL_ADDR);
+ *do_replace = 1;
+ }
+ }
+ f2fs_put_dnode(&dn);
+next:
+ len -= done;
+ off += done;
+ if (len)
+ goto next_dnode;
+ return 0;
+}
+
+static int __roll_back_blkaddrs(struct inode *inode, block_t *blkaddr,
+ int *do_replace, pgoff_t off, int len)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct dnode_of_data dn;
+ int ret, i;
+
+ for (i = 0; i < len; i++, do_replace++, blkaddr++) {
+ if (*do_replace == 0)
+ continue;
+
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ ret = get_dnode_of_data(&dn, off + i, LOOKUP_NODE_RA);
+ if (ret) {
+ dec_valid_block_count(sbi, inode, 1);
+ invalidate_blocks(sbi, *blkaddr);
+ } else {
+ f2fs_update_data_blkaddr(&dn, *blkaddr);
+ }
+ f2fs_put_dnode(&dn);
+ }
+ return 0;
+}
+
+static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
+ block_t *blkaddr, int *do_replace,
+ pgoff_t src, pgoff_t dst, pgoff_t len, bool full)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(src_inode);
+ pgoff_t i = 0;
+ int ret;
+
+ while (i < len) {
+ if (blkaddr[i] == NULL_ADDR && !full) {
+ i++;
+ continue;
+ }
+
+ if (do_replace[i] || blkaddr[i] == NULL_ADDR) {
+ struct dnode_of_data dn;
+ struct node_info ni;
+ size_t new_size;
+ pgoff_t ilen;
+
+ set_new_dnode(&dn, dst_inode, NULL, NULL, 0);
+ ret = get_dnode_of_data(&dn, dst + i, ALLOC_NODE);
+ if (ret)
+ return ret;
+
+ get_node_info(sbi, dn.nid, &ni);
+ ilen = min((pgoff_t)
+ ADDRS_PER_PAGE(dn.node_page, dst_inode) -
+ dn.ofs_in_node, len - i);
+ do {
+ dn.data_blkaddr = datablock_addr(dn.node_page,
+ dn.ofs_in_node);
+ truncate_data_blocks_range(&dn, 1);
+
+ if (do_replace[i]) {
+ f2fs_i_blocks_write(src_inode,
+ 1, false);
+ f2fs_i_blocks_write(dst_inode,
+ 1, true);
+ f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
+ blkaddr[i], ni.version, true, false);
+
+ do_replace[i] = 0;
+ }
+ dn.ofs_in_node++;
+ i++;
+ new_size = (dst + i) << PAGE_SHIFT;
+ if (dst_inode->i_size < new_size)
+ f2fs_i_size_write(dst_inode, new_size);
+ } while (--ilen && (do_replace[i] || blkaddr[i] == NULL_ADDR));
+
+ f2fs_put_dnode(&dn);
+ } else {
+ struct page *psrc, *pdst;
+
+ psrc = get_lock_data_page(src_inode, src + i, true);
+ if (IS_ERR(psrc))
+ return PTR_ERR(psrc);
+ pdst = get_new_data_page(dst_inode, NULL, dst + i,
+ true);
+ if (IS_ERR(pdst)) {
+ f2fs_put_page(psrc, 1);
+ return PTR_ERR(pdst);
+ }
+ f2fs_copy_page(psrc, pdst);
+ set_page_dirty(pdst);
+ f2fs_put_page(pdst, 1);
+ f2fs_put_page(psrc, 1);
+
+ ret = truncate_hole(src_inode, src + i, src + i + 1);
+ if (ret)
+ return ret;
+ i++;
+ }
+ }
+ return 0;
+}
+
+static int __exchange_data_block(struct inode *src_inode,
+ struct inode *dst_inode, pgoff_t src, pgoff_t dst,
+ pgoff_t len, bool full)
+{
+ block_t *src_blkaddr;
+ int *do_replace;
+ pgoff_t olen;
+ int ret;
+
+ while (len) {
+ olen = min((pgoff_t)4 * ADDRS_PER_BLOCK, len);
+
+ src_blkaddr = f2fs_kvzalloc(sizeof(block_t) * olen, GFP_KERNEL);
+ if (!src_blkaddr)
+ return -ENOMEM;
+
+ do_replace = f2fs_kvzalloc(sizeof(int) * olen, GFP_KERNEL);
+ if (!do_replace) {
+ kvfree(src_blkaddr);
+ return -ENOMEM;
+ }
+
+ ret = __read_out_blkaddrs(src_inode, src_blkaddr,
+ do_replace, src, olen);
+ if (ret)
+ goto roll_back;
+
+ ret = __clone_blkaddrs(src_inode, dst_inode, src_blkaddr,
+ do_replace, src, dst, olen, full);
+ if (ret)
+ goto roll_back;
+
+ src += olen;
+ dst += olen;
+ len -= olen;
+
+ kvfree(src_blkaddr);
+ kvfree(do_replace);
+ }
+ return 0;
+
+roll_back:
+ __roll_back_blkaddrs(src_inode, src_blkaddr, do_replace, src, len);
+ kvfree(src_blkaddr);
+ kvfree(do_replace);
+ return ret;
+}
+
+static int f2fs_do_collapse(struct inode *inode, pgoff_t start, pgoff_t end)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ pgoff_t nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE;
+ int ret;
+
+ f2fs_balance_fs(sbi, true);
+ f2fs_lock_op(sbi);
+
+ f2fs_drop_extent_tree(inode);
+
+ ret = __exchange_data_block(inode, inode, end, start, nrpages - end, true);
+ f2fs_unlock_op(sbi);
+ return ret;
+}
+
+static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
+{
+ pgoff_t pg_start, pg_end;
+ loff_t new_size;
+ int ret;
+
+ if (offset + len >= i_size_read(inode))
+ return -EINVAL;
+
+ /* collapse range should be aligned to block size of f2fs. */
+ if (offset & (F2FS_BLKSIZE - 1) || len & (F2FS_BLKSIZE - 1))
+ return -EINVAL;
+
+ ret = f2fs_convert_inline_inode(inode);
+ if (ret)
+ return ret;
+
+ pg_start = offset >> PAGE_SHIFT;
+ pg_end = (offset + len) >> PAGE_SHIFT;
+
+ /* write out all dirty pages from offset */
+ ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
+ if (ret)
+ return ret;
+
+ truncate_pagecache(inode, offset);
+
+ ret = f2fs_do_collapse(inode, pg_start, pg_end);
+ if (ret)
+ return ret;
+
+ /* write out all moved pages, if possible */
+ filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
+ truncate_pagecache(inode, offset);
+
+ new_size = i_size_read(inode) - len;
+ truncate_pagecache(inode, new_size);
+
+ ret = truncate_blocks(inode, new_size, true);
+ if (!ret)
+ f2fs_i_size_write(inode, new_size);
+
+ return ret;
+}
+
+static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start,
+ pgoff_t end)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
+ pgoff_t index = start;
+ unsigned int ofs_in_node = dn->ofs_in_node;
+ blkcnt_t count = 0;
+ int ret;
+
+ for (; index < end; index++, dn->ofs_in_node++) {
+ if (datablock_addr(dn->node_page, dn->ofs_in_node) == NULL_ADDR)
+ count++;
+ }
+
+ dn->ofs_in_node = ofs_in_node;
+ ret = reserve_new_blocks(dn, count);
+ if (ret)
+ return ret;
+
+ dn->ofs_in_node = ofs_in_node;
+ for (index = start; index < end; index++, dn->ofs_in_node++) {
+ dn->data_blkaddr =
+ datablock_addr(dn->node_page, dn->ofs_in_node);
+ /*
+ * reserve_new_blocks will not guarantee entire block
+ * allocation.
+ */
+ if (dn->data_blkaddr == NULL_ADDR) {
+ ret = -ENOSPC;
+ break;
+ }
+ if (dn->data_blkaddr != NEW_ADDR) {
+ invalidate_blocks(sbi, dn->data_blkaddr);
+ dn->data_blkaddr = NEW_ADDR;
+ set_data_blkaddr(dn);
+ }
+ }
+
+ f2fs_update_extent_cache_range(dn, start, 0, index - start);
+
+ return ret;
+}
+
+static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
+ int mode)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct address_space *mapping = inode->i_mapping;
pgoff_t index, pg_start, pg_end;
loff_t new_size = i_size_read(inode);
loff_t off_start, off_end;
int ret = 0;
- f2fs_balance_fs(sbi);
-
ret = inode_newsize_ok(inode, (len + offset));
if (ret)
return ret;
- ret = f2fs_convert_inline_data(inode, offset + len, NULL);
+ ret = f2fs_convert_inline_inode(inode);
if (ret)
return ret;
- pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT;
- pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT;
+ ret = filemap_write_and_wait_range(mapping, offset, offset + len - 1);
+ if (ret)
+ return ret;
- off_start = offset & (PAGE_CACHE_SIZE - 1);
- off_end = (offset + len) & (PAGE_CACHE_SIZE - 1);
+ truncate_pagecache_range(inode, offset, offset + len - 1);
- f2fs_lock_op(sbi);
+ pg_start = ((unsigned long long) offset) >> PAGE_SHIFT;
+ pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT;
- for (index = pg_start; index <= pg_end; index++) {
- struct dnode_of_data dn;
+ off_start = offset & (PAGE_SIZE - 1);
+ off_end = (offset + len) & (PAGE_SIZE - 1);
- if (index == pg_end && !off_end)
- goto noalloc;
-
- set_new_dnode(&dn, inode, NULL, NULL, 0);
- ret = f2fs_reserve_block(&dn, index);
+ if (pg_start == pg_end) {
+ ret = fill_zero(inode, pg_start, off_start,
+ off_end - off_start);
if (ret)
- break;
-noalloc:
- if (pg_start == pg_end)
- new_size = offset + len;
- else if (index == pg_start && off_start)
- new_size = (index + 1) << PAGE_CACHE_SHIFT;
- else if (index == pg_end)
- new_size = (index << PAGE_CACHE_SHIFT) + off_end;
- else
- new_size += PAGE_CACHE_SIZE;
+ return ret;
+
+ new_size = max_t(loff_t, new_size, offset + len);
+ } else {
+ if (off_start) {
+ ret = fill_zero(inode, pg_start++, off_start,
+ PAGE_SIZE - off_start);
+ if (ret)
+ return ret;
+
+ new_size = max_t(loff_t, new_size,
+ (loff_t)pg_start << PAGE_SHIFT);
+ }
+
+ for (index = pg_start; index < pg_end;) {
+ struct dnode_of_data dn;
+ unsigned int end_offset;
+ pgoff_t end;
+
+ f2fs_lock_op(sbi);
+
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ ret = get_dnode_of_data(&dn, index, ALLOC_NODE);
+ if (ret) {
+ f2fs_unlock_op(sbi);
+ goto out;
+ }
+
+ end_offset = ADDRS_PER_PAGE(dn.node_page, inode);
+ end = min(pg_end, end_offset - dn.ofs_in_node + index);
+
+ ret = f2fs_do_zero_range(&dn, index, end);
+ f2fs_put_dnode(&dn);
+ f2fs_unlock_op(sbi);
+
+ f2fs_balance_fs(sbi, dn.node_changed);
+
+ if (ret)
+ goto out;
+
+ index = end;
+ new_size = max_t(loff_t, new_size,
+ (loff_t)index << PAGE_SHIFT);
+ }
+
+ if (off_end) {
+ ret = fill_zero(inode, pg_end, 0, off_end);
+ if (ret)
+ goto out;
+
+ new_size = max_t(loff_t, new_size, offset + len);
+ }
}
- if (!(mode & FALLOC_FL_KEEP_SIZE) &&
- i_size_read(inode) < new_size) {
- i_size_write(inode, new_size);
- mark_inode_dirty(inode);
- update_inode_page(inode);
- }
- f2fs_unlock_op(sbi);
+out:
+ if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size)
+ f2fs_i_size_write(inode, new_size);
return ret;
}
+static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ pgoff_t nr, pg_start, pg_end, delta, idx;
+ loff_t new_size;
+ int ret = 0;
+
+ new_size = i_size_read(inode) + len;
+ ret = inode_newsize_ok(inode, new_size);
+ if (ret)
+ return ret;
+
+ if (offset >= i_size_read(inode))
+ return -EINVAL;
+
+ /* insert range should be aligned to block size of f2fs. */
+ if (offset & (F2FS_BLKSIZE - 1) || len & (F2FS_BLKSIZE - 1))
+ return -EINVAL;
+
+ ret = f2fs_convert_inline_inode(inode);
+ if (ret)
+ return ret;
+
+ f2fs_balance_fs(sbi, true);
+
+ ret = truncate_blocks(inode, i_size_read(inode), true);
+ if (ret)
+ return ret;
+
+ /* write out all dirty pages from offset */
+ ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
+ if (ret)
+ return ret;
+
+ truncate_pagecache(inode, offset);
+
+ pg_start = offset >> PAGE_SHIFT;
+ pg_end = (offset + len) >> PAGE_SHIFT;
+ delta = pg_end - pg_start;
+ idx = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE;
+
+ while (!ret && idx > pg_start) {
+ nr = idx - pg_start;
+ if (nr > delta)
+ nr = delta;
+ idx -= nr;
+
+ f2fs_lock_op(sbi);
+ f2fs_drop_extent_tree(inode);
+
+ ret = __exchange_data_block(inode, inode, idx,
+ idx + delta, nr, false);
+ f2fs_unlock_op(sbi);
+ }
+
+ /* write out all moved pages, if possible */
+ filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
+ truncate_pagecache(inode, offset);
+
+ if (!ret)
+ f2fs_i_size_write(inode, new_size);
+ return ret;
+}
+
+static int expand_inode_data(struct inode *inode, loff_t offset,
+ loff_t len, int mode)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_map_blocks map = { .m_next_pgofs = NULL };
+ pgoff_t pg_end;
+ loff_t new_size = i_size_read(inode);
+ loff_t off_end;
+ int err;
+
+ err = inode_newsize_ok(inode, (len + offset));
+ if (err)
+ return err;
+
+ err = f2fs_convert_inline_inode(inode);
+ if (err)
+ return err;
+
+ f2fs_balance_fs(sbi, true);
+
+ pg_end = ((unsigned long long)offset + len) >> PAGE_SHIFT;
+ off_end = (offset + len) & (PAGE_SIZE - 1);
+
+ map.m_lblk = ((unsigned long long)offset) >> PAGE_SHIFT;
+ map.m_len = pg_end - map.m_lblk;
+ if (off_end)
+ map.m_len++;
+
+ err = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
+ if (err) {
+ pgoff_t last_off;
+
+ if (!map.m_len)
+ return err;
+
+ last_off = map.m_lblk + map.m_len - 1;
+
+ /* update new size to the failed position */
+ new_size = (last_off == pg_end) ? offset + len:
+ (loff_t)(last_off + 1) << PAGE_SHIFT;
+ } else {
+ new_size = ((loff_t)pg_end << PAGE_SHIFT) + off_end;
+ }
+
+ if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size)
+ f2fs_i_size_write(inode, new_size);
+
+ return err;
+}
+
+#ifndef FALLOC_FL_COLLAPSE_RANGE
+#define FALLOC_FL_COLLAPSE_RANGE 0X08
+#endif
+#ifndef FALLOC_FL_ZERO_RANGE
+#define FALLOC_FL_ZERO_RANGE 0X10
+#endif
+#ifndef FALLOC_FL_INSERT_RANGE
+#define FALLOC_FL_INSERT_RANGE 0X20
+#endif
+
static long f2fs_fallocate(struct file *file, int mode,
loff_t offset, loff_t len)
{
struct inode *inode = file_inode(file);
- long ret;
+ long ret = 0;
- if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+ /* f2fs only support ->fallocate for regular file */
+ if (!S_ISREG(inode->i_mode))
+ return -EINVAL;
+
+ if (f2fs_encrypted_inode(inode) &&
+ (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE)))
return -EOPNOTSUPP;
- mutex_lock(&inode->i_mutex);
+ if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
+ FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE |
+ FALLOC_FL_INSERT_RANGE))
+ return -EOPNOTSUPP;
- if (mode & FALLOC_FL_PUNCH_HOLE)
+ inode_lock(inode);
+
+ if (mode & FALLOC_FL_PUNCH_HOLE) {
+ if (offset >= inode->i_size)
+ goto out;
+
ret = punch_hole(inode, offset, len);
- else
+ } else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
+ ret = f2fs_collapse_range(inode, offset, len);
+ } else if (mode & FALLOC_FL_ZERO_RANGE) {
+ ret = f2fs_zero_range(inode, offset, len, mode);
+ } else if (mode & FALLOC_FL_INSERT_RANGE) {
+ ret = f2fs_insert_range(inode, offset, len);
+ } else {
ret = expand_inode_data(inode, offset, len, mode);
-
- if (!ret) {
- inode->i_mtime = inode->i_ctime = CURRENT_TIME;
- mark_inode_dirty(inode);
}
- mutex_unlock(&inode->i_mutex);
+ if (!ret) {
+ inode->i_mtime = inode->i_ctime = current_time(inode);
+ f2fs_mark_inode_dirty_sync(inode, false);
+ if (mode & FALLOC_FL_KEEP_SIZE)
+ file_set_keep_isize(inode);
+ f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
+ }
+
+out:
+ inode_unlock(inode);
trace_f2fs_fallocate(inode, mode, offset, len, ret);
return ret;
}
+static int f2fs_release_file(struct inode *inode, struct file *filp)
+{
+ /*
+ * f2fs_relase_file is called at every close calls. So we should
+ * not drop any inmemory pages by close called by other process.
+ */
+ if (!(filp->f_mode & FMODE_WRITE) ||
+ atomic_read(&inode->i_writecount) != 1)
+ return 0;
+
+ /* some remained atomic pages should discarded */
+ if (f2fs_is_atomic_file(inode))
+ drop_inmem_pages(inode);
+ if (f2fs_is_volatile_file(inode)) {
+ clear_inode_flag(inode, FI_VOLATILE_FILE);
+ stat_dec_volatile_write(inode);
+ set_inode_flag(inode, FI_DROP_CACHE);
+ filemap_fdatawrite(inode->i_mapping);
+ clear_inode_flag(inode, FI_DROP_CACHE);
+ }
+ return 0;
+}
+
#define F2FS_REG_FLMASK (~(FS_DIRSYNC_FL | FS_TOPDIR_FL))
#define F2FS_OTHER_FLMASK (FS_NODUMP_FL | FS_NOATIME_FL)
@@ -817,33 +1474,29 @@
{
struct inode *inode = file_inode(filp);
struct f2fs_inode_info *fi = F2FS_I(inode);
- unsigned int flags = fi->i_flags & FS_FL_USER_VISIBLE;
+ unsigned int flags;
unsigned int oldflags;
int ret;
+ if (!inode_owner_or_capable(inode))
+ return -EACCES;
+
+ if (get_user(flags, (int __user *)arg))
+ return -EFAULT;
+
ret = mnt_want_write_file(filp);
if (ret)
return ret;
- if (!inode_owner_or_capable(inode)) {
- ret = -EACCES;
- goto out;
- }
-
- if (get_user(flags, (int __user *)arg)) {
- ret = -EFAULT;
- goto out;
- }
+ inode_lock(inode);
flags = f2fs_mask_flags(inode->i_mode, flags);
- mutex_lock(&inode->i_mutex);
-
oldflags = fi->i_flags;
if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) {
if (!capable(CAP_LINUX_IMMUTABLE)) {
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
ret = -EPERM;
goto out;
}
@@ -852,29 +1505,70 @@
flags = flags & FS_FL_USER_MODIFIABLE;
flags |= oldflags & ~FS_FL_USER_MODIFIABLE;
fi->i_flags = flags;
- mutex_unlock(&inode->i_mutex);
+ inode->i_ctime = current_time(inode);
f2fs_set_inode_flags(inode);
- inode->i_ctime = CURRENT_TIME;
- mark_inode_dirty(inode);
+
+ inode_unlock(inode);
out:
mnt_drop_write_file(filp);
return ret;
}
+static int f2fs_ioc_getversion(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+
+ return put_user(inode->i_generation, (int __user *)arg);
+}
+
static int f2fs_ioc_start_atomic_write(struct file *filp)
{
struct inode *inode = file_inode(filp);
- struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ int ret;
if (!inode_owner_or_capable(inode))
return -EACCES;
- f2fs_balance_fs(sbi);
+ if (!S_ISREG(inode->i_mode))
+ return -EINVAL;
- set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
- return f2fs_convert_inline_data(inode, MAX_INLINE_DATA + 1, NULL);
+ inode_lock(inode);
+
+ if (f2fs_is_atomic_file(inode))
+ goto out;
+
+ ret = f2fs_convert_inline_inode(inode);
+ if (ret)
+ goto out;
+
+ set_inode_flag(inode, FI_ATOMIC_FILE);
+ set_inode_flag(inode, FI_HOT_DATA);
+ f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
+
+ if (!get_dirty_pages(inode))
+ goto inc_stat;
+
+ f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING,
+ "Unexpected flush for atomic writes: ino=%lu, npages=%u",
+ inode->i_ino, get_dirty_pages(inode));
+ ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX);
+ if (ret) {
+ clear_inode_flag(inode, FI_ATOMIC_FILE);
+ goto out;
+ }
+
+inc_stat:
+ stat_inc_atomic_write(inode);
+ stat_update_max_atomic_write(inode);
+out:
+ inode_unlock(inode);
+ mnt_drop_write_file(filp);
+ return ret;
}
static int f2fs_ioc_commit_atomic_write(struct file *filp)
@@ -885,17 +1579,30 @@
if (!inode_owner_or_capable(inode))
return -EACCES;
- if (f2fs_is_volatile_file(inode))
- return 0;
-
ret = mnt_want_write_file(filp);
if (ret)
return ret;
- if (f2fs_is_atomic_file(inode))
- commit_inmem_pages(inode, false);
+ inode_lock(inode);
- ret = f2fs_sync_file(filp, 0, LONG_MAX, 0);
+ if (f2fs_is_volatile_file(inode))
+ goto err_out;
+
+ if (f2fs_is_atomic_file(inode)) {
+ ret = commit_inmem_pages(inode);
+ if (ret)
+ goto err_out;
+
+ ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
+ if (!ret) {
+ clear_inode_flag(inode, FI_ATOMIC_FILE);
+ stat_dec_atomic_write(inode);
+ }
+ } else {
+ ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
+ }
+err_out:
+ inode_unlock(inode);
mnt_drop_write_file(filp);
return ret;
}
@@ -903,12 +1610,142 @@
static int f2fs_ioc_start_volatile_write(struct file *filp)
{
struct inode *inode = file_inode(filp);
+ int ret;
if (!inode_owner_or_capable(inode))
return -EACCES;
- set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
- return 0;
+ if (!S_ISREG(inode->i_mode))
+ return -EINVAL;
+
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ inode_lock(inode);
+
+ if (f2fs_is_volatile_file(inode))
+ goto out;
+
+ ret = f2fs_convert_inline_inode(inode);
+ if (ret)
+ goto out;
+
+ stat_inc_volatile_write(inode);
+ stat_update_max_volatile_write(inode);
+
+ set_inode_flag(inode, FI_VOLATILE_FILE);
+ f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
+out:
+ inode_unlock(inode);
+ mnt_drop_write_file(filp);
+ return ret;
+}
+
+static int f2fs_ioc_release_volatile_write(struct file *filp)
+{
+ struct inode *inode = file_inode(filp);
+ int ret;
+
+ if (!inode_owner_or_capable(inode))
+ return -EACCES;
+
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ inode_lock(inode);
+
+ if (!f2fs_is_volatile_file(inode))
+ goto out;
+
+ if (!f2fs_is_first_block_written(inode)) {
+ ret = truncate_partial_data_page(inode, 0, true);
+ goto out;
+ }
+
+ ret = punch_hole(inode, 0, F2FS_BLKSIZE);
+out:
+ inode_unlock(inode);
+ mnt_drop_write_file(filp);
+ return ret;
+}
+
+static int f2fs_ioc_abort_volatile_write(struct file *filp)
+{
+ struct inode *inode = file_inode(filp);
+ int ret;
+
+ if (!inode_owner_or_capable(inode))
+ return -EACCES;
+
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ inode_lock(inode);
+
+ if (f2fs_is_atomic_file(inode))
+ drop_inmem_pages(inode);
+ if (f2fs_is_volatile_file(inode)) {
+ clear_inode_flag(inode, FI_VOLATILE_FILE);
+ stat_dec_volatile_write(inode);
+ ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
+ }
+
+ inode_unlock(inode);
+
+ mnt_drop_write_file(filp);
+ f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
+ return ret;
+}
+
+static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct super_block *sb = sbi->sb;
+ __u32 in;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (get_user(in, (__u32 __user *)arg))
+ return -EFAULT;
+
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ switch (in) {
+ case F2FS_GOING_DOWN_FULLSYNC:
+ sb = freeze_bdev(sb->s_bdev);
+ if (sb && !IS_ERR(sb)) {
+ f2fs_stop_checkpoint(sbi, false);
+ thaw_bdev(sb->s_bdev, sb);
+ }
+ break;
+ case F2FS_GOING_DOWN_METASYNC:
+ /* do checkpoint only */
+ f2fs_sync_fs(sb, 1);
+ f2fs_stop_checkpoint(sbi, false);
+ break;
+ case F2FS_GOING_DOWN_NOSYNC:
+ f2fs_stop_checkpoint(sbi, false);
+ break;
+ case F2FS_GOING_DOWN_METAFLUSH:
+ sync_meta_pages(sbi, META, LONG_MAX);
+ f2fs_stop_checkpoint(sbi, false);
+ break;
+ default:
+ ret = -EINVAL;
+ goto out;
+ }
+ f2fs_update_time(sbi, REQ_TIME);
+out:
+ mnt_drop_write_file(filp);
+ return ret;
}
static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
@@ -929,18 +1766,530 @@
sizeof(range)))
return -EFAULT;
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
range.minlen = max((unsigned int)range.minlen,
q->limits.discard_granularity);
ret = f2fs_trim_fs(F2FS_SB(sb), &range);
+ mnt_drop_write_file(filp);
if (ret < 0)
return ret;
if (copy_to_user((struct fstrim_range __user *)arg, &range,
sizeof(range)))
return -EFAULT;
+ f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return 0;
}
+static bool uuid_is_nonzero(__u8 u[16])
+{
+ int i;
+
+ for (i = 0; i < 16; i++)
+ if (u[i])
+ return true;
+ return false;
+}
+
+static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+
+ f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
+
+ return fscrypt_ioctl_set_policy(filp, (const void __user *)arg);
+}
+
+static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg)
+{
+ return fscrypt_ioctl_get_policy(filp, (void __user *)arg);
+}
+
+static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ int err;
+
+ if (!f2fs_sb_has_crypto(inode->i_sb))
+ return -EOPNOTSUPP;
+
+ if (uuid_is_nonzero(sbi->raw_super->encrypt_pw_salt))
+ goto got_it;
+
+ err = mnt_want_write_file(filp);
+ if (err)
+ return err;
+
+ /* update superblock with uuid */
+ generate_random_uuid(sbi->raw_super->encrypt_pw_salt);
+
+ err = f2fs_commit_super(sbi, false);
+ if (err) {
+ /* undo new data */
+ memset(sbi->raw_super->encrypt_pw_salt, 0, 16);
+ mnt_drop_write_file(filp);
+ return err;
+ }
+ mnt_drop_write_file(filp);
+got_it:
+ if (copy_to_user((__u8 __user *)arg, sbi->raw_super->encrypt_pw_salt,
+ 16))
+ return -EFAULT;
+ return 0;
+}
+
+static int f2fs_ioc_gc(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ __u32 sync;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (get_user(sync, (__u32 __user *)arg))
+ return -EFAULT;
+
+ if (f2fs_readonly(sbi->sb))
+ return -EROFS;
+
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ if (!sync) {
+ if (!mutex_trylock(&sbi->gc_mutex)) {
+ ret = -EBUSY;
+ goto out;
+ }
+ } else {
+ mutex_lock(&sbi->gc_mutex);
+ }
+
+ ret = f2fs_gc(sbi, sync, true, NULL_SEGNO);
+out:
+ mnt_drop_write_file(filp);
+ return ret;
+}
+
+static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (f2fs_readonly(sbi->sb))
+ return -EROFS;
+
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ ret = f2fs_sync_fs(sbi->sb, 1);
+
+ mnt_drop_write_file(filp);
+ return ret;
+}
+
+static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
+ struct file *filp,
+ struct f2fs_defragment *range)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_map_blocks map = { .m_next_pgofs = NULL };
+ struct extent_info ei = {0,0,0};
+ pgoff_t pg_start, pg_end;
+ unsigned int blk_per_seg = sbi->blocks_per_seg;
+ unsigned int total = 0, sec_num;
+ block_t blk_end = 0;
+ bool fragmented = false;
+ int err;
+
+ /* if in-place-update policy is enabled, don't waste time here */
+ if (need_inplace_update_policy(inode, NULL))
+ return -EINVAL;
+
+ pg_start = range->start >> PAGE_SHIFT;
+ pg_end = (range->start + range->len) >> PAGE_SHIFT;
+
+ f2fs_balance_fs(sbi, true);
+
+ inode_lock(inode);
+
+ /* writeback all dirty pages in the range */
+ err = filemap_write_and_wait_range(inode->i_mapping, range->start,
+ range->start + range->len - 1);
+ if (err)
+ goto out;
+
+ /*
+ * lookup mapping info in extent cache, skip defragmenting if physical
+ * block addresses are continuous.
+ */
+ if (f2fs_lookup_extent_cache(inode, pg_start, &ei)) {
+ if (ei.fofs + ei.len >= pg_end)
+ goto out;
+ }
+
+ map.m_lblk = pg_start;
+
+ /*
+ * lookup mapping info in dnode page cache, skip defragmenting if all
+ * physical block addresses are continuous even if there are hole(s)
+ * in logical blocks.
+ */
+ while (map.m_lblk < pg_end) {
+ map.m_len = pg_end - map.m_lblk;
+ err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_READ);
+ if (err)
+ goto out;
+
+ if (!(map.m_flags & F2FS_MAP_FLAGS)) {
+ map.m_lblk++;
+ continue;
+ }
+
+ if (blk_end && blk_end != map.m_pblk) {
+ fragmented = true;
+ break;
+ }
+ blk_end = map.m_pblk + map.m_len;
+
+ map.m_lblk += map.m_len;
+ }
+
+ if (!fragmented)
+ goto out;
+
+ map.m_lblk = pg_start;
+ map.m_len = pg_end - pg_start;
+
+ sec_num = (map.m_len + BLKS_PER_SEC(sbi) - 1) / BLKS_PER_SEC(sbi);
+
+ /*
+ * make sure there are enough free section for LFS allocation, this can
+ * avoid defragment running in SSR mode when free section are allocated
+ * intensively
+ */
+ if (has_not_enough_free_secs(sbi, 0, sec_num)) {
+ err = -EAGAIN;
+ goto out;
+ }
+
+ while (map.m_lblk < pg_end) {
+ pgoff_t idx;
+ int cnt = 0;
+
+do_map:
+ map.m_len = pg_end - map.m_lblk;
+ err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_READ);
+ if (err)
+ goto clear_out;
+
+ if (!(map.m_flags & F2FS_MAP_FLAGS)) {
+ map.m_lblk++;
+ continue;
+ }
+
+ set_inode_flag(inode, FI_DO_DEFRAG);
+
+ idx = map.m_lblk;
+ while (idx < map.m_lblk + map.m_len && cnt < blk_per_seg) {
+ struct page *page;
+
+ page = get_lock_data_page(inode, idx, true);
+ if (IS_ERR(page)) {
+ err = PTR_ERR(page);
+ goto clear_out;
+ }
+
+ set_page_dirty(page);
+ f2fs_put_page(page, 1);
+
+ idx++;
+ cnt++;
+ total++;
+ }
+
+ map.m_lblk = idx;
+
+ if (idx < pg_end && cnt < blk_per_seg)
+ goto do_map;
+
+ clear_inode_flag(inode, FI_DO_DEFRAG);
+
+ err = filemap_fdatawrite(inode->i_mapping);
+ if (err)
+ goto out;
+ }
+clear_out:
+ clear_inode_flag(inode, FI_DO_DEFRAG);
+out:
+ inode_unlock(inode);
+ if (!err)
+ range->len = (u64)total << PAGE_SHIFT;
+ return err;
+}
+
+static int f2fs_ioc_defragment(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_defragment range;
+ int err;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (!S_ISREG(inode->i_mode) || f2fs_is_atomic_file(inode))
+ return -EINVAL;
+
+ if (f2fs_readonly(sbi->sb))
+ return -EROFS;
+
+ if (copy_from_user(&range, (struct f2fs_defragment __user *)arg,
+ sizeof(range)))
+ return -EFAULT;
+
+ /* verify alignment of offset & size */
+ if (range.start & (F2FS_BLKSIZE - 1) || range.len & (F2FS_BLKSIZE - 1))
+ return -EINVAL;
+
+ if (unlikely((range.start + range.len) >> PAGE_SHIFT >
+ sbi->max_file_blocks))
+ return -EINVAL;
+
+ err = mnt_want_write_file(filp);
+ if (err)
+ return err;
+
+ err = f2fs_defragment_range(sbi, filp, &range);
+ mnt_drop_write_file(filp);
+
+ f2fs_update_time(sbi, REQ_TIME);
+ if (err < 0)
+ return err;
+
+ if (copy_to_user((struct f2fs_defragment __user *)arg, &range,
+ sizeof(range)))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out, size_t len)
+{
+ struct inode *src = file_inode(file_in);
+ struct inode *dst = file_inode(file_out);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(src);
+ size_t olen = len, dst_max_i_size = 0;
+ size_t dst_osize;
+ int ret;
+
+ if (file_in->f_path.mnt != file_out->f_path.mnt ||
+ src->i_sb != dst->i_sb)
+ return -EXDEV;
+
+ if (unlikely(f2fs_readonly(src->i_sb)))
+ return -EROFS;
+
+ if (!S_ISREG(src->i_mode) || !S_ISREG(dst->i_mode))
+ return -EINVAL;
+
+ if (f2fs_encrypted_inode(src) || f2fs_encrypted_inode(dst))
+ return -EOPNOTSUPP;
+
+ if (src == dst) {
+ if (pos_in == pos_out)
+ return 0;
+ if (pos_out > pos_in && pos_out < pos_in + len)
+ return -EINVAL;
+ }
+
+ inode_lock(src);
+ if (src != dst) {
+ if (!inode_trylock(dst)) {
+ ret = -EBUSY;
+ goto out;
+ }
+ }
+
+ ret = -EINVAL;
+ if (pos_in + len > src->i_size || pos_in + len < pos_in)
+ goto out_unlock;
+ if (len == 0)
+ olen = len = src->i_size - pos_in;
+ if (pos_in + len == src->i_size)
+ len = ALIGN(src->i_size, F2FS_BLKSIZE) - pos_in;
+ if (len == 0) {
+ ret = 0;
+ goto out_unlock;
+ }
+
+ dst_osize = dst->i_size;
+ if (pos_out + olen > dst->i_size)
+ dst_max_i_size = pos_out + olen;
+
+ /* verify the end result is block aligned */
+ if (!IS_ALIGNED(pos_in, F2FS_BLKSIZE) ||
+ !IS_ALIGNED(pos_in + len, F2FS_BLKSIZE) ||
+ !IS_ALIGNED(pos_out, F2FS_BLKSIZE))
+ goto out_unlock;
+
+ ret = f2fs_convert_inline_inode(src);
+ if (ret)
+ goto out_unlock;
+
+ ret = f2fs_convert_inline_inode(dst);
+ if (ret)
+ goto out_unlock;
+
+ /* write out all dirty pages from offset */
+ ret = filemap_write_and_wait_range(src->i_mapping,
+ pos_in, pos_in + len);
+ if (ret)
+ goto out_unlock;
+
+ ret = filemap_write_and_wait_range(dst->i_mapping,
+ pos_out, pos_out + len);
+ if (ret)
+ goto out_unlock;
+
+ f2fs_balance_fs(sbi, true);
+ f2fs_lock_op(sbi);
+ ret = __exchange_data_block(src, dst, pos_in >> F2FS_BLKSIZE_BITS,
+ pos_out >> F2FS_BLKSIZE_BITS,
+ len >> F2FS_BLKSIZE_BITS, false);
+
+ if (!ret) {
+ if (dst_max_i_size)
+ f2fs_i_size_write(dst, dst_max_i_size);
+ else if (dst_osize != dst->i_size)
+ f2fs_i_size_write(dst, dst_osize);
+ }
+ f2fs_unlock_op(sbi);
+out_unlock:
+ if (src != dst)
+ inode_unlock(dst);
+out:
+ inode_unlock(src);
+ return ret;
+}
+
+static int f2fs_ioc_move_range(struct file *filp, unsigned long arg)
+{
+ struct f2fs_move_range range;
+ struct fd dst;
+ int err;
+
+ if (!(filp->f_mode & FMODE_READ) ||
+ !(filp->f_mode & FMODE_WRITE))
+ return -EBADF;
+
+ if (copy_from_user(&range, (struct f2fs_move_range __user *)arg,
+ sizeof(range)))
+ return -EFAULT;
+
+ dst = fdget(range.dst_fd);
+ if (!dst.file)
+ return -EBADF;
+
+ if (!(dst.file->f_mode & FMODE_WRITE)) {
+ err = -EBADF;
+ goto err_out;
+ }
+
+ err = mnt_want_write_file(filp);
+ if (err)
+ goto err_out;
+
+ err = f2fs_move_file_range(filp, range.pos_in, dst.file,
+ range.pos_out, range.len);
+
+ mnt_drop_write_file(filp);
+ if (err)
+ goto err_out;
+
+ if (copy_to_user((struct f2fs_move_range __user *)arg,
+ &range, sizeof(range)))
+ err = -EFAULT;
+err_out:
+ fdput(dst);
+ return err;
+}
+
+static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg)
+{
+ struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct sit_info *sm = SIT_I(sbi);
+ unsigned int start_segno = 0, end_segno = 0;
+ unsigned int dev_start_segno = 0, dev_end_segno = 0;
+ struct f2fs_flush_device range;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (f2fs_readonly(sbi->sb))
+ return -EROFS;
+
+ if (copy_from_user(&range, (struct f2fs_flush_device __user *)arg,
+ sizeof(range)))
+ return -EFAULT;
+
+ if (sbi->s_ndevs <= 1 || sbi->s_ndevs - 1 <= range.dev_num ||
+ sbi->segs_per_sec != 1) {
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "Can't flush %u in %d for segs_per_sec %u != 1\n",
+ range.dev_num, sbi->s_ndevs,
+ sbi->segs_per_sec);
+ return -EINVAL;
+ }
+
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ if (range.dev_num != 0)
+ dev_start_segno = GET_SEGNO(sbi, FDEV(range.dev_num).start_blk);
+ dev_end_segno = GET_SEGNO(sbi, FDEV(range.dev_num).end_blk);
+
+ start_segno = sm->last_victim[FLUSH_DEVICE];
+ if (start_segno < dev_start_segno || start_segno >= dev_end_segno)
+ start_segno = dev_start_segno;
+ end_segno = min(start_segno + range.segments, dev_end_segno);
+
+ while (start_segno < end_segno) {
+ if (!mutex_trylock(&sbi->gc_mutex)) {
+ ret = -EBUSY;
+ goto out;
+ }
+ sm->last_victim[GC_CB] = end_segno + 1;
+ sm->last_victim[GC_GREEDY] = end_segno + 1;
+ sm->last_victim[ALLOC_NEXT] = end_segno + 1;
+ ret = f2fs_gc(sbi, true, true, start_segno);
+ if (ret == -EAGAIN)
+ ret = 0;
+ else if (ret < 0)
+ break;
+ start_segno++;
+ }
+out:
+ mnt_drop_write_file(filp);
+ return ret;
+}
+
+
long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
switch (cmd) {
@@ -948,19 +2297,82 @@
return f2fs_ioc_getflags(filp, arg);
case F2FS_IOC_SETFLAGS:
return f2fs_ioc_setflags(filp, arg);
+ case F2FS_IOC_GETVERSION:
+ return f2fs_ioc_getversion(filp, arg);
case F2FS_IOC_START_ATOMIC_WRITE:
return f2fs_ioc_start_atomic_write(filp);
case F2FS_IOC_COMMIT_ATOMIC_WRITE:
return f2fs_ioc_commit_atomic_write(filp);
case F2FS_IOC_START_VOLATILE_WRITE:
return f2fs_ioc_start_volatile_write(filp);
+ case F2FS_IOC_RELEASE_VOLATILE_WRITE:
+ return f2fs_ioc_release_volatile_write(filp);
+ case F2FS_IOC_ABORT_VOLATILE_WRITE:
+ return f2fs_ioc_abort_volatile_write(filp);
+ case F2FS_IOC_SHUTDOWN:
+ return f2fs_ioc_shutdown(filp, arg);
case FITRIM:
return f2fs_ioc_fitrim(filp, arg);
+ case F2FS_IOC_SET_ENCRYPTION_POLICY:
+ return f2fs_ioc_set_encryption_policy(filp, arg);
+ case F2FS_IOC_GET_ENCRYPTION_POLICY:
+ return f2fs_ioc_get_encryption_policy(filp, arg);
+ case F2FS_IOC_GET_ENCRYPTION_PWSALT:
+ return f2fs_ioc_get_encryption_pwsalt(filp, arg);
+ case F2FS_IOC_GARBAGE_COLLECT:
+ return f2fs_ioc_gc(filp, arg);
+ case F2FS_IOC_WRITE_CHECKPOINT:
+ return f2fs_ioc_write_checkpoint(filp, arg);
+ case F2FS_IOC_DEFRAGMENT:
+ return f2fs_ioc_defragment(filp, arg);
+ case F2FS_IOC_MOVE_RANGE:
+ return f2fs_ioc_move_range(filp, arg);
+ case F2FS_IOC_FLUSH_DEVICE:
+ return f2fs_ioc_flush_device(filp, arg);
default:
return -ENOTTY;
}
}
+static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file_inode(file);
+ size_t count = iov_iter_count(from);
+ loff_t pos = iocb->ki_pos;
+ struct blk_plug plug;
+ ssize_t ret;
+
+ if (f2fs_encrypted_inode(inode) &&
+ !fscrypt_has_encryption_key(inode) &&
+ fscrypt_get_encryption_info(inode))
+ return -EACCES;
+
+ inode_lock(inode);
+ ret = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
+ if (!ret) {
+ int err = f2fs_preallocate_blocks(inode, pos, count,
+ file->f_flags & O_DIRECT);
+ if (err) {
+ inode_unlock(inode);
+ return err;
+ }
+ blk_start_plug(&plug);
+ ret = __generic_file_write_iter(iocb, from);
+ blk_finish_plug(&plug);
+ }
+ inode_unlock(inode);
+
+ if (ret > 0) {
+ ssize_t err;
+
+ err = generic_write_sync(file, iocb->ki_pos - ret, ret);
+ if (err < 0)
+ ret = err;
+ }
+ return ret;
+}
+
#ifdef CONFIG_COMPAT
long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
@@ -971,6 +2383,24 @@
case F2FS_IOC32_SETFLAGS:
cmd = F2FS_IOC_SETFLAGS;
break;
+ case F2FS_IOC32_GETVERSION:
+ cmd = F2FS_IOC_GETVERSION;
+ break;
+ case F2FS_IOC_START_ATOMIC_WRITE:
+ case F2FS_IOC_COMMIT_ATOMIC_WRITE:
+ case F2FS_IOC_START_VOLATILE_WRITE:
+ case F2FS_IOC_RELEASE_VOLATILE_WRITE:
+ case F2FS_IOC_ABORT_VOLATILE_WRITE:
+ case F2FS_IOC_SHUTDOWN:
+ case F2FS_IOC_SET_ENCRYPTION_POLICY:
+ case F2FS_IOC_GET_ENCRYPTION_PWSALT:
+ case F2FS_IOC_GET_ENCRYPTION_POLICY:
+ case F2FS_IOC_GARBAGE_COLLECT:
+ case F2FS_IOC_WRITE_CHECKPOINT:
+ case F2FS_IOC_DEFRAGMENT:
+ case F2FS_IOC_MOVE_RANGE:
+ case F2FS_IOC_FLUSH_DEVICE:
+ break;
default:
return -ENOIOCTLCMD;
}
@@ -983,8 +2413,9 @@
.read = new_sync_read,
.write = new_sync_write,
.read_iter = generic_file_read_iter,
- .write_iter = generic_file_write_iter,
- .open = generic_file_open,
+ .write_iter = f2fs_file_write_iter,
+ .open = f2fs_file_open,
+ .release = f2fs_release_file,
.mmap = f2fs_file_mmap,
.fsync = f2fs_sync_file,
.fallocate = f2fs_fallocate,
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 2a8f4ac..0265221 100644
--- a/fs/f2fs/gc.c
+++ b/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;
@@ -46,10 +43,17 @@
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;
}
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(sbi, FAULT_CHECKPOINT)) {
+ f2fs_show_injection_info(FAULT_CHECKPOINT);
+ f2fs_stop_checkpoint(sbi, false);
+ }
+#endif
+
/*
* [GC triggering condition]
* 0. GC is not conducted currently.
@@ -67,22 +71,25 @@
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), true, NULL_SEGNO))
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 +103,7 @@
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(sbi, sizeof(struct f2fs_gc_kthread), GFP_KERNEL);
if (!gc_th) {
err = -ENOMEM;
goto out;
@@ -163,10 +168,15 @@
p->ofs_unit = sbi->segs_per_sec;
}
- if (p->max_search > sbi->max_victim_search)
+ /* we need to check every dirty segments in the FG_GC case */
+ if (gc_type != FG_GC && p->max_search > sbi->max_victim_search)
p->max_search = sbi->max_victim_search;
- p->offset = sbi->last_victim[p->gc_mode];
+ /* let's select beginning hot/small space first */
+ if (type == CURSEG_HOT_DATA || IS_NODESEG(type))
+ p->offset = 0;
+ else
+ p->offset = SIT_I(sbi)->last_victim[p->gc_mode];
}
static unsigned int get_max_cost(struct f2fs_sb_info *sbi,
@@ -174,9 +184,9 @@
{
/* 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 2 * sbi->blocks_per_seg * p->ofs_unit;
else if (p->gc_mode == GC_CB)
return UINT_MAX;
else /* No other gc_mode */
@@ -196,8 +206,12 @@
for_each_set_bit(secno, dirty_i->victim_secmap, MAIN_SECS(sbi)) {
if (sec_usage_check(sbi, secno))
continue;
+
+ if (no_fggc_candidate(sbi, secno))
+ continue;
+
clear_bit(secno, dirty_i->victim_secmap);
- return secno * sbi->segs_per_sec;
+ return GET_SEG_FROM_SEC(sbi, secno);
}
return NULL_SEGNO;
}
@@ -205,8 +219,8 @@
static unsigned int get_cb_cost(struct f2fs_sb_info *sbi, unsigned int segno)
{
struct sit_info *sit_i = SIT_I(sbi);
- unsigned int secno = GET_SECNO(sbi, segno);
- unsigned int start = secno * sbi->segs_per_sec;
+ unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+ unsigned int start = GET_SEG_FROM_SEC(sbi, secno);
unsigned long long mtime = 0;
unsigned int vblocks;
unsigned char age = 0;
@@ -215,7 +229,7 @@
for (i = 0; i < sbi->segs_per_sec; i++)
mtime += get_seg_entry(sbi, start + i)->mtime;
- vblocks = get_valid_blocks(sbi, segno, sbi->segs_per_sec);
+ vblocks = get_valid_blocks(sbi, segno, true);
mtime = div_u64(mtime, sbi->segs_per_sec);
vblocks = div_u64(vblocks, sbi->segs_per_sec);
@@ -234,6 +248,16 @@
return UINT_MAX - ((100 * (100 - u) * age) / (100 + u));
}
+static unsigned int get_greedy_cost(struct f2fs_sb_info *sbi,
+ unsigned int segno)
+{
+ unsigned int valid_blocks =
+ get_valid_blocks(sbi, segno, true);
+
+ return IS_DATASEG(get_seg_entry(sbi, segno)->type) ?
+ valid_blocks * 2 : valid_blocks;
+}
+
static inline unsigned int get_gc_cost(struct f2fs_sb_info *sbi,
unsigned int segno, struct victim_sel_policy *p)
{
@@ -242,11 +266,23 @@
/* alloc_mode == LFS */
if (p->gc_mode == GC_GREEDY)
- return get_valid_blocks(sbi, segno, sbi->segs_per_sec);
+ return get_greedy_cost(sbi, segno);
else
return get_cb_cost(sbi, segno);
}
+static unsigned int count_bits(const unsigned long *addr,
+ unsigned int offset, unsigned int len)
+{
+ unsigned int end = offset + len, sum = 0;
+
+ while (offset < end) {
+ if (test_bit(offset++, addr))
+ ++sum;
+ }
+ return sum;
+}
+
/*
* This function is called from two paths.
* One is garbage collection and the other is SSR segment selection.
@@ -259,9 +295,11 @@
unsigned int *result, int gc_type, int type, char alloc_mode)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+ struct sit_info *sm = SIT_I(sbi);
struct victim_sel_policy p;
- unsigned int secno, max_cost;
- int nsearched = 0;
+ unsigned int secno, last_victim;
+ unsigned int last_segment = MAIN_SEGS(sbi);
+ unsigned int nsearched = 0;
mutex_lock(&dirty_i->seglist_lock);
@@ -269,8 +307,20 @@
select_policy(sbi, gc_type, type, &p);
p.min_segno = NULL_SEGNO;
- p.min_cost = max_cost = get_max_cost(sbi, &p);
+ p.min_cost = get_max_cost(sbi, &p);
+ if (*result != NULL_SEGNO) {
+ if (IS_DATASEG(get_seg_entry(sbi, *result)->type) &&
+ get_valid_blocks(sbi, *result, false) &&
+ !sec_usage_check(sbi, GET_SEC_FROM_SEG(sbi, *result)))
+ p.min_segno = *result;
+ goto out;
+ }
+
+ if (p.max_search == 0)
+ goto out;
+
+ last_victim = sm->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)
@@ -281,10 +331,12 @@
unsigned long cost;
unsigned int segno;
- segno = find_next_bit(p.dirty_segmap, MAIN_SEGS(sbi), p.offset);
- if (segno >= MAIN_SEGS(sbi)) {
- if (sbi->last_victim[p.gc_mode]) {
- sbi->last_victim[p.gc_mode] = 0;
+ segno = find_next_bit(p.dirty_segmap, last_segment, p.offset);
+ if (segno >= last_segment) {
+ if (sm->last_victim[p.gc_mode]) {
+ last_segment =
+ sm->last_victim[p.gc_mode];
+ sm->last_victim[p.gc_mode] = 0;
p.offset = 0;
continue;
}
@@ -292,34 +344,45 @@
}
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);
+ secno = GET_SEC_FROM_SEG(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;
+ if (gc_type == FG_GC && p.alloc_mode == LFS &&
+ no_fggc_candidate(sbi, secno))
+ 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 (!sm->last_victim[p.gc_mode] && segno <= last_victim)
+ sm->last_victim[p.gc_mode] = last_victim + 1;
+ else
+ sm->last_victim[p.gc_mode] = segno + 1;
+ sm->last_victim[p.gc_mode] %= MAIN_SEGS(sbi);
break;
}
}
if (p.min_segno != NULL_SEGNO) {
got_it:
if (p.alloc_mode == LFS) {
- secno = GET_SECNO(sbi, p.min_segno);
+ secno = GET_SEC_FROM_SEG(sbi, p.min_segno);
if (gc_type == FG_GC)
sbi->cur_victim_sec = secno;
else
@@ -331,6 +394,7 @@
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 +404,39 @@
.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);
}
}
@@ -396,9 +462,12 @@
static void gc_node_segment(struct f2fs_sb_info *sbi,
struct f2fs_summary *sum, unsigned int segno, int gc_type)
{
- bool initial = true;
struct f2fs_summary *entry;
+ block_t start_addr;
int off;
+ int phase = 0;
+
+ start_addr = START_BLOCK(sbi, segno);
next_step:
entry = sum;
@@ -406,18 +475,27 @@
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))
+ if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0))
return;
if (check_valid_map(sbi, segno, off) == 0)
continue;
- if (initial) {
+ if (phase == 0) {
+ ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1,
+ META_NAT, true);
+ continue;
+ }
+
+ if (phase == 1) {
ra_node_page(sbi, nid);
continue;
}
+
+ /* phase == 2 */
node_page = get_node_page(sbi, nid);
if (IS_ERR(node_page))
continue;
@@ -428,38 +506,18 @@
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;
+ if (++phase < 3)
goto next_step;
- }
-
- if (gc_type == FG_GC) {
- struct writeback_control wbc = {
- .sync_mode = WB_SYNC_ALL,
- .nr_to_write = LONG_MAX,
- .for_reclaim = 0,
- };
- sync_node_pages(sbi, 0, &wbc);
-
- /*
- * 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 +527,7 @@
* 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 +544,10 @@
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 +560,15 @@
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;
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "%s: valid data with mismatched node version.",
+ __func__);
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
}
*nofs = ofs_of_node(node_page);
@@ -516,16 +576,132 @@
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,
+ unsigned int segno, int off)
{
struct f2fs_io_info fio = {
+ .sbi = F2FS_I_SB(inode),
.type = DATA,
- .rw = WRITE_SYNC,
+ .op = REQ_OP_READ,
+ .op_flags = 0,
+ .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;
+
+ if (!check_valid_map(F2FS_I_SB(inode), segno, off))
+ goto out;
+
+ if (f2fs_is_atomic_file(inode))
+ goto out;
+
+ 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.op = REQ_OP_WRITE;
+ fio.op_flags = REQ_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,
+ unsigned int segno, int off)
+{
+ struct page *page;
+
+ page = get_lock_data_page(inode, bidx, true);
+ if (IS_ERR(page))
+ return;
+
+ if (!check_valid_map(F2FS_I_SB(inode), segno, off))
+ goto out;
+
+ if (f2fs_is_atomic_file(inode))
+ goto out;
if (gc_type == BG_GC) {
if (PageWriteback(page))
@@ -533,13 +709,34 @@
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,
+ .op = REQ_OP_WRITE,
+ .op_flags = REQ_SYNC,
+ .old_blkaddr = NULL_ADDR,
+ .page = page,
+ .encrypted_page = NULL,
+ .need_lock = true,
+ };
+ bool is_dirty = PageDirty(page);
+ int err;
- if (clear_page_dirty_for_io(page))
+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);
+ remove_dirty_inode(inode);
+ }
+
set_cold_data(page);
- do_write_data_page(page, &fio);
- clear_cold_data(page);
+
+ err = do_write_data_page(&fio);
+ if (err == -ENOMEM && is_dirty) {
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ goto retry;
+ }
}
out:
f2fs_put_page(page, 1);
@@ -553,7 +750,7 @@
* 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;
@@ -572,188 +769,275 @@
struct node_info dni; /* dnode info for the data */
unsigned int ofs_in_node, nofs;
block_t start_bidx;
+ nid_t nid = le32_to_cpu(entry->nid);
/* stop BG_GC if there is not enough free sections. */
- if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0))
+ if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0))
return;
if (check_valid_map(sbi, segno, off) == 0)
continue;
if (phase == 0) {
- ra_node_page(sbi, le32_to_cpu(entry->nid));
+ ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1,
+ META_NAT, true);
+ continue;
+ }
+
+ if (phase == 1) {
+ ra_node_page(sbi, nid);
continue;
}
/* 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) {
+ if (phase == 2) {
ra_node_page(sbi, dni.ino);
continue;
}
ofs_in_node = le16_to_cpu(entry->ofs_in_node);
- if (phase == 2) {
+ if (phase == 3) {
inode = f2fs_iget(sb, dni.ino);
if (IS_ERR(inode) || is_bad_inode(inode))
continue;
- 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, REQ_RAHEAD,
+ 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))
+ add_gc_inode(gc_list, inode);
+ continue;
+ }
+
+ /* phase 4 */
+ 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;
- move_data_page(inode, data_page, gc_type);
- stat_inc_data_blk_count(sbi, 1);
+ 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, segno, off);
+ else
+ move_data_page(inode, start_bidx, gc_type, segno, off);
+
+ 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)
+ if (++phase < 5)
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 sec_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++) {
+
+ /* find segment summary of victim */
+ sum_page = find_get_page(META_MAPPING(sbi),
+ GET_SUM_BLOCK(sbi, segno));
+ f2fs_put_page(sum_page, 0);
+
+ if (get_valid_blocks(sbi, segno, false) == 0 ||
+ !PageUptodate(sum_page) ||
+ unlikely(f2fs_cp_error(sbi)))
+ goto next;
+
+ sum = page_address(sum_page);
+ f2fs_bug_on(sbi, type != GET_SUM_TYPE((&sum->footer)));
+
+ /*
+ * this is to avoid deadlock:
+ * - lock_page(sum_page) - f2fs_replace_block
+ * - check_valid_map() - mutex_lock(sentry_lock)
+ * - mutex_lock(sentry_lock) - change_curseg()
+ * - lock_page(sum_page)
+ */
+ if (type == SUM_TYPE_NODE)
+ gc_node_segment(sbi, sum->entries, segno, gc_type);
+ else
+ gc_data_segment(sbi, sum->entries, gc_list, segno,
+ gc_type);
+
+ stat_inc_seg_count(sbi, type, gc_type);
+next:
+ f2fs_put_page(sum_page, 0);
+ }
if (gc_type == FG_GC)
- 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 &&
+ get_valid_blocks(sbi, start_segno, true) == 0)
+ sec_freed = 1;
+
+ stat_inc_call_count(sbi->stat_info);
+
+ return sec_freed;
+}
+
+int f2fs_gc(struct f2fs_sb_info *sbi, bool sync,
+ bool background, unsigned int segno)
+{
+ int gc_type = sync ? FG_GC : BG_GC;
+ int sec_freed = 0;
+ int ret = -EINVAL;
+ struct cp_control cpc;
+ unsigned int init_segno = segno;
+ 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:
+ 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, 0, 0)) {
+ /*
+ * For example, if there are many prefree_segments below given
+ * threshold, we can make them free by checkpoint. Then, we
+ * secure free segments which doesn't need fggc any more.
+ */
+ if (prefree_segments(sbi)) {
+ ret = write_checkpoint(sbi, &cpc);
+ if (ret)
+ goto stop;
+ }
+ if (has_not_enough_free_secs(sbi, 0, 0))
+ gc_type = FG_GC;
+ }
+
+ /* f2fs_balance_fs doesn't need to do BG_GC in critical path. */
+ if (gc_type == BG_GC && !background)
+ goto stop;
+ if (!__get_victim(sbi, &segno, gc_type))
+ goto stop;
+ ret = 0;
+
+ if (do_garbage_collect(sbi, segno, &gc_list, gc_type) &&
+ gc_type == FG_GC)
+ sec_freed++;
+
+ if (gc_type == FG_GC)
+ sbi->cur_victim_sec = NULL_SEGNO;
+
+ if (!sync) {
+ if (has_not_enough_free_secs(sbi, sec_freed, 0)) {
+ segno = NULL_SEGNO;
+ goto gc_more;
+ }
+
+ if (gc_type == FG_GC)
+ ret = write_checkpoint(sbi, &cpc);
+ }
stop:
+ SIT_I(sbi)->last_victim[ALLOC_NEXT] = 0;
+ SIT_I(sbi)->last_victim[FLUSH_DEVICE] = init_segno;
mutex_unlock(&sbi->gc_mutex);
- put_gc_inode(&ilist);
+ put_gc_inode(&gc_list);
+
+ if (sync)
+ ret = sec_freed ? 0 : -EAGAIN;
return ret;
}
void build_gc_manager(struct f2fs_sb_info *sbi)
{
+ u64 main_count, resv_count, ovp_count;
+
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;
-}
+ /* threshold of # of valid blocks in a section for victims of FG_GC */
+ main_count = SM_I(sbi)->main_segments << sbi->log_blocks_per_seg;
+ resv_count = SM_I(sbi)->reserved_segments << sbi->log_blocks_per_seg;
+ ovp_count = SM_I(sbi)->ovp_segments << sbi->log_blocks_per_seg;
-void destroy_gc_caches(void)
-{
- kmem_cache_destroy(winode_slab);
+ sbi->fggc_threshold = div64_u64((main_count - ovp_count) *
+ BLKS_PER_SEC(sbi), (main_count - resv_count));
+
+ /* give warm/cold data area from slower device */
+ if (sbi->s_ndevs && sbi->segs_per_sec == 1)
+ SIT_I(sbi)->last_victim[ALLOC_NEXT] =
+ GET_SEGNO(sbi, FDEV(0).end_blk) + 1;
}
diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h
index 16f0b2b..a993967 100644
--- a/fs/f2fs/gc.h
+++ b/fs/f2fs/gc.h
@@ -35,9 +35,9 @@
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 @@
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 @@
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]);
-}
diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c
index a844fcf..eb2e031 100644
--- a/fs/f2fs/hash.c
+++ b/fs/f2fs/hash.c
@@ -70,7 +70,8 @@
*buf++ = pad;
}
-f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info)
+f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info,
+ struct fscrypt_name *fname)
{
__u32 hash;
f2fs_hash_t f2fs_hash;
@@ -79,8 +80,11 @@
const unsigned char *name = name_info->name;
size_t len = name_info->len;
- if ((len <= 2) && (name[0] == '.') &&
- (name[1] == '.' || name[1] == '\0'))
+ /* encrypted bigname case */
+ if (fname && !fname->disk_name.name)
+ return cpu_to_le32(fname->hash);
+
+ if (is_dot_dotdot(name_info))
return 0;
/* Initialize the default seed for the hash checksum functions */
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 546171c..ce2c0a6 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -10,35 +10,41 @@
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
-
-#include "f2fs.h"
#include <trace/events/android_fs.h>
-bool f2fs_may_inline(struct inode *inode)
+#include "f2fs.h"
+#include "node.h"
+
+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;
}
-int f2fs_read_inline_data(struct inode *inode, struct page *page)
+bool f2fs_may_inline_dentry(struct inode *inode)
{
- struct page *ipage;
+ 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 (trace_android_fs_dataread_start_enabled()) {
@@ -46,16 +52,50 @@
path = android_fstrace_get_pathname(pathbuf,
MAX_TRACE_PATHBUF_LEN,
- inode);
- trace_android_fs_dataread_start(inode, page_offset(page),
+ page->mapping->host);
+ trace_android_fs_dataread_start(page->mapping->host,
+ page_offset(page),
PAGE_SIZE, current->pid,
path, current->comm);
}
- if (page->index) {
- zero_user_segment(page, 0, PAGE_CACHE_SIZE);
- goto out;
- }
+ 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);
+}
+
+void truncate_inline_inode(struct inode *inode, struct page *ipage, u64 from)
+{
+ void *addr;
+
+ if (from >= MAX_INLINE_DATA)
+ return;
+
+ 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);
+
+ if (from == 0)
+ clear_inode_flag(inode, FI_DATA_EXIST);
+}
+
+int f2fs_read_inline_data(struct inode *inode, struct page *page)
+{
+ struct page *ipage;
ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino);
if (IS_ERR(ipage)) {
@@ -65,113 +105,118 @@
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:
trace_android_fs_dataread_end(inode, page_offset(page), PAGE_SIZE);
- 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,
+ .op = REQ_OP_WRITE,
+ .op_flags = REQ_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;
+ set_inode_flag(dn->inode, FI_HOT_DATA);
+ write_data_page(dn, &fio);
+ f2fs_wait_on_page_writeback(page, DATA, true);
+ if (dirty) {
+ inode_dec_dirty_pages(dn->inode);
+ remove_dirty_inode(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, dn->inode_page, 0);
+ clear_inline_node(dn->inode_page);
+clear_out:
+ stat_dec_inline_inode(dn->inode);
+ clear_inode_flag(dn->inode, FI_INLINE_DATA);
+ 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;
@@ -179,49 +224,29 @@
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);
@@ -246,12 +271,16 @@
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;
}
@@ -259,16 +288,400 @@
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);
+ truncate_inline_inode(inode, ipage, 0);
+ clear_inode_flag(inode, FI_INLINE_DATA);
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, fname);
+
+ inline_dentry = inline_data_addr(ipage);
+
+ make_dentry_ptr_inline(NULL, &d, inline_dentry);
+ 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_inline(NULL, &d, dentry_blk);
+ 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(dir, 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_inline(NULL, &d, inline_dentry);
+
+ 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 = le16_to_cpu(de->name_len);
+
+ ino = le32_to_cpu(de->ino);
+ fake_mode = get_de_type(de) << S_SHIFT;
+
+ err = f2fs_add_regular_entry(dir, &new_name, NULL, NULL,
+ ino, fake_mode);
+ if (err)
+ goto punch_dentry_pages;
+
+ bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len));
+ }
+ return 0;
+punch_dentry_pages:
+ truncate_inode_pages(&dir->i_data, 0);
+ truncate_blocks(dir, 0, false);
+ remove_dirty_inode(dir);
+ return err;
+}
+
+static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage,
+ struct f2fs_inline_dentry *inline_dentry)
+{
+ struct f2fs_inline_dentry *backup_dentry;
+ int err;
+
+ backup_dentry = f2fs_kmalloc(F2FS_I_SB(dir),
+ sizeof(struct f2fs_inline_dentry), GFP_F2FS_ZERO);
+ if (!backup_dentry) {
+ f2fs_put_page(ipage, 1);
+ return -ENOMEM;
+ }
+
+ memcpy(backup_dentry, inline_dentry, MAX_INLINE_DATA);
+ truncate_inline_inode(dir, ipage, 0);
+
+ unlock_page(ipage);
+
+ err = f2fs_add_inline_entries(dir, backup_dentry);
+ if (err)
+ goto recover;
+
+ lock_page(ipage);
+
+ stat_dec_inline_dir(dir);
+ clear_inode_flag(dir, FI_INLINE_DENTRY);
+ kfree(backup_dentry);
+ return 0;
+recover:
+ lock_page(ipage);
+ memcpy(inline_dentry, backup_dentry, MAX_INLINE_DATA);
+ f2fs_i_depth_write(dir, 0);
+ f2fs_i_size_write(dir, MAX_INLINE_DATA);
+ set_page_dirty(ipage);
+ f2fs_put_page(ipage, 1);
+
+ kfree(backup_dentry);
+ return err;
+}
+
+static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage,
+ struct f2fs_inline_dentry *inline_dentry)
+{
+ if (!F2FS_I(dir)->i_dir_level)
+ return f2fs_move_inline_dirents(dir, ipage, inline_dentry);
+ else
+ return f2fs_move_rehashed_dirents(dir, ipage, inline_dentry);
+}
+
+int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
+ const struct qstr *orig_name,
+ struct inode *inode, nid_t ino, umode_t mode)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
+ struct page *ipage;
+ unsigned int bit_pos;
+ f2fs_hash_t name_hash;
+ struct f2fs_inline_dentry *dentry_blk = NULL;
+ struct f2fs_dentry_ptr d;
+ int slots = GET_DENTRY_SLOTS(new_name->len);
+ 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, new_name,
+ orig_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(new_name, NULL);
+ make_dentry_ptr_inline(NULL, &d, dentry_blk);
+ f2fs_update_dentry(ino, mode, &d, new_name, name_hash, bit_pos);
+
+ set_page_dirty(ipage);
+
+ /* we don't need to mark_inode_dirty now */
+ if (inode) {
+ f2fs_i_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++)
+ __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(dir);
+ f2fs_mark_inode_dirty_sync(dir, false);
+
+ 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;
+ int err;
+
+ 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_inline(inode, &d, inline_dentry);
+
+ err = f2fs_fill_dentries(ctx, &d, 0, fstr);
+ if (!err)
+ ctx->pos = NR_INLINE_DENTRY;
+
+ f2fs_put_page(ipage, 1);
+ return err < 0 ? err : 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;
+}
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 0deead4..20782deb 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -11,14 +11,22 @@
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/buffer_head.h>
+#include <linux/backing-dev.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, bool sync)
+{
+ if (f2fs_inode_dirtied(inode, sync))
+ return;
+
+ mark_inode_dirty_sync(inode);
+}
+
void f2fs_set_inode_flags(struct inode *inode)
{
unsigned int flags = F2FS_I(inode)->i_flags;
@@ -34,8 +42,9 @@
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, false);
}
static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
@@ -51,6 +60,15 @@
}
}
+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 +85,25 @@
}
}
+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 +148,30 @@
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 +210,13 @@
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 +236,28 @@
return ERR_PTR(ret);
}
-void update_inode(struct inode *inode, struct page *node_page)
+struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino)
+{
+ struct inode *inode;
+retry:
+ inode = f2fs_iget(sb, ino);
+ if (IS_ERR(inode)) {
+ if (PTR_ERR(inode) == -ENOMEM) {
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ goto retry;
+ }
+ }
+ return inode;
+}
+
+int update_inode(struct inode *inode, struct page *node_page)
{
struct f2fs_inode *ri;
+ struct extent_tree *et = F2FS_I(inode)->extent_tree;
- 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 +268,15 @@
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 (et) {
+ read_lock(&et->lock);
+ set_raw_extent(&et->largest, &ri->i_ext);
+ read_unlock(&et->lock);
+ } 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 +293,19 @@
__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 +314,13 @@
cond_resched();
goto retry;
} else if (err != -ENOENT) {
- f2fs_stop_checkpoint(sbi);
+ f2fs_stop_checkpoint(sbi, false);
}
- return;
+ 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 +331,16 @@
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 (wbc && wbc->nr_to_write)
+ f2fs_balance_fs(sbi, true);
return 0;
}
@@ -268,46 +351,85 @@
{
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;
+ remove_ino_entry(sbi, inode->i_ino, APPEND_INO);
+ remove_ino_entry(sbi, inode->i_ino, UPDATE_INO);
+
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);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(sbi, FAULT_EVICT_INODE)) {
+ f2fs_show_injection_info(FAULT_EVICT_INODE);
+ err = -EIO;
+ }
+#endif
+ if (!err) {
+ f2fs_lock_op(sbi);
+ err = remove_inode_page(inode);
+ f2fs_unlock_op(sbi);
+ if (err == -ENOENT)
+ err = 0;
+ }
+ /* 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:
- invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino, inode->i_ino);
+ stat_dec_inline_xattr(inode);
+ stat_dec_inline_dir(inode);
+ stat_dec_inline_inode(inode);
+
+ /* ino == 0, if f2fs_new_inode() was failed t*/
+ if (inode->i_ino)
+ 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 (inode->i_nlink) {
+ 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 +437,45 @@
void handle_failed_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct node_info ni;
+ /*
+ * clear nlink of inode in order to release resource of inode
+ * immediately.
+ */
clear_nlink(inode);
- make_bad_inode(inode);
+
+ /*
+ * we must call this to avoid inode being remained as dirty, resulting
+ * in a panic when flushing dirty inodes in gdirty_list.
+ */
+ update_inode_page(inode);
+ f2fs_inode_synced(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 */
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 0d2526e..b5a5239 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -9,11 +9,13 @@
* published by the Free Software Foundation.
*/
#include <linux/fs.h>
+#include <linux/namei.h>
#include <linux/f2fs_fs.h>
#include <linux/pagemap.h>
#include <linux/sched.h>
#include <linux/ctype.h>
#include <linux/dcache.h>
+#include <linux/namei.h>
#include "f2fs.h"
#include "node.h"
@@ -45,28 +47,44 @@
inode->i_ino = ino;
inode->i_blocks = 0;
- inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+ inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
inode->i_generation = sbi->s_next_generation++;
err = insert_inode_locked(inode);
if (err) {
err = -EINVAL;
nid_free = true;
- goto out;
+ goto fail;
}
+
+ /* If the directory encrypted, then we should encrypt the inode. */
+ if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode))
+ f2fs_set_encrypted_inode(inode);
+
+ set_inode_flag(inode, FI_NEW_INODE);
+
+ if (test_opt(sbi, INLINE_XATTR))
+ set_inode_flag(inode, FI_INLINE_XATTR);
+ if (test_opt(sbi, INLINE_DATA) && f2fs_may_inline_data(inode))
+ set_inode_flag(inode, FI_INLINE_DATA);
+ if (f2fs_may_inline_dentry(inode))
+ set_inode_flag(inode, FI_INLINE_DENTRY);
+
+ f2fs_init_extent_tree(inode, NULL);
+
+ stat_inc_inline_xattr(inode);
+ stat_inc_inline_inode(inode);
+ stat_inc_inline_dir(inode);
+
trace_f2fs_new_inode(inode, 0);
- mark_inode_dirty(inode);
return inode;
-out:
- clear_nlink(inode);
- unlock_new_inode(inode);
fail:
trace_f2fs_new_inode(inode, err);
make_bad_inode(inode);
- iput(inode);
if (nid_free)
- alloc_nid_failed(sbi, ino);
+ set_inode_flag(inode, FI_FREE_NID);
+ iput(inode);
return ERR_PTR(err);
}
@@ -74,11 +92,23 @@
{
size_t slen = strlen(s);
size_t sublen = strlen(sub);
+ int i;
- if (sublen > slen)
+ /*
+ * filename format of multimedia file should be defined as:
+ * "filename + '.' + extension + (optional: '.' + temp extension)".
+ */
+ if (slen < sublen + 2)
return 0;
- return !strncasecmp(s + slen - sublen, sub, sublen);
+ for (i = 1; i < slen - sublen; i++) {
+ if (s[i] != '.')
+ continue;
+ if (!strncasecmp(s + i + 1, sub, sublen))
+ return 1;
+ }
+
+ return 0;
}
/*
@@ -107,8 +137,6 @@
nid_t ino = 0;
int err;
- f2fs_balance_fs(sbi);
-
inode = f2fs_new_inode(dir, mode);
if (IS_ERR(inode))
return PTR_ERR(inode);
@@ -131,6 +159,11 @@
d_instantiate(dentry, inode);
unlock_new_inode(inode);
+
+ if (IS_DIRSYNC(dir))
+ f2fs_sync_fs(sbi->sb, 1);
+
+ f2fs_balance_fs(sbi, true);
return 0;
out:
handle_failed_inode(inode);
@@ -140,16 +173,20 @@
static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
struct dentry *dentry)
{
- struct inode *inode = old_dentry->d_inode;
+ struct inode *inode = d_inode(old_dentry);
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
int err;
- f2fs_balance_fs(sbi);
+ if (f2fs_encrypted_inode(dir) &&
+ !fscrypt_has_permitted_context(dir, inode))
+ return -EPERM;
- inode->i_ctime = CURRENT_TIME;
+ f2fs_balance_fs(sbi, true);
+
+ inode->i_ctime = current_time(inode);
ihold(inode);
- set_inode_flag(F2FS_I(inode), FI_INC_LINK);
+ set_inode_flag(inode, FI_INC_LINK);
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
if (err)
@@ -157,9 +194,12 @@
f2fs_unlock_op(sbi);
d_instantiate(dentry, inode);
+
+ if (IS_DIRSYNC(dir))
+ f2fs_sync_fs(sbi->sb, 1);
return 0;
out:
- clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
+ clear_inode_flag(inode, FI_INC_LINK);
iput(inode);
f2fs_unlock_op(sbi);
return err;
@@ -168,10 +208,64 @@
struct dentry *f2fs_get_parent(struct dentry *child)
{
struct qstr dotdot = QSTR_INIT("..", 2);
- unsigned long ino = f2fs_inode_by_name(child->d_inode, &dotdot);
- if (!ino)
+ struct page *page;
+ unsigned long ino = f2fs_inode_by_name(d_inode(child), &dotdot, &page);
+ if (!ino) {
+ if (IS_ERR(page))
+ return ERR_CAST(page);
return ERR_PTR(-ENOENT);
- return d_obtain_alias(f2fs_iget(child->d_inode->i_sb, ino));
+ }
+ return d_obtain_alias(f2fs_iget(child->d_sb, ino));
+}
+
+static int __recover_dot_dentries(struct inode *dir, nid_t pino)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
+ struct qstr dot = QSTR_INIT(".", 1);
+ struct qstr dotdot = QSTR_INIT("..", 2);
+ struct f2fs_dir_entry *de;
+ struct page *page;
+ int err = 0;
+
+ if (f2fs_readonly(sbi->sb)) {
+ f2fs_msg(sbi->sb, KERN_INFO,
+ "skip recovering inline_dots inode (ino:%lu, pino:%u) "
+ "in readonly mountpoint", dir->i_ino, pino);
+ return 0;
+ }
+
+ f2fs_balance_fs(sbi, true);
+
+ f2fs_lock_op(sbi);
+
+ de = f2fs_find_entry(dir, &dot, &page);
+ if (de) {
+ f2fs_dentry_kunmap(dir, page);
+ f2fs_put_page(page, 0);
+ } else if (IS_ERR(page)) {
+ err = PTR_ERR(page);
+ goto out;
+ } else {
+ err = __f2fs_add_link(dir, &dot, NULL, dir->i_ino, S_IFDIR);
+ if (err)
+ goto out;
+ }
+
+ de = f2fs_find_entry(dir, &dotdot, &page);
+ if (de) {
+ f2fs_dentry_kunmap(dir, page);
+ f2fs_put_page(page, 0);
+ } else if (IS_ERR(page)) {
+ err = PTR_ERR(page);
+ } else {
+ err = __f2fs_add_link(dir, &dotdot, NULL, pino, S_IFDIR);
+ }
+out:
+ if (!err)
+ clear_inode_flag(dir, FI_INLINE_DOTS);
+
+ f2fs_unlock_op(sbi);
+ return err;
}
static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
@@ -180,74 +274,163 @@
struct inode *inode = NULL;
struct f2fs_dir_entry *de;
struct page *page;
+ nid_t ino;
+ int err = 0;
+ unsigned int root_ino = F2FS_ROOT_INO(F2FS_I_SB(dir));
+
+ if (f2fs_encrypted_inode(dir)) {
+ int res = fscrypt_get_encryption_info(dir);
+
+ /*
+ * DCACHE_ENCRYPTED_WITH_KEY is set if the dentry is
+ * created while the directory was encrypted and we
+ * don't have access to the key.
+ */
+ if (fscrypt_has_encryption_key(dir))
+ fscrypt_set_encrypted_dentry(dentry);
+ fscrypt_set_d_op(dentry);
+ if (res && res != -ENOKEY)
+ return ERR_PTR(res);
+ }
if (dentry->d_name.len > F2FS_NAME_LEN)
return ERR_PTR(-ENAMETOOLONG);
de = f2fs_find_entry(dir, &dentry->d_name, &page);
- if (de) {
- nid_t ino = le32_to_cpu(de->ino);
- kunmap(page);
- f2fs_put_page(page, 0);
-
- inode = f2fs_iget(dir->i_sb, ino);
- if (IS_ERR(inode))
- return ERR_CAST(inode);
-
- stat_inc_inline_inode(inode);
+ if (!de) {
+ if (IS_ERR(page))
+ return (struct dentry *)page;
+ return d_splice_alias(inode, dentry);
}
+ ino = le32_to_cpu(de->ino);
+ f2fs_dentry_kunmap(dir, page);
+ f2fs_put_page(page, 0);
+
+ inode = f2fs_iget(dir->i_sb, ino);
+ if (IS_ERR(inode))
+ return ERR_CAST(inode);
+
+ if ((dir->i_ino == root_ino) && f2fs_has_inline_dots(dir)) {
+ err = __recover_dot_dentries(dir, root_ino);
+ if (err)
+ goto err_out;
+ }
+
+ if (f2fs_has_inline_dots(inode)) {
+ err = __recover_dot_dentries(inode, dir->i_ino);
+ if (err)
+ goto err_out;
+ }
+ if (f2fs_encrypted_inode(dir) &&
+ (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
+ !fscrypt_has_permitted_context(dir, inode)) {
+ f2fs_msg(inode->i_sb, KERN_WARNING,
+ "Inconsistent encryption contexts: %lu/%lu",
+ dir->i_ino, inode->i_ino);
+ err = -EPERM;
+ goto err_out;
+ }
return d_splice_alias(inode, dentry);
+
+err_out:
+ iput(inode);
+ return ERR_PTR(err);
}
static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
struct f2fs_dir_entry *de;
struct page *page;
int err = -ENOENT;
trace_f2fs_unlink_enter(dir, dentry);
- f2fs_balance_fs(sbi);
de = f2fs_find_entry(dir, &dentry->d_name, &page);
- if (!de)
+ if (!de) {
+ if (IS_ERR(page))
+ err = PTR_ERR(page);
goto fail;
+ }
+
+ f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
err = acquire_orphan_inode(sbi);
if (err) {
f2fs_unlock_op(sbi);
- kunmap(page);
+ f2fs_dentry_kunmap(dir, page);
f2fs_put_page(page, 0);
goto fail;
}
- f2fs_delete_entry(de, page, inode);
+ f2fs_delete_entry(de, page, dir, inode);
f2fs_unlock_op(sbi);
- /* In order to evict this inode, we set it dirty */
- mark_inode_dirty(inode);
+ if (IS_DIRSYNC(dir))
+ f2fs_sync_fs(sbi->sb, 1);
fail:
trace_f2fs_unlink_exit(inode, err);
return err;
}
+static void *f2fs_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+ struct page *page;
+ char *link;
+
+ page = page_follow_link_light(dentry, nd);
+ if (IS_ERR(page))
+ return page;
+
+ link = nd_get_link(nd);
+ if (IS_ERR(link))
+ return link;
+
+ /* this is broken symlink case */
+ if (*link == 0) {
+ kunmap(page);
+ page_cache_release(page);
+ return ERR_PTR(-ENOENT);
+ }
+ return page;
+}
+
static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
const char *symname)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
struct inode *inode;
- size_t symlen = strlen(symname) + 1;
+ size_t len = strlen(symname);
+ struct fscrypt_str disk_link = FSTR_INIT((char *)symname, len + 1);
+ struct fscrypt_symlink_data *sd = NULL;
int err;
- f2fs_balance_fs(sbi);
+ if (f2fs_encrypted_inode(dir)) {
+ err = fscrypt_get_encryption_info(dir);
+ if (err)
+ return err;
+
+ if (!fscrypt_has_encryption_key(dir))
+ return -ENOKEY;
+
+ disk_link.len = (fscrypt_fname_encrypted_size(dir, len) +
+ sizeof(struct fscrypt_symlink_data));
+ }
+
+ if (disk_link.len > dir->i_sb->s_blocksize)
+ return -ENAMETOOLONG;
inode = f2fs_new_inode(dir, S_IFLNK | S_IRWXUGO);
if (IS_ERR(inode))
return PTR_ERR(inode);
- 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;
f2fs_lock_op(sbi);
@@ -255,12 +438,65 @@
if (err)
goto out;
f2fs_unlock_op(sbi);
-
- err = page_symlink(inode, symname, symlen);
alloc_nid_done(sbi, inode->i_ino);
+ if (f2fs_encrypted_inode(inode)) {
+ struct qstr istr = QSTR_INIT(symname, len);
+ struct fscrypt_str ostr;
+
+ sd = kzalloc(disk_link.len, GFP_NOFS);
+ if (!sd) {
+ err = -ENOMEM;
+ goto err_out;
+ }
+
+ err = fscrypt_get_encryption_info(inode);
+ if (err)
+ goto err_out;
+
+ if (!fscrypt_has_encryption_key(inode)) {
+ err = -ENOKEY;
+ goto err_out;
+ }
+
+ ostr.name = sd->encrypted_path;
+ ostr.len = disk_link.len;
+ err = fscrypt_fname_usr_to_disk(inode, &istr, &ostr);
+ if (err)
+ goto err_out;
+
+ sd->len = cpu_to_le16(ostr.len);
+ disk_link.name = (char *)sd;
+ }
+
+ err = page_symlink(inode, disk_link.name, disk_link.len);
+
+err_out:
d_instantiate(dentry, inode);
unlock_new_inode(inode);
+
+ /*
+ * Let's flush symlink data in order to avoid broken symlink as much as
+ * possible. Nevertheless, fsyncing is the best way, but there is no
+ * way to get a file descriptor in order to flush that.
+ *
+ * Note that, it needs to do dir->fsync to make this recoverable.
+ * If the symlink path is stored into inline_data, there is no
+ * performance regression.
+ */
+ if (!err) {
+ filemap_write_and_wait_range(inode->i_mapping, 0,
+ disk_link.len - 1);
+
+ if (IS_DIRSYNC(dir))
+ f2fs_sync_fs(sbi->sb, 1);
+ } else {
+ f2fs_unlink(dir, dentry);
+ }
+
+ kfree(sd);
+
+ f2fs_balance_fs(sbi, true);
return err;
out:
handle_failed_inode(inode);
@@ -273,8 +509,6 @@
struct inode *inode;
int err;
- f2fs_balance_fs(sbi);
-
inode = f2fs_new_inode(dir, S_IFDIR | mode);
if (IS_ERR(inode))
return PTR_ERR(inode);
@@ -282,9 +516,9 @@
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);
- set_inode_flag(F2FS_I(inode), FI_INC_LINK);
+ set_inode_flag(inode, FI_INC_LINK);
f2fs_lock_op(sbi);
err = f2fs_add_link(dentry, inode);
if (err)
@@ -296,17 +530,21 @@
d_instantiate(dentry, inode);
unlock_new_inode(inode);
+ if (IS_DIRSYNC(dir))
+ f2fs_sync_fs(sbi->sb, 1);
+
+ f2fs_balance_fs(sbi, true);
return 0;
out_fail:
- clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
+ clear_inode_flag(inode, FI_INC_LINK);
handle_failed_inode(inode);
return err;
}
static int f2fs_rmdir(struct inode *dir, struct dentry *dentry)
{
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = d_inode(dentry);
if (f2fs_empty_dir(inode))
return f2fs_unlink(dir, dentry);
return -ENOTEMPTY;
@@ -322,8 +560,6 @@
if (!new_valid_dev(rdev))
return -EINVAL;
- f2fs_balance_fs(sbi);
-
inode = f2fs_new_inode(dir, mode);
if (IS_ERR(inode))
return PTR_ERR(inode);
@@ -338,51 +574,158 @@
f2fs_unlock_op(sbi);
alloc_nid_done(sbi, inode->i_ino);
+
d_instantiate(dentry, inode);
unlock_new_inode(inode);
+
+ if (IS_DIRSYNC(dir))
+ f2fs_sync_fs(sbi->sb, 1);
+
+ f2fs_balance_fs(sbi, true);
return 0;
out:
handle_failed_inode(inode);
return err;
}
+static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
+ umode_t mode, struct inode **whiteout)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
+ struct inode *inode;
+ int err;
+
+ inode = f2fs_new_inode(dir, mode);
+ if (IS_ERR(inode))
+ return PTR_ERR(inode);
+
+ if (whiteout) {
+ init_special_inode(inode, inode->i_mode, WHITEOUT_DEV);
+ inode->i_op = &f2fs_special_inode_operations;
+ } else {
+ inode->i_op = &f2fs_file_inode_operations;
+ inode->i_fop = &f2fs_file_operations;
+ inode->i_mapping->a_ops = &f2fs_dblock_aops;
+ }
+
+ f2fs_lock_op(sbi);
+ err = acquire_orphan_inode(sbi);
+ if (err)
+ goto out;
+
+ err = f2fs_do_tmpfile(inode, dir);
+ if (err)
+ goto release_out;
+
+ /*
+ * add this non-linked tmpfile to orphan list, in this way we could
+ * remove all unused data of tmpfile after abnormal power-off.
+ */
+ add_orphan_inode(inode);
+ alloc_nid_done(sbi, inode->i_ino);
+
+ if (whiteout) {
+ f2fs_i_links_write(inode, false);
+ *whiteout = inode;
+ } else {
+ d_tmpfile(dentry, inode);
+ }
+ /* link_count was changed by d_tmpfile as well. */
+ f2fs_unlock_op(sbi);
+ unlock_new_inode(inode);
+
+ f2fs_balance_fs(sbi, true);
+ return 0;
+
+release_out:
+ release_orphan_inode(sbi);
+out:
+ handle_failed_inode(inode);
+ return err;
+}
+
+static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+ if (f2fs_encrypted_inode(dir)) {
+ int err = fscrypt_get_encryption_info(dir);
+ if (err)
+ return err;
+ }
+
+ return __f2fs_tmpfile(dir, dentry, mode, NULL);
+}
+
+static int f2fs_create_whiteout(struct inode *dir, struct inode **whiteout)
+{
+ return __f2fs_tmpfile(dir, NULL, S_IFCHR | WHITEOUT_MODE, whiteout);
+}
+
static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry)
+ struct inode *new_dir, struct dentry *new_dentry,
+ unsigned int flags)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(old_dir);
- struct inode *old_inode = old_dentry->d_inode;
- struct inode *new_inode = new_dentry->d_inode;
+ struct inode *old_inode = d_inode(old_dentry);
+ struct inode *new_inode = d_inode(new_dentry);
+ struct inode *whiteout = NULL;
struct page *old_dir_page;
- struct page *old_page, *new_page;
+ struct page *old_page, *new_page = NULL;
struct f2fs_dir_entry *old_dir_entry = NULL;
struct f2fs_dir_entry *old_entry;
struct f2fs_dir_entry *new_entry;
+ bool is_old_inline = f2fs_has_inline_dentry(old_dir);
int err = -ENOENT;
- f2fs_balance_fs(sbi);
+ if ((f2fs_encrypted_inode(old_dir) &&
+ !fscrypt_has_encryption_key(old_dir)) ||
+ (f2fs_encrypted_inode(new_dir) &&
+ !fscrypt_has_encryption_key(new_dir)))
+ return -ENOKEY;
+
+ if ((old_dir != new_dir) && f2fs_encrypted_inode(new_dir) &&
+ !fscrypt_has_permitted_context(new_dir, old_inode)) {
+ err = -EPERM;
+ goto out;
+ }
old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
- if (!old_entry)
+ if (!old_entry) {
+ if (IS_ERR(old_page))
+ err = PTR_ERR(old_page);
goto out;
+ }
if (S_ISDIR(old_inode->i_mode)) {
- err = -EIO;
old_dir_entry = f2fs_parent_dir(old_inode, &old_dir_page);
- if (!old_dir_entry)
+ if (!old_dir_entry) {
+ if (IS_ERR(old_dir_page))
+ err = PTR_ERR(old_dir_page);
goto out_old;
+ }
+ }
+
+ if (flags & RENAME_WHITEOUT) {
+ err = f2fs_create_whiteout(old_dir, &whiteout);
+ if (err)
+ goto out_dir;
}
if (new_inode) {
err = -ENOTEMPTY;
if (old_dir_entry && !f2fs_empty_dir(new_inode))
- goto out_dir;
+ goto out_whiteout;
err = -ENOENT;
new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name,
&new_page);
- if (!new_entry)
- goto out_dir;
+ if (!new_entry) {
+ if (IS_ERR(new_page))
+ err = PTR_ERR(new_page);
+ goto out_whiteout;
+ }
+
+ f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
@@ -390,41 +733,53 @@
if (err)
goto put_out_dir;
- if (update_dent_inode(old_inode, &new_dentry->d_name)) {
- release_orphan_inode(sbi);
- goto put_out_dir;
- }
-
f2fs_set_link(new_dir, new_entry, new_page, old_inode);
- new_inode->i_ctime = CURRENT_TIME;
+ new_inode->i_ctime = current_time(new_inode);
down_write(&F2FS_I(new_inode)->i_sem);
if (old_dir_entry)
- drop_nlink(new_inode);
- drop_nlink(new_inode);
+ f2fs_i_links_write(new_inode, false);
+ f2fs_i_links_write(new_inode, false);
up_write(&F2FS_I(new_inode)->i_sem);
- mark_inode_dirty(new_inode);
-
if (!new_inode->i_nlink)
- add_orphan_inode(sbi, new_inode->i_ino);
+ add_orphan_inode(new_inode);
else
release_orphan_inode(sbi);
-
- update_inode_page(old_inode);
- update_inode_page(new_inode);
} else {
+ f2fs_balance_fs(sbi, true);
+
f2fs_lock_op(sbi);
err = f2fs_add_link(new_dentry, old_inode);
if (err) {
f2fs_unlock_op(sbi);
- goto out_dir;
+ goto out_whiteout;
}
- if (old_dir_entry) {
- inc_nlink(new_dir);
- update_inode_page(new_dir);
+ if (old_dir_entry)
+ f2fs_i_links_write(new_dir, true);
+
+ /*
+ * old entry and new entry can locate in the same inline
+ * dentry in inode, when attaching new entry in inline dentry,
+ * it could force inline dentry conversion, after that,
+ * old_entry and old_page will point to wrong address, in
+ * order to avoid this, let's do the check and update here.
+ */
+ if (is_old_inline && !f2fs_has_inline_dentry(old_dir)) {
+ f2fs_put_page(old_page, 0);
+ old_page = NULL;
+
+ old_entry = f2fs_find_entry(old_dir,
+ &old_dentry->d_name, &old_page);
+ if (!old_entry) {
+ err = -ENOENT;
+ if (IS_ERR(old_page))
+ err = PTR_ERR(old_page);
+ f2fs_unlock_op(sbi);
+ goto out_dir;
+ }
}
}
@@ -432,39 +787,54 @@
file_lost_pino(old_inode);
up_write(&F2FS_I(old_inode)->i_sem);
- old_inode->i_ctime = CURRENT_TIME;
- mark_inode_dirty(old_inode);
+ old_inode->i_ctime = current_time(old_inode);
+ f2fs_mark_inode_dirty_sync(old_inode, false);
- f2fs_delete_entry(old_entry, old_page, NULL);
+ f2fs_delete_entry(old_entry, old_page, old_dir, NULL);
+
+ if (whiteout) {
+ whiteout->i_state |= I_LINKABLE;
+ set_inode_flag(whiteout, FI_INC_LINK);
+ err = f2fs_add_link(old_dentry, whiteout);
+ if (err)
+ goto put_out_dir;
+ whiteout->i_state &= ~I_LINKABLE;
+ iput(whiteout);
+ }
if (old_dir_entry) {
- if (old_dir != new_dir) {
+ if (old_dir != new_dir && !whiteout) {
f2fs_set_link(old_inode, old_dir_entry,
old_dir_page, new_dir);
- update_inode_page(old_inode);
} else {
- kunmap(old_dir_page);
+ f2fs_dentry_kunmap(old_inode, old_dir_page);
f2fs_put_page(old_dir_page, 0);
}
- drop_nlink(old_dir);
- mark_inode_dirty(old_dir);
- update_inode_page(old_dir);
+ f2fs_i_links_write(old_dir, false);
}
f2fs_unlock_op(sbi);
+
+ if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
+ f2fs_sync_fs(sbi->sb, 1);
return 0;
put_out_dir:
f2fs_unlock_op(sbi);
- kunmap(new_page);
- f2fs_put_page(new_page, 0);
+ if (new_page) {
+ f2fs_dentry_kunmap(new_dir, new_page);
+ f2fs_put_page(new_page, 0);
+ }
+out_whiteout:
+ if (whiteout)
+ iput(whiteout);
out_dir:
if (old_dir_entry) {
- kunmap(old_dir_page);
+ f2fs_dentry_kunmap(old_inode, old_dir_page);
f2fs_put_page(old_dir_page, 0);
}
out_old:
- kunmap(old_page);
+ f2fs_dentry_kunmap(old_dir, old_page);
f2fs_put_page(old_page, 0);
out:
return err;
@@ -474,8 +844,8 @@
struct inode *new_dir, struct dentry *new_dentry)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(old_dir);
- struct inode *old_inode = old_dentry->d_inode;
- struct inode *new_inode = new_dentry->d_inode;
+ struct inode *old_inode = d_inode(old_dentry);
+ struct inode *new_inode = d_inode(new_dentry);
struct page *old_dir_page, *new_dir_page;
struct page *old_page, *new_page;
struct f2fs_dir_entry *old_dir_entry = NULL, *new_dir_entry = NULL;
@@ -483,32 +853,52 @@
int old_nlink = 0, new_nlink = 0;
int err = -ENOENT;
- f2fs_balance_fs(sbi);
+ if ((f2fs_encrypted_inode(old_dir) &&
+ !fscrypt_has_encryption_key(old_dir)) ||
+ (f2fs_encrypted_inode(new_dir) &&
+ !fscrypt_has_encryption_key(new_dir)))
+ return -ENOKEY;
+
+ if ((f2fs_encrypted_inode(old_dir) || f2fs_encrypted_inode(new_dir)) &&
+ (old_dir != new_dir) &&
+ (!fscrypt_has_permitted_context(new_dir, old_inode) ||
+ !fscrypt_has_permitted_context(old_dir, new_inode)))
+ return -EPERM;
old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
- if (!old_entry)
+ if (!old_entry) {
+ if (IS_ERR(old_page))
+ err = PTR_ERR(old_page);
goto out;
+ }
new_entry = f2fs_find_entry(new_dir, &new_dentry->d_name, &new_page);
- if (!new_entry)
+ if (!new_entry) {
+ if (IS_ERR(new_page))
+ err = PTR_ERR(new_page);
goto out_old;
+ }
/* prepare for updating ".." directory entry info later */
if (old_dir != new_dir) {
if (S_ISDIR(old_inode->i_mode)) {
- err = -EIO;
old_dir_entry = f2fs_parent_dir(old_inode,
&old_dir_page);
- if (!old_dir_entry)
+ if (!old_dir_entry) {
+ if (IS_ERR(old_dir_page))
+ err = PTR_ERR(old_dir_page);
goto out_new;
+ }
}
if (S_ISDIR(new_inode->i_mode)) {
- err = -EIO;
new_dir_entry = f2fs_parent_dir(new_inode,
&new_dir_page);
- if (!new_dir_entry)
+ if (!new_dir_entry) {
+ if (IS_ERR(new_dir_page))
+ err = PTR_ERR(new_dir_page);
goto out_old_dir;
+ }
}
}
@@ -522,21 +912,15 @@
old_nlink = old_dir_entry ? -1 : 1;
new_nlink = -old_nlink;
err = -EMLINK;
- if ((old_nlink > 0 && old_inode->i_nlink >= F2FS_LINK_MAX) ||
- (new_nlink > 0 && new_inode->i_nlink >= F2FS_LINK_MAX))
+ if ((old_nlink > 0 && old_dir->i_nlink >= F2FS_LINK_MAX) ||
+ (new_nlink > 0 && new_dir->i_nlink >= F2FS_LINK_MAX))
goto out_new_dir;
}
+ f2fs_balance_fs(sbi, true);
+
f2fs_lock_op(sbi);
- err = update_dent_inode(old_inode, &new_dentry->d_name);
- if (err)
- goto out_unlock;
-
- err = update_dent_inode(new_inode, &old_dentry->d_name);
- if (err)
- goto out_undo;
-
/* update ".." directory entry info of old dentry */
if (old_dir_entry)
f2fs_set_link(old_inode, old_dir_entry, old_dir_page, new_dir);
@@ -552,19 +936,13 @@
file_lost_pino(old_inode);
up_write(&F2FS_I(old_inode)->i_sem);
- update_inode_page(old_inode);
-
old_dir->i_ctime = CURRENT_TIME;
if (old_nlink) {
down_write(&F2FS_I(old_dir)->i_sem);
- if (old_nlink < 0)
- drop_nlink(old_dir);
- else
- inc_nlink(old_dir);
+ f2fs_i_links_write(old_dir, old_nlink > 0);
up_write(&F2FS_I(old_dir)->i_sem);
}
- mark_inode_dirty(old_dir);
- update_inode_page(old_dir);
+ f2fs_mark_inode_dirty_sync(old_dir, false);
/* update directory entry info of new dir inode */
f2fs_set_link(new_dir, new_entry, new_page, old_inode);
@@ -573,42 +951,34 @@
file_lost_pino(new_inode);
up_write(&F2FS_I(new_inode)->i_sem);
- update_inode_page(new_inode);
-
new_dir->i_ctime = CURRENT_TIME;
if (new_nlink) {
down_write(&F2FS_I(new_dir)->i_sem);
- if (new_nlink < 0)
- drop_nlink(new_dir);
- else
- inc_nlink(new_dir);
+ f2fs_i_links_write(new_dir, new_nlink > 0);
up_write(&F2FS_I(new_dir)->i_sem);
}
- mark_inode_dirty(new_dir);
- update_inode_page(new_dir);
+ f2fs_mark_inode_dirty_sync(new_dir, false);
f2fs_unlock_op(sbi);
+
+ if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
+ f2fs_sync_fs(sbi->sb, 1);
return 0;
-out_undo:
- /* Still we may fail to recover name info of f2fs_inode here */
- update_dent_inode(old_inode, &old_dentry->d_name);
-out_unlock:
- f2fs_unlock_op(sbi);
out_new_dir:
if (new_dir_entry) {
- kunmap(new_dir_page);
+ f2fs_dentry_kunmap(new_inode, new_dir_page);
f2fs_put_page(new_dir_page, 0);
}
out_old_dir:
if (old_dir_entry) {
- kunmap(old_dir_page);
+ f2fs_dentry_kunmap(old_inode, old_dir_page);
f2fs_put_page(old_dir_page, 0);
}
out_new:
- kunmap(new_page);
+ f2fs_dentry_kunmap(new_dir, new_page);
f2fs_put_page(new_page, 0);
out_old:
- kunmap(old_page);
+ f2fs_dentry_kunmap(old_dir, old_page);
f2fs_put_page(old_page, 0);
out:
return err;
@@ -618,7 +988,7 @@
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
- if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
+ if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
return -EINVAL;
if (flags & RENAME_EXCHANGE) {
@@ -629,51 +999,90 @@
* VFS has already handled the new dentry existence case,
* here, we just deal with "RENAME_NOREPLACE" as regular rename.
*/
- return f2fs_rename(old_dir, old_dentry, new_dir, new_dentry);
+ return f2fs_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
}
-static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
+static void *f2fs_encrypted_follow_link(struct dentry *dentry,
+ struct nameidata *nd)
{
- struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
- struct inode *inode;
- int err;
+ struct page *cpage = NULL;
+ char *caddr, *paddr = NULL;
+ struct fscrypt_str cstr = FSTR_INIT(NULL, 0);
+ struct fscrypt_str pstr = FSTR_INIT(NULL, 0);
+ struct fscrypt_symlink_data *sd;
+ struct inode *inode = d_inode(dentry);
+ u32 max_size = inode->i_sb->s_blocksize;
+ int res;
- inode = f2fs_new_inode(dir, mode);
- if (IS_ERR(inode))
- return PTR_ERR(inode);
+ res = fscrypt_get_encryption_info(inode);
+ if (res)
+ return ERR_PTR(res);
- inode->i_op = &f2fs_file_inode_operations;
- inode->i_fop = &f2fs_file_operations;
- inode->i_mapping->a_ops = &f2fs_dblock_aops;
+ cpage = read_mapping_page(inode->i_mapping, 0, NULL);
+ if (IS_ERR(cpage))
+ return ERR_CAST(cpage);
+ caddr = kmap(cpage);
- f2fs_lock_op(sbi);
- err = acquire_orphan_inode(sbi);
- if (err)
- goto out;
+ /* Symlink is encrypted */
+ sd = (struct fscrypt_symlink_data *)caddr;
+ cstr.name = sd->encrypted_path;
+ cstr.len = le16_to_cpu(sd->len);
- err = f2fs_do_tmpfile(inode, dir);
- if (err)
- goto release_out;
+ /* this is broken symlink case */
+ if (unlikely(cstr.len == 0)) {
+ res = -ENOENT;
+ goto errout;
+ }
- /*
- * add this non-linked tmpfile to orphan list, in this way we could
- * remove all unused data of tmpfile after abnormal power-off.
- */
- add_orphan_inode(sbi, inode->i_ino);
- f2fs_unlock_op(sbi);
+ if ((cstr.len + sizeof(struct fscrypt_symlink_data) - 1) > max_size) {
+ /* Symlink data on the disk is corrupted */
+ res = -EIO;
+ goto errout;
+ }
+ res = fscrypt_fname_alloc_buffer(inode, cstr.len, &pstr);
+ if (res)
+ goto errout;
- alloc_nid_done(sbi, inode->i_ino);
- d_tmpfile(dentry, inode);
- unlock_new_inode(inode);
- return 0;
+ res = fscrypt_fname_disk_to_usr(inode, 0, 0, &cstr, &pstr);
+ if (res)
+ goto errout;
-release_out:
- release_orphan_inode(sbi);
-out:
- handle_failed_inode(inode);
- return err;
+ /* this is broken symlink case */
+ if (unlikely(pstr.name[0] == 0)) {
+ res = -ENOENT;
+ goto errout;
+ }
+
+ paddr = pstr.name;
+
+ /* Null-terminate the name */
+ paddr[pstr.len] = '\0';
+ nd_set_link(nd, paddr);
+
+ kunmap(cpage);
+ page_cache_release(cpage);
+ return NULL;
+errout:
+ fscrypt_fname_free_buffer(&pstr);
+ kunmap(cpage);
+ page_cache_release(cpage);
+ return ERR_PTR(res);
}
+const struct inode_operations f2fs_encrypted_symlink_inode_operations = {
+ .readlink = generic_readlink,
+ .follow_link = f2fs_encrypted_follow_link,
+ .put_link = kfree_put_link,
+ .getattr = f2fs_getattr,
+ .setattr = f2fs_setattr,
+#ifdef CONFIG_F2FS_FS_XATTR
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
+ .listxattr = f2fs_listxattr,
+ .removexattr = generic_removexattr,
+#endif
+};
+
const struct inode_operations f2fs_dir_inode_operations = {
.create = f2fs_create,
.lookup = f2fs_lookup,
@@ -699,7 +1108,7 @@
const struct inode_operations f2fs_symlink_inode_operations = {
.readlink = generic_readlink,
- .follow_link = page_follow_link_light,
+ .follow_link = f2fs_follow_link,
.put_link = page_put_link,
.getattr = f2fs_getattr,
.setattr = f2fs_setattr,
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 44b8afe..b06e270 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -19,9 +19,10 @@
#include "f2fs.h"
#include "node.h"
#include "segment.h"
+#include "trace.h"
#include <trace/events/f2fs.h>
-#define on_build_free_nids(nmi) mutex_is_locked(&nm_i->build_lock)
+#define on_build_free_nids(nmi) mutex_is_locked(&(nm_i)->build_lock)
static struct kmem_cache *nat_entry_slab;
static struct kmem_cache *free_nid_slab;
@@ -31,22 +32,50 @@
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct sysinfo val;
+ unsigned long avail_ram;
unsigned long mem_size = 0;
bool res = false;
si_meminfo(&val);
- /* give 25%, 25%, 50% memory for each components respectively */
+
+ /* only uses low memory */
+ avail_ram = val.totalram - val.totalhigh;
+
+ /*
+ * give 25%, 25%, 50%, 50%, 50% memory for each components respectively
+ */
if (type == FREE_NIDS) {
- mem_size = (nm_i->fcnt * sizeof(struct free_nid)) >> 12;
- res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 2);
+ mem_size = (nm_i->nid_cnt[FREE_NID_LIST] *
+ sizeof(struct free_nid)) >> PAGE_SHIFT;
+ res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
} else if (type == NAT_ENTRIES) {
- mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >> 12;
- res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 2);
+ mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >>
+ PAGE_SHIFT;
+ res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2);
+ if (excess_cached_nats(sbi))
+ res = false;
} else if (type == DIRTY_DENTS) {
if (sbi->sb->s_bdi->dirty_exceeded)
return false;
mem_size = get_pages(sbi, F2FS_DIRTY_DENTS);
- res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 1);
+ res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
+ } else if (type == INO_ENTRIES) {
+ int i;
+
+ for (i = 0; i <= UPDATE_INO; i++)
+ mem_size += sbi->im[i].ino_num *
+ sizeof(struct ino_entry);
+ mem_size >>= PAGE_SHIFT;
+ res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
+ } else if (type == EXTENT_CACHE) {
+ mem_size = (atomic_read(&sbi->total_ext_tree) *
+ sizeof(struct extent_tree) +
+ atomic_read(&sbi->total_ext_node) *
+ sizeof(struct extent_node)) >> PAGE_SHIFT;
+ res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
+ } else {
+ if (!sbi->sb->s_bdi->dirty_exceeded)
+ return true;
}
return res;
}
@@ -95,7 +124,7 @@
src_addr = page_address(src_page);
dst_addr = page_address(dst_page);
- memcpy(dst_addr, src_addr, PAGE_CACHE_SIZE);
+ memcpy(dst_addr, src_addr, PAGE_SIZE);
set_page_dirty(dst_page);
f2fs_put_page(src_page, 1);
@@ -131,20 +160,16 @@
if (get_nat_flag(ne, IS_DIRTY))
return;
-retry:
+
head = radix_tree_lookup(&nm_i->nat_set_root, set);
if (!head) {
- head = f2fs_kmem_cache_alloc(nat_entry_set_slab, GFP_ATOMIC);
+ head = f2fs_kmem_cache_alloc(nat_entry_set_slab, GFP_NOFS);
INIT_LIST_HEAD(&head->entry_list);
INIT_LIST_HEAD(&head->set_list);
head->set = set;
head->entry_cnt = 0;
-
- if (radix_tree_insert(&nm_i->nat_set_root, set, head)) {
- cond_resched();
- goto retry;
- }
+ f2fs_radix_tree_insert(&nm_i->nat_set_root, set, head);
}
list_move_tail(&ne->list, &head->entry_list);
nm_i->dirty_nat_cnt++;
@@ -153,18 +178,12 @@
}
static void __clear_nat_cache_dirty(struct f2fs_nm_info *nm_i,
- struct nat_entry *ne)
+ struct nat_entry_set *set, struct nat_entry *ne)
{
- nid_t set = ne->ni.nid / NAT_ENTRY_PER_BLOCK;
- struct nat_entry_set *head;
-
- head = radix_tree_lookup(&nm_i->nat_set_root, set);
- if (head) {
- list_move_tail(&ne->list, &nm_i->nat_entries);
- set_nat_flag(ne, IS_DIRTY, false);
- head->entry_cnt--;
- nm_i->dirty_nat_cnt--;
- }
+ list_move_tail(&ne->list, &nm_i->nat_entries);
+ set_nat_flag(ne, IS_DIRTY, false);
+ set->entry_cnt--;
+ nm_i->dirty_nat_cnt--;
}
static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i,
@@ -174,61 +193,71 @@
start, nr);
}
+int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ struct nat_entry *e;
+ bool need = false;
+
+ down_read(&nm_i->nat_tree_lock);
+ e = __lookup_nat_cache(nm_i, nid);
+ if (e) {
+ if (!get_nat_flag(e, IS_CHECKPOINTED) &&
+ !get_nat_flag(e, HAS_FSYNCED_INODE))
+ need = true;
+ }
+ up_read(&nm_i->nat_tree_lock);
+ return need;
+}
+
bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
bool is_cp = true;
- read_lock(&nm_i->nat_tree_lock);
+ down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
if (e && !get_nat_flag(e, IS_CHECKPOINTED))
is_cp = false;
- read_unlock(&nm_i->nat_tree_lock);
+ up_read(&nm_i->nat_tree_lock);
return is_cp;
}
-bool has_fsynced_inode(struct f2fs_sb_info *sbi, nid_t ino)
-{
- struct f2fs_nm_info *nm_i = NM_I(sbi);
- struct nat_entry *e;
- bool fsynced = false;
-
- read_lock(&nm_i->nat_tree_lock);
- e = __lookup_nat_cache(nm_i, ino);
- if (e && get_nat_flag(e, HAS_FSYNCED_INODE))
- fsynced = true;
- read_unlock(&nm_i->nat_tree_lock);
- return fsynced;
-}
-
bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
bool need_update = true;
- read_lock(&nm_i->nat_tree_lock);
+ down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, ino);
if (e && get_nat_flag(e, HAS_LAST_FSYNC) &&
(get_nat_flag(e, IS_CHECKPOINTED) ||
get_nat_flag(e, HAS_FSYNCED_INODE)))
need_update = false;
- read_unlock(&nm_i->nat_tree_lock);
+ up_read(&nm_i->nat_tree_lock);
return need_update;
}
-static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid)
+static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid,
+ bool no_fail)
{
struct nat_entry *new;
- new = kmem_cache_alloc(nat_entry_slab, GFP_ATOMIC);
- if (!new)
- return NULL;
- if (radix_tree_insert(&nm_i->nat_root, nid, new)) {
- kmem_cache_free(nat_entry_slab, new);
- return NULL;
+ if (no_fail) {
+ new = f2fs_kmem_cache_alloc(nat_entry_slab, GFP_NOFS);
+ f2fs_radix_tree_insert(&nm_i->nat_root, nid, new);
+ } else {
+ new = kmem_cache_alloc(nat_entry_slab, GFP_NOFS);
+ if (!new)
+ return NULL;
+ if (radix_tree_insert(&nm_i->nat_root, nid, new)) {
+ kmem_cache_free(nat_entry_slab, new);
+ return NULL;
+ }
}
+
memset(new, 0, sizeof(struct nat_entry));
nat_set_nid(new, nid);
nat_reset_flag(new);
@@ -237,22 +266,23 @@
return new;
}
-static void cache_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid,
+static void cache_nat_entry(struct f2fs_sb_info *sbi, nid_t nid,
struct f2fs_nat_entry *ne)
{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
-retry:
- write_lock(&nm_i->nat_tree_lock);
+
e = __lookup_nat_cache(nm_i, nid);
if (!e) {
- e = grab_nat_entry(nm_i, nid);
- if (!e) {
- write_unlock(&nm_i->nat_tree_lock);
- goto retry;
- }
- node_info_from_raw_nat(&e->ni, ne);
+ e = grab_nat_entry(nm_i, nid, false);
+ if (e)
+ node_info_from_raw_nat(&e->ni, ne);
+ } else {
+ f2fs_bug_on(sbi, nat_get_ino(e) != le32_to_cpu(ne->ino) ||
+ nat_get_blkaddr(e) !=
+ le32_to_cpu(ne->block_addr) ||
+ nat_get_version(e) != ne->version);
}
- write_unlock(&nm_i->nat_tree_lock);
}
static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
@@ -260,16 +290,12 @@
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
-retry:
- write_lock(&nm_i->nat_tree_lock);
+
+ down_write(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, ni->nid);
if (!e) {
- e = grab_nat_entry(nm_i, ni->nid);
- if (!e) {
- write_unlock(&nm_i->nat_tree_lock);
- goto retry;
- }
- e->ni = *ni;
+ e = grab_nat_entry(nm_i, ni->nid, true);
+ copy_node_info(&e->ni, ni);
f2fs_bug_on(sbi, ni->blk_addr == NEW_ADDR);
} else if (new_blkaddr == NEW_ADDR) {
/*
@@ -277,7 +303,7 @@
* previous nat entry can be remained in nat cache.
* So, reinitialize it with new information.
*/
- e->ni = *ni;
+ copy_node_info(&e->ni, ni);
f2fs_bug_on(sbi, ni->blk_addr != NULL_ADDR);
}
@@ -295,6 +321,10 @@
if (nat_get_blkaddr(e) != NEW_ADDR && new_blkaddr == NULL_ADDR) {
unsigned char version = nat_get_version(e);
nat_set_version(e, inc_node_version(version));
+
+ /* in order to reuse the nid */
+ if (nm_i->next_scan_nid > ni->nid)
+ nm_i->next_scan_nid = ni->nid;
}
/* change address */
@@ -304,23 +334,24 @@
__set_nat_cache_dirty(nm_i, e);
/* update fsync_mark if its inode nat entry is still alive */
- e = __lookup_nat_cache(nm_i, ni->ino);
+ if (ni->nid != ni->ino)
+ e = __lookup_nat_cache(nm_i, ni->ino);
if (e) {
if (fsync_done && ni->nid == ni->ino)
set_nat_flag(e, HAS_FSYNCED_INODE, true);
set_nat_flag(e, HAS_LAST_FSYNC, fsync_done);
}
- write_unlock(&nm_i->nat_tree_lock);
+ up_write(&nm_i->nat_tree_lock);
}
int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
+ int nr = nr_shrink;
- if (available_free_memory(sbi, NAT_ENTRIES))
+ if (!down_write_trylock(&nm_i->nat_tree_lock))
return 0;
- write_lock(&nm_i->nat_tree_lock);
while (nr_shrink && !list_empty(&nm_i->nat_entries)) {
struct nat_entry *ne;
ne = list_first_entry(&nm_i->nat_entries,
@@ -328,8 +359,8 @@
__del_from_nat_cache(nm_i, ne);
nr_shrink--;
}
- write_unlock(&nm_i->nat_tree_lock);
- return nr_shrink;
+ up_write(&nm_i->nat_tree_lock);
+ return nr - nr_shrink;
}
/*
@@ -339,59 +370,121 @@
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
- struct f2fs_summary_block *sum = curseg->sum_blk;
+ struct f2fs_journal *journal = curseg->journal;
nid_t start_nid = START_NID(nid);
struct f2fs_nat_block *nat_blk;
struct page *page = NULL;
struct f2fs_nat_entry ne;
struct nat_entry *e;
+ pgoff_t index;
int i;
- memset(&ne, 0, sizeof(struct f2fs_nat_entry));
ni->nid = nid;
/* Check nat cache */
- read_lock(&nm_i->nat_tree_lock);
+ down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
if (e) {
ni->ino = nat_get_ino(e);
ni->blk_addr = nat_get_blkaddr(e);
ni->version = nat_get_version(e);
- }
- read_unlock(&nm_i->nat_tree_lock);
- if (e)
+ up_read(&nm_i->nat_tree_lock);
return;
+ }
+
+ memset(&ne, 0, sizeof(struct f2fs_nat_entry));
/* Check current segment summary */
- mutex_lock(&curseg->curseg_mutex);
- i = lookup_journal_in_cursum(sum, NAT_JOURNAL, nid, 0);
+ down_read(&curseg->journal_rwsem);
+ i = lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 0);
if (i >= 0) {
- ne = nat_in_journal(sum, i);
+ ne = nat_in_journal(journal, i);
node_info_from_raw_nat(ni, &ne);
}
- mutex_unlock(&curseg->curseg_mutex);
- if (i >= 0)
+ up_read(&curseg->journal_rwsem);
+ if (i >= 0) {
+ up_read(&nm_i->nat_tree_lock);
goto cache;
+ }
/* Fill node_info from nat page */
- page = get_current_nat_page(sbi, start_nid);
+ index = current_nat_addr(sbi, nid);
+ up_read(&nm_i->nat_tree_lock);
+
+ page = get_meta_page(sbi, index);
nat_blk = (struct f2fs_nat_block *)page_address(page);
ne = nat_blk->entries[nid - start_nid];
node_info_from_raw_nat(ni, &ne);
f2fs_put_page(page, 1);
cache:
/* cache nat entry */
- cache_nat_entry(NM_I(sbi), nid, &ne);
+ down_write(&nm_i->nat_tree_lock);
+ cache_nat_entry(sbi, nid, &ne);
+ up_write(&nm_i->nat_tree_lock);
+}
+
+/*
+ * readahead MAX_RA_NODE number of node pages.
+ */
+static void ra_node_pages(struct page *parent, int start, int n)
+{
+ struct f2fs_sb_info *sbi = F2FS_P_SB(parent);
+ struct blk_plug plug;
+ int i, end;
+ nid_t nid;
+
+ blk_start_plug(&plug);
+
+ /* Then, try readahead for siblings of the desired node */
+ end = start + n;
+ end = min(end, NIDS_PER_BLOCK);
+ for (i = start; i < end; i++) {
+ nid = get_nid(parent, i, false);
+ ra_node_page(sbi, nid);
+ }
+
+ blk_finish_plug(&plug);
+}
+
+pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs)
+{
+ const long direct_index = ADDRS_PER_INODE(dn->inode);
+ const long direct_blks = ADDRS_PER_BLOCK;
+ const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK;
+ unsigned int skipped_unit = ADDRS_PER_BLOCK;
+ int cur_level = dn->cur_level;
+ int max_level = dn->max_level;
+ pgoff_t base = 0;
+
+ if (!dn->max_level)
+ return pgofs + 1;
+
+ while (max_level-- > cur_level)
+ skipped_unit *= NIDS_PER_BLOCK;
+
+ switch (dn->max_level) {
+ case 3:
+ base += 2 * indirect_blks;
+ case 2:
+ base += 2 * direct_blks;
+ case 1:
+ base += direct_index;
+ break;
+ default:
+ f2fs_bug_on(F2FS_I_SB(dn->inode), 1);
+ }
+
+ return ((pgofs - base) / skipped_unit + 1) * skipped_unit + base;
}
/*
* The maximum depth is four.
* Offset[0] will have raw inode offset.
*/
-static int get_node_path(struct f2fs_inode_info *fi, long block,
+static int get_node_path(struct inode *inode, long block,
int offset[4], unsigned int noffset[4])
{
- const long direct_index = ADDRS_PER_INODE(fi);
+ const long direct_index = ADDRS_PER_INODE(inode);
const long direct_blks = ADDRS_PER_BLOCK;
const long dptrs_per_blk = NIDS_PER_BLOCK;
const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK;
@@ -472,14 +565,14 @@
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
struct page *npage[4];
- struct page *parent;
+ struct page *parent = NULL;
int offset[4];
unsigned int noffset[4];
nid_t nids[4];
- int level, i;
+ int level, i = 0;
int err = 0;
- level = get_node_path(F2FS_I(dn->inode), index, offset, noffset);
+ level = get_node_path(dn->inode, index, offset, noffset);
nids[0] = dn->inode->i_ino;
npage[0] = dn->inode_page;
@@ -489,6 +582,14 @@
if (IS_ERR(npage[0]))
return PTR_ERR(npage[0]);
}
+
+ /* if inline_data is set, should not report any block indices */
+ if (f2fs_has_inline_data(dn->inode) && index) {
+ err = -ENOENT;
+ f2fs_put_page(npage[0], 1);
+ goto release_out;
+ }
+
parent = npage[0];
if (level != 0)
nids[1] = get_nid(parent, offset[0], true);
@@ -558,6 +659,11 @@
release_out:
dn->inode_page = NULL;
dn->node_page = NULL;
+ if (err == -ENOENT) {
+ dn->cur_level = i;
+ dn->max_level = level;
+ dn->ofs_in_node = offset[level];
+ }
return err;
}
@@ -581,12 +687,11 @@
if (dn->nid == dn->inode->i_ino) {
remove_orphan_inode(sbi, dn->nid);
dec_valid_inode_count(sbi);
- } else {
- sync_inode_page(dn);
+ f2fs_inode_synced(dn->inode);
}
invalidate:
clear_node_page_dirty(dn->node_page);
- F2FS_SET_SB_DIRT(sbi);
+ set_sbi_flag(sbi, SBI_IS_DIRTY);
f2fs_put_page(dn->node_page, 1);
@@ -641,6 +746,8 @@
return PTR_ERR(page);
}
+ ra_node_pages(page, ofs, NIDS_PER_BLOCK);
+
rn = F2FS_NODE(page);
if (depth < 3) {
for (i = ofs; i < NIDS_PER_BLOCK; i++, freed++) {
@@ -651,7 +758,8 @@
ret = truncate_dnode(&rdn);
if (ret < 0)
goto out_err;
- set_nid(page, i, 0, false);
+ if (set_nid(page, i, 0, false))
+ dn->node_changed = true;
}
} else {
child_nofs = nofs + ofs * (NIDS_PER_BLOCK + 1) + 1;
@@ -664,7 +772,8 @@
rdn.nid = child_nid;
ret = truncate_nodes(&rdn, child_nofs, 0, depth - 1);
if (ret == (NIDS_PER_BLOCK + 1)) {
- set_nid(page, i, 0, false);
+ if (set_nid(page, i, 0, false))
+ dn->node_changed = true;
child_nofs += ret;
} else if (ret < 0 && ret != -ENOENT) {
goto out_err;
@@ -716,6 +825,8 @@
nid[i + 1] = get_nid(pages[i], offset[i + 1], false);
}
+ ra_node_pages(pages[idx], offset[idx + 1], NIDS_PER_BLOCK);
+
/* free direct nodes linked to a partial indirect node */
for (i = offset[idx + 1]; i < NIDS_PER_BLOCK; i++) {
child_nid = get_nid(pages[idx], i, false);
@@ -725,7 +836,8 @@
err = truncate_dnode(dn);
if (err < 0)
goto fail;
- set_nid(pages[idx], i, 0, false);
+ if (set_nid(pages[idx], i, 0, false))
+ dn->node_changed = true;
}
if (offset[idx + 1] == 0) {
@@ -762,8 +874,8 @@
trace_f2fs_truncate_inode_blocks_enter(inode, from);
- level = get_node_path(F2FS_I(inode), from, offset, noffset);
-restart:
+ level = get_node_path(inode, from, offset, noffset);
+
page = get_node_page(sbi, inode->i_ino);
if (IS_ERR(page)) {
trace_f2fs_truncate_inode_blocks_exit(inode, PTR_ERR(page));
@@ -827,11 +939,8 @@
if (offset[1] == 0 &&
ri->i_nid[offset[0] - NODE_DIR1_BLOCK]) {
lock_page(page);
- if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
- f2fs_put_page(page, 1);
- goto restart;
- }
- f2fs_wait_on_page_writeback(page, NODE);
+ BUG_ON(page->mapping != NODE_MAPPING(sbi));
+ f2fs_wait_on_page_writeback(page, NODE, true);
ri->i_nid[offset[0] - NODE_DIR1_BLOCK] = 0;
set_page_dirty(page);
unlock_page(page);
@@ -860,10 +969,7 @@
if (IS_ERR(npage))
return PTR_ERR(npage);
- F2FS_I(inode)->i_xattr_nid = 0;
-
- /* need to do checkpoint during fsync */
- F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi));
+ f2fs_i_xnid_write(inode, 0);
set_new_dnode(&dn, inode, page, npage, nid);
@@ -877,17 +983,20 @@
* Caller should grab and release a rwsem by calling f2fs_lock_op() and
* f2fs_unlock_op().
*/
-void remove_inode_page(struct inode *inode)
+int remove_inode_page(struct inode *inode)
{
struct dnode_of_data dn;
+ int err;
set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino);
- if (get_dnode_of_data(&dn, 0, LOOKUP_NODE))
- return;
+ err = get_dnode_of_data(&dn, 0, LOOKUP_NODE);
+ if (err)
+ return err;
- if (truncate_xattr_node(inode, dn.inode_page)) {
+ err = truncate_xattr_node(inode, dn.inode_page);
+ if (err) {
f2fs_put_dnode(&dn);
- return;
+ return err;
}
/* remove potential inline_data blocks */
@@ -901,6 +1010,7 @@
/* will put inode & node pages */
truncate_node(&dn);
+ return 0;
}
struct page *new_inode_page(struct inode *inode)
@@ -918,14 +1028,14 @@
unsigned int ofs, struct page *ipage)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
- struct node_info old_ni, new_ni;
+ struct node_info new_ni;
struct page *page;
int err;
- if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
+ if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
return ERR_PTR(-EPERM);
- page = grab_cache_page(NODE_MAPPING(sbi), dn->nid);
+ page = f2fs_grab_cache_page(NODE_MAPPING(sbi), dn->nid, false);
if (!page)
return ERR_PTR(-ENOMEM);
@@ -933,32 +1043,30 @@
err = -ENOSPC;
goto fail;
}
-
- get_node_info(sbi, dn->nid, &old_ni);
-
- /* Reinitialize old_ni with new node page */
- f2fs_bug_on(sbi, old_ni.blk_addr != NULL_ADDR);
- new_ni = old_ni;
+#ifdef CONFIG_F2FS_CHECK_FS
+ get_node_info(sbi, dn->nid, &new_ni);
+ f2fs_bug_on(sbi, new_ni.blk_addr != NULL_ADDR);
+#endif
+ new_ni.nid = dn->nid;
new_ni.ino = dn->inode->i_ino;
+ new_ni.blk_addr = NULL_ADDR;
+ new_ni.flag = 0;
+ new_ni.version = 0;
set_node_addr(sbi, &new_ni, NEW_ADDR, false);
- f2fs_wait_on_page_writeback(page, NODE);
+ f2fs_wait_on_page_writeback(page, NODE, true);
fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true);
set_cold_node(dn->inode, page);
- SetPageUptodate(page);
- set_page_dirty(page);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
+ if (set_page_dirty(page))
+ dn->node_changed = true;
if (f2fs_has_xattr_block(ofs))
- F2FS_I(dn->inode)->i_xattr_nid = dn->nid;
+ f2fs_i_xnid_write(dn->inode, dn->nid);
- dn->node_page = page;
- if (ipage)
- update_inode(dn->inode, ipage);
- else
- sync_inode_page(dn);
if (ofs == 0)
inc_valid_inode_count(sbi);
-
return page;
fail:
@@ -970,25 +1078,33 @@
/*
* Caller should do after getting the following values.
* 0: f2fs_put_page(page, 0)
- * LOCKED_PAGE: f2fs_put_page(page, 1)
- * error: nothing
+ * LOCKED_PAGE or error: f2fs_put_page(page, 1)
*/
-static int read_node_page(struct page *page, int rw)
+static int read_node_page(struct page *page, int op_flags)
{
struct f2fs_sb_info *sbi = F2FS_P_SB(page);
struct node_info ni;
-
- get_node_info(sbi, page->index, &ni);
-
- if (unlikely(ni.blk_addr == NULL_ADDR)) {
- f2fs_put_page(page, 1);
- return -ENOENT;
- }
+ struct f2fs_io_info fio = {
+ .sbi = sbi,
+ .type = NODE,
+ .op = REQ_OP_READ,
+ .op_flags = op_flags,
+ .page = page,
+ .encrypted_page = NULL,
+ };
if (PageUptodate(page))
return LOCKED_PAGE;
- return f2fs_submit_page_bio(sbi, page, ni.blk_addr, rw);
+ get_node_info(sbi, page->index, &ni);
+
+ if (unlikely(ni.blk_addr == NULL_ADDR)) {
+ ClearPageUptodate(page);
+ return -ENOENT;
+ }
+
+ fio.new_blkaddr = fio.old_blkaddr = ni.blk_addr;
+ return f2fs_submit_page_bio(&fio);
}
/*
@@ -999,134 +1115,163 @@
struct page *apage;
int err;
- apage = find_get_page(NODE_MAPPING(sbi), nid);
- if (apage && PageUptodate(apage)) {
- f2fs_put_page(apage, 0);
+ if (!nid)
return;
- }
- f2fs_put_page(apage, 0);
+ f2fs_bug_on(sbi, check_nid_range(sbi, nid));
- apage = grab_cache_page(NODE_MAPPING(sbi), nid);
+ rcu_read_lock();
+ apage = radix_tree_lookup(&NODE_MAPPING(sbi)->page_tree, nid);
+ rcu_read_unlock();
+ if (apage)
+ return;
+
+ apage = f2fs_grab_cache_page(NODE_MAPPING(sbi), nid, false);
if (!apage)
return;
- err = read_node_page(apage, READA);
- if (err == 0)
- f2fs_put_page(apage, 0);
- else if (err == LOCKED_PAGE)
- f2fs_put_page(apage, 1);
+ err = read_node_page(apage, REQ_RAHEAD);
+ f2fs_put_page(apage, err ? 1 : 0);
+}
+
+static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid,
+ struct page *parent, int start)
+{
+ struct page *page;
+ int err;
+
+ if (!nid)
+ return ERR_PTR(-ENOENT);
+ f2fs_bug_on(sbi, check_nid_range(sbi, nid));
+repeat:
+ page = f2fs_grab_cache_page(NODE_MAPPING(sbi), nid, false);
+ if (!page)
+ return ERR_PTR(-ENOMEM);
+
+ err = read_node_page(page, 0);
+ if (err < 0) {
+ f2fs_put_page(page, 1);
+ return ERR_PTR(err);
+ } else if (err == LOCKED_PAGE) {
+ goto page_hit;
+ }
+
+ if (parent)
+ ra_node_pages(parent, start + 1, MAX_RA_NODE);
+
+ lock_page(page);
+
+ if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
+ f2fs_put_page(page, 1);
+ goto repeat;
+ }
+
+ if (unlikely(!PageUptodate(page)))
+ goto out_err;
+page_hit:
+ if(unlikely(nid != nid_of_node(page))) {
+ f2fs_bug_on(sbi, 1);
+ ClearPageUptodate(page);
+out_err:
+ f2fs_put_page(page, 1);
+ return ERR_PTR(-EIO);
+ }
+ mark_page_accessed(page);
+ return page;
}
struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid)
{
- struct page *page;
- int err;
-repeat:
- page = grab_cache_page(NODE_MAPPING(sbi), nid);
- if (!page)
- return ERR_PTR(-ENOMEM);
-
- err = read_node_page(page, READ_SYNC);
- if (err < 0)
- return ERR_PTR(err);
- else if (err == LOCKED_PAGE)
- goto got_it;
-
- lock_page(page);
- if (unlikely(!PageUptodate(page) || nid != nid_of_node(page))) {
- f2fs_put_page(page, 1);
- return ERR_PTR(-EIO);
- }
- if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
- f2fs_put_page(page, 1);
- goto repeat;
- }
-got_it:
- return page;
+ return __get_node_page(sbi, nid, NULL, 0);
}
-/*
- * Return a locked page for the desired node page.
- * And, readahead MAX_RA_NODE number of node pages.
- */
struct page *get_node_page_ra(struct page *parent, int start)
{
struct f2fs_sb_info *sbi = F2FS_P_SB(parent);
- struct blk_plug plug;
- struct page *page;
- int err, i, end;
- nid_t nid;
+ nid_t nid = get_nid(parent, start, false);
- /* First, try getting the desired direct node. */
- nid = get_nid(parent, start, false);
- if (!nid)
- return ERR_PTR(-ENOENT);
-repeat:
- page = grab_cache_page(NODE_MAPPING(sbi), nid);
- if (!page)
- return ERR_PTR(-ENOMEM);
-
- err = read_node_page(page, READ_SYNC);
- if (err < 0)
- return ERR_PTR(err);
- else if (err == LOCKED_PAGE)
- goto page_hit;
-
- blk_start_plug(&plug);
-
- /* Then, try readahead for siblings of the desired node */
- end = start + MAX_RA_NODE;
- end = min(end, NIDS_PER_BLOCK);
- for (i = start + 1; i < end; i++) {
- nid = get_nid(parent, i, false);
- if (!nid)
- continue;
- ra_node_page(sbi, nid);
- }
-
- blk_finish_plug(&plug);
-
- lock_page(page);
- if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
- f2fs_put_page(page, 1);
- goto repeat;
- }
-page_hit:
- if (unlikely(!PageUptodate(page))) {
- f2fs_put_page(page, 1);
- return ERR_PTR(-EIO);
- }
- return page;
+ return __get_node_page(sbi, nid, parent, start);
}
-void sync_inode_page(struct dnode_of_data *dn)
+static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino)
{
- if (IS_INODE(dn->node_page) || dn->inode_page == dn->node_page) {
- update_inode(dn->inode, dn->node_page);
- } else if (dn->inode_page) {
- if (!dn->inode_page_locked)
- lock_page(dn->inode_page);
- update_inode(dn->inode, dn->inode_page);
- if (!dn->inode_page_locked)
- unlock_page(dn->inode_page);
- } else {
- update_inode_page(dn->inode);
- }
+ struct inode *inode;
+ struct page *page;
+ int ret;
+
+ /* should flush inline_data before evict_inode */
+ inode = ilookup(sbi->sb, ino);
+ if (!inode)
+ return;
+
+ page = find_get_page(inode->i_mapping, 0);
+ if (!page)
+ goto iput_out;
+
+ if (!trylock_page(page))
+ goto release_out;
+
+ if (!PageUptodate(page))
+ goto page_out;
+
+ if (!PageDirty(page))
+ goto page_out;
+
+ if (!clear_page_dirty_for_io(page))
+ goto page_out;
+
+ ret = f2fs_write_inline_data(inode, page);
+ inode_dec_dirty_pages(inode);
+ remove_dirty_inode(inode);
+ if (ret)
+ set_page_dirty(page);
+page_out:
+ unlock_page(page);
+release_out:
+ f2fs_put_page(page, 0);
+iput_out:
+ iput(inode);
}
-int sync_node_pages(struct f2fs_sb_info *sbi, nid_t ino,
- struct writeback_control *wbc)
+void move_node_page(struct page *node_page, int gc_type)
+{
+ if (gc_type == FG_GC) {
+ struct f2fs_sb_info *sbi = F2FS_P_SB(node_page);
+ struct writeback_control wbc = {
+ .sync_mode = WB_SYNC_ALL,
+ .nr_to_write = 1,
+ .for_reclaim = 0,
+ };
+
+ set_page_dirty(node_page);
+ f2fs_wait_on_page_writeback(node_page, NODE, true);
+
+ f2fs_bug_on(sbi, PageWriteback(node_page));
+ if (!clear_page_dirty_for_io(node_page))
+ goto out_page;
+
+ if (NODE_MAPPING(sbi)->a_ops->writepage(node_page, &wbc))
+ unlock_page(node_page);
+ goto release_page;
+ } else {
+ /* set page dirty and write it */
+ if (!PageWriteback(node_page))
+ set_page_dirty(node_page);
+ }
+out_page:
+ unlock_page(node_page);
+release_page:
+ f2fs_put_page(node_page, 0);
+}
+
+static struct page *last_fsync_dnode(struct f2fs_sb_info *sbi, nid_t ino)
{
pgoff_t index, end;
struct pagevec pvec;
- int step = ino ? 2 : 0;
- int nwritten = 0, wrote = 0;
+ struct page *last_page = NULL;
pagevec_init(&pvec, 0);
-
-next_step:
index = 0;
- end = LONG_MAX;
+ end = ULONG_MAX;
while (index <= end) {
int i, nr_pages;
@@ -1139,6 +1284,283 @@
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
+ if (unlikely(f2fs_cp_error(sbi))) {
+ f2fs_put_page(last_page, 0);
+ pagevec_release(&pvec);
+ return ERR_PTR(-EIO);
+ }
+
+ if (!IS_DNODE(page) || !is_cold_node(page))
+ continue;
+ if (ino_of_node(page) != ino)
+ continue;
+
+ lock_page(page);
+
+ if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
+continue_unlock:
+ unlock_page(page);
+ continue;
+ }
+ if (ino_of_node(page) != ino)
+ goto continue_unlock;
+
+ if (!PageDirty(page)) {
+ /* someone wrote it for us */
+ goto continue_unlock;
+ }
+
+ if (last_page)
+ f2fs_put_page(last_page, 0);
+
+ get_page(page);
+ last_page = page;
+ unlock_page(page);
+ }
+ pagevec_release(&pvec);
+ cond_resched();
+ }
+ return last_page;
+}
+
+static int __write_node_page(struct page *page, bool atomic, bool *submitted,
+ struct writeback_control *wbc)
+{
+ struct f2fs_sb_info *sbi = F2FS_P_SB(page);
+ nid_t nid;
+ struct node_info ni;
+ struct f2fs_io_info fio = {
+ .sbi = sbi,
+ .type = NODE,
+ .op = REQ_OP_WRITE,
+ .op_flags = wbc_to_write_flags(wbc),
+ .page = page,
+ .encrypted_page = NULL,
+ .submitted = false,
+ };
+
+ trace_f2fs_writepage(page, NODE);
+
+ if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+ goto redirty_out;
+ if (unlikely(f2fs_cp_error(sbi)))
+ goto redirty_out;
+
+ /* get old block addr of this node page */
+ nid = nid_of_node(page);
+ f2fs_bug_on(sbi, page->index != nid);
+
+ if (wbc->for_reclaim) {
+ if (!down_read_trylock(&sbi->node_write))
+ goto redirty_out;
+ } else {
+ down_read(&sbi->node_write);
+ }
+
+ get_node_info(sbi, nid, &ni);
+
+ /* This page is already truncated */
+ if (unlikely(ni.blk_addr == NULL_ADDR)) {
+ ClearPageUptodate(page);
+ dec_page_count(sbi, F2FS_DIRTY_NODES);
+ up_read(&sbi->node_write);
+ unlock_page(page);
+ return 0;
+ }
+
+ if (atomic && !test_opt(sbi, NOBARRIER))
+ fio.op_flags |= WRITE_FLUSH_FUA;
+
+ set_page_writeback(page);
+ fio.old_blkaddr = ni.blk_addr;
+ write_node_page(nid, &fio);
+ set_node_addr(sbi, &ni, fio.new_blkaddr, is_fsync_dnode(page));
+ dec_page_count(sbi, F2FS_DIRTY_NODES);
+ up_read(&sbi->node_write);
+
+ if (wbc->for_reclaim) {
+ f2fs_submit_merged_bio_cond(sbi, page->mapping->host, 0,
+ page->index, NODE, WRITE);
+ submitted = NULL;
+ }
+
+ unlock_page(page);
+
+ if (unlikely(f2fs_cp_error(sbi))) {
+ f2fs_submit_merged_bio(sbi, NODE, WRITE);
+ submitted = NULL;
+ }
+ if (submitted)
+ *submitted = fio.submitted;
+
+ return 0;
+
+redirty_out:
+ redirty_page_for_writepage(wbc, page);
+ return AOP_WRITEPAGE_ACTIVATE;
+}
+
+static int f2fs_write_node_page(struct page *page,
+ struct writeback_control *wbc)
+{
+ return __write_node_page(page, false, NULL, wbc);
+}
+
+int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
+ struct writeback_control *wbc, bool atomic)
+{
+ pgoff_t index, end;
+ pgoff_t last_idx = ULONG_MAX;
+ struct pagevec pvec;
+ int ret = 0;
+ struct page *last_page = NULL;
+ bool marked = false;
+ nid_t ino = inode->i_ino;
+
+ if (atomic) {
+ last_page = last_fsync_dnode(sbi, ino);
+ if (IS_ERR_OR_NULL(last_page))
+ return PTR_ERR_OR_ZERO(last_page);
+ }
+retry:
+ pagevec_init(&pvec, 0);
+ index = 0;
+ end = ULONG_MAX;
+
+ while (index <= end) {
+ int i, nr_pages;
+ nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index,
+ PAGECACHE_TAG_DIRTY,
+ min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
+ if (nr_pages == 0)
+ break;
+
+ for (i = 0; i < nr_pages; i++) {
+ struct page *page = pvec.pages[i];
+ bool submitted = false;
+
+ if (unlikely(f2fs_cp_error(sbi))) {
+ f2fs_put_page(last_page, 0);
+ pagevec_release(&pvec);
+ ret = -EIO;
+ goto out;
+ }
+
+ if (!IS_DNODE(page) || !is_cold_node(page))
+ continue;
+ if (ino_of_node(page) != ino)
+ continue;
+
+ lock_page(page);
+
+ if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
+continue_unlock:
+ unlock_page(page);
+ continue;
+ }
+ if (ino_of_node(page) != ino)
+ goto continue_unlock;
+
+ if (!PageDirty(page) && page != last_page) {
+ /* someone wrote it for us */
+ goto continue_unlock;
+ }
+
+ f2fs_wait_on_page_writeback(page, NODE, true);
+ BUG_ON(PageWriteback(page));
+
+ set_fsync_mark(page, 0);
+ set_dentry_mark(page, 0);
+
+ if (!atomic || page == last_page) {
+ set_fsync_mark(page, 1);
+ if (IS_INODE(page)) {
+ if (is_inode_flag_set(inode,
+ FI_DIRTY_INODE))
+ update_inode(inode, page);
+ set_dentry_mark(page,
+ need_dentry_mark(sbi, ino));
+ }
+ /* may be written by other thread */
+ if (!PageDirty(page))
+ set_page_dirty(page);
+ }
+
+ if (!clear_page_dirty_for_io(page))
+ goto continue_unlock;
+
+ ret = __write_node_page(page, atomic &&
+ page == last_page,
+ &submitted, wbc);
+ if (ret) {
+ unlock_page(page);
+ f2fs_put_page(last_page, 0);
+ break;
+ } else if (submitted) {
+ last_idx = page->index;
+ }
+
+ if (page == last_page) {
+ f2fs_put_page(page, 0);
+ marked = true;
+ break;
+ }
+ }
+ pagevec_release(&pvec);
+ cond_resched();
+
+ if (ret || marked)
+ break;
+ }
+ if (!ret && atomic && !marked) {
+ f2fs_msg(sbi->sb, KERN_DEBUG,
+ "Retry to write fsync mark: ino=%u, idx=%lx",
+ ino, last_page->index);
+ lock_page(last_page);
+ f2fs_wait_on_page_writeback(last_page, NODE, true);
+ set_page_dirty(last_page);
+ unlock_page(last_page);
+ goto retry;
+ }
+out:
+ if (last_idx != ULONG_MAX)
+ f2fs_submit_merged_bio_cond(sbi, NULL, ino, last_idx,
+ NODE, WRITE);
+ return ret ? -EIO: 0;
+}
+
+int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc)
+{
+ pgoff_t index, end;
+ struct pagevec pvec;
+ int step = 0;
+ int nwritten = 0;
+ int ret = 0;
+
+ pagevec_init(&pvec, 0);
+
+next_step:
+ index = 0;
+ end = ULONG_MAX;
+
+ while (index <= end) {
+ int i, nr_pages;
+ nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index,
+ PAGECACHE_TAG_DIRTY,
+ min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
+ if (nr_pages == 0)
+ break;
+
+ for (i = 0; i < nr_pages; i++) {
+ struct page *page = pvec.pages[i];
+ bool submitted = false;
+
+ if (unlikely(f2fs_cp_error(sbi))) {
+ pagevec_release(&pvec);
+ ret = -EIO;
+ goto out;
+ }
+
/*
* flushing sequence with step:
* 0. indirect nodes
@@ -1153,14 +1575,8 @@
if (step == 2 && (!IS_DNODE(page) ||
!is_cold_node(page)))
continue;
-
- /*
- * If an fsync mode,
- * we should not skip writing node pages.
- */
- if (ino && ino_of_node(page) == ino)
- lock_page(page);
- else if (!trylock_page(page))
+lock_node:
+ if (!trylock_page(page))
continue;
if (unlikely(page->mapping != NODE_MAPPING(sbi))) {
@@ -1168,37 +1584,34 @@
unlock_page(page);
continue;
}
- if (ino && ino_of_node(page) != ino)
- goto continue_unlock;
if (!PageDirty(page)) {
/* someone wrote it for us */
goto continue_unlock;
}
+ /* flush inline_data */
+ if (is_inline_node(page)) {
+ clear_inline_node(page);
+ unlock_page(page);
+ flush_inline_data(sbi, ino_of_node(page));
+ goto lock_node;
+ }
+
+ f2fs_wait_on_page_writeback(page, NODE, true);
+
+ BUG_ON(PageWriteback(page));
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
- /* called by fsync() */
- if (ino && IS_DNODE(page)) {
- set_fsync_mark(page, 1);
- if (IS_INODE(page)) {
- if (!is_checkpointed_node(sbi, ino) &&
- !has_fsynced_inode(sbi, ino))
- set_dentry_mark(page, 1);
- else
- set_dentry_mark(page, 0);
- }
- nwritten++;
- } else {
- set_fsync_mark(page, 0);
- set_dentry_mark(page, 0);
- }
+ set_fsync_mark(page, 0);
+ set_dentry_mark(page, 0);
- if (NODE_MAPPING(sbi)->a_ops->writepage(page, wbc))
+ ret = __write_node_page(page, false, &submitted, wbc);
+ if (ret)
unlock_page(page);
- else
- wrote++;
+ else if (submitted)
+ nwritten++;
if (--wbc->nr_to_write == 0)
break;
@@ -1216,15 +1629,15 @@
step++;
goto next_step;
}
-
- if (wrote)
+out:
+ if (nwritten)
f2fs_submit_merged_bio(sbi, NODE, WRITE);
- return nwritten;
+ return ret;
}
int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino)
{
- pgoff_t index = 0, end = LONG_MAX;
+ pgoff_t index = 0, end = ULONG_MAX;
struct pagevec pvec;
int ret2 = 0, ret = 0;
@@ -1246,7 +1659,7 @@
continue;
if (ino && ino_of_node(page) == ino) {
- f2fs_wait_on_page_writeback(page, NODE);
+ f2fs_wait_on_page_writeback(page, NODE, true);
if (TestClearPageError(page))
ret = -EIO;
}
@@ -1264,65 +1677,13 @@
return ret;
}
-static int f2fs_write_node_page(struct page *page,
- struct writeback_control *wbc)
-{
- struct f2fs_sb_info *sbi = F2FS_P_SB(page);
- nid_t nid;
- block_t new_addr;
- struct node_info ni;
- struct f2fs_io_info fio = {
- .type = NODE,
- .rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE,
- };
-
- trace_f2fs_writepage(page, NODE);
-
- if (unlikely(sbi->por_doing))
- goto redirty_out;
- if (unlikely(f2fs_cp_error(sbi)))
- goto redirty_out;
-
- f2fs_wait_on_page_writeback(page, NODE);
-
- /* get old block addr of this node page */
- nid = nid_of_node(page);
- f2fs_bug_on(sbi, page->index != nid);
-
- get_node_info(sbi, nid, &ni);
-
- /* This page is already truncated */
- if (unlikely(ni.blk_addr == NULL_ADDR)) {
- dec_page_count(sbi, F2FS_DIRTY_NODES);
- unlock_page(page);
- return 0;
- }
-
- if (wbc->for_reclaim)
- goto redirty_out;
-
- down_read(&sbi->node_write);
- set_page_writeback(page);
- write_node_page(sbi, page, &fio, nid, ni.blk_addr, &new_addr);
- set_node_addr(sbi, &ni, new_addr, is_fsync_dnode(page));
- dec_page_count(sbi, F2FS_DIRTY_NODES);
- up_read(&sbi->node_write);
- unlock_page(page);
- return 0;
-
-redirty_out:
- redirty_page_for_writepage(wbc, page);
- return AOP_WRITEPAGE_ACTIVATE;
-}
-
static int f2fs_write_node_pages(struct address_space *mapping,
struct writeback_control *wbc)
{
struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
+ struct blk_plug plug;
long diff;
- trace_f2fs_writepages(mapping->host, wbc, NODE);
-
/* balancing f2fs's metadata in background */
f2fs_balance_fs_bg(sbi);
@@ -1330,14 +1691,19 @@
if (get_pages(sbi, F2FS_DIRTY_NODES) < nr_pages_to_skip(sbi, NODE))
goto skip_write;
+ trace_f2fs_writepages(mapping->host, wbc, NODE);
+
diff = nr_pages_to_write(sbi, NODE, wbc);
wbc->sync_mode = WB_SYNC_NONE;
- sync_node_pages(sbi, 0, wbc);
+ blk_start_plug(&plug);
+ sync_node_pages(sbi, wbc);
+ blk_finish_plug(&plug);
wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff);
return 0;
skip_write:
wbc->pages_skipped += get_pages(sbi, F2FS_DIRTY_NODES);
+ trace_f2fs_writepages(mapping->host, wbc, NODE);
return 0;
}
@@ -1345,31 +1711,18 @@
{
trace_f2fs_set_page_dirty(page, NODE);
- SetPageUptodate(page);
+ if (!PageUptodate(page))
+ SetPageUptodate(page);
if (!PageDirty(page)) {
- __set_page_dirty_nobuffers(page);
+ f2fs_set_page_dirty_nobuffers(page);
inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES);
SetPagePrivate(page);
+ f2fs_trace_pid(page);
return 1;
}
return 0;
}
-static void f2fs_invalidate_node_page(struct page *page, unsigned int offset,
- unsigned int length)
-{
- struct inode *inode = page->mapping->host;
- if (PageDirty(page))
- dec_page_count(F2FS_I_SB(inode), F2FS_DIRTY_NODES);
- ClearPagePrivate(page);
-}
-
-static int f2fs_release_node_page(struct page *page, gfp_t wait)
-{
- ClearPagePrivate(page);
- return 1;
-}
-
/*
* Structure of the f2fs node operations
*/
@@ -1377,8 +1730,11 @@
.writepage = f2fs_write_node_page,
.writepages = f2fs_write_node_pages,
.set_page_dirty = f2fs_set_node_page_dirty,
- .invalidatepage = f2fs_invalidate_node_page,
- .releasepage = f2fs_release_node_page,
+ .invalidatepage = f2fs_invalidate_page,
+ .releasepage = f2fs_release_page,
+#ifdef CONFIG_F2FS_MIGRATION
+ .migratepage = f2fs_migrate_page,
+#endif
};
static struct free_nid *__lookup_free_nid_list(struct f2fs_nm_info *nm_i,
@@ -1387,112 +1743,250 @@
return radix_tree_lookup(&nm_i->free_nid_root, n);
}
-static void __del_from_free_nid_list(struct f2fs_nm_info *nm_i,
- struct free_nid *i)
-{
- list_del(&i->list);
- radix_tree_delete(&nm_i->free_nid_root, i->nid);
-}
-
-static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
+static int __insert_nid_to_list(struct f2fs_sb_info *sbi,
+ struct free_nid *i, enum nid_list list, bool new)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
- struct free_nid *i;
- struct nat_entry *ne;
- bool allocated = false;
- if (!available_free_memory(sbi, FREE_NIDS))
- return -1;
+ if (new) {
+ int err = radix_tree_insert(&nm_i->free_nid_root, i->nid, i);
+ if (err)
+ return err;
+ }
+
+ f2fs_bug_on(sbi, list == FREE_NID_LIST ? i->state != NID_NEW :
+ i->state != NID_ALLOC);
+ nm_i->nid_cnt[list]++;
+ list_add_tail(&i->list, &nm_i->nid_list[list]);
+ return 0;
+}
+
+static void __remove_nid_from_list(struct f2fs_sb_info *sbi,
+ struct free_nid *i, enum nid_list list, bool reuse)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+
+ f2fs_bug_on(sbi, list == FREE_NID_LIST ? i->state != NID_NEW :
+ i->state != NID_ALLOC);
+ nm_i->nid_cnt[list]--;
+ list_del(&i->list);
+ if (!reuse)
+ radix_tree_delete(&nm_i->free_nid_root, i->nid);
+}
+
+/* return if the nid is recognized as free */
+static bool add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ struct free_nid *i, *e;
+ struct nat_entry *ne;
+ int err = -EINVAL;
+ bool ret = false;
/* 0 nid should not be used */
if (unlikely(nid == 0))
- return 0;
-
- if (build) {
- /* do not add allocated nids */
- read_lock(&nm_i->nat_tree_lock);
- ne = __lookup_nat_cache(nm_i, nid);
- if (ne &&
- (!get_nat_flag(ne, IS_CHECKPOINTED) ||
- nat_get_blkaddr(ne) != NULL_ADDR))
- allocated = true;
- read_unlock(&nm_i->nat_tree_lock);
- if (allocated)
- return 0;
- }
+ return false;
i = f2fs_kmem_cache_alloc(free_nid_slab, GFP_NOFS);
i->nid = nid;
i->state = NID_NEW;
- spin_lock(&nm_i->free_nid_list_lock);
- if (radix_tree_insert(&nm_i->free_nid_root, i->nid, i)) {
- spin_unlock(&nm_i->free_nid_list_lock);
- kmem_cache_free(free_nid_slab, i);
- return 0;
+ if (radix_tree_preload(GFP_NOFS))
+ goto err;
+
+ spin_lock(&nm_i->nid_list_lock);
+
+ if (build) {
+ /*
+ * Thread A Thread B
+ * - f2fs_create
+ * - f2fs_new_inode
+ * - alloc_nid
+ * - __insert_nid_to_list(ALLOC_NID_LIST)
+ * - f2fs_balance_fs_bg
+ * - build_free_nids
+ * - __build_free_nids
+ * - scan_nat_page
+ * - add_free_nid
+ * - __lookup_nat_cache
+ * - f2fs_add_link
+ * - init_inode_metadata
+ * - new_inode_page
+ * - new_node_page
+ * - set_node_addr
+ * - alloc_nid_done
+ * - __remove_nid_from_list(ALLOC_NID_LIST)
+ * - __insert_nid_to_list(FREE_NID_LIST)
+ */
+ ne = __lookup_nat_cache(nm_i, nid);
+ if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) ||
+ nat_get_blkaddr(ne) != NULL_ADDR))
+ goto err_out;
+
+ e = __lookup_free_nid_list(nm_i, nid);
+ if (e) {
+ if (e->state == NID_NEW)
+ ret = true;
+ goto err_out;
+ }
}
- list_add_tail(&i->list, &nm_i->free_nid_list);
- nm_i->fcnt++;
- spin_unlock(&nm_i->free_nid_list_lock);
- return 1;
+ ret = true;
+ err = __insert_nid_to_list(sbi, i, FREE_NID_LIST, true);
+err_out:
+ spin_unlock(&nm_i->nid_list_lock);
+ radix_tree_preload_end();
+err:
+ if (err)
+ kmem_cache_free(free_nid_slab, i);
+ return ret;
}
-static void remove_free_nid(struct f2fs_nm_info *nm_i, nid_t nid)
+static void remove_free_nid(struct f2fs_sb_info *sbi, nid_t nid)
{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i;
bool need_free = false;
- spin_lock(&nm_i->free_nid_list_lock);
+ spin_lock(&nm_i->nid_list_lock);
i = __lookup_free_nid_list(nm_i, nid);
if (i && i->state == NID_NEW) {
- __del_from_free_nid_list(nm_i, i);
- nm_i->fcnt--;
+ __remove_nid_from_list(sbi, i, FREE_NID_LIST, false);
need_free = true;
}
- spin_unlock(&nm_i->free_nid_list_lock);
+ spin_unlock(&nm_i->nid_list_lock);
if (need_free)
kmem_cache_free(free_nid_slab, i);
}
+static void update_free_nid_bitmap(struct f2fs_sb_info *sbi, nid_t nid,
+ bool set, bool build)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ unsigned int nat_ofs = NAT_BLOCK_OFFSET(nid);
+ unsigned int nid_ofs = nid - START_NID(nid);
+
+ if (!test_bit_le(nat_ofs, nm_i->nat_block_bitmap))
+ return;
+
+ if (set)
+ __set_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]);
+ else
+ __clear_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]);
+
+ if (set)
+ nm_i->free_nid_count[nat_ofs]++;
+ else if (!build)
+ nm_i->free_nid_count[nat_ofs]--;
+}
+
static void scan_nat_page(struct f2fs_sb_info *sbi,
struct page *nat_page, nid_t start_nid)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct f2fs_nat_block *nat_blk = page_address(nat_page);
block_t blk_addr;
+ unsigned int nat_ofs = NAT_BLOCK_OFFSET(start_nid);
int i;
+ if (test_bit_le(nat_ofs, nm_i->nat_block_bitmap))
+ return;
+
+ __set_bit_le(nat_ofs, nm_i->nat_block_bitmap);
+
i = start_nid % NAT_ENTRY_PER_BLOCK;
for (; i < NAT_ENTRY_PER_BLOCK; i++, start_nid++) {
+ bool freed = false;
if (unlikely(start_nid >= nm_i->max_nid))
break;
blk_addr = le32_to_cpu(nat_blk->entries[i].block_addr);
f2fs_bug_on(sbi, blk_addr == NEW_ADDR);
- if (blk_addr == NULL_ADDR) {
- if (add_free_nid(sbi, start_nid, true) < 0)
- break;
- }
+ if (blk_addr == NULL_ADDR)
+ freed = add_free_nid(sbi, start_nid, true);
+ spin_lock(&NM_I(sbi)->nid_list_lock);
+ update_free_nid_bitmap(sbi, start_nid, freed, true);
+ spin_unlock(&NM_I(sbi)->nid_list_lock);
}
}
-static void build_free_nids(struct f2fs_sb_info *sbi)
+static void scan_free_nid_bits(struct f2fs_sb_info *sbi)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
- struct f2fs_summary_block *sum = curseg->sum_blk;
+ struct f2fs_journal *journal = curseg->journal;
+ unsigned int i, idx;
+
+ down_read(&nm_i->nat_tree_lock);
+
+ for (i = 0; i < nm_i->nat_blocks; i++) {
+ if (!test_bit_le(i, nm_i->nat_block_bitmap))
+ continue;
+ if (!nm_i->free_nid_count[i])
+ continue;
+ for (idx = 0; idx < NAT_ENTRY_PER_BLOCK; idx++) {
+ nid_t nid;
+
+ if (!test_bit_le(idx, nm_i->free_nid_bitmap[i]))
+ continue;
+
+ nid = i * NAT_ENTRY_PER_BLOCK + idx;
+ add_free_nid(sbi, nid, true);
+
+ if (nm_i->nid_cnt[FREE_NID_LIST] >= MAX_FREE_NIDS)
+ goto out;
+ }
+ }
+out:
+ down_read(&curseg->journal_rwsem);
+ for (i = 0; i < nats_in_cursum(journal); i++) {
+ block_t addr;
+ nid_t nid;
+
+ addr = le32_to_cpu(nat_in_journal(journal, i).block_addr);
+ nid = le32_to_cpu(nid_in_journal(journal, i));
+ if (addr == NULL_ADDR)
+ add_free_nid(sbi, nid, true);
+ else
+ remove_free_nid(sbi, nid);
+ }
+ up_read(&curseg->journal_rwsem);
+ up_read(&nm_i->nat_tree_lock);
+}
+
+static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
+ struct f2fs_journal *journal = curseg->journal;
int i = 0;
nid_t nid = nm_i->next_scan_nid;
+ if (unlikely(nid >= nm_i->max_nid))
+ nid = 0;
+
/* Enough entries */
- if (nm_i->fcnt > NAT_ENTRY_PER_BLOCK)
+ if (nm_i->nid_cnt[FREE_NID_LIST] >= NAT_ENTRY_PER_BLOCK)
return;
+ if (!sync && !available_free_memory(sbi, FREE_NIDS))
+ return;
+
+ if (!mount) {
+ /* try to find free nids in free_nid_bitmap */
+ scan_free_nid_bits(sbi);
+
+ if (nm_i->nid_cnt[FREE_NID_LIST])
+ return;
+ }
+
/* readahead nat pages to be scanned */
- ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES, META_NAT);
+ ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES,
+ META_NAT, true);
+
+ down_read(&nm_i->nat_tree_lock);
while (1) {
struct page *page = get_current_nat_page(sbi, nid);
@@ -1504,7 +1998,7 @@
if (unlikely(nid >= nm_i->max_nid))
nid = 0;
- if (i++ == FREE_NID_PAGES)
+ if (++i >= FREE_NID_PAGES)
break;
}
@@ -1512,16 +2006,29 @@
nm_i->next_scan_nid = nid;
/* find free nids from current sum_pages */
- mutex_lock(&curseg->curseg_mutex);
- for (i = 0; i < nats_in_cursum(sum); i++) {
- block_t addr = le32_to_cpu(nat_in_journal(sum, i).block_addr);
- nid = le32_to_cpu(nid_in_journal(sum, i));
+ down_read(&curseg->journal_rwsem);
+ for (i = 0; i < nats_in_cursum(journal); i++) {
+ block_t addr;
+
+ addr = le32_to_cpu(nat_in_journal(journal, i).block_addr);
+ nid = le32_to_cpu(nid_in_journal(journal, i));
if (addr == NULL_ADDR)
add_free_nid(sbi, nid, true);
else
- remove_free_nid(nm_i, nid);
+ remove_free_nid(sbi, nid);
}
- mutex_unlock(&curseg->curseg_mutex);
+ up_read(&curseg->journal_rwsem);
+ up_read(&nm_i->nat_tree_lock);
+
+ ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid),
+ nm_i->ra_nid_pages, META_NAT, false);
+}
+
+void build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
+{
+ mutex_lock(&NM_I(sbi)->build_lock);
+ __build_free_nids(sbi, sync, mount);
+ mutex_unlock(&NM_I(sbi)->build_lock);
}
/*
@@ -1534,31 +2041,40 @@
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i = NULL;
retry:
- if (unlikely(sbi->total_valid_node_count + 1 > nm_i->available_nids))
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(sbi, FAULT_ALLOC_NID)) {
+ f2fs_show_injection_info(FAULT_ALLOC_NID);
return false;
+ }
+#endif
+ spin_lock(&nm_i->nid_list_lock);
- spin_lock(&nm_i->free_nid_list_lock);
+ if (unlikely(nm_i->available_nids == 0)) {
+ spin_unlock(&nm_i->nid_list_lock);
+ return false;
+ }
/* We should not use stale free nids created by build_free_nids */
- if (nm_i->fcnt && !on_build_free_nids(nm_i)) {
- f2fs_bug_on(sbi, list_empty(&nm_i->free_nid_list));
- list_for_each_entry(i, &nm_i->free_nid_list, list)
- if (i->state == NID_NEW)
- break;
-
- f2fs_bug_on(sbi, i->state != NID_NEW);
+ if (nm_i->nid_cnt[FREE_NID_LIST] && !on_build_free_nids(nm_i)) {
+ f2fs_bug_on(sbi, list_empty(&nm_i->nid_list[FREE_NID_LIST]));
+ i = list_first_entry(&nm_i->nid_list[FREE_NID_LIST],
+ struct free_nid, list);
*nid = i->nid;
+
+ __remove_nid_from_list(sbi, i, FREE_NID_LIST, true);
i->state = NID_ALLOC;
- nm_i->fcnt--;
- spin_unlock(&nm_i->free_nid_list_lock);
+ __insert_nid_to_list(sbi, i, ALLOC_NID_LIST, false);
+ nm_i->available_nids--;
+
+ update_free_nid_bitmap(sbi, *nid, false, false);
+
+ spin_unlock(&nm_i->nid_list_lock);
return true;
}
- spin_unlock(&nm_i->free_nid_list_lock);
+ spin_unlock(&nm_i->nid_list_lock);
/* Let's scan nat pages and its caches to get free nids */
- mutex_lock(&nm_i->build_lock);
- build_free_nids(sbi);
- mutex_unlock(&nm_i->build_lock);
+ build_free_nids(sbi, true, false);
goto retry;
}
@@ -1570,11 +2086,11 @@
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i;
- spin_lock(&nm_i->free_nid_list_lock);
+ spin_lock(&nm_i->nid_list_lock);
i = __lookup_free_nid_list(nm_i, nid);
- f2fs_bug_on(sbi, !i || i->state != NID_ALLOC);
- __del_from_free_nid_list(nm_i, i);
- spin_unlock(&nm_i->free_nid_list_lock);
+ f2fs_bug_on(sbi, !i);
+ __remove_nid_from_list(sbi, i, ALLOC_NID_LIST, false);
+ spin_unlock(&nm_i->nid_list_lock);
kmem_cache_free(free_nid_slab, i);
}
@@ -1591,22 +2107,58 @@
if (!nid)
return;
- spin_lock(&nm_i->free_nid_list_lock);
+ spin_lock(&nm_i->nid_list_lock);
i = __lookup_free_nid_list(nm_i, nid);
- f2fs_bug_on(sbi, !i || i->state != NID_ALLOC);
+ f2fs_bug_on(sbi, !i);
+
if (!available_free_memory(sbi, FREE_NIDS)) {
- __del_from_free_nid_list(nm_i, i);
+ __remove_nid_from_list(sbi, i, ALLOC_NID_LIST, false);
need_free = true;
} else {
+ __remove_nid_from_list(sbi, i, ALLOC_NID_LIST, true);
i->state = NID_NEW;
- nm_i->fcnt++;
+ __insert_nid_to_list(sbi, i, FREE_NID_LIST, false);
}
- spin_unlock(&nm_i->free_nid_list_lock);
+
+ nm_i->available_nids++;
+
+ update_free_nid_bitmap(sbi, nid, true, false);
+
+ spin_unlock(&nm_i->nid_list_lock);
if (need_free)
kmem_cache_free(free_nid_slab, i);
}
+int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ struct free_nid *i, *next;
+ int nr = nr_shrink;
+
+ if (nm_i->nid_cnt[FREE_NID_LIST] <= MAX_FREE_NIDS)
+ return 0;
+
+ if (!mutex_trylock(&nm_i->build_lock))
+ return 0;
+
+ spin_lock(&nm_i->nid_list_lock);
+ list_for_each_entry_safe(i, next, &nm_i->nid_list[FREE_NID_LIST],
+ list) {
+ if (nr_shrink <= 0 ||
+ nm_i->nid_cnt[FREE_NID_LIST] <= MAX_FREE_NIDS)
+ break;
+
+ __remove_nid_from_list(sbi, i, FREE_NID_LIST, false);
+ kmem_cache_free(free_nid_slab, i);
+ nr_shrink--;
+ }
+ spin_unlock(&nm_i->nid_list_lock);
+ mutex_unlock(&nm_i->build_lock);
+
+ return nr - nr_shrink;
+}
+
void recover_inline_xattr(struct inode *inode, struct page *page)
{
void *src_addr, *dst_addr;
@@ -1619,7 +2171,7 @@
ri = F2FS_INODE(page);
if (!(ri->i_inline & F2FS_INLINE_XATTR)) {
- clear_inode_flag(F2FS_I(inode), FI_INLINE_XATTR);
+ clear_inode_flag(inode, FI_INLINE_XATTR);
goto update_inode;
}
@@ -1627,25 +2179,25 @@
src_addr = inline_xattr_addr(page);
inline_size = inline_xattr_size(inode);
- f2fs_wait_on_page_writeback(ipage, NODE);
+ f2fs_wait_on_page_writeback(ipage, NODE, true);
memcpy(dst_addr, src_addr, inline_size);
update_inode:
update_inode(inode, ipage);
f2fs_put_page(ipage, 1);
}
-void recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr)
+int recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
nid_t prev_xnid = F2FS_I(inode)->i_xattr_nid;
nid_t new_xnid = nid_of_node(page);
struct node_info ni;
+ struct page *xpage;
- /* 1: invalidate the previous xattr nid */
if (!prev_xnid)
goto recover_xnid;
- /* Deallocate node address */
+ /* 1: invalidate the previous xattr nid */
get_node_info(sbi, prev_xnid, &ni);
f2fs_bug_on(sbi, ni.blk_addr == NULL_ADDR);
invalidate_blocks(sbi, ni.blk_addr);
@@ -1653,21 +2205,27 @@
set_node_addr(sbi, &ni, NULL_ADDR, false);
recover_xnid:
- /* 2: allocate new xattr nid */
+ /* 2: update xattr nid in inode */
+ remove_free_nid(sbi, new_xnid);
+ f2fs_i_xnid_write(inode, new_xnid);
if (unlikely(!inc_valid_node_count(sbi, inode)))
f2fs_bug_on(sbi, 1);
+ update_inode_page(inode);
- remove_free_nid(NM_I(sbi), new_xnid);
+ /* 3: update and set xattr node page dirty */
+ xpage = grab_cache_page(NODE_MAPPING(sbi), new_xnid);
+ if (!xpage)
+ return -ENOMEM;
+
+ memcpy(F2FS_NODE(xpage), F2FS_NODE(page), PAGE_SIZE);
+
get_node_info(sbi, new_xnid, &ni);
ni.ino = inode->i_ino;
set_node_addr(sbi, &ni, NEW_ADDR, false);
- F2FS_I(inode)->i_xattr_nid = new_xnid;
+ set_page_dirty(xpage);
+ f2fs_put_page(xpage, 1);
- /* 3: update xattr blkaddr */
- refresh_sit_entry(sbi, NEW_ADDR, blkaddr);
- set_node_addr(sbi, &ni, blkaddr, false);
-
- update_inode_page(inode);
+ return 0;
}
int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
@@ -1681,15 +2239,18 @@
if (unlikely(old_ni.blk_addr != NULL_ADDR))
return -EINVAL;
-
- ipage = grab_cache_page(NODE_MAPPING(sbi), ino);
- if (!ipage)
- return -ENOMEM;
+retry:
+ ipage = f2fs_grab_cache_page(NODE_MAPPING(sbi), ino, false);
+ if (!ipage) {
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ goto retry;
+ }
/* Should not use this inode from free nid list */
- remove_free_nid(NM_I(sbi), ino);
+ remove_free_nid(sbi, ino);
- SetPageUptodate(ipage);
+ if (!PageUptodate(ipage))
+ SetPageUptodate(ipage);
fill_node_footer(ipage, ino, ino, 0, true);
src = F2FS_INODE(page);
@@ -1714,114 +2275,79 @@
return 0;
}
-/*
- * ra_sum_pages() merge contiguous pages into one bio and submit.
- * these pre-read pages are allocated in bd_inode's mapping tree.
- */
-static int ra_sum_pages(struct f2fs_sb_info *sbi, struct page **pages,
- int start, int nrpages)
-{
- struct inode *inode = sbi->sb->s_bdev->bd_inode;
- struct address_space *mapping = inode->i_mapping;
- int i, page_idx = start;
- struct f2fs_io_info fio = {
- .type = META,
- .rw = READ_SYNC | REQ_META | REQ_PRIO
- };
-
- for (i = 0; page_idx < start + nrpages; page_idx++, i++) {
- /* alloc page in bd_inode for reading node summary info */
- pages[i] = grab_cache_page(mapping, page_idx);
- if (!pages[i])
- break;
- f2fs_submit_page_mbio(sbi, pages[i], page_idx, &fio);
- }
-
- f2fs_submit_merged_bio(sbi, META, READ);
- return i;
-}
-
int restore_node_summary(struct f2fs_sb_info *sbi,
unsigned int segno, struct f2fs_summary_block *sum)
{
struct f2fs_node *rn;
struct f2fs_summary *sum_entry;
- struct inode *inode = sbi->sb->s_bdev->bd_inode;
block_t addr;
- int bio_blocks = MAX_BIO_BLOCKS(sbi);
- struct page *pages[bio_blocks];
- int i, idx, last_offset, nrpages, err = 0;
+ int i, idx, last_offset, nrpages;
/* scan the node segment */
last_offset = sbi->blocks_per_seg;
addr = START_BLOCK(sbi, segno);
sum_entry = &sum->entries[0];
- for (i = 0; !err && i < last_offset; i += nrpages, addr += nrpages) {
- nrpages = min(last_offset - i, bio_blocks);
+ for (i = 0; i < last_offset; i += nrpages, addr += nrpages) {
+ nrpages = min(last_offset - i, BIO_MAX_PAGES);
/* readahead node pages */
- nrpages = ra_sum_pages(sbi, pages, addr, nrpages);
- if (!nrpages)
- return -ENOMEM;
+ ra_meta_pages(sbi, addr, nrpages, META_POR, true);
- for (idx = 0; idx < nrpages; idx++) {
- if (err)
- goto skip;
+ for (idx = addr; idx < addr + nrpages; idx++) {
+ struct page *page = get_tmp_page(sbi, idx);
- lock_page(pages[idx]);
- if (unlikely(!PageUptodate(pages[idx]))) {
- err = -EIO;
- } else {
- rn = F2FS_NODE(pages[idx]);
- sum_entry->nid = rn->footer.nid;
- sum_entry->version = 0;
- sum_entry->ofs_in_node = 0;
- sum_entry++;
- }
- unlock_page(pages[idx]);
-skip:
- page_cache_release(pages[idx]);
+ rn = F2FS_NODE(page);
+ sum_entry->nid = rn->footer.nid;
+ sum_entry->version = 0;
+ sum_entry->ofs_in_node = 0;
+ sum_entry++;
+ f2fs_put_page(page, 1);
}
- invalidate_mapping_pages(inode->i_mapping, addr,
+ invalidate_mapping_pages(META_MAPPING(sbi), addr,
addr + nrpages);
}
- return err;
+ return 0;
}
static void remove_nats_in_journal(struct f2fs_sb_info *sbi)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
- struct f2fs_summary_block *sum = curseg->sum_blk;
+ struct f2fs_journal *journal = curseg->journal;
int i;
- mutex_lock(&curseg->curseg_mutex);
- for (i = 0; i < nats_in_cursum(sum); i++) {
+ down_write(&curseg->journal_rwsem);
+ for (i = 0; i < nats_in_cursum(journal); i++) {
struct nat_entry *ne;
struct f2fs_nat_entry raw_ne;
- nid_t nid = le32_to_cpu(nid_in_journal(sum, i));
+ nid_t nid = le32_to_cpu(nid_in_journal(journal, i));
- raw_ne = nat_in_journal(sum, i);
-retry:
- write_lock(&nm_i->nat_tree_lock);
+ raw_ne = nat_in_journal(journal, i);
+
ne = __lookup_nat_cache(nm_i, nid);
- if (ne)
- goto found;
-
- ne = grab_nat_entry(nm_i, nid);
if (!ne) {
- write_unlock(&nm_i->nat_tree_lock);
- goto retry;
+ ne = grab_nat_entry(nm_i, nid, true);
+ node_info_from_raw_nat(&ne->ni, &raw_ne);
}
- node_info_from_raw_nat(&ne->ni, &raw_ne);
-found:
+
+ /*
+ * if a free nat in journal has not been used after last
+ * checkpoint, we should remove it from available nids,
+ * since later we will add it again.
+ */
+ if (!get_nat_flag(ne, IS_DIRTY) &&
+ le32_to_cpu(raw_ne.block_addr) == NULL_ADDR) {
+ spin_lock(&nm_i->nid_list_lock);
+ nm_i->available_nids--;
+ spin_unlock(&nm_i->nid_list_lock);
+ }
+
__set_nat_cache_dirty(nm_i, ne);
- write_unlock(&nm_i->nat_tree_lock);
}
- update_nats_in_cursum(sum, -i);
- mutex_unlock(&curseg->curseg_mutex);
+ update_nats_in_cursum(journal, -i);
+ up_write(&curseg->journal_rwsem);
}
static void __adjust_nat_entry_set(struct nat_entry_set *nes,
@@ -1842,11 +2368,42 @@
list_add_tail(&nes->set_list, head);
}
+static void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid,
+ struct page *page)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ unsigned int nat_index = start_nid / NAT_ENTRY_PER_BLOCK;
+ struct f2fs_nat_block *nat_blk = page_address(page);
+ int valid = 0;
+ int i;
+
+ if (!enabled_nat_bits(sbi, NULL))
+ return;
+
+ for (i = 0; i < NAT_ENTRY_PER_BLOCK; i++) {
+ if (start_nid == 0 && i == 0)
+ valid++;
+ if (nat_blk->entries[i].block_addr)
+ valid++;
+ }
+ if (valid == 0) {
+ __set_bit_le(nat_index, nm_i->empty_nat_bits);
+ __clear_bit_le(nat_index, nm_i->full_nat_bits);
+ return;
+ }
+
+ __clear_bit_le(nat_index, nm_i->empty_nat_bits);
+ if (valid == NAT_ENTRY_PER_BLOCK)
+ __set_bit_le(nat_index, nm_i->full_nat_bits);
+ else
+ __clear_bit_le(nat_index, nm_i->full_nat_bits);
+}
+
static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
- struct nat_entry_set *set)
+ struct nat_entry_set *set, struct cp_control *cpc)
{
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
- struct f2fs_summary_block *sum = curseg->sum_blk;
+ struct f2fs_journal *journal = curseg->journal;
nid_t start_nid = set->set * NAT_ENTRY_PER_BLOCK;
bool to_journal = true;
struct f2fs_nat_block *nat_blk;
@@ -1858,11 +2415,12 @@
* #1, flush nat entries to journal in current hot data summary block.
* #2, flush nat entries to nat page.
*/
- if (!__has_cursum_space(sum, set->entry_cnt, NAT_JOURNAL))
+ if (enabled_nat_bits(sbi, cpc) ||
+ !__has_cursum_space(journal, set->entry_cnt, NAT_JOURNAL))
to_journal = false;
if (to_journal) {
- mutex_lock(&curseg->curseg_mutex);
+ down_write(&curseg->journal_rwsem);
} else {
page = get_next_nat_page(sbi, start_nid);
nat_blk = page_address(page);
@@ -1879,30 +2437,38 @@
continue;
if (to_journal) {
- offset = lookup_journal_in_cursum(sum,
+ offset = lookup_journal_in_cursum(journal,
NAT_JOURNAL, nid, 1);
f2fs_bug_on(sbi, offset < 0);
- raw_ne = &nat_in_journal(sum, offset);
- nid_in_journal(sum, offset) = cpu_to_le32(nid);
+ raw_ne = &nat_in_journal(journal, offset);
+ nid_in_journal(journal, offset) = cpu_to_le32(nid);
} else {
raw_ne = &nat_blk->entries[nid - start_nid];
}
raw_nat_from_node_info(raw_ne, &ne->ni);
-
- write_lock(&NM_I(sbi)->nat_tree_lock);
nat_reset_flag(ne);
- __clear_nat_cache_dirty(NM_I(sbi), ne);
- write_unlock(&NM_I(sbi)->nat_tree_lock);
-
- if (nat_get_blkaddr(ne) == NULL_ADDR)
+ __clear_nat_cache_dirty(NM_I(sbi), set, ne);
+ if (nat_get_blkaddr(ne) == NULL_ADDR) {
add_free_nid(sbi, nid, false);
+ spin_lock(&NM_I(sbi)->nid_list_lock);
+ NM_I(sbi)->available_nids++;
+ update_free_nid_bitmap(sbi, nid, true, false);
+ spin_unlock(&NM_I(sbi)->nid_list_lock);
+ } else {
+ spin_lock(&NM_I(sbi)->nid_list_lock);
+ update_free_nid_bitmap(sbi, nid, false, false);
+ spin_unlock(&NM_I(sbi)->nid_list_lock);
+ }
}
- if (to_journal)
- mutex_unlock(&curseg->curseg_mutex);
- else
+ if (to_journal) {
+ up_write(&curseg->journal_rwsem);
+ } else {
+ __update_nat_bits(sbi, start_nid, page);
f2fs_put_page(page, 1);
+ }
+ /* Allow dirty nats by node block allocation in write_begin */
if (!set->entry_cnt) {
radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set);
kmem_cache_free(nat_entry_set_slab, set);
@@ -1912,42 +2478,122 @@
/*
* This function is called during the checkpointing process.
*/
-void flush_nat_entries(struct f2fs_sb_info *sbi)
+void flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
- struct f2fs_summary_block *sum = curseg->sum_blk;
- struct nat_entry_set *setvec[NATVEC_SIZE];
+ struct f2fs_journal *journal = curseg->journal;
+ struct nat_entry_set *setvec[SETVEC_SIZE];
struct nat_entry_set *set, *tmp;
unsigned int found;
nid_t set_idx = 0;
LIST_HEAD(sets);
+ if (!nm_i->dirty_nat_cnt)
+ return;
+
+ down_write(&nm_i->nat_tree_lock);
+
/*
* if there are no enough space in journal to store dirty nat
* entries, remove all entries from journal and merge them
* into nat entry set.
*/
- if (!__has_cursum_space(sum, nm_i->dirty_nat_cnt, NAT_JOURNAL))
+ if (enabled_nat_bits(sbi, cpc) ||
+ !__has_cursum_space(journal, nm_i->dirty_nat_cnt, NAT_JOURNAL))
remove_nats_in_journal(sbi);
- if (!nm_i->dirty_nat_cnt)
- return;
-
while ((found = __gang_lookup_nat_set(nm_i,
- set_idx, NATVEC_SIZE, setvec))) {
+ set_idx, SETVEC_SIZE, setvec))) {
unsigned idx;
set_idx = setvec[found - 1]->set + 1;
for (idx = 0; idx < found; idx++)
__adjust_nat_entry_set(setvec[idx], &sets,
- MAX_NAT_JENTRIES(sum));
+ MAX_NAT_JENTRIES(journal));
}
/* flush dirty nats in nat entry set */
list_for_each_entry_safe(set, tmp, &sets, set_list)
- __flush_nat_entry_set(sbi, set);
+ __flush_nat_entry_set(sbi, set, cpc);
- f2fs_bug_on(sbi, nm_i->dirty_nat_cnt);
+ up_write(&nm_i->nat_tree_lock);
+ /* Allow dirty nats by node block allocation in write_begin */
+}
+
+static int __get_nat_bitmaps(struct f2fs_sb_info *sbi)
+{
+ struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ unsigned int nat_bits_bytes = nm_i->nat_blocks / BITS_PER_BYTE;
+ unsigned int i;
+ __u64 cp_ver = cur_cp_version(ckpt);
+ block_t nat_bits_addr;
+
+ if (!enabled_nat_bits(sbi, NULL))
+ return 0;
+
+ nm_i->nat_bits_blocks = F2FS_BYTES_TO_BLK((nat_bits_bytes << 1) + 8 +
+ F2FS_BLKSIZE - 1);
+ nm_i->nat_bits = kzalloc(nm_i->nat_bits_blocks << F2FS_BLKSIZE_BITS,
+ GFP_KERNEL);
+ if (!nm_i->nat_bits)
+ return -ENOMEM;
+
+ nat_bits_addr = __start_cp_addr(sbi) + sbi->blocks_per_seg -
+ nm_i->nat_bits_blocks;
+ for (i = 0; i < nm_i->nat_bits_blocks; i++) {
+ struct page *page = get_meta_page(sbi, nat_bits_addr++);
+
+ memcpy(nm_i->nat_bits + (i << F2FS_BLKSIZE_BITS),
+ page_address(page), F2FS_BLKSIZE);
+ f2fs_put_page(page, 1);
+ }
+
+ cp_ver |= (cur_cp_crc(ckpt) << 32);
+ if (cpu_to_le64(cp_ver) != *(__le64 *)nm_i->nat_bits) {
+ disable_nat_bits(sbi, true);
+ return 0;
+ }
+
+ nm_i->full_nat_bits = nm_i->nat_bits + 8;
+ nm_i->empty_nat_bits = nm_i->full_nat_bits + nat_bits_bytes;
+
+ f2fs_msg(sbi->sb, KERN_NOTICE, "Found nat_bits in checkpoint");
+ return 0;
+}
+
+inline void load_free_nid_bitmap(struct f2fs_sb_info *sbi)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+ unsigned int i = 0;
+ nid_t nid, last_nid;
+
+ if (!enabled_nat_bits(sbi, NULL))
+ return;
+
+ for (i = 0; i < nm_i->nat_blocks; i++) {
+ i = find_next_bit_le(nm_i->empty_nat_bits, nm_i->nat_blocks, i);
+ if (i >= nm_i->nat_blocks)
+ break;
+
+ __set_bit_le(i, nm_i->nat_block_bitmap);
+
+ nid = i * NAT_ENTRY_PER_BLOCK;
+ last_nid = (i + 1) * NAT_ENTRY_PER_BLOCK;
+
+ spin_lock(&NM_I(sbi)->nid_list_lock);
+ for (; nid < last_nid; nid++)
+ update_free_nid_bitmap(sbi, nid, true, true);
+ spin_unlock(&NM_I(sbi)->nid_list_lock);
+ }
+
+ for (i = 0; i < nm_i->nat_blocks; i++) {
+ i = find_next_bit_le(nm_i->full_nat_bits, nm_i->nat_blocks, i);
+ if (i >= nm_i->nat_blocks)
+ break;
+
+ __set_bit_le(i, nm_i->nat_block_bitmap);
+ }
}
static int init_node_manager(struct f2fs_sb_info *sbi)
@@ -1955,31 +2601,36 @@
struct f2fs_super_block *sb_raw = F2FS_RAW_SUPER(sbi);
struct f2fs_nm_info *nm_i = NM_I(sbi);
unsigned char *version_bitmap;
- unsigned int nat_segs, nat_blocks;
+ unsigned int nat_segs;
+ int err;
nm_i->nat_blkaddr = le32_to_cpu(sb_raw->nat_blkaddr);
/* segment_count_nat includes pair segment so divide to 2. */
nat_segs = le32_to_cpu(sb_raw->segment_count_nat) >> 1;
- nat_blocks = nat_segs << le32_to_cpu(sb_raw->log_blocks_per_seg);
-
- nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nat_blocks;
+ nm_i->nat_blocks = nat_segs << le32_to_cpu(sb_raw->log_blocks_per_seg);
+ nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nm_i->nat_blocks;
/* not used nids: 0, node, meta, (and root counted as valid node) */
- nm_i->available_nids = nm_i->max_nid - F2FS_RESERVED_NODE_NUM;
- nm_i->fcnt = 0;
+ nm_i->available_nids = nm_i->max_nid - sbi->total_valid_node_count -
+ F2FS_RESERVED_NODE_NUM;
+ nm_i->nid_cnt[FREE_NID_LIST] = 0;
+ nm_i->nid_cnt[ALLOC_NID_LIST] = 0;
nm_i->nat_cnt = 0;
nm_i->ram_thresh = DEF_RAM_THRESHOLD;
+ nm_i->ra_nid_pages = DEF_RA_NID_PAGES;
+ nm_i->dirty_nats_ratio = DEF_DIRTY_NAT_RATIO_THRESHOLD;
INIT_RADIX_TREE(&nm_i->free_nid_root, GFP_ATOMIC);
- INIT_LIST_HEAD(&nm_i->free_nid_list);
- INIT_RADIX_TREE(&nm_i->nat_root, GFP_ATOMIC);
- INIT_RADIX_TREE(&nm_i->nat_set_root, GFP_ATOMIC);
+ INIT_LIST_HEAD(&nm_i->nid_list[FREE_NID_LIST]);
+ INIT_LIST_HEAD(&nm_i->nid_list[ALLOC_NID_LIST]);
+ INIT_RADIX_TREE(&nm_i->nat_root, GFP_NOIO);
+ INIT_RADIX_TREE(&nm_i->nat_set_root, GFP_NOIO);
INIT_LIST_HEAD(&nm_i->nat_entries);
mutex_init(&nm_i->build_lock);
- spin_lock_init(&nm_i->free_nid_list_lock);
- rwlock_init(&nm_i->nat_tree_lock);
+ spin_lock_init(&nm_i->nid_list_lock);
+ init_rwsem(&nm_i->nat_tree_lock);
nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid);
nm_i->bitmap_size = __bitmap_size(sbi, NAT_BITMAP);
@@ -1991,6 +2642,39 @@
GFP_KERNEL);
if (!nm_i->nat_bitmap)
return -ENOMEM;
+
+ err = __get_nat_bitmaps(sbi);
+ if (err)
+ return err;
+
+#ifdef CONFIG_F2FS_CHECK_FS
+ nm_i->nat_bitmap_mir = kmemdup(version_bitmap, nm_i->bitmap_size,
+ GFP_KERNEL);
+ if (!nm_i->nat_bitmap_mir)
+ return -ENOMEM;
+#endif
+
+ return 0;
+}
+
+static int init_free_nid_cache(struct f2fs_sb_info *sbi)
+{
+ struct f2fs_nm_info *nm_i = NM_I(sbi);
+
+ nm_i->free_nid_bitmap = f2fs_kvzalloc(nm_i->nat_blocks *
+ NAT_ENTRY_BITMAP_SIZE, GFP_KERNEL);
+ if (!nm_i->free_nid_bitmap)
+ return -ENOMEM;
+
+ nm_i->nat_block_bitmap = f2fs_kvzalloc(nm_i->nat_blocks / 8,
+ GFP_KERNEL);
+ if (!nm_i->nat_block_bitmap)
+ return -ENOMEM;
+
+ nm_i->free_nid_count = f2fs_kvzalloc(nm_i->nat_blocks *
+ sizeof(unsigned short), GFP_KERNEL);
+ if (!nm_i->free_nid_count)
+ return -ENOMEM;
return 0;
}
@@ -2006,7 +2690,14 @@
if (err)
return err;
- build_free_nids(sbi);
+ err = init_free_nid_cache(sbi);
+ if (err)
+ return err;
+
+ /* load free nid status from nat_bits table */
+ load_free_nid_bitmap(sbi);
+
+ build_free_nids(sbi, true, true);
return 0;
}
@@ -2015,6 +2706,7 @@
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i, *next_i;
struct nat_entry *natvec[NATVEC_SIZE];
+ struct nat_entry_set *setvec[SETVEC_SIZE];
nid_t nid = 0;
unsigned int found;
@@ -2022,31 +2714,56 @@
return;
/* destroy free nid list */
- spin_lock(&nm_i->free_nid_list_lock);
- list_for_each_entry_safe(i, next_i, &nm_i->free_nid_list, list) {
- f2fs_bug_on(sbi, i->state == NID_ALLOC);
- __del_from_free_nid_list(nm_i, i);
- nm_i->fcnt--;
- spin_unlock(&nm_i->free_nid_list_lock);
+ spin_lock(&nm_i->nid_list_lock);
+ list_for_each_entry_safe(i, next_i, &nm_i->nid_list[FREE_NID_LIST],
+ list) {
+ __remove_nid_from_list(sbi, i, FREE_NID_LIST, false);
+ spin_unlock(&nm_i->nid_list_lock);
kmem_cache_free(free_nid_slab, i);
- spin_lock(&nm_i->free_nid_list_lock);
+ spin_lock(&nm_i->nid_list_lock);
}
- f2fs_bug_on(sbi, nm_i->fcnt);
- spin_unlock(&nm_i->free_nid_list_lock);
+ f2fs_bug_on(sbi, nm_i->nid_cnt[FREE_NID_LIST]);
+ f2fs_bug_on(sbi, nm_i->nid_cnt[ALLOC_NID_LIST]);
+ f2fs_bug_on(sbi, !list_empty(&nm_i->nid_list[ALLOC_NID_LIST]));
+ spin_unlock(&nm_i->nid_list_lock);
/* destroy nat cache */
- write_lock(&nm_i->nat_tree_lock);
+ down_write(&nm_i->nat_tree_lock);
while ((found = __gang_lookup_nat_cache(nm_i,
nid, NATVEC_SIZE, natvec))) {
unsigned idx;
+
nid = nat_get_nid(natvec[found - 1]) + 1;
for (idx = 0; idx < found; idx++)
__del_from_nat_cache(nm_i, natvec[idx]);
}
f2fs_bug_on(sbi, nm_i->nat_cnt);
- write_unlock(&nm_i->nat_tree_lock);
+
+ /* destroy nat set cache */
+ nid = 0;
+ while ((found = __gang_lookup_nat_set(nm_i,
+ nid, SETVEC_SIZE, setvec))) {
+ unsigned idx;
+
+ nid = setvec[found - 1]->set + 1;
+ for (idx = 0; idx < found; idx++) {
+ /* entry_cnt is not zero, when cp_error was occurred */
+ f2fs_bug_on(sbi, !list_empty(&setvec[idx]->entry_list));
+ radix_tree_delete(&nm_i->nat_set_root, setvec[idx]->set);
+ kmem_cache_free(nat_entry_set_slab, setvec[idx]);
+ }
+ }
+ up_write(&nm_i->nat_tree_lock);
+
+ kvfree(nm_i->nat_block_bitmap);
+ kvfree(nm_i->free_nid_bitmap);
+ kvfree(nm_i->free_nid_count);
kfree(nm_i->nat_bitmap);
+ kfree(nm_i->nat_bits);
+#ifdef CONFIG_F2FS_CHECK_FS
+ kfree(nm_i->nat_bitmap_mir);
+#endif
sbi->nm_info = NULL;
kfree(nm_i);
}
@@ -2061,17 +2778,17 @@
free_nid_slab = f2fs_kmem_cache_create("free_nid",
sizeof(struct free_nid));
if (!free_nid_slab)
- goto destory_nat_entry;
+ goto destroy_nat_entry;
nat_entry_set_slab = f2fs_kmem_cache_create("nat_entry_set",
sizeof(struct nat_entry_set));
if (!nat_entry_set_slab)
- goto destory_free_nid;
+ goto destroy_free_nid;
return 0;
-destory_free_nid:
+destroy_free_nid:
kmem_cache_destroy(free_nid_slab);
-destory_nat_entry:
+destroy_nat_entry:
kmem_cache_destroy(nat_entry_slab);
fail:
return -ENOMEM;
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index 8d5e6e0d..558048e 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -9,26 +9,43 @@
* published by the Free Software Foundation.
*/
/* start node id of a node block dedicated to the given node id */
-#define START_NID(nid) ((nid / NAT_ENTRY_PER_BLOCK) * NAT_ENTRY_PER_BLOCK)
+#define START_NID(nid) (((nid) / NAT_ENTRY_PER_BLOCK) * NAT_ENTRY_PER_BLOCK)
/* 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)
+#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
*/
@@ -37,46 +54,49 @@
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 */
};
-#define nat_get_nid(nat) (nat->ni.nid)
-#define nat_set_nid(nat, n) (nat->ni.nid = n)
-#define nat_get_blkaddr(nat) (nat->ni.blk_addr)
-#define nat_set_blkaddr(nat, b) (nat->ni.blk_addr = b)
-#define nat_get_ino(nat) (nat->ni.ino)
-#define nat_set_ino(nat, i) (nat->ni.ino = i)
-#define nat_get_version(nat) (nat->ni.version)
-#define nat_set_version(nat, v) (nat->ni.version = v)
+#define nat_get_nid(nat) ((nat)->ni.nid)
+#define nat_set_nid(nat, n) ((nat)->ni.nid = (n))
+#define nat_get_blkaddr(nat) ((nat)->ni.blk_addr)
+#define nat_set_blkaddr(nat, b) ((nat)->ni.blk_addr = (b))
+#define nat_get_ino(nat) ((nat)->ni.ino)
+#define nat_set_ino(nat, i) ((nat)->ni.ino = (i))
+#define nat_get_version(nat) ((nat)->ni.version)
+#define nat_set_version(nat, v) ((nat)->ni.version = (v))
-#define inc_node_version(version) (++version)
+#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 @@
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 {
@@ -135,14 +169,15 @@
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *fnid;
- spin_lock(&nm_i->free_nid_list_lock);
- if (nm_i->fcnt <= 0) {
- spin_unlock(&nm_i->free_nid_list_lock);
+ spin_lock(&nm_i->nid_list_lock);
+ if (nm_i->nid_cnt[FREE_NID_LIST] <= 0) {
+ spin_unlock(&nm_i->nid_list_lock);
return;
}
- fnid = list_entry(nm_i->free_nid_list.next, struct free_nid, list);
+ fnid = list_first_entry(&nm_i->nid_list[FREE_NID_LIST],
+ struct free_nid, list);
*nid = fnid->nid;
- spin_unlock(&nm_i->free_nid_list_lock);
+ spin_unlock(&nm_i->nid_list_lock);
}
/*
@@ -151,6 +186,12 @@
static inline void get_nat_bitmap(struct f2fs_sb_info *sbi, void *addr)
{
struct f2fs_nm_info *nm_i = NM_I(sbi);
+
+#ifdef CONFIG_F2FS_CHECK_FS
+ if (memcmp(nm_i->nat_bitmap, nm_i->nat_bitmap_mir,
+ nm_i->bitmap_size))
+ f2fs_bug_on(sbi, 1);
+#endif
memcpy(addr, nm_i->nat_bitmap, nm_i->bitmap_size);
}
@@ -159,14 +200,17 @@
struct f2fs_nm_info *nm_i = NM_I(sbi);
pgoff_t block_off;
pgoff_t block_addr;
- int seg_off;
+ /*
+ * block_off = segment_off * 512 + off_in_segment
+ * OLD = (segment_off * 512) * 2 + off_in_segment
+ * NEW = 2 * (segment_off * 512 + off_in_segment) - off_in_segment
+ */
block_off = NAT_BLOCK_OFFSET(start);
- seg_off = block_off >> sbi->log_blocks_per_seg;
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 << 1) -
+ (block_off & (sbi->blocks_per_seg - 1)));
if (f2fs_test_bit(block_off, nm_i->nat_bitmap))
block_addr += sbi->blocks_per_seg;
@@ -192,37 +236,10 @@
{
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);
-}
-
-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);
- if (reset)
- memset(rn, 0, sizeof(*rn));
- rn->footer.nid = cpu_to_le32(nid);
- rn->footer.ino = cpu_to_le32(ino);
- rn->footer.flag = cpu_to_le32(ofs << OFFSET_BIT_SHIFT);
-}
-
-static inline void copy_node_footer(struct page *dst, struct page *src)
-{
- struct f2fs_node *src_rn = F2FS_NODE(src);
- struct f2fs_node *dst_rn = F2FS_NODE(dst);
- memcpy(&dst_rn->footer, &src_rn->footer, sizeof(struct node_footer));
-}
-
-static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr)
-{
- struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
- struct f2fs_node *rn = F2FS_NODE(page);
-
- rn->footer.cp_ver = ckpt->checkpoint_ver;
- rn->footer.next_blkaddr = cpu_to_le32(blkaddr);
+ f2fs_change_bit(block_off, nm_i->nat_bitmap);
+#ifdef CONFIG_F2FS_CHECK_FS
+ f2fs_change_bit(block_off, nm_i->nat_bitmap_mir);
+#endif
}
static inline nid_t ino_of_node(struct page *node_page)
@@ -244,7 +261,7 @@
return flag >> OFFSET_BIT_SHIFT;
}
-static inline unsigned long long cpver_of_node(struct page *node_page)
+static inline __u64 cpver_of_node(struct page *node_page)
{
struct f2fs_node *rn = F2FS_NODE(node_page);
return le64_to_cpu(rn->footer.cp_ver);
@@ -256,6 +273,56 @@
return le32_to_cpu(rn->footer.next_blkaddr);
}
+static inline void fill_node_footer(struct page *page, nid_t nid,
+ nid_t ino, unsigned int ofs, bool reset)
+{
+ 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);
+
+ /* 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)
+{
+ struct f2fs_node *src_rn = F2FS_NODE(src);
+ struct f2fs_node *dst_rn = F2FS_NODE(dst);
+ memcpy(&dst_rn->footer, &src_rn->footer, sizeof(struct node_footer));
+}
+
+static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr)
+{
+ struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
+ struct f2fs_node *rn = F2FS_NODE(page);
+ __u64 cp_ver = cur_cp_version(ckpt);
+
+ if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG))
+ cp_ver |= (cur_cp_crc(ckpt) << 32);
+
+ rn->footer.cp_ver = cpu_to_le64(cp_ver);
+ rn->footer.next_blkaddr = cpu_to_le32(blkaddr);
+}
+
+static inline bool is_recoverable_dnode(struct page *page)
+{
+ struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
+ __u64 cp_ver = cur_cp_version(ckpt);
+
+ if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG))
+ cp_ver |= (cur_cp_crc(ckpt) << 32);
+
+ return cp_ver == cpver_of_node(page);
+}
+
/*
* f2fs assigns the following node offsets described as (num).
* N = NIDS_PER_BLOCK
@@ -282,7 +349,7 @@
unsigned int ofs = ofs_of_node(node_page);
if (f2fs_has_xattr_block(ofs))
- return false;
+ return true;
if (ofs == 3 || ofs == 4 + NIDS_PER_BLOCK ||
ofs == 5 + 2 * NIDS_PER_BLOCK)
@@ -295,17 +362,17 @@
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 +390,6 @@
* - 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 +415,21 @@
#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);
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index ebd0132..20147d2 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -49,8 +49,9 @@
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;
}
@@ -67,38 +68,71 @@
return NULL;
}
-static int recover_dentry(struct inode *inode, struct page *ipage)
+static struct fsync_inode_entry *add_fsync_inode(struct f2fs_sb_info *sbi,
+ struct list_head *head, nid_t ino)
+{
+ struct inode *inode;
+ struct fsync_inode_entry *entry;
+
+ inode = f2fs_iget_retry(sbi->sb, ino);
+ if (IS_ERR(inode))
+ return ERR_CAST(inode);
+
+ entry = f2fs_kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
+ entry->inode = inode;
+ list_add_tail(&entry->list, head);
+
+ return entry;
+}
+
+static void del_fsync_inode(struct fsync_inode_entry *entry)
+{
+ iput(entry->inode);
+ list_del(&entry->list);
+ kmem_cache_free(fsync_entry_slab, entry);
+}
+
+static int recover_dentry(struct inode *inode, struct page *ipage,
+ struct list_head *dir_list)
{
struct f2fs_inode *raw_inode = F2FS_INODE(ipage);
nid_t pino = le32_to_cpu(raw_inode->i_pino);
struct f2fs_dir_entry *de;
- struct qstr name;
+ struct fscrypt_name fname;
struct page *page;
struct inode *dir, *einode;
+ struct fsync_inode_entry *entry;
int err = 0;
+ char *name;
- dir = f2fs_iget(inode->i_sb, pino);
- if (IS_ERR(dir)) {
- err = PTR_ERR(dir);
- goto out;
+ entry = get_fsync_inode(dir_list, pino);
+ if (!entry) {
+ entry = add_fsync_inode(F2FS_I_SB(inode), dir_list, pino);
+ if (IS_ERR(entry)) {
+ dir = ERR_CAST(entry);
+ err = PTR_ERR(entry);
+ goto out;
+ }
}
- name.len = le32_to_cpu(raw_inode->i_namelen);
- name.name = raw_inode->i_name;
+ dir = entry->inode;
- if (unlikely(name.len > F2FS_NAME_LEN)) {
+ memset(&fname, 0, sizeof(struct fscrypt_name));
+ fname.disk_name.len = le32_to_cpu(raw_inode->i_namelen);
+ fname.disk_name.name = raw_inode->i_name;
+
+ if (unlikely(fname.disk_name.len > F2FS_NAME_LEN)) {
WARN_ON(1);
err = -ENAMETOOLONG;
- goto out_err;
+ goto out;
}
retry:
- de = f2fs_find_entry(dir, &name, &page);
- if (de && inode->i_ino == le32_to_cpu(de->ino)) {
- clear_inode_flag(F2FS_I(inode), FI_INC_LINK);
+ de = __f2fs_find_entry(dir, &fname, &page);
+ if (de && inode->i_ino == le32_to_cpu(de->ino))
goto out_unmap_put;
- }
+
if (de) {
- einode = f2fs_iget(inode->i_sb, le32_to_cpu(de->ino));
+ einode = f2fs_iget_retry(inode->i_sb, le32_to_cpu(de->ino));
if (IS_ERR(einode)) {
WARN_ON(1);
err = PTR_ERR(einode);
@@ -111,32 +145,30 @@
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_do_add_link(dir, &fname, inode,
+ inode->i_ino, inode->i_mode);
}
-
+ if (err == -ENOMEM)
+ goto retry;
goto out;
out_unmap_put:
- kunmap(page);
+ f2fs_dentry_kunmap(dir, page);
f2fs_put_page(page, 0);
-out_err:
- iput(dir);
out:
+ if (file_enc_name(inode))
+ name = "<encrypted>";
+ else
+ name = raw_inode->i_name;
f2fs_msg(inode->i_sb, KERN_NOTICE,
"%s: ino = %x, name = %s, dir = %lx, err = %d",
- __func__, ino_of_node(ipage), raw_inode->i_name,
+ __func__, ino_of_node(ipage), name,
IS_ERR(dir) ? 0 : dir->i_ino, err);
return err;
}
@@ -144,23 +176,31 @@
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));
- inode->i_atime.tv_sec = le64_to_cpu(raw->i_mtime);
+ f2fs_i_size_write(inode, le64_to_cpu(raw->i_size));
+ inode->i_atime.tv_sec = le64_to_cpu(raw->i_atime);
inode->i_ctime.tv_sec = le64_to_cpu(raw->i_ctime);
inode->i_mtime.tv_sec = le64_to_cpu(raw->i_mtime);
- inode->i_atime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec);
+ inode->i_atime.tv_nsec = le32_to_cpu(raw->i_atime_nsec);
inode->i_ctime.tv_nsec = le32_to_cpu(raw->i_ctime_nsec);
inode->i_mtime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec);
+ F2FS_I(inode)->i_advise = raw->i_advise;
+
+ 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 int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
+static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head,
+ bool check_only)
{
- unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
struct curseg_info *curseg;
struct page *page = NULL;
block_t blkaddr;
@@ -173,60 +213,50 @@
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))
+ if (!is_recoverable_dnode(page))
break;
if (!is_fsync_dnode(page))
goto next;
entry = get_fsync_inode(head, ino_of_node(page));
- if (entry) {
- if (IS_INODE(page) && is_dent_dnode(page))
- set_inode_flag(F2FS_I(entry->inode),
- FI_INC_LINK);
- } else {
- if (IS_INODE(page) && is_dent_dnode(page)) {
+ if (!entry) {
+ if (!check_only &&
+ IS_INODE(page) && is_dent_dnode(page)) {
err = recover_inode_page(sbi, page);
if (err)
break;
}
- /* add this fsync inode to the list */
- entry = kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO);
- if (!entry) {
- err = -ENOMEM;
- break;
- }
/*
* CP | dnode(F) | inode(DF)
* For this case, we should not give up now.
*/
- entry->inode = f2fs_iget(sbi->sb, ino_of_node(page));
- if (IS_ERR(entry->inode)) {
- err = PTR_ERR(entry->inode);
- kmem_cache_free(fsync_entry_slab, entry);
- if (err == -ENOENT)
+ entry = add_fsync_inode(sbi, head, ino_of_node(page));
+ if (IS_ERR(entry)) {
+ err = PTR_ERR(entry);
+ if (err == -ENOENT) {
+ err = 0;
goto next;
+ }
break;
}
- list_add_tail(&entry->list, head);
}
entry->blkaddr = blkaddr;
- if (IS_INODE(page)) {
- entry->last_inode = blkaddr;
- if (is_dent_dnode(page))
- entry->last_dentry = blkaddr;
- }
+ if (IS_INODE(page) && is_dent_dnode(page))
+ entry->last_dentry = blkaddr;
next:
/* check next segment */
blkaddr = next_blkaddr_of_node(page);
f2fs_put_page(page, 1);
+
+ ra_meta_pages_cond(sbi, blkaddr);
}
f2fs_put_page(page, 1);
return err;
@@ -236,11 +266,8 @@
{
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 +279,7 @@
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 +307,15 @@
/* 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 */
@@ -303,46 +329,60 @@
if (ino != dn->inode->i_ino) {
/* Deallocate previous index in the node page */
- inode = f2fs_iget(sbi->sb, ino);
+ inode = f2fs_iget_retry(sbi->sb, ino);
if (IS_ERR(inode))
return PTR_ERR(inode);
} else {
inode = dn->inode;
}
- bidx = start_bidx_of_node(offset, F2FS_I(inode)) +
- le16_to_cpu(sum.ofs_in_node);
+ bidx = start_bidx_of_node(offset, inode) + le16_to_cpu(sum.ofs_in_node);
- if (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))) {
- recover_xattr_data(inode, page, blkaddr);
+ err = recover_xattr_data(inode, page, blkaddr);
+ if (!err)
+ recovered++;
goto out;
}
@@ -351,99 +391,132 @@
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);
-
+retry_dn:
err = get_dnode_of_data(&dn, start, ALLOC_NODE);
if (err) {
- f2fs_unlock_op(sbi);
+ if (err == -ENOMEM) {
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ goto retry_dn;
+ }
goto out;
}
- f2fs_wait_on_page_writeback(dn.node_page, NODE);
+ f2fs_wait_on_page_writeback(dn.node_page, NODE, true);
get_node_info(sbi, dn.nid, &ni);
f2fs_bug_on(sbi, ni.ino != ino_of_node(page));
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 (!file_keep_isize(inode) &&
+ (i_size_read(inode) <= ((loff_t)start << PAGE_SHIFT)))
+ f2fs_i_size_write(inode,
+ (loff_t)(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;
}
-
+retry_prev:
/* Check the previous node page having this index */
err = check_index_in_prev_nodes(sbi, dest, &dn);
- if (err)
+ if (err) {
+ if (err == -ENOMEM) {
+ congestion_wait(BLK_RW_ASYNC, HZ/50);
+ goto retry_prev;
+ }
goto err;
-
- 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",
- inode->i_ino, recovered, err);
+ "recover_data: ino = %lx (i_size: %s) recovered = %d, err = %d",
+ inode->i_ino,
+ file_keep_isize(inode) ? "keep" : "recover",
+ recovered, err);
return err;
}
-static int recover_data(struct f2fs_sb_info *sbi,
- struct list_head *head, int type)
+static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
+ struct list_head *dir_list)
{
- unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
struct curseg_info *curseg;
struct page *page = NULL;
int err = 0;
block_t blkaddr;
/* get node pages in the current segment */
- curseg = CURSEG_I(sbi, type);
+ curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
while (1) {
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);
- if (cp_ver != cpver_of_node(page)) {
+ page = get_tmp_page(sbi, blkaddr);
+
+ if (!is_recoverable_dnode(page)) {
f2fs_put_page(page, 1);
break;
}
- entry = get_fsync_inode(head, ino_of_node(page));
+ entry = get_fsync_inode(inode_list, ino_of_node(page));
if (!entry)
goto next;
/*
@@ -451,10 +524,10 @@
* 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 +539,8 @@
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 +551,12 @@
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;
- block_t blkaddr;
+ struct list_head dir_list;
int err;
+ int ret = 0;
bool need_writecp = false;
fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry",
@@ -495,58 +565,54 @@
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);
-
- err = find_fsync_dnodes(sbi, &inode_list);
- if (err)
+ /* step #1: find fsynced inode numbers */
+ err = find_fsync_dnodes(sbi, &inode_list, check_only);
+ 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;
- if (err) {
- discard_next_dnode(sbi, blkaddr);
+ clear_sbi_flag(sbi, SBI_POR_DOING);
+ if (err)
+ set_ckpt_flags(sbi, CP_ERROR_FLAG);
+ mutex_unlock(&sbi->cp_mutex);
- /* Flush all the NAT/SIT pages */
- while (get_pages(sbi, F2FS_DIRTY_META))
- sync_meta_pages(sbi, META, LONG_MAX);
- set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
- mutex_unlock(&sbi->cp_mutex);
- } else if (need_writecp) {
+ /* let's drop all the directory inodes for clean checkpoint */
+ destroy_fsync_dnodes(&dir_list);
+
+ if (!err && need_writecp) {
struct cp_control cpc = {
- .reason = CP_SYNC,
+ .reason = CP_RECOVERY,
};
- mutex_unlock(&sbi->cp_mutex);
- write_checkpoint(sbi, &cpc);
- } else {
- mutex_unlock(&sbi->cp_mutex);
+ err = write_checkpoint(sbi, &cpc);
}
- return err;
+
+ kmem_cache_destroy(fsync_entry_slab);
+ return ret ? ret: err;
}
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 3c31221..1f1010b 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -14,20 +14,37 @@
#include <linux/blkdev.h>
#include <linux/prefetch.h>
#include <linux/kthread.h>
-#include <linux/vmalloc.h>
#include <linux/swap.h>
+#include <linux/timer.h>
#include "f2fs.h"
#include "segment.h"
#include "node.h"
+#include "trace.h"
#include <trace/events/f2fs.h>
#define __reverse_ffz(x) __reverse_ffs(~(x))
static struct kmem_cache *discard_entry_slab;
+static struct kmem_cache *discard_cmd_slab;
static struct kmem_cache *sit_entry_set_slab;
static struct kmem_cache *inmem_entry_slab;
+static unsigned long __reverse_ulong(unsigned char *str)
+{
+ unsigned long tmp = 0;
+ int shift = 24, idx = 0;
+
+#if BITS_PER_LONG == 64
+ shift = 56;
+#endif
+ while (shift >= 0) {
+ tmp |= (unsigned long)str[idx++] << shift;
+ shift -= BITS_PER_BYTE;
+ }
+ return tmp;
+}
+
/*
* __reverse_ffs is copied from include/asm-generic/bitops/__ffs.h since
* MSB and LSB are reversed in a byte by f2fs_set_bit.
@@ -37,27 +54,31 @@
int num = 0;
#if BITS_PER_LONG == 64
- if ((word & 0xffffffff) == 0) {
+ if ((word & 0xffffffff00000000UL) == 0)
num += 32;
+ else
word >>= 32;
- }
#endif
- if ((word & 0xffff) == 0) {
+ if ((word & 0xffff0000) == 0)
num += 16;
+ else
word >>= 16;
- }
- if ((word & 0xff) == 0) {
+
+ if ((word & 0xff00) == 0)
num += 8;
+ else
word >>= 8;
- }
+
if ((word & 0xf0) == 0)
num += 4;
else
word >>= 4;
+
if ((word & 0xc) == 0)
num += 2;
else
word >>= 2;
+
if ((word & 0x2) == 0)
num += 1;
return num;
@@ -66,112 +87,83 @@
/*
* __find_rev_next(_zero)_bit is copied from lib/find_next_bit.c because
* f2fs_set_bit makes MSB and LSB reversed in a byte.
+ * @size must be integral times of unsigned long.
* Example:
- * LSB <--> MSB
- * f2fs_set_bit(0, bitmap) => 0000 0001
- * f2fs_set_bit(7, bitmap) => 1000 0000
+ * MSB <--> LSB
+ * f2fs_set_bit(0, bitmap) => 1000 0000
+ * f2fs_set_bit(7, bitmap) => 0000 0001
*/
static unsigned long __find_rev_next_bit(const unsigned long *addr,
unsigned long size, unsigned long offset)
{
const unsigned long *p = addr + BIT_WORD(offset);
- unsigned long result = offset & ~(BITS_PER_LONG - 1);
+ unsigned long result = size;
unsigned long tmp;
- unsigned long mask, submask;
- unsigned long quot, rest;
if (offset >= size)
return size;
- size -= result;
+ size -= (offset & ~(BITS_PER_LONG - 1));
offset %= BITS_PER_LONG;
- if (!offset)
- goto aligned;
- tmp = *(p++);
- quot = (offset >> 3) << 3;
- rest = offset & 0x7;
- mask = ~0UL << quot;
- submask = (unsigned char)(0xff << rest) >> rest;
- submask <<= quot;
- mask &= submask;
- tmp &= mask;
- if (size < BITS_PER_LONG)
- goto found_first;
- if (tmp)
- goto found_middle;
+ while (1) {
+ if (*p == 0)
+ goto pass;
- size -= BITS_PER_LONG;
- result += BITS_PER_LONG;
-aligned:
- while (size & ~(BITS_PER_LONG-1)) {
- tmp = *(p++);
+ tmp = __reverse_ulong((unsigned char *)p);
+
+ tmp &= ~0UL >> offset;
+ if (size < BITS_PER_LONG)
+ tmp &= (~0UL << (BITS_PER_LONG - size));
if (tmp)
- goto found_middle;
- result += BITS_PER_LONG;
+ goto found;
+pass:
+ if (size <= BITS_PER_LONG)
+ break;
size -= BITS_PER_LONG;
+ offset = 0;
+ p++;
}
- if (!size)
- return result;
- tmp = *p;
-found_first:
- tmp &= (~0UL >> (BITS_PER_LONG - size));
- if (tmp == 0UL) /* Are any bits set? */
- return result + size; /* Nope. */
-found_middle:
- return result + __reverse_ffs(tmp);
+ return result;
+found:
+ return result - size + __reverse_ffs(tmp);
}
static unsigned long __find_rev_next_zero_bit(const unsigned long *addr,
unsigned long size, unsigned long offset)
{
const unsigned long *p = addr + BIT_WORD(offset);
- unsigned long result = offset & ~(BITS_PER_LONG - 1);
+ unsigned long result = size;
unsigned long tmp;
- unsigned long mask, submask;
- unsigned long quot, rest;
if (offset >= size)
return size;
- size -= result;
+ size -= (offset & ~(BITS_PER_LONG - 1));
offset %= BITS_PER_LONG;
- if (!offset)
- goto aligned;
- tmp = *(p++);
- quot = (offset >> 3) << 3;
- rest = offset & 0x7;
- mask = ~(~0UL << quot);
- submask = (unsigned char)~((unsigned char)(0xff << rest) >> rest);
- submask <<= quot;
- mask += submask;
- tmp |= mask;
- if (size < BITS_PER_LONG)
- goto found_first;
- if (~tmp)
- goto found_middle;
+ while (1) {
+ if (*p == ~0UL)
+ goto pass;
- size -= BITS_PER_LONG;
- result += BITS_PER_LONG;
-aligned:
- while (size & ~(BITS_PER_LONG - 1)) {
- tmp = *(p++);
- if (~tmp)
- goto found_middle;
- result += BITS_PER_LONG;
+ tmp = __reverse_ulong((unsigned char *)p);
+
+ if (offset)
+ tmp |= ~0UL << (BITS_PER_LONG - offset);
+ if (size < BITS_PER_LONG)
+ tmp |= ~0UL >> size;
+ if (tmp != ~0UL)
+ goto found;
+pass:
+ if (size <= BITS_PER_LONG)
+ break;
size -= BITS_PER_LONG;
+ offset = 0;
+ p++;
}
- if (!size)
- return result;
- tmp = *p;
-
-found_first:
- tmp |= ~0UL << size;
- if (tmp == ~0UL) /* Are any bits zero? */
- return result + size; /* Nope. */
-found_middle:
- return result + __reverse_ffz(tmp);
+ return result;
+found:
+ return result - size + __reverse_ffz(tmp);
}
void register_inmem_page(struct inode *inode, struct page *page)
@@ -179,6 +171,11 @@
struct f2fs_inode_info *fi = F2FS_I(inode);
struct inmem_pages *new;
+ f2fs_trace_pid(page);
+
+ set_page_private(page, (unsigned long)ATOMIC_WRITTEN_PAGE);
+ SetPagePrivate(page);
+
new = f2fs_kmem_cache_alloc(inmem_entry_slab, GFP_NOFS);
/* add atomic page indices to the list */
@@ -189,95 +186,316 @@
mutex_lock(&fi->inmem_lock);
get_page(page);
list_add_tail(&new->list, &fi->inmem_pages);
+ inc_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
mutex_unlock(&fi->inmem_lock);
+
+ trace_f2fs_register_inmem_page(page, INMEM);
}
-void commit_inmem_pages(struct inode *inode, bool abort)
+static int __revoke_inmem_pages(struct inode *inode,
+ struct list_head *head, bool drop, bool recover)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct inmem_pages *cur, *tmp;
+ int err = 0;
+
+ list_for_each_entry_safe(cur, tmp, head, list) {
+ struct page *page = cur->page;
+
+ if (drop)
+ trace_f2fs_commit_inmem_page(page, INMEM_DROP);
+
+ lock_page(page);
+
+ if (recover) {
+ struct dnode_of_data dn;
+ struct node_info ni;
+
+ trace_f2fs_commit_inmem_page(page, INMEM_REVOKE);
+
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+ if (get_dnode_of_data(&dn, page->index, LOOKUP_NODE)) {
+ err = -EAGAIN;
+ goto next;
+ }
+ get_node_info(sbi, dn.nid, &ni);
+ f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
+ cur->old_addr, ni.version, true, true);
+ f2fs_put_dnode(&dn);
+ }
+next:
+ /* we don't need to invalidate this in the sccessful status */
+ if (drop || recover)
+ ClearPageUptodate(page);
+ set_page_private(page, 0);
+ ClearPagePrivate(page);
+ f2fs_put_page(page, 1);
+
+ list_del(&cur->list);
+ kmem_cache_free(inmem_entry_slab, cur);
+ dec_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
+ }
+ return err;
+}
+
+void drop_inmem_pages(struct inode *inode)
+{
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+
+ mutex_lock(&fi->inmem_lock);
+ __revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
+ mutex_unlock(&fi->inmem_lock);
+
+ clear_inode_flag(inode, FI_ATOMIC_FILE);
+ stat_dec_atomic_write(inode);
+}
+
+void drop_inmem_page(struct inode *inode, struct page *page)
+{
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct list_head *head = &fi->inmem_pages;
+ struct inmem_pages *cur = NULL;
+
+ f2fs_bug_on(sbi, !IS_ATOMIC_WRITTEN_PAGE(page));
+
+ mutex_lock(&fi->inmem_lock);
+ list_for_each_entry(cur, head, list) {
+ if (cur->page == page)
+ break;
+ }
+
+ f2fs_bug_on(sbi, !cur || cur->page != page);
+ list_del(&cur->list);
+ mutex_unlock(&fi->inmem_lock);
+
+ dec_page_count(sbi, F2FS_INMEM_PAGES);
+ kmem_cache_free(inmem_entry_slab, cur);
+
+ ClearPageUptodate(page);
+ set_page_private(page, 0);
+ ClearPagePrivate(page);
+ f2fs_put_page(page, 0);
+
+ trace_f2fs_commit_inmem_page(page, INMEM_INVALIDATE);
+}
+
+static int __commit_inmem_pages(struct inode *inode,
+ struct list_head *revoke_list)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct f2fs_inode_info *fi = F2FS_I(inode);
struct inmem_pages *cur, *tmp;
- bool submit_bio = false;
struct f2fs_io_info fio = {
+ .sbi = sbi,
.type = DATA,
- .rw = WRITE_SYNC,
+ .op = REQ_OP_WRITE,
+ .op_flags = REQ_SYNC | REQ_PRIO,
};
+ pgoff_t last_idx = ULONG_MAX;
+ int err = 0;
- f2fs_balance_fs(sbi);
+ list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) {
+ struct page *page = cur->page;
+
+ lock_page(page);
+ if (page->mapping == inode->i_mapping) {
+ trace_f2fs_commit_inmem_page(page, INMEM);
+
+ set_page_dirty(page);
+ f2fs_wait_on_page_writeback(page, DATA, true);
+ if (clear_page_dirty_for_io(page)) {
+ inode_dec_dirty_pages(inode);
+ remove_dirty_inode(inode);
+ }
+
+ fio.page = page;
+ fio.old_blkaddr = NULL_ADDR;
+ fio.encrypted_page = NULL;
+ fio.need_lock = false,
+ err = do_write_data_page(&fio);
+ if (err) {
+ unlock_page(page);
+ break;
+ }
+
+ /* record old blkaddr for revoking */
+ cur->old_addr = fio.old_blkaddr;
+ last_idx = page->index;
+ }
+ unlock_page(page);
+ list_move_tail(&cur->list, revoke_list);
+ }
+
+ if (last_idx != ULONG_MAX)
+ f2fs_submit_merged_bio_cond(sbi, inode, 0, last_idx,
+ DATA, WRITE);
+
+ if (!err)
+ __revoke_inmem_pages(inode, revoke_list, false, false);
+
+ return err;
+}
+
+int commit_inmem_pages(struct inode *inode)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ struct list_head revoke_list;
+ int err;
+
+ INIT_LIST_HEAD(&revoke_list);
+ f2fs_balance_fs(sbi, true);
f2fs_lock_op(sbi);
+ set_inode_flag(inode, FI_ATOMIC_COMMIT);
+
mutex_lock(&fi->inmem_lock);
- list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) {
- lock_page(cur->page);
- if (!abort && cur->page->mapping == inode->i_mapping) {
- f2fs_wait_on_page_writeback(cur->page, DATA);
- if (clear_page_dirty_for_io(cur->page))
- inode_dec_dirty_pages(inode);
- do_write_data_page(cur->page, &fio);
- submit_bio = true;
- }
- f2fs_put_page(cur->page, 1);
- list_del(&cur->list);
- kmem_cache_free(inmem_entry_slab, cur);
+ err = __commit_inmem_pages(inode, &revoke_list);
+ if (err) {
+ int ret;
+ /*
+ * try to revoke all committed pages, but still we could fail
+ * due to no memory or other reason, if that happened, EAGAIN
+ * will be returned, which means in such case, transaction is
+ * already not integrity, caller should use journal to do the
+ * recovery or rewrite & commit last transaction. For other
+ * error number, revoking was done by filesystem itself.
+ */
+ ret = __revoke_inmem_pages(inode, &revoke_list, false, true);
+ if (ret)
+ err = ret;
+
+ /* drop all uncommitted pages */
+ __revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
}
- if (submit_bio)
- f2fs_submit_merged_bio(sbi, DATA, WRITE);
mutex_unlock(&fi->inmem_lock);
- filemap_fdatawait_range(inode->i_mapping, 0, LLONG_MAX);
+ clear_inode_flag(inode, FI_ATOMIC_COMMIT);
+
f2fs_unlock_op(sbi);
+ return err;
}
/*
* This function balances dirty node and dentry pages.
* In addition, it controls garbage collection.
*/
-void f2fs_balance_fs(struct f2fs_sb_info *sbi)
+void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
{
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (time_to_inject(sbi, FAULT_CHECKPOINT)) {
+ f2fs_show_injection_info(FAULT_CHECKPOINT);
+ f2fs_stop_checkpoint(sbi, false);
+ }
+#endif
+
+ /* balance_fs_bg is able to be pending */
+ if (need && excess_cached_nats(sbi))
+ f2fs_balance_fs_bg(sbi);
+
/*
* We should do GC or end up with checkpoint, if there are so many dirty
* dir/node pages without enough free segments.
*/
- if (has_not_enough_free_secs(sbi, 0)) {
+ if (has_not_enough_free_secs(sbi, 0, 0)) {
mutex_lock(&sbi->gc_mutex);
- f2fs_gc(sbi);
+ f2fs_gc(sbi, false, false, NULL_SEGNO);
}
}
void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
{
- /* check the # of cached NAT entries and prefree segments */
- if (try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK) ||
- excess_prefree_segs(sbi))
+ /* try to shrink extent cache when there is no enough memory */
+ if (!available_free_memory(sbi, EXTENT_CACHE))
+ f2fs_shrink_extent_tree(sbi, EXTENT_CACHE_SHRINK_NUMBER);
+
+ /* check the # of cached NAT entries */
+ if (!available_free_memory(sbi, NAT_ENTRIES))
+ try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK);
+
+ if (!available_free_memory(sbi, FREE_NIDS))
+ try_to_free_nids(sbi, MAX_FREE_NIDS);
+ else
+ build_free_nids(sbi, false, false);
+
+ if (!is_idle(sbi) && !excess_dirty_nats(sbi))
+ return;
+
+ /* checkpoint is the only way to shrink partial cached entries */
+ if (!available_free_memory(sbi, NAT_ENTRIES) ||
+ !available_free_memory(sbi, INO_ENTRIES) ||
+ excess_prefree_segs(sbi) ||
+ excess_dirty_nats(sbi) ||
+ f2fs_time_over(sbi, CP_TIME)) {
+ if (test_opt(sbi, DATA_FLUSH)) {
+ struct blk_plug plug;
+
+ blk_start_plug(&plug);
+ sync_dirty_inodes(sbi, FILE_INODE);
+ blk_finish_plug(&plug);
+ }
f2fs_sync_fs(sbi->sb, true);
+ stat_inc_bg_cp_count(sbi->stat_info);
+ }
+}
+
+static int __submit_flush_wait(struct f2fs_sb_info *sbi,
+ struct block_device *bdev)
+{
+ struct bio *bio = f2fs_bio_alloc(0);
+ int ret;
+
+ bio->bi_rw = REQ_OP_WRITE;
+ bio->bi_bdev = bdev;
+ ret = submit_bio_wait(WRITE_FLUSH, bio);
+ bio_put(bio);
+
+ trace_f2fs_issue_flush(bdev, test_opt(sbi, NOBARRIER),
+ test_opt(sbi, FLUSH_MERGE), ret);
+ return ret;
+}
+
+static int submit_flush_wait(struct f2fs_sb_info *sbi)
+{
+ int ret = __submit_flush_wait(sbi, sbi->sb->s_bdev);
+ int i;
+
+ if (!sbi->s_ndevs || ret)
+ return ret;
+
+ for (i = 1; i < sbi->s_ndevs; i++) {
+ ret = __submit_flush_wait(sbi, FDEV(i).bdev);
+ if (ret)
+ break;
+ }
+ return ret;
}
static int issue_flush_thread(void *data)
{
struct f2fs_sb_info *sbi = data;
- struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info;
+ struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info;
wait_queue_head_t *q = &fcc->flush_wait_queue;
repeat:
if (kthread_should_stop())
return 0;
if (!llist_empty(&fcc->issue_list)) {
- struct bio *bio = bio_alloc(GFP_NOIO, 0);
struct flush_cmd *cmd, *next;
int ret;
fcc->dispatch_list = llist_del_all(&fcc->issue_list);
fcc->dispatch_list = llist_reverse_order(fcc->dispatch_list);
- bio->bi_bdev = sbi->sb->s_bdev;
- ret = submit_bio_wait(WRITE_FLUSH, bio);
+ ret = submit_flush_wait(sbi);
+ atomic_inc(&fcc->issued_flush);
llist_for_each_entry_safe(cmd, next,
fcc->dispatch_list, llnode) {
cmd->ret = ret;
complete(&cmd->wait);
}
- bio_put(bio);
fcc->dispatch_list = NULL;
}
@@ -288,26 +506,43 @@
int f2fs_issue_flush(struct f2fs_sb_info *sbi)
{
- struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info;
+ struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info;
struct flush_cmd cmd;
-
- trace_f2fs_issue_flush(sbi->sb, test_opt(sbi, NOBARRIER),
- test_opt(sbi, FLUSH_MERGE));
+ int ret;
if (test_opt(sbi, NOBARRIER))
return 0;
- if (!test_opt(sbi, FLUSH_MERGE))
- return blkdev_issue_flush(sbi->sb->s_bdev, GFP_KERNEL, NULL);
+ if (!test_opt(sbi, FLUSH_MERGE)) {
+ ret = submit_flush_wait(sbi);
+ atomic_inc(&fcc->issued_flush);
+ return ret;
+ }
+
+ if (!atomic_read(&fcc->issing_flush)) {
+ atomic_inc(&fcc->issing_flush);
+ ret = submit_flush_wait(sbi);
+ atomic_dec(&fcc->issing_flush);
+
+ atomic_inc(&fcc->issued_flush);
+ return ret;
+ }
init_completion(&cmd.wait);
+ atomic_inc(&fcc->issing_flush);
llist_add(&cmd.llnode, &fcc->issue_list);
if (!fcc->dispatch_list)
wake_up(&fcc->flush_wait_queue);
- wait_for_completion(&cmd.wait);
+ if (fcc->f2fs_issue_flush) {
+ wait_for_completion(&cmd.wait);
+ atomic_dec(&fcc->issing_flush);
+ } else {
+ llist_del_all(&fcc->issue_list);
+ atomic_set(&fcc->issing_flush, 0);
+ }
return cmd.ret;
}
@@ -318,32 +553,46 @@
struct flush_cmd_control *fcc;
int err = 0;
+ if (SM_I(sbi)->fcc_info) {
+ fcc = SM_I(sbi)->fcc_info;
+ goto init_thread;
+ }
+
fcc = kzalloc(sizeof(struct flush_cmd_control), GFP_KERNEL);
if (!fcc)
return -ENOMEM;
+ atomic_set(&fcc->issued_flush, 0);
+ atomic_set(&fcc->issing_flush, 0);
init_waitqueue_head(&fcc->flush_wait_queue);
init_llist_head(&fcc->issue_list);
- SM_I(sbi)->cmd_control_info = fcc;
+ SM_I(sbi)->fcc_info = fcc;
+init_thread:
fcc->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi,
"f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
if (IS_ERR(fcc->f2fs_issue_flush)) {
err = PTR_ERR(fcc->f2fs_issue_flush);
kfree(fcc);
- SM_I(sbi)->cmd_control_info = NULL;
+ SM_I(sbi)->fcc_info = NULL;
return err;
}
return err;
}
-void destroy_flush_cmd_control(struct f2fs_sb_info *sbi)
+void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free)
{
- struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info;
+ struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info;
- if (fcc && fcc->f2fs_issue_flush)
- kthread_stop(fcc->f2fs_issue_flush);
- kfree(fcc);
- SM_I(sbi)->cmd_control_info = NULL;
+ if (fcc && fcc->f2fs_issue_flush) {
+ struct task_struct *flush_thread = fcc->f2fs_issue_flush;
+
+ fcc->f2fs_issue_flush = NULL;
+ kthread_stop(flush_thread);
+ }
+ if (free) {
+ kfree(fcc);
+ SM_I(sbi)->fcc_info = NULL;
+ }
}
static void __locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
@@ -386,8 +635,8 @@
if (test_and_clear_bit(segno, dirty_i->dirty_segmap[t]))
dirty_i->nr_dirty[t]--;
- if (get_valid_blocks(sbi, segno, sbi->segs_per_sec) == 0)
- clear_bit(GET_SECNO(sbi, segno),
+ if (get_valid_blocks(sbi, segno, true) == 0)
+ clear_bit(GET_SEC_FROM_SEG(sbi, segno),
dirty_i->victim_secmap);
}
}
@@ -407,7 +656,7 @@
mutex_lock(&dirty_i->seglist_lock);
- valid_blocks = get_valid_blocks(sbi, segno, 0);
+ valid_blocks = get_valid_blocks(sbi, segno, false);
if (valid_blocks == 0) {
__locate_dirty_segment(sbi, segno, PRE);
@@ -422,99 +671,649 @@
mutex_unlock(&dirty_i->seglist_lock);
}
-static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
- block_t blkstart, block_t blklen)
+static struct discard_cmd *__create_discard_cmd(struct f2fs_sb_info *sbi,
+ struct block_device *bdev, block_t lstart,
+ block_t start, block_t len)
{
- sector_t start = SECTOR_FROM_BLOCK(blkstart);
- sector_t len = SECTOR_FROM_BLOCK(blklen);
- trace_f2fs_issue_discard(sbi->sb, blkstart, blklen);
- return blkdev_issue_discard(sbi->sb->s_bdev, start, len, GFP_NOFS, 0);
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct list_head *pend_list;
+ struct discard_cmd *dc;
+
+ f2fs_bug_on(sbi, !len);
+
+ pend_list = &dcc->pend_list[plist_idx(len)];
+
+ dc = f2fs_kmem_cache_alloc(discard_cmd_slab, GFP_NOFS);
+ INIT_LIST_HEAD(&dc->list);
+ dc->bdev = bdev;
+ dc->lstart = lstart;
+ dc->start = start;
+ dc->len = len;
+ dc->ref = 0;
+ dc->state = D_PREP;
+ dc->error = 0;
+ init_completion(&dc->wait);
+ list_add_tail(&dc->list, pend_list);
+ atomic_inc(&dcc->discard_cmd_cnt);
+ dcc->undiscard_blks += len;
+
+ return dc;
}
-void discard_next_dnode(struct f2fs_sb_info *sbi, block_t blkaddr)
+static struct discard_cmd *__attach_discard_cmd(struct f2fs_sb_info *sbi,
+ struct block_device *bdev, block_t lstart,
+ block_t start, block_t len,
+ struct rb_node *parent, struct rb_node **p)
{
- if (f2fs_issue_discard(sbi, blkaddr, 1)) {
- struct page *page = grab_meta_page(sbi, blkaddr);
- /* zero-filled page */
- set_page_dirty(page);
- f2fs_put_page(page, 1);
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct discard_cmd *dc;
+
+ dc = __create_discard_cmd(sbi, bdev, lstart, start, len);
+
+ rb_link_node(&dc->rb_node, parent, p);
+ rb_insert_color(&dc->rb_node, &dcc->root);
+
+ return dc;
+}
+
+static void __detach_discard_cmd(struct discard_cmd_control *dcc,
+ struct discard_cmd *dc)
+{
+ if (dc->state == D_DONE)
+ atomic_dec(&dcc->issing_discard);
+
+ list_del(&dc->list);
+ rb_erase(&dc->rb_node, &dcc->root);
+ dcc->undiscard_blks -= dc->len;
+
+ kmem_cache_free(discard_cmd_slab, dc);
+
+ atomic_dec(&dcc->discard_cmd_cnt);
+}
+
+static void __remove_discard_cmd(struct f2fs_sb_info *sbi,
+ struct discard_cmd *dc)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+
+ if (dc->error == -EOPNOTSUPP)
+ dc->error = 0;
+
+ if (dc->error)
+ f2fs_msg(sbi->sb, KERN_INFO,
+ "Issue discard failed, ret: %d", dc->error);
+ __detach_discard_cmd(dcc, dc);
+}
+
+static void f2fs_submit_discard_endio(struct bio *bio, int err)
+{
+ struct discard_cmd *dc = (struct discard_cmd *)bio->bi_private;
+
+ dc->error = err;
+ dc->state = D_DONE;
+ complete(&dc->wait);
+ bio_put(bio);
+}
+
+/* copied from block/blk-lib.c in 4.10-rc1 */
+static int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
+ sector_t nr_sects, gfp_t gfp_mask, int flags,
+ struct bio **biop)
+{
+ struct request_queue *q = bdev_get_queue(bdev);
+ struct bio *bio = *biop;
+ unsigned int granularity;
+ int op = REQ_WRITE | REQ_DISCARD;
+ int alignment;
+ sector_t bs_mask;
+
+ if (!q)
+ return -ENXIO;
+
+ if (!blk_queue_discard(q))
+ return -EOPNOTSUPP;
+
+ if (flags & BLKDEV_DISCARD_SECURE) {
+ if (!blk_queue_secdiscard(q))
+ return -EOPNOTSUPP;
+ op |= REQ_SECURE;
+ }
+
+ bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
+ if ((sector | nr_sects) & bs_mask)
+ return -EINVAL;
+
+ /* Zero-sector (unknown) and one-sector granularities are the same. */
+ granularity = max(q->limits.discard_granularity >> 9, 1U);
+ alignment = (bdev_discard_alignment(bdev) >> 9) % granularity;
+
+ while (nr_sects) {
+ unsigned int req_sects;
+ sector_t end_sect, tmp;
+
+ /* Make sure bi_size doesn't overflow */
+ req_sects = min_t(sector_t, nr_sects, UINT_MAX >> 9);
+
+ /**
+ * If splitting a request, and the next starting sector would be
+ * misaligned, stop the discard at the previous aligned sector.
+ */
+ end_sect = sector + req_sects;
+ tmp = end_sect;
+ if (req_sects < nr_sects &&
+ sector_div(tmp, granularity) != alignment) {
+ end_sect = end_sect - alignment;
+ sector_div(end_sect, granularity);
+ end_sect = end_sect * granularity + alignment;
+ req_sects = end_sect - sector;
+ }
+
+ if (bio) {
+ int ret = submit_bio_wait(0, bio);
+ bio_put(bio);
+ if (ret)
+ return ret;
+ }
+ bio = f2fs_bio_alloc(1);
+ bio->bi_iter.bi_sector = sector;
+ bio->bi_bdev = bdev;
+ bio_set_op_attrs(bio, op, 0);
+
+ bio->bi_iter.bi_size = req_sects << 9;
+ nr_sects -= req_sects;
+ sector = end_sect;
+
+ /*
+ * We can loop for a long time in here, if someone does
+ * full device discards (like mkfs). Be nice and allow
+ * us to schedule out to avoid softlocking if preempt
+ * is disabled.
+ */
+ cond_resched();
+ }
+
+ *biop = bio;
+ return 0;
+}
+
+static void __submit_discard_cmd(struct f2fs_sb_info *sbi,
+ struct discard_cmd *dc)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct bio *bio = NULL;
+
+ if (dc->state != D_PREP)
+ return;
+
+ trace_f2fs_issue_discard(dc->bdev, dc->start, dc->len);
+
+ dc->error = __blkdev_issue_discard(dc->bdev,
+ SECTOR_FROM_BLOCK(dc->start),
+ SECTOR_FROM_BLOCK(dc->len),
+ GFP_NOFS, 0, &bio);
+ if (!dc->error) {
+ /* should keep before submission to avoid D_DONE right away */
+ dc->state = D_SUBMIT;
+ atomic_inc(&dcc->issued_discard);
+ atomic_inc(&dcc->issing_discard);
+ if (bio) {
+ bio->bi_private = dc;
+ bio->bi_end_io = f2fs_submit_discard_endio;
+ submit_bio(REQ_SYNC, bio);
+ list_move_tail(&dc->list, &dcc->wait_list);
+ }
+ } else {
+ __remove_discard_cmd(sbi, dc);
}
}
-static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
+static struct discard_cmd *__insert_discard_tree(struct f2fs_sb_info *sbi,
+ struct block_device *bdev, block_t lstart,
+ block_t start, block_t len,
+ struct rb_node **insert_p,
+ struct rb_node *insert_parent)
{
- struct list_head *head = &SM_I(sbi)->discard_list;
- struct discard_entry *new;
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct rb_node **p = &dcc->root.rb_node;
+ struct rb_node *parent = NULL;
+ struct discard_cmd *dc = NULL;
+
+ if (insert_p && insert_parent) {
+ parent = insert_parent;
+ p = insert_p;
+ goto do_insert;
+ }
+
+ p = __lookup_rb_tree_for_insert(sbi, &dcc->root, &parent, lstart);
+do_insert:
+ dc = __attach_discard_cmd(sbi, bdev, lstart, start, len, parent, p);
+ if (!dc)
+ return NULL;
+
+ return dc;
+}
+
+static void __relocate_discard_cmd(struct discard_cmd_control *dcc,
+ struct discard_cmd *dc)
+{
+ list_move_tail(&dc->list, &dcc->pend_list[plist_idx(dc->len)]);
+}
+
+static void __punch_discard_cmd(struct f2fs_sb_info *sbi,
+ struct discard_cmd *dc, block_t blkaddr)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct discard_info di = dc->di;
+ bool modified = false;
+
+ if (dc->state == D_DONE || dc->len == 1) {
+ __remove_discard_cmd(sbi, dc);
+ return;
+ }
+
+ dcc->undiscard_blks -= di.len;
+
+ if (blkaddr > di.lstart) {
+ dc->len = blkaddr - dc->lstart;
+ dcc->undiscard_blks += dc->len;
+ __relocate_discard_cmd(dcc, dc);
+ f2fs_bug_on(sbi, !__check_rb_tree_consistence(sbi, &dcc->root));
+ modified = true;
+ }
+
+ if (blkaddr < di.lstart + di.len - 1) {
+ if (modified) {
+ __insert_discard_tree(sbi, dc->bdev, blkaddr + 1,
+ di.start + blkaddr + 1 - di.lstart,
+ di.lstart + di.len - 1 - blkaddr,
+ NULL, NULL);
+ f2fs_bug_on(sbi,
+ !__check_rb_tree_consistence(sbi, &dcc->root));
+ } else {
+ dc->lstart++;
+ dc->len--;
+ dc->start++;
+ dcc->undiscard_blks += dc->len;
+ __relocate_discard_cmd(dcc, dc);
+ f2fs_bug_on(sbi,
+ !__check_rb_tree_consistence(sbi, &dcc->root));
+ }
+ }
+}
+
+static void __update_discard_tree_range(struct f2fs_sb_info *sbi,
+ struct block_device *bdev, block_t lstart,
+ block_t start, block_t len)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct discard_cmd *prev_dc = NULL, *next_dc = NULL;
+ struct discard_cmd *dc;
+ struct discard_info di = {0};
+ struct rb_node **insert_p = NULL, *insert_parent = NULL;
+ block_t end = lstart + len;
+
+ mutex_lock(&dcc->cmd_lock);
+
+ dc = (struct discard_cmd *)__lookup_rb_tree_ret(&dcc->root,
+ NULL, lstart,
+ (struct rb_entry **)&prev_dc,
+ (struct rb_entry **)&next_dc,
+ &insert_p, &insert_parent, true);
+ if (dc)
+ prev_dc = dc;
+
+ if (!prev_dc) {
+ di.lstart = lstart;
+ di.len = next_dc ? next_dc->lstart - lstart : len;
+ di.len = min(di.len, len);
+ di.start = start;
+ }
+
+ while (1) {
+ struct rb_node *node;
+ bool merged = false;
+ struct discard_cmd *tdc = NULL;
+
+ if (prev_dc) {
+ di.lstart = prev_dc->lstart + prev_dc->len;
+ if (di.lstart < lstart)
+ di.lstart = lstart;
+ if (di.lstart >= end)
+ break;
+
+ if (!next_dc || next_dc->lstart > end)
+ di.len = end - di.lstart;
+ else
+ di.len = next_dc->lstart - di.lstart;
+ di.start = start + di.lstart - lstart;
+ }
+
+ if (!di.len)
+ goto next;
+
+ if (prev_dc && prev_dc->state == D_PREP &&
+ prev_dc->bdev == bdev &&
+ __is_discard_back_mergeable(&di, &prev_dc->di)) {
+ prev_dc->di.len += di.len;
+ dcc->undiscard_blks += di.len;
+ __relocate_discard_cmd(dcc, prev_dc);
+ f2fs_bug_on(sbi,
+ !__check_rb_tree_consistence(sbi, &dcc->root));
+ di = prev_dc->di;
+ tdc = prev_dc;
+ merged = true;
+ }
+
+ if (next_dc && next_dc->state == D_PREP &&
+ next_dc->bdev == bdev &&
+ __is_discard_front_mergeable(&di, &next_dc->di)) {
+ next_dc->di.lstart = di.lstart;
+ next_dc->di.len += di.len;
+ next_dc->di.start = di.start;
+ dcc->undiscard_blks += di.len;
+ __relocate_discard_cmd(dcc, next_dc);
+ if (tdc)
+ __remove_discard_cmd(sbi, tdc);
+ f2fs_bug_on(sbi,
+ !__check_rb_tree_consistence(sbi, &dcc->root));
+ merged = true;
+ }
+
+ if (!merged) {
+ __insert_discard_tree(sbi, bdev, di.lstart, di.start,
+ di.len, NULL, NULL);
+ f2fs_bug_on(sbi,
+ !__check_rb_tree_consistence(sbi, &dcc->root));
+ }
+ next:
+ prev_dc = next_dc;
+ if (!prev_dc)
+ break;
+
+ node = rb_next(&prev_dc->rb_node);
+ next_dc = rb_entry_safe(node, struct discard_cmd, rb_node);
+ }
+
+ mutex_unlock(&dcc->cmd_lock);
+}
+
+static int __queue_discard_cmd(struct f2fs_sb_info *sbi,
+ struct block_device *bdev, block_t blkstart, block_t blklen)
+{
+ block_t lblkstart = blkstart;
+
+ trace_f2fs_queue_discard(bdev, blkstart, blklen);
+
+ if (sbi->s_ndevs) {
+ int devi = f2fs_target_device_index(sbi, blkstart);
+
+ blkstart -= FDEV(devi).start_blk;
+ }
+ __update_discard_tree_range(sbi, bdev, lblkstart, blkstart, blklen);
+ return 0;
+}
+
+static void __issue_discard_cmd(struct f2fs_sb_info *sbi, bool issue_cond)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct list_head *pend_list;
+ struct discard_cmd *dc, *tmp;
+ struct blk_plug plug;
+ int i, iter = 0;
+
+ mutex_lock(&dcc->cmd_lock);
+ blk_start_plug(&plug);
+ for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
+ pend_list = &dcc->pend_list[i];
+ list_for_each_entry_safe(dc, tmp, pend_list, list) {
+ f2fs_bug_on(sbi, dc->state != D_PREP);
+
+ if (!issue_cond || is_idle(sbi))
+ __submit_discard_cmd(sbi, dc);
+ if (issue_cond && iter++ > DISCARD_ISSUE_RATE)
+ goto out;
+ }
+ }
+out:
+ blk_finish_plug(&plug);
+ mutex_unlock(&dcc->cmd_lock);
+}
+
+static void __wait_discard_cmd(struct f2fs_sb_info *sbi, bool wait_cond)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct list_head *wait_list = &(dcc->wait_list);
+ struct discard_cmd *dc, *tmp;
+
+ mutex_lock(&dcc->cmd_lock);
+ list_for_each_entry_safe(dc, tmp, wait_list, list) {
+ if (!wait_cond || dc->state == D_DONE) {
+ if (dc->ref)
+ continue;
+ wait_for_completion_io(&dc->wait);
+ __remove_discard_cmd(sbi, dc);
+ }
+ }
+ mutex_unlock(&dcc->cmd_lock);
+}
+
+/* This should be covered by global mutex, &sit_i->sentry_lock */
+void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ struct discard_cmd *dc;
+ bool need_wait = false;
+
+ mutex_lock(&dcc->cmd_lock);
+ dc = (struct discard_cmd *)__lookup_rb_tree(&dcc->root, NULL, blkaddr);
+ if (dc) {
+ if (dc->state == D_PREP) {
+ __punch_discard_cmd(sbi, dc, blkaddr);
+ } else {
+ dc->ref++;
+ need_wait = true;
+ }
+ }
+ mutex_unlock(&dcc->cmd_lock);
+
+ if (need_wait) {
+ wait_for_completion_io(&dc->wait);
+ mutex_lock(&dcc->cmd_lock);
+ f2fs_bug_on(sbi, dc->state != D_DONE);
+ dc->ref--;
+ if (!dc->ref)
+ __remove_discard_cmd(sbi, dc);
+ mutex_unlock(&dcc->cmd_lock);
+ }
+}
+
+/* This comes from f2fs_put_super */
+void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi)
+{
+ __issue_discard_cmd(sbi, false);
+ __wait_discard_cmd(sbi, false);
+}
+
+static int issue_discard_thread(void *data)
+{
+ struct f2fs_sb_info *sbi = data;
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+ wait_queue_head_t *q = &dcc->discard_wait_queue;
+repeat:
+ if (kthread_should_stop())
+ return 0;
+
+ __issue_discard_cmd(sbi, true);
+ __wait_discard_cmd(sbi, true);
+
+ congestion_wait(BLK_RW_SYNC, HZ/50);
+
+ wait_event_interruptible(*q, kthread_should_stop() ||
+ atomic_read(&dcc->discard_cmd_cnt));
+ goto repeat;
+}
+
+#ifdef CONFIG_BLK_DEV_ZONED
+static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi,
+ struct block_device *bdev, block_t blkstart, block_t blklen)
+{
+ sector_t sector, nr_sects;
+ block_t lblkstart = blkstart;
+ int devi = 0;
+
+ if (sbi->s_ndevs) {
+ devi = f2fs_target_device_index(sbi, blkstart);
+ blkstart -= FDEV(devi).start_blk;
+ }
+
+ /*
+ * We need to know the type of the zone: for conventional zones,
+ * use regular discard if the drive supports it. For sequential
+ * zones, reset the zone write pointer.
+ */
+ switch (get_blkz_type(sbi, bdev, blkstart)) {
+
+ case BLK_ZONE_TYPE_CONVENTIONAL:
+ if (!blk_queue_discard(bdev_get_queue(bdev)))
+ return 0;
+ return __queue_discard_cmd(sbi, bdev, lblkstart, blklen);
+ case BLK_ZONE_TYPE_SEQWRITE_REQ:
+ case BLK_ZONE_TYPE_SEQWRITE_PREF:
+ sector = SECTOR_FROM_BLOCK(blkstart);
+ nr_sects = SECTOR_FROM_BLOCK(blklen);
+
+ if (sector & (bdev_zone_size(bdev) - 1) ||
+ nr_sects != bdev_zone_size(bdev)) {
+ f2fs_msg(sbi->sb, KERN_INFO,
+ "(%d) %s: Unaligned discard attempted (block %x + %x)",
+ devi, sbi->s_ndevs ? FDEV(devi).path: "",
+ blkstart, blklen);
+ return -EIO;
+ }
+ trace_f2fs_issue_reset_zone(bdev, blkstart);
+ return blkdev_reset_zones(bdev, sector,
+ nr_sects, GFP_NOFS);
+ default:
+ /* Unknown zone type: broken device ? */
+ return -EIO;
+ }
+}
+#endif
+
+static int __issue_discard_async(struct f2fs_sb_info *sbi,
+ struct block_device *bdev, block_t blkstart, block_t blklen)
+{
+#ifdef CONFIG_BLK_DEV_ZONED
+ if (f2fs_sb_mounted_blkzoned(sbi->sb) &&
+ bdev_zoned_model(bdev) != BLK_ZONED_NONE)
+ return __f2fs_issue_discard_zone(sbi, bdev, blkstart, blklen);
+#endif
+ return __queue_discard_cmd(sbi, bdev, blkstart, blklen);
+}
+
+static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
+ block_t blkstart, block_t blklen)
+{
+ sector_t start = blkstart, len = 0;
+ struct block_device *bdev;
+ struct seg_entry *se;
+ unsigned int offset;
+ block_t i;
+ int err = 0;
+
+ bdev = f2fs_target_device(sbi, blkstart, NULL);
+
+ for (i = blkstart; i < blkstart + blklen; i++, len++) {
+ if (i != start) {
+ struct block_device *bdev2 =
+ f2fs_target_device(sbi, i, NULL);
+
+ if (bdev2 != bdev) {
+ err = __issue_discard_async(sbi, bdev,
+ start, len);
+ if (err)
+ return err;
+ bdev = bdev2;
+ start = i;
+ len = 0;
+ }
+ }
+
+ se = get_seg_entry(sbi, GET_SEGNO(sbi, i));
+ offset = GET_BLKOFF_FROM_SEG0(sbi, i);
+
+ if (!f2fs_test_and_set_bit(offset, se->discard_map))
+ sbi->discard_blks--;
+ }
+
+ if (len)
+ err = __issue_discard_async(sbi, bdev, start, len);
+ return err;
+}
+
+static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc,
+ bool check_only)
+{
int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long);
int max_blocks = sbi->blocks_per_seg;
struct seg_entry *se = get_seg_entry(sbi, cpc->trim_start);
unsigned long *cur_map = (unsigned long *)se->cur_valid_map;
unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map;
- unsigned long dmap[entries];
+ unsigned long *discard_map = (unsigned long *)se->discard_map;
+ unsigned long *dmap = SIT_I(sbi)->tmp_map;
unsigned int start = 0, end = -1;
- bool force = (cpc->reason == CP_DISCARD);
+ bool force = (cpc->reason & CP_DISCARD);
+ struct discard_entry *de = NULL;
+ struct list_head *head = &SM_I(sbi)->dcc_info->entry_list;
int i;
- if (!force && !test_opt(sbi, DISCARD))
- return;
+ if (se->valid_blocks == max_blocks || !f2fs_discard_en(sbi))
+ return false;
- if (force && !se->valid_blocks) {
- struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- /*
- * if this segment is registered in the prefree list, then
- * we should skip adding a discard candidate, and let the
- * checkpoint do that later.
- */
- mutex_lock(&dirty_i->seglist_lock);
- if (test_bit(cpc->trim_start, dirty_i->dirty_segmap[PRE])) {
- mutex_unlock(&dirty_i->seglist_lock);
- cpc->trimmed += sbi->blocks_per_seg;
- return;
- }
- mutex_unlock(&dirty_i->seglist_lock);
-
- new = f2fs_kmem_cache_alloc(discard_entry_slab, GFP_NOFS);
- INIT_LIST_HEAD(&new->list);
- new->blkaddr = START_BLOCK(sbi, cpc->trim_start);
- new->len = sbi->blocks_per_seg;
- list_add_tail(&new->list, head);
- SM_I(sbi)->nr_discards += sbi->blocks_per_seg;
- cpc->trimmed += sbi->blocks_per_seg;
- return;
+ if (!force) {
+ if (!test_opt(sbi, DISCARD) || !se->valid_blocks ||
+ SM_I(sbi)->dcc_info->nr_discards >=
+ SM_I(sbi)->dcc_info->max_discards)
+ return false;
}
- /* zero block will be discarded through the prefree list */
- if (!se->valid_blocks || se->valid_blocks == max_blocks)
- return;
-
/* SIT_VBLOCK_MAP_SIZE should be multiple of sizeof(unsigned long) */
for (i = 0; i < entries; i++)
- dmap[i] = (cur_map[i] ^ ckpt_map[i]) & ckpt_map[i];
+ dmap[i] = force ? ~ckpt_map[i] & ~discard_map[i] :
+ (cur_map[i] ^ ckpt_map[i]) & ckpt_map[i];
- while (force || SM_I(sbi)->nr_discards <= SM_I(sbi)->max_discards) {
+ while (force || SM_I(sbi)->dcc_info->nr_discards <=
+ SM_I(sbi)->dcc_info->max_discards) {
start = __find_rev_next_bit(dmap, max_blocks, end + 1);
if (start >= max_blocks)
break;
end = __find_rev_next_zero_bit(dmap, max_blocks, start + 1);
-
- if (end - start < cpc->trim_minlen)
+ if (force && start && end != max_blocks
+ && (end - start) < cpc->trim_minlen)
continue;
- new = f2fs_kmem_cache_alloc(discard_entry_slab, GFP_NOFS);
- INIT_LIST_HEAD(&new->list);
- new->blkaddr = START_BLOCK(sbi, cpc->trim_start) + start;
- new->len = end - start;
- cpc->trimmed += end - start;
+ if (check_only)
+ return true;
- list_add_tail(&new->list, head);
- SM_I(sbi)->nr_discards += end - start;
+ if (!de) {
+ de = f2fs_kmem_cache_alloc(discard_entry_slab,
+ GFP_F2FS_ZERO);
+ de->start_blkaddr = START_BLOCK(sbi, cpc->trim_start);
+ list_add_tail(&de->list, head);
+ }
+
+ for (i = start; i < end; i++)
+ __set_bit_le(i, (void *)de->discard_map);
+
+ SM_I(sbi)->dcc_info->nr_discards += end - start;
}
+ return false;
}
void release_discard_addrs(struct f2fs_sb_info *sbi)
{
- struct list_head *head = &(SM_I(sbi)->discard_list);
+ struct list_head *head = &(SM_I(sbi)->dcc_info->entry_list);
struct discard_entry *entry, *this;
/* drop caches */
@@ -538,13 +1337,15 @@
mutex_unlock(&dirty_i->seglist_lock);
}
-void clear_prefree_segments(struct f2fs_sb_info *sbi)
+void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
{
- struct list_head *head = &(SM_I(sbi)->discard_list);
+ struct list_head *head = &(SM_I(sbi)->dcc_info->entry_list);
struct discard_entry *entry, *this;
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
unsigned long *prefree_map = dirty_i->dirty_segmap[PRE];
unsigned int start = 0, end = -1;
+ unsigned int secno, start_segno;
+ bool force = (cpc->reason & CP_DISCARD);
mutex_lock(&dirty_i->seglist_lock);
@@ -564,18 +1365,127 @@
if (!test_opt(sbi, DISCARD))
continue;
- f2fs_issue_discard(sbi, START_BLOCK(sbi, start),
+ if (force && start >= cpc->trim_start &&
+ (end - 1) <= cpc->trim_end)
+ continue;
+
+ if (!test_opt(sbi, LFS) || sbi->segs_per_sec == 1) {
+ f2fs_issue_discard(sbi, START_BLOCK(sbi, start),
(end - start) << sbi->log_blocks_per_seg);
+ continue;
+ }
+next:
+ secno = GET_SEC_FROM_SEG(sbi, start);
+ start_segno = GET_SEG_FROM_SEC(sbi, secno);
+ if (!IS_CURSEC(sbi, secno) &&
+ !get_valid_blocks(sbi, start, true))
+ f2fs_issue_discard(sbi, START_BLOCK(sbi, start_segno),
+ sbi->segs_per_sec << sbi->log_blocks_per_seg);
+
+ start = start_segno + sbi->segs_per_sec;
+ if (start < end)
+ goto next;
+ else
+ end = start - 1;
}
mutex_unlock(&dirty_i->seglist_lock);
/* send small discards */
list_for_each_entry_safe(entry, this, head, list) {
- f2fs_issue_discard(sbi, entry->blkaddr, entry->len);
+ unsigned int cur_pos = 0, next_pos, len, total_len = 0;
+ bool is_valid = test_bit_le(0, entry->discard_map);
+
+find_next:
+ if (is_valid) {
+ next_pos = find_next_zero_bit_le(entry->discard_map,
+ sbi->blocks_per_seg, cur_pos);
+ len = next_pos - cur_pos;
+
+ if (force && len < cpc->trim_minlen)
+ goto skip;
+
+ f2fs_issue_discard(sbi, entry->start_blkaddr + cur_pos,
+ len);
+ cpc->trimmed += len;
+ total_len += len;
+ } else {
+ next_pos = find_next_bit_le(entry->discard_map,
+ sbi->blocks_per_seg, cur_pos);
+ }
+skip:
+ cur_pos = next_pos;
+ is_valid = !is_valid;
+
+ if (cur_pos < sbi->blocks_per_seg)
+ goto find_next;
+
list_del(&entry->list);
- SM_I(sbi)->nr_discards -= entry->len;
+ SM_I(sbi)->dcc_info->nr_discards -= total_len;
kmem_cache_free(discard_entry_slab, entry);
}
+
+ wake_up(&SM_I(sbi)->dcc_info->discard_wait_queue);
+}
+
+static int create_discard_cmd_control(struct f2fs_sb_info *sbi)
+{
+ dev_t dev = sbi->sb->s_bdev->bd_dev;
+ struct discard_cmd_control *dcc;
+ int err = 0, i;
+
+ if (SM_I(sbi)->dcc_info) {
+ dcc = SM_I(sbi)->dcc_info;
+ goto init_thread;
+ }
+
+ dcc = kzalloc(sizeof(struct discard_cmd_control), GFP_KERNEL);
+ if (!dcc)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&dcc->entry_list);
+ for (i = 0; i < MAX_PLIST_NUM; i++)
+ INIT_LIST_HEAD(&dcc->pend_list[i]);
+ INIT_LIST_HEAD(&dcc->wait_list);
+ mutex_init(&dcc->cmd_lock);
+ atomic_set(&dcc->issued_discard, 0);
+ atomic_set(&dcc->issing_discard, 0);
+ atomic_set(&dcc->discard_cmd_cnt, 0);
+ dcc->nr_discards = 0;
+ dcc->max_discards = MAIN_SEGS(sbi) << sbi->log_blocks_per_seg;
+ dcc->undiscard_blks = 0;
+ dcc->root = RB_ROOT;
+
+ init_waitqueue_head(&dcc->discard_wait_queue);
+ SM_I(sbi)->dcc_info = dcc;
+init_thread:
+ dcc->f2fs_issue_discard = kthread_run(issue_discard_thread, sbi,
+ "f2fs_discard-%u:%u", MAJOR(dev), MINOR(dev));
+ if (IS_ERR(dcc->f2fs_issue_discard)) {
+ err = PTR_ERR(dcc->f2fs_issue_discard);
+ kfree(dcc);
+ SM_I(sbi)->dcc_info = NULL;
+ return err;
+ }
+
+ return err;
+}
+
+static void destroy_discard_cmd_control(struct f2fs_sb_info *sbi)
+{
+ struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+
+ if (!dcc)
+ return;
+
+ if (dcc->f2fs_issue_discard) {
+ struct task_struct *discard_thread = dcc->f2fs_issue_discard;
+
+ dcc->f2fs_issue_discard = NULL;
+ kthread_stop(discard_thread);
+ }
+
+ kfree(dcc);
+ SM_I(sbi)->dcc_info = NULL;
}
static bool __mark_sit_entry_dirty(struct f2fs_sb_info *sbi, unsigned int segno)
@@ -620,11 +1530,41 @@
/* Update valid block bitmap */
if (del > 0) {
- if (f2fs_set_bit(offset, se->cur_valid_map))
+ if (f2fs_test_and_set_bit(offset, se->cur_valid_map)) {
+#ifdef CONFIG_F2FS_CHECK_FS
+ if (f2fs_test_and_set_bit(offset,
+ se->cur_valid_map_mir))
+ f2fs_bug_on(sbi, 1);
+ else
+ WARN_ON(1);
+#else
f2fs_bug_on(sbi, 1);
+#endif
+ }
+ if (f2fs_discard_en(sbi) &&
+ !f2fs_test_and_set_bit(offset, se->discard_map))
+ sbi->discard_blks--;
+
+ /* don't overwrite by SSR to keep node chain */
+ if (se->type == CURSEG_WARM_NODE) {
+ if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map))
+ se->ckpt_valid_blocks++;
+ }
} else {
- if (!f2fs_clear_bit(offset, se->cur_valid_map))
+ if (!f2fs_test_and_clear_bit(offset, se->cur_valid_map)) {
+#ifdef CONFIG_F2FS_CHECK_FS
+ if (!f2fs_test_and_clear_bit(offset,
+ se->cur_valid_map_mir))
+ f2fs_bug_on(sbi, 1);
+ else
+ WARN_ON(1);
+#else
f2fs_bug_on(sbi, 1);
+#endif
+ }
+ if (f2fs_discard_en(sbi) &&
+ f2fs_test_and_clear_bit(offset, se->discard_map))
+ sbi->discard_blks++;
}
if (!f2fs_test_bit(offset, se->ckpt_valid_map))
se->ckpt_valid_blocks += del;
@@ -668,6 +1608,30 @@
mutex_unlock(&sit_i->sentry_lock);
}
+bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr)
+{
+ struct sit_info *sit_i = SIT_I(sbi);
+ unsigned int segno, offset;
+ struct seg_entry *se;
+ bool is_cp = false;
+
+ if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR)
+ return true;
+
+ mutex_lock(&sit_i->sentry_lock);
+
+ segno = GET_SEGNO(sbi, blkaddr);
+ se = get_seg_entry(sbi, segno);
+ offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr);
+
+ if (f2fs_test_bit(offset, se->ckpt_valid_map))
+ is_cp = true;
+
+ mutex_unlock(&sit_i->sentry_lock);
+
+ return is_cp;
+}
+
/*
* This function should be resided under the curseg_mutex lock
*/
@@ -683,7 +1647,7 @@
/*
* Calculate the number of current summary pages for writing
*/
-int npages_for_summary_flush(struct f2fs_sb_info *sbi)
+int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra)
{
int valid_sum_count = 0;
int i, sum_in_page;
@@ -691,16 +1655,21 @@
for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
if (sbi->ckpt->alloc_type[i] == SSR)
valid_sum_count += sbi->blocks_per_seg;
- else
- valid_sum_count += curseg_blkoff(sbi, i);
+ else {
+ if (for_ra)
+ valid_sum_count += le16_to_cpu(
+ F2FS_CKPT(sbi)->cur_data_blkoff[i]);
+ else
+ valid_sum_count += curseg_blkoff(sbi, i);
+ }
}
- sum_in_page = (PAGE_CACHE_SIZE - 2 * SUM_JOURNAL_SIZE -
+ sum_in_page = (PAGE_SIZE - 2 * SUM_JOURNAL_SIZE -
SUM_FOOTER_SIZE) / SUMMARY_SIZE;
if (valid_sum_count <= sum_in_page)
return 1;
else if ((valid_sum_count - sum_in_page) <=
- (PAGE_CACHE_SIZE - SUM_FOOTER_SIZE) / SUMMARY_SIZE)
+ (PAGE_SIZE - SUM_FOOTER_SIZE) / SUMMARY_SIZE)
return 2;
return 3;
}
@@ -713,12 +1682,46 @@
return get_meta_page(sbi, GET_SUM_BLOCK(sbi, segno));
}
+void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr)
+{
+ struct page *page = grab_meta_page(sbi, blk_addr);
+ void *dst = page_address(page);
+
+ if (src)
+ memcpy(dst, src, PAGE_SIZE);
+ else
+ memset(dst, 0, PAGE_SIZE);
+ set_page_dirty(page);
+ f2fs_put_page(page, 1);
+}
+
static void write_sum_page(struct f2fs_sb_info *sbi,
struct f2fs_summary_block *sum_blk, block_t blk_addr)
{
+ update_meta_page(sbi, (void *)sum_blk, blk_addr);
+}
+
+static void write_current_sum_page(struct f2fs_sb_info *sbi,
+ int type, block_t blk_addr)
+{
+ struct curseg_info *curseg = CURSEG_I(sbi, type);
struct page *page = grab_meta_page(sbi, blk_addr);
- void *kaddr = page_address(page);
- memcpy(kaddr, sum_blk, PAGE_CACHE_SIZE);
+ struct f2fs_summary_block *src = curseg->sum_blk;
+ struct f2fs_summary_block *dst;
+
+ dst = (struct f2fs_summary_block *)page_address(page);
+
+ mutex_lock(&curseg->curseg_mutex);
+
+ down_read(&curseg->journal_rwsem);
+ memcpy(&dst->journal, curseg->journal, SUM_JOURNAL_SIZE);
+ up_read(&curseg->journal_rwsem);
+
+ memcpy(dst->entries, src->entries, SUM_ENTRY_SIZE);
+ memcpy(&dst->footer, &src->footer, SUM_FOOTER_SIZE);
+
+ mutex_unlock(&curseg->curseg_mutex);
+
set_page_dirty(page);
f2fs_put_page(page, 1);
}
@@ -744,20 +1747,19 @@
struct free_segmap_info *free_i = FREE_I(sbi);
unsigned int segno, secno, zoneno;
unsigned int total_zones = MAIN_SECS(sbi) / sbi->secs_per_zone;
- unsigned int hint = *newseg / sbi->segs_per_sec;
- unsigned int old_zoneno = GET_ZONENO_FROM_SEGNO(sbi, *newseg);
+ unsigned int hint = GET_SEC_FROM_SEG(sbi, *newseg);
+ unsigned int old_zoneno = GET_ZONE_FROM_SEG(sbi, *newseg);
unsigned int left_start = hint;
bool init = true;
int go_left = 0;
int i;
- write_lock(&free_i->segmap_lock);
+ spin_lock(&free_i->segmap_lock);
if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) {
segno = find_next_zero_bit(free_i->free_segmap,
- MAIN_SEGS(sbi), *newseg + 1);
- if (segno - *newseg < sbi->segs_per_sec -
- (*newseg % sbi->segs_per_sec))
+ GET_SEG_FROM_SEC(sbi, hint + 1), *newseg + 1);
+ if (segno < GET_SEG_FROM_SEC(sbi, hint + 1))
goto got_it;
}
find_other_zone:
@@ -788,8 +1790,8 @@
secno = left_start;
skip_left:
hint = secno;
- segno = secno * sbi->segs_per_sec;
- zoneno = secno / sbi->secs_per_zone;
+ segno = GET_SEG_FROM_SEC(sbi, secno);
+ zoneno = GET_ZONE_FROM_SEC(sbi, secno);
/* give up on finding another zone */
if (!init)
@@ -824,7 +1826,7 @@
f2fs_bug_on(sbi, test_bit(segno, free_i->free_segmap));
__set_inuse(sbi, segno);
*newseg = segno;
- write_unlock(&free_i->segmap_lock);
+ spin_unlock(&free_i->segmap_lock);
}
static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified)
@@ -833,7 +1835,7 @@
struct summary_footer *sum_footer;
curseg->segno = curseg->next_segno;
- curseg->zone = GET_ZONENO_FROM_SEGNO(sbi, curseg->segno);
+ curseg->zone = GET_ZONE_FROM_SEG(sbi, curseg->segno);
curseg->next_blkoff = 0;
curseg->next_segno = NULL_SEGNO;
@@ -846,6 +1848,20 @@
__set_sit_entry_type(sbi, type, curseg->segno, modified);
}
+static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type)
+{
+ /* if segs_per_sec is large than 1, we need to keep original policy. */
+ if (sbi->segs_per_sec != 1)
+ return CURSEG_I(sbi, type)->segno;
+
+ if (type == CURSEG_HOT_DATA || IS_NODESEG(type))
+ return 0;
+
+ if (SIT_I(sbi)->last_victim[ALLOC_NEXT])
+ return SIT_I(sbi)->last_victim[ALLOC_NEXT];
+ return CURSEG_I(sbi, type)->segno;
+}
+
/*
* Allocate a current working segment.
* This function always allocates a free segment in LFS manner.
@@ -864,6 +1880,7 @@
if (test_opt(sbi, NOHEAP))
dir = ALLOC_RIGHT;
+ segno = __get_next_segno(sbi, type);
get_new_segment(sbi, &segno, new_sec, dir);
curseg->next_segno = segno;
reset_curseg(sbi, type, 1);
@@ -875,7 +1892,7 @@
{
struct seg_entry *se = get_seg_entry(sbi, seg->segno);
int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long);
- unsigned long target_map[entries];
+ unsigned long *target_map = SIT_I(sbi)->tmp_map;
unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map;
unsigned long *cur_map = (unsigned long *)se->cur_valid_map;
int i, pos;
@@ -939,16 +1956,43 @@
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
const struct victim_selection *v_ops = DIRTY_I(sbi)->v_ops;
+ unsigned segno = NULL_SEGNO;
+ int i, cnt;
+ bool reversed = false;
- if (IS_NODESEG(type) || !has_not_enough_free_secs(sbi, 0))
- return v_ops->get_victim(sbi,
- &(curseg)->next_segno, BG_GC, type, SSR);
+ /* need_SSR() already forces to do this */
+ if (v_ops->get_victim(sbi, &segno, BG_GC, type, SSR)) {
+ curseg->next_segno = segno;
+ return 1;
+ }
- /* For data segments, let's do SSR more intensively */
- for (; type >= CURSEG_HOT_DATA; type--)
- if (v_ops->get_victim(sbi, &(curseg)->next_segno,
- BG_GC, type, SSR))
+ /* For node segments, let's do SSR more intensively */
+ if (IS_NODESEG(type)) {
+ if (type >= CURSEG_WARM_NODE) {
+ reversed = true;
+ i = CURSEG_COLD_NODE;
+ } else {
+ i = CURSEG_HOT_NODE;
+ }
+ cnt = NR_CURSEG_NODE_TYPE;
+ } else {
+ if (type >= CURSEG_WARM_DATA) {
+ reversed = true;
+ i = CURSEG_COLD_DATA;
+ } else {
+ i = CURSEG_HOT_DATA;
+ }
+ cnt = NR_CURSEG_DATA_TYPE;
+ }
+
+ for (; cnt-- > 0; reversed ? i-- : i++) {
+ if (i == type)
+ continue;
+ if (v_ops->get_victim(sbi, &segno, BG_GC, i, SSR)) {
+ curseg->next_segno = segno;
return 1;
+ }
+ }
return 0;
}
@@ -963,7 +2007,8 @@
if (force)
new_curseg(sbi, type, true);
- else if (type == CURSEG_WARM_NODE)
+ else if (!is_set_ckpt_flags(sbi, CP_CRC_RECOVERY_FLAG) &&
+ type == CURSEG_WARM_NODE)
new_curseg(sbi, type, false);
else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type))
new_curseg(sbi, type, false);
@@ -978,14 +2023,14 @@
void allocate_new_segments(struct f2fs_sb_info *sbi)
{
struct curseg_info *curseg;
- unsigned int old_curseg;
+ unsigned int old_segno;
int i;
for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
curseg = CURSEG_I(sbi, i);
- old_curseg = curseg->segno;
+ old_segno = curseg->segno;
SIT_I(sbi)->s_ops->allocate_segment(sbi, i, true);
- locate_dirty_segment(sbi, old_curseg);
+ locate_dirty_segment(sbi, old_segno);
}
}
@@ -993,35 +2038,77 @@
.allocate_segment = allocate_segment_by_default,
};
+bool exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc)
+{
+ __u64 trim_start = cpc->trim_start;
+ bool has_candidate = false;
+
+ mutex_lock(&SIT_I(sbi)->sentry_lock);
+ for (; cpc->trim_start <= cpc->trim_end; cpc->trim_start++) {
+ if (add_discard_addrs(sbi, cpc, true)) {
+ has_candidate = true;
+ break;
+ }
+ }
+ mutex_unlock(&SIT_I(sbi)->sentry_lock);
+
+ cpc->trim_start = trim_start;
+ return has_candidate;
+}
+
int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
{
- __u64 start = range->start >> sbi->log_blocksize;
- __u64 end = start + (range->len >> sbi->log_blocksize) - 1;
+ __u64 start = F2FS_BYTES_TO_BLK(range->start);
+ __u64 end = start + F2FS_BYTES_TO_BLK(range->len) - 1;
unsigned int start_segno, end_segno;
struct cp_control cpc;
+ int err = 0;
- if (range->minlen > SEGMENT_SIZE(sbi) || start >= MAX_BLKADDR(sbi) ||
- range->len < sbi->blocksize)
+ if (start >= MAX_BLKADDR(sbi) || range->len < sbi->blocksize)
return -EINVAL;
cpc.trimmed = 0;
if (end <= MAIN_BLKADDR(sbi))
goto out;
+ if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) {
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "Found FS corruption, run fsck to fix.");
+ goto out;
+ }
+
/* start/end segment number in main_area */
start_segno = (start <= MAIN_BLKADDR(sbi)) ? 0 : GET_SEGNO(sbi, start);
end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 :
GET_SEGNO(sbi, end);
cpc.reason = CP_DISCARD;
- cpc.trim_start = start_segno;
- cpc.trim_end = end_segno;
- cpc.trim_minlen = range->minlen >> sbi->log_blocksize;
+ cpc.trim_minlen = max_t(__u64, 1, F2FS_BYTES_TO_BLK(range->minlen));
/* do checkpoint to issue discard commands safely */
- write_checkpoint(sbi, &cpc);
+ for (; start_segno <= end_segno; start_segno = cpc.trim_end + 1) {
+ cpc.trim_start = start_segno;
+
+ if (sbi->discard_blks == 0)
+ break;
+ else if (sbi->discard_blks < BATCHED_TRIM_BLOCKS(sbi))
+ cpc.trim_end = end_segno;
+ else
+ cpc.trim_end = min_t(unsigned int,
+ rounddown(start_segno +
+ BATCHED_TRIM_SEGMENTS(sbi),
+ sbi->segs_per_sec) - 1, end_segno);
+
+ mutex_lock(&sbi->gc_mutex);
+ err = write_checkpoint(sbi, &cpc);
+ mutex_unlock(&sbi->gc_mutex);
+ if (err)
+ break;
+
+ schedule();
+ }
out:
- range->len = cpc.trimmed << sbi->log_blocksize;
- return 0;
+ range->len = F2FS_BLK_TO_BYTES(cpc.trimmed);
+ return err;
}
static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type)
@@ -1050,8 +2137,8 @@
else
return CURSEG_COLD_DATA;
} else {
- if (IS_DNODE(page) && !is_cold_node(page))
- return CURSEG_HOT_NODE;
+ if (IS_DNODE(page) && is_cold_node(page))
+ return CURSEG_WARM_NODE;
else
return CURSEG_COLD_NODE;
}
@@ -1062,18 +2149,16 @@
if (p_type == DATA) {
struct inode *inode = page->mapping->host;
- if (S_ISDIR(inode->i_mode))
- return CURSEG_HOT_DATA;
- else if (is_cold_data(page) || file_is_cold(inode))
+ if (is_cold_data(page) || file_is_cold(inode))
return CURSEG_COLD_DATA;
- else
- return CURSEG_WARM_DATA;
+ if (is_inode_flag_set(inode, FI_HOT_DATA))
+ return CURSEG_HOT_DATA;
+ return CURSEG_WARM_DATA;
} else {
if (IS_DNODE(page))
return is_cold_node(page) ? CURSEG_WARM_NODE :
CURSEG_HOT_NODE;
- else
- return CURSEG_COLD_NODE;
+ return CURSEG_COLD_NODE;
}
}
@@ -1096,14 +2181,15 @@
struct f2fs_summary *sum, int type)
{
struct sit_info *sit_i = SIT_I(sbi);
- struct curseg_info *curseg;
-
- curseg = CURSEG_I(sbi, type);
+ struct curseg_info *curseg = CURSEG_I(sbi, type);
mutex_lock(&curseg->curseg_mutex);
+ mutex_lock(&sit_i->sentry_lock);
*new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
+ f2fs_wait_discard_bio(sbi, *new_blkaddr);
+
/*
* __add_sum_entry should be resided under the curseg_mutex
* because, this function updates a summary entry in the
@@ -1111,7 +2197,6 @@
*/
__add_sum_entry(sbi, type, sum);
- mutex_lock(&sit_i->sentry_lock);
__refresh_next_blkoff(sbi, curseg);
stat_inc_block_count(sbi, curseg);
@@ -1119,8 +2204,8 @@
if (!__has_curseg_space(sbi, type))
sit_i->s_ops->allocate_segment(sbi, type, false);
/*
- * SIT information should be updated before segment allocation,
- * since SSR needs latest valid block information.
+ * SIT information should be updated after segment allocation,
+ * since we need to keep dirty segments precisely under SSR.
*/
refresh_sit_entry(sbi, old_blkaddr, *new_blkaddr);
@@ -1132,84 +2217,111 @@
mutex_unlock(&curseg->curseg_mutex);
}
-static void do_write_page(struct f2fs_sb_info *sbi, struct page *page,
- block_t old_blkaddr, block_t *new_blkaddr,
- struct f2fs_summary *sum, struct f2fs_io_info *fio)
+static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
{
- int type = __get_segment_type(page, fio->type);
+ int type = __get_segment_type(fio->page, fio->type);
+ int err;
- allocate_data_block(sbi, page, old_blkaddr, new_blkaddr, sum, type);
+ if (fio->type == NODE || fio->type == DATA)
+ mutex_lock(&fio->sbi->wio_mutex[fio->type]);
+reallocate:
+ allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
+ &fio->new_blkaddr, sum, type);
/* writeout dirty page into bdev */
- f2fs_submit_page_mbio(sbi, page, *new_blkaddr, fio);
+ err = f2fs_submit_page_mbio(fio);
+ if (err == -EAGAIN) {
+ fio->old_blkaddr = fio->new_blkaddr;
+ goto reallocate;
+ }
+
+ if (fio->type == NODE || fio->type == DATA)
+ mutex_unlock(&fio->sbi->wio_mutex[fio->type]);
}
void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
{
struct f2fs_io_info fio = {
+ .sbi = sbi,
.type = META,
- .rw = WRITE_SYNC | REQ_META | REQ_PRIO
+ .op = REQ_OP_WRITE,
+ .op_flags = REQ_SYNC | REQ_META | REQ_PRIO,
+ .old_blkaddr = page->index,
+ .new_blkaddr = page->index,
+ .page = page,
+ .encrypted_page = NULL,
};
+ if (unlikely(page->index >= MAIN_BLKADDR(sbi)))
+ fio.op_flags &= ~REQ_META;
+
set_page_writeback(page);
- f2fs_submit_page_mbio(sbi, page, page->index, &fio);
+ f2fs_submit_page_mbio(&fio);
}
-void write_node_page(struct f2fs_sb_info *sbi, struct page *page,
- struct f2fs_io_info *fio,
- unsigned int nid, block_t old_blkaddr, block_t *new_blkaddr)
+void write_node_page(unsigned int nid, struct f2fs_io_info *fio)
{
struct f2fs_summary sum;
+
set_summary(&sum, nid, 0, 0);
- do_write_page(sbi, page, old_blkaddr, new_blkaddr, &sum, fio);
+ do_write_page(&sum, fio);
}
-void write_data_page(struct page *page, struct dnode_of_data *dn,
- block_t *new_blkaddr, struct f2fs_io_info *fio)
+void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio)
{
- struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
+ struct f2fs_sb_info *sbi = fio->sbi;
struct f2fs_summary sum;
struct node_info ni;
f2fs_bug_on(sbi, dn->data_blkaddr == NULL_ADDR);
get_node_info(sbi, dn->nid, &ni);
set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
-
- do_write_page(sbi, page, dn->data_blkaddr, new_blkaddr, &sum, fio);
+ do_write_page(&sum, fio);
+ f2fs_update_data_blkaddr(dn, fio->new_blkaddr);
}
-void rewrite_data_page(struct page *page, block_t old_blkaddr,
- struct f2fs_io_info *fio)
+int rewrite_data_page(struct f2fs_io_info *fio)
{
- f2fs_submit_page_mbio(F2FS_P_SB(page), page, old_blkaddr, fio);
+ fio->new_blkaddr = fio->old_blkaddr;
+ stat_inc_inplace_blocks(fio->sbi);
+ return f2fs_submit_page_bio(fio);
}
-void recover_data_page(struct f2fs_sb_info *sbi,
- struct page *page, struct f2fs_summary *sum,
- block_t old_blkaddr, block_t new_blkaddr)
+void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
+ block_t old_blkaddr, block_t new_blkaddr,
+ bool recover_curseg, bool recover_newaddr)
{
struct sit_info *sit_i = SIT_I(sbi);
struct curseg_info *curseg;
unsigned int segno, old_cursegno;
struct seg_entry *se;
int type;
+ unsigned short old_blkoff;
segno = GET_SEGNO(sbi, new_blkaddr);
se = get_seg_entry(sbi, segno);
type = se->type;
- if (se->valid_blocks == 0 && !IS_CURSEG(sbi, segno)) {
- if (old_blkaddr == NULL_ADDR)
- type = CURSEG_COLD_DATA;
- else
+ if (!recover_curseg) {
+ /* for recovery flow */
+ if (se->valid_blocks == 0 && !IS_CURSEG(sbi, segno)) {
+ if (old_blkaddr == NULL_ADDR)
+ type = CURSEG_COLD_DATA;
+ else
+ type = CURSEG_WARM_DATA;
+ }
+ } else {
+ if (!IS_CURSEG(sbi, segno))
type = CURSEG_WARM_DATA;
}
+
curseg = CURSEG_I(sbi, type);
mutex_lock(&curseg->curseg_mutex);
mutex_lock(&sit_i->sentry_lock);
old_cursegno = curseg->segno;
+ old_blkoff = curseg->next_blkoff;
/* change the current segment */
if (segno != curseg->segno) {
@@ -1220,46 +2332,70 @@
curseg->next_blkoff = GET_BLKOFF_FROM_SEG0(sbi, new_blkaddr);
__add_sum_entry(sbi, type, sum);
- refresh_sit_entry(sbi, old_blkaddr, new_blkaddr);
+ if (!recover_curseg || recover_newaddr)
+ update_sit_entry(sbi, new_blkaddr, 1);
+ if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO)
+ update_sit_entry(sbi, old_blkaddr, -1);
+
+ locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr));
+ locate_dirty_segment(sbi, GET_SEGNO(sbi, new_blkaddr));
+
locate_dirty_segment(sbi, old_cursegno);
+ if (recover_curseg) {
+ if (old_cursegno != curseg->segno) {
+ curseg->next_segno = old_cursegno;
+ change_curseg(sbi, type, true);
+ }
+ curseg->next_blkoff = old_blkoff;
+ }
+
mutex_unlock(&sit_i->sentry_lock);
mutex_unlock(&curseg->curseg_mutex);
}
-static inline bool is_merged_page(struct f2fs_sb_info *sbi,
- struct page *page, enum page_type type)
+void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
+ block_t old_addr, block_t new_addr,
+ unsigned char version, bool recover_curseg,
+ bool recover_newaddr)
{
- enum page_type btype = PAGE_TYPE_OF_BIO(type);
- struct f2fs_bio_info *io = &sbi->write_io[btype];
- struct bio_vec *bvec;
- int i;
+ struct f2fs_summary sum;
- down_read(&io->io_rwsem);
- if (!io->bio)
- goto out;
+ set_summary(&sum, dn->nid, dn->ofs_in_node, version);
- bio_for_each_segment_all(bvec, io->bio, i) {
- if (page == bvec->bv_page) {
- up_read(&io->io_rwsem);
- return true;
- }
- }
+ __f2fs_replace_block(sbi, &sum, old_addr, new_addr,
+ recover_curseg, recover_newaddr);
-out:
- up_read(&io->io_rwsem);
- return false;
+ f2fs_update_data_blkaddr(dn, new_addr);
}
void f2fs_wait_on_page_writeback(struct page *page,
- enum page_type type)
+ enum page_type type, bool ordered)
{
if (PageWriteback(page)) {
struct f2fs_sb_info *sbi = F2FS_P_SB(page);
- if (is_merged_page(sbi, page, type))
- f2fs_submit_merged_bio(sbi, type, WRITE);
- wait_on_page_writeback(page);
+ f2fs_submit_merged_bio_cond(sbi, page->mapping->host,
+ 0, page->index, type, WRITE);
+ if (ordered)
+ wait_on_page_writeback(page);
+ else
+ wait_for_stable_page(page);
+ }
+}
+
+void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi,
+ block_t blkaddr)
+{
+ struct page *cpage;
+
+ if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR)
+ return;
+
+ cpage = find_lock_page(META_MAPPING(sbi), blkaddr);
+ if (cpage) {
+ f2fs_wait_on_page_writeback(cpage, DATA, true);
+ f2fs_put_page(cpage, 1);
}
}
@@ -1279,12 +2415,11 @@
/* Step 1: restore nat cache */
seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA);
- memcpy(&seg_i->sum_blk->n_nats, kaddr, SUM_JOURNAL_SIZE);
+ memcpy(seg_i->journal, kaddr, SUM_JOURNAL_SIZE);
/* Step 2: restore sit cache */
seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA);
- memcpy(&seg_i->sum_blk->n_sits, kaddr + SUM_JOURNAL_SIZE,
- SUM_JOURNAL_SIZE);
+ memcpy(seg_i->journal, kaddr + SUM_JOURNAL_SIZE, SUM_JOURNAL_SIZE);
offset = 2 * SUM_JOURNAL_SIZE;
/* Step 3: restore summary entries */
@@ -1308,7 +2443,7 @@
s = (struct f2fs_summary *)(kaddr + offset);
seg_i->sum_blk->entries[j] = *s;
offset += SUMMARY_SIZE;
- if (offset + SUMMARY_SIZE <= PAGE_CACHE_SIZE -
+ if (offset + SUMMARY_SIZE <= PAGE_SIZE -
SUM_FOOTER_SIZE)
continue;
@@ -1339,7 +2474,7 @@
segno = le32_to_cpu(ckpt->cur_data_segno[type]);
blk_off = le16_to_cpu(ckpt->cur_data_blkoff[type -
CURSEG_HOT_DATA]);
- if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG))
+ if (__exist_node_summaries(sbi))
blk_addr = sum_blk_addr(sbi, NR_CURSEG_TYPE, type);
else
blk_addr = sum_blk_addr(sbi, NR_CURSEG_DATA_TYPE, type);
@@ -1348,7 +2483,7 @@
CURSEG_HOT_NODE]);
blk_off = le16_to_cpu(ckpt->cur_node_blkoff[type -
CURSEG_HOT_NODE]);
- if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG))
+ if (__exist_node_summaries(sbi))
blk_addr = sum_blk_addr(sbi, NR_CURSEG_NODE_TYPE,
type - CURSEG_HOT_NODE);
else
@@ -1359,7 +2494,7 @@
sum = (struct f2fs_summary_block *)page_address(new);
if (IS_NODESEG(type)) {
- if (is_set_ckpt_flags(ckpt, CP_UMOUNT_FLAG)) {
+ if (__exist_node_summaries(sbi)) {
struct f2fs_summary *ns = &sum->entries[0];
int i;
for (i = 0; i < sbi->blocks_per_seg; i++, ns++) {
@@ -1380,7 +2515,14 @@
/* set uncompleted segment to curseg */
curseg = CURSEG_I(sbi, type);
mutex_lock(&curseg->curseg_mutex);
- memcpy(curseg->sum_blk, sum, PAGE_CACHE_SIZE);
+
+ /* update journal info */
+ down_write(&curseg->journal_rwsem);
+ memcpy(curseg->journal, &sum->journal, SUM_JOURNAL_SIZE);
+ up_write(&curseg->journal_rwsem);
+
+ memcpy(curseg->sum_blk->entries, sum->entries, SUM_ENTRY_SIZE);
+ memcpy(&curseg->sum_blk->footer, &sum->footer, SUM_FOOTER_SIZE);
curseg->next_segno = segno;
reset_curseg(sbi, type, 0);
curseg->alloc_type = ckpt->alloc_type[type];
@@ -1392,22 +2534,39 @@
static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
{
+ struct f2fs_journal *sit_j = CURSEG_I(sbi, CURSEG_COLD_DATA)->journal;
+ struct f2fs_journal *nat_j = CURSEG_I(sbi, CURSEG_HOT_DATA)->journal;
int type = CURSEG_HOT_DATA;
int err;
- if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_COMPACT_SUM_FLAG)) {
+ if (is_set_ckpt_flags(sbi, CP_COMPACT_SUM_FLAG)) {
+ int npages = npages_for_summary_flush(sbi, true);
+
+ if (npages >= 2)
+ ra_meta_pages(sbi, start_sum_block(sbi), npages,
+ META_CP, true);
+
/* restore for compacted data summary */
if (read_compacted_summaries(sbi))
return -EINVAL;
type = CURSEG_HOT_NODE;
}
+ if (__exist_node_summaries(sbi))
+ ra_meta_pages(sbi, sum_blk_addr(sbi, NR_CURSEG_TYPE, type),
+ NR_CURSEG_TYPE - type, META_CP, true);
+
for (; type <= CURSEG_COLD_NODE; type++) {
err = read_normal_summaries(sbi, type);
if (err)
return err;
}
+ /* sanity check for summary blocks */
+ if (nats_in_cursum(nat_j) > NAT_JOURNAL_ENTRIES ||
+ sits_in_cursum(sit_j) > SIT_JOURNAL_ENTRIES)
+ return -EINVAL;
+
return 0;
}
@@ -1425,13 +2584,12 @@
/* Step 1: write nat cache */
seg_i = CURSEG_I(sbi, CURSEG_HOT_DATA);
- memcpy(kaddr, &seg_i->sum_blk->n_nats, SUM_JOURNAL_SIZE);
+ memcpy(kaddr, seg_i->journal, SUM_JOURNAL_SIZE);
written_size += SUM_JOURNAL_SIZE;
/* Step 2: write sit cache */
seg_i = CURSEG_I(sbi, CURSEG_COLD_DATA);
- memcpy(kaddr + written_size, &seg_i->sum_blk->n_sits,
- SUM_JOURNAL_SIZE);
+ memcpy(kaddr + written_size, seg_i->journal, SUM_JOURNAL_SIZE);
written_size += SUM_JOURNAL_SIZE;
/* Step 3: write summary entries */
@@ -1453,7 +2611,7 @@
*summary = seg_i->sum_blk->entries[j];
written_size += SUMMARY_SIZE;
- if (written_size + SUMMARY_SIZE <= PAGE_CACHE_SIZE -
+ if (written_size + SUMMARY_SIZE <= PAGE_SIZE -
SUM_FOOTER_SIZE)
continue;
@@ -1477,17 +2635,13 @@
else
end = type + NR_CURSEG_NODE_TYPE;
- for (i = type; i < end; i++) {
- struct curseg_info *sum = CURSEG_I(sbi, i);
- mutex_lock(&sum->curseg_mutex);
- write_sum_page(sbi, sum->sum_blk, blkaddr + (i - type));
- mutex_unlock(&sum->curseg_mutex);
- }
+ for (i = type; i < end; i++)
+ write_current_sum_page(sbi, i, blkaddr + (i - type));
}
void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
{
- if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_COMPACT_SUM_FLAG))
+ if (is_set_ckpt_flags(sbi, CP_COMPACT_SUM_FLAG))
write_compacted_summaries(sbi, start_blk);
else
write_normal_summaries(sbi, start_blk, CURSEG_HOT_DATA);
@@ -1495,28 +2649,27 @@
void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
{
- if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG))
- write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE);
+ write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE);
}
-int lookup_journal_in_cursum(struct f2fs_summary_block *sum, int type,
+int lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
unsigned int val, int alloc)
{
int i;
if (type == NAT_JOURNAL) {
- for (i = 0; i < nats_in_cursum(sum); i++) {
- if (le32_to_cpu(nid_in_journal(sum, i)) == val)
+ for (i = 0; i < nats_in_cursum(journal); i++) {
+ if (le32_to_cpu(nid_in_journal(journal, i)) == val)
return i;
}
- if (alloc && nats_in_cursum(sum) < NAT_JOURNAL_ENTRIES)
- return update_nats_in_cursum(sum, 1);
+ if (alloc && __has_cursum_space(journal, 1, NAT_JOURNAL))
+ return update_nats_in_cursum(journal, 1);
} else if (type == SIT_JOURNAL) {
- for (i = 0; i < sits_in_cursum(sum); i++)
- if (le32_to_cpu(segno_in_journal(sum, i)) == val)
+ for (i = 0; i < sits_in_cursum(journal); i++)
+ if (le32_to_cpu(segno_in_journal(journal, i)) == val)
return i;
- if (alloc && sits_in_cursum(sum) < SIT_JOURNAL_ENTRIES)
- return update_sits_in_cursum(sum, 1);
+ if (alloc && __has_cursum_space(journal, 1, SIT_JOURNAL))
+ return update_sits_in_cursum(journal, 1);
}
return -1;
}
@@ -1524,17 +2677,7 @@
static struct page *get_current_sit_page(struct f2fs_sb_info *sbi,
unsigned int segno)
{
- struct sit_info *sit_i = SIT_I(sbi);
- unsigned int offset = SIT_BLOCK_OFFSET(segno);
- block_t blk_addr = sit_i->sit_base_addr + offset;
-
- check_seg_range(sbi, segno);
-
- /* calculate sit block address */
- if (f2fs_test_bit(offset, sit_i->sit_bitmap))
- blk_addr += sit_i->sit_blocks;
-
- return get_meta_page(sbi, blk_addr);
+ return get_meta_page(sbi, current_sit_addr(sbi, segno));
}
static struct page *get_next_sit_page(struct f2fs_sb_info *sbi,
@@ -1555,7 +2698,7 @@
src_addr = page_address(src_page);
dst_addr = page_address(dst_page);
- memcpy(dst_addr, src_addr, PAGE_CACHE_SIZE);
+ memcpy(dst_addr, src_addr, PAGE_SIZE);
set_page_dirty(dst_page);
f2fs_put_page(src_page, 1);
@@ -1568,7 +2711,7 @@
static struct sit_entry_set *grab_sit_entry_set(void)
{
struct sit_entry_set *ses =
- f2fs_kmem_cache_alloc(sit_entry_set_slab, GFP_ATOMIC);
+ f2fs_kmem_cache_alloc(sit_entry_set_slab, GFP_NOFS);
ses->entry_cnt = 0;
INIT_LIST_HEAD(&ses->set_list);
@@ -1630,20 +2773,22 @@
static void remove_sits_in_journal(struct f2fs_sb_info *sbi)
{
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
- struct f2fs_summary_block *sum = curseg->sum_blk;
+ struct f2fs_journal *journal = curseg->journal;
int i;
- for (i = sits_in_cursum(sum) - 1; i >= 0; i--) {
+ down_write(&curseg->journal_rwsem);
+ for (i = 0; i < sits_in_cursum(journal); i++) {
unsigned int segno;
bool dirtied;
- segno = le32_to_cpu(segno_in_journal(sum, i));
+ segno = le32_to_cpu(segno_in_journal(journal, i));
dirtied = __mark_sit_entry_dirty(sbi, segno);
if (!dirtied)
add_sit_entry(segno, &SM_I(sbi)->sit_entry_set);
}
- update_sits_in_cursum(sum, -sits_in_cursum(sum));
+ update_sits_in_cursum(journal, -i);
+ up_write(&curseg->journal_rwsem);
}
/*
@@ -1655,15 +2800,17 @@
struct sit_info *sit_i = SIT_I(sbi);
unsigned long *bitmap = sit_i->dirty_sentries_bitmap;
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
- struct f2fs_summary_block *sum = curseg->sum_blk;
+ struct f2fs_journal *journal = curseg->journal;
struct sit_entry_set *ses, *tmp;
struct list_head *head = &SM_I(sbi)->sit_entry_set;
bool to_journal = true;
struct seg_entry *se;
- mutex_lock(&curseg->curseg_mutex);
mutex_lock(&sit_i->sentry_lock);
+ if (!sit_i->dirty_sentries)
+ goto out;
+
/*
* add and account sit entries of dirty bitmap in sit entry
* set temporarily
@@ -1675,19 +2822,16 @@
* entries, remove all entries from journal and add and account
* them in sit entry set.
*/
- if (!__has_cursum_space(sum, sit_i->dirty_sentries, SIT_JOURNAL))
+ if (!__has_cursum_space(journal, sit_i->dirty_sentries, SIT_JOURNAL))
remove_sits_in_journal(sbi);
- if (!sit_i->dirty_sentries)
- goto out;
-
/*
* there are two steps to flush sit entries:
* #1, flush sit entries to journal in current cold data summary block.
* #2, flush sit entries to sit page.
*/
list_for_each_entry_safe(ses, tmp, head, set_list) {
- struct page *page;
+ struct page *page = NULL;
struct f2fs_sit_block *raw_sit = NULL;
unsigned int start_segno = ses->start_segno;
unsigned int end = min(start_segno + SIT_ENTRY_PER_BLOCK,
@@ -1695,10 +2839,12 @@
unsigned int segno = start_segno;
if (to_journal &&
- !__has_cursum_space(sum, ses->entry_cnt, SIT_JOURNAL))
+ !__has_cursum_space(journal, ses->entry_cnt, SIT_JOURNAL))
to_journal = false;
- if (!to_journal) {
+ if (to_journal) {
+ down_write(&curseg->journal_rwsem);
+ } else {
page = get_next_sit_page(sbi, start_segno);
raw_sit = page_address(page);
}
@@ -1710,19 +2856,19 @@
se = get_seg_entry(sbi, segno);
/* add discard candidates */
- if (SM_I(sbi)->nr_discards < SM_I(sbi)->max_discards) {
+ if (!(cpc->reason & CP_DISCARD)) {
cpc->trim_start = segno;
- add_discard_addrs(sbi, cpc);
+ add_discard_addrs(sbi, cpc, false);
}
if (to_journal) {
- offset = lookup_journal_in_cursum(sum,
+ offset = lookup_journal_in_cursum(journal,
SIT_JOURNAL, segno, 1);
f2fs_bug_on(sbi, offset < 0);
- segno_in_journal(sum, offset) =
+ segno_in_journal(journal, offset) =
cpu_to_le32(segno);
seg_info_to_raw_sit(se,
- &sit_in_journal(sum, offset));
+ &sit_in_journal(journal, offset));
} else {
sit_offset = SIT_ENTRY_OFFSET(sit_i, segno);
seg_info_to_raw_sit(se,
@@ -1734,7 +2880,9 @@
ses->entry_cnt--;
}
- if (!to_journal)
+ if (to_journal)
+ up_write(&curseg->journal_rwsem);
+ else
f2fs_put_page(page, 1);
f2fs_bug_on(sbi, ses->entry_cnt);
@@ -1744,12 +2892,15 @@
f2fs_bug_on(sbi, !list_empty(head));
f2fs_bug_on(sbi, sit_i->dirty_sentries);
out:
- if (cpc->reason == CP_DISCARD) {
+ if (cpc->reason & CP_DISCARD) {
+ __u64 trim_start = cpc->trim_start;
+
for (; cpc->trim_start <= cpc->trim_end; cpc->trim_start++)
- add_discard_addrs(sbi, cpc);
+ add_discard_addrs(sbi, cpc, false);
+
+ cpc->trim_start = trim_start;
}
mutex_unlock(&sit_i->sentry_lock);
- mutex_unlock(&curseg->curseg_mutex);
set_prefree_as_free_segments(sbi);
}
@@ -1757,10 +2908,9 @@
static int build_sit_info(struct f2fs_sb_info *sbi)
{
struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
- struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
struct sit_info *sit_i;
unsigned int sit_segs, start;
- char *src_bitmap, *dst_bitmap;
+ char *src_bitmap;
unsigned int bitmap_size;
/* allocate memory for SIT information */
@@ -1770,12 +2920,13 @@
SM_I(sbi)->sit_info = sit_i;
- sit_i->sentries = vzalloc(MAIN_SEGS(sbi) * sizeof(struct seg_entry));
+ sit_i->sentries = f2fs_kvzalloc(MAIN_SEGS(sbi) *
+ sizeof(struct seg_entry), GFP_KERNEL);
if (!sit_i->sentries)
return -ENOMEM;
bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
- sit_i->dirty_sentries_bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+ sit_i->dirty_sentries_bitmap = f2fs_kvzalloc(bitmap_size, GFP_KERNEL);
if (!sit_i->dirty_sentries_bitmap)
return -ENOMEM;
@@ -1784,14 +2935,32 @@
= kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
sit_i->sentries[start].ckpt_valid_map
= kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
- if (!sit_i->sentries[start].cur_valid_map
- || !sit_i->sentries[start].ckpt_valid_map)
+ if (!sit_i->sentries[start].cur_valid_map ||
+ !sit_i->sentries[start].ckpt_valid_map)
return -ENOMEM;
+
+#ifdef CONFIG_F2FS_CHECK_FS
+ sit_i->sentries[start].cur_valid_map_mir
+ = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+ if (!sit_i->sentries[start].cur_valid_map_mir)
+ return -ENOMEM;
+#endif
+
+ if (f2fs_discard_en(sbi)) {
+ sit_i->sentries[start].discard_map
+ = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+ if (!sit_i->sentries[start].discard_map)
+ return -ENOMEM;
+ }
}
+ sit_i->tmp_map = kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+ if (!sit_i->tmp_map)
+ return -ENOMEM;
+
if (sbi->segs_per_sec > 1) {
- sit_i->sec_entries = vzalloc(MAIN_SECS(sbi) *
- sizeof(struct sec_entry));
+ sit_i->sec_entries = f2fs_kvzalloc(MAIN_SECS(sbi) *
+ sizeof(struct sec_entry), GFP_KERNEL);
if (!sit_i->sec_entries)
return -ENOMEM;
}
@@ -1803,17 +2972,22 @@
bitmap_size = __bitmap_size(sbi, SIT_BITMAP);
src_bitmap = __bitmap_ptr(sbi, SIT_BITMAP);
- dst_bitmap = kmemdup(src_bitmap, bitmap_size, GFP_KERNEL);
- if (!dst_bitmap)
+ sit_i->sit_bitmap = kmemdup(src_bitmap, bitmap_size, GFP_KERNEL);
+ if (!sit_i->sit_bitmap)
return -ENOMEM;
+#ifdef CONFIG_F2FS_CHECK_FS
+ sit_i->sit_bitmap_mir = kmemdup(src_bitmap, bitmap_size, GFP_KERNEL);
+ if (!sit_i->sit_bitmap_mir)
+ return -ENOMEM;
+#endif
+
/* init SIT information */
sit_i->s_ops = &default_salloc_ops;
sit_i->sit_base_addr = le32_to_cpu(raw_super->sit_blkaddr);
sit_i->sit_blocks = sit_segs << sbi->log_blocks_per_seg;
- sit_i->written_valid_blocks = le64_to_cpu(ckpt->valid_block_count);
- sit_i->sit_bitmap = dst_bitmap;
+ sit_i->written_valid_blocks = 0;
sit_i->bitmap_size = bitmap_size;
sit_i->dirty_sentries = 0;
sit_i->sents_per_block = SIT_ENTRY_PER_BLOCK;
@@ -1836,12 +3010,12 @@
SM_I(sbi)->free_info = free_i;
bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
- free_i->free_segmap = kmalloc(bitmap_size, GFP_KERNEL);
+ free_i->free_segmap = f2fs_kvmalloc(bitmap_size, GFP_KERNEL);
if (!free_i->free_segmap)
return -ENOMEM;
sec_bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi));
- free_i->free_secmap = kmalloc(sec_bitmap_size, GFP_KERNEL);
+ free_i->free_secmap = f2fs_kvmalloc(sec_bitmap_size, GFP_KERNEL);
if (!free_i->free_secmap)
return -ENOMEM;
@@ -1853,7 +3027,7 @@
free_i->start_segno = GET_SEGNO_FROM_SEG0(sbi, MAIN_BLKADDR(sbi));
free_i->free_segments = 0;
free_i->free_sections = 0;
- rwlock_init(&free_i->segmap_lock);
+ spin_lock_init(&free_i->segmap_lock);
return 0;
}
@@ -1870,9 +3044,14 @@
for (i = 0; i < NR_CURSEG_TYPE; i++) {
mutex_init(&array[i].curseg_mutex);
- array[i].sum_blk = kzalloc(PAGE_CACHE_SIZE, GFP_KERNEL);
+ array[i].sum_blk = kzalloc(PAGE_SIZE, GFP_KERNEL);
if (!array[i].sum_blk)
return -ENOMEM;
+ init_rwsem(&array[i].journal_rwsem);
+ array[i].journal = kzalloc(sizeof(struct f2fs_journal),
+ GFP_KERNEL);
+ if (!array[i].journal)
+ return -ENOMEM;
array[i].segno = NULL_SEGNO;
array[i].next_blkoff = 0;
}
@@ -1883,49 +3062,85 @@
{
struct sit_info *sit_i = SIT_I(sbi);
struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_COLD_DATA);
- struct f2fs_summary_block *sum = curseg->sum_blk;
+ struct f2fs_journal *journal = curseg->journal;
+ struct seg_entry *se;
+ struct f2fs_sit_entry sit;
int sit_blk_cnt = SIT_BLK_CNT(sbi);
unsigned int i, start, end;
unsigned int readed, start_blk = 0;
- int nrpages = MAX_BIO_BLOCKS(sbi);
do {
- readed = ra_meta_pages(sbi, start_blk, nrpages, META_SIT);
+ readed = ra_meta_pages(sbi, start_blk, BIO_MAX_PAGES,
+ META_SIT, true);
start = start_blk * sit_i->sents_per_block;
end = (start_blk + readed) * sit_i->sents_per_block;
for (; start < end && start < MAIN_SEGS(sbi); start++) {
- struct seg_entry *se = &sit_i->sentries[start];
struct f2fs_sit_block *sit_blk;
- struct f2fs_sit_entry sit;
struct page *page;
- mutex_lock(&curseg->curseg_mutex);
- for (i = 0; i < sits_in_cursum(sum); i++) {
- if (le32_to_cpu(segno_in_journal(sum, i))
- == start) {
- sit = sit_in_journal(sum, i);
- mutex_unlock(&curseg->curseg_mutex);
- goto got_it;
- }
- }
- mutex_unlock(&curseg->curseg_mutex);
-
+ se = &sit_i->sentries[start];
page = get_current_sit_page(sbi, start);
sit_blk = (struct f2fs_sit_block *)page_address(page);
sit = sit_blk->entries[SIT_ENTRY_OFFSET(sit_i, start)];
f2fs_put_page(page, 1);
-got_it:
+
check_block_count(sbi, start, &sit);
seg_info_from_raw_sit(se, &sit);
- if (sbi->segs_per_sec > 1) {
- struct sec_entry *e = get_sec_entry(sbi, start);
- e->valid_blocks += se->valid_blocks;
+
+ /* build discard map only one time */
+ if (f2fs_discard_en(sbi)) {
+ if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) {
+ memset(se->discard_map, 0xff,
+ SIT_VBLOCK_MAP_SIZE);
+ } else {
+ memcpy(se->discard_map,
+ se->cur_valid_map,
+ SIT_VBLOCK_MAP_SIZE);
+ sbi->discard_blks +=
+ sbi->blocks_per_seg -
+ se->valid_blocks;
+ }
}
+
+ if (sbi->segs_per_sec > 1)
+ get_sec_entry(sbi, start)->valid_blocks +=
+ se->valid_blocks;
}
start_blk += readed;
} while (start_blk < sit_blk_cnt);
+
+ down_read(&curseg->journal_rwsem);
+ for (i = 0; i < sits_in_cursum(journal); i++) {
+ unsigned int old_valid_blocks;
+
+ start = le32_to_cpu(segno_in_journal(journal, i));
+ se = &sit_i->sentries[start];
+ sit = sit_in_journal(journal, i);
+
+ old_valid_blocks = se->valid_blocks;
+
+ check_block_count(sbi, start, &sit);
+ seg_info_from_raw_sit(se, &sit);
+
+ if (f2fs_discard_en(sbi)) {
+ if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) {
+ memset(se->discard_map, 0xff,
+ SIT_VBLOCK_MAP_SIZE);
+ } else {
+ memcpy(se->discard_map, se->cur_valid_map,
+ SIT_VBLOCK_MAP_SIZE);
+ sbi->discard_blks += old_valid_blocks -
+ se->valid_blocks;
+ }
+ }
+
+ if (sbi->segs_per_sec > 1)
+ get_sec_entry(sbi, start)->valid_blocks +=
+ se->valid_blocks - old_valid_blocks;
+ }
+ up_read(&curseg->journal_rwsem);
}
static void init_free_segmap(struct f2fs_sb_info *sbi)
@@ -1937,6 +3152,9 @@
struct seg_entry *sentry = get_seg_entry(sbi, start);
if (!sentry->valid_blocks)
__set_free(sbi, start);
+ else
+ SIT_I(sbi)->written_valid_blocks +=
+ sentry->valid_blocks;
}
/* set use the current segments */
@@ -1959,7 +3177,7 @@
if (segno >= MAIN_SEGS(sbi))
break;
offset = segno + 1;
- valid_blocks = get_valid_blocks(sbi, segno, 0);
+ valid_blocks = get_valid_blocks(sbi, segno, false);
if (valid_blocks == sbi->blocks_per_seg || !valid_blocks)
continue;
if (valid_blocks > sbi->blocks_per_seg) {
@@ -1977,7 +3195,7 @@
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
unsigned int bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi));
- dirty_i->victim_secmap = kzalloc(bitmap_size, GFP_KERNEL);
+ dirty_i->victim_secmap = f2fs_kvzalloc(bitmap_size, GFP_KERNEL);
if (!dirty_i->victim_secmap)
return -ENOMEM;
return 0;
@@ -1999,7 +3217,7 @@
bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
for (i = 0; i < NR_DIRTY_TYPE; i++) {
- dirty_i->dirty_segmap[i] = kzalloc(bitmap_size, GFP_KERNEL);
+ dirty_i->dirty_segmap[i] = f2fs_kvzalloc(bitmap_size, GFP_KERNEL);
if (!dirty_i->dirty_segmap[i])
return -ENOMEM;
}
@@ -2058,13 +3276,16 @@
sm_info->ssa_blkaddr = le32_to_cpu(raw_super->ssa_blkaddr);
sm_info->rec_prefree_segments = sm_info->main_segments *
DEF_RECLAIM_PREFREE_SEGMENTS / 100;
- sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC;
+ if (sm_info->rec_prefree_segments > DEF_MAX_RECLAIM_PREFREE_SEGMENTS)
+ sm_info->rec_prefree_segments = DEF_MAX_RECLAIM_PREFREE_SEGMENTS;
+
+ if (!test_opt(sbi, LFS))
+ sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC;
sm_info->min_ipu_util = DEF_MIN_IPU_UTIL;
sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS;
+ sm_info->min_hot_blocks = DEF_MIN_HOT_BLOCKS;
- INIT_LIST_HEAD(&sm_info->discard_list);
- sm_info->nr_discards = 0;
- sm_info->max_discards = 0;
+ sm_info->trim_sections = DEF_BATCHED_TRIM_SECTIONS;
INIT_LIST_HEAD(&sm_info->sit_entry_set);
@@ -2074,6 +3295,10 @@
return err;
}
+ err = create_discard_cmd_control(sbi);
+ if (err)
+ return err;
+
err = build_sit_info(sbi);
if (err)
return err;
@@ -2102,7 +3327,7 @@
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
mutex_lock(&dirty_i->seglist_lock);
- kfree(dirty_i->dirty_segmap[dirty_type]);
+ kvfree(dirty_i->dirty_segmap[dirty_type]);
dirty_i->nr_dirty[dirty_type] = 0;
mutex_unlock(&dirty_i->seglist_lock);
}
@@ -2110,7 +3335,7 @@
static void destroy_victim_secmap(struct f2fs_sb_info *sbi)
{
struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
- kfree(dirty_i->victim_secmap);
+ kvfree(dirty_i->victim_secmap);
}
static void destroy_dirty_segmap(struct f2fs_sb_info *sbi)
@@ -2138,8 +3363,10 @@
if (!array)
return;
SM_I(sbi)->curseg_array = NULL;
- for (i = 0; i < NR_CURSEG_TYPE; i++)
+ for (i = 0; i < NR_CURSEG_TYPE; i++) {
kfree(array[i].sum_blk);
+ kfree(array[i].journal);
+ }
kfree(array);
}
@@ -2149,8 +3376,8 @@
if (!free_i)
return;
SM_I(sbi)->free_info = NULL;
- kfree(free_i->free_segmap);
- kfree(free_i->free_secmap);
+ kvfree(free_i->free_segmap);
+ kvfree(free_i->free_secmap);
kfree(free_i);
}
@@ -2165,15 +3392,24 @@
if (sit_i->sentries) {
for (start = 0; start < MAIN_SEGS(sbi); start++) {
kfree(sit_i->sentries[start].cur_valid_map);
+#ifdef CONFIG_F2FS_CHECK_FS
+ kfree(sit_i->sentries[start].cur_valid_map_mir);
+#endif
kfree(sit_i->sentries[start].ckpt_valid_map);
+ kfree(sit_i->sentries[start].discard_map);
}
}
- vfree(sit_i->sentries);
- vfree(sit_i->sec_entries);
- kfree(sit_i->dirty_sentries_bitmap);
+ kfree(sit_i->tmp_map);
+
+ kvfree(sit_i->sentries);
+ kvfree(sit_i->sec_entries);
+ kvfree(sit_i->dirty_sentries_bitmap);
SM_I(sbi)->sit_info = NULL;
kfree(sit_i->sit_bitmap);
+#ifdef CONFIG_F2FS_CHECK_FS
+ kfree(sit_i->sit_bitmap_mir);
+#endif
kfree(sit_i);
}
@@ -2183,7 +3419,8 @@
if (!sm_info)
return;
- destroy_flush_cmd_control(sbi);
+ destroy_flush_cmd_control(sbi, true);
+ destroy_discard_cmd_control(sbi);
destroy_dirty_segmap(sbi);
destroy_curseg(sbi);
destroy_free_segmap(sbi);
@@ -2199,10 +3436,15 @@
if (!discard_entry_slab)
goto fail;
+ discard_cmd_slab = f2fs_kmem_cache_create("discard_cmd",
+ sizeof(struct discard_cmd));
+ if (!discard_cmd_slab)
+ goto destroy_discard_entry;
+
sit_entry_set_slab = f2fs_kmem_cache_create("sit_entry_set",
- sizeof(struct nat_entry_set));
+ sizeof(struct sit_entry_set));
if (!sit_entry_set_slab)
- goto destory_discard_entry;
+ goto destroy_discard_cmd;
inmem_entry_slab = f2fs_kmem_cache_create("inmem_page_entry",
sizeof(struct inmem_pages));
@@ -2212,7 +3454,9 @@
destroy_sit_entry_set:
kmem_cache_destroy(sit_entry_set_slab);
-destory_discard_entry:
+destroy_discard_cmd:
+ kmem_cache_destroy(discard_cmd_slab);
+destroy_discard_entry:
kmem_cache_destroy(discard_entry_slab);
fail:
return -ENOMEM;
@@ -2221,6 +3465,7 @@
void destroy_segment_manager_caches(void)
{
kmem_cache_destroy(sit_entry_set_slab);
+ kmem_cache_destroy(discard_cmd_slab);
kmem_cache_destroy(discard_entry_slab);
kmem_cache_destroy(inmem_entry_slab);
}
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 2495bec..f488f0e 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -15,80 +15,89 @@
#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 */
+
+#define F2FS_MIN_SEGMENTS 9 /* SB + 2 (CP + SIT + NAT) + SSA + MAIN */
/* L: Logical segment # in volume, R: Relative segment # in main area */
-#define GET_L2R_SEGNO(free_i, segno) (segno - free_i->start_segno)
-#define GET_R2L_SEGNO(free_i, segno) (segno + free_i->start_segno)
+#define GET_L2R_SEGNO(free_i, segno) ((segno) - (free_i)->start_segno)
+#define GET_R2L_SEGNO(free_i, segno) ((segno) + (free_i)->start_segno)
-#define IS_DATASEG(t) (t <= CURSEG_COLD_DATA)
-#define IS_NODESEG(t) (t >= CURSEG_HOT_NODE)
+#define IS_DATASEG(t) ((t) <= CURSEG_COLD_DATA)
+#define IS_NODESEG(t) ((t) >= CURSEG_HOT_NODE)
#define IS_CURSEG(sbi, seg) \
- ((seg == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno) || \
- (seg == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno) || \
- (seg == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno) || \
- (seg == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno) || \
- (seg == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno) || \
- (seg == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno))
+ (((seg) == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno) || \
+ ((seg) == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno) || \
+ ((seg) == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno) || \
+ ((seg) == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno) || \
+ ((seg) == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno) || \
+ ((seg) == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno))
#define IS_CURSEC(sbi, secno) \
- ((secno == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno / \
- sbi->segs_per_sec) || \
- (secno == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno / \
- sbi->segs_per_sec) || \
- (secno == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno / \
- sbi->segs_per_sec) || \
- (secno == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno / \
- sbi->segs_per_sec) || \
- (secno == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno / \
- sbi->segs_per_sec) || \
- (secno == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno / \
- sbi->segs_per_sec)) \
+ (((secno) == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno / \
+ (sbi)->segs_per_sec) || \
+ ((secno) == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno / \
+ (sbi)->segs_per_sec) || \
+ ((secno) == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno / \
+ (sbi)->segs_per_sec) || \
+ ((secno) == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno / \
+ (sbi)->segs_per_sec) || \
+ ((secno) == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno / \
+ (sbi)->segs_per_sec) || \
+ ((secno) == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno / \
+ (sbi)->segs_per_sec)) \
#define MAIN_BLKADDR(sbi) (SM_I(sbi)->main_blkaddr)
#define SEG0_BLKADDR(sbi) (SM_I(sbi)->seg0_blkaddr)
#define MAIN_SEGS(sbi) (SM_I(sbi)->main_segments)
-#define MAIN_SECS(sbi) (sbi->total_sections)
+#define MAIN_SECS(sbi) ((sbi)->total_sections)
#define TOTAL_SEGS(sbi) (SM_I(sbi)->segment_count)
-#define TOTAL_BLKS(sbi) (TOTAL_SEGS(sbi) << sbi->log_blocks_per_seg)
+#define TOTAL_BLKS(sbi) (TOTAL_SEGS(sbi) << (sbi)->log_blocks_per_seg)
#define MAX_BLKADDR(sbi) (SEG0_BLKADDR(sbi) + TOTAL_BLKS(sbi))
-#define SEGMENT_SIZE(sbi) (1ULL << (sbi->log_blocksize + \
- sbi->log_blocks_per_seg))
+#define SEGMENT_SIZE(sbi) (1ULL << ((sbi)->log_blocksize + \
+ (sbi)->log_blocks_per_seg))
#define START_BLOCK(sbi, segno) (SEG0_BLKADDR(sbi) + \
- (GET_R2L_SEGNO(FREE_I(sbi), segno) << sbi->log_blocks_per_seg))
+ (GET_R2L_SEGNO(FREE_I(sbi), segno) << (sbi)->log_blocks_per_seg))
#define NEXT_FREE_BLKADDR(sbi, curseg) \
- (START_BLOCK(sbi, curseg->segno) + curseg->next_blkoff)
+ (START_BLOCK(sbi, (curseg)->segno) + (curseg)->next_blkoff)
#define GET_SEGOFF_FROM_SEG0(sbi, blk_addr) ((blk_addr) - SEG0_BLKADDR(sbi))
#define GET_SEGNO_FROM_SEG0(sbi, blk_addr) \
- (GET_SEGOFF_FROM_SEG0(sbi, blk_addr) >> sbi->log_blocks_per_seg)
+ (GET_SEGOFF_FROM_SEG0(sbi, blk_addr) >> (sbi)->log_blocks_per_seg)
#define GET_BLKOFF_FROM_SEG0(sbi, blk_addr) \
- (GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & (sbi->blocks_per_seg - 1))
+ (GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & ((sbi)->blocks_per_seg - 1))
#define GET_SEGNO(sbi, blk_addr) \
- (((blk_addr == NULL_ADDR) || (blk_addr == NEW_ADDR)) ? \
+ ((((blk_addr) == NULL_ADDR) || ((blk_addr) == NEW_ADDR)) ? \
NULL_SEGNO : GET_L2R_SEGNO(FREE_I(sbi), \
GET_SEGNO_FROM_SEG0(sbi, blk_addr)))
-#define GET_SECNO(sbi, segno) \
- ((segno) / sbi->segs_per_sec)
-#define GET_ZONENO_FROM_SEGNO(sbi, segno) \
- ((segno / sbi->segs_per_sec) / sbi->secs_per_zone)
+#define BLKS_PER_SEC(sbi) \
+ ((sbi)->segs_per_sec * (sbi)->blocks_per_seg)
+#define GET_SEC_FROM_SEG(sbi, segno) \
+ ((segno) / (sbi)->segs_per_sec)
+#define GET_SEG_FROM_SEC(sbi, secno) \
+ ((secno) * (sbi)->segs_per_sec)
+#define GET_ZONE_FROM_SEC(sbi, secno) \
+ ((secno) / (sbi)->secs_per_zone)
+#define GET_ZONE_FROM_SEG(sbi, segno) \
+ GET_ZONE_FROM_SEC(sbi, GET_SEC_FROM_SEG(sbi, segno))
#define GET_SUM_BLOCK(sbi, segno) \
- ((sbi->sm_info->ssa_blkaddr) + segno)
+ ((sbi)->sm_info->ssa_blkaddr + (segno))
#define GET_SUM_TYPE(footer) ((footer)->entry_type)
-#define SET_SUM_TYPE(footer, type) ((footer)->entry_type = type)
+#define SET_SUM_TYPE(footer, type) ((footer)->entry_type = (type))
#define SIT_ENTRY_OFFSET(sit_i, segno) \
- (segno % sit_i->sents_per_block)
+ ((segno) % (sit_i)->sents_per_block)
#define SIT_BLOCK_OFFSET(segno) \
- (segno / SIT_ENTRY_PER_BLOCK)
+ ((segno) / SIT_ENTRY_PER_BLOCK)
#define START_SEGNO(segno) \
(SIT_BLOCK_OFFSET(segno) * SIT_ENTRY_PER_BLOCK)
#define SIT_BLK_CNT(sbi) \
@@ -99,9 +108,7 @@
#define SECTOR_FROM_BLOCK(blk_addr) \
(((sector_t)blk_addr) << F2FS_LOG_SECTORS_PER_BLOCK)
#define SECTOR_TO_BLOCK(sectors) \
- (sectors >> F2FS_LOG_SECTORS_PER_BLOCK)
-#define MAX_BIO_BLOCKS(sbi) \
- ((int)min((int)max_hw_blocks(sbi), BIO_MAX_PAGES))
+ ((sectors) >> F2FS_LOG_SECTORS_PER_BLOCK)
/*
* indicate a block allocation direction: RIGHT and LEFT.
@@ -130,16 +137,21 @@
*/
enum {
GC_CB = 0,
- GC_GREEDY
+ GC_GREEDY,
+ ALLOC_NEXT,
+ FLUSH_DEVICE,
+ MAX_GC_POLICY,
};
/*
* 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 +167,20 @@
};
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 */
+#ifdef CONFIG_F2FS_CHECK_FS
+ unsigned char *cur_valid_map_mir; /* mirror of current valid bitmap */
+#endif
/*
* # 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 +192,22 @@
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 DUMMY_WRITTEN_PAGE ((unsigned long)-2)
+
+#define IS_ATOMIC_WRITTEN_PAGE(page) \
+ (page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE)
+#define IS_DUMMY_WRITTEN_PAGE(page) \
+ (page_private(page) == (unsigned long)DUMMY_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 {
@@ -187,8 +217,12 @@
block_t sit_blocks; /* # of blocks used by SIT area */
block_t written_valid_blocks; /* # of valid blocks in main area */
char *sit_bitmap; /* SIT bitmap pointer */
+#ifdef CONFIG_F2FS_CHECK_FS
+ char *sit_bitmap_mir; /* SIT bitmap mirror */
+#endif
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 */
@@ -201,13 +235,15 @@
unsigned long long mounted_time; /* mount time */
unsigned long long min_mtime; /* min. modification time */
unsigned long long max_mtime; /* max. modification time */
+
+ unsigned int last_victim[MAX_GC_POLICY]; /* last victim segment # */
};
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 +279,8 @@
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 */
@@ -275,17 +313,17 @@
unsigned int segno)
{
struct sit_info *sit_i = SIT_I(sbi);
- return &sit_i->sec_entries[GET_SECNO(sbi, segno)];
+ return &sit_i->sec_entries[GET_SEC_FROM_SEG(sbi, segno)];
}
static inline unsigned int get_valid_blocks(struct f2fs_sb_info *sbi,
- unsigned int segno, int section)
+ unsigned int segno, bool use_section)
{
/*
* In order to get # of valid blocks in a section instantly from many
* segments, f2fs manages two counting structures separately.
*/
- if (section > 1)
+ if (use_section && sbi->segs_per_sec > 1)
return get_sec_entry(sbi, segno)->valid_blocks;
else
return get_seg_entry(sbi, segno)->valid_blocks;
@@ -298,6 +336,9 @@
se->ckpt_valid_blocks = GET_SIT_VBLOCKS(rs);
memcpy(se->cur_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
+#ifdef CONFIG_F2FS_CHECK_FS
+ memcpy(se->cur_valid_map_mir, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
+#endif
se->type = GET_SIT_TYPE(rs);
se->mtime = le64_to_cpu(rs->mtime);
}
@@ -318,36 +359,38 @@
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;
}
static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
{
struct free_segmap_info *free_i = FREE_I(sbi);
- unsigned int secno = segno / sbi->segs_per_sec;
- unsigned int start_segno = secno * sbi->segs_per_sec;
+ unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+ unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
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,
unsigned int segno)
{
struct free_segmap_info *free_i = FREE_I(sbi);
- unsigned int secno = segno / sbi->segs_per_sec;
+ unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+
set_bit(segno, free_i->free_segmap);
free_i->free_segments--;
if (!test_and_set_bit(secno, free_i->free_secmap))
@@ -358,11 +401,11 @@
unsigned int segno)
{
struct free_segmap_info *free_i = FREE_I(sbi);
- unsigned int secno = segno / sbi->segs_per_sec;
- unsigned int start_segno = secno * sbi->segs_per_sec;
+ unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+ unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
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++;
@@ -373,27 +416,34 @@
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,
unsigned int segno)
{
struct free_segmap_info *free_i = FREE_I(sbi);
- unsigned int secno = segno / sbi->segs_per_sec;
- write_lock(&free_i->segmap_lock);
+ unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+
+ 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,
void *dst_addr)
{
struct sit_info *sit_i = SIT_I(sbi);
+
+#ifdef CONFIG_F2FS_CHECK_FS
+ if (memcmp(sit_i->sit_bitmap, sit_i->sit_bitmap_mir,
+ sit_i->bitmap_size))
+ f2fs_bug_on(sbi, 1);
+#endif
memcpy(dst_addr, sit_i->sit_bitmap, sit_i->bitmap_size);
}
@@ -439,32 +489,40 @@
static inline int overprovision_sections(struct f2fs_sb_info *sbi)
{
- return ((unsigned int) overprovision_segments(sbi)) / sbi->segs_per_sec;
+ return GET_SEC_FROM_SEG(sbi, (unsigned int)overprovision_segments(sbi));
}
static inline int reserved_sections(struct f2fs_sb_info *sbi)
{
- return ((unsigned int) reserved_segments(sbi)) / sbi->segs_per_sec;
+ return GET_SEC_FROM_SEG(sbi, (unsigned int)reserved_segments(sbi));
}
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);
- return free_sections(sbi) <= (node_secs + 2 * dent_secs +
- reserved_sections(sbi) + 1);
+ int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA);
+
+ if (test_opt(sbi, LFS))
+ return false;
+
+ return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs +
+ 2 * reserved_sections(sbi));
}
-static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed)
+static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi,
+ int freed, int needed)
{
int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES);
int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS);
+ int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA);
- if (unlikely(sbi->por_doing))
+ if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
return false;
- return (free_sections(sbi) + freed) <= (node_secs + 2 * dent_secs +
- reserved_sections(sbi));
+ return (free_sections(sbi) + freed) <=
+ (node_secs + 2 * dent_secs + imeta_secs +
+ reserved_sections(sbi) + needed);
}
static inline bool excess_prefree_segs(struct f2fs_sb_info *sbi)
@@ -494,6 +552,7 @@
*/
#define DEF_MIN_IPU_UTIL 70
#define DEF_MIN_FSYNC_BLOCKS 8
+#define DEF_MIN_HOT_BLOCKS 16
enum {
F2FS_IPU_FORCE,
@@ -501,15 +560,16 @@
F2FS_IPU_UTIL,
F2FS_IPU_SSR_UTIL,
F2FS_IPU_FSYNC,
+ F2FS_IPU_ASYNC,
};
-static inline bool need_inplace_update(struct inode *inode)
+static inline bool need_inplace_update_policy(struct inode *inode,
+ struct f2fs_io_info *fio)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
unsigned int policy = SM_I(sbi)->ipu_policy;
- /* IPU can be done only for the user data */
- if (S_ISDIR(inode->i_mode) || f2fs_is_atomic_file(inode))
+ if (test_opt(sbi, LFS))
return false;
if (policy & (0x1 << F2FS_IPU_FORCE))
@@ -523,9 +583,18 @@
utilization(sbi) > SM_I(sbi)->min_ipu_util)
return true;
+ /*
+ * IPU for rewrite async pages
+ */
+ if (policy & (0x1 << F2FS_IPU_ASYNC) &&
+ fio && fio->op == REQ_OP_WRITE &&
+ !(fio->op_flags & REQ_SYNC) &&
+ !f2fs_encrypted_inode(inode))
+ return true;
+
/* 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 +620,15 @@
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));
+ BUG_ON(blk_addr < SEG0_BLKADDR(sbi)
+ || blk_addr >= MAX_BLKADDR(sbi));
}
/*
@@ -569,16 +637,11 @@
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 +657,11 @@
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)
@@ -633,6 +672,12 @@
check_seg_range(sbi, start);
+#ifdef CONFIG_F2FS_CHECK_FS
+ if (f2fs_test_bit(offset, sit_i->sit_bitmap) !=
+ f2fs_test_bit(offset, sit_i->sit_bitmap_mir))
+ f2fs_bug_on(sbi, 1);
+#endif
+
/* calculate sit block address */
if (f2fs_test_bit(offset, sit_i->sit_bitmap))
blk_addr += sit_i->sit_blocks;
@@ -657,10 +702,10 @@
{
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);
+#ifdef CONFIG_F2FS_CHECK_FS
+ f2fs_change_bit(block_off, sit_i->sit_bitmap_mir);
+#endif
}
static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi)
@@ -691,6 +736,15 @@
- (base + 1) + type;
}
+static inline bool no_fggc_candidate(struct f2fs_sb_info *sbi,
+ unsigned int secno)
+{
+ if (get_valid_blocks(sbi, GET_SEG_FROM_SEC(sbi, secno), true) >=
+ sbi->fggc_threshold)
+ return true;
+ return false;
+}
+
static inline bool sec_usage_check(struct f2fs_sb_info *sbi, unsigned int secno)
{
if (IS_CURSEC(sbi, secno) || (sbi->cur_victim_sec == secno))
@@ -698,28 +752,24 @@
return false;
}
-static inline unsigned int max_hw_blocks(struct f2fs_sb_info *sbi)
-{
- struct block_device *bdev = sbi->sb->s_bdev;
- struct request_queue *q = bdev_get_queue(bdev);
- return SECTOR_TO_BLOCK(queue_max_sectors(q));
-}
-
/*
* It is very important to gather dirty pages and write at once, so that we can
* submit a big bio without interfering other data writes.
* By default, 512 pages for directory data,
- * 512 pages (2MB) * 3 for three types of nodes, and
- * max_bio_blocks for meta are set.
+ * 512 pages (2MB) * 8 for nodes, and
+ * 256 pages * 8 for meta are set.
*/
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 * BIO_MAX_PAGES;
else
return 0;
}
@@ -736,13 +786,9 @@
return 0;
nr_to_write = wbc->nr_to_write;
-
- if (type == DATA)
- desired = 4096;
- else if (type == NODE)
- desired = 3 * max_hw_blocks(sbi);
- else
- desired = MAX_BIO_BLOCKS(sbi);
+ desired = BIO_MAX_PAGES;
+ if (type == NODE)
+ desired <<= 1;
wbc->nr_to_write = desired;
return desired - nr_to_write;
diff --git a/fs/f2fs/shrinker.c b/fs/f2fs/shrinker.c
new file mode 100644
index 0000000..5c60fc2
--- /dev/null
+++ b/fs/f2fs/shrinker.c
@@ -0,0 +1,143 @@
+/*
+ * 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)
+{
+ long count = NM_I(sbi)->nat_cnt - NM_I(sbi)->dirty_nat_cnt;
+
+ return count > 0 ? count : 0;
+}
+
+static unsigned long __count_free_nids(struct f2fs_sb_info *sbi)
+{
+ long count = NM_I(sbi)->nid_cnt[FREE_NID_LIST] - MAX_FREE_NIDS;
+
+ return count > 0 ? count : 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);
+}
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 840efcc..d1db520 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -30,6 +30,7 @@
#include "segment.h"
#include "xattr.h"
#include "gc.h"
+#include "trace.h"
#define CREATE_TRACE_POINTS
#include <trace/events/f2fs.h>
@@ -38,11 +39,51 @@
static struct kmem_cache *f2fs_inode_cachep;
static struct kset *f2fs_kset;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+
+char *fault_name[FAULT_MAX] = {
+ [FAULT_KMALLOC] = "kmalloc",
+ [FAULT_PAGE_ALLOC] = "page alloc",
+ [FAULT_ALLOC_NID] = "alloc nid",
+ [FAULT_ORPHAN] = "orphan",
+ [FAULT_BLOCK] = "no more block",
+ [FAULT_DIR_DEPTH] = "too big dir depth",
+ [FAULT_EVICT_INODE] = "evict_inode fail",
+ [FAULT_TRUNCATE] = "truncate fail",
+ [FAULT_IO] = "IO error",
+ [FAULT_CHECKPOINT] = "checkpoint error",
+};
+
+static void f2fs_build_fault_attr(struct f2fs_sb_info *sbi,
+ unsigned int rate)
+{
+ struct f2fs_fault_info *ffi = &sbi->fault_info;
+
+ if (rate) {
+ atomic_set(&ffi->inject_ops, 0);
+ ffi->inject_rate = rate;
+ ffi->inject_type = (1 << FAULT_MAX) - 1;
+ } else {
+ memset(ffi, 0, sizeof(struct f2fs_fault_info));
+ }
+}
+#endif
+
+/* f2fs-wide shrinker description */
+static struct shrinker f2fs_shrinker_info = {
+ .scan_objects = f2fs_shrink_scan,
+ .count_objects = f2fs_shrink_count,
+ .seeks = DEFAULT_SEEKS,
+};
+
enum {
Opt_gc_background,
Opt_disable_roll_forward,
+ Opt_norecovery,
Opt_discard,
+ Opt_nodiscard,
Opt_noheap,
+ Opt_heap,
Opt_user_xattr,
Opt_nouser_xattr,
Opt_acl,
@@ -50,17 +91,32 @@
Opt_active_logs,
Opt_disable_ext_identify,
Opt_inline_xattr,
+ Opt_noinline_xattr,
Opt_inline_data,
+ Opt_inline_dentry,
+ Opt_noinline_dentry,
Opt_flush_merge,
+ Opt_noflush_merge,
Opt_nobarrier,
+ Opt_fastboot,
+ Opt_extent_cache,
+ Opt_noextent_cache,
+ Opt_noinline_data,
+ Opt_data_flush,
+ Opt_mode,
+ Opt_io_size_bits,
+ Opt_fault_injection,
Opt_err,
};
static match_table_t f2fs_tokens = {
{Opt_gc_background, "background_gc=%s"},
{Opt_disable_roll_forward, "disable_roll_forward"},
+ {Opt_norecovery, "norecovery"},
{Opt_discard, "discard"},
+ {Opt_nodiscard, "nodiscard"},
{Opt_noheap, "no_heap"},
+ {Opt_heap, "heap"},
{Opt_user_xattr, "user_xattr"},
{Opt_nouser_xattr, "nouser_xattr"},
{Opt_acl, "acl"},
@@ -68,9 +124,21 @@
{Opt_active_logs, "active_logs=%u"},
{Opt_disable_ext_identify, "disable_ext_identify"},
{Opt_inline_xattr, "inline_xattr"},
+ {Opt_noinline_xattr, "noinline_xattr"},
{Opt_inline_data, "inline_data"},
+ {Opt_inline_dentry, "inline_dentry"},
+ {Opt_noinline_dentry, "noinline_dentry"},
{Opt_flush_merge, "flush_merge"},
+ {Opt_noflush_merge, "noflush_merge"},
{Opt_nobarrier, "nobarrier"},
+ {Opt_fastboot, "fastboot"},
+ {Opt_extent_cache, "extent_cache"},
+ {Opt_noextent_cache, "noextent_cache"},
+ {Opt_noinline_data, "noinline_data"},
+ {Opt_data_flush, "data_flush"},
+ {Opt_mode, "mode=%s"},
+ {Opt_io_size_bits, "io_bits=%u"},
+ {Opt_fault_injection, "fault_injection=%u"},
{Opt_err, NULL},
};
@@ -78,8 +146,13 @@
enum {
GC_THREAD, /* struct f2fs_gc_thread */
SM_INFO, /* struct f2fs_sm_info */
+ DCC_INFO, /* struct discard_cmd_control */
NM_INFO, /* struct f2fs_nm_info */
F2FS_SBI, /* struct f2fs_sb_info */
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ FAULT_INFO_RATE, /* struct f2fs_fault_info */
+ FAULT_INFO_TYPE, /* struct f2fs_fault_info */
+#endif
};
struct f2fs_attr {
@@ -97,13 +170,33 @@
return (unsigned char *)sbi->gc_thread;
else if (struct_type == SM_INFO)
return (unsigned char *)SM_I(sbi);
+ else if (struct_type == DCC_INFO)
+ return (unsigned char *)SM_I(sbi)->dcc_info;
else if (struct_type == NM_INFO)
return (unsigned char *)NM_I(sbi);
else if (struct_type == F2FS_SBI)
return (unsigned char *)sbi;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ else if (struct_type == FAULT_INFO_RATE ||
+ struct_type == FAULT_INFO_TYPE)
+ return (unsigned char *)&sbi->fault_info;
+#endif
return NULL;
}
+static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi, char *buf)
+{
+ struct super_block *sb = sbi->sb;
+
+ if (!sb->s_bdev->bd_part)
+ return snprintf(buf, PAGE_SIZE, "0\n");
+
+ return snprintf(buf, PAGE_SIZE, "%llu\n",
+ (unsigned long long)(sbi->kbytes_written +
+ BD_PART_WRITTEN(sbi)));
+}
+
static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
struct f2fs_sb_info *sbi, char *buf)
{
@@ -137,6 +230,10 @@
ret = kstrtoul(skip_spaces(buf), 0, &t);
if (ret < 0)
return ret;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (a->struct_type == FAULT_INFO_TYPE && t >= (1 << FAULT_MAX))
+ return -EINVAL;
+#endif
*ui = t;
return count;
}
@@ -182,18 +279,32 @@
f2fs_sbi_show, f2fs_sbi_store, \
offsetof(struct struct_name, elname))
+#define F2FS_GENERAL_RO_ATTR(name) \
+static struct f2fs_attr f2fs_attr_##name = __ATTR(name, 0444, name##_show, NULL)
+
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_min_sleep_time, min_sleep_time);
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_max_sleep_time, max_sleep_time);
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time);
F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_idle, gc_idle);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments);
-F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, max_small_discards, max_discards);
+F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, max_small_discards, max_discards);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, batched_trim_sections, trim_sections);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util);
F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_hot_blocks, min_hot_blocks);
F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh);
+F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ra_nid_pages, ra_nid_pages);
+F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, dirty_nats_ratio, dirty_nats_ratio);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search);
F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, interval_time[CP_TIME]);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+F2FS_RW_ATTR(FAULT_INFO_RATE, f2fs_fault_info, inject_rate, inject_rate);
+F2FS_RW_ATTR(FAULT_INFO_TYPE, f2fs_fault_info, inject_type, inject_type);
+#endif
+F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes);
#define ATTR_LIST(name) (&f2fs_attr_##name.attr)
static struct attribute *f2fs_attrs[] = {
@@ -203,12 +314,23 @@
ATTR_LIST(gc_idle),
ATTR_LIST(reclaim_segments),
ATTR_LIST(max_small_discards),
+ ATTR_LIST(batched_trim_sections),
ATTR_LIST(ipu_policy),
ATTR_LIST(min_ipu_util),
ATTR_LIST(min_fsync_blocks),
+ ATTR_LIST(min_hot_blocks),
ATTR_LIST(max_victim_search),
ATTR_LIST(dir_level),
ATTR_LIST(ram_thresh),
+ ATTR_LIST(ra_nid_pages),
+ ATTR_LIST(dirty_nats_ratio),
+ ATTR_LIST(cp_interval),
+ ATTR_LIST(idle_interval),
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ ATTR_LIST(inject_rate),
+ ATTR_LIST(inject_type),
+#endif
+ ATTR_LIST(lifetime_write_kbytes),
NULL,
};
@@ -245,6 +367,7 @@
static int parse_options(struct super_block *sb, char *options)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ struct request_queue *q;
substring_t args[MAX_OPT_ARGS];
char *p, *name;
int arg = 0;
@@ -269,11 +392,16 @@
if (!name)
return -ENOMEM;
- if (strlen(name) == 2 && !strncmp(name, "on", 2))
+ if (strlen(name) == 2 && !strncmp(name, "on", 2)) {
set_opt(sbi, BG_GC);
- else if (strlen(name) == 3 && !strncmp(name, "off", 3))
+ clear_opt(sbi, FORCE_FG_GC);
+ } else if (strlen(name) == 3 && !strncmp(name, "off", 3)) {
clear_opt(sbi, BG_GC);
- else {
+ clear_opt(sbi, FORCE_FG_GC);
+ } else if (strlen(name) == 4 && !strncmp(name, "sync", 4)) {
+ set_opt(sbi, BG_GC);
+ set_opt(sbi, FORCE_FG_GC);
+ } else {
kfree(name);
return -EINVAL;
}
@@ -282,12 +410,36 @@
case Opt_disable_roll_forward:
set_opt(sbi, DISABLE_ROLL_FORWARD);
break;
+ case Opt_norecovery:
+ /* this option mounts f2fs with ro */
+ set_opt(sbi, DISABLE_ROLL_FORWARD);
+ if (!f2fs_readonly(sb))
+ return -EINVAL;
+ break;
case Opt_discard:
- set_opt(sbi, DISCARD);
+ q = bdev_get_queue(sb->s_bdev);
+ if (blk_queue_discard(q)) {
+ set_opt(sbi, DISCARD);
+ } else if (!f2fs_sb_mounted_blkzoned(sb)) {
+ f2fs_msg(sb, KERN_WARNING,
+ "mounting with \"discard\" option, but "
+ "the device does not support discard");
+ }
+ break;
+ case Opt_nodiscard:
+ if (f2fs_sb_mounted_blkzoned(sb)) {
+ f2fs_msg(sb, KERN_WARNING,
+ "discard is required for zoned block devices");
+ return -EINVAL;
+ }
+ clear_opt(sbi, DISCARD);
break;
case Opt_noheap:
set_opt(sbi, NOHEAP);
break;
+ case Opt_heap:
+ clear_opt(sbi, NOHEAP);
+ break;
#ifdef CONFIG_F2FS_FS_XATTR
case Opt_user_xattr:
set_opt(sbi, XATTR_USER);
@@ -298,6 +450,9 @@
case Opt_inline_xattr:
set_opt(sbi, INLINE_XATTR);
break;
+ case Opt_noinline_xattr:
+ clear_opt(sbi, INLINE_XATTR);
+ break;
#else
case Opt_user_xattr:
f2fs_msg(sb, KERN_INFO,
@@ -311,6 +466,10 @@
f2fs_msg(sb, KERN_INFO,
"inline_xattr options not supported");
break;
+ case Opt_noinline_xattr:
+ f2fs_msg(sb, KERN_INFO,
+ "noinline_xattr options not supported");
+ break;
#endif
#ifdef CONFIG_F2FS_FS_POSIX_ACL
case Opt_acl:
@@ -340,12 +499,82 @@
case Opt_inline_data:
set_opt(sbi, INLINE_DATA);
break;
+ case Opt_inline_dentry:
+ set_opt(sbi, INLINE_DENTRY);
+ break;
+ case Opt_noinline_dentry:
+ clear_opt(sbi, INLINE_DENTRY);
+ break;
case Opt_flush_merge:
set_opt(sbi, FLUSH_MERGE);
break;
+ case Opt_noflush_merge:
+ clear_opt(sbi, FLUSH_MERGE);
+ break;
case Opt_nobarrier:
set_opt(sbi, NOBARRIER);
break;
+ case Opt_fastboot:
+ set_opt(sbi, FASTBOOT);
+ break;
+ case Opt_extent_cache:
+ set_opt(sbi, EXTENT_CACHE);
+ break;
+ case Opt_noextent_cache:
+ clear_opt(sbi, EXTENT_CACHE);
+ break;
+ case Opt_noinline_data:
+ clear_opt(sbi, INLINE_DATA);
+ break;
+ case Opt_data_flush:
+ set_opt(sbi, DATA_FLUSH);
+ break;
+ case Opt_mode:
+ name = match_strdup(&args[0]);
+
+ if (!name)
+ return -ENOMEM;
+ if (strlen(name) == 8 &&
+ !strncmp(name, "adaptive", 8)) {
+ if (f2fs_sb_mounted_blkzoned(sb)) {
+ f2fs_msg(sb, KERN_WARNING,
+ "adaptive mode is not allowed with "
+ "zoned block device feature");
+ kfree(name);
+ return -EINVAL;
+ }
+ set_opt_mode(sbi, F2FS_MOUNT_ADAPTIVE);
+ } else if (strlen(name) == 3 &&
+ !strncmp(name, "lfs", 3)) {
+ set_opt_mode(sbi, F2FS_MOUNT_LFS);
+ } else {
+ kfree(name);
+ return -EINVAL;
+ }
+ kfree(name);
+ break;
+ case Opt_io_size_bits:
+ if (args->from && match_int(args, &arg))
+ return -EINVAL;
+ if (arg > __ilog2_u32(BIO_MAX_PAGES)) {
+ f2fs_msg(sb, KERN_WARNING,
+ "Not support %d, larger than %d",
+ 1 << arg, BIO_MAX_PAGES);
+ return -EINVAL;
+ }
+ sbi->write_io_size_bits = arg;
+ break;
+ case Opt_fault_injection:
+ if (args->from && match_int(args, &arg))
+ return -EINVAL;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ f2fs_build_fault_attr(sbi, arg);
+ set_opt(sbi, FAULT_INJECTION);
+#else
+ f2fs_msg(sb, KERN_INFO,
+ "FAULT_INJECTION was not selected");
+#endif
+ break;
default:
f2fs_msg(sb, KERN_ERR,
"Unrecognized mount option \"%s\" or missing value",
@@ -353,6 +582,13 @@
return -EINVAL;
}
}
+
+ if (F2FS_IO_SIZE_BITS(sbi) && !test_opt(sbi, LFS)) {
+ f2fs_msg(sb, KERN_ERR,
+ "Should set mode=lfs with %uKB-sized IO",
+ F2FS_IO_SIZE_KB(sbi));
+ return -EINVAL;
+ }
return 0;
}
@@ -371,24 +607,22 @@
atomic_set(&fi->dirty_pages, 0);
fi->i_current_depth = 1;
fi->i_advise = 0;
- rwlock_init(&fi->ext.ext_lock);
init_rwsem(&fi->i_sem);
+ INIT_LIST_HEAD(&fi->dirty_list);
+ INIT_LIST_HEAD(&fi->gdirty_list);
INIT_LIST_HEAD(&fi->inmem_pages);
mutex_init(&fi->inmem_lock);
-
- set_inode_flag(fi, FI_NEW_INODE);
-
- if (test_opt(F2FS_SB(sb), INLINE_XATTR))
- set_inode_flag(fi, FI_INLINE_XATTR);
+ init_rwsem(&fi->dio_rwsem[READ]);
+ init_rwsem(&fi->dio_rwsem[WRITE]);
/* Will be used by directory only */
fi->i_dir_level = F2FS_SB(sb)->dir_level;
-
return &fi->vfs_inode;
}
static int f2fs_drop_inode(struct inode *inode)
{
+ int ret;
/*
* This is to avoid a deadlock condition like below.
* writeback_single_inode(inode)
@@ -396,9 +630,77 @@
* - f2fs_gc -> iput -> evict
* - inode_wait_for_writeback(inode)
*/
- if (!inode_unhashed(inode) && inode->i_state & I_SYNC)
+ if ((!inode_unhashed(inode) && inode->i_state & I_SYNC)) {
+ if (!inode->i_nlink && !is_bad_inode(inode)) {
+ /* to avoid evict_inode call simultaneously */
+ atomic_inc(&inode->i_count);
+ spin_unlock(&inode->i_lock);
+
+ /* some remained atomic pages should discarded */
+ if (f2fs_is_atomic_file(inode))
+ drop_inmem_pages(inode);
+
+ /* should remain fi->extent_tree for writepage */
+ f2fs_destroy_extent_node(inode);
+
+ sb_start_intwrite(inode->i_sb);
+ f2fs_i_size_write(inode, 0);
+
+ if (F2FS_HAS_BLOCKS(inode))
+ f2fs_truncate(inode);
+
+ sb_end_intwrite(inode->i_sb);
+
+ fscrypt_put_encryption_info(inode, NULL);
+ spin_lock(&inode->i_lock);
+ atomic_dec(&inode->i_count);
+ }
+ trace_f2fs_drop_inode(inode, 0);
return 0;
- return generic_drop_inode(inode);
+ }
+ ret = generic_drop_inode(inode);
+ trace_f2fs_drop_inode(inode, ret);
+ return ret;
+}
+
+int f2fs_inode_dirtied(struct inode *inode, bool sync)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ int ret = 0;
+
+ spin_lock(&sbi->inode_lock[DIRTY_META]);
+ if (is_inode_flag_set(inode, FI_DIRTY_INODE)) {
+ ret = 1;
+ } else {
+ set_inode_flag(inode, FI_DIRTY_INODE);
+ stat_inc_dirty_inode(sbi, DIRTY_META);
+ }
+ if (sync && list_empty(&F2FS_I(inode)->gdirty_list)) {
+ list_add_tail(&F2FS_I(inode)->gdirty_list,
+ &sbi->inode_list[DIRTY_META]);
+ inc_page_count(sbi, F2FS_DIRTY_IMETA);
+ }
+ spin_unlock(&sbi->inode_lock[DIRTY_META]);
+ return ret;
+}
+
+void f2fs_inode_synced(struct inode *inode)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+ spin_lock(&sbi->inode_lock[DIRTY_META]);
+ if (!is_inode_flag_set(inode, FI_DIRTY_INODE)) {
+ spin_unlock(&sbi->inode_lock[DIRTY_META]);
+ return;
+ }
+ if (!list_empty(&F2FS_I(inode)->gdirty_list)) {
+ list_del_init(&F2FS_I(inode)->gdirty_list);
+ dec_page_count(sbi, F2FS_DIRTY_IMETA);
+ }
+ clear_inode_flag(inode, FI_DIRTY_INODE);
+ clear_inode_flag(inode, FI_AUTO_RECOVER);
+ stat_dec_dirty_inode(F2FS_I_SB(inode), DIRTY_META);
+ spin_unlock(&sbi->inode_lock[DIRTY_META]);
}
/*
@@ -408,7 +710,16 @@
*/
static void f2fs_dirty_inode(struct inode *inode, int flags)
{
- set_inode_flag(F2FS_I(inode), FI_DIRTY_INODE);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+
+ if (inode->i_ino == F2FS_NODE_INO(sbi) ||
+ inode->i_ino == F2FS_META_INO(sbi))
+ return;
+
+ if (is_inode_flag_set(inode, FI_AUTO_RECOVER))
+ clear_inode_flag(inode, FI_AUTO_RECOVER);
+
+ f2fs_inode_dirtied(inode, false);
}
static void f2fs_i_callback(struct rcu_head *head)
@@ -422,33 +733,78 @@
call_rcu(&inode->i_rcu, f2fs_i_callback);
}
+static void destroy_percpu_info(struct f2fs_sb_info *sbi)
+{
+ percpu_counter_destroy(&sbi->alloc_valid_block_count);
+ percpu_counter_destroy(&sbi->total_valid_inode_count);
+}
+
+static void destroy_device_list(struct f2fs_sb_info *sbi)
+{
+ int i;
+
+ for (i = 0; i < sbi->s_ndevs; i++) {
+ blkdev_put(FDEV(i).bdev, FMODE_EXCL);
+#ifdef CONFIG_BLK_DEV_ZONED
+ kfree(FDEV(i).blkz_type);
+#endif
+ }
+ kfree(sbi->devs);
+}
+
static void f2fs_put_super(struct super_block *sb)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
if (sbi->s_proc) {
remove_proc_entry("segment_info", sbi->s_proc);
+ remove_proc_entry("segment_bits", sbi->s_proc);
remove_proc_entry(sb->s_id, f2fs_proc_root);
}
kobject_del(&sbi->s_kobj);
- f2fs_destroy_stats(sbi);
stop_gc_thread(sbi);
- /* We don't need to do checkpoint when it's clean */
- if (sbi->s_dirty) {
+ /* prevent remaining shrinker jobs */
+ mutex_lock(&sbi->umount_mutex);
+
+ /*
+ * We don't need to do checkpoint when superblock is clean.
+ * But, the previous checkpoint was not done by umount, it needs to do
+ * clean checkpoint again.
+ */
+ if (is_sbi_flag_set(sbi, SBI_IS_DIRTY) ||
+ !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) {
struct cp_control cpc = {
.reason = CP_UMOUNT,
};
write_checkpoint(sbi, &cpc);
}
+ /* be sure to wait for any on-going discard commands */
+ f2fs_wait_discard_bios(sbi);
+
+ if (!sbi->discard_blks) {
+ struct cp_control cpc = {
+ .reason = CP_UMOUNT | CP_TRIMMED,
+ };
+ write_checkpoint(sbi, &cpc);
+ }
+
+ /* write_checkpoint can update stat informaion */
+ f2fs_destroy_stats(sbi);
+
/*
* normally superblock is clean, so we need to release this.
* In addition, EIO will skip do checkpoint, we need this as well.
*/
- release_dirty_inode(sbi);
- release_discard_addrs(sbi);
+ release_ino_entry(sbi, true);
+
+ f2fs_leave_shrinker(sbi);
+ mutex_unlock(&sbi->umount_mutex);
+
+ /* our cp_error case, we can wait for any writeback page */
+ f2fs_flush_merged_bios(sbi);
iput(sbi->node_inode);
iput(sbi->meta_inode);
@@ -462,39 +818,51 @@
wait_for_completion(&sbi->s_kobj_unregister);
sb->s_fs_info = NULL;
- brelse(sbi->raw_super_buf);
+ if (sbi->s_chksum_driver)
+ crypto_free_shash(sbi->s_chksum_driver);
+ kfree(sbi->raw_super);
+
+ destroy_device_list(sbi);
+ if (sbi->write_io_dummy)
+ mempool_destroy(sbi->write_io_dummy);
+ destroy_percpu_info(sbi);
kfree(sbi);
}
int f2fs_sync_fs(struct super_block *sb, int sync)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ int err = 0;
trace_f2fs_sync_fs(sb, sync);
if (sync) {
- struct cp_control cpc = {
- .reason = CP_SYNC,
- };
- mutex_lock(&sbi->gc_mutex);
- write_checkpoint(sbi, &cpc);
- mutex_unlock(&sbi->gc_mutex);
- } else {
- f2fs_balance_fs(sbi);
- }
+ struct cp_control cpc;
- return 0;
+ cpc.reason = __get_cp_reason(sbi);
+
+ mutex_lock(&sbi->gc_mutex);
+ err = write_checkpoint(sbi, &cpc);
+ mutex_unlock(&sbi->gc_mutex);
+ }
+ f2fs_trace_ios(NULL, 1);
+
+ return err;
}
static int f2fs_freeze(struct super_block *sb)
{
- int err;
-
if (f2fs_readonly(sb))
return 0;
- err = f2fs_sync_fs(sb, 1);
- return err;
+ /* IO error happened before */
+ if (unlikely(f2fs_cp_error(F2FS_SB(sb))))
+ return -EIO;
+
+ /* must be clean, since sync_filesystem() was already called */
+ if (is_sbi_flag_set(F2FS_SB(sb), SBI_IS_DIRTY))
+ return -EINVAL;
+ return 0;
}
static int f2fs_unfreeze(struct super_block *sb)
@@ -517,11 +885,12 @@
buf->f_bsize = sbi->blocksize;
buf->f_blocks = total_count - start_count;
- buf->f_bfree = buf->f_blocks - valid_user_blocks(sbi) - ovp_count;
+ buf->f_bfree = user_block_count - valid_user_blocks(sbi) + ovp_count;
buf->f_bavail = user_block_count - valid_user_blocks(sbi);
buf->f_files = sbi->total_node_count - F2FS_RESERVED_NODE_NUM;
- buf->f_ffree = buf->f_files - valid_inode_count(sbi);
+ buf->f_ffree = min(buf->f_files - valid_node_count(sbi),
+ buf->f_bavail);
buf->f_namelen = F2FS_NAME_LEN;
buf->f_fsid.val[0] = (u32)id;
@@ -534,16 +903,22 @@
{
struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb);
- if (!f2fs_readonly(sbi->sb) && test_opt(sbi, BG_GC))
- seq_printf(seq, ",background_gc=%s", "on");
- else
+ if (!f2fs_readonly(sbi->sb) && test_opt(sbi, BG_GC)) {
+ if (test_opt(sbi, FORCE_FG_GC))
+ seq_printf(seq, ",background_gc=%s", "sync");
+ else
+ seq_printf(seq, ",background_gc=%s", "on");
+ } else {
seq_printf(seq, ",background_gc=%s", "off");
+ }
if (test_opt(sbi, DISABLE_ROLL_FORWARD))
seq_puts(seq, ",disable_roll_forward");
if (test_opt(sbi, DISCARD))
seq_puts(seq, ",discard");
if (test_opt(sbi, NOHEAP))
- seq_puts(seq, ",no_heap_alloc");
+ seq_puts(seq, ",no_heap");
+ else
+ seq_puts(seq, ",heap");
#ifdef CONFIG_F2FS_FS_XATTR
if (test_opt(sbi, XATTR_USER))
seq_puts(seq, ",user_xattr");
@@ -551,6 +926,8 @@
seq_puts(seq, ",nouser_xattr");
if (test_opt(sbi, INLINE_XATTR))
seq_puts(seq, ",inline_xattr");
+ else
+ seq_puts(seq, ",noinline_xattr");
#endif
#ifdef CONFIG_F2FS_FS_POSIX_ACL
if (test_opt(sbi, POSIX_ACL))
@@ -562,11 +939,37 @@
seq_puts(seq, ",disable_ext_identify");
if (test_opt(sbi, INLINE_DATA))
seq_puts(seq, ",inline_data");
+ else
+ seq_puts(seq, ",noinline_data");
+ if (test_opt(sbi, INLINE_DENTRY))
+ seq_puts(seq, ",inline_dentry");
+ else
+ seq_puts(seq, ",noinline_dentry");
if (!f2fs_readonly(sbi->sb) && test_opt(sbi, FLUSH_MERGE))
seq_puts(seq, ",flush_merge");
if (test_opt(sbi, NOBARRIER))
seq_puts(seq, ",nobarrier");
+ if (test_opt(sbi, FASTBOOT))
+ seq_puts(seq, ",fastboot");
+ if (test_opt(sbi, EXTENT_CACHE))
+ seq_puts(seq, ",extent_cache");
+ else
+ seq_puts(seq, ",noextent_cache");
+ if (test_opt(sbi, DATA_FLUSH))
+ seq_puts(seq, ",data_flush");
+
+ seq_puts(seq, ",mode=");
+ if (test_opt(sbi, ADAPTIVE))
+ seq_puts(seq, "adaptive");
+ else if (test_opt(sbi, LFS))
+ seq_puts(seq, "lfs");
seq_printf(seq, ",active_logs=%u", sbi->active_logs);
+ if (F2FS_IO_SIZE_BITS(sbi))
+ seq_printf(seq, ",io_size=%uKB", F2FS_IO_SIZE_KB(sbi));
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ if (test_opt(sbi, FAULT_INJECTION))
+ seq_puts(seq, ",fault_injection");
+#endif
return 0;
}
@@ -586,9 +989,9 @@
struct seg_entry *se = get_seg_entry(sbi, i);
if ((i % 10) == 0)
- seq_printf(seq, "%-5d", i);
+ seq_printf(seq, "%-10d", i);
seq_printf(seq, "%d|%-3u", se->type,
- get_valid_blocks(sbi, i, 1));
+ get_valid_blocks(sbi, i, false));
if ((i % 10) == 9 || i == (total_segs - 1))
seq_putc(seq, '\n');
else
@@ -598,19 +1001,78 @@
return 0;
}
-static int segment_info_open_fs(struct inode *inode, struct file *file)
+static int segment_bits_seq_show(struct seq_file *seq, void *offset)
{
- return single_open(file, segment_info_seq_show, PDE_DATA(inode));
+ struct super_block *sb = seq->private;
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ unsigned int total_segs =
+ le32_to_cpu(sbi->raw_super->segment_count_main);
+ int i, j;
+
+ seq_puts(seq, "format: segment_type|valid_blocks|bitmaps\n"
+ "segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n");
+
+ for (i = 0; i < total_segs; i++) {
+ struct seg_entry *se = get_seg_entry(sbi, i);
+
+ seq_printf(seq, "%-10d", i);
+ seq_printf(seq, "%d|%-3u|", se->type,
+ get_valid_blocks(sbi, i, false));
+ for (j = 0; j < SIT_VBLOCK_MAP_SIZE; j++)
+ seq_printf(seq, " %.2x", se->cur_valid_map[j]);
+ seq_putc(seq, '\n');
+ }
+ return 0;
}
-static const struct file_operations f2fs_seq_segment_info_fops = {
- .owner = THIS_MODULE,
- .open = segment_info_open_fs,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
+#define F2FS_PROC_FILE_DEF(_name) \
+static int _name##_open_fs(struct inode *inode, struct file *file) \
+{ \
+ return single_open(file, _name##_seq_show, PDE_DATA(inode)); \
+} \
+ \
+static const struct file_operations f2fs_seq_##_name##_fops = { \
+ .owner = THIS_MODULE, \
+ .open = _name##_open_fs, \
+ .read = seq_read, \
+ .llseek = seq_lseek, \
+ .release = single_release, \
};
+F2FS_PROC_FILE_DEF(segment_info);
+F2FS_PROC_FILE_DEF(segment_bits);
+
+static void default_options(struct f2fs_sb_info *sbi)
+{
+ /* init some FS parameters */
+ sbi->active_logs = NR_CURSEG_TYPE;
+
+ set_opt(sbi, BG_GC);
+ set_opt(sbi, INLINE_XATTR);
+ set_opt(sbi, INLINE_DATA);
+ set_opt(sbi, INLINE_DENTRY);
+ set_opt(sbi, EXTENT_CACHE);
+ set_opt(sbi, NOHEAP);
+ set_opt(sbi, FLUSH_MERGE);
+ if (f2fs_sb_mounted_blkzoned(sbi->sb)) {
+ set_opt_mode(sbi, F2FS_MOUNT_LFS);
+ set_opt(sbi, DISCARD);
+ } else {
+ set_opt_mode(sbi, F2FS_MOUNT_ADAPTIVE);
+ }
+
+#ifdef CONFIG_F2FS_FS_XATTR
+ set_opt(sbi, XATTR_USER);
+#endif
+#ifdef CONFIG_F2FS_FS_POSIX_ACL
+ set_opt(sbi, POSIX_ACL);
+#endif
+
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ f2fs_build_fault_attr(sbi, 0);
+#endif
+}
+
static int f2fs_remount(struct super_block *sb, int *flags, char *data)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
@@ -618,8 +1080,10 @@
int err, active_logs;
bool need_restart_gc = false;
bool need_stop_gc = false;
-
- sync_filesystem(sb);
+ bool no_extent_cache = !test_opt(sbi, EXTENT_CACHE);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ struct f2fs_fault_info ffi = sbi->fault_info;
+#endif
/*
* Save the old mount options in case we
@@ -628,8 +1092,17 @@
org_mount_opt = sbi->mount_opt;
active_logs = sbi->active_logs;
+ /* recover superblocks we couldn't write due to previous RO mount */
+ if (!(*flags & MS_RDONLY) && is_sbi_flag_set(sbi, SBI_NEED_SB_WRITE)) {
+ err = f2fs_commit_super(sbi, false);
+ f2fs_msg(sb, KERN_INFO,
+ "Try to recover all the superblocks, ret: %d", err);
+ if (!err)
+ clear_sbi_flag(sbi, SBI_NEED_SB_WRITE);
+ }
+
sbi->mount_opt.opt = 0;
- sbi->active_logs = NR_CURSEG_TYPE;
+ default_options(sbi);
/* parse mount options */
err = parse_options(sb, data);
@@ -643,6 +1116,14 @@
if (f2fs_readonly(sb) && (*flags & MS_RDONLY))
goto skip;
+ /* disallow enable/disable extent_cache dynamically */
+ if (no_extent_cache == !!test_opt(sbi, EXTENT_CACHE)) {
+ err = -EINVAL;
+ f2fs_msg(sbi->sb, KERN_WARNING,
+ "switch extent_cache option is not allowed");
+ goto restore_opts;
+ }
+
/*
* We stop the GC thread if FS is mounted as RO
* or if background_gc = off is passed in mount
@@ -651,31 +1132,42 @@
if ((*flags & MS_RDONLY) || !test_opt(sbi, BG_GC)) {
if (sbi->gc_thread) {
stop_gc_thread(sbi);
- f2fs_sync_fs(sb, 1);
need_restart_gc = true;
}
- } else if (test_opt(sbi, BG_GC) && !sbi->gc_thread) {
+ } else if (!sbi->gc_thread) {
err = start_gc_thread(sbi);
if (err)
goto restore_opts;
need_stop_gc = true;
}
+ if (*flags & MS_RDONLY) {
+ writeback_inodes_sb(sb, WB_REASON_SYNC);
+ sync_inodes_sb(sb);
+
+ set_sbi_flag(sbi, SBI_IS_DIRTY);
+ set_sbi_flag(sbi, SBI_IS_CLOSE);
+ f2fs_sync_fs(sb, 1);
+ clear_sbi_flag(sbi, SBI_IS_CLOSE);
+ }
+
/*
* We stop issue flush thread if FS is mounted as RO
* or if flush_merge is not passed in mount option.
*/
if ((*flags & MS_RDONLY) || !test_opt(sbi, FLUSH_MERGE)) {
- destroy_flush_cmd_control(sbi);
- } else if (test_opt(sbi, FLUSH_MERGE) && !SM_I(sbi)->cmd_control_info) {
+ clear_opt(sbi, FLUSH_MERGE);
+ destroy_flush_cmd_control(sbi, false);
+ } else {
err = create_flush_cmd_control(sbi);
if (err)
goto restore_gc;
}
skip:
/* Update the POSIXACL Flag */
- sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
+ sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
+
return 0;
restore_gc:
if (need_restart_gc) {
@@ -688,6 +1180,9 @@
restore_opts:
sbi->mount_opt = org_mount_opt;
sbi->active_logs = active_logs;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+ sbi->fault_info = ffi;
+#endif
return err;
}
@@ -707,6 +1202,42 @@
.remount_fs = f2fs_remount,
};
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+static int f2fs_get_context(struct inode *inode, void *ctx, size_t len)
+{
+ return f2fs_getxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
+ F2FS_XATTR_NAME_ENCRYPTION_CONTEXT,
+ ctx, len, NULL);
+}
+
+static int f2fs_set_context(struct inode *inode, const void *ctx, size_t len,
+ void *fs_data)
+{
+ return f2fs_setxattr(inode, F2FS_XATTR_INDEX_ENCRYPTION,
+ F2FS_XATTR_NAME_ENCRYPTION_CONTEXT,
+ ctx, len, fs_data, XATTR_CREATE);
+}
+
+static unsigned f2fs_max_namelen(struct inode *inode)
+{
+ return S_ISLNK(inode->i_mode) ?
+ inode->i_sb->s_blocksize : F2FS_NAME_LEN;
+}
+
+static const struct fscrypt_operations f2fs_cryptops = {
+ .key_prefix = "f2fs:",
+ .get_context = f2fs_get_context,
+ .set_context = f2fs_set_context,
+ .is_encrypted = f2fs_encrypted_inode,
+ .empty_dir = f2fs_empty_dir,
+ .max_namelen = f2fs_max_namelen,
+};
+#else
+static const struct fscrypt_operations f2fs_cryptops = {
+ .is_encrypted = f2fs_encrypted_inode,
+};
+#endif
+
static struct inode *f2fs_nfs_get_inode(struct super_block *sb,
u64 ino, u32 generation)
{
@@ -752,7 +1283,7 @@
.get_parent = f2fs_get_parent,
};
-static loff_t max_file_size(unsigned bits)
+static loff_t max_file_blocks(void)
{
loff_t result = (DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS);
loff_t leaf_count = ADDRS_PER_BLOCK;
@@ -768,13 +1299,131 @@
leaf_count *= NIDS_PER_BLOCK;
result += leaf_count;
- result <<= bits;
return result;
}
-static int sanity_check_raw_super(struct super_block *sb,
- struct f2fs_super_block *raw_super)
+static int __f2fs_commit_super(struct buffer_head *bh,
+ struct f2fs_super_block *super)
{
+ lock_buffer(bh);
+ if (super)
+ memcpy(bh->b_data + F2FS_SUPER_OFFSET, super, sizeof(*super));
+ set_buffer_uptodate(bh);
+ set_buffer_dirty(bh);
+ unlock_buffer(bh);
+
+ /* it's rare case, we can do fua all the time */
+ return __sync_dirty_buffer(bh, WRITE_FLUSH_FUA);
+}
+
+static inline bool sanity_check_area_boundary(struct f2fs_sb_info *sbi,
+ struct buffer_head *bh)
+{
+ struct f2fs_super_block *raw_super = (struct f2fs_super_block *)
+ (bh->b_data + F2FS_SUPER_OFFSET);
+ struct super_block *sb = sbi->sb;
+ u32 segment0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr);
+ u32 cp_blkaddr = le32_to_cpu(raw_super->cp_blkaddr);
+ u32 sit_blkaddr = le32_to_cpu(raw_super->sit_blkaddr);
+ u32 nat_blkaddr = le32_to_cpu(raw_super->nat_blkaddr);
+ u32 ssa_blkaddr = le32_to_cpu(raw_super->ssa_blkaddr);
+ u32 main_blkaddr = le32_to_cpu(raw_super->main_blkaddr);
+ u32 segment_count_ckpt = le32_to_cpu(raw_super->segment_count_ckpt);
+ u32 segment_count_sit = le32_to_cpu(raw_super->segment_count_sit);
+ u32 segment_count_nat = le32_to_cpu(raw_super->segment_count_nat);
+ u32 segment_count_ssa = le32_to_cpu(raw_super->segment_count_ssa);
+ u32 segment_count_main = le32_to_cpu(raw_super->segment_count_main);
+ u32 segment_count = le32_to_cpu(raw_super->segment_count);
+ u32 log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);
+ u64 main_end_blkaddr = main_blkaddr +
+ (segment_count_main << log_blocks_per_seg);
+ u64 seg_end_blkaddr = segment0_blkaddr +
+ (segment_count << log_blocks_per_seg);
+
+ if (segment0_blkaddr != cp_blkaddr) {
+ f2fs_msg(sb, KERN_INFO,
+ "Mismatch start address, segment0(%u) cp_blkaddr(%u)",
+ segment0_blkaddr, cp_blkaddr);
+ return true;
+ }
+
+ if (cp_blkaddr + (segment_count_ckpt << log_blocks_per_seg) !=
+ sit_blkaddr) {
+ f2fs_msg(sb, KERN_INFO,
+ "Wrong CP boundary, start(%u) end(%u) blocks(%u)",
+ cp_blkaddr, sit_blkaddr,
+ segment_count_ckpt << log_blocks_per_seg);
+ return true;
+ }
+
+ if (sit_blkaddr + (segment_count_sit << log_blocks_per_seg) !=
+ nat_blkaddr) {
+ f2fs_msg(sb, KERN_INFO,
+ "Wrong SIT boundary, start(%u) end(%u) blocks(%u)",
+ sit_blkaddr, nat_blkaddr,
+ segment_count_sit << log_blocks_per_seg);
+ return true;
+ }
+
+ if (nat_blkaddr + (segment_count_nat << log_blocks_per_seg) !=
+ ssa_blkaddr) {
+ f2fs_msg(sb, KERN_INFO,
+ "Wrong NAT boundary, start(%u) end(%u) blocks(%u)",
+ nat_blkaddr, ssa_blkaddr,
+ segment_count_nat << log_blocks_per_seg);
+ return true;
+ }
+
+ if (ssa_blkaddr + (segment_count_ssa << log_blocks_per_seg) !=
+ main_blkaddr) {
+ f2fs_msg(sb, KERN_INFO,
+ "Wrong SSA boundary, start(%u) end(%u) blocks(%u)",
+ ssa_blkaddr, main_blkaddr,
+ segment_count_ssa << log_blocks_per_seg);
+ return true;
+ }
+
+ if (main_end_blkaddr > seg_end_blkaddr) {
+ f2fs_msg(sb, KERN_INFO,
+ "Wrong MAIN_AREA boundary, start(%u) end(%u) block(%u)",
+ main_blkaddr,
+ segment0_blkaddr +
+ (segment_count << log_blocks_per_seg),
+ segment_count_main << log_blocks_per_seg);
+ return true;
+ } else if (main_end_blkaddr < seg_end_blkaddr) {
+ int err = 0;
+ char *res;
+
+ /* fix in-memory information all the time */
+ raw_super->segment_count = cpu_to_le32((main_end_blkaddr -
+ segment0_blkaddr) >> log_blocks_per_seg);
+
+ if (f2fs_readonly(sb) || bdev_read_only(sb->s_bdev)) {
+ set_sbi_flag(sbi, SBI_NEED_SB_WRITE);
+ res = "internally";
+ } else {
+ err = __f2fs_commit_super(bh, NULL);
+ res = err ? "failed" : "done";
+ }
+ f2fs_msg(sb, KERN_INFO,
+ "Fix alignment : %s, start(%u) end(%u) block(%u)",
+ res, main_blkaddr,
+ segment0_blkaddr +
+ (segment_count << log_blocks_per_seg),
+ segment_count_main << log_blocks_per_seg);
+ if (err)
+ return true;
+ }
+ return false;
+}
+
+static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
+ struct buffer_head *bh)
+{
+ struct f2fs_super_block *raw_super = (struct f2fs_super_block *)
+ (bh->b_data + F2FS_SUPER_OFFSET);
+ struct super_block *sb = sbi->sb;
unsigned int blocksize;
if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) {
@@ -785,10 +1434,10 @@
}
/* Currently, support only 4KB page cache size */
- if (F2FS_BLKSIZE != PAGE_CACHE_SIZE) {
+ if (F2FS_BLKSIZE != PAGE_SIZE) {
f2fs_msg(sb, KERN_INFO,
"Invalid page_cache_size (%lu), supports only 4KB\n",
- PAGE_CACHE_SIZE);
+ PAGE_SIZE);
return 1;
}
@@ -827,15 +1476,20 @@
return 1;
}
+ /* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */
+ if (sanity_check_area_boundary(sbi, bh))
+ return 1;
+
return 0;
}
-static int sanity_check_ckpt(struct f2fs_sb_info *sbi)
+int sanity_check_ckpt(struct f2fs_sb_info *sbi)
{
unsigned int total, fsmeta;
struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
unsigned int main_segs, blocks_per_seg;
+ unsigned int ovp_segments, reserved_segments;
int i;
total = le32_to_cpu(raw_super->segment_count);
@@ -862,6 +1516,16 @@
return 1;
}
+ ovp_segments = le32_to_cpu(ckpt->overprov_segment_count);
+ reserved_segments = le32_to_cpu(ckpt->rsvd_segment_count);
+
+ if (unlikely(fsmeta < F2FS_MIN_SEGMENTS ||
+ ovp_segments == 0 || reserved_segments == 0)) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "Wrong layout: check mkfs.f2fs version");
+ return 1;
+ }
+
if (unlikely(f2fs_cp_error(sbi))) {
f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck");
return 1;
@@ -892,54 +1556,287 @@
sbi->cur_victim_sec = NULL_SECNO;
sbi->max_victim_search = DEF_MAX_VICTIM_SEARCH;
+ sbi->dir_level = DEF_DIR_LEVEL;
+ sbi->interval_time[CP_TIME] = DEF_CP_INTERVAL;
+ sbi->interval_time[REQ_TIME] = DEF_IDLE_INTERVAL;
+ clear_sbi_flag(sbi, SBI_NEED_FSCK);
+
for (i = 0; i < NR_COUNT_TYPE; i++)
atomic_set(&sbi->nr_pages[i], 0);
- sbi->dir_level = DEF_DIR_LEVEL;
- sbi->need_fsck = false;
+ atomic_set(&sbi->wb_sync_req, 0);
+
+ INIT_LIST_HEAD(&sbi->s_list);
+ mutex_init(&sbi->umount_mutex);
+ mutex_init(&sbi->wio_mutex[NODE]);
+ mutex_init(&sbi->wio_mutex[DATA]);
+ spin_lock_init(&sbi->cp_lock);
}
+static int init_percpu_info(struct f2fs_sb_info *sbi)
+{
+ int err;
+
+ err = percpu_counter_init(&sbi->alloc_valid_block_count, 0, GFP_KERNEL);
+ if (err)
+ return err;
+
+ return percpu_counter_init(&sbi->total_valid_inode_count, 0,
+ GFP_KERNEL);
+}
+
+#ifdef CONFIG_BLK_DEV_ZONED
+static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
+{
+ struct block_device *bdev = FDEV(devi).bdev;
+ sector_t nr_sectors = bdev->bd_part->nr_sects;
+ sector_t sector = 0;
+ struct blk_zone *zones;
+ unsigned int i, nr_zones;
+ unsigned int n = 0;
+ int err = -EIO;
+
+ if (!f2fs_sb_mounted_blkzoned(sbi->sb))
+ return 0;
+
+ if (sbi->blocks_per_blkz && sbi->blocks_per_blkz !=
+ SECTOR_TO_BLOCK(bdev_zone_size(bdev)))
+ return -EINVAL;
+ sbi->blocks_per_blkz = SECTOR_TO_BLOCK(bdev_zone_size(bdev));
+ if (sbi->log_blocks_per_blkz && sbi->log_blocks_per_blkz !=
+ __ilog2_u32(sbi->blocks_per_blkz))
+ return -EINVAL;
+ sbi->log_blocks_per_blkz = __ilog2_u32(sbi->blocks_per_blkz);
+ FDEV(devi).nr_blkz = SECTOR_TO_BLOCK(nr_sectors) >>
+ sbi->log_blocks_per_blkz;
+ if (nr_sectors & (bdev_zone_size(bdev) - 1))
+ FDEV(devi).nr_blkz++;
+
+ FDEV(devi).blkz_type = kmalloc(FDEV(devi).nr_blkz, GFP_KERNEL);
+ if (!FDEV(devi).blkz_type)
+ return -ENOMEM;
+
+#define F2FS_REPORT_NR_ZONES 4096
+
+ zones = kcalloc(F2FS_REPORT_NR_ZONES, sizeof(struct blk_zone),
+ GFP_KERNEL);
+ if (!zones)
+ return -ENOMEM;
+
+ /* Get block zones type */
+ while (zones && sector < nr_sectors) {
+
+ nr_zones = F2FS_REPORT_NR_ZONES;
+ err = blkdev_report_zones(bdev, sector,
+ zones, &nr_zones,
+ GFP_KERNEL);
+ if (err)
+ break;
+ if (!nr_zones) {
+ err = -EIO;
+ break;
+ }
+
+ for (i = 0; i < nr_zones; i++) {
+ FDEV(devi).blkz_type[n] = zones[i].type;
+ sector += zones[i].len;
+ n++;
+ }
+ }
+
+ kfree(zones);
+
+ return err;
+}
+#endif
+
/*
* Read f2fs raw super block.
- * Because we have two copies of super block, so read the first one at first,
- * if the first one is invalid, move to read the second one.
+ * Because we have two copies of super block, so read both of them
+ * to get the first valid one. If any one of them is broken, we pass
+ * them recovery flag back to the caller.
*/
-static int read_raw_super_block(struct super_block *sb,
+static int read_raw_super_block(struct f2fs_sb_info *sbi,
struct f2fs_super_block **raw_super,
- struct buffer_head **raw_super_buf)
+ int *valid_super_block, int *recovery)
{
- int block = 0;
+ struct super_block *sb = sbi->sb;
+ int block;
+ struct buffer_head *bh;
+ struct f2fs_super_block *super;
+ int err = 0;
-retry:
- *raw_super_buf = sb_bread(sb, block);
- if (!*raw_super_buf) {
- f2fs_msg(sb, KERN_ERR, "Unable to read %dth superblock",
+ super = kzalloc(sizeof(struct f2fs_super_block), GFP_KERNEL);
+ if (!super)
+ return -ENOMEM;
+
+ for (block = 0; block < 2; block++) {
+ bh = sb_bread(sb, block);
+ if (!bh) {
+ f2fs_msg(sb, KERN_ERR, "Unable to read %dth superblock",
block + 1);
- if (block == 0) {
- block++;
- goto retry;
- } else {
- return -EIO;
+ err = -EIO;
+ continue;
}
+
+ /* sanity checking of raw super */
+ if (sanity_check_raw_super(sbi, bh)) {
+ f2fs_msg(sb, KERN_ERR,
+ "Can't find valid F2FS filesystem in %dth superblock",
+ block + 1);
+ err = -EINVAL;
+ brelse(bh);
+ continue;
+ }
+
+ if (!*raw_super) {
+ memcpy(super, bh->b_data + F2FS_SUPER_OFFSET,
+ sizeof(*super));
+ *valid_super_block = block;
+ *raw_super = super;
+ }
+ brelse(bh);
}
- *raw_super = (struct f2fs_super_block *)
- ((char *)(*raw_super_buf)->b_data + F2FS_SUPER_OFFSET);
+ /* Fail to read any one of the superblocks*/
+ if (err < 0)
+ *recovery = 1;
- /* sanity checking of raw super */
- if (sanity_check_raw_super(sb, *raw_super)) {
- brelse(*raw_super_buf);
- f2fs_msg(sb, KERN_ERR,
- "Can't find valid F2FS filesystem in %dth superblock",
- block + 1);
- if (block == 0) {
- block++;
- goto retry;
+ /* No valid superblock */
+ if (!*raw_super)
+ kfree(super);
+ else
+ err = 0;
+
+ return err;
+}
+
+int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
+{
+ struct buffer_head *bh;
+ int err;
+
+ if ((recover && f2fs_readonly(sbi->sb)) ||
+ bdev_read_only(sbi->sb->s_bdev)) {
+ set_sbi_flag(sbi, SBI_NEED_SB_WRITE);
+ return -EROFS;
+ }
+
+ /* write back-up superblock first */
+ bh = sb_getblk(sbi->sb, sbi->valid_super_block ? 0: 1);
+ if (!bh)
+ return -EIO;
+ err = __f2fs_commit_super(bh, F2FS_RAW_SUPER(sbi));
+ brelse(bh);
+
+ /* if we are in recovery path, skip writing valid superblock */
+ if (recover || err)
+ return err;
+
+ /* write current valid superblock */
+ bh = sb_getblk(sbi->sb, sbi->valid_super_block);
+ if (!bh)
+ return -EIO;
+ err = __f2fs_commit_super(bh, F2FS_RAW_SUPER(sbi));
+ brelse(bh);
+ return err;
+}
+
+static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
+{
+ struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
+ unsigned int max_devices = MAX_DEVICES;
+ int i;
+
+ /* Initialize single device information */
+ if (!RDEV(0).path[0]) {
+#ifdef CONFIG_BLK_DEV_ZONED
+ if (bdev_zoned_model(sbi->sb->s_bdev) == BLK_ZONED_NONE)
+ return 0;
+ max_devices = 1;
+#else
+ return 0;
+#endif
+ }
+
+ /*
+ * Initialize multiple devices information, or single
+ * zoned block device information.
+ */
+ sbi->devs = kcalloc(max_devices, sizeof(struct f2fs_dev_info),
+ GFP_KERNEL);
+ if (!sbi->devs)
+ return -ENOMEM;
+
+ for (i = 0; i < max_devices; i++) {
+
+ if (i > 0 && !RDEV(i).path[0])
+ break;
+
+ if (max_devices == 1) {
+ /* Single zoned block device mount */
+ FDEV(0).bdev =
+ blkdev_get_by_dev(sbi->sb->s_bdev->bd_dev,
+ sbi->sb->s_mode, sbi->sb->s_type);
} else {
+ /* Multi-device mount */
+ memcpy(FDEV(i).path, RDEV(i).path, MAX_PATH_LEN);
+ FDEV(i).total_segments =
+ le32_to_cpu(RDEV(i).total_segments);
+ if (i == 0) {
+ FDEV(i).start_blk = 0;
+ FDEV(i).end_blk = FDEV(i).start_blk +
+ (FDEV(i).total_segments <<
+ sbi->log_blocks_per_seg) - 1 +
+ le32_to_cpu(raw_super->segment0_blkaddr);
+ } else {
+ FDEV(i).start_blk = FDEV(i - 1).end_blk + 1;
+ FDEV(i).end_blk = FDEV(i).start_blk +
+ (FDEV(i).total_segments <<
+ sbi->log_blocks_per_seg) - 1;
+ }
+ FDEV(i).bdev = blkdev_get_by_path(FDEV(i).path,
+ sbi->sb->s_mode, sbi->sb->s_type);
+ }
+ if (IS_ERR(FDEV(i).bdev))
+ return PTR_ERR(FDEV(i).bdev);
+
+ /* to release errored devices */
+ sbi->s_ndevs = i + 1;
+
+#ifdef CONFIG_BLK_DEV_ZONED
+ if (bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HM &&
+ !f2fs_sb_mounted_blkzoned(sbi->sb)) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "Zoned block device feature not enabled\n");
return -EINVAL;
}
+ if (bdev_zoned_model(FDEV(i).bdev) != BLK_ZONED_NONE) {
+ if (init_blkz_info(sbi, i)) {
+ f2fs_msg(sbi->sb, KERN_ERR,
+ "Failed to initialize F2FS blkzone information");
+ return -EINVAL;
+ }
+ if (max_devices == 1)
+ break;
+ f2fs_msg(sbi->sb, KERN_INFO,
+ "Mount Device [%2d]: %20s, %8u, %8x - %8x (zone: %s)",
+ i, FDEV(i).path,
+ FDEV(i).total_segments,
+ FDEV(i).start_blk, FDEV(i).end_blk,
+ bdev_zoned_model(FDEV(i).bdev) == BLK_ZONED_HA ?
+ "Host-aware" : "Host-managed");
+ continue;
+ }
+#endif
+ f2fs_msg(sbi->sb, KERN_INFO,
+ "Mount Device [%2d]: %20s, %8u, %8x - %8x",
+ i, FDEV(i).path,
+ FDEV(i).total_segments,
+ FDEV(i).start_blk, FDEV(i).end_blk);
}
-
+ f2fs_msg(sbi->sb, KERN_INFO,
+ "IO Block Size: %8d KB", F2FS_IO_SIZE_KB(sbi));
return 0;
}
@@ -947,50 +1844,81 @@
{
struct f2fs_sb_info *sbi;
struct f2fs_super_block *raw_super;
- struct buffer_head *raw_super_buf;
struct inode *root;
- long err = -EINVAL;
- bool retry = true;
- int i;
+ int err;
+ bool retry = true, need_fsck = false;
+ char *options = NULL;
+ int recovery, i, valid_super_block;
+ struct curseg_info *seg_i;
try_onemore:
+ err = -EINVAL;
+ raw_super = NULL;
+ valid_super_block = -1;
+ recovery = 0;
+
/* allocate memory for f2fs-specific super block info */
sbi = kzalloc(sizeof(struct f2fs_sb_info), GFP_KERNEL);
if (!sbi)
return -ENOMEM;
+ sbi->sb = sb;
+
+ /* Load the checksum driver */
+ sbi->s_chksum_driver = crypto_alloc_shash("crc32", 0, 0);
+ if (IS_ERR(sbi->s_chksum_driver)) {
+ f2fs_msg(sb, KERN_ERR, "Cannot load crc32 driver.");
+ err = PTR_ERR(sbi->s_chksum_driver);
+ sbi->s_chksum_driver = NULL;
+ goto free_sbi;
+ }
+
/* set a block size */
if (unlikely(!sb_set_blocksize(sb, F2FS_BLKSIZE))) {
f2fs_msg(sb, KERN_ERR, "unable to set blocksize");
goto free_sbi;
}
- err = read_raw_super_block(sb, &raw_super, &raw_super_buf);
+ err = read_raw_super_block(sbi, &raw_super, &valid_super_block,
+ &recovery);
if (err)
goto free_sbi;
sb->s_fs_info = sbi;
- /* init some FS parameters */
- sbi->active_logs = NR_CURSEG_TYPE;
+ sbi->raw_super = raw_super;
- set_opt(sbi, BG_GC);
-
-#ifdef CONFIG_F2FS_FS_XATTR
- set_opt(sbi, XATTR_USER);
-#endif
-#ifdef CONFIG_F2FS_FS_POSIX_ACL
- set_opt(sbi, POSIX_ACL);
-#endif
- /* parse mount options */
- err = parse_options(sb, (char *)data);
- if (err)
+ /*
+ * The BLKZONED feature indicates that the drive was formatted with
+ * zone alignment optimization. This is optional for host-aware
+ * devices, but mandatory for host-managed zoned block devices.
+ */
+#ifndef CONFIG_BLK_DEV_ZONED
+ if (f2fs_sb_mounted_blkzoned(sb)) {
+ f2fs_msg(sb, KERN_ERR,
+ "Zoned block device support is not enabled\n");
goto free_sb_buf;
+ }
+#endif
+ default_options(sbi);
+ /* parse mount options */
+ options = kstrdup((const char *)data, GFP_KERNEL);
+ if (data && !options) {
+ err = -ENOMEM;
+ goto free_sb_buf;
+ }
- sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize));
+ err = parse_options(sb, options);
+ if (err)
+ goto free_options;
+
+ sbi->max_file_blocks = max_file_blocks();
+ sb->s_maxbytes = sbi->max_file_blocks <<
+ le32_to_cpu(raw_super->log_blocksize);
sb->s_max_links = F2FS_LINK_MAX;
get_random_bytes(&sbi->s_next_generation, sizeof(u32));
sb->s_op = &f2fs_sops;
+ sb->s_cop = &f2fs_cryptops;
sb->s_xattr = f2fs_xattr_handlers;
sb->s_export_op = &f2fs_export_ops;
sb->s_magic = F2FS_SUPER_MAGIC;
@@ -1000,14 +1928,14 @@
memcpy(sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));
/* init f2fs-specific super block info */
- sbi->sb = sb;
- sbi->raw_super = raw_super;
- sbi->raw_super_buf = raw_super_buf;
+ sbi->valid_super_block = valid_super_block;
mutex_init(&sbi->gc_mutex);
- mutex_init(&sbi->writepages);
mutex_init(&sbi->cp_mutex);
init_rwsem(&sbi->node_write);
- sbi->por_doing = false;
+ init_rwsem(&sbi->node_change);
+
+ /* disallow all the data/node/meta page writes */
+ set_sbi_flag(sbi, SBI_POR_DOING);
spin_lock_init(&sbi->stat_lock);
init_rwsem(&sbi->read_io.io_rwsem);
@@ -1023,12 +1951,23 @@
init_waitqueue_head(&sbi->cp_wait);
init_sb_info(sbi);
+ err = init_percpu_info(sbi);
+ if (err)
+ goto free_options;
+
+ if (F2FS_IO_SIZE(sbi) > 1) {
+ sbi->write_io_dummy =
+ mempool_create_page_pool(2 * (F2FS_IO_SIZE(sbi) - 1), 0);
+ if (!sbi->write_io_dummy)
+ goto free_options;
+ }
+
/* get an inode for meta space */
sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi));
if (IS_ERR(sbi->meta_inode)) {
f2fs_msg(sb, KERN_ERR, "Failed to read F2FS meta data inode");
err = PTR_ERR(sbi->meta_inode);
- goto free_sb_buf;
+ goto free_io_dummy;
}
err = get_valid_checkpoint(sbi);
@@ -1037,24 +1976,28 @@
goto free_meta_inode;
}
- /* sanity checking of checkpoint */
- err = -EINVAL;
- if (sanity_check_ckpt(sbi)) {
- f2fs_msg(sb, KERN_ERR, "Invalid F2FS checkpoint");
- goto free_cp;
+ /* Initialize device list */
+ err = f2fs_scan_devices(sbi);
+ if (err) {
+ f2fs_msg(sb, KERN_ERR, "Failed to find devices");
+ goto free_devices;
}
sbi->total_valid_node_count =
le32_to_cpu(sbi->ckpt->valid_node_count);
- sbi->total_valid_inode_count =
- le32_to_cpu(sbi->ckpt->valid_inode_count);
+ percpu_counter_set(&sbi->total_valid_inode_count,
+ le32_to_cpu(sbi->ckpt->valid_inode_count));
sbi->user_block_count = le64_to_cpu(sbi->ckpt->user_block_count);
sbi->total_valid_block_count =
le64_to_cpu(sbi->ckpt->valid_block_count);
sbi->last_valid_block_count = sbi->total_valid_block_count;
- sbi->alloc_valid_block_count = 0;
- INIT_LIST_HEAD(&sbi->dir_inode_list);
- spin_lock_init(&sbi->dir_inode_lock);
+
+ for (i = 0; i < NR_INODE_TYPE; i++) {
+ INIT_LIST_HEAD(&sbi->inode_list[i]);
+ spin_lock_init(&sbi->inode_lock[i]);
+ }
+
+ init_extent_cache_info(sbi);
init_ino_entry_info(sbi);
@@ -1072,6 +2015,17 @@
goto free_nm;
}
+ /* For write statistics */
+ if (sb->s_bdev->bd_part)
+ sbi->sectors_written_start =
+ (u64)part_stat_read(sb->s_bdev->bd_part, sectors[1]);
+
+ /* Read accumulated write IO statistics if exists */
+ seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
+ if (__exist_node_summaries(sbi))
+ sbi->kbytes_written =
+ le64_to_cpu(seg_i->journal->info.kbytes_written);
+
build_gc_manager(sbi);
/* get an inode for node space */
@@ -1082,8 +2036,16 @@
goto free_nm;
}
+ f2fs_join_shrinker(sbi);
+
+ err = f2fs_build_stats(sbi);
+ if (err)
+ goto free_nm;
+
/* if there are nt orphan nodes free them */
- recover_orphan_inodes(sbi);
+ err = recover_orphan_inodes(sbi);
+ if (err)
+ goto free_node_inode;
/* read root inode and dentry */
root = f2fs_iget(sb, F2FS_ROOT_INO(sbi));
@@ -1104,23 +2066,14 @@
goto free_root_inode;
}
- err = f2fs_build_stats(sbi);
- if (err)
- goto free_root_inode;
-
if (f2fs_proc_root)
sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
- if (sbi->s_proc)
+ if (sbi->s_proc) {
proc_create_data("segment_info", S_IRUGO, sbi->s_proc,
&f2fs_seq_segment_info_fops, sb);
-
- if (test_opt(sbi, DISCARD)) {
- struct request_queue *q = bdev_get_queue(sb->s_bdev);
- if (!blk_queue_discard(q))
- f2fs_msg(sb, KERN_WARNING,
- "mounting with \"discard\" option, but "
- "the device does not support discard");
+ proc_create_data("segment_bits", S_IRUGO, sbi->s_proc,
+ &f2fs_seq_segment_bits_fops, sb);
}
sbi->s_kobj.kset = f2fs_kset;
@@ -1130,61 +2083,126 @@
if (err)
goto free_proc;
- if (!retry)
- sbi->need_fsck = true;
-
/* recover fsynced data */
if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
- err = recover_fsync_data(sbi);
- if (err) {
+ /*
+ * mount should be failed, when device has readonly mode, and
+ * previous checkpoint was not done by clean system shutdown.
+ */
+ if (bdev_read_only(sb->s_bdev) &&
+ !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) {
+ err = -EROFS;
+ goto free_kobj;
+ }
+
+ if (need_fsck)
+ set_sbi_flag(sbi, SBI_NEED_FSCK);
+
+ if (!retry)
+ goto skip_recovery;
+
+ err = recover_fsync_data(sbi, false);
+ if (err < 0) {
+ need_fsck = true;
f2fs_msg(sb, KERN_ERR,
- "Cannot recover all fsync data errno=%ld", err);
+ "Cannot recover all fsync data errno=%d", err);
+ goto free_kobj;
+ }
+ } else {
+ err = recover_fsync_data(sbi, true);
+
+ if (!f2fs_readonly(sb) && err > 0) {
+ err = -EINVAL;
+ f2fs_msg(sb, KERN_ERR,
+ "Need to recover fsync data");
goto free_kobj;
}
}
+skip_recovery:
+ /* recover_fsync_data() cleared this already */
+ clear_sbi_flag(sbi, SBI_POR_DOING);
/*
* If filesystem is not mounted as read-only then
* do start the gc_thread.
*/
- if (!f2fs_readonly(sb)) {
+ if (test_opt(sbi, BG_GC) && !f2fs_readonly(sb)) {
/* After POR, we can run background GC thread.*/
err = start_gc_thread(sbi);
if (err)
goto free_kobj;
}
+ kfree(options);
+
+ /* recover broken superblock */
+ if (recovery) {
+ err = f2fs_commit_super(sbi, true);
+ f2fs_msg(sb, KERN_INFO,
+ "Try to recover %dth superblock, ret: %d",
+ sbi->valid_super_block ? 1 : 2, err);
+ }
+
+ f2fs_msg(sbi->sb, KERN_NOTICE, "Mounted with checkpoint version = %llx",
+ cur_cp_version(F2FS_CKPT(sbi)));
+ f2fs_update_time(sbi, CP_TIME);
+ f2fs_update_time(sbi, REQ_TIME);
return 0;
free_kobj:
+ f2fs_sync_inode_meta(sbi);
kobject_del(&sbi->s_kobj);
+ kobject_put(&sbi->s_kobj);
+ wait_for_completion(&sbi->s_kobj_unregister);
free_proc:
if (sbi->s_proc) {
remove_proc_entry("segment_info", sbi->s_proc);
+ remove_proc_entry("segment_bits", sbi->s_proc);
remove_proc_entry(sb->s_id, f2fs_proc_root);
}
- f2fs_destroy_stats(sbi);
free_root_inode:
dput(sb->s_root);
sb->s_root = NULL;
free_node_inode:
+ truncate_inode_pages_final(NODE_MAPPING(sbi));
+ mutex_lock(&sbi->umount_mutex);
+ release_ino_entry(sbi, true);
+ f2fs_leave_shrinker(sbi);
+ /*
+ * Some dirty meta pages can be produced by recover_orphan_inodes()
+ * failed by EIO. Then, iput(node_inode) can trigger balance_fs_bg()
+ * followed by write_checkpoint() through f2fs_write_node_pages(), which
+ * falls into an infinite loop in sync_meta_pages().
+ */
+ truncate_inode_pages_final(META_MAPPING(sbi));
iput(sbi->node_inode);
+ mutex_unlock(&sbi->umount_mutex);
+ f2fs_destroy_stats(sbi);
free_nm:
destroy_node_manager(sbi);
free_sm:
destroy_segment_manager(sbi);
-free_cp:
+free_devices:
+ destroy_device_list(sbi);
kfree(sbi->ckpt);
free_meta_inode:
make_bad_inode(sbi->meta_inode);
iput(sbi->meta_inode);
+free_io_dummy:
+ if (sbi->write_io_dummy)
+ mempool_destroy(sbi->write_io_dummy);
+free_options:
+ destroy_percpu_info(sbi);
+ kfree(options);
free_sb_buf:
- brelse(raw_super_buf);
+ kfree(raw_super);
free_sbi:
+ if (sbi->s_chksum_driver)
+ crypto_free_shash(sbi->s_chksum_driver);
kfree(sbi);
/* give only one another chance */
if (retry) {
- retry = 0;
+ retry = false;
shrink_dcache_sb(sb);
goto try_onemore;
}
@@ -1197,11 +2215,18 @@
return mount_bdev(fs_type, flags, dev_name, data, f2fs_fill_super);
}
+static void kill_f2fs_super(struct super_block *sb)
+{
+ if (sb->s_root)
+ set_sbi_flag(F2FS_SB(sb), SBI_IS_CLOSE);
+ kill_block_super(sb);
+}
+
static struct file_system_type f2fs_fs_type = {
.owner = THIS_MODULE,
.name = "f2fs",
.mount = f2fs_mount,
- .kill_sb = kill_block_super,
+ .kill_sb = kill_f2fs_super,
.fs_flags = FS_REQUIRES_DEV,
};
MODULE_ALIAS_FS("f2fs");
@@ -1229,6 +2254,8 @@
{
int err;
+ f2fs_build_trace_ios();
+
err = init_inodecache();
if (err)
goto fail;
@@ -1238,30 +2265,40 @@
err = create_segment_manager_caches();
if (err)
goto free_node_manager_caches;
- err = create_gc_caches();
- if (err)
- goto free_segment_manager_caches;
err = create_checkpoint_caches();
if (err)
- goto free_gc_caches;
+ goto free_segment_manager_caches;
+ err = create_extent_cache();
+ if (err)
+ goto free_checkpoint_caches;
f2fs_kset = kset_create_and_add("f2fs", NULL, fs_kobj);
if (!f2fs_kset) {
err = -ENOMEM;
- goto free_checkpoint_caches;
+ goto free_extent_cache;
}
- err = register_filesystem(&f2fs_fs_type);
+ err = register_shrinker(&f2fs_shrinker_info);
if (err)
goto free_kset;
- f2fs_create_root_stats();
+
+ err = register_filesystem(&f2fs_fs_type);
+ if (err)
+ goto free_shrinker;
+ err = f2fs_create_root_stats();
+ if (err)
+ goto free_filesystem;
f2fs_proc_root = proc_mkdir("fs/f2fs", NULL);
return 0;
+free_filesystem:
+ unregister_filesystem(&f2fs_fs_type);
+free_shrinker:
+ unregister_shrinker(&f2fs_shrinker_info);
free_kset:
kset_unregister(f2fs_kset);
+free_extent_cache:
+ destroy_extent_cache();
free_checkpoint_caches:
destroy_checkpoint_caches();
-free_gc_caches:
- destroy_gc_caches();
free_segment_manager_caches:
destroy_segment_manager_caches();
free_node_manager_caches:
@@ -1277,12 +2314,14 @@
remove_proc_entry("fs/f2fs", NULL);
f2fs_destroy_root_stats();
unregister_filesystem(&f2fs_fs_type);
+ unregister_shrinker(&f2fs_shrinker_info);
+ kset_unregister(f2fs_kset);
+ destroy_extent_cache();
destroy_checkpoint_caches();
- destroy_gc_caches();
destroy_segment_manager_caches();
destroy_node_manager_caches();
destroy_inodecache();
- kset_unregister(f2fs_kset);
+ f2fs_destroy_trace_ios();
}
module_init(init_f2fs_fs)
@@ -1291,3 +2330,4 @@
MODULE_AUTHOR("Samsung Electronics's Praesto Team");
MODULE_DESCRIPTION("Flash Friendly File System");
MODULE_LICENSE("GPL");
+
diff --git a/fs/f2fs/trace.c b/fs/f2fs/trace.c
new file mode 100644
index 0000000..bccbbf2
--- /dev/null
+++ b/fs/f2fs/trace.c
@@ -0,0 +1,162 @@
+/*
+ * 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 %5x %12x %4x\n",
+ last_io.major, last_io.minor,
+ last_io.pid, "----------------",
+ last_io.type,
+ last_io.fio.op, last_io.fio.op_flags,
+ 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;
+
+ set_page_private(page, (unsigned long)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.op == fio->op &&
+ last_io.fio.op_flags == fio->op_flags &&
+ 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 == max_items)
+ 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);
+}
diff --git a/fs/f2fs/trace.h b/fs/f2fs/trace.h
new file mode 100644
index 0000000..67db24a
--- /dev/null
+++ b/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__ */
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index deca872..c01e2b6 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -83,7 +83,7 @@
}
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 @@
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 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 @@
return -EINVAL;
F2FS_I(inode)->i_advise |= *(char *)value;
+ f2fs_mark_inode_dirty_sync(inode, true);
return 0;
}
@@ -264,18 +266,49 @@
return entry;
}
-static void *read_all_xattrs(struct inode *inode, struct page *ipage)
+static struct f2fs_xattr_entry *__find_inline_xattr(void *base_addr,
+ void **last_addr, int index,
+ size_t len, const char *name)
+{
+ struct f2fs_xattr_entry *entry;
+ unsigned int inline_size = F2FS_INLINE_XATTR_ADDRS << 2;
+
+ list_for_each_xattr(entry, base_addr) {
+ if ((void *)entry + sizeof(__u32) > base_addr + inline_size ||
+ (void *)XATTR_NEXT_ENTRY(entry) + sizeof(__u32) >
+ base_addr + inline_size) {
+ *last_addr = entry;
+ return NULL;
+ }
+ if (entry->e_name_index != index)
+ continue;
+ if (entry->e_name_len != len)
+ continue;
+ if (!memcmp(entry->e_name, name, len))
+ break;
+ }
+ return entry;
+}
+
+static int lookup_all_xattrs(struct inode *inode, struct page *ipage,
+ unsigned int index, unsigned int len,
+ const char *name, struct f2fs_xattr_entry **xe,
+ void **base_addr)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- struct f2fs_xattr_header *header;
- size_t size = PAGE_SIZE, inline_size = 0;
- void *txattr_addr;
+ void *cur_addr, *txattr_addr, *last_addr = NULL;
+ nid_t xnid = F2FS_I(inode)->i_xattr_nid;
+ unsigned int size = xnid ? VALID_XATTR_BLOCK_SIZE : 0;
+ unsigned int inline_size = inline_xattr_size(inode);
+ int err = 0;
- inline_size = inline_xattr_size(inode);
+ if (!size && !inline_size)
+ return -ENODATA;
- txattr_addr = kzalloc(inline_size + size, GFP_F2FS_ZERO);
+ txattr_addr = kzalloc(inline_size + size + XATTR_PADDING_SIZE,
+ GFP_F2FS_ZERO);
if (!txattr_addr)
- return NULL;
+ return -ENOMEM;
/* read from inline xattr */
if (inline_size) {
@@ -286,8 +319,86 @@
inline_addr = inline_xattr_addr(ipage);
} else {
page = get_node_page(sbi, inode->i_ino);
- if (IS_ERR(page))
+ if (IS_ERR(page)) {
+ err = PTR_ERR(page);
+ goto out;
+ }
+ inline_addr = inline_xattr_addr(page);
+ }
+ memcpy(txattr_addr, inline_addr, inline_size);
+ f2fs_put_page(page, 1);
+
+ *xe = __find_inline_xattr(txattr_addr, &last_addr,
+ index, len, name);
+ if (*xe)
+ goto check;
+ }
+
+ /* read from xattr node block */
+ if (xnid) {
+ struct page *xpage;
+ void *xattr_addr;
+
+ /* The inode already has an extended attribute block. */
+ xpage = get_node_page(sbi, xnid);
+ if (IS_ERR(xpage)) {
+ err = PTR_ERR(xpage);
+ goto out;
+ }
+
+ xattr_addr = page_address(xpage);
+ memcpy(txattr_addr + inline_size, xattr_addr, size);
+ f2fs_put_page(xpage, 1);
+ }
+
+ if (last_addr)
+ cur_addr = XATTR_HDR(last_addr) - 1;
+ else
+ cur_addr = txattr_addr;
+
+ *xe = __find_xattr(cur_addr, index, len, name);
+check:
+ if (IS_XATTR_LAST_ENTRY(*xe)) {
+ err = -ENODATA;
+ goto out;
+ }
+
+ *base_addr = txattr_addr;
+ return 0;
+out:
+ kzfree(txattr_addr);
+ return err;
+}
+
+static int read_all_xattrs(struct inode *inode, struct page *ipage,
+ void **base_addr)
+{
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_xattr_header *header;
+ nid_t xnid = F2FS_I(inode)->i_xattr_nid;
+ unsigned int size = VALID_XATTR_BLOCK_SIZE;
+ unsigned int inline_size = inline_xattr_size(inode);
+ void *txattr_addr;
+ int err;
+
+ txattr_addr = kzalloc(inline_size + size + XATTR_PADDING_SIZE,
+ GFP_F2FS_ZERO);
+ if (!txattr_addr)
+ return -ENOMEM;
+
+ /* read from inline xattr */
+ if (inline_size) {
+ struct page *page = NULL;
+ void *inline_addr;
+
+ if (ipage) {
+ inline_addr = inline_xattr_addr(ipage);
+ } else {
+ page = get_node_page(sbi, inode->i_ino);
+ if (IS_ERR(page)) {
+ err = PTR_ERR(page);
goto fail;
+ }
inline_addr = inline_xattr_addr(page);
}
memcpy(txattr_addr, inline_addr, inline_size);
@@ -295,17 +406,19 @@
}
/* read from xattr node block */
- if (F2FS_I(inode)->i_xattr_nid) {
+ if (xnid) {
struct page *xpage;
void *xattr_addr;
/* The inode already has an extended attribute block. */
- xpage = get_node_page(sbi, F2FS_I(inode)->i_xattr_nid);
- if (IS_ERR(xpage))
+ xpage = get_node_page(sbi, xnid);
+ if (IS_ERR(xpage)) {
+ err = PTR_ERR(xpage);
goto fail;
+ }
xattr_addr = page_address(xpage);
- memcpy(txattr_addr + inline_size, xattr_addr, PAGE_SIZE);
+ memcpy(txattr_addr + inline_size, xattr_addr, size);
f2fs_put_page(xpage, 1);
}
@@ -316,24 +429,23 @@
header->h_magic = cpu_to_le32(F2FS_XATTR_MAGIC);
header->h_refcount = cpu_to_le32(1);
}
- return txattr_addr;
+ *base_addr = txattr_addr;
+ return 0;
fail:
kzfree(txattr_addr);
- return NULL;
+ return err;
}
static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
void *txattr_addr, struct page *ipage)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
- size_t inline_size = 0;
+ size_t inline_size = inline_xattr_size(inode);
void *xattr_addr;
struct page *xpage;
nid_t new_nid = 0;
int err;
- inline_size = inline_xattr_size(inode);
-
if (hsize > inline_size && !F2FS_I(inode)->i_xattr_nid)
if (!alloc_nid(sbi, &new_nid))
return -ENOSPC;
@@ -345,7 +457,8 @@
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 +466,7 @@
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 +487,7 @@
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);
@@ -387,23 +500,20 @@
}
xattr_addr = page_address(xpage);
- memcpy(xattr_addr, txattr_addr + inline_size, PAGE_SIZE -
- sizeof(struct node_footer));
+ memcpy(xattr_addr, txattr_addr + inline_size, VALID_XATTR_BLOCK_SIZE);
set_page_dirty(xpage);
f2fs_put_page(xpage, 1);
- /* need to checkpoint during fsync */
- F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi));
return 0;
}
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;
+ struct f2fs_xattr_entry *entry = NULL;
int error = 0;
- size_t size, len;
+ unsigned int size, len;
+ void *base_addr = NULL;
if (name == NULL)
return -EINVAL;
@@ -412,21 +522,16 @@
if (len > F2FS_NAME_LEN)
return -ERANGE;
- base_addr = read_all_xattrs(inode, NULL);
- if (!base_addr)
- return -ENOMEM;
-
- entry = __find_xattr(base_addr, index, len, name);
- if (IS_XATTR_LAST_ENTRY(entry)) {
- error = -ENODATA;
- goto cleanup;
- }
+ error = lookup_all_xattrs(inode, ipage, index, len, name,
+ &entry, &base_addr);
+ if (error)
+ return error;
size = le16_to_cpu(entry->e_value_size);
if (buffer && size > buffer_size) {
error = -ERANGE;
- goto cleanup;
+ goto out;
}
if (buffer) {
@@ -434,23 +539,22 @@
memcpy(buffer, pval, size);
}
error = size;
-
-cleanup:
+out:
kzfree(base_addr);
return error;
}
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;
size_t rest = buffer_size;
- base_addr = read_all_xattrs(inode, NULL);
- if (!base_addr)
- return -ENOMEM;
+ error = read_all_xattrs(inode, NULL, &base_addr);
+ if (error)
+ return error;
list_for_each_xattr(entry, base_addr) {
const struct xattr_handler *handler =
@@ -477,17 +581,25 @@
return error;
}
+static bool f2fs_xattr_value_same(struct f2fs_xattr_entry *entry,
+ const void *value, size_t size)
+{
+ void *pval = entry->e_name + entry->e_name_len;
+
+ return (le16_to_cpu(entry->e_value_size) == size) &&
+ !memcmp(pval, value, size);
+}
+
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;
@@ -497,24 +609,32 @@
len = strlen(name);
- if (len > F2FS_NAME_LEN || size > MAX_VALUE_LEN(inode))
+ if (len > F2FS_NAME_LEN)
return -ERANGE;
- base_addr = read_all_xattrs(inode, ipage);
- if (!base_addr)
- goto exit;
+ if (size > MAX_VALUE_LEN(inode))
+ return -E2BIG;
+
+ error = read_all_xattrs(inode, ipage, &base_addr);
+ if (error)
+ return error;
/* find entry with wanted name. */
here = __find_xattr(base_addr, index, len, name);
found = IS_XATTR_LAST_ENTRY(here) ? 0 : 1;
- if ((flags & XATTR_REPLACE) && !found) {
+ if (found) {
+ if ((flags & XATTR_CREATE)) {
+ error = -EEXIST;
+ goto exit;
+ }
+
+ if (f2fs_xattr_value_same(here, value, size))
+ goto exit;
+ } else if ((flags & XATTR_REPLACE)) {
error = -ENODATA;
goto exit;
- } else if ((flags & XATTR_CREATE) && found) {
- error = -EEXIST;
- goto exit;
}
last = here;
@@ -535,7 +655,7 @@
free = free + ENTRY_SIZE(here);
if (unlikely(free < newsize)) {
- error = -ENOSPC;
+ error = -E2BIG;
goto exit;
}
}
@@ -563,7 +683,6 @@
* 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 +696,17 @@
if (error)
goto exit;
- if (is_inode_flag_set(fi, FI_ACL_MODE)) {
- inode->i_mode = fi->i_acl_mode;
- inode->i_ctime = CURRENT_TIME;
- clear_inode_flag(fi, FI_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(inode);
+ 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, true);
+ if (!error && S_ISDIR(inode->i_mode))
+ set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_CP);
exit:
kzfree(base_addr);
return error;
@@ -603,7 +723,7 @@
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 +732,6 @@
up_write(&F2FS_I(inode)->i_sem);
f2fs_unlock_op(sbi);
+ f2fs_update_time(sbi, REQ_TIME);
return err;
}
diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h
index 34ab7db..08a4840 100644
--- a/fs/f2fs/xattr.h
+++ b/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 */
@@ -54,10 +58,10 @@
#define XATTR_FIRST_ENTRY(ptr) (XATTR_ENTRY(XATTR_HDR(ptr) + 1))
#define XATTR_ROUND (3)
-#define XATTR_ALIGN(size) ((size + XATTR_ROUND) & ~XATTR_ROUND)
+#define XATTR_ALIGN(size) (((size) + XATTR_ROUND) & ~XATTR_ROUND)
#define ENTRY_SIZE(entry) (XATTR_ALIGN(sizeof(struct f2fs_xattr_entry) + \
- entry->e_name_len + le16_to_cpu(entry->e_value_size)))
+ (entry)->e_name_len + le16_to_cpu((entry)->e_value_size)))
#define XATTR_NEXT_ENTRY(entry) ((struct f2fs_xattr_entry *)((char *)(entry) +\
ENTRY_SIZE(entry)))
@@ -68,9 +72,10 @@
for (entry = XATTR_FIRST_ENTRY(addr);\
!IS_XATTR_LAST_ENTRY(entry);\
entry = XATTR_NEXT_ENTRY(entry))
-
-#define MIN_OFFSET(i) XATTR_ALIGN(inline_xattr_size(i) + PAGE_SIZE - \
- sizeof(struct node_footer) - sizeof(__u32))
+#define VALID_XATTR_BLOCK_SIZE (PAGE_SIZE - sizeof(struct node_footer))
+#define XATTR_PADDING_SIZE (sizeof(__u32))
+#define MIN_OFFSET(i) XATTR_ALIGN(inline_xattr_size(i) + \
+ VALID_XATTR_BLOCK_SIZE)
#define MAX_VALUE_LEN(i) (MIN_OFFSET(i) - \
sizeof(struct f2fs_xattr_header) - \
@@ -115,18 +120,21 @@
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;
}
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 3c4a212..f0da3b0 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -226,6 +226,8 @@
#define DCACHE_MAY_FREE 0x00800000
#define DCACHE_OP_SELECT_INODE 0x02000000 /* Unioned entry: dcache op selects inode */
+#define DCACHE_ENCRYPTED_WITH_KEY 0x04000000 /* dir is encrypted with a valid key */
+
extern seqlock_t rename_lock;
/*
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 2df22ea..67303b8 100644
--- a/include/linux/f2fs_fs.h
+++ b/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
@@ -32,8 +36,15 @@
#define F2FS_NODE_INO(sbi) (sbi->node_ino_num)
#define F2FS_META_INO(sbi) (sbi->meta_ino_num)
+#define F2FS_IO_SIZE(sbi) (1 << (sbi)->write_io_size_bits) /* Blocks */
+#define F2FS_IO_SIZE_KB(sbi) (1 << ((sbi)->write_io_size_bits + 2)) /* KB */
+#define F2FS_IO_SIZE_BYTES(sbi) (1 << ((sbi)->write_io_size_bits + 12)) /* B */
+#define F2FS_IO_SIZE_BITS(sbi) ((sbi)->write_io_size_bits) /* power of 2 */
+#define F2FS_IO_SIZE_MASK(sbi) (F2FS_IO_SIZE(sbi) - 1)
+
/* 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
@@ -45,9 +56,19 @@
#define MAX_ACTIVE_NODE_LOGS 8
#define MAX_ACTIVE_DATA_LOGS 8
+#define VERSION_LEN 256
+#define MAX_VOLUME_NAME 512
+#define MAX_PATH_LEN 64
+#define MAX_DEVICES 8
+
/*
* For superblock
*/
+struct f2fs_device {
+ __u8 path[MAX_PATH_LEN];
+ __le32 total_segments;
+} __packed;
+
struct f2fs_super_block {
__le32 magic; /* Magic Number */
__le16 major_ver; /* Major Version */
@@ -77,15 +98,26 @@
__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 */
+ struct f2fs_device devs[MAX_DEVICES]; /* device list */
+ __u8 reserved[327]; /* valid reserved region */
} __packed;
/*
* For checkpoint
*/
+#define CP_TRIMMED_FLAG 0x00000100
+#define CP_NAT_BITS_FLAG 0x00000080
+#define CP_CRC_RECOVERY_FLAG 0x00000040
+#define CP_FASTBOOT_FLAG 0x00000020
#define CP_FSCK_FLAG 0x00000010
#define CP_ERROR_FLAG 0x00000008
#define CP_COMPACT_SUM_FLAG 0x00000004
@@ -147,7 +179,7 @@
*/
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 +187,12 @@
#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 +202,13 @@
#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 +256,8 @@
OFFSET_BIT_SHIFT
};
+#define OFFSET_BIT_MASK (0x07) /* (0x01 << OFFSET_BIT_SHIFT) - 1 */
+
struct node_footer {
__le32 nid; /* node id */
__le32 ino; /* inode nunmber */
@@ -246,7 +279,8 @@
/*
* For NAT entries
*/
-#define NAT_ENTRY_PER_BLOCK (PAGE_CACHE_SIZE / sizeof(struct f2fs_nat_entry))
+#define NAT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_nat_entry))
+#define NAT_ENTRY_BITMAP_SIZE ((NAT_ENTRY_PER_BLOCK + 7) / 8)
struct f2fs_nat_entry {
__u8 version; /* latest version of cached nat entry */
@@ -335,7 +369,7 @@
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 -\
@@ -348,6 +382,12 @@
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
@@ -377,18 +417,28 @@
__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;
@@ -408,15 +458,25 @@
#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)
@@ -441,6 +501,24 @@
__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,
@@ -454,4 +532,6 @@
F2FS_FT_MAX
};
+#define S_SHIFT 12
+
#endif /* _LINUX_F2FS_FS_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 5832e89..ab1e4b33 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -49,6 +49,8 @@
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);
@@ -623,6 +625,10 @@
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 */
};
@@ -1217,6 +1223,9 @@
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;
diff --git a/include/linux/fscrypt_common.h b/include/linux/fscrypt_common.h
new file mode 100644
index 0000000..10c1abf
--- /dev/null
+++ b/include/linux/fscrypt_common.h
@@ -0,0 +1,145 @@
+/*
+ * fscrypt_common.h: common declarations for per-file encryption
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * Written by Michael Halcrow, 2015.
+ * Modified by Jaegeuk Kim, 2015.
+ */
+
+#ifndef _LINUX_FSCRYPT_COMMON_H
+#define _LINUX_FSCRYPT_COMMON_H
+
+#include <linux/key.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/bio.h>
+#include <linux/dcache.h>
+#include <crypto/skcipher.h>
+#include <uapi/linux/fs.h>
+
+#define FS_CRYPTO_BLOCK_SIZE 16
+
+struct fscrypt_info;
+
+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 */
+};
+
+/**
+ * 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)
+
+/*
+ * fscrypt superblock flags
+ */
+#define FS_CFLG_OWN_PAGES (1U << 1)
+
+/*
+ * crypto opertions for filesystems
+ */
+struct fscrypt_operations {
+ unsigned int flags;
+ const char *key_prefix;
+ int (*get_context)(struct inode *, void *, size_t);
+ 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 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(const struct inode *inode)
+{
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+ return (inode->i_crypt_info != NULL);
+#else
+ return 0;
+#endif
+}
+
+#endif /* _LINUX_FSCRYPT_COMMON_H */
diff --git a/include/linux/fscrypt_notsupp.h b/include/linux/fscrypt_notsupp.h
new file mode 100644
index 0000000..ec406ae
--- /dev/null
+++ b/include/linux/fscrypt_notsupp.h
@@ -0,0 +1,177 @@
+/*
+ * fscrypt_notsupp.h
+ *
+ * This stubs out the fscrypt functions for filesystems configured without
+ * encryption support.
+ */
+
+#ifndef _LINUX_FSCRYPT_NOTSUPP_H
+#define _LINUX_FSCRYPT_NOTSUPP_H
+
+#include <linux/fscrypt_common.h>
+
+/* crypto.c */
+static inline struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *inode,
+ gfp_t gfp_flags)
+{
+ return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline void fscrypt_release_ctx(struct fscrypt_ctx *ctx)
+{
+ return;
+}
+
+static inline struct page *fscrypt_encrypt_page(const struct inode *inode,
+ struct page *page,
+ unsigned int len,
+ unsigned int offs,
+ u64 lblk_num, gfp_t gfp_flags)
+{
+ return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline int fscrypt_decrypt_page(const struct inode *inode,
+ struct page *page,
+ unsigned int len, unsigned int offs,
+ u64 lblk_num)
+{
+ return -EOPNOTSUPP;
+}
+
+
+static inline void fscrypt_restore_control_page(struct page *page)
+{
+ return;
+}
+
+static inline void fscrypt_set_d_op(struct dentry *dentry)
+{
+ return;
+}
+
+static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry)
+{
+ return;
+}
+
+/* policy.c */
+static inline int fscrypt_ioctl_set_policy(struct file *filp,
+ const void __user *arg)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int fscrypt_has_permitted_context(struct inode *parent,
+ struct inode *child)
+{
+ return 0;
+}
+
+static inline int fscrypt_inherit_context(struct inode *parent,
+ struct inode *child,
+ void *fs_data, bool preload)
+{
+ return -EOPNOTSUPP;
+}
+
+/* keyinfo.c */
+static inline int fscrypt_get_encryption_info(struct inode *inode)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void fscrypt_put_encryption_info(struct inode *inode,
+ struct fscrypt_info *ci)
+{
+ return;
+}
+
+ /* fname.c */
+static inline int fscrypt_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_free_filename(struct fscrypt_name *fname)
+{
+ return;
+}
+
+static inline u32 fscrypt_fname_encrypted_size(const struct inode *inode,
+ u32 ilen)
+{
+ /* never happens */
+ WARN_ON(1);
+ return 0;
+}
+
+static inline int fscrypt_fname_alloc_buffer(const struct inode *inode,
+ u32 ilen,
+ struct fscrypt_str *crypto_str)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str)
+{
+ return;
+}
+
+static inline int fscrypt_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_fname_usr_to_disk(struct inode *inode,
+ const struct qstr *iname,
+ struct fscrypt_str *oname)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline bool fscrypt_match_name(const struct fscrypt_name *fname,
+ const u8 *de_name, u32 de_name_len)
+{
+ /* Encryption support disabled; use standard comparison */
+ if (de_name_len != fname->disk_name.len)
+ return false;
+ return !memcmp(de_name, fname->disk_name.name, fname->disk_name.len);
+}
+
+/* bio.c */
+static inline void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *ctx,
+ struct bio *bio)
+{
+ return;
+}
+
+static inline void fscrypt_pullback_bio_page(struct page **page, bool restore)
+{
+ return;
+}
+
+static inline int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
+ sector_t pblk, unsigned int len)
+{
+ return -EOPNOTSUPP;
+}
+
+#endif /* _LINUX_FSCRYPT_NOTSUPP_H */
diff --git a/include/linux/fscrypt_supp.h b/include/linux/fscrypt_supp.h
new file mode 100644
index 0000000..e12c224
--- /dev/null
+++ b/include/linux/fscrypt_supp.h
@@ -0,0 +1,144 @@
+/*
+ * fscrypt_supp.h
+ *
+ * This is included by filesystems configured with encryption support.
+ */
+
+#ifndef _LINUX_FSCRYPT_SUPP_H
+#define _LINUX_FSCRYPT_SUPP_H
+
+#include <linux/fscrypt_common.h>
+
+/* crypto.c */
+extern struct kmem_cache *fscrypt_info_cachep;
+extern struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *, gfp_t);
+extern void fscrypt_release_ctx(struct fscrypt_ctx *);
+extern struct page *fscrypt_encrypt_page(const struct inode *, struct page *,
+ unsigned int, unsigned int,
+ u64, gfp_t);
+extern int fscrypt_decrypt_page(const struct inode *, struct page *, unsigned int,
+ unsigned int, u64);
+extern void fscrypt_restore_control_page(struct page *);
+
+extern const struct dentry_operations fscrypt_d_ops;
+
+static inline void fscrypt_set_d_op(struct dentry *dentry)
+{
+ d_set_d_op(dentry, &fscrypt_d_ops);
+}
+
+static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry)
+{
+ spin_lock(&dentry->d_lock);
+ dentry->d_flags |= DCACHE_ENCRYPTED_WITH_KEY;
+ spin_unlock(&dentry->d_lock);
+}
+
+/* policy.c */
+extern int fscrypt_ioctl_set_policy(struct file *, const void __user *);
+extern int fscrypt_ioctl_get_policy(struct file *, void __user *);
+extern int fscrypt_has_permitted_context(struct inode *, struct inode *);
+extern int fscrypt_inherit_context(struct inode *, struct inode *,
+ void *, bool);
+/* keyinfo.c */
+extern int 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(const struct inode *, u32);
+extern int fscrypt_fname_alloc_buffer(const struct inode *, u32,
+ struct fscrypt_str *);
+extern void fscrypt_fname_free_buffer(struct fscrypt_str *);
+extern int fscrypt_fname_disk_to_usr(struct inode *, u32, u32,
+ const struct fscrypt_str *, struct fscrypt_str *);
+extern int fscrypt_fname_usr_to_disk(struct inode *, const struct qstr *,
+ struct fscrypt_str *);
+
+#define FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE 32
+
+/* Extracts the second-to-last ciphertext block; see explanation below */
+#define FSCRYPT_FNAME_DIGEST(name, len) \
+ ((name) + round_down((len) - FS_CRYPTO_BLOCK_SIZE - 1, \
+ FS_CRYPTO_BLOCK_SIZE))
+
+#define FSCRYPT_FNAME_DIGEST_SIZE FS_CRYPTO_BLOCK_SIZE
+
+/**
+ * fscrypt_digested_name - alternate identifier for an on-disk filename
+ *
+ * When userspace lists an encrypted directory without access to the key,
+ * filenames whose ciphertext is longer than FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE
+ * bytes are shown in this abbreviated form (base64-encoded) rather than as the
+ * full ciphertext (base64-encoded). This is necessary to allow supporting
+ * filenames up to NAME_MAX bytes, since base64 encoding expands the length.
+ *
+ * To make it possible for filesystems to still find the correct directory entry
+ * despite not knowing the full on-disk name, we encode any filesystem-specific
+ * 'hash' and/or 'minor_hash' which the filesystem may need for its lookups,
+ * followed by the second-to-last ciphertext block of the filename. Due to the
+ * use of the CBC-CTS encryption mode, the second-to-last ciphertext block
+ * depends on the full plaintext. (Note that ciphertext stealing causes the
+ * last two blocks to appear "flipped".) This makes collisions very unlikely:
+ * just a 1 in 2^128 chance for two filenames to collide even if they share the
+ * same filesystem-specific hashes.
+ *
+ * This scheme isn't strictly immune to intentional collisions because it's
+ * basically like a CBC-MAC, which isn't secure on variable-length inputs.
+ * However, generating a CBC-MAC collision requires the ability to choose
+ * arbitrary ciphertext, which won't normally be possible with filename
+ * encryption since it would require write access to the raw disk.
+ *
+ * Taking a real cryptographic hash like SHA-256 over the full ciphertext would
+ * be better in theory but would be less efficient and more complicated to
+ * implement, especially since the filesystem would need to calculate it for
+ * each directory entry examined during a search.
+ */
+struct fscrypt_digested_name {
+ u32 hash;
+ u32 minor_hash;
+ u8 digest[FSCRYPT_FNAME_DIGEST_SIZE];
+};
+
+/**
+ * fscrypt_match_name() - test whether the given name matches a directory entry
+ * @fname: the name being searched for
+ * @de_name: the name from the directory entry
+ * @de_name_len: the length of @de_name in bytes
+ *
+ * Normally @fname->disk_name will be set, and in that case we simply compare
+ * that to the name stored in the directory entry. The only exception is that
+ * if we don't have the key for an encrypted directory and a filename in it is
+ * very long, then we won't have the full disk_name and we'll instead need to
+ * match against the fscrypt_digested_name.
+ *
+ * Return: %true if the name matches, otherwise %false.
+ */
+static inline bool fscrypt_match_name(const struct fscrypt_name *fname,
+ const u8 *de_name, u32 de_name_len)
+{
+ if (unlikely(!fname->disk_name.name)) {
+ const struct fscrypt_digested_name *n =
+ (const void *)fname->crypto_buf.name;
+ if (WARN_ON_ONCE(fname->usr_fname->name[0] != '_'))
+ return false;
+ if (de_name_len <= FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE)
+ return false;
+ return !memcmp(FSCRYPT_FNAME_DIGEST(de_name, de_name_len),
+ n->digest, FSCRYPT_FNAME_DIGEST_SIZE);
+ }
+
+ if (de_name_len != fname->disk_name.len)
+ return false;
+ return !memcmp(de_name, fname->disk_name.name, fname->disk_name.len);
+}
+
+/* bio.c */
+extern void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *, struct bio *);
+extern void fscrypt_pullback_bio_page(struct page **, bool);
+extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t,
+ unsigned int);
+
+#endif /* _LINUX_FSCRYPT_SUPP_H */
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index bbc4de9..83c7a11 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -6,20 +6,27 @@
#include <linux/tracepoint.h>
-#define show_dev(entry) MAJOR(entry->dev), MINOR(entry->dev)
-#define show_dev_ino(entry) show_dev(entry), (unsigned long)entry->ino
+#define show_dev(dev) MAJOR(dev), MINOR(dev)
+#define show_dev_ino(entry) show_dev(entry->dev), (unsigned long)entry->ino
#define show_block_type(type) \
__print_symbolic(type, \
{ NODE, "NODE" }, \
{ DATA, "DATA" }, \
{ META, "META" }, \
- { META_FLUSH, "META_FLUSH" })
+ { META_FLUSH, "META_FLUSH" }, \
+ { INMEM, "INMEM" }, \
+ { INMEM_DROP, "INMEM_DROP" }, \
+ { INMEM_INVALIDATE, "INMEM_INVALIDATE" }, \
+ { 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))
-#define show_bio_type(type) show_bio_base(type), show_bio_extra(type)
+#define show_bio_type(op, op_flags) \
+ show_bio_base((op|op_flags)), show_bio_extra((op|op_flags))
#define show_bio_base(type) \
__print_symbolic(F2FS_BIO_MASK(type), \
@@ -72,10 +79,14 @@
#define show_cpreason(type) \
__print_symbolic(type, \
{ CP_UMOUNT, "Umount" }, \
+ { CP_FASTBOOT, "Fastboot" }, \
{ CP_SYNC, "Sync" }, \
- { CP_DISCARD, "Discard" })
+ { CP_RECOVERY, "Recovery" }, \
+ { CP_DISCARD, "Discard" }, \
+ { CP_UMOUNT | CP_TRIMMED, "Umount,Trimmed" })
struct victim_sel_policy;
+struct f2fs_map_blocks;
DECLARE_EVENT_CLASS(f2fs__inode,
@@ -148,14 +159,14 @@
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)
),
@@ -190,12 +201,12 @@
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;
),
TP_printk("dev = (%d,%d), superblock is %s, wait = %d",
- show_dev(__entry),
+ show_dev(__entry->dev),
__entry->dirty ? "dirty" : "not dirty",
__entry->wait)
);
@@ -265,6 +276,13 @@
TP_ARGS(inode, ret)
);
+DEFINE_EVENT(f2fs__inode_exit, f2fs_drop_inode,
+
+ TP_PROTO(struct inode *inode, int ret),
+
+ TP_ARGS(inode, ret)
+);
+
DEFINE_EVENT(f2fs__inode, f2fs_truncate,
TP_PROTO(struct inode *inode),
@@ -440,71 +458,66 @@
__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->dev),
+ __entry->wait_ms,
+ __entry->prefree,
+ __entry->free)
+);
+
TRACE_EVENT(f2fs_get_victim,
TP_PROTO(struct super_block *sb, int type, int gc_type,
@@ -541,7 +554,7 @@
TP_printk("dev = (%d,%d), type = %s, policy = (%s, %s, %s), victim = %u "
"ofs_unit = %u, pre_victim_secno = %d, prefree = %u, free = %u",
- show_dev(__entry),
+ show_dev(__entry->dev),
show_data_type(__entry->type),
show_gc_type(__entry->gc_type),
show_alloc_mode(__entry->alloc_mode),
@@ -656,39 +669,101 @@
__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",
- show_dev(__entry),
+ TP_printk("dev = (%d,%d), nid = %u, ofs_in_node = %u, count = %llu",
+ show_dev(__entry->dev),
(unsigned int)__entry->nid,
- __entry->ofs_in_node)
+ __entry->ofs_in_node,
+ (unsigned long long)__entry->count)
);
-DECLARE_EVENT_CLASS(f2fs__submit_bio,
+DECLARE_EVENT_CLASS(f2fs__submit_page_bio,
- TP_PROTO(struct super_block *sb, int rw, int type, struct bio *bio),
+ TP_PROTO(struct page *page, struct f2fs_io_info *fio),
- TP_ARGS(sb, rw, type, bio),
+ 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, op)
+ __field(int, op_flags)
+ __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->op = fio->op;
+ __entry->op_flags = fio->op_flags;
+ __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->op, __entry->op_flags),
+ 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__bio,
+
+ TP_PROTO(struct super_block *sb, int type, struct bio *bio),
+
+ TP_ARGS(sb, type, bio),
TP_STRUCT__entry(
__field(dev_t, dev)
- __field(int, rw)
+ __field(dev_t, target)
+ __field(int, op)
+ __field(int, op_flags)
__field(int, type)
__field(sector_t, sector)
__field(unsigned int, size)
@@ -696,34 +771,55 @@
TP_fast_assign(
__entry->dev = sb->s_dev;
- __entry->rw = rw;
+ __entry->target = bio->bi_bdev->bd_dev;
+ __entry->op = bio_op(bio);
+ __entry->op_flags = bio->bi_rw;
__entry->type = type;
__entry->sector = bio->bi_iter.bi_sector;
__entry->size = bio->bi_iter.bi_size;
),
- TP_printk("dev = (%d,%d), %s%s, %s, sector = %lld, size = %u",
- show_dev(__entry),
- show_bio_type(__entry->rw),
+ TP_printk("dev = (%d,%d)/(%d,%d), rw = %s%s, %s, sector = %lld, size = %u",
+ show_dev(__entry->target),
+ show_dev(__entry->dev),
+ show_bio_type(__entry->op, __entry->op_flags),
show_block_type(__entry->type),
(unsigned long long)__entry->sector,
__entry->size)
);
-DEFINE_EVENT_CONDITION(f2fs__submit_bio, f2fs_submit_write_bio,
+DEFINE_EVENT_CONDITION(f2fs__bio, f2fs_prepare_write_bio,
- TP_PROTO(struct super_block *sb, int rw, int type, struct bio *bio),
+ TP_PROTO(struct super_block *sb, int type, struct bio *bio),
- TP_ARGS(sb, rw, type, bio),
+ TP_ARGS(sb, type, bio),
TP_CONDITION(bio)
);
-DEFINE_EVENT_CONDITION(f2fs__submit_bio, f2fs_submit_read_bio,
+DEFINE_EVENT_CONDITION(f2fs__bio, f2fs_prepare_read_bio,
- TP_PROTO(struct super_block *sb, int rw, int type, struct bio *bio),
+ TP_PROTO(struct super_block *sb, int type, struct bio *bio),
- TP_ARGS(sb, rw, type, bio),
+ TP_ARGS(sb, type, bio),
+
+ TP_CONDITION(bio)
+);
+
+DEFINE_EVENT_CONDITION(f2fs__bio, f2fs_submit_read_bio,
+
+ TP_PROTO(struct super_block *sb, int type, struct bio *bio),
+
+ TP_ARGS(sb, type, bio),
+
+ TP_CONDITION(bio)
+);
+
+DEFINE_EVENT_CONDITION(f2fs__bio, f2fs_submit_write_bio,
+
+ TP_PROTO(struct super_block *sb, int type, struct bio *bio),
+
+ TP_ARGS(sb, type, bio),
TP_CONDITION(bio)
);
@@ -831,6 +927,13 @@
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 +955,20 @@
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 +1033,30 @@
__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,
@@ -967,16 +1078,16 @@
),
TP_printk("dev = (%d,%d), checkpoint for %s, state = %s",
- show_dev(__entry),
+ show_dev(__entry->dev),
show_cpreason(__entry->reason),
__entry->msg)
);
-TRACE_EVENT(f2fs_issue_discard,
+DECLARE_EVENT_CLASS(f2fs_discard,
- TP_PROTO(struct super_block *sb, block_t blkstart, block_t blklen),
+ TP_PROTO(struct block_device *dev, block_t blkstart, block_t blklen),
- TP_ARGS(sb, blkstart, blklen),
+ TP_ARGS(dev, blkstart, blklen),
TP_STRUCT__entry(
__field(dev_t, dev)
@@ -985,40 +1096,256 @@
),
TP_fast_assign(
- __entry->dev = sb->s_dev;
+ __entry->dev = dev->bd_dev;
__entry->blkstart = blkstart;
__entry->blklen = blklen;
),
TP_printk("dev = (%d,%d), blkstart = 0x%llx, blklen = 0x%llx",
- show_dev(__entry),
+ show_dev(__entry->dev),
(unsigned long long)__entry->blkstart,
(unsigned long long)__entry->blklen)
);
-TRACE_EVENT(f2fs_issue_flush,
+DEFINE_EVENT(f2fs_discard, f2fs_queue_discard,
- TP_PROTO(struct super_block *sb, bool nobarrier, bool flush_merge),
+ TP_PROTO(struct block_device *dev, block_t blkstart, block_t blklen),
- TP_ARGS(sb, nobarrier, flush_merge),
+ TP_ARGS(dev, blkstart, blklen)
+);
+
+DEFINE_EVENT(f2fs_discard, f2fs_issue_discard,
+
+ TP_PROTO(struct block_device *dev, block_t blkstart, block_t blklen),
+
+ TP_ARGS(dev, blkstart, blklen)
+);
+
+TRACE_EVENT(f2fs_issue_reset_zone,
+
+ TP_PROTO(struct block_device *dev, block_t blkstart),
+
+ TP_ARGS(dev, blkstart),
TP_STRUCT__entry(
__field(dev_t, dev)
- __field(bool, nobarrier)
- __field(bool, flush_merge)
+ __field(block_t, blkstart)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = dev->bd_dev;
+ __entry->blkstart = blkstart;
+ ),
+
+ TP_printk("dev = (%d,%d), reset zone at block = 0x%llx",
+ show_dev(__entry->dev),
+ (unsigned long long)__entry->blkstart)
+);
+
+TRACE_EVENT(f2fs_issue_flush,
+
+ TP_PROTO(struct block_device *dev, unsigned int nobarrier,
+ unsigned int flush_merge, int ret),
+
+ TP_ARGS(dev, nobarrier, flush_merge, ret),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(unsigned int, nobarrier)
+ __field(unsigned int, flush_merge)
+ __field(int, ret)
+ ),
+
+ TP_fast_assign(
+ __entry->dev = dev->bd_dev;
+ __entry->nobarrier = nobarrier;
+ __entry->flush_merge = flush_merge;
+ __entry->ret = ret;
+ ),
+
+ TP_printk("dev = (%d,%d), %s %s, ret = %d",
+ show_dev(__entry->dev),
+ __entry->nobarrier ? "skip (nobarrier)" : "issue",
+ __entry->flush_merge ? " with flush_merge" : "",
+ __entry->ret)
+);
+
+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->dev),
+ __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->nobarrier = nobarrier;
- __entry->flush_merge = flush_merge;
+ __entry->type = type;
+ __entry->count = count;
),
- TP_printk("dev = (%d,%d), %s %s",
- show_dev(__entry),
- __entry->nobarrier ? "skip (nobarrier)" : "issue",
- __entry->flush_merge ? " with flush_merge" : "")
+ TP_printk("dev = (%d,%d), %s, dirty count = %lld",
+ show_dev(__entry->dev),
+ 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 */
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 48e59f9..829a567 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -171,6 +171,52 @@
#define FS_IOC32_SETVERSION _IOW('v', 2, int)
/*
+ * File system encryption support
+ */
+/* Policy provided via an ioctl on the topmost directory */
+#define FS_KEY_DESCRIPTOR_SIZE 8
+
+#define FS_POLICY_FLAGS_PAD_4 0x00
+#define FS_POLICY_FLAGS_PAD_8 0x01
+#define FS_POLICY_FLAGS_PAD_16 0x02
+#define FS_POLICY_FLAGS_PAD_32 0x03
+#define FS_POLICY_FLAGS_PAD_MASK 0x03
+#define FS_POLICY_FLAGS_VALID 0x03
+
+/* Encryption algorithms */
+#define FS_ENCRYPTION_MODE_INVALID 0
+#define FS_ENCRYPTION_MODE_AES_256_XTS 1
+#define FS_ENCRYPTION_MODE_AES_256_GCM 2
+#define FS_ENCRYPTION_MODE_AES_256_CBC 3
+#define FS_ENCRYPTION_MODE_AES_256_CTS 4
+
+
+struct fscrypt_policy {
+ __u8 version;
+ __u8 contents_encryption_mode;
+ __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)
+
+/* Parameters for passing an encryption key into the kernel keyring */
+#define FS_KEY_DESC_PREFIX "fscrypt:"
+#define FS_KEY_DESC_PREFIX_SIZE 8
+
+/* Structure that userspace passes to the kernel keyring */
+#define FS_MAX_KEY_SIZE 64
+
+struct fscrypt_key {
+ __u32 mode;
+ __u8 raw[FS_MAX_KEY_SIZE];
+ __u32 size;
+};
+
+/*
* Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
*/
#define FS_SECRM_FL 0x00000001 /* Secure deletion */