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

Pull vfs updates from Al Viro:
 "This the bunch that sat in -next + lock_parent() fix.  This is the
  minimal set; there's more pending stuff.

  In particular, I really hope to get acct.c fixes merged this cycle -
  we need that to deal sanely with delayed-mntput stuff.  In the next
  pile, hopefully - that series is fairly short and localized
  (kernel/acct.c, fs/super.c and fs/namespace.c).  In this pile: more
  iov_iter work.  Most of prereqs for ->splice_write with sane locking
  order are there and Kent's dio rewrite would also fit nicely on top of
  this pile"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (70 commits)
  lock_parent: don't step on stale ->d_parent of all-but-freed one
  kill generic_file_splice_write()
  ceph: switch to iter_file_splice_write()
  shmem: switch to iter_file_splice_write()
  nfs: switch to iter_splice_write_file()
  fs/splice.c: remove unneeded exports
  ocfs2: switch to iter_file_splice_write()
  ->splice_write() via ->write_iter()
  bio_vec-backed iov_iter
  optimize copy_page_{to,from}_iter()
  bury generic_file_aio_{read,write}
  lustre: get rid of messing with iovecs
  ceph: switch to ->write_iter()
  ceph_sync_direct_write: stop poking into iov_iter guts
  ceph_sync_read: stop poking into iov_iter guts
  new helper: copy_page_from_iter()
  fuse: switch to ->write_iter()
  btrfs: switch to ->write_iter()
  ocfs2: switch to ->write_iter()
  xfs: switch to ->write_iter()
  ...

1 files changed, 102 insertions, 224 deletions

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 4ad7bc388679..8f98138cbc43 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -212,20 +212,20 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq,
  * shunt off direct read and write requests before the VFS gets them,
  * so this method is only ever called for swap.
  */
-ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t pos, unsigned long nr_segs)
+ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
 {
 #ifndef CONFIG_NFS_SWAP
         dprintk("NFS: nfs_direct_IO (%pD) off/no(%Ld/%lu) EINVAL\n",
-                        iocb->ki_filp, (long long) pos, nr_segs);
+                        iocb->ki_filp, (long long) pos, iter->nr_segs);
 
         return -EINVAL;
 #else
         VM_BUG_ON(iocb->ki_nbytes != PAGE_SIZE);
 
         if (rw == READ || rw == KERNEL_READ)
-                return nfs_file_direct_read(iocb, iov, nr_segs, pos,
+                return nfs_file_direct_read(iocb, iter, pos,
                                 rw == READ ? true : false);
-        return nfs_file_direct_write(iocb, iov, nr_segs, pos,
+        return nfs_file_direct_write(iocb, iter, pos,
                                 rw == WRITE ? true : false);
 #endif /* CONFIG_NFS_SWAP */
 }
@@ -414,60 +414,37 @@ static const struct nfs_pgio_completion_ops nfs_direct_read_completion_ops = {
  * handled automatically by nfs_direct_read_result().  Otherwise, if
  * no requests have been sent, just return an error.
  */
-static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *desc,
-                                                const struct iovec *iov,
-                                                loff_t pos, bool uio)
-{
-        struct nfs_direct_req *dreq = desc->pg_dreq;
-        struct nfs_open_context *ctx = dreq->ctx;
-        struct inode *inode = ctx->dentry->d_inode;
-        unsigned long user_addr = (unsigned long)iov->iov_base;
-        size_t count = iov->iov_len;
-        size_t rsize = NFS_SERVER(inode)->rsize;
-        unsigned int pgbase;
-        int result;
-        ssize_t started = 0;
-        struct page **pagevec = NULL;
-        unsigned int npages;
-
-        do {
-                size_t bytes;
-                int i;
 
-                pgbase = user_addr & ~PAGE_MASK;
-                bytes = min(max_t(size_t, rsize, PAGE_SIZE), count);
+static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
+                                              struct iov_iter *iter,
+                                              loff_t pos)
+{
+        struct nfs_pageio_descriptor desc;
+        struct inode *inode = dreq->inode;
+        ssize_t result = -EINVAL;
+        size_t requested_bytes = 0;
+        size_t rsize = max_t(size_t, NFS_SERVER(inode)->rsize, PAGE_SIZE);
 
-                result = -ENOMEM;
-                npages = nfs_page_array_len(pgbase, bytes);
-                if (!pagevec)
-                        pagevec = kmalloc(npages * sizeof(struct page *),
-                                          GFP_KERNEL);
-                if (!pagevec)
-                        break;
-                if (uio) {
-                        down_read(&current->mm->mmap_sem);
-                        result = get_user_pages(current, current->mm, user_addr,
-                                        npages, 1, 0, pagevec, NULL);
-                        up_read(&current->mm->mmap_sem);
-                        if (result < 0)
-                                break;
-                } else {
-                        WARN_ON(npages != 1);
-                        result = get_kernel_page(user_addr, 1, pagevec);
-                        if (WARN_ON(result != 1))
-                                break;
-                }
+        nfs_pageio_init_read(&desc, dreq->inode, false,
+                             &nfs_direct_read_completion_ops);
+        get_dreq(dreq);
+        desc.pg_dreq = dreq;
+        atomic_inc(&inode->i_dio_count);
 
-                if ((unsigned)result < npages) {
-                        bytes = result * PAGE_SIZE;
-                        if (bytes <= pgbase) {
-                                nfs_direct_release_pages(pagevec, result);
-                                break;
-                        }
-                        bytes -= pgbase;
-                        npages = result;
-                }
+        while (iov_iter_count(iter)) {
+                struct page **pagevec;
+                size_t bytes;
+                size_t pgbase;
+                unsigned npages, i;
 
+                result = iov_iter_get_pages_alloc(iter, &pagevec, 
+                                                  rsize, &pgbase);
+                if (result < 0)
+                        break;
+        
+                bytes = result;
+                iov_iter_advance(iter, bytes);
+                npages = (result + pgbase + PAGE_SIZE - 1) / PAGE_SIZE;
                 for (i = 0; i < npages; i++) {
                         struct nfs_page *req;
                         unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase);
@@ -480,56 +457,21 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *de
                         }
                         req->wb_index = pos >> PAGE_SHIFT;
                         req->wb_offset = pos & ~PAGE_MASK;
-                        if (!nfs_pageio_add_request(desc, req)) {
-                                result = desc->pg_error;
+                        if (!nfs_pageio_add_request(&desc, req)) {
+                                result = desc.pg_error;
                                 nfs_release_request(req);
                                 break;
                         }
                         pgbase = 0;
                         bytes -= req_len;
-                        started += req_len;
-                        user_addr += req_len;
+                        requested_bytes += req_len;
                         pos += req_len;
-                        count -= req_len;
                         dreq->bytes_left -= req_len;
                 }
-                /* The nfs_page now hold references to these pages */
                 nfs_direct_release_pages(pagevec, npages);
-        } while (count != 0 && result >= 0);
-
-        kfree(pagevec);
-
-        if (started)
-                return started;
-        return result < 0 ? (ssize_t) result : -EFAULT;
-}
-
-static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
-                                              const struct iovec *iov,
-                                              unsigned long nr_segs,
-                                              loff_t pos, bool uio)
-{
-        struct nfs_pageio_descriptor desc;
-        struct inode *inode = dreq->inode;
-        ssize_t result = -EINVAL;
-        size_t requested_bytes = 0;
-        unsigned long seg;
-
-        nfs_pageio_init_read(&desc, dreq->inode, false,
-                             &nfs_direct_read_completion_ops);
-        get_dreq(dreq);
-        desc.pg_dreq = dreq;
-        atomic_inc(&inode->i_dio_count);
-
-        for (seg = 0; seg < nr_segs; seg++) {
-                const struct iovec *vec = &iov[seg];
-                result = nfs_direct_read_schedule_segment(&desc, vec, pos, uio);
+                kvfree(pagevec);
                 if (result < 0)
                         break;
-                requested_bytes += result;
-                if ((size_t)result < vec->iov_len)
-                        break;
-                pos += vec->iov_len;
         }
 
         nfs_pageio_complete(&desc);
@@ -552,8 +494,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 /**
  * nfs_file_direct_read - file direct read operation for NFS files
  * @iocb: target I/O control block
- * @iov: vector of user buffers into which to read data
- * @nr_segs: size of iov vector
+ * @iter: vector of user buffers into which to read data
  * @pos: byte offset in file where reading starts
  *
  * We use this function for direct reads instead of calling
@@ -570,8 +511,8 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
  * client must read the updated atime from the server back into its
  * cache.
  */
-ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
-                                unsigned long nr_segs, loff_t pos, bool uio)
+ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
+                                loff_t pos, bool uio)
 {
         struct file *file = iocb->ki_filp;
         struct address_space *mapping = file->f_mapping;
@@ -579,9 +520,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
         struct nfs_direct_req *dreq;
         struct nfs_lock_context *l_ctx;
         ssize_t result = -EINVAL;
-        size_t count;
-
-        count = iov_length(iov, nr_segs);
+        size_t count = iov_iter_count(iter);
         nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count);
 
         dfprintk(FILE, "NFS: direct read(%pD2, %zd@%Ld)\n",
@@ -604,7 +543,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
                 goto out_unlock;
 
         dreq->inode = inode;
-        dreq->bytes_left = iov_length(iov, nr_segs);
+        dreq->bytes_left = count;
         dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
         l_ctx = nfs_get_lock_context(dreq->ctx);
         if (IS_ERR(l_ctx)) {
@@ -615,8 +554,8 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
         if (!is_sync_kiocb(iocb))
                 dreq->iocb = iocb;
 
-        NFS_I(inode)->read_io += iov_length(iov, nr_segs);
-        result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos, uio);
+        NFS_I(inode)->read_io += count;
+        result = nfs_direct_read_schedule_iovec(dreq, iter, pos);
 
         mutex_unlock(&inode->i_mutex);
 
@@ -772,108 +711,6 @@ static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode
 }
 #endif
 
-/*
- * NB: Return the value of the first error return code.  Subsequent
- *     errors after the first one are ignored.
- */
-/*
- * For each wsize'd chunk of the user's buffer, dispatch an NFS WRITE
- * operation.  If nfs_writedata_alloc() or get_user_pages() fails,
- * bail and stop sending more writes.  Write length accounting is
- * handled automatically by nfs_direct_write_result().  Otherwise, if
- * no requests have been sent, just return an error.
- */
-static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *desc,
-                                                 const struct iovec *iov,
-                                                 loff_t pos, bool uio)
-{
-        struct nfs_direct_req *dreq = desc->pg_dreq;
-        struct nfs_open_context *ctx = dreq->ctx;
-        struct inode *inode = ctx->dentry->d_inode;
-        unsigned long user_addr = (unsigned long)iov->iov_base;
-        size_t count = iov->iov_len;
-        size_t wsize = NFS_SERVER(inode)->wsize;
-        unsigned int pgbase;
-        int result;
-        ssize_t started = 0;
-        struct page **pagevec = NULL;
-        unsigned int npages;
-
-        do {
-                size_t bytes;
-                int i;
-
-                pgbase = user_addr & ~PAGE_MASK;
-                bytes = min(max_t(size_t, wsize, PAGE_SIZE), count);
-
-                result = -ENOMEM;
-                npages = nfs_page_array_len(pgbase, bytes);
-                if (!pagevec)
-                        pagevec = kmalloc(npages * sizeof(struct page *), GFP_KERNEL);
-                if (!pagevec)
-                        break;
-
-                if (uio) {
-                        down_read(&current->mm->mmap_sem);
-                        result = get_user_pages(current, current->mm, user_addr,
-                                                npages, 0, 0, pagevec, NULL);
-                        up_read(&current->mm->mmap_sem);
-                        if (result < 0)
-                                break;
-                } else {
-                        WARN_ON(npages != 1);
-                        result = get_kernel_page(user_addr, 0, pagevec);
-                        if (WARN_ON(result != 1))
-                                break;
-                }
-
-                if ((unsigned)result < npages) {
-                        bytes = result * PAGE_SIZE;
-                        if (bytes <= pgbase) {
-                                nfs_direct_release_pages(pagevec, result);
-                                break;
-                        }
-                        bytes -= pgbase;
-                        npages = result;
-                }
-
-                for (i = 0; i < npages; i++) {
-                        struct nfs_page *req;
-                        unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase);
-
-                        req = nfs_create_request(dreq->ctx, pagevec[i], NULL,
-                                                 pgbase, req_len);
-                        if (IS_ERR(req)) {
-                                result = PTR_ERR(req);
-                                break;
-                        }
-                        nfs_lock_request(req);
-                        req->wb_index = pos >> PAGE_SHIFT;
-                        req->wb_offset = pos & ~PAGE_MASK;
-                        if (!nfs_pageio_add_request(desc, req)) {
-                                result = desc->pg_error;
-                                nfs_unlock_and_release_request(req);
-                                break;
-                        }
-                        pgbase = 0;
-                        bytes -= req_len;
-                        started += req_len;
-                        user_addr += req_len;
-                        pos += req_len;
-                        count -= req_len;
-                        dreq->bytes_left -= req_len;
-                }
-                /* The nfs_page now hold references to these pages */
-                nfs_direct_release_pages(pagevec, npages);
-        } while (count != 0 && result >= 0);
-
-        kfree(pagevec);
-
-        if (started)
-                return started;
-        return result < 0 ? (ssize_t) result : -EFAULT;
-}
-
 static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 {
         struct nfs_direct_req *dreq = hdr->dreq;
@@ -956,16 +793,27 @@ static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = {
         .completion = nfs_direct_write_completion,
 };
 
+
+/*
+ * NB: Return the value of the first error return code.  Subsequent
+ *     errors after the first one are ignored.
+ */
+/*
+ * For each wsize'd chunk of the user's buffer, dispatch an NFS WRITE
+ * operation.  If nfs_writedata_alloc() or get_user_pages() fails,
+ * bail and stop sending more writes.  Write length accounting is
+ * handled automatically by nfs_direct_write_result().  Otherwise, if
+ * no requests have been sent, just return an error.
+ */
 static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
-                                               const struct iovec *iov,
-                                               unsigned long nr_segs,
-                                               loff_t pos, bool uio)
+                                               struct iov_iter *iter,
+                                               loff_t pos)
 {
         struct nfs_pageio_descriptor desc;
         struct inode *inode = dreq->inode;
         ssize_t result = 0;
         size_t requested_bytes = 0;
-        unsigned long seg;
+        size_t wsize = max_t(size_t, NFS_SERVER(inode)->wsize, PAGE_SIZE);
 
         nfs_pageio_init_write(&desc, inode, FLUSH_COND_STABLE, false,
                               &nfs_direct_write_completion_ops);
@@ -973,16 +821,49 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
         get_dreq(dreq);
         atomic_inc(&inode->i_dio_count);
 
-        NFS_I(dreq->inode)->write_io += iov_length(iov, nr_segs);
-        for (seg = 0; seg < nr_segs; seg++) {
-                const struct iovec *vec = &iov[seg];
-                result = nfs_direct_write_schedule_segment(&desc, vec, pos, uio);
+        NFS_I(inode)->write_io += iov_iter_count(iter);
+        while (iov_iter_count(iter)) {
+                struct page **pagevec;
+                size_t bytes;
+                size_t pgbase;
+                unsigned npages, i;
+
+                result = iov_iter_get_pages_alloc(iter, &pagevec, 
+                                                  wsize, &pgbase);
                 if (result < 0)
                         break;
-                requested_bytes += result;
-                if ((size_t)result < vec->iov_len)
+
+                bytes = result;
+                iov_iter_advance(iter, bytes);
+                npages = (result + pgbase + PAGE_SIZE - 1) / PAGE_SIZE;
+                for (i = 0; i < npages; i++) {
+                        struct nfs_page *req;
+                        unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase);
+
+                        req = nfs_create_request(dreq->ctx, pagevec[i], NULL,
+                                                 pgbase, req_len);
+                        if (IS_ERR(req)) {
+                                result = PTR_ERR(req);
+                                break;
+                        }
+                        nfs_lock_request(req);
+                        req->wb_index = pos >> PAGE_SHIFT;
+                        req->wb_offset = pos & ~PAGE_MASK;
+                        if (!nfs_pageio_add_request(&desc, req)) {
+                                result = desc.pg_error;
+                                nfs_unlock_and_release_request(req);
+                                break;
+                        }
+                        pgbase = 0;
+                        bytes -= req_len;
+                        requested_bytes += req_len;
+                        pos += req_len;
+                        dreq->bytes_left -= req_len;
+                }
+                nfs_direct_release_pages(pagevec, npages);
+                kvfree(pagevec);
+                if (result < 0)
                         break;
-                pos += vec->iov_len;
         }
         nfs_pageio_complete(&desc);
 
@@ -1004,8 +885,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 /**
  * nfs_file_direct_write - file direct write operation for NFS files
  * @iocb: target I/O control block
- * @iov: vector of user buffers from which to write data
- * @nr_segs: size of iov vector
+ * @iter: vector of user buffers from which to write data
  * @pos: byte offset in file where writing starts
  *
  * We use this function for direct writes instead of calling
@@ -1023,8 +903,8 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
  * Note that O_APPEND is not supported for NFS direct writes, as there
  * is no atomic O_APPEND write facility in the NFS protocol.
  */
-ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
-                                unsigned long nr_segs, loff_t pos, bool uio)
+ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter,
+                                loff_t pos, bool uio)
 {
         ssize_t result = -EINVAL;
         struct file *file = iocb->ki_filp;
@@ -1033,9 +913,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
         struct nfs_direct_req *dreq;
         struct nfs_lock_context *l_ctx;
         loff_t end;
-        size_t count;
-
-        count = iov_length(iov, nr_segs);
+        size_t count = iov_iter_count(iter);
         end = (pos + count - 1) >> PAGE_CACHE_SHIFT;
 
         nfs_add_stats(mapping->host, NFSIOS_DIRECTWRITTENBYTES, count);
@@ -1086,7 +964,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
         if (!is_sync_kiocb(iocb))
                 dreq->iocb = iocb;
 
-        result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos, uio);
+        result = nfs_direct_write_schedule_iovec(dreq, iter, pos);
 
         if (mapping->nrpages) {
                 invalidate_inode_pages2_range(mapping,