*/
#define DEBUG_SUBSYSTEM S_LLITE
-#include "../include/lustre_dlm.h"
+#include <lustre_dlm.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/sched.h>
#include <linux/mount.h>
-#include "../include/lustre/ll_fiemap.h"
-#include "../include/lustre/lustre_ioctl.h"
-#include "../include/lustre_swab.h"
+#include <uapi/linux/lustre/lustre_fiemap.h>
+#include <uapi/linux/lustre/lustre_ioctl.h>
+#include <lustre_swab.h>
-#include "../include/cl_object.h"
+#include <cl_object.h>
#include "llite_internal.h"
static int
PFID(ll_inode2fid(inode)), inode);
ll_stats_ops_tally(ll_i2sbi(inode), LPROC_LL_FSYNC, 1);
- rc = filemap_write_and_wait_range(inode->i_mapping, start, end);
+ rc = file_write_and_wait_range(file, start, end);
inode_lock(inode);
/* catch async errors that were recorded back when async writeback
spin_lock(&lli->lli_lock);
/* VFS' acl_permission_check->check_acl will release the refcount */
acl = posix_acl_dup(lli->lli_posix_acl);
-#ifdef CONFIG_FS_POSIX_ACL
- forget_cached_acl(inode, type);
-#endif
spin_unlock(&lli->lli_lock);
return acl;
fl->fl_end = OFFSET_MAX;
else
fl->fl_end = glock.start + glock.length - 1;
- fl->fl_pid = glock.proc_id;
+ fl->fl_pid = -glock.proc_id;
}
kfree(glock.client_id);
return res;
struct p9_wstat wstat;
int retval;
- retval = filemap_write_and_wait_range(inode->i_mapping, start, end);
+ retval = file_write_and_wait_range(filp, start, end);
if (retval)
return retval;
struct inode *inode = filp->f_mapping->host;
int retval;
- retval = filemap_write_and_wait_range(inode->i_mapping, start, end);
+ retval = file_write_and_wait_range(filp, start, end);
if (retval)
return retval;
/* if fdatasync is triggered, let's do in-place-update */
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);
+ ret = file_write_and_wait_range(file, start, end);
clear_inode_flag(inode, FI_NEED_IPU);
if (ret) {
/* Is it quota file? Do not allow user to mess with it */
if (IS_NOQUOTA(inode)) {
- inode_unlock(inode);
ret = -EPERM;
goto unlock_out;
}
if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) {
if (!capable(CAP_LINUX_IMMUTABLE)) {
- inode_unlock(inode);
ret = -EPERM;
- goto out;
+ goto unlock_out;
}
}
f2fs_mark_inode_dirty_sync(inode, false);
unlock_out:
inode_unlock(inode);
-out:
mnt_drop_write_file(filp);
return ret;
}
{
struct fuse_file *ff;
- ff = kmalloc(sizeof(struct fuse_file), GFP_KERNEL);
+ ff = kzalloc(sizeof(struct fuse_file), GFP_KERNEL);
if (unlikely(!ff))
return NULL;
* wait for all outstanding writes, before sending the FSYNC
* request.
*/
- err = filemap_write_and_wait_range(inode->i_mapping, start, end);
+ err = file_write_and_wait_range(file, start, end);
if (err)
goto out;
/*
* Due to implementation of fuse writeback
- * filemap_write_and_wait_range() does not catch errors.
+ * file_write_and_wait_range() does not catch errors.
* We have to do this directly after fuse_sync_writes()
*/
- err = filemap_check_errors(file->f_mapping);
+ err = file_check_and_advance_wb_err(file);
if (err)
goto out;
struct fuse_io_priv *io = req->io;
ssize_t pos = -1;
- fuse_release_user_pages(req, !io->write);
+ fuse_release_user_pages(req, io->should_dirty);
if (io->write) {
if (req->misc.write.in.size != req->misc.write.out.size)
loff_t *ppos, int flags)
{
int write = flags & FUSE_DIO_WRITE;
- bool should_dirty = !write && iter_is_iovec(iter);
int cuse = flags & FUSE_DIO_CUSE;
struct file *file = io->file;
struct inode *inode = file->f_mapping->host;
inode_unlock(inode);
}
+ io->should_dirty = !write && iter_is_iovec(iter);
while (count) {
size_t nres;
fl_owner_t owner = current->files;
nres = fuse_send_read(req, io, pos, nbytes, owner);
if (!io->async)
- fuse_release_user_pages(req, should_dirty);
+ fuse_release_user_pages(req, io->should_dirty);
if (req->out.h.error) {
err = req->out.h.error;
break;
err_free:
fuse_request_free(req);
err:
+ mapping_set_error(page->mapping, error);
end_page_writeback(page);
return error;
}
fl->fl_end = ffl->end;
/*
- * Convert pid into the caller's pid namespace. If the pid
- * does not map into the namespace fl_pid will get set to 0.
+ * Convert pid into init's pid namespace. The locks API will
+ * translate it into the caller's pid namespace.
*/
rcu_read_lock();
- fl->fl_pid = pid_vnr(find_pid_ns(ffl->pid, fc->pid_ns));
+ fl->fl_pid = pid_nr_ns(find_pid_ns(ffl->pid, fc->pid_ns), &init_pid_ns);
rcu_read_unlock();
break;
if (ret)
return ret;
if (gfs2_is_jdata(ip))
- filemap_write_and_wait(mapping);
+ ret = file_write_and_wait(file);
+ if (ret)
+ return ret;
gfs2_ail_flush(ip->i_gl, 1);
}
if (mapping->nrpages)
- ret = filemap_fdatawait_range(mapping, start, end);
+ ret = file_fdatawait_range(file, start, end);
return ret ? ret : ret1;
}
mutex_lock(&fp->f_fl_mutex);
- gl = fl_gh->gh_gl;
- if (gl) {
+ if (gfs2_holder_initialized(fl_gh)) {
if (fl_gh->gh_state == state)
goto out;
locks_lock_file_wait(file,
extern int sysctl_protected_symlinks;
extern int sysctl_protected_hardlinks;
+typedef __kernel_rwf_t rwf_t;
+
struct buffer_head;
typedef int (get_block_t)(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
void *private;
int ki_flags;
enum rw_hint ki_hint;
-};
+} __randomize_layout;
static inline bool is_sync_kiocb(struct kiocb *kiocb)
{
struct list_head private_list; /* ditto */
void *private_data; /* ditto */
errseq_t wb_err;
-} __attribute__((aligned(sizeof(long))));
+} __attribute__((aligned(sizeof(long)))) __randomize_layout;
/*
* On most architectures that alignment is already the case; but
* must be enforced here for CRIS, to let the least significant bit
int bd_fsfreeze_count;
/* Mutex for freeze */
struct mutex bd_fsfreeze_mutex;
-};
+} __randomize_layout;
/*
* Radix-tree tags, for tagging dirty and writeback pages within the pagecache
#endif
void *i_private; /* fs or device private pointer */
-};
+} __randomize_layout;
static inline unsigned int i_blocksize(const struct inode *node)
{
#endif /* #ifdef CONFIG_EPOLL */
struct address_space *f_mapping;
errseq_t f_wb_err;
-} __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */
+} __randomize_layout
+ __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */
struct file_handle {
__u32 handle_bytes;
/* Page cache limit. The filesystems should put that into their s_maxbytes
limits, otherwise bad things can happen in VM. */
#if BITS_PER_LONG==32
-#define MAX_LFS_FILESIZE (((loff_t)PAGE_SIZE << (BITS_PER_LONG-1))-1)
+#define MAX_LFS_FILESIZE ((loff_t)ULONG_MAX << PAGE_SHIFT)
#elif BITS_PER_LONG==64
-#define MAX_LFS_FILESIZE ((loff_t)0x7fffffffffffffffLL)
+#define MAX_LFS_FILESIZE ((loff_t)LLONG_MAX)
#endif
#define FL_POSIX 1
unsigned char fl_type;
unsigned int fl_pid;
int fl_link_cpu; /* what cpu's list is this on? */
- struct pid *fl_nspid;
wait_queue_head_t fl_wait;
struct file *fl_file;
loff_t fl_start;
int state; /* state of grant or error if -ve */
} afs;
} fl_u;
-};
+} __randomize_layout;
struct file_lock_context {
spinlock_t flc_lock;
spinlock_t s_inode_wblist_lock;
struct list_head s_inodes_wb; /* writeback inodes */
-};
+} __randomize_layout;
/* Helper functions so that in most cases filesystems will
* not need to deal directly with kuid_t and kgid_t and can
u64);
ssize_t (*dedupe_file_range)(struct file *, u64, u64, struct file *,
u64);
-};
+} __randomize_layout;
struct inode_operations {
struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
- unsigned long, loff_t *, int);
+ unsigned long, loff_t *, rwf_t);
extern ssize_t vfs_writev(struct file *, const struct iovec __user *,
- unsigned long, loff_t *, int);
+ unsigned long, loff_t *, rwf_t);
extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
loff_t, size_t, unsigned int);
extern int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in,
#endif
/* fs/char_dev.c */
-#define CHRDEV_MAJOR_HASH_SIZE 255
+#define CHRDEV_MAJOR_MAX 512
/* Marks the bottom of the first segment of free char majors */
#define CHRDEV_MAJOR_DYN_END 234
+/* Marks the top and bottom of the second segment of free char majors */
+#define CHRDEV_MAJOR_DYN_EXT_START 511
+#define CHRDEV_MAJOR_DYN_EXT_END 384
+
extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *);
extern int register_chrdev_region(dev_t, unsigned, const char *);
extern int __register_chrdev(unsigned int major, unsigned int baseminor,
#define BDEVT_SIZE 10 /* Largest string for MAJ:MIN for blkdev */
#ifdef CONFIG_BLOCK
-#define BLKDEV_MAJOR_HASH_SIZE 255
+#define BLKDEV_MAJOR_MAX 512
extern const char *__bdevname(dev_t, char *buffer);
extern const char *bdevname(struct block_device *bdev, char *buffer);
extern struct block_device *lookup_bdev(const char *);
extern void blkdev_show(struct seq_file *,off_t);
#else
-#define BLKDEV_MAJOR_HASH_SIZE 0
+#define BLKDEV_MAJOR_MAX 0
#endif
extern void init_special_inode(struct inode *, umode_t, dev_t);
extern int write_inode_now(struct inode *, int);
extern int filemap_fdatawrite(struct address_space *);
extern int filemap_flush(struct address_space *);
- extern int filemap_fdatawait(struct address_space *);
extern int filemap_fdatawait_keep_errors(struct address_space *mapping);
extern int filemap_fdatawait_range(struct address_space *, loff_t lstart,
loff_t lend);
+
+ static inline int filemap_fdatawait(struct address_space *mapping)
+ {
+ return filemap_fdatawait_range(mapping, 0, LLONG_MAX);
+ }
+
extern bool filemap_range_has_page(struct address_space *, loff_t lstart,
loff_t lend);
+ extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart,
+ loff_t lend);
extern int filemap_write_and_wait(struct address_space *mapping);
extern int filemap_write_and_wait_range(struct address_space *mapping,
loff_t lstart, loff_t lend);
extern int filemap_fdatawrite_range(struct address_space *mapping,
loff_t start, loff_t end);
extern int filemap_check_errors(struct address_space *mapping);
-
extern void __filemap_set_wb_err(struct address_space *mapping, int err);
+
+ extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart,
+ loff_t lend);
extern int __must_check file_check_and_advance_wb_err(struct file *file);
extern int __must_check file_write_and_wait_range(struct file *file,
loff_t start, loff_t end);
+ static inline int file_write_and_wait(struct file *file)
+ {
+ return file_write_and_wait_range(file, 0, LLONG_MAX);
+ }
+
/**
* filemap_set_wb_err - set a writeback error on an address_space
* @mapping: mapping in which to set writeback error
* When a writeback error occurs, most filesystems will want to call
* filemap_set_wb_err to record the error in the mapping so that it will be
* automatically reported whenever fsync is called on the file.
- *
- * FIXME: mention FS_* flag here?
*/
static inline void filemap_set_wb_err(struct address_space *mapping, int err)
{
#endif
extern void unlock_new_inode(struct inode *);
extern unsigned int get_next_ino(void);
+extern void evict_inodes(struct super_block *sb);
extern void __iget(struct inode * inode);
extern void iget_failed(struct inode *);
extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t);
ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos,
- int flags);
+ rwf_t flags);
ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
- int flags);
+ rwf_t flags);
/* fs/block_dev.c */
extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to);
return res;
}
-static inline int kiocb_set_rw_flags(struct kiocb *ki, int flags)
+static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
{
if (unlikely(flags & ~RWF_SUPPORTED))
return -EOPNOTSUPP;
}
EXPORT_SYMBOL(filemap_fdatawait_range);
+ /**
+ * file_fdatawait_range - wait for writeback to complete
+ * @file: file pointing to address space structure to wait for
+ * @start_byte: offset in bytes where the range starts
+ * @end_byte: offset in bytes where the range ends (inclusive)
+ *
+ * Walk the list of under-writeback pages of the address space that file
+ * refers to, in the given range and wait for all of them. Check error
+ * status of the address space vs. the file->f_wb_err cursor and return it.
+ *
+ * Since the error status of the file is advanced by this function,
+ * callers are responsible for checking the return value and handling and/or
+ * reporting the error.
+ */
+ int file_fdatawait_range(struct file *file, loff_t start_byte, loff_t end_byte)
+ {
+ struct address_space *mapping = file->f_mapping;
+
+ __filemap_fdatawait_range(mapping, start_byte, end_byte);
+ return file_check_and_advance_wb_err(file);
+ }
+ EXPORT_SYMBOL(file_fdatawait_range);
+
/**
* filemap_fdatawait_keep_errors - wait for writeback without clearing errors
* @mapping: address space structure to wait for
*/
int filemap_fdatawait_keep_errors(struct address_space *mapping)
{
- loff_t i_size = i_size_read(mapping->host);
-
- if (i_size == 0)
- return 0;
-
- __filemap_fdatawait_range(mapping, 0, i_size - 1);
+ __filemap_fdatawait_range(mapping, 0, LLONG_MAX);
return filemap_check_and_keep_errors(mapping);
}
EXPORT_SYMBOL(filemap_fdatawait_keep_errors);
- /**
- * filemap_fdatawait - wait for all under-writeback pages to complete
- * @mapping: address space structure to wait for
- *
- * Walk the list of under-writeback pages of the given address space
- * and wait for all of them. Check error status of the address space
- * and return it.
- *
- * Since the error status of the address space is cleared by this function,
- * callers are responsible for checking the return value and handling and/or
- * reporting the error.
- */
- int filemap_fdatawait(struct address_space *mapping)
+ static bool mapping_needs_writeback(struct address_space *mapping)
{
- loff_t i_size = i_size_read(mapping->host);
-
- if (i_size == 0)
- return 0;
-
- return filemap_fdatawait_range(mapping, 0, i_size - 1);
+ return (!dax_mapping(mapping) && mapping->nrpages) ||
+ (dax_mapping(mapping) && mapping->nrexceptional);
}
- EXPORT_SYMBOL(filemap_fdatawait);
int filemap_write_and_wait(struct address_space *mapping)
{
int err = 0;
- if ((!dax_mapping(mapping) && mapping->nrpages) ||
- (dax_mapping(mapping) && mapping->nrexceptional)) {
+ if (mapping_needs_writeback(mapping)) {
err = filemap_fdatawrite(mapping);
/*
* Even if the above returned error, the pages may be
{
int err = 0;
- if ((!dax_mapping(mapping) && mapping->nrpages) ||
- (dax_mapping(mapping) && mapping->nrexceptional)) {
+ if (mapping_needs_writeback(mapping)) {
err = __filemap_fdatawrite_range(mapping, lstart, lend,
WB_SYNC_ALL);
/* See comment of filemap_write_and_wait() */
void __filemap_set_wb_err(struct address_space *mapping, int err)
{
- errseq_t eseq = __errseq_set(&mapping->wb_err, err);
+ errseq_t eseq = errseq_set(&mapping->wb_err, err);
trace_filemap_set_wb_err(mapping, eseq);
}
int err = 0, err2;
struct address_space *mapping = file->f_mapping;
- if ((!dax_mapping(mapping) && mapping->nrpages) ||
- (dax_mapping(mapping) && mapping->nrexceptional)) {
+ if (mapping_needs_writeback(mapping)) {
err = __filemap_fdatawrite_range(mapping, lstart, lend,
WB_SYNC_ALL);
/* See comment of filemap_write_and_wait() */
page_writeback_init();
}
+/* This has the same layout as wait_bit_key - see fs/cachefiles/rdwr.c */
struct wait_page_key {
struct page *page;
int bit_nr;
if (wait_page->bit_nr != key->bit_nr)
return 0;
+
+ /* Stop walking if it's locked */
if (test_bit(key->bit_nr, &key->page->flags))
- return 0;
+ return -1;
return autoremove_wake_function(wait, mode, sync, key);
}
int ret = 0;
init_wait(wait);
+ wait->flags = lock ? WQ_FLAG_EXCLUSIVE : 0;
wait->func = wake_page_function;
wait_page.page = page;
wait_page.bit_nr = bit_nr;
spin_lock_irq(&q->lock);
if (likely(list_empty(&wait->entry))) {
- if (lock)
- __add_wait_queue_entry_tail_exclusive(q, wait);
- else
- __add_wait_queue(q, wait);
+ __add_wait_queue_entry_tail(q, wait);
SetPageWaiters(page);
}
if (likely(test_bit(bit_nr, &page->flags))) {
io_schedule();
- if (unlikely(signal_pending_state(state, current))) {
- ret = -EINTR;
- break;
- }
}
if (lock) {
if (!test_bit(bit_nr, &page->flags))
break;
}
+
+ if (unlikely(signal_pending_state(state, current))) {
+ ret = -EINTR;
+ break;
+ }
}
finish_wait(q, wait);
unsigned long flags;
spin_lock_irqsave(&q->lock, flags);
- __add_wait_queue(q, waiter);
+ __add_wait_queue_entry_tail(q, waiter);
SetPageWaiters(page);
spin_unlock_irqrestore(&q->lock, flags);
}
projects / linux.git / commitdiff