Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull VFS changes from Al Viro:
 "First pile out of several (there _definitely_ will be more).  Stuff in
  this one:

   - unification of d_splice_alias()/d_materialize_unique()

   - iov_iter rewrite

   - killing a bunch of ->f_path.dentry users (and f_dentry macro).

     Getting that completed will make life much simpler for
     unionmount/overlayfs, since then we'll be able to limit the places
     sensitive to file _dentry_ to reasonably few.  Which allows to have
     file_inode(file) pointing to inode in a covered layer, with dentry
     pointing to (negative) dentry in union one.

     Still not complete, but much closer now.

   - crapectomy in lustre (dead code removal, mostly)

   - "let's make seq_printf return nothing" preparations

   - assorted cleanups and fixes

  There _definitely_ will be more piles"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (63 commits)
  copy_from_iter_nocache()
  new helper: iov_iter_kvec()
  csum_and_copy_..._iter()
  iov_iter.c: handle ITER_KVEC directly
  iov_iter.c: convert copy_to_iter() to iterate_and_advance
  iov_iter.c: convert copy_from_iter() to iterate_and_advance
  iov_iter.c: get rid of bvec_copy_page_{to,from}_iter()
  iov_iter.c: convert iov_iter_zero() to iterate_and_advance
  iov_iter.c: convert iov_iter_get_pages_alloc() to iterate_all_kinds
  iov_iter.c: convert iov_iter_get_pages() to iterate_all_kinds
  iov_iter.c: convert iov_iter_npages() to iterate_all_kinds
  iov_iter.c: iterate_and_advance
  iov_iter.c: macros for iterating over iov_iter
  kill f_dentry macro
  dcache: fix kmemcheck warning in switch_names
  new helper: audit_file()
  nfsd_vfs_write(): use file_inode()
  ncpfs: use file_inode()
  kill f_dentry uses
  lockd: get rid of ->f_path.dentry->d_sb
  ...

Documentation/filesystems/debugfs.txt

@@ -140,7 +140,7 @@ file.
 				     struct dentry *parent,
 				     struct debugfs_regset32 *regset);
 
-    int debugfs_print_regs32(struct seq_file *s, struct debugfs_reg32 *regs,
+    void debugfs_print_regs32(struct seq_file *s, struct debugfs_reg32 *regs,
 			 int nregs, void __iomem *base, char *prefix);
 
 The "base" argument may be 0, but you may want to build the reg32 array

Documentation/filesystems/nfs/Exporting

@@ -72,24 +72,11 @@ c/ Helper routines to allocate anonymous dentries, and to help attach
         DCACHE_DISCONNECTED) dentry is allocated and attached.
       In the case of a directory, care is taken that only one dentry
       can ever be attached.
-    d_splice_alias(inode, dentry) or d_materialise_unique(dentry, inode)
-      will introduce a new dentry into the tree; either the passed-in
-      dentry or a preexisting alias for the given inode (such as an
-      anonymous one created by d_obtain_alias), if appropriate.  The two
-      functions differ in their handling of directories with preexisting
-      aliases:
-        d_splice_alias will use any existing IS_ROOT dentry, but it will
-	  return -EIO rather than try to move a dentry with a different
-	  parent.  This is appropriate for local filesystems, which
-	  should never see such an alias unless the filesystem is
-	  corrupted somehow (for example, if two on-disk directory
-	  entries refer to the same directory.)
-	d_materialise_unique will attempt to move any dentry.  This is
-	  appropriate for distributed filesystems, where finding a
-	  directory other than where we last cached it may be a normal
-	  consequence of concurrent operations on other hosts.
-      Both functions return NULL when the passed-in dentry is used,
-      following the calling convention of ->lookup.
+    d_splice_alias(inode, dentry) will introduce a new dentry into the tree;
+      either the passed-in dentry or a preexisting alias for the given inode
+      (such as an anonymous one created by d_obtain_alias), if appropriate.
+      It returns NULL when the passed-in dentry is used, following the calling
+      convention of ->lookup.
 
  
 Filesystem Issues

Documentation/filesystems/porting

@@ -463,3 +463,11 @@ in your dentry operations instead.
 	of the in-tree instances did).  inode_hash_lock is still held,
 	of course, so they are still serialized wrt removal from inode hash,
 	as well as wrt set() callback of iget5_locked().
+--
+[mandatory]
+	d_materialise_unique() is gone; d_splice_alias() does everything you
+	need now.  Remember that they have opposite orders of arguments ;-/
+--
+[mandatory]
+	f_dentry is gone; use f_path.dentry, or, better yet, see if you can avoid
+	it entirely.

Documentation/filesystems/seq_file.txt

@@ -180,23 +180,19 @@ output must be passed to the seq_file code. Some utility functions have
 been defined which make this task easy.
 
 Most code will simply use seq_printf(), which works pretty much like
-printk(), but which requires the seq_file pointer as an argument. It is
-common to ignore the return value from seq_printf(), but a function
-producing complicated output may want to check that value and quit if
-something non-zero is returned; an error return means that the seq_file
-buffer has been filled and further output will be discarded.
+printk(), but which requires the seq_file pointer as an argument.
 
 For straight character output, the following functions may be used:
 
-	int seq_putc(struct seq_file *m, char c);
-	int seq_puts(struct seq_file *m, const char *s);
-	int seq_escape(struct seq_file *m, const char *s, const char *esc);
+	seq_putc(struct seq_file *m, char c);
+	seq_puts(struct seq_file *m, const char *s);
+	seq_escape(struct seq_file *m, const char *s, const char *esc);
 
 The first two output a single character and a string, just like one would
 expect. seq_escape() is like seq_puts(), except that any character in s
 which is in the string esc will be represented in octal form in the output.
 
-There is also a pair of functions for printing filenames:
+There are also a pair of functions for printing filenames:
 
 	int seq_path(struct seq_file *m, struct path *path, char *esc);
 	int seq_path_root(struct seq_file *m, struct path *path,
@@ -209,6 +205,14 @@ root is desired, it can be used with seq_path_root().  Note that, if it
 turns out that path cannot be reached from root, the value of root will be
 changed in seq_file_root() to a root which *does* work.
 
+A function producing complicated output may want to check
+	bool seq_has_overflowed(struct seq_file *m);
+and avoid further seq_<output> calls if true is returned.
+
+A true return from seq_has_overflowed means that the seq_file buffer will
+be discarded and the seq_show function will attempt to allocate a larger
+buffer and retry printing.
+
 
 Making it all work
 

Documentation/filesystems/vfs.txt

@@ -835,7 +835,7 @@ struct file_operations {
 	ssize_t (*splice_read)(struct file *, struct pipe_inode_info *, size_t, unsigned int);
 	int (*setlease)(struct file *, long arg, struct file_lock **, void **);
 	long (*fallocate)(struct file *, int mode, loff_t offset, loff_t len);
-	int (*show_fdinfo)(struct seq_file *m, struct file *f);
+	void (*show_fdinfo)(struct seq_file *m, struct file *f);
 };
 
 Again, all methods are called without any locks being held, unless

arch/alpha/kernel/osf_sys.c

@@ -104,11 +104,12 @@ struct osf_dirent_callback {
 };
 
 static int
-osf_filldir(void *__buf, const char *name, int namlen, loff_t offset,
-	    u64 ino, unsigned int d_type)
+osf_filldir(struct dir_context *ctx, const char *name, int namlen,
+	    loff_t offset, u64 ino, unsigned int d_type)
 {
 	struct osf_dirent __user *dirent;
-	struct osf_dirent_callback *buf = (struct osf_dirent_callback *) __buf;
+	struct osf_dirent_callback *buf =
+		container_of(ctx, struct osf_dirent_callback, ctx);
 	unsigned int reclen = ALIGN(NAME_OFFSET + namlen + 1, sizeof(u32));
 	unsigned int d_ino;
 

arch/parisc/hpux/fs.c

@@ -56,11 +56,12 @@ struct getdents_callback {
 
 #define NAME_OFFSET(de) ((int) ((de)->d_name - (char __user *) (de)))
 
-static int filldir(void * __buf, const char * name, int namlen, loff_t offset,
-		u64 ino, unsigned d_type)
+static int filldir(struct dir_context *ctx, const char *name, int namlen,
+		   loff_t offset, u64 ino, unsigned d_type)
 {
 	struct hpux_dirent __user * dirent;
-	struct getdents_callback * buf = (struct getdents_callback *) __buf;
+	struct getdents_callback *buf =
+		container_of(ctx, struct getdents_callback, ctx);
 	ino_t d_ino;
 	int reclen = ALIGN(NAME_OFFSET(dirent) + namlen + 1, sizeof(long));
 

arch/powerpc/oprofile/cell/spu_task_sync.c

@@ -331,8 +331,7 @@ get_exec_dcookie_and_offset(struct spu *spu, unsigned int *offsetp,
 
 	if (mm->exe_file) {
 		app_cookie = fast_get_dcookie(&mm->exe_file->f_path);
-		pr_debug("got dcookie for %s\n",
-			 mm->exe_file->f_dentry->d_name.name);
+		pr_debug("got dcookie for %pD\n", mm->exe_file);
 	}
 
 	for (vma = mm->mmap; vma; vma = vma->vm_next) {
@@ -342,15 +341,14 @@ get_exec_dcookie_and_offset(struct spu *spu, unsigned int *offsetp,
 		if (!vma->vm_file)
 			goto fail_no_image_cookie;
 
-		pr_debug("Found spu ELF at %X(object-id:%lx) for file %s\n",
-			 my_offset, spu_ref,
-			 vma->vm_file->f_dentry->d_name.name);
+		pr_debug("Found spu ELF at %X(object-id:%lx) for file %pD\n",
+			 my_offset, spu_ref, vma->vm_file);
 		*offsetp = my_offset;
 		break;
 	}
 
 	*spu_bin_dcookie = fast_get_dcookie(&vma->vm_file->f_path);
-	pr_debug("got dcookie for %s\n", vma->vm_file->f_dentry->d_name.name);
+	pr_debug("got dcookie for %pD\n", vma->vm_file);
 
 	up_read(&mm->mmap_sem);
 

arch/powerpc/platforms/cell/spufs/inode.c

@@ -164,7 +164,7 @@ static void spufs_prune_dir(struct dentry *dir)
 	struct dentry *dentry, *tmp;
 
 	mutex_lock(&dir->d_inode->i_mutex);
-	list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_u.d_child) {
+	list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_child) {
 		spin_lock(&dentry->d_lock);
 		if (!(d_unhashed(dentry)) && dentry->d_inode) {
 			dget_dlock(dentry);

arch/s390/hypfs/hypfs_dbfs.c

@@ -83,10 +83,9 @@ static ssize_t dbfs_read(struct file *file, char __user *buf,
 
 static long dbfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
-	struct hypfs_dbfs_file *df;
+	struct hypfs_dbfs_file *df = file_inode(file)->i_private;
 	long rc;
 
-	df = file->f_path.dentry->d_inode->i_private;
 	mutex_lock(&df->lock);
 	if (df->unlocked_ioctl)
 		rc = df->unlocked_ioctl(file, cmd, arg);

arch/x86/ia32/ia32_aout.c

@@ -342,8 +342,8 @@ static int load_aout_binary(struct linux_binprm *bprm)
 			    time_after(jiffies, error_time + 5*HZ)) {
 			printk(KERN_WARNING
 			       "fd_offset is not page aligned. Please convert "
-			       "program: %s\n",
-			       bprm->file->f_path.dentry->d_name.name);
+			       "program: %pD\n",
+			       bprm->file);
 			error_time = jiffies;
 		}
 #endif
@@ -429,8 +429,8 @@ static int load_aout_library(struct file *file)
 		if (time_after(jiffies, error_time + 5*HZ)) {
 			printk(KERN_WARNING
 			       "N_TXTOFF is not page aligned. Please convert "
-			       "library: %s\n",
-			       file->f_path.dentry->d_name.name);
+			       "library: %pD\n",
+			       file);
 			error_time = jiffies;
 		}
 #endif

drivers/block/drbd/drbd_debugfs.c

@@ -419,7 +419,7 @@ static int in_flight_summary_show(struct seq_file *m, void *pos)
 	return 0;
 }
 
-/* simple_positive(file->f_dentry) respectively debugfs_positive(),
+/* simple_positive(file->f_path.dentry) respectively debugfs_positive(),
  * but neither is "reachable" from here.
  * So we have our own inline version of it above.  :-( */
 static inline int debugfs_positive(struct dentry *dentry)
@@ -437,14 +437,14 @@ static int drbd_single_open(struct file *file, int (*show)(struct seq_file *, vo
 
 	/* Are we still linked,
 	 * or has debugfs_remove() already been called? */
-	parent = file->f_dentry->d_parent;
+	parent = file->f_path.dentry->d_parent;
 	/* not sure if this can happen: */
 	if (!parent || !parent->d_inode)
 		goto out;
 	/* serialize with d_delete() */
 	mutex_lock(&parent->d_inode->i_mutex);
 	/* Make sure the object is still alive */
-	if (debugfs_positive(file->f_dentry)
+	if (debugfs_positive(file->f_path.dentry)
 	&& kref_get_unless_zero(kref))
 		ret = 0;
 	mutex_unlock(&parent->d_inode->i_mutex);

drivers/gpu/drm/armada/armada_gem.c

@@ -226,7 +226,7 @@ struct armada_gem_object *armada_gem_alloc_object(struct drm_device *dev,
 
 	obj->dev_addr = DMA_ERROR_CODE;
 
-	mapping = obj->obj.filp->f_path.dentry->d_inode->i_mapping;
+	mapping = file_inode(obj->obj.filp)->i_mapping;
 	mapping_set_gfp_mask(mapping, GFP_HIGHUSER | __GFP_RECLAIMABLE);
 
 	DRM_DEBUG_DRIVER("alloc obj %p size %zu\n", obj, size);

drivers/media/pci/zoran/zoran_procfs.c

@@ -157,8 +157,8 @@ static ssize_t zoran_write(struct file *file, const char __user *buffer,
 		return -EFAULT;
 	}
 	string[count] = 0;
-	dprintk(4, KERN_INFO "%s: write_proc: name=%s count=%zu zr=%p\n",
-		ZR_DEVNAME(zr), file->f_path.dentry->d_name.name, count, zr);
+	dprintk(4, KERN_INFO "%s: write_proc: name=%pD count=%zu zr=%p\n",
+		ZR_DEVNAME(zr), file, count, zr);
 	ldelim = " \t\n";
 	tdelim = "=";
 	line = strpbrk(sp, ldelim);

drivers/misc/genwqe/card_dev.c

@@ -395,7 +395,7 @@ static void genwqe_vma_open(struct vm_area_struct *vma)
 static void genwqe_vma_close(struct vm_area_struct *vma)
 {
 	unsigned long vsize = vma->vm_end - vma->vm_start;
-	struct inode *inode = vma->vm_file->f_dentry->d_inode;
+	struct inode *inode = file_inode(vma->vm_file);
 	struct dma_mapping *dma_map;
 	struct genwqe_dev *cd = container_of(inode->i_cdev, struct genwqe_dev,
 					    cdev_genwqe);

drivers/net/tun.c

@@ -2222,7 +2222,7 @@ static int tun_chr_close(struct inode *inode, struct file *file)
 }
 
 #ifdef CONFIG_PROC_FS
-static int tun_chr_show_fdinfo(struct seq_file *m, struct file *f)
+static void tun_chr_show_fdinfo(struct seq_file *m, struct file *f)
 {
 	struct tun_struct *tun;
 	struct ifreq ifr;
@@ -2238,7 +2238,7 @@ static int tun_chr_show_fdinfo(struct seq_file *m, struct file *f)
 	if (tun)
 		tun_put(tun);
 
-	return seq_printf(m, "iff:\t%s\n", ifr.ifr_name);
+	seq_printf(m, "iff:\t%s\n", ifr.ifr_name);
 }
 #endif
 

drivers/s390/char/hmcdrv_dev.c

@@ -136,8 +136,7 @@ static int hmcdrv_dev_open(struct inode *inode, struct file *fp)
 	if (rc)
 		module_put(THIS_MODULE);
 
-	pr_debug("open file '/dev/%s' with return code %d\n",
-		 fp->f_dentry->d_name.name, rc);
+	pr_debug("open file '/dev/%pD' with return code %d\n", fp, rc);
 	return rc;
 }
 
@@ -146,7 +145,7 @@ static int hmcdrv_dev_open(struct inode *inode, struct file *fp)
  */
 static int hmcdrv_dev_release(struct inode *inode, struct file *fp)
 {
-	pr_debug("closing file '/dev/%s'\n", fp->f_dentry->d_name.name);
+	pr_debug("closing file '/dev/%pD'\n", fp);
 	kfree(fp->private_data);
 	fp->private_data = NULL;
 	hmcdrv_ftp_shutdown();
@@ -231,8 +230,8 @@ static ssize_t hmcdrv_dev_read(struct file *fp, char __user *ubuf,
 	retlen = hmcdrv_dev_transfer((char *) fp->private_data,
 				     *pos, ubuf, len);
 
-	pr_debug("read from file '/dev/%s' at %lld returns %zd/%zu\n",
-		 fp->f_dentry->d_name.name, (long long) *pos, retlen, len);
+	pr_debug("read from file '/dev/%pD' at %lld returns %zd/%zu\n",
+		 fp, (long long) *pos, retlen, len);
 
 	if (retlen > 0)
 		*pos += retlen;
@@ -248,8 +247,8 @@ static ssize_t hmcdrv_dev_write(struct file *fp, const char __user *ubuf,
 {
 	ssize_t retlen;
 
-	pr_debug("writing file '/dev/%s' at pos. %lld with length %zd\n",
-		 fp->f_dentry->d_name.name, (long long) *pos, len);
+	pr_debug("writing file '/dev/%pD' at pos. %lld with length %zd\n",
+		 fp, (long long) *pos, len);
 
 	if (!fp->private_data) { /* first expect a cmd write */
 		fp->private_data = kmalloc(len + 1, GFP_KERNEL);
@@ -272,8 +271,7 @@ static ssize_t hmcdrv_dev_write(struct file *fp, const char __user *ubuf,
 	if (retlen > 0)
 		*pos += retlen;
 
-	pr_debug("write to file '/dev/%s' returned %zd\n",
-		 fp->f_dentry->d_name.name, retlen);
+	pr_debug("write to file '/dev/%pD' returned %zd\n", fp, retlen);
 
 	return retlen;
 }

drivers/scsi/lpfc/lpfc_debugfs.c

@@ -968,8 +968,8 @@ lpfc_debugfs_dumpDif_open(struct inode *inode, struct file *file)
 		goto out;
 
 	/* Round to page boundary */
-	printk(KERN_ERR	"9060 BLKGRD: %s: _dump_buf_dif=0x%p file=%s\n",
-		__func__, _dump_buf_dif, file->f_dentry->d_name.name);
+	printk(KERN_ERR	"9060 BLKGRD: %s: _dump_buf_dif=0x%p file=%pD\n",
+		__func__, _dump_buf_dif, file);
 	debug->buffer = _dump_buf_dif;
 	if (!debug->buffer) {
 		kfree(debug);
@@ -1011,7 +1011,7 @@ static ssize_t
 lpfc_debugfs_dif_err_read(struct file *file, char __user *buf,
 	size_t nbytes, loff_t *ppos)
 {
-	struct dentry *dent = file->f_dentry;
+	struct dentry *dent = file->f_path.dentry;
 	struct lpfc_hba *phba = file->private_data;
 	char cbuf[32];
 	uint64_t tmp = 0;
@@ -1052,7 +1052,7 @@ static ssize_t
 lpfc_debugfs_dif_err_write(struct file *file, const char __user *buf,
 	size_t nbytes, loff_t *ppos)
 {
-	struct dentry *dent = file->f_dentry;
+	struct dentry *dent = file->f_path.dentry;
 	struct lpfc_hba *phba = file->private_data;
 	char dstbuf[32];
 	uint64_t tmp = 0;

drivers/staging/lustre/lustre/libcfs/tracefile.c

@@ -1025,8 +1025,8 @@ static int tracefiled(void *arg)
 
 			if (f_pos >= (off_t)cfs_tracefile_size)
 				f_pos = 0;
-			else if (f_pos > i_size_read(filp->f_dentry->d_inode))
-				f_pos = i_size_read(filp->f_dentry->d_inode);
+			else if (f_pos > i_size_read(file_inode(filp)))
+				f_pos = i_size_read(file_inode(filp));
 
 			buf = kmap(tage->page);
 			rc = vfs_write(filp, (__force const char __user *)buf,

drivers/staging/lustre/lustre/llite/dcache.c

@@ -151,10 +151,10 @@ static int ll_ddelete(const struct dentry *de)
 {
 	LASSERT(de);
 
-	CDEBUG(D_DENTRY, "%s dentry %.*s (%p, parent %p, inode %p) %s%s\n",
+	CDEBUG(D_DENTRY, "%s dentry %pd (%p, parent %p, inode %p) %s%s\n",
 	       d_lustre_invalid((struct dentry *)de) ? "deleting" : "keeping",
-	       de->d_name.len, de->d_name.name, de, de->d_parent, de->d_inode,
-	       d_unhashed((struct dentry *)de) ? "" : "hashed,",
+	       de, de, de->d_parent, de->d_inode,
+	       d_unhashed(de) ? "" : "hashed,",
 	       list_empty(&de->d_subdirs) ? "" : "subdirs");
 
 	/* kernel >= 2.6.38 last refcount is decreased after this function. */
@@ -180,8 +180,8 @@ int ll_d_init(struct dentry *de)
 {
 	LASSERT(de != NULL);
 
-	CDEBUG(D_DENTRY, "ldd on dentry %.*s (%p) parent %p inode %p refc %d\n",
-		de->d_name.len, de->d_name.name, de, de->d_parent, de->d_inode,
+	CDEBUG(D_DENTRY, "ldd on dentry %pd (%p) parent %p inode %p refc %d\n",
+		de, de, de->d_parent, de->d_inode,
 		d_count(de));
 
 	if (de->d_fsdata == NULL) {
@@ -258,10 +258,9 @@ void ll_invalidate_aliases(struct inode *inode)
 	       inode->i_ino, inode->i_generation, inode);
 
 	ll_lock_dcache(inode);
-	ll_d_hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) {
-		CDEBUG(D_DENTRY, "dentry in drop %.*s (%p) parent %p "
-		       "inode %p flags %d\n", dentry->d_name.len,
-		       dentry->d_name.name, dentry, dentry->d_parent,
+	ll_d_hlist_for_each_entry(dentry, p, &inode->i_dentry, d_u.d_alias) {
+		CDEBUG(D_DENTRY, "dentry in drop %pd (%p) parent %p "
+		       "inode %p flags %d\n", dentry, dentry, dentry->d_parent,
 		       dentry->d_inode, dentry->d_flags);
 
 		if (unlikely(dentry == dentry->d_sb->s_root)) {
@@ -352,8 +351,8 @@ static int ll_revalidate_nd(struct dentry *dentry, unsigned int flags)
 {
 	int rc;
 
-	CDEBUG(D_VFSTRACE, "VFS Op:name=%s, flags=%u\n",
-	       dentry->d_name.name, flags);
+	CDEBUG(D_VFSTRACE, "VFS Op:name=%pd, flags=%u\n",
+	       dentry, flags);
 
 	rc = ll_revalidate_dentry(dentry, flags);
 	return rc;