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

Pull vfs updates from Al Viro:
 "The first vfs pile, with deep apologies for being very late in this
  window.

  Assorted cleanups and fixes, plus a large preparatory part of iov_iter
  work.  There's a lot more of that, but it'll probably go into the next
  merge window - it *does* shape up nicely, removes a lot of
  boilerplate, gets rid of locking inconsistencie between aio_write and
  splice_write and I hope to get Kent's direct-io rewrite merged into
  the same queue, but some of the stuff after this point is having
  (mostly trivial) conflicts with the things already merged into
  mainline and with some I want more testing.

  This one passes LTP and xfstests without regressions, in addition to
  usual beating.  BTW, readahead02 in ltp syscalls testsuite has started
  giving failures since "mm/readahead.c: fix readahead failure for
  memoryless NUMA nodes and limit readahead pages" - might be a false
  positive, might be a real regression..."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (63 commits)
  missing bits of "splice: fix racy pipe->buffers uses"
  cifs: fix the race in cifs_writev()
  ceph_sync_{,direct_}write: fix an oops on ceph_osdc_new_request() failure
  kill generic_file_buffered_write()
  ocfs2_file_aio_write(): switch to generic_perform_write()
  ceph_aio_write(): switch to generic_perform_write()
  xfs_file_buffered_aio_write(): switch to generic_perform_write()
  export generic_perform_write(), start getting rid of generic_file_buffer_write()
  generic_file_direct_write(): get rid of ppos argument
  btrfs_file_aio_write(): get rid of ppos
  kill the 5th argument of generic_file_buffered_write()
  kill the 4th argument of __generic_file_aio_write()
  lustre: don't open-code kernel_recvmsg()
  ocfs2: don't open-code kernel_recvmsg()
  drbd: don't open-code kernel_recvmsg()
  constify blk_rq_map_user_iov() and friends
  lustre: switch to kernel_sendmsg()
  ocfs2: don't open-code kernel_sendmsg()
  take iov_iter stuff to mm/iov_iter.c
  process_vm_access: tidy up a bit
  ...

1 files changed, 76 insertions, 174 deletions

diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index cb79065..8505c92 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -23,129 +23,44 @@
 
 /**
  * process_vm_rw_pages - read/write pages from task specified
- * @task: task to read/write from
- * @mm: mm for task
- * @process_pages: struct pages area that can store at least
- *  nr_pages_to_copy struct page pointers
- * @pa: address of page in task to start copying from/to
+ * @pages: array of pointers to pages we want to copy
  * @start_offset: offset in page to start copying from/to
  * @len: number of bytes to copy
- * @lvec: iovec array specifying where to copy to/from
- * @lvec_cnt: number of elements in iovec array
- * @lvec_current: index in iovec array we are up to
- * @lvec_offset: offset in bytes from current iovec iov_base we are up to
+ * @iter: where to copy to/from locally
  * @vm_write: 0 means copy from, 1 means copy to
- * @nr_pages_to_copy: number of pages to copy
- * @bytes_copied: returns number of bytes successfully copied
  * Returns 0 on success, error code otherwise
  */
-static int process_vm_rw_pages(struct task_struct *task,
-			       struct mm_struct *mm,
-			       struct page **process_pages,
-			       unsigned long pa,
-			       unsigned long start_offset,
-			       unsigned long len,
-			       const struct iovec *lvec,
-			       unsigned long lvec_cnt,
-			       unsigned long *lvec_current,
-			       size_t *lvec_offset,
-			       int vm_write,
-			       unsigned int nr_pages_to_copy,
-			       ssize_t *bytes_copied)
+static int process_vm_rw_pages(struct page **pages,
+			       unsigned offset,
+			       size_t len,
+			       struct iov_iter *iter,
+			       int vm_write)
 {
-	int pages_pinned;
-	void *target_kaddr;
-	int pgs_copied = 0;
-	int j;
-	int ret;
-	ssize_t bytes_to_copy;
-	ssize_t rc = 0;
-
-	*bytes_copied = 0;
-
-	/* Get the pages we're interested in */
-	down_read(&mm->mmap_sem);
-	pages_pinned = get_user_pages(task, mm, pa,
-				      nr_pages_to_copy,
-				      vm_write, 0, process_pages, NULL);
-	up_read(&mm->mmap_sem);
-
-	if (pages_pinned != nr_pages_to_copy) {
-		rc = -EFAULT;
-		goto end;
-	}
-
 	/* Do the copy for each page */
-	for (pgs_copied = 0;
-	     (pgs_copied < nr_pages_to_copy) && (*lvec_current < lvec_cnt);
-	     pgs_copied++) {
-		/* Make sure we have a non zero length iovec */
-		while (*lvec_current < lvec_cnt
-		       && lvec[*lvec_current].iov_len == 0)
-			(*lvec_current)++;
-		if (*lvec_current == lvec_cnt)
-			break;
-
-		/*
-		 * Will copy smallest of:
-		 * - bytes remaining in page
-		 * - bytes remaining in destination iovec
-		 */
-		bytes_to_copy = min_t(ssize_t, PAGE_SIZE - start_offset,
-				      len - *bytes_copied);
-		bytes_to_copy = min_t(ssize_t, bytes_to_copy,
-				      lvec[*lvec_current].iov_len
-				      - *lvec_offset);
-
-		target_kaddr = kmap(process_pages[pgs_copied]) + start_offset;
-
-		if (vm_write)
-			ret = copy_from_user(target_kaddr,
-					     lvec[*lvec_current].iov_base
-					     + *lvec_offset,
-					     bytes_to_copy);
-		else
-			ret = copy_to_user(lvec[*lvec_current].iov_base
-					   + *lvec_offset,
-					   target_kaddr, bytes_to_copy);
-		kunmap(process_pages[pgs_copied]);
-		if (ret) {
-			*bytes_copied += bytes_to_copy - ret;
-			pgs_copied++;
-			rc = -EFAULT;
-			goto end;
-		}
-		*bytes_copied += bytes_to_copy;
-		*lvec_offset += bytes_to_copy;
-		if (*lvec_offset == lvec[*lvec_current].iov_len) {
-			/*
-			 * Need to copy remaining part of page into the
-			 * next iovec if there are any bytes left in page
-			 */
-			(*lvec_current)++;
-			*lvec_offset = 0;
-			start_offset = (start_offset + bytes_to_copy)
-				% PAGE_SIZE;
-			if (start_offset)
-				pgs_copied--;
+	while (len && iov_iter_count(iter)) {
+		struct page *page = *pages++;
+		size_t copy = PAGE_SIZE - offset;
+		size_t copied;
+
+		if (copy > len)
+			copy = len;
+
+		if (vm_write) {
+			if (copy > iov_iter_count(iter))
+				copy = iov_iter_count(iter);
+			copied = iov_iter_copy_from_user(page, iter,
+					offset, copy);
+			iov_iter_advance(iter, copied);
+			set_page_dirty_lock(page);
 		} else {
-			start_offset = 0;
-		}
-	}
-
-end:
-	if (vm_write) {
-		for (j = 0; j < pages_pinned; j++) {
-			if (j < pgs_copied)
-				set_page_dirty_lock(process_pages[j]);
-			put_page(process_pages[j]);
+			copied = copy_page_to_iter(page, offset, copy, iter);
 		}
-	} else {
-		for (j = 0; j < pages_pinned; j++)
-			put_page(process_pages[j]);
+		len -= copied;
+		if (copied < copy && iov_iter_count(iter))
+			return -EFAULT;
+		offset = 0;
 	}
-
-	return rc;
+	return 0;
 }
 
 /* Maximum number of pages kmalloc'd to hold struct page's during copy */
@@ -155,67 +70,60 @@ end:
  * process_vm_rw_single_vec - read/write pages from task specified
  * @addr: start memory address of target process
  * @len: size of area to copy to/from
- * @lvec: iovec array specifying where to copy to/from locally
- * @lvec_cnt: number of elements in iovec array
- * @lvec_current: index in iovec array we are up to
- * @lvec_offset: offset in bytes from current iovec iov_base we are up to
+ * @iter: where to copy to/from locally
  * @process_pages: struct pages area that can store at least
  *  nr_pages_to_copy struct page pointers
  * @mm: mm for task
  * @task: task to read/write from
  * @vm_write: 0 means copy from, 1 means copy to
- * @bytes_copied: returns number of bytes successfully copied
  * Returns 0 on success or on failure error code
  */
 static int process_vm_rw_single_vec(unsigned long addr,
 				    unsigned long len,
-				    const struct iovec *lvec,
-				    unsigned long lvec_cnt,
-				    unsigned long *lvec_current,
-				    size_t *lvec_offset,
+				    struct iov_iter *iter,
 				    struct page **process_pages,
 				    struct mm_struct *mm,
 				    struct task_struct *task,
-				    int vm_write,
-				    ssize_t *bytes_copied)
+				    int vm_write)
 {
 	unsigned long pa = addr & PAGE_MASK;
 	unsigned long start_offset = addr - pa;
 	unsigned long nr_pages;
-	ssize_t bytes_copied_loop;
 	ssize_t rc = 0;
-	unsigned long nr_pages_copied = 0;
-	unsigned long nr_pages_to_copy;
 	unsigned long max_pages_per_loop = PVM_MAX_KMALLOC_PAGES
 		/ sizeof(struct pages *);
 
-	*bytes_copied = 0;
-
 	/* Work out address and page range required */
 	if (len == 0)
 		return 0;
 	nr_pages = (addr + len - 1) / PAGE_SIZE - addr / PAGE_SIZE + 1;
 
-	while ((nr_pages_copied < nr_pages) && (*lvec_current < lvec_cnt)) {
-		nr_pages_to_copy = min(nr_pages - nr_pages_copied,
-				       max_pages_per_loop);
+	while (!rc && nr_pages && iov_iter_count(iter)) {
+		int pages = min(nr_pages, max_pages_per_loop);
+		size_t bytes;
 
-		rc = process_vm_rw_pages(task, mm, process_pages, pa,
-					 start_offset, len,
-					 lvec, lvec_cnt,
-					 lvec_current, lvec_offset,
-					 vm_write, nr_pages_to_copy,
-					 &bytes_copied_loop);
-		start_offset = 0;
-		*bytes_copied += bytes_copied_loop;
+		/* Get the pages we're interested in */
+		down_read(&mm->mmap_sem);
+		pages = get_user_pages(task, mm, pa, pages,
+				      vm_write, 0, process_pages, NULL);
+		up_read(&mm->mmap_sem);
 
-		if (rc < 0) {
-			return rc;
-		} else {
-			len -= bytes_copied_loop;
-			nr_pages_copied += nr_pages_to_copy;
-			pa += nr_pages_to_copy * PAGE_SIZE;
-		}
+		if (pages <= 0)
+			return -EFAULT;
+
+		bytes = pages * PAGE_SIZE - start_offset;
+		if (bytes > len)
+			bytes = len;
+
+		rc = process_vm_rw_pages(process_pages,
+					 start_offset, bytes, iter,
+					 vm_write);
+		len -= bytes;
+		start_offset = 0;
+		nr_pages -= pages;
+		pa += pages * PAGE_SIZE;
+		while (pages)
+			put_page(process_pages[--pages]);
 	}
 
 	return rc;
@@ -228,8 +136,7 @@ static int process_vm_rw_single_vec(unsigned long addr,
 /**
  * process_vm_rw_core - core of reading/writing pages from task specified
  * @pid: PID of process to read/write from/to
- * @lvec: iovec array specifying where to copy to/from locally
- * @liovcnt: size of lvec array
+ * @iter: where to copy to/from locally
  * @rvec: iovec array specifying where to copy to/from in the other process
  * @riovcnt: size of rvec array
  * @flags: currently unused
@@ -238,8 +145,7 @@ static int process_vm_rw_single_vec(unsigned long addr,
  *  return less bytes than expected if an error occurs during the copying
  *  process.
  */
-static ssize_t process_vm_rw_core(pid_t pid, const struct iovec *lvec,
-				  unsigned long liovcnt,
+static ssize_t process_vm_rw_core(pid_t pid, struct iov_iter *iter,
 				  const struct iovec *rvec,
 				  unsigned long riovcnt,
 				  unsigned long flags, int vm_write)
@@ -250,13 +156,10 @@ static ssize_t process_vm_rw_core(pid_t pid, const struct iovec *lvec,
 	struct mm_struct *mm;
 	unsigned long i;
 	ssize_t rc = 0;
-	ssize_t bytes_copied_loop;
-	ssize_t bytes_copied = 0;
 	unsigned long nr_pages = 0;
 	unsigned long nr_pages_iov;
-	unsigned long iov_l_curr_idx = 0;
-	size_t iov_l_curr_offset = 0;
 	ssize_t iov_len;
+	size_t total_len = iov_iter_count(iter);
 
 	/*
 	 * Work out how many pages of struct pages we're going to need
@@ -310,24 +213,20 @@ static ssize_t process_vm_rw_core(pid_t pid, const struct iovec *lvec,
 		goto put_task_struct;
 	}
 
-	for (i = 0; i < riovcnt && iov_l_curr_idx < liovcnt; i++) {
+	for (i = 0; i < riovcnt && iov_iter_count(iter) && !rc; i++)
 		rc = process_vm_rw_single_vec(
 			(unsigned long)rvec[i].iov_base, rvec[i].iov_len,
-			lvec, liovcnt, &iov_l_curr_idx, &iov_l_curr_offset,
-			process_pages, mm, task, vm_write, &bytes_copied_loop);
-		bytes_copied += bytes_copied_loop;
-		if (rc != 0) {
-			/* If we have managed to copy any data at all then
-			   we return the number of bytes copied. Otherwise
-			   we return the error code */
-			if (bytes_copied)
-				rc = bytes_copied;
-			goto put_mm;
-		}
-	}
+			iter, process_pages, mm, task, vm_write);
+
+	/* copied = space before - space after */
+	total_len -= iov_iter_count(iter);
+
+	/* If we have managed to copy any data at all then
+	   we return the number of bytes copied. Otherwise
+	   we return the error code */
+	if (total_len)
+		rc = total_len;
 
-	rc = bytes_copied;
-put_mm:
 	mmput(mm);
 
 put_task_struct:
@@ -363,6 +262,7 @@ static ssize_t process_vm_rw(pid_t pid,
 	struct iovec iovstack_r[UIO_FASTIOV];
 	struct iovec *iov_l = iovstack_l;
 	struct iovec *iov_r = iovstack_r;
+	struct iov_iter iter;
 	ssize_t rc;
 
 	if (flags != 0)
@@ -378,13 +278,14 @@ static ssize_t process_vm_rw(pid_t pid,
 	if (rc <= 0)
 		goto free_iovecs;
 
+	iov_iter_init(&iter, iov_l, liovcnt, rc, 0);
+
 	rc = rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt, UIO_FASTIOV,
 				   iovstack_r, &iov_r);
 	if (rc <= 0)
 		goto free_iovecs;
 
-	rc = process_vm_rw_core(pid, iov_l, liovcnt, iov_r, riovcnt, flags,
-				vm_write);
+	rc = process_vm_rw_core(pid, &iter, iov_r, riovcnt, flags, vm_write);
 
 free_iovecs:
 	if (iov_r != iovstack_r)
@@ -424,6 +325,7 @@ compat_process_vm_rw(compat_pid_t pid,
 	struct iovec iovstack_r[UIO_FASTIOV];
 	struct iovec *iov_l = iovstack_l;
 	struct iovec *iov_r = iovstack_r;
+	struct iov_iter iter;
 	ssize_t rc = -EFAULT;
 
 	if (flags != 0)
@@ -439,14 +341,14 @@ compat_process_vm_rw(compat_pid_t pid,
 						  &iov_l);
 	if (rc <= 0)
 		goto free_iovecs;
+	iov_iter_init(&iter, iov_l, liovcnt, rc, 0);
 	rc = compat_rw_copy_check_uvector(CHECK_IOVEC_ONLY, rvec, riovcnt,
 					  UIO_FASTIOV, iovstack_r,
 					  &iov_r);
 	if (rc <= 0)
 		goto free_iovecs;
 
-	rc = process_vm_rw_core(pid, iov_l, liovcnt, iov_r, riovcnt, flags,
-			   vm_write);
+	rc = process_vm_rw_core(pid, &iter, iov_r, riovcnt, flags, vm_write);
 
 free_iovecs:
 	if (iov_r != iovstack_r)