> -----Original Message----- > From: Dave Kleikamp [mailto:dave.kleikamp@xxxxxxxxxx] > Sent: Monday, October 22, 2012 11:15 AM > To: linux-fsdevel@xxxxxxxxxxxxxxx > Cc: linux-kernel@xxxxxxxxxxxxxxx; Zach Brown; Maxim V. Patlasov; Dave > Kleikamp; Myklebust, Trond; linux-nfs@xxxxxxxxxxxxxxx > Subject: [PATCH 20/22] nfs: add support for read_iter, write_iter > > This patch implements the read_iter and write_iter file operations which > allow kernel code to initiate directIO. This allows the loop device to read and > write directly to the server, bypassing the page cache. > > Signed-off-by: Dave Kleikamp <dave.kleikamp@xxxxxxxxxx> > Cc: Zach Brown <zab@xxxxxxxxx> > Cc: Trond Myklebust <Trond.Myklebust@xxxxxxxxxx> > Cc: linux-nfs@xxxxxxxxxxxxxxx > --- > fs/nfs/direct.c | 169 +++++++++++++++++++++++++++++++++----------- > ----- > fs/nfs/file.c | 48 ++++++++++---- > fs/nfs/internal.h | 2 + > fs/nfs/nfs4file.c | 2 + > include/linux/nfs_fs.h | 6 +- > 5 files changed, 155 insertions(+), 72 deletions(-) > > diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 4532781..b1fda1c 100644 > --- a/fs/nfs/direct.c > +++ b/fs/nfs/direct.c > @@ -90,6 +90,7 @@ struct nfs_direct_req { > int flags; > #define NFS_ODIRECT_DO_COMMIT (1) /* an unstable reply > was received */ > #define NFS_ODIRECT_RESCHED_WRITES (2) /* write verification > failed */ > +#define NFS_ODIRECT_MARK_DIRTY (4) /* mark read pages > dirty */ > struct nfs_writeverf verf; /* unstable write verifier */ > }; > > @@ -131,15 +132,13 @@ ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, > struct iov_iter *iter, > > return -EINVAL; > #else > - const struct iovec *iov = iov_iter_iovec(iter); > - > VM_BUG_ON(iocb->ki_left != PAGE_SIZE); > VM_BUG_ON(iocb->ki_nbytes != PAGE_SIZE); > > if (rw == READ || rw == KERNEL_READ) > - return nfs_file_direct_read(iocb, iov, iter->nr_segs, pos, > + return nfs_file_direct_read(iocb, iter, pos, > rw == READ ? true : false); > - return nfs_file_direct_write(iocb, iov, iter->nr_segs, pos, > + return nfs_file_direct_write(iocb, iter, pos, > rw == WRITE ? true : false); > #endif /* CONFIG_NFS_SWAP */ > } > @@ -277,7 +276,8 @@ static void nfs_direct_read_completion(struct > nfs_pgio_header *hdr) > hdr->good_bytes & ~PAGE_MASK, > PAGE_SIZE); > } > - if (!PageCompound(page)) { > + if ((dreq->flags & NFS_ODIRECT_MARK_DIRTY) && > + !PageCompound(page)) { > if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) { > if (bytes < hdr->good_bytes) > set_page_dirty(page); > @@ -414,10 +414,9 @@ static ssize_t > nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *de > 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) > +static ssize_t nfs_direct_read_schedule(struct nfs_direct_req *dreq, > + struct iov_iter *iter, loff_t pos, > + bool uio) > { > struct nfs_pageio_descriptor desc; > ssize_t result = -EINVAL; > @@ -429,16 +428,47 @@ static ssize_t > nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, > get_dreq(dreq); > desc.pg_dreq = dreq; > > - for (seg = 0; seg < nr_segs; seg++) { > - const struct iovec *vec = &iov[seg]; > - result = nfs_direct_read_schedule_segment(&desc, vec, > pos, uio); > - if (result < 0) > - break; > - requested_bytes += result; > - if ((size_t)result < vec->iov_len) > - break; > - pos += vec->iov_len; > - } > + if (iov_iter_has_iovec(iter)) { > + const struct iovec *iov = iov_iter_iovec(iter); > + if (uio) > + dreq->flags = NFS_ODIRECT_MARK_DIRTY; > + for (seg = 0; seg < iter->nr_segs; seg++) { > + const struct iovec *vec = &iov[seg]; > + result = nfs_direct_read_schedule_segment(&desc, > vec, > + pos, uio); > + if (result < 0) > + break; > + requested_bytes += result; > + if ((size_t)result < vec->iov_len) > + break; > + pos += vec->iov_len; > + } > + } else if (iov_iter_has_bvec(iter)) { > + struct nfs_open_context *ctx = dreq->ctx; > + struct inode *inode = ctx->dentry->d_inode; > + struct bio_vec *bvec = iov_iter_bvec(iter); > + for (seg = 0; seg < iter->nr_segs; seg++) { > + struct nfs_page *req; > + unsigned int req_len = bvec[seg].bv_len; > + req = nfs_create_request(ctx, inode, > + bvec[seg].bv_page, > + bvec[seg].bv_offset, > req_len); > + if (IS_ERR(req)) { > + result = PTR_ERR(req); > + break; > + } > + req->wb_index = pos >> PAGE_SHIFT; > + req->wb_offset = pos & ~PAGE_MASK; > + if (!nfs_pageio_add_request(&desc, req)) { > + result = desc.pg_error; > + nfs_release_request(req); > + break; > + } > + requested_bytes += req_len; > + pos += req_len; > + } > + } else > + BUG(); Can we please split the contents of these 2 if statements into 2 helper functions nfs_direct_do_schedule_read_iovec() and nfs_direct_do_schedule_read_bvec()? > > nfs_pageio_complete(&desc); > > @@ -456,8 +486,8 @@ static ssize_t nfs_direct_read_schedule_iovec(struct > nfs_direct_req *dreq, > return 0; > } > > -static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov, > - unsigned long nr_segs, loff_t pos, bool uio) > +static ssize_t nfs_direct_read(struct kiocb *iocb, struct iov_iter *iter, > + loff_t pos, bool uio) > { > ssize_t result = -ENOMEM; > struct inode *inode = iocb->ki_filp->f_mapping->host; @@ -469,7 > +499,7 @@ static ssize_t nfs_direct_read(struct kiocb *iocb, const struct > iovec *iov, > goto out; > > dreq->inode = inode; > - dreq->bytes_left = iov_length(iov, nr_segs); > + dreq->bytes_left = iov_iter_count(iter); > 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)) { > @@ -480,8 +510,8 @@ static ssize_t nfs_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 += iov_iter_count(iter); > + result = nfs_direct_read_schedule(dreq, iter, pos, uio); > if (!result) > result = nfs_direct_wait(dreq); > out_release: > @@ -815,10 +845,9 @@ static const struct nfs_pgio_completion_ops > nfs_direct_write_completion_ops = { > .completion = nfs_direct_write_completion, }; > > -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) > +static ssize_t nfs_direct_write_schedule(struct nfs_direct_req *dreq, > + struct iov_iter *iter, loff_t pos, > + bool uio) > { > struct nfs_pageio_descriptor desc; > struct inode *inode = dreq->inode; > @@ -832,17 +861,48 @@ 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); > - if (result < 0) > - break; > - requested_bytes += result; > - if ((size_t)result < vec->iov_len) > - break; > - pos += vec->iov_len; > - } > + NFS_I(dreq->inode)->write_io += iov_iter_count(iter); > + > + if (iov_iter_has_iovec(iter)) { > + const struct iovec *iov = iov_iter_iovec(iter); > + for (seg = 0; seg < iter->nr_segs; seg++) { > + const struct iovec *vec = &iov[seg]; > + result = nfs_direct_write_schedule_segment(&desc, > vec, > + pos, uio); > + if (result < 0) > + break; > + requested_bytes += result; > + if ((size_t)result < vec->iov_len) > + break; > + pos += vec->iov_len; > + } > + } else if (iov_iter_has_bvec(iter)) { > + struct nfs_open_context *ctx = dreq->ctx; > + struct bio_vec *bvec = iov_iter_bvec(iter); > + for (seg = 0; seg < iter->nr_segs; seg++) { > + struct nfs_page *req; > + unsigned int req_len = bvec[seg].bv_len; > + > + req = nfs_create_request(ctx, inode, > bvec[seg].bv_page, > + bvec[seg].bv_offset, > 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; > + } > + requested_bytes += req_len; > + pos += req_len; > + } > + } else > + BUG(); Ditto... > + > nfs_pageio_complete(&desc); > > /* > @@ -860,9 +920,8 @@ static ssize_t nfs_direct_write_schedule_iovec(struct > nfs_direct_req *dreq, > return 0; > } > > -static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov, > - unsigned long nr_segs, loff_t pos, > - size_t count, bool uio) > +static ssize_t nfs_direct_write(struct kiocb *iocb, struct iov_iter *iter, > + loff_t pos, bool uio) > { > ssize_t result = -ENOMEM; > struct inode *inode = iocb->ki_filp->f_mapping->host; @@ -874,7 > +933,7 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, const struct > iovec *iov, > goto out; > > dreq->inode = inode; > - dreq->bytes_left = count; > + dreq->bytes_left = iov_iter_count(iter); > 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)) { > @@ -885,7 +944,7 @@ static ssize_t nfs_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(dreq, iter, pos, uio); > if (!result) > result = nfs_direct_wait(dreq); > out_release: > @@ -897,8 +956,7 @@ out: > /** > * 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 buffers into which to read data > * @pos: byte offset in file where reading starts > * > * We use this function for direct reads instead of calling @@ -915,15 +973,15 > @@ out: > * 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) > { > ssize_t retval = -EINVAL; > struct file *file = iocb->ki_filp; > struct address_space *mapping = file->f_mapping; > size_t count; > > - count = iov_length(iov, nr_segs); > + count = iov_iter_count(iter); > nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count); > > dfprintk(FILE, "NFS: direct read(%s/%s, %zd@%Ld)\n", @@ -941,7 > +999,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec > *iov, > > task_io_account_read(count); > > - retval = nfs_direct_read(iocb, iov, nr_segs, pos, uio); > + retval = nfs_direct_read(iocb, iter, pos, uio); > if (retval > 0) > iocb->ki_pos = pos + retval; > > @@ -952,8 +1010,7 @@ out: > /** > * 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 buffers from which to write data > * @pos: byte offset in file where writing starts > * > * We use this function for direct writes instead of calling @@ -971,15 > +1028,15 @@ out: > * 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 retval = -EINVAL; > struct file *file = iocb->ki_filp; > struct address_space *mapping = file->f_mapping; > size_t count; > > - count = iov_length(iov, nr_segs); > + count = iov_iter_count(iter); > nfs_add_stats(mapping->host, NFSIOS_DIRECTWRITTENBYTES, > count); > > dfprintk(FILE, "NFS: direct write(%s/%s, %zd@%Ld)\n", @@ -1004,7 > +1061,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct > iovec *iov, > > task_io_account_write(count); > > - retval = nfs_direct_write(iocb, iov, nr_segs, pos, count, uio); > + retval = nfs_direct_write(iocb, iter, pos, uio); > if (retval > 0) { > struct inode *inode = mapping->host; > > diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 582bb88..b4bf6ef 100644 > --- a/fs/nfs/file.c > +++ b/fs/nfs/file.c > @@ -172,28 +172,39 @@ nfs_file_flush(struct file *file, fl_owner_t id) > EXPORT_SYMBOL_GPL(nfs_file_flush); > > ssize_t > -nfs_file_read(struct kiocb *iocb, const struct iovec *iov, > - unsigned long nr_segs, loff_t pos) > +nfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter, loff_t > +pos) > { > struct dentry * dentry = iocb->ki_filp->f_path.dentry; > struct inode * inode = dentry->d_inode; > ssize_t result; > > if (iocb->ki_filp->f_flags & O_DIRECT) > - return nfs_file_direct_read(iocb, iov, nr_segs, pos, true); > + return nfs_file_direct_read(iocb, iter, pos, true); > > - dprintk("NFS: read(%s/%s, %lu@%lu)\n", > + dprintk("NFS: read_iter(%s/%s, %lu@%lu)\n", > dentry->d_parent->d_name.name, dentry->d_name.name, > - (unsigned long) iov_length(iov, nr_segs), (unsigned long) > pos); > + (unsigned long) iov_iter_count(iter), (unsigned long) pos); > > result = nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping); > if (!result) { > - result = generic_file_aio_read(iocb, iov, nr_segs, pos); > + result = generic_file_read_iter(iocb, iter, pos); > if (result > 0) > nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, > result); > } > return result; > } > +EXPORT_SYMBOL_GPL(nfs_file_read_iter); > + > +ssize_t > +nfs_file_read(struct kiocb *iocb, const struct iovec *iov, > + unsigned long nr_segs, loff_t pos) > +{ > + struct iov_iter iter; > + > + iov_iter_init(&iter, iov, nr_segs, iov_length(iov, nr_segs), 0); > + > + return nfs_file_read_iter(iocb, &iter, pos); } > EXPORT_SYMBOL_GPL(nfs_file_read); > > ssize_t > @@ -610,19 +621,19 @@ static int nfs_need_sync_write(struct file *filp, > struct inode *inode) > return 0; > } > > -ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov, > - unsigned long nr_segs, loff_t pos) > +ssize_t nfs_file_write_iter(struct kiocb *iocb, struct iov_iter *iter, > + loff_t pos) > { > struct dentry * dentry = iocb->ki_filp->f_path.dentry; > struct inode * inode = dentry->d_inode; > unsigned long written = 0; > ssize_t result; > - size_t count = iov_length(iov, nr_segs); > + size_t count = iov_iter_count(iter); > > if (iocb->ki_filp->f_flags & O_DIRECT) > - return nfs_file_direct_write(iocb, iov, nr_segs, pos, true); > + return nfs_file_direct_write(iocb, iter, pos, true); > > - dprintk("NFS: write(%s/%s, %lu@%Ld)\n", > + dprintk("NFS: write_iter(%s/%s, %lu@%lld)\n", > dentry->d_parent->d_name.name, dentry->d_name.name, > (unsigned long) count, (long long) pos); > > @@ -642,7 +653,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, const struct > iovec *iov, > if (!count) > goto out; > > - result = generic_file_aio_write(iocb, iov, nr_segs, pos); > + result = generic_file_write_iter(iocb, iter, pos); > if (result > 0) > written = result; > > @@ -661,6 +672,17 @@ out_swapfile: > printk(KERN_INFO "NFS: attempt to write to active swap file!\n"); > goto out; > } > +EXPORT_SYMBOL_GPL(nfs_file_write_iter); > + > +ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov, > + unsigned long nr_segs, loff_t pos) { > + struct iov_iter iter; > + > + iov_iter_init(&iter, iov, nr_segs, iov_length(iov, nr_segs), 0); > + > + return nfs_file_write_iter(iocb, &iter, pos); } > EXPORT_SYMBOL_GPL(nfs_file_write); > > ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe, @@ -914,6 > +936,8 @@ const struct file_operations nfs_file_operations = { > .write = do_sync_write, > .aio_read = nfs_file_read, > .aio_write = nfs_file_write, > + .read_iter = nfs_file_read_iter, > + .write_iter = nfs_file_write_iter, > .mmap = nfs_file_mmap, > .open = nfs_file_open, > .flush = nfs_file_flush, > diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 59b133c..8db3b11 > 100644 > --- a/fs/nfs/internal.h > +++ b/fs/nfs/internal.h > @@ -302,10 +302,12 @@ int nfs_file_fsync_commit(struct file *, loff_t, > loff_t, int); loff_t nfs_file_llseek(struct file *, loff_t, int); int > nfs_file_flush(struct file *, fl_owner_t); ssize_t nfs_file_read(struct kiocb *, > const struct iovec *, unsigned long, loff_t); > +ssize_t nfs_file_read_iter(struct kiocb *, struct iov_iter *, loff_t); > ssize_t nfs_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *, > size_t, unsigned int); > int nfs_file_mmap(struct file *, struct vm_area_struct *); ssize_t > nfs_file_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); > +ssize_t nfs_file_write_iter(struct kiocb *, struct iov_iter *, loff_t); > int nfs_file_release(struct inode *, struct file *); int nfs_lock(struct file *, int, > struct file_lock *); int nfs_flock(struct file *, int, struct file_lock *); diff --git > a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index afddd66..195188e 100644 > --- a/fs/nfs/nfs4file.c > +++ b/fs/nfs/nfs4file.c > @@ -123,6 +123,8 @@ const struct file_operations nfs4_file_operations = { > .write = do_sync_write, > .aio_read = nfs_file_read, > .aio_write = nfs_file_write, > + .read_iter = nfs_file_read_iter, > + .write_iter = nfs_file_write_iter, > .mmap = nfs_file_mmap, > .open = nfs4_file_open, > .flush = nfs_file_flush, > diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index > 4913e3c..9f8e8a9 100644 > --- a/include/linux/nfs_fs.h > +++ b/include/linux/nfs_fs.h > @@ -445,11 +445,9 @@ extern int nfs3_removexattr (struct dentry *, const > char *name); > * linux/fs/nfs/direct.c > */ > extern ssize_t nfs_direct_IO(int, struct kiocb *, struct iov_iter *, loff_t); - > extern ssize_t nfs_file_direct_read(struct kiocb *iocb, > - const struct iovec *iov, unsigned long nr_segs, > +extern ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter > +*iter, > loff_t pos, bool uio); > -extern ssize_t nfs_file_direct_write(struct kiocb *iocb, > - const struct iovec *iov, unsigned long nr_segs, > +extern ssize_t nfs_file_direct_write(struct kiocb *iocb, struct > +iov_iter *iter, > loff_t pos, bool uio); > > /* Otherwise, everything looks fine to me... Acked-by: Trond Myklebust <Trond.Myklebust@xxxxxxxxxx> Cheers Trond -- To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html