aboutsummaryrefslogtreecommitdiff
path: root/fs/nilfs2
diff options
context:
space:
mode:
Diffstat (limited to 'fs/nilfs2')
-rw-r--r--fs/nilfs2/Kconfig3
-rw-r--r--fs/nilfs2/alloc.c63
-rw-r--r--fs/nilfs2/alloc.h2
-rw-r--r--fs/nilfs2/cpfile.c12
-rw-r--r--fs/nilfs2/dat.c12
-rw-r--r--fs/nilfs2/dir.c48
-rw-r--r--fs/nilfs2/file.c13
-rw-r--r--fs/nilfs2/ifile.c22
-rw-r--r--fs/nilfs2/ifile.h2
-rw-r--r--fs/nilfs2/inode.c71
-rw-r--r--fs/nilfs2/ioctl.c515
-rw-r--r--fs/nilfs2/mdt.c19
-rw-r--r--fs/nilfs2/namei.c4
-rw-r--r--fs/nilfs2/page.c72
-rw-r--r--fs/nilfs2/page.h3
-rw-r--r--fs/nilfs2/segbuf.c8
-rw-r--r--fs/nilfs2/segment.c25
-rw-r--r--fs/nilfs2/sufile.c295
-rw-r--r--fs/nilfs2/sufile.h2
-rw-r--r--fs/nilfs2/super.c59
-rw-r--r--fs/nilfs2/the_nilfs.c14
-rw-r--r--fs/nilfs2/the_nilfs.h4
22 files changed, 1145 insertions, 123 deletions
diff --git a/fs/nilfs2/Kconfig b/fs/nilfs2/Kconfig
index 251da07b2a1..80da8eb2739 100644
--- a/fs/nilfs2/Kconfig
+++ b/fs/nilfs2/Kconfig
@@ -1,6 +1,5 @@
config NILFS2_FS
- tristate "NILFS2 file system support (EXPERIMENTAL)"
- depends on EXPERIMENTAL
+ tristate "NILFS2 file system support"
select CRC32
help
NILFS2 is a log-structured file system (LFS) supporting continuous
diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c
index eed4d7b2624..741fd02e044 100644
--- a/fs/nilfs2/alloc.c
+++ b/fs/nilfs2/alloc.c
@@ -398,6 +398,69 @@ nilfs_palloc_rest_groups_in_desc_block(const struct inode *inode,
}
/**
+ * nilfs_palloc_count_desc_blocks - count descriptor blocks number
+ * @inode: inode of metadata file using this allocator
+ * @desc_blocks: descriptor blocks number [out]
+ */
+static int nilfs_palloc_count_desc_blocks(struct inode *inode,
+ unsigned long *desc_blocks)
+{
+ unsigned long blknum;
+ int ret;
+
+ ret = nilfs_bmap_last_key(NILFS_I(inode)->i_bmap, &blknum);
+ if (likely(!ret))
+ *desc_blocks = DIV_ROUND_UP(
+ blknum, NILFS_MDT(inode)->mi_blocks_per_desc_block);
+ return ret;
+}
+
+/**
+ * nilfs_palloc_mdt_file_can_grow - check potential opportunity for
+ * MDT file growing
+ * @inode: inode of metadata file using this allocator
+ * @desc_blocks: known current descriptor blocks count
+ */
+static inline bool nilfs_palloc_mdt_file_can_grow(struct inode *inode,
+ unsigned long desc_blocks)
+{
+ return (nilfs_palloc_groups_per_desc_block(inode) * desc_blocks) <
+ nilfs_palloc_groups_count(inode);
+}
+
+/**
+ * nilfs_palloc_count_max_entries - count max number of entries that can be
+ * described by descriptor blocks count
+ * @inode: inode of metadata file using this allocator
+ * @nused: current number of used entries
+ * @nmaxp: max number of entries [out]
+ */
+int nilfs_palloc_count_max_entries(struct inode *inode, u64 nused, u64 *nmaxp)
+{
+ unsigned long desc_blocks = 0;
+ u64 entries_per_desc_block, nmax;
+ int err;
+
+ err = nilfs_palloc_count_desc_blocks(inode, &desc_blocks);
+ if (unlikely(err))
+ return err;
+
+ entries_per_desc_block = (u64)nilfs_palloc_entries_per_group(inode) *
+ nilfs_palloc_groups_per_desc_block(inode);
+ nmax = entries_per_desc_block * desc_blocks;
+
+ if (nused == nmax &&
+ nilfs_palloc_mdt_file_can_grow(inode, desc_blocks))
+ nmax += entries_per_desc_block;
+
+ if (nused > nmax)
+ return -ERANGE;
+
+ *nmaxp = nmax;
+ return 0;
+}
+
+/**
* nilfs_palloc_prepare_alloc_entry - prepare to allocate a persistent object
* @inode: inode of metadata file using this allocator
* @req: nilfs_palloc_req structure exchanged for the allocation
diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h
index fb723810054..4bd6451b570 100644
--- a/fs/nilfs2/alloc.h
+++ b/fs/nilfs2/alloc.h
@@ -48,6 +48,8 @@ int nilfs_palloc_get_entry_block(struct inode *, __u64, int,
void *nilfs_palloc_block_get_entry(const struct inode *, __u64,
const struct buffer_head *, void *);
+int nilfs_palloc_count_max_entries(struct inode *, u64, u64 *);
+
/**
* nilfs_palloc_req - persistent allocator request and reply
* @pr_entry_nr: entry number (vblocknr or inode number)
diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c
index deaa3d33a0a..0d58075f34e 100644
--- a/fs/nilfs2/cpfile.c
+++ b/fs/nilfs2/cpfile.c
@@ -942,6 +942,18 @@ int nilfs_cpfile_read(struct super_block *sb, size_t cpsize,
struct inode *cpfile;
int err;
+ if (cpsize > sb->s_blocksize) {
+ printk(KERN_ERR
+ "NILFS: too large checkpoint size: %zu bytes.\n",
+ cpsize);
+ return -EINVAL;
+ } else if (cpsize < NILFS_MIN_CHECKPOINT_SIZE) {
+ printk(KERN_ERR
+ "NILFS: too small checkpoint size: %zu bytes.\n",
+ cpsize);
+ return -EINVAL;
+ }
+
cpfile = nilfs_iget_locked(sb, NULL, NILFS_CPFILE_INO);
if (unlikely(!cpfile))
return -ENOMEM;
diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c
index fa0f80308c2..0d5fada9119 100644
--- a/fs/nilfs2/dat.c
+++ b/fs/nilfs2/dat.c
@@ -484,6 +484,18 @@ int nilfs_dat_read(struct super_block *sb, size_t entry_size,
struct nilfs_dat_info *di;
int err;
+ if (entry_size > sb->s_blocksize) {
+ printk(KERN_ERR
+ "NILFS: too large DAT entry size: %zu bytes.\n",
+ entry_size);
+ return -EINVAL;
+ } else if (entry_size < NILFS_MIN_DAT_ENTRY_SIZE) {
+ printk(KERN_ERR
+ "NILFS: too small DAT entry size: %zu bytes.\n",
+ entry_size);
+ return -EINVAL;
+ }
+
dat = nilfs_iget_locked(sb, NULL, NILFS_DAT_INO);
if (unlikely(!dat))
return -ENOMEM;
diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c
index df1a7fb238d..197a63e9d10 100644
--- a/fs/nilfs2/dir.c
+++ b/fs/nilfs2/dir.c
@@ -256,22 +256,18 @@ static void nilfs_set_de_type(struct nilfs_dir_entry *de, struct inode *inode)
de->file_type = nilfs_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
}
-static int nilfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
+static int nilfs_readdir(struct file *file, struct dir_context *ctx)
{
- loff_t pos = filp->f_pos;
- struct inode *inode = filp->f_dentry->d_inode;
+ loff_t pos = ctx->pos;
+ struct inode *inode = file_inode(file);
struct super_block *sb = inode->i_sb;
unsigned int offset = pos & ~PAGE_CACHE_MASK;
unsigned long n = pos >> PAGE_CACHE_SHIFT;
unsigned long npages = dir_pages(inode);
/* unsigned chunk_mask = ~(nilfs_chunk_size(inode)-1); */
- unsigned char *types = NULL;
- int ret;
if (pos > inode->i_size - NILFS_DIR_REC_LEN(1))
- goto success;
-
- types = nilfs_filetype_table;
+ return 0;
for ( ; n < npages; n++, offset = 0) {
char *kaddr, *limit;
@@ -281,9 +277,8 @@ static int nilfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
if (IS_ERR(page)) {
nilfs_error(sb, __func__, "bad page in #%lu",
inode->i_ino);
- filp->f_pos += PAGE_CACHE_SIZE - offset;
- ret = -EIO;
- goto done;
+ ctx->pos += PAGE_CACHE_SIZE - offset;
+ return -EIO;
}
kaddr = page_address(page);
de = (struct nilfs_dir_entry *)(kaddr + offset);
@@ -293,35 +288,28 @@ static int nilfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
if (de->rec_len == 0) {
nilfs_error(sb, __func__,
"zero-length directory entry");
- ret = -EIO;
nilfs_put_page(page);
- goto done;
+ return -EIO;
}
if (de->inode) {
- int over;
- unsigned char d_type = DT_UNKNOWN;
+ unsigned char t;
- if (types && de->file_type < NILFS_FT_MAX)
- d_type = types[de->file_type];
+ if (de->file_type < NILFS_FT_MAX)
+ t = nilfs_filetype_table[de->file_type];
+ else
+ t = DT_UNKNOWN;
- offset = (char *)de - kaddr;
- over = filldir(dirent, de->name, de->name_len,
- (n<<PAGE_CACHE_SHIFT) | offset,
- le64_to_cpu(de->inode), d_type);
- if (over) {
+ if (!dir_emit(ctx, de->name, de->name_len,
+ le64_to_cpu(de->inode), t)) {
nilfs_put_page(page);
- goto success;
+ return 0;
}
}
- filp->f_pos += nilfs_rec_len_from_disk(de->rec_len);
+ ctx->pos += nilfs_rec_len_from_disk(de->rec_len);
}
nilfs_put_page(page);
}
-
-success:
- ret = 0;
-done:
- return ret;
+ return 0;
}
/*
@@ -678,7 +666,7 @@ not_empty:
const struct file_operations nilfs_dir_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
- .readdir = nilfs_readdir,
+ .iterate = nilfs_readdir,
.unlocked_ioctl = nilfs_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = nilfs_compat_ioctl,
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index 61946883025..24978153c0c 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -67,7 +67,7 @@ int nilfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
- struct inode *inode = vma->vm_file->f_dentry->d_inode;
+ struct inode *inode = file_inode(vma->vm_file);
struct nilfs_transaction_info ti;
int ret = 0;
@@ -126,7 +126,7 @@ static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
nilfs_transaction_commit(inode->i_sb);
mapped:
- wait_on_page_writeback(page);
+ wait_for_stable_page(page);
out:
sb_end_pagefault(inode->i_sb);
return block_page_mkwrite_return(ret);
@@ -134,6 +134,7 @@ static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
static const struct vm_operations_struct nilfs_file_vm_ops = {
.fault = filemap_fault,
+ .map_pages = filemap_map_pages,
.page_mkwrite = nilfs_page_mkwrite,
.remap_pages = generic_file_remap_pages,
};
@@ -151,10 +152,10 @@ static int nilfs_file_mmap(struct file *file, struct vm_area_struct *vma)
*/
const struct file_operations nilfs_file_operations = {
.llseek = generic_file_llseek,
- .read = do_sync_read,
- .write = do_sync_write,
- .aio_read = generic_file_aio_read,
- .aio_write = generic_file_aio_write,
+ .read = new_sync_read,
+ .write = new_sync_write,
+ .read_iter = generic_file_read_iter,
+ .write_iter = generic_file_write_iter,
.unlocked_ioctl = nilfs_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = nilfs_compat_ioctl,
diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c
index d8e65bde083..6548c7851b4 100644
--- a/fs/nilfs2/ifile.c
+++ b/fs/nilfs2/ifile.c
@@ -160,6 +160,28 @@ int nilfs_ifile_get_inode_block(struct inode *ifile, ino_t ino,
}
/**
+ * nilfs_ifile_count_free_inodes - calculate free inodes count
+ * @ifile: ifile inode
+ * @nmaxinodes: current maximum of available inodes count [out]
+ * @nfreeinodes: free inodes count [out]
+ */
+int nilfs_ifile_count_free_inodes(struct inode *ifile,
+ u64 *nmaxinodes, u64 *nfreeinodes)
+{
+ u64 nused;
+ int err;
+
+ *nmaxinodes = 0;
+ *nfreeinodes = 0;
+
+ nused = atomic64_read(&NILFS_I(ifile)->i_root->inodes_count);
+ err = nilfs_palloc_count_max_entries(ifile, nused, nmaxinodes);
+ if (likely(!err))
+ *nfreeinodes = *nmaxinodes - nused;
+ return err;
+}
+
+/**
* nilfs_ifile_read - read or get ifile inode
* @sb: super block instance
* @root: root object
diff --git a/fs/nilfs2/ifile.h b/fs/nilfs2/ifile.h
index 59b6f2b51df..679674d1337 100644
--- a/fs/nilfs2/ifile.h
+++ b/fs/nilfs2/ifile.h
@@ -49,6 +49,8 @@ int nilfs_ifile_create_inode(struct inode *, ino_t *, struct buffer_head **);
int nilfs_ifile_delete_inode(struct inode *, ino_t);
int nilfs_ifile_get_inode_block(struct inode *, ino_t, struct buffer_head **);
+int nilfs_ifile_count_free_inodes(struct inode *, u64 *, u64 *);
+
int nilfs_ifile_read(struct super_block *sb, struct nilfs_root *root,
size_t inode_size, struct nilfs_inode *raw_inode,
struct inode **inodep);
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 6b49f14eac8..6252b173a46 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -25,7 +25,7 @@
#include <linux/gfp.h>
#include <linux/mpage.h>
#include <linux/writeback.h>
-#include <linux/uio.h>
+#include <linux/aio.h>
#include "nilfs.h"
#include "btnode.h"
#include "segment.h"
@@ -54,7 +54,7 @@ void nilfs_inode_add_blocks(struct inode *inode, int n)
inode_add_bytes(inode, (1 << inode->i_blkbits) * n);
if (root)
- atomic_add(n, &root->blocks_count);
+ atomic64_add(n, &root->blocks_count);
}
void nilfs_inode_sub_blocks(struct inode *inode, int n)
@@ -63,7 +63,7 @@ void nilfs_inode_sub_blocks(struct inode *inode, int n)
inode_sub_bytes(inode, (1 << inode->i_blkbits) * n);
if (root)
- atomic_sub(n, &root->blocks_count);
+ atomic64_sub(n, &root->blocks_count);
}
/**
@@ -175,6 +175,11 @@ static int nilfs_writepages(struct address_space *mapping,
struct inode *inode = mapping->host;
int err = 0;
+ if (inode->i_sb->s_flags & MS_RDONLY) {
+ nilfs_clear_dirty_pages(mapping, false);
+ return -EROFS;
+ }
+
if (wbc->sync_mode == WB_SYNC_ALL)
err = nilfs_construct_dsync_segment(inode->i_sb, inode,
wbc->range_start,
@@ -187,6 +192,18 @@ static int nilfs_writepage(struct page *page, struct writeback_control *wbc)
struct inode *inode = page->mapping->host;
int err;
+ if (inode->i_sb->s_flags & MS_RDONLY) {
+ /*
+ * It means that filesystem was remounted in read-only
+ * mode because of error or metadata corruption. But we
+ * have dirty pages that try to be flushed in background.
+ * So, here we simply discard this dirty page.
+ */
+ nilfs_clear_dirty_page(page, false);
+ unlock_page(page);
+ return -EROFS;
+ }
+
redirty_page_for_writepage(wbc, page);
unlock_page(page);
@@ -202,13 +219,32 @@ static int nilfs_writepage(struct page *page, struct writeback_control *wbc)
static int nilfs_set_page_dirty(struct page *page)
{
- int ret = __set_page_dirty_buffers(page);
+ int ret = __set_page_dirty_nobuffers(page);
- if (ret) {
+ if (page_has_buffers(page)) {
struct inode *inode = page->mapping->host;
- unsigned nr_dirty = 1 << (PAGE_SHIFT - inode->i_blkbits);
+ unsigned nr_dirty = 0;
+ struct buffer_head *bh, *head;
- nilfs_set_file_dirty(inode, nr_dirty);
+ /*
+ * This page is locked by callers, and no other thread
+ * concurrently marks its buffers dirty since they are
+ * only dirtied through routines in fs/buffer.c in
+ * which call sites of mark_buffer_dirty are protected
+ * by page lock.
+ */
+ bh = head = page_buffers(page);
+ do {
+ /* Do not mark hole blocks dirty */
+ if (buffer_dirty(bh) || !buffer_mapped(bh))
+ continue;
+
+ set_buffer_dirty(bh);
+ nr_dirty++;
+ } while (bh = bh->b_this_page, bh != head);
+
+ if (nr_dirty)
+ nilfs_set_file_dirty(inode, nr_dirty);
}
return ret;
}
@@ -218,7 +254,7 @@ void nilfs_write_failed(struct address_space *mapping, loff_t to)
struct inode *inode = mapping->host;
if (to > inode->i_size) {
- truncate_pagecache(inode, to, inode->i_size);
+ truncate_pagecache(inode, inode->i_size);
nilfs_truncate(inode);
}
}
@@ -262,19 +298,20 @@ static int nilfs_write_end(struct file *file, struct address_space *mapping,
}
static ssize_t
-nilfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
- loff_t offset, unsigned long nr_segs)
+nilfs_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 inode *inode = file->f_mapping->host;
+ size_t count = iov_iter_count(iter);
ssize_t size;
if (rw == WRITE)
return 0;
/* Needs synchronization with the cleaner */
- size = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
+ size = blockdev_direct_IO(rw, iocb, inode, iter, offset,
nilfs_get_block);
/*
@@ -283,7 +320,7 @@ nilfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
*/
if (unlikely((rw & WRITE) && size < 0)) {
loff_t isize = i_size_read(inode);
- loff_t end = offset + iov_length(iov, nr_segs);
+ loff_t end = offset + count;
if (end > isize)
nilfs_write_failed(mapping, end);
@@ -333,7 +370,7 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
goto failed_ifile_create_inode;
/* reference count of i_bh inherits from nilfs_mdt_read_block() */
- atomic_inc(&root->inodes_count);
+ atomic64_inc(&root->inodes_count);
inode_init_owner(inode, dir, mode);
inode->i_ino = ino;
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
@@ -747,16 +784,14 @@ void nilfs_evict_inode(struct inode *inode)
int ret;
if (inode->i_nlink || !ii->i_root || unlikely(is_bad_inode(inode))) {
- if (inode->i_data.nrpages)
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
nilfs_clear_inode(inode);
return;
}
nilfs_transaction_begin(sb, &ti, 0); /* never fails */
- if (inode->i_data.nrpages)
- truncate_inode_pages(&inode->i_data, 0);
+ truncate_inode_pages_final(&inode->i_data);
/* TODO: some of the following operations may fail. */
nilfs_truncate_bmap(ii, 0);
@@ -765,7 +800,7 @@ void nilfs_evict_inode(struct inode *inode)
ret = nilfs_ifile_delete_inode(ii->i_root->ifile, inode->i_ino);
if (!ret)
- atomic_dec(&ii->i_root->inodes_count);
+ atomic64_dec(&ii->i_root->inodes_count);
nilfs_clear_inode(inode);
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index fdb18076948..422fb54b737 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -37,7 +37,26 @@
#include "sufile.h"
#include "dat.h"
-
+/**
+ * nilfs_ioctl_wrap_copy - wrapping function of get/set metadata info
+ * @nilfs: nilfs object
+ * @argv: vector of arguments from userspace
+ * @dir: set of direction flags
+ * @dofunc: concrete function of get/set metadata info
+ *
+ * Description: nilfs_ioctl_wrap_copy() gets/sets metadata info by means of
+ * calling dofunc() function on the basis of @argv argument.
+ *
+ * Return Value: On success, 0 is returned and requested metadata info
+ * is copied into userspace. On error, one of the following
+ * negative error codes is returned.
+ *
+ * %-EINVAL - Invalid arguments from userspace.
+ *
+ * %-ENOMEM - Insufficient amount of memory available.
+ *
+ * %-EFAULT - Failure during execution of requested operation.
+ */
static int nilfs_ioctl_wrap_copy(struct the_nilfs *nilfs,
struct nilfs_argv *argv, int dir,
ssize_t (*dofunc)(struct the_nilfs *,
@@ -57,6 +76,14 @@ static int nilfs_ioctl_wrap_copy(struct the_nilfs *nilfs,
if (argv->v_size > PAGE_SIZE)
return -EINVAL;
+ /*
+ * Reject pairs of a start item position (argv->v_index) and a
+ * total count (argv->v_nmembs) which leads position 'pos' to
+ * overflow by the increment at the end of the loop.
+ */
+ if (argv->v_index > ~(__u64)0 - argv->v_nmembs)
+ return -EINVAL;
+
buf = (void *)__get_free_pages(GFP_NOFS, 0);
if (unlikely(!buf))
return -ENOMEM;
@@ -99,6 +126,9 @@ static int nilfs_ioctl_wrap_copy(struct the_nilfs *nilfs,
return ret;
}
+/**
+ * nilfs_ioctl_getflags - ioctl to support lsattr
+ */
static int nilfs_ioctl_getflags(struct inode *inode, void __user *argp)
{
unsigned int flags = NILFS_I(inode)->i_flags & FS_FL_USER_VISIBLE;
@@ -106,6 +136,9 @@ static int nilfs_ioctl_getflags(struct inode *inode, void __user *argp)
return put_user(flags, (int __user *)argp);
}
+/**
+ * nilfs_ioctl_setflags - ioctl to support chattr
+ */
static int nilfs_ioctl_setflags(struct inode *inode, struct file *filp,
void __user *argp)
{
@@ -158,11 +191,33 @@ out:
return ret;
}
+/**
+ * nilfs_ioctl_getversion - get info about a file's version (generation number)
+ */
static int nilfs_ioctl_getversion(struct inode *inode, void __user *argp)
{
return put_user(inode->i_generation, (int __user *)argp);
}
+/**
+ * nilfs_ioctl_change_cpmode - change checkpoint mode (checkpoint/snapshot)
+ * @inode: inode object
+ * @filp: file object
+ * @cmd: ioctl's request code
+ * @argp: pointer on argument from userspace
+ *
+ * Description: nilfs_ioctl_change_cpmode() function changes mode of
+ * given checkpoint between checkpoint and snapshot state. This ioctl
+ * is used in chcp and mkcp utilities.
+ *
+ * Return Value: On success, 0 is returned and mode of a checkpoint is
+ * changed. On error, one of the following negative error codes
+ * is returned.
+ *
+ * %-EPERM - Operation not permitted.
+ *
+ * %-EFAULT - Failure during checkpoint mode changing.
+ */
static int nilfs_ioctl_change_cpmode(struct inode *inode, struct file *filp,
unsigned int cmd, void __user *argp)
{
@@ -198,6 +253,25 @@ out:
return ret;
}
+/**
+ * nilfs_ioctl_delete_checkpoint - remove checkpoint
+ * @inode: inode object
+ * @filp: file object
+ * @cmd: ioctl's request code
+ * @argp: pointer on argument from userspace
+ *
+ * Description: nilfs_ioctl_delete_checkpoint() function removes
+ * checkpoint from NILFS2 file system. This ioctl is used in rmcp
+ * utility.
+ *
+ * Return Value: On success, 0 is returned and a checkpoint is
+ * removed. On error, one of the following negative error codes
+ * is returned.
+ *
+ * %-EPERM - Operation not permitted.
+ *
+ * %-EFAULT - Failure during checkpoint removing.
+ */
static int
nilfs_ioctl_delete_checkpoint(struct inode *inode, struct file *filp,
unsigned int cmd, void __user *argp)
@@ -229,6 +303,21 @@ out:
return ret;
}
+/**
+ * nilfs_ioctl_do_get_cpinfo - callback method getting info about checkpoints
+ * @nilfs: nilfs object
+ * @posp: pointer on array of checkpoint's numbers
+ * @flags: checkpoint mode (checkpoint or snapshot)
+ * @buf: buffer for storing checkponts' info
+ * @size: size in bytes of one checkpoint info item in array
+ * @nmembs: number of checkpoints in array (numbers and infos)
+ *
+ * Description: nilfs_ioctl_do_get_cpinfo() function returns info about
+ * requested checkpoints. The NILFS_IOCTL_GET_CPINFO ioctl is used in
+ * lscp utility and by nilfs_cleanerd daemon.
+ *
+ * Return value: count of nilfs_cpinfo structures in output buffer.
+ */
static ssize_t
nilfs_ioctl_do_get_cpinfo(struct the_nilfs *nilfs, __u64 *posp, int flags,
void *buf, size_t size, size_t nmembs)
@@ -242,6 +331,27 @@ nilfs_ioctl_do_get_cpinfo(struct the_nilfs *nilfs, __u64 *posp, int flags,
return ret;
}
+/**
+ * nilfs_ioctl_get_cpstat - get checkpoints statistics
+ * @inode: inode object
+ * @filp: file object
+ * @cmd: ioctl's request code
+ * @argp: pointer on argument from userspace
+ *
+ * Description: nilfs_ioctl_get_cpstat() returns information about checkpoints.
+ * The NILFS_IOCTL_GET_CPSTAT ioctl is used by lscp, rmcp utilities
+ * and by nilfs_cleanerd daemon.
+ *
+ * Return Value: On success, 0 is returned, and checkpoints information is
+ * copied into userspace pointer @argp. On error, one of the following
+ * negative error codes is returned.
+ *
+ * %-EIO - I/O error.
+ *
+ * %-ENOMEM - Insufficient amount of memory available.
+ *
+ * %-EFAULT - Failure during getting checkpoints statistics.
+ */
static int nilfs_ioctl_get_cpstat(struct inode *inode, struct file *filp,
unsigned int cmd, void __user *argp)
{
@@ -260,6 +370,21 @@ static int nilfs_ioctl_get_cpstat(struct inode *inode, struct file *filp,
return ret;
}
+/**
+ * nilfs_ioctl_do_get_suinfo - callback method getting segment usage info
+ * @nilfs: nilfs object
+ * @posp: pointer on array of segment numbers
+ * @flags: *not used*
+ * @buf: buffer for storing suinfo array
+ * @size: size in bytes of one suinfo item in array
+ * @nmembs: count of segment numbers and suinfos in array
+ *
+ * Description: nilfs_ioctl_do_get_suinfo() function returns segment usage
+ * info about requested segments. The NILFS_IOCTL_GET_SUINFO ioctl is used
+ * in lssu, nilfs_resize utilities and by nilfs_cleanerd daemon.
+ *
+ * Return value: count of nilfs_suinfo structures in output buffer.
+ */
static ssize_t
nilfs_ioctl_do_get_suinfo(struct the_nilfs *nilfs, __u64 *posp, int flags,
void *buf, size_t size, size_t nmembs)
@@ -273,6 +398,27 @@ nilfs_ioctl_do_get_suinfo(struct the_nilfs *nilfs, __u64 *posp, int flags,
return ret;
}
+/**
+ * nilfs_ioctl_get_sustat - get segment usage statistics
+ * @inode: inode object
+ * @filp: file object
+ * @cmd: ioctl's request code
+ * @argp: pointer on argument from userspace
+ *
+ * Description: nilfs_ioctl_get_sustat() returns segment usage statistics.
+ * The NILFS_IOCTL_GET_SUSTAT ioctl is used in lssu, nilfs_resize utilities
+ * and by nilfs_cleanerd daemon.
+ *
+ * Return Value: On success, 0 is returned, and segment usage information is
+ * copied into userspace pointer @argp. On error, one of the following
+ * negative error codes is returned.
+ *
+ * %-EIO - I/O error.
+ *
+ * %-ENOMEM - Insufficient amount of memory available.
+ *
+ * %-EFAULT - Failure during getting segment usage statistics.
+ */
static int nilfs_ioctl_get_sustat(struct inode *inode, struct file *filp,
unsigned int cmd, void __user *argp)
{
@@ -291,6 +437,21 @@ static int nilfs_ioctl_get_sustat(struct inode *inode, struct file *filp,
return ret;
}
+/**
+ * nilfs_ioctl_do_get_vinfo - callback method getting virtual blocks info
+ * @nilfs: nilfs object
+ * @posp: *not used*
+ * @flags: *not used*
+ * @buf: buffer for storing array of nilfs_vinfo structures
+ * @size: size in bytes of one vinfo item in array
+ * @nmembs: count of vinfos in array
+ *
+ * Description: nilfs_ioctl_do_get_vinfo() function returns information
+ * on virtual block addresses. The NILFS_IOCTL_GET_VINFO ioctl is used
+ * by nilfs_cleanerd daemon.
+ *
+ * Return value: count of nilfs_vinfo structures in output buffer.
+ */
static ssize_t
nilfs_ioctl_do_get_vinfo(struct the_nilfs *nilfs, __u64 *posp, int flags,
void *buf, size_t size, size_t nmembs)
@@ -303,6 +464,21 @@ nilfs_ioctl_do_get_vinfo(struct the_nilfs *nilfs, __u64 *posp, int flags,
return ret;
}
+/**
+ * nilfs_ioctl_do_get_bdescs - callback method getting disk block descriptors
+ * @nilfs: nilfs object
+ * @posp: *not used*
+ * @flags: *not used*
+ * @buf: buffer for storing array of nilfs_bdesc structures
+ * @size: size in bytes of one bdesc item in array
+ * @nmembs: count of bdescs in array
+ *
+ * Description: nilfs_ioctl_do_get_bdescs() function returns information
+ * about descriptors of disk block numbers. The NILFS_IOCTL_GET_BDESCS ioctl
+ * is used by nilfs_cleanerd daemon.
+ *
+ * Return value: count of nilfs_bdescs structures in output buffer.
+ */
static ssize_t
nilfs_ioctl_do_get_bdescs(struct the_nilfs *nilfs, __u64 *posp, int flags,
void *buf, size_t size, size_t nmembs)
@@ -329,6 +505,29 @@ nilfs_ioctl_do_get_bdescs(struct the_nilfs *nilfs, __u64 *posp, int flags,
return nmembs;
}
+/**
+ * nilfs_ioctl_get_bdescs - get disk block descriptors
+ * @inode: inode object
+ * @filp: file object
+ * @cmd: ioctl's request code
+ * @argp: pointer on argument from userspace
+ *
+ * Description: nilfs_ioctl_do_get_bdescs() function returns information
+ * about descriptors of disk block numbers. The NILFS_IOCTL_GET_BDESCS ioctl
+ * is used by nilfs_cleanerd daemon.
+ *
+ * Return Value: On success, 0 is returned, and disk block descriptors are
+ * copied into userspace pointer @argp. On error, one of the following
+ * negative error codes is returned.
+ *
+ * %-EINVAL - Invalid arguments from userspace.
+ *
+ * %-EIO - I/O error.
+ *
+ * %-ENOMEM - Insufficient amount of memory available.
+ *
+ * %-EFAULT - Failure during getting disk block descriptors.
+ */
static int nilfs_ioctl_get_bdescs(struct inode *inode, struct file *filp,
unsigned int cmd, void __user *argp)
{
@@ -352,6 +551,26 @@ static int nilfs_ioctl_get_bdescs(struct inode *inode, struct file *filp,
return ret;
}
+/**
+ * nilfs_ioctl_move_inode_block - prepare data/node block for moving by GC
+ * @inode: inode object
+ * @vdesc: descriptor of virtual block number
+ * @buffers: list of moving buffers
+ *
+ * Description: nilfs_ioctl_move_inode_block() function registers data/node
+ * buffer in the GC pagecache and submit read request.
+ *
+ * Return Value: On success, 0 is returned. On error, one of the following
+ * negative error codes is returned.
+ *
+ * %-EIO - I/O error.
+ *
+ * %-ENOMEM - Insufficient amount of memory available.
+ *
+ * %-ENOENT - Requested block doesn't exist.
+ *
+ * %-EEXIST - Blocks conflict is detected.
+ */
static int nilfs_ioctl_move_inode_block(struct inode *inode,
struct nilfs_vdesc *vdesc,
struct list_head *buffers)
@@ -397,6 +616,19 @@ static int nilfs_ioctl_move_inode_block(struct inode *inode,
return 0;
}
+/**
+ * nilfs_ioctl_move_blocks - move valid inode's blocks during garbage collection
+ * @sb: superblock object
+ * @argv: vector of arguments from userspace
+ * @buf: array of nilfs_vdesc structures
+ *
+ * Description: nilfs_ioctl_move_blocks() function reads valid data/node
+ * blocks that garbage collector specified with the array of nilfs_vdesc
+ * structures and stores them into page caches of GC inodes.
+ *
+ * Return Value: Number of processed nilfs_vdesc structures or
+ * error code, otherwise.
+ */
static int nilfs_ioctl_move_blocks(struct super_block *sb,
struct nilfs_argv *argv, void *buf)
{
@@ -462,6 +694,25 @@ static int nilfs_ioctl_move_blocks(struct super_block *sb,
return ret;
}
+/**
+ * nilfs_ioctl_delete_checkpoints - delete checkpoints
+ * @nilfs: nilfs object
+ * @argv: vector of arguments from userspace
+ * @buf: array of periods of checkpoints numbers
+ *
+ * Description: nilfs_ioctl_delete_checkpoints() function deletes checkpoints
+ * in the period from p_start to p_end, excluding p_end itself. The checkpoints
+ * which have been already deleted are ignored.
+ *
+ * Return Value: Number of processed nilfs_period structures or
+ * error code, otherwise.
+ *
+ * %-EIO - I/O error.
+ *
+ * %-ENOMEM - Insufficient amount of memory available.
+ *
+ * %-EINVAL - invalid checkpoints.
+ */
static int nilfs_ioctl_delete_checkpoints(struct the_nilfs *nilfs,
struct nilfs_argv *argv, void *buf)
{
@@ -479,6 +730,24 @@ static int nilfs_ioctl_delete_checkpoints(struct the_nilfs *nilfs,
return nmembs;
}
+/**
+ * nilfs_ioctl_free_vblocknrs - free virtual block numbers
+ * @nilfs: nilfs object
+ * @argv: vector of arguments from userspace
+ * @buf: array of virtual block numbers
+ *
+ * Description: nilfs_ioctl_free_vblocknrs() function frees
+ * the virtual block numbers specified by @buf and @argv->v_nmembs.
+ *
+ * Return Value: Number of processed virtual block numbers or
+ * error code, otherwise.
+ *
+ * %-EIO - I/O error.
+ *
+ * %-ENOMEM - Insufficient amount of memory available.
+ *
+ * %-ENOENT - The virtual block number have not been allocated.
+ */
static int nilfs_ioctl_free_vblocknrs(struct the_nilfs *nilfs,
struct nilfs_argv *argv, void *buf)
{
@@ -490,6 +759,24 @@ static int nilfs_ioctl_free_vblocknrs(struct the_nilfs *nilfs,
return (ret < 0) ? ret : nmembs;
}
+/**
+ * nilfs_ioctl_mark_blocks_dirty - mark blocks dirty
+ * @nilfs: nilfs object
+ * @argv: vector of arguments from userspace
+ * @buf: array of block descriptors
+ *
+ * Description: nilfs_ioctl_mark_blocks_dirty() function marks
+ * metadata file or data blocks as dirty.
+ *
+ * Return Value: Number of processed block descriptors or
+ * error code, otherwise.
+ *
+ * %-ENOMEM - Insufficient memory available.
+ *
+ * %-EIO - I/O error
+ *
+ * %-ENOENT - the specified block does not exist (hole block)
+ */
static int nilfs_ioctl_mark_blocks_dirty(struct the_nilfs *nilfs,
struct nilfs_argv *argv, void *buf)
{
@@ -571,6 +858,20 @@ int nilfs_ioctl_prepare_clean_segments(struct the_nilfs *nilfs,
return ret;
}
+/**
+ * nilfs_ioctl_clean_segments - clean segments
+ * @inode: inode object
+ * @filp: file object
+ * @cmd: ioctl's request code
+ * @argp: pointer on argument from userspace
+ *
+ * Description: nilfs_ioctl_clean_segments() function makes garbage
+ * collection operation in the environment of requested parameters
+ * from userspace. The NILFS_IOCTL_CLEAN_SEGMENTS ioctl is used by
+ * nilfs_cleanerd daemon.
+ *
+ * Return Value: On success, 0 is returned or error code, otherwise.
+ */
static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp,
unsigned int cmd, void __user *argp)
{
@@ -664,8 +965,11 @@ static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp,
if (ret < 0)
printk(KERN_ERR "NILFS: GC failed during preparation: "
"cannot read source blocks: err=%d\n", ret);
- else
+ else {
+ if (nilfs_sb_need_update(nilfs))
+ set_nilfs_discontinued(nilfs);
ret = nilfs_clean_segments(inode->i_sb, argv, kbufs);
+ }
nilfs_remove_all_gcinodes(nilfs);
clear_nilfs_gc_running(nilfs);
@@ -679,6 +983,33 @@ out:
return ret;
}
+/**
+ * nilfs_ioctl_sync - make a checkpoint
+ * @inode: inode object
+ * @filp: file object
+ * @cmd: ioctl's request code
+ * @argp: pointer on argument from userspace
+ *
+ * Description: nilfs_ioctl_sync() function constructs a logical segment
+ * for checkpointing. This function guarantees that all modified data
+ * and metadata are written out to the device when it successfully
+ * returned.
+ *
+ * Return Value: On success, 0 is retured. On errors, one of the following
+ * negative error code is returned.
+ *
+ * %-EROFS - Read only filesystem.
+ *
+ * %-EIO - I/O error
+ *
+ * %-ENOSPC - No space left on device (only in a panic state).
+ *
+ * %-ERESTARTSYS - Interrupted.
+ *
+ * %-ENOMEM - Insufficient memory available.
+ *
+ * %-EFAULT - Failure during execution of requested operation.
+ */
static int nilfs_ioctl_sync(struct inode *inode, struct file *filp,
unsigned int cmd, void __user *argp)
{
@@ -707,6 +1038,14 @@ static int nilfs_ioctl_sync(struct inode *inode, struct file *filp,
return 0;
}
+/**
+ * nilfs_ioctl_resize - resize NILFS2 volume
+ * @inode: inode object
+ * @filp: file object
+ * @argp: pointer on argument from userspace
+ *
+ * Return Value: On success, 0 is returned or error code, otherwise.
+ */
static int nilfs_ioctl_resize(struct inode *inode, struct file *filp,
void __user *argp)
{
@@ -732,6 +1071,59 @@ out:
return ret;
}
+/**
+ * nilfs_ioctl_trim_fs() - trim ioctl handle function
+ * @inode: inode object
+ * @argp: pointer on argument from userspace
+ *
+ * Decription: nilfs_ioctl_trim_fs is the FITRIM ioctl handle function. It
+ * checks the arguments from userspace and calls nilfs_sufile_trim_fs, which
+ * performs the actual trim operation.
+ *
+ * Return Value: On success, 0 is returned or negative error code, otherwise.
+ */
+static int nilfs_ioctl_trim_fs(struct inode *inode, void __user *argp)
+{
+ struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
+ struct request_queue *q = bdev_get_queue(nilfs->ns_bdev);
+ struct fstrim_range range;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (!blk_queue_discard(q))
+ return -EOPNOTSUPP;
+
+ if (copy_from_user(&range, argp, sizeof(range)))
+ return -EFAULT;
+
+ range.minlen = max_t(u64, range.minlen, q->limits.discard_granularity);
+
+ down_read(&nilfs->ns_segctor_sem);
+ ret = nilfs_sufile_trim_fs(nilfs->ns_sufile, &range);
+ up_read(&nilfs->ns_segctor_sem);
+
+ if (ret < 0)
+ return ret;
+
+ if (copy_to_user(argp, &range, sizeof(range)))
+ return -EFAULT;
+
+ return 0;
+}
+
+/**
+ * nilfs_ioctl_set_alloc_range - limit range of segments to be allocated
+ * @inode: inode object
+ * @argp: pointer on argument from userspace
+ *
+ * Decription: nilfs_ioctl_set_alloc_range() function defines lower limit
+ * of segments in bytes and upper limit of segments in bytes.
+ * The NILFS_IOCTL_SET_ALLOC_RANGE is used by nilfs_resize utility.
+ *
+ * Return Value: On success, 0 is returned or error code, otherwise.
+ */
static int nilfs_ioctl_set_alloc_range(struct inode *inode, void __user *argp)
{
struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
@@ -764,6 +1156,28 @@ out:
return ret;
}
+/**
+ * nilfs_ioctl_get_info - wrapping function of get metadata info
+ * @inode: inode object
+ * @filp: file object
+ * @cmd: ioctl's request code
+ * @argp: pointer on argument from userspace
+ * @membsz: size of an item in bytes
+ * @dofunc: concrete function of getting metadata info
+ *
+ * Description: nilfs_ioctl_get_info() gets metadata info by means of
+ * calling dofunc() function.
+ *
+ * Return Value: On success, 0 is returned and requested metadata info
+ * is copied into userspace. On error, one of the following
+ * negative error codes is returned.
+ *
+ * %-EINVAL - Invalid arguments from userspace.
+ *
+ * %-ENOMEM - Insufficient amount of memory available.
+ *
+ * %-EFAULT - Failure during execution of requested operation.
+ */
static int nilfs_ioctl_get_info(struct inode *inode, struct file *filp,
unsigned int cmd, void __user *argp,
size_t membsz,
@@ -791,9 +1205,98 @@ static int nilfs_ioctl_get_info(struct inode *inode, struct file *filp,
return ret;
}
+/**
+ * nilfs_ioctl_set_suinfo - set segment usage info
+ * @inode: inode object
+ * @filp: file object
+ * @cmd: ioctl's request code
+ * @argp: pointer on argument from userspace
+ *
+ * Description: Expects an array of nilfs_suinfo_update structures
+ * encapsulated in nilfs_argv and updates the segment usage info
+ * according to the flags in nilfs_suinfo_update.
+ *
+ * Return Value: On success, 0 is returned. On error, one of the
+ * following negative error codes is returned.
+ *
+ * %-EPERM - Not enough permissions
+ *
+ * %-EFAULT - Error copying input data
+ *
+ * %-EIO - I/O error.
+ *
+ * %-ENOMEM - Insufficient amount of memory available.
+ *
+ * %-EINVAL - Invalid values in input (segment number, flags or nblocks)
+ */
+static int nilfs_ioctl_set_suinfo(struct inode *inode, struct file *filp,
+ unsigned int cmd, void __user *argp)
+{
+ struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
+ struct nilfs_transaction_info ti;
+ struct nilfs_argv argv;
+ size_t len;
+ void __user *base;
+ void *kbuf;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ ret = -EFAULT;
+ if (copy_from_user(&argv, argp, sizeof(argv)))
+ goto out;
+
+ ret = -EINVAL;
+ if (argv.v_size < sizeof(struct nilfs_suinfo_update))
+ goto out;
+
+ if (argv.v_nmembs > nilfs->ns_nsegments)
+ goto out;
+
+ if (argv.v_nmembs >= UINT_MAX / argv.v_size)
+ goto out;
+
+ len = argv.v_size * argv.v_nmembs;
+ if (!len) {
+ ret = 0;
+ goto out;
+ }
+
+ base = (void __user *)(unsigned long)argv.v_base;
+ kbuf = vmalloc(len);
+ if (!kbuf) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ if (copy_from_user(kbuf, base, len)) {
+ ret = -EFAULT;
+ goto out_free;
+ }
+
+ nilfs_transaction_begin(inode->i_sb, &ti, 0);
+ ret = nilfs_sufile_set_suinfo(nilfs->ns_sufile, kbuf, argv.v_size,
+ argv.v_nmembs);
+ if (unlikely(ret < 0))
+ nilfs_transaction_abort(inode->i_sb);
+ else
+ nilfs_transaction_commit(inode->i_sb); /* never fails */
+
+out_free:
+ vfree(kbuf);
+out:
+ mnt_drop_write_file(filp);
+ return ret;
+}
+
long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
- struct inode *inode = filp->f_dentry->d_inode;
+ struct inode *inode = file_inode(filp);
void __user *argp = (void __user *)arg;
switch (cmd) {
@@ -817,6 +1320,8 @@ long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return nilfs_ioctl_get_info(inode, filp, cmd, argp,
sizeof(struct nilfs_suinfo),
nilfs_ioctl_do_get_suinfo);
+ case NILFS_IOCTL_SET_SUINFO:
+ return nilfs_ioctl_set_suinfo(inode, filp, cmd, argp);
case NILFS_IOCTL_GET_SUSTAT:
return nilfs_ioctl_get_sustat(inode, filp, cmd, argp);
case NILFS_IOCTL_GET_VINFO:
@@ -833,6 +1338,8 @@ long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return nilfs_ioctl_resize(inode, filp, argp);
case NILFS_IOCTL_SET_ALLOC_RANGE:
return nilfs_ioctl_set_alloc_range(inode, argp);
+ case FITRIM:
+ return nilfs_ioctl_trim_fs(inode, argp);
default:
return -ENOTTY;
}
@@ -856,6 +1363,7 @@ long nilfs_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
case NILFS_IOCTL_GET_CPINFO:
case NILFS_IOCTL_GET_CPSTAT:
case NILFS_IOCTL_GET_SUINFO:
+ case NILFS_IOCTL_SET_SUINFO:
case NILFS_IOCTL_GET_SUSTAT:
case NILFS_IOCTL_GET_VINFO:
case NILFS_IOCTL_GET_BDESCS:
@@ -863,6 +1371,7 @@ long nilfs_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
case NILFS_IOCTL_SYNC:
case NILFS_IOCTL_RESIZE:
case NILFS_IOCTL_SET_ALLOC_RANGE:
+ case FITRIM:
break;
default:
return -ENOIOCTLCMD;
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index f9897d09c69..c4dcd1db57e 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -375,14 +375,25 @@ int nilfs_mdt_fetch_dirty(struct inode *inode)
static int
nilfs_mdt_write_page(struct page *page, struct writeback_control *wbc)
{
- struct inode *inode;
+ struct inode *inode = page->mapping->host;
struct super_block *sb;
int err = 0;
+ if (inode && (inode->i_sb->s_flags & MS_RDONLY)) {
+ /*
+ * It means that filesystem was remounted in read-only
+ * mode because of error or metadata corruption. But we
+ * have dirty pages that try to be flushed in background.
+ * So, here we simply discard this dirty page.
+ */
+ nilfs_clear_dirty_page(page, false);
+ unlock_page(page);
+ return -EROFS;
+ }
+
redirty_page_for_writepage(wbc, page);
unlock_page(page);
- inode = page->mapping->host;
if (!inode)
return 0;
@@ -561,10 +572,10 @@ void nilfs_mdt_restore_from_shadow_map(struct inode *inode)
if (mi->mi_palloc_cache)
nilfs_palloc_clear_cache(inode);
- nilfs_clear_dirty_pages(inode->i_mapping);
+ nilfs_clear_dirty_pages(inode->i_mapping, true);
nilfs_copy_back_pages(inode->i_mapping, &shadow->frozen_data);
- nilfs_clear_dirty_pages(&ii->i_btnode_cache);
+ nilfs_clear_dirty_pages(&ii->i_btnode_cache, true);
nilfs_copy_back_pages(&ii->i_btnode_cache, &shadow->frozen_btnodes);
nilfs_bmap_restore(ii->i_bmap, &shadow->bmap_store);
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 1d0c0b84c5a..9de78f08989 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -517,11 +517,11 @@ static int nilfs_encode_fh(struct inode *inode, __u32 *fh, int *lenp,
if (parent && *lenp < NILFS_FID_SIZE_CONNECTABLE) {
*lenp = NILFS_FID_SIZE_CONNECTABLE;
- return 255;
+ return FILEID_INVALID;
}
if (*lenp < NILFS_FID_SIZE_NON_CONNECTABLE) {
*lenp = NILFS_FID_SIZE_NON_CONNECTABLE;
- return 255;
+ return FILEID_INVALID;
}
fid->cno = root->cno;
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index 07f76db04ec..da276640f77 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -94,6 +94,7 @@ void nilfs_forget_buffer(struct buffer_head *bh)
clear_buffer_nilfs_volatile(bh);
clear_buffer_nilfs_checked(bh);
clear_buffer_nilfs_redirected(bh);
+ clear_buffer_async_write(bh);
clear_buffer_dirty(bh);
if (nilfs_page_buffers_clean(page))
__nilfs_clear_page_dirty(page);
@@ -370,7 +371,12 @@ repeat:
goto repeat;
}
-void nilfs_clear_dirty_pages(struct address_space *mapping)
+/**
+ * nilfs_clear_dirty_pages - discard dirty pages in address space
+ * @mapping: address space with dirty pages for discarding
+ * @silent: suppress [true] or print [false] warning messages
+ */
+void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent)
{
struct pagevec pvec;
unsigned int i;
@@ -382,25 +388,9 @@ void nilfs_clear_dirty_pages(struct address_space *mapping)
PAGEVEC_SIZE)) {
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
- struct buffer_head *bh, *head;
lock_page(page);
- ClearPageUptodate(page);
- ClearPageMappedToDisk(page);
- bh = head = page_buffers(page);
- do {
- lock_buffer(bh);
- clear_buffer_dirty(bh);
- clear_buffer_nilfs_volatile(bh);
- clear_buffer_nilfs_checked(bh);
- clear_buffer_nilfs_redirected(bh);
- clear_buffer_uptodate(bh);
- clear_buffer_mapped(bh);
- unlock_buffer(bh);
- bh = bh->b_this_page;
- } while (bh != head);
-
- __nilfs_clear_page_dirty(page);
+ nilfs_clear_dirty_page(page, silent);
unlock_page(page);
}
pagevec_release(&pvec);
@@ -408,6 +398,52 @@ void nilfs_clear_dirty_pages(struct address_space *mapping)
}
}
+/**
+ * nilfs_clear_dirty_page - discard dirty page
+ * @page: dirty page that will be discarded
+ * @silent: suppress [true] or print [false] warning messages
+ */
+void nilfs_clear_dirty_page(struct page *page, bool silent)
+{
+ struct inode *inode = page->mapping->host;
+ struct super_block *sb = inode->i_sb;
+
+ BUG_ON(!PageLocked(page));
+
+ if (!silent) {
+ nilfs_warning(sb, __func__,
+ "discard page: offset %lld, ino %lu",
+ page_offset(page), inode->i_ino);
+ }
+
+ ClearPageUptodate(page);
+ ClearPageMappedToDisk(page);
+
+ if (page_has_buffers(page)) {
+ struct buffer_head *bh, *head;
+
+ bh = head = page_buffers(page);
+ do {
+ lock_buffer(bh);
+ if (!silent) {
+ nilfs_warning(sb, __func__,
+ "discard block %llu, size %zu",
+ (u64)bh->b_blocknr, bh->b_size);
+ }
+ clear_buffer_async_write(bh);
+ clear_buffer_dirty(bh);
+ clear_buffer_nilfs_volatile(bh);
+ clear_buffer_nilfs_checked(bh);
+ clear_buffer_nilfs_redirected(bh);
+ clear_buffer_uptodate(bh);
+ clear_buffer_mapped(bh);
+ unlock_buffer(bh);
+ } while (bh = bh->b_this_page, bh != head);
+ }
+
+ __nilfs_clear_page_dirty(page);
+}
+
unsigned nilfs_page_count_clean_buffers(struct page *page,
unsigned from, unsigned to)
{
diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h
index fb7de71605a..ef30c5c2426 100644
--- a/fs/nilfs2/page.h
+++ b/fs/nilfs2/page.h
@@ -55,7 +55,8 @@ void nilfs_page_bug(struct page *);
int nilfs_copy_dirty_pages(struct address_space *, struct address_space *);
void nilfs_copy_back_pages(struct address_space *, struct address_space *);
-void nilfs_clear_dirty_pages(struct address_space *);
+void nilfs_clear_dirty_page(struct page *, bool);
+void nilfs_clear_dirty_pages(struct address_space *, bool);
void nilfs_mapping_init(struct address_space *mapping, struct inode *inode,
struct backing_dev_info *bdi);
unsigned nilfs_page_count_clean_buffers(struct page *, unsigned, unsigned);
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index dc9a913784a..dc3a9efdaab 100644
--- a/fs/nilfs2/segbuf.c
+++ b/fs/nilfs2/segbuf.c
@@ -345,8 +345,7 @@ static void nilfs_end_bio_write(struct bio *bio, int err)
if (err == -EOPNOTSUPP) {
set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
- bio_put(bio);
- /* to be detected by submit_seg_bio() */
+ /* to be detected by nilfs_segbuf_submit_bio() */
}
if (!uptodate)
@@ -377,12 +376,12 @@ static int nilfs_segbuf_submit_bio(struct nilfs_segment_buffer *segbuf,
bio->bi_private = segbuf;
bio_get(bio);
submit_bio(mode, bio);
+ segbuf->sb_nbio++;
if (bio_flagged(bio, BIO_EOPNOTSUPP)) {
bio_put(bio);
err = -EOPNOTSUPP;
goto failed;
}
- segbuf->sb_nbio++;
bio_put(bio);
wi->bio = NULL;
@@ -417,7 +416,8 @@ static struct bio *nilfs_alloc_seg_bio(struct the_nilfs *nilfs, sector_t start,
}
if (likely(bio)) {
bio->bi_bdev = nilfs->ns_bdev;
- bio->bi_sector = start << (nilfs->ns_blocksize_bits - 9);
+ bio->bi_iter.bi_sector =
+ start << (nilfs->ns_blocksize_bits - 9);
}
return bio;
}
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index a5752a58993..a1a191634ab 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -665,7 +665,7 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode,
bh = head = page_buffers(page);
do {
- if (!buffer_dirty(bh))
+ if (!buffer_dirty(bh) || buffer_async_write(bh))
continue;
get_bh(bh);
list_add_tail(&bh->b_assoc_buffers, listp);
@@ -699,7 +699,8 @@ static void nilfs_lookup_dirty_node_buffers(struct inode *inode,
for (i = 0; i < pagevec_count(&pvec); i++) {
bh = head = page_buffers(pvec.pages[i]);
do {
- if (buffer_dirty(bh)) {
+ if (buffer_dirty(bh) &&
+ !buffer_async_write(bh)) {
get_bh(bh);
list_add_tail(&bh->b_assoc_buffers,
listp);
@@ -835,9 +836,9 @@ static int nilfs_segctor_fill_in_checkpoint(struct nilfs_sc_info *sci)
raw_cp->cp_snapshot_list.ssl_next = 0;
raw_cp->cp_snapshot_list.ssl_prev = 0;
raw_cp->cp_inodes_count =
- cpu_to_le64(atomic_read(&sci->sc_root->inodes_count));
+ cpu_to_le64(atomic64_read(&sci->sc_root->inodes_count));
raw_cp->cp_blocks_count =
- cpu_to_le64(atomic_read(&sci->sc_root->blocks_count));
+ cpu_to_le64(atomic64_read(&sci->sc_root->blocks_count));
raw_cp->cp_nblk_inc =
cpu_to_le64(sci->sc_nblk_inc + sci->sc_nblk_this_inc);
raw_cp->cp_create = cpu_to_le64(sci->sc_seg_ctime);
@@ -1439,17 +1440,19 @@ static int nilfs_segctor_collect(struct nilfs_sc_info *sci,
nilfs_clear_logs(&sci->sc_segbufs);
- err = nilfs_segctor_extend_segments(sci, nilfs, nadd);
- if (unlikely(err))
- return err;
-
if (sci->sc_stage.flags & NILFS_CF_SUFREED) {
err = nilfs_sufile_cancel_freev(nilfs->ns_sufile,
sci->sc_freesegs,
sci->sc_nfreesegs,
NULL);
WARN_ON(err); /* do not happen */
+ sci->sc_stage.flags &= ~NILFS_CF_SUFREED;
}
+
+ err = nilfs_segctor_extend_segments(sci, nilfs, nadd);
+ if (unlikely(err))
+ return err;
+
nadd = min_t(int, nadd << 1, SC_MAX_SEGDELTA);
sci->sc_stage = prev_stage;
}
@@ -1579,6 +1582,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
list_for_each_entry(bh, &segbuf->sb_segsum_buffers,
b_assoc_buffers) {
+ set_buffer_async_write(bh);
if (bh->b_page != bd_page) {
if (bd_page) {
lock_page(bd_page);
@@ -1592,6 +1596,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
list_for_each_entry(bh, &segbuf->sb_payload_buffers,
b_assoc_buffers) {
+ set_buffer_async_write(bh);
if (bh == segbuf->sb_super_root) {
if (bh->b_page != bd_page) {
lock_page(bd_page);
@@ -1677,6 +1682,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err)
list_for_each_entry(segbuf, logs, sb_list) {
list_for_each_entry(bh, &segbuf->sb_segsum_buffers,
b_assoc_buffers) {
+ clear_buffer_async_write(bh);
if (bh->b_page != bd_page) {
if (bd_page)
end_page_writeback(bd_page);
@@ -1686,6 +1692,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err)
list_for_each_entry(bh, &segbuf->sb_payload_buffers,
b_assoc_buffers) {
+ clear_buffer_async_write(bh);
if (bh == segbuf->sb_super_root) {
if (bh->b_page != bd_page) {
end_page_writeback(bd_page);
@@ -1755,6 +1762,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
b_assoc_buffers) {
set_buffer_uptodate(bh);
clear_buffer_dirty(bh);
+ clear_buffer_async_write(bh);
if (bh->b_page != bd_page) {
if (bd_page)
end_page_writeback(bd_page);
@@ -1776,6 +1784,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
b_assoc_buffers) {
set_buffer_uptodate(bh);
clear_buffer_dirty(bh);
+ clear_buffer_async_write(bh);
clear_buffer_delay(bh);
clear_buffer_nilfs_volatile(bh);
clear_buffer_nilfs_redirected(bh);
diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c
index 3127e9f438a..2a869c35c36 100644
--- a/fs/nilfs2/sufile.c
+++ b/fs/nilfs2/sufile.c
@@ -870,6 +870,289 @@ ssize_t nilfs_sufile_get_suinfo(struct inode *sufile, __u64 segnum, void *buf,
}
/**
+ * nilfs_sufile_set_suinfo - sets segment usage info
+ * @sufile: inode of segment usage file
+ * @buf: array of suinfo_update
+ * @supsz: byte size of suinfo_update
+ * @nsup: size of suinfo_update array
+ *
+ * Description: Takes an array of nilfs_suinfo_update structs and updates
+ * segment usage accordingly. Only the fields indicated by the sup_flags
+ * are updated.
+ *
+ * Return Value: On success, 0 is returned. On error, one of the
+ * following negative error codes is returned.
+ *
+ * %-EIO - I/O error.
+ *
+ * %-ENOMEM - Insufficient amount of memory available.
+ *
+ * %-EINVAL - Invalid values in input (segment number, flags or nblocks)
+ */
+ssize_t nilfs_sufile_set_suinfo(struct inode *sufile, void *buf,
+ unsigned supsz, size_t nsup)
+{
+ struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
+ struct buffer_head *header_bh, *bh;
+ struct nilfs_suinfo_update *sup, *supend = buf + supsz * nsup;
+ struct nilfs_segment_usage *su;
+ void *kaddr;
+ unsigned long blkoff, prev_blkoff;
+ int cleansi, cleansu, dirtysi, dirtysu;
+ long ncleaned = 0, ndirtied = 0;
+ int ret = 0;
+
+ if (unlikely(nsup == 0))
+ return ret;
+
+ for (sup = buf; sup < supend; sup = (void *)sup + supsz) {
+ if (sup->sup_segnum >= nilfs->ns_nsegments
+ || (sup->sup_flags &
+ (~0UL << __NR_NILFS_SUINFO_UPDATE_FIELDS))
+ || (nilfs_suinfo_update_nblocks(sup) &&
+ sup->sup_sui.sui_nblocks >
+ nilfs->ns_blocks_per_segment))
+ return -EINVAL;
+ }
+
+ down_write(&NILFS_MDT(sufile)->mi_sem);
+
+ ret = nilfs_sufile_get_header_block(sufile, &header_bh);
+ if (ret < 0)
+ goto out_sem;
+
+ sup = buf;
+ blkoff = nilfs_sufile_get_blkoff(sufile, sup->sup_segnum);
+ ret = nilfs_mdt_get_block(sufile, blkoff, 1, NULL, &bh);
+ if (ret < 0)
+ goto out_header;
+
+ for (;;) {
+ kaddr = kmap_atomic(bh->b_page);
+ su = nilfs_sufile_block_get_segment_usage(
+ sufile, sup->sup_segnum, bh, kaddr);
+
+ if (nilfs_suinfo_update_lastmod(sup))
+ su->su_lastmod = cpu_to_le64(sup->sup_sui.sui_lastmod);
+
+ if (nilfs_suinfo_update_nblocks(sup))
+ su->su_nblocks = cpu_to_le32(sup->sup_sui.sui_nblocks);
+
+ if (nilfs_suinfo_update_flags(sup)) {
+ /*
+ * Active flag is a virtual flag projected by running
+ * nilfs kernel code - drop it not to write it to
+ * disk.
+ */
+ sup->sup_sui.sui_flags &=
+ ~(1UL << NILFS_SEGMENT_USAGE_ACTIVE);
+
+ cleansi = nilfs_suinfo_clean(&sup->sup_sui);
+ cleansu = nilfs_segment_usage_clean(su);
+ dirtysi = nilfs_suinfo_dirty(&sup->sup_sui);
+ dirtysu = nilfs_segment_usage_dirty(su);
+
+ if (cleansi && !cleansu)
+ ++ncleaned;
+ else if (!cleansi && cleansu)
+ --ncleaned;
+
+ if (dirtysi && !dirtysu)
+ ++ndirtied;
+ else if (!dirtysi && dirtysu)
+ --ndirtied;
+
+ su->su_flags = cpu_to_le32(sup->sup_sui.sui_flags);
+ }
+
+ kunmap_atomic(kaddr);
+
+ sup = (void *)sup + supsz;
+ if (sup >= supend)
+ break;
+
+ prev_blkoff = blkoff;
+ blkoff = nilfs_sufile_get_blkoff(sufile, sup->sup_segnum);
+ if (blkoff == prev_blkoff)
+ continue;
+
+ /* get different block */
+ mark_buffer_dirty(bh);
+ put_bh(bh);
+ ret = nilfs_mdt_get_block(sufile, blkoff, 1, NULL, &bh);
+ if (unlikely(ret < 0))
+ goto out_mark;
+ }
+ mark_buffer_dirty(bh);
+ put_bh(bh);
+
+ out_mark:
+ if (ncleaned || ndirtied) {
+ nilfs_sufile_mod_counter(header_bh, (u64)ncleaned,
+ (u64)ndirtied);
+ NILFS_SUI(sufile)->ncleansegs += ncleaned;
+ }
+ nilfs_mdt_mark_dirty(sufile);
+ out_header:
+ put_bh(header_bh);
+ out_sem:
+ up_write(&NILFS_MDT(sufile)->mi_sem);
+ return ret;
+}
+
+/**
+ * nilfs_sufile_trim_fs() - trim ioctl handle function
+ * @sufile: inode of segment usage file
+ * @range: fstrim_range structure
+ *
+ * start: First Byte to trim
+ * len: number of Bytes to trim from start
+ * minlen: minimum extent length in Bytes
+ *
+ * Decription: nilfs_sufile_trim_fs goes through all segments containing bytes
+ * from start to start+len. start is rounded up to the next block boundary
+ * and start+len is rounded down. For each clean segment blkdev_issue_discard
+ * function is invoked.
+ *
+ * Return Value: On success, 0 is returned or negative error code, otherwise.
+ */
+int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range)
+{
+ struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
+ struct buffer_head *su_bh;
+ struct nilfs_segment_usage *su;
+ void *kaddr;
+ size_t n, i, susz = NILFS_MDT(sufile)->mi_entry_size;
+ sector_t seg_start, seg_end, start_block, end_block;
+ sector_t start = 0, nblocks = 0;
+ u64 segnum, segnum_end, minlen, len, max_blocks, ndiscarded = 0;
+ int ret = 0;
+ unsigned int sects_per_block;
+
+ sects_per_block = (1 << nilfs->ns_blocksize_bits) /
+ bdev_logical_block_size(nilfs->ns_bdev);
+ len = range->len >> nilfs->ns_blocksize_bits;
+ minlen = range->minlen >> nilfs->ns_blocksize_bits;
+ max_blocks = ((u64)nilfs->ns_nsegments * nilfs->ns_blocks_per_segment);
+
+ if (!len || range->start >= max_blocks << nilfs->ns_blocksize_bits)
+ return -EINVAL;
+
+ start_block = (range->start + nilfs->ns_blocksize - 1) >>
+ nilfs->ns_blocksize_bits;
+
+ /*
+ * range->len can be very large (actually, it is set to
+ * ULLONG_MAX by default) - truncate upper end of the range
+ * carefully so as not to overflow.
+ */
+ if (max_blocks - start_block < len)
+ end_block = max_blocks - 1;
+ else
+ end_block = start_block + len - 1;
+
+ segnum = nilfs_get_segnum_of_block(nilfs, start_block);
+ segnum_end = nilfs_get_segnum_of_block(nilfs, end_block);
+
+ down_read(&NILFS_MDT(sufile)->mi_sem);
+
+ while (segnum <= segnum_end) {
+ n = nilfs_sufile_segment_usages_in_block(sufile, segnum,
+ segnum_end);
+
+ ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0,
+ &su_bh);
+ if (ret < 0) {
+ if (ret != -ENOENT)
+ goto out_sem;
+ /* hole */
+ segnum += n;
+ continue;
+ }
+
+ kaddr = kmap_atomic(su_bh->b_page);
+ su = nilfs_sufile_block_get_segment_usage(sufile, segnum,
+ su_bh, kaddr);
+ for (i = 0; i < n; ++i, ++segnum, su = (void *)su + susz) {
+ if (!nilfs_segment_usage_clean(su))
+ continue;
+
+ nilfs_get_segment_range(nilfs, segnum, &seg_start,
+ &seg_end);
+
+ if (!nblocks) {
+ /* start new extent */
+ start = seg_start;
+ nblocks = seg_end - seg_start + 1;
+ continue;
+ }
+
+ if (start + nblocks == seg_start) {
+ /* add to previous extent */
+ nblocks += seg_end - seg_start + 1;
+ continue;
+ }
+
+ /* discard previous extent */
+ if (start < start_block) {
+ nblocks -= start_block - start;
+ start = start_block;
+ }
+
+ if (nblocks >= minlen) {
+ kunmap_atomic(kaddr);
+
+ ret = blkdev_issue_discard(nilfs->ns_bdev,
+ start * sects_per_block,
+ nblocks * sects_per_block,
+ GFP_NOFS, 0);
+ if (ret < 0) {
+ put_bh(su_bh);
+ goto out_sem;
+ }
+
+ ndiscarded += nblocks;
+ kaddr = kmap_atomic(su_bh->b_page);
+ su = nilfs_sufile_block_get_segment_usage(
+ sufile, segnum, su_bh, kaddr);
+ }
+
+ /* start new extent */
+ start = seg_start;
+ nblocks = seg_end - seg_start + 1;
+ }
+ kunmap_atomic(kaddr);
+ put_bh(su_bh);
+ }
+
+
+ if (nblocks) {
+ /* discard last extent */
+ if (start < start_block) {
+ nblocks -= start_block - start;
+ start = start_block;
+ }
+ if (start + nblocks > end_block + 1)
+ nblocks = end_block - start + 1;
+
+ if (nblocks >= minlen) {
+ ret = blkdev_issue_discard(nilfs->ns_bdev,
+ start * sects_per_block,
+ nblocks * sects_per_block,
+ GFP_NOFS, 0);
+ if (!ret)
+ ndiscarded += nblocks;
+ }
+ }
+
+out_sem:
+ up_read(&NILFS_MDT(sufile)->mi_sem);
+
+ range->len = ndiscarded << nilfs->ns_blocksize_bits;
+ return ret;
+}
+
+/**
* nilfs_sufile_read - read or get sufile inode
* @sb: super block instance
* @susize: size of a segment usage entry
@@ -886,6 +1169,18 @@ int nilfs_sufile_read(struct super_block *sb, size_t susize,
void *kaddr;
int err;
+ if (susize > sb->s_blocksize) {
+ printk(KERN_ERR
+ "NILFS: too large segment usage size: %zu bytes.\n",
+ susize);
+ return -EINVAL;
+ } else if (susize < NILFS_MIN_SEGMENT_USAGE_SIZE) {
+ printk(KERN_ERR
+ "NILFS: too small segment usage size: %zu bytes.\n",
+ susize);
+ return -EINVAL;
+ }
+
sufile = nilfs_iget_locked(sb, NULL, NILFS_SUFILE_INO);
if (unlikely(!sufile))
return -ENOMEM;
diff --git a/fs/nilfs2/sufile.h b/fs/nilfs2/sufile.h
index e84bc5b51fc..b8afd72f237 100644
--- a/fs/nilfs2/sufile.h
+++ b/fs/nilfs2/sufile.h
@@ -44,6 +44,7 @@ int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum,
int nilfs_sufile_get_stat(struct inode *, struct nilfs_sustat *);
ssize_t nilfs_sufile_get_suinfo(struct inode *, __u64, void *, unsigned,
size_t);
+ssize_t nilfs_sufile_set_suinfo(struct inode *, void *, unsigned , size_t);
int nilfs_sufile_updatev(struct inode *, __u64 *, size_t, int, size_t *,
void (*dofunc)(struct inode *, __u64,
@@ -65,6 +66,7 @@ void nilfs_sufile_do_set_error(struct inode *, __u64, struct buffer_head *,
int nilfs_sufile_resize(struct inode *sufile, __u64 newnsegs);
int nilfs_sufile_read(struct super_block *sb, size_t susize,
struct nilfs_inode *raw_inode, struct inode **inodep);
+int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range);
/**
* nilfs_sufile_scrap - make a segment garbage
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 3c991dc84f2..8c532b2ca3a 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -554,8 +554,10 @@ int nilfs_attach_checkpoint(struct super_block *sb, __u64 cno, int curr_mnt,
if (err)
goto failed_bh;
- atomic_set(&root->inodes_count, le64_to_cpu(raw_cp->cp_inodes_count));
- atomic_set(&root->blocks_count, le64_to_cpu(raw_cp->cp_blocks_count));
+ atomic64_set(&root->inodes_count,
+ le64_to_cpu(raw_cp->cp_inodes_count));
+ atomic64_set(&root->blocks_count,
+ le64_to_cpu(raw_cp->cp_blocks_count));
nilfs_cpfile_put_checkpoint(nilfs->ns_cpfile, cno, bh_cp);
@@ -609,6 +611,7 @@ static int nilfs_statfs(struct dentry *dentry, struct kstatfs *buf)
unsigned long overhead;
unsigned long nrsvblocks;
sector_t nfreeblocks;
+ u64 nmaxinodes, nfreeinodes;
int err;
/*
@@ -633,14 +636,34 @@ static int nilfs_statfs(struct dentry *dentry, struct kstatfs *buf)
if (unlikely(err))
return err;
+ err = nilfs_ifile_count_free_inodes(root->ifile,
+ &nmaxinodes, &nfreeinodes);
+ if (unlikely(err)) {
+ printk(KERN_WARNING
+ "NILFS warning: fail to count free inodes: err %d.\n",
+ err);
+ if (err == -ERANGE) {
+ /*
+ * If nilfs_palloc_count_max_entries() returns
+ * -ERANGE error code then we simply treat
+ * curent inodes count as maximum possible and
+ * zero as free inodes value.
+ */
+ nmaxinodes = atomic64_read(&root->inodes_count);
+ nfreeinodes = 0;
+ err = 0;
+ } else
+ return err;
+ }
+
buf->f_type = NILFS_SUPER_MAGIC;
buf->f_bsize = sb->s_blocksize;
buf->f_blocks = blocks - overhead;
buf->f_bfree = nfreeblocks;
buf->f_bavail = (buf->f_bfree >= nrsvblocks) ?
(buf->f_bfree - nrsvblocks) : 0;
- buf->f_files = atomic_read(&root->inodes_count);
- buf->f_ffree = 0; /* nilfs_count_free_inodes(sb); */
+ buf->f_files = nmaxinodes;
+ buf->f_ffree = nfreeinodes;
buf->f_namelen = NILFS_NAME_LEN;
buf->f_fsid.val[0] = (u32)id;
buf->f_fsid.val[1] = (u32)(id >> 32);
@@ -971,23 +994,16 @@ static int nilfs_attach_snapshot(struct super_block *s, __u64 cno,
return ret;
}
-static int nilfs_tree_was_touched(struct dentry *root_dentry)
-{
- return root_dentry->d_count > 1;
-}
-
/**
- * nilfs_try_to_shrink_tree() - try to shrink dentries of a checkpoint
+ * nilfs_tree_is_busy() - try to shrink dentries of a checkpoint
* @root_dentry: root dentry of the tree to be shrunk
*
* This function returns true if the tree was in-use.
*/
-static int nilfs_try_to_shrink_tree(struct dentry *root_dentry)
+static bool nilfs_tree_is_busy(struct dentry *root_dentry)
{
- if (have_submounts(root_dentry))
- return true;
shrink_dcache_parent(root_dentry);
- return nilfs_tree_was_touched(root_dentry);
+ return d_count(root_dentry) > 1;
}
int nilfs_checkpoint_is_mounted(struct super_block *sb, __u64 cno)
@@ -1011,8 +1027,7 @@ int nilfs_checkpoint_is_mounted(struct super_block *sb, __u64 cno)
if (inode) {
dentry = d_find_alias(inode);
if (dentry) {
- if (nilfs_tree_was_touched(dentry))
- ret = nilfs_try_to_shrink_tree(dentry);
+ ret = nilfs_tree_is_busy(dentry);
dput(dentry);
}
iput(inode);
@@ -1114,6 +1129,7 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data)
unsigned long old_mount_opt;
int err;
+ sync_filesystem(sb);
old_sb_flags = sb->s_flags;
old_mount_opt = nilfs->ns_mount_opt;
@@ -1308,11 +1324,8 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
s->s_flags |= MS_ACTIVE;
} else if (!sd.cno) {
- int busy = false;
-
- if (nilfs_tree_was_touched(s->s_root)) {
- busy = nilfs_try_to_shrink_tree(s->s_root);
- if (busy && (flags ^ s->s_flags) & MS_RDONLY) {
+ if (nilfs_tree_is_busy(s->s_root)) {
+ if ((flags ^ s->s_flags) & MS_RDONLY) {
printk(KERN_ERR "NILFS: the device already "
"has a %s mount.\n",
(s->s_flags & MS_RDONLY) ?
@@ -1320,8 +1333,7 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
err = -EBUSY;
goto failed_super;
}
- }
- if (!busy) {
+ } else {
/*
* Try remount to setup mount states if the current
* tree is not mounted and only snapshots use this sb.
@@ -1361,6 +1373,7 @@ struct file_system_type nilfs_fs_type = {
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
+MODULE_ALIAS_FS("nilfs2");
static void nilfs_inode_init_once(void *obj)
{
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 41e6a04a561..8ba8229ba07 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -399,6 +399,16 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs,
return -EINVAL;
nilfs->ns_inode_size = le16_to_cpu(sbp->s_inode_size);
+ if (nilfs->ns_inode_size > nilfs->ns_blocksize) {
+ printk(KERN_ERR "NILFS: too large inode size: %d bytes.\n",
+ nilfs->ns_inode_size);
+ return -EINVAL;
+ } else if (nilfs->ns_inode_size < NILFS_MIN_INODE_SIZE) {
+ printk(KERN_ERR "NILFS: too small inode size: %d bytes.\n",
+ nilfs->ns_inode_size);
+ return -EINVAL;
+ }
+
nilfs->ns_first_ino = le32_to_cpu(sbp->s_first_ino);
nilfs->ns_blocks_per_segment = le32_to_cpu(sbp->s_blocks_per_segment);
@@ -764,8 +774,8 @@ nilfs_find_or_create_root(struct the_nilfs *nilfs, __u64 cno)
new->ifile = NULL;
new->nilfs = nilfs;
atomic_set(&new->count, 1);
- atomic_set(&new->inodes_count, 0);
- atomic_set(&new->blocks_count, 0);
+ atomic64_set(&new->inodes_count, 0);
+ atomic64_set(&new->blocks_count, 0);
rb_link_node(&new->rb_node, parent, p);
rb_insert_color(&new->rb_node, &nilfs->ns_cptree);
diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h
index be1267a34ce..de8cc53b4a5 100644
--- a/fs/nilfs2/the_nilfs.h
+++ b/fs/nilfs2/the_nilfs.h
@@ -241,8 +241,8 @@ struct nilfs_root {
struct the_nilfs *nilfs;
struct inode *ifile;
- atomic_t inodes_count;
- atomic_t blocks_count;
+ atomic64_t inodes_count;
+ atomic64_t blocks_count;
};
/* Special checkpoint number */
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-09 22:02:40 +0000