direct-io: only inc/dec inode->i_dio_count for file systems

[cascardo/linux.git] / include / linux / fs.h

diff --git a/include/linux/fs.h b/include/linux/fs.h
index f4131e8..9055eef 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -314,6 +314,33 @@ struct page;
 struct address_space;
 struct writeback_control;
 
+#define IOCB_EVENTFD           (1 << 0)
+#define IOCB_APPEND            (1 << 1)
+#define IOCB_DIRECT            (1 << 2)
+
+struct kiocb {
+       struct file             *ki_filp;
+       loff_t                  ki_pos;
+       void (*ki_complete)(struct kiocb *iocb, long ret, long ret2);
+       void                    *private;
+       int                     ki_flags;
+};
+
+static inline bool is_sync_kiocb(struct kiocb *kiocb)
+{
+       return kiocb->ki_complete == NULL;
+}
+
+static inline int iocb_flags(struct file *file);
+
+static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
+{
+       *kiocb = (struct kiocb) {
+               .ki_filp = filp,
+               .ki_flags = iocb_flags(filp),
+       };
+}
+
 /*
  * "descriptor" for what we're up to with a read.
  * This allows us to use the same read code yet
@@ -361,7 +388,7 @@ struct address_space_operations {
        void (*invalidatepage) (struct page *, unsigned int, unsigned int);
        int (*releasepage) (struct page *, gfp_t);
        void (*freepage)(struct page *);
-       ssize_t (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset);
+       ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter, loff_t offset);
        /*
         * migrate the contents of a page to the specified target. If
         * migrate_mode is MIGRATE_ASYNC, it must not block.
@@ -1540,8 +1567,6 @@ struct file_operations {
        loff_t (*llseek) (struct file *, loff_t, int);
        ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
        ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
-       ssize_t (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
-       ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t);
        ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
        ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
        int (*iterate) (struct file *, struct dir_context *);
@@ -1549,7 +1574,7 @@ struct file_operations {
        long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
        long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
        int (*mmap) (struct file *, struct vm_area_struct *);
-       void (*mremap)(struct file *, struct vm_area_struct *);
+       int (*mremap)(struct file *, struct vm_area_struct *);
        int (*open) (struct inode *, struct file *);
        int (*flush) (struct file *, fl_owner_t id);
        int (*release) (struct inode *, struct file *);
@@ -1617,6 +1642,7 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
                              struct iovec **ret_pointer);
 
 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_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 *,
@@ -2145,7 +2171,7 @@ struct filename {
        const __user char       *uptr;  /* original userland pointer */
        struct audit_names      *aname;
        int                     refcnt;
-       bool                    separate; /* should "name" be freed? */
+       const char              iname[];
 };
 
 extern long vfs_truncate(struct path *, loff_t);
@@ -2545,16 +2571,12 @@ extern int sb_min_blocksize(struct super_block *, int);
 
 extern int generic_file_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
-int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
+extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *);
 extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *, loff_t);
 extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t);
-extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos);
-extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos);
-extern ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos);
-extern ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos);
 
 ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos);
 ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos);
@@ -2592,8 +2614,8 @@ extern loff_t fixed_size_llseek(struct file *file, loff_t offset,
 extern int generic_file_open(struct inode * inode, struct file * filp);
 extern int nonseekable_open(struct inode * inode, struct file * filp);
 
-ssize_t dax_do_io(int rw, struct kiocb *, struct inode *, struct iov_iter *,
-               loff_t, get_block_t, dio_iodone_t, int flags);
+ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t,
+                 get_block_t, dio_iodone_t, int flags);
 int dax_clear_blocks(struct inode *, sector_t block, long size);
 int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
 int dax_truncate_page(struct inode *, loff_t from, get_block_t);
@@ -2613,27 +2635,56 @@ enum {
 
        /* filesystem can handle aio writes beyond i_size */
        DIO_ASYNC_EXTEND = 0x04,
+
+       /* inode/fs/bdev does not need truncate protection */
+       DIO_SKIP_DIO_COUNT = 0x08,
 };
 
 void dio_end_io(struct bio *bio, int error);
 
-ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
-       struct block_device *bdev, struct iov_iter *iter, loff_t offset,
-       get_block_t get_block, dio_iodone_t end_io,
-       dio_submit_t submit_io, int flags);
+ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
+                            struct block_device *bdev, struct iov_iter *iter,
+                            loff_t offset, get_block_t get_block,
+                            dio_iodone_t end_io, dio_submit_t submit_io,
+                            int flags);
 
-static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
-               struct inode *inode, struct iov_iter *iter, loff_t offset,
-               get_block_t get_block)
+static inline ssize_t blockdev_direct_IO(struct kiocb *iocb,
+                                        struct inode *inode,
+                                        struct iov_iter *iter, loff_t offset,
+                                        get_block_t get_block)
 {
-       return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iter,
+       return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
                                    offset, get_block, NULL, NULL,
                                    DIO_LOCKING | DIO_SKIP_HOLES);
 }
 #endif
 
 void inode_dio_wait(struct inode *inode);
-void inode_dio_done(struct inode *inode);
+
+/*
+ * inode_dio_begin - signal start of a direct I/O requests
+ * @inode: inode the direct I/O happens on
+ *
+ * This is called once we've finished processing a direct I/O request,
+ * and is used to wake up callers waiting for direct I/O to be quiesced.
+ */
+static inline void inode_dio_begin(struct inode *inode)
+{
+       atomic_inc(&inode->i_dio_count);
+}
+
+/*
+ * inode_dio_end - signal finish of a direct I/O requests
+ * @inode: inode the direct I/O happens on
+ *
+ * This is called once we've finished processing a direct I/O request,
+ * and is used to wake up callers waiting for direct I/O to be quiesced.
+ */
+static inline void inode_dio_end(struct inode *inode)
+{
+       if (atomic_dec_and_test(&inode->i_dio_count))
+               wake_up_bit(&inode->i_state, __I_DIO_WAKEUP);
+}
 
 extern void inode_set_flags(struct inode *inode, unsigned int flags,
                            unsigned int mask);
@@ -2760,6 +2811,16 @@ static inline bool io_is_direct(struct file *filp)
        return (filp->f_flags & O_DIRECT) || IS_DAX(file_inode(filp));
 }
 
+static inline int iocb_flags(struct file *file)
+{
+       int res = 0;
+       if (file->f_flags & O_APPEND)
+               res |= IOCB_APPEND;
+       if (io_is_direct(file))
+               res |= IOCB_DIRECT;
+       return res;
+}
+
 static inline ino_t parent_ino(struct dentry *dentry)
 {
        ino_t res;