Return-Path: linux-nfs-owner@vger.kernel.org Received: from userp1040.oracle.com ([156.151.31.81]:23971 "EHLO userp1040.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932567Ab3AIT7x (ORCPT ); Wed, 9 Jan 2013 14:59:53 -0500 From: Dave Kleikamp To: linux-fsdevel@vger.kernel.org Cc: linux-kernel@vger.kernel.org, Zach Brown , "Maxim V. Patlasov" , Dave Kleikamp , Mel Gorman , Trond Myklebust , linux-nfs@vger.kernel.org, Rik van Riel Subject: [PATCH V5 22/30] nfs: simplify swap Date: Wed, 9 Jan 2013 13:58:37 -0600 Message-Id: <1357761525-22718-23-git-send-email-dave.kleikamp@oracle.com> In-Reply-To: <1357761525-22718-1-git-send-email-dave.kleikamp@oracle.com> References: <1357761525-22718-1-git-send-email-dave.kleikamp@oracle.com> Sender: linux-nfs-owner@vger.kernel.org List-ID: swap_writepage can now call nfs's write_iter f_op, eliminating the need to implement for the special-case direct_IO a_op. There is no longer a need to pass the uio flag through the direct write path. Signed-off-by: Dave Kleikamp Cc: Mel Gorman Cc: Trond Myklebust Cc: linux-nfs@vger.kernel.org Cc: Rik van Riel --- fs/nfs/direct.c | 94 ++++++++++++++++------------------------------- fs/nfs/file.c | 4 +- include/linux/blk_types.h | 2 - include/linux/fs.h | 2 - include/linux/nfs_fs.h | 4 +- mm/page_io.c | 13 +++---- 6 files changed, 42 insertions(+), 77 deletions(-) diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 2b0ebcb..239c2fe 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -118,29 +118,18 @@ static inline int put_dreq(struct nfs_direct_req *dreq) * @nr_segs: size of iovec array * * The presence of this routine in the address space ops vector means - * the NFS client supports direct I/O. However, for most direct IO, we - * shunt off direct read and write requests before the VFS gets them, - * so this method is only ever called for swap. + * the NFS client supports direct I/O. However, we shunt off direct + * read and write requests before the VFS gets them, so this method + * should never be called. */ 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 (%s) off/no(%Ld/%lu) EINVAL\n", iocb->ki_filp->f_path.dentry->d_name.name, (long long) pos, iter->nr_segs); return -EINVAL; -#else - 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, iter, pos, - rw == READ ? true : false); - return nfs_file_direct_write(iocb, iter, pos, - rw == WRITE ? true : false); -#endif /* CONFIG_NFS_SWAP */ } static void nfs_direct_release_pages(struct page **pages, unsigned int npages) @@ -312,7 +301,7 @@ static const struct nfs_pgio_completion_ops nfs_direct_read_completion_ops = { */ static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *desc, const struct iovec *iov, - loff_t pos, bool uio) + loff_t pos) { struct nfs_direct_req *dreq = desc->pg_dreq; struct nfs_open_context *ctx = dreq->ctx; @@ -340,20 +329,12 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *de GFP_KERNEL); if (!pagevec) break; - if (uio) { - down_read(¤t->mm->mmap_sem); - result = get_user_pages(current, current->mm, user_addr, + down_read(¤t->mm->mmap_sem); + result = get_user_pages(current, current->mm, user_addr, npages, 1, 0, pagevec, NULL); - up_read(¤t->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; - } - + up_read(¤t->mm->mmap_sem); + if (result < 0) + break; if ((unsigned)result < npages) { bytes = result * PAGE_SIZE; if (bytes <= pgbase) { @@ -403,7 +384,7 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *de static ssize_t nfs_direct_do_schedule_read_iovec( struct nfs_pageio_descriptor *desc, const struct iovec *iov, - unsigned long nr_segs, loff_t pos, bool uio) + unsigned long nr_segs, loff_t pos) { ssize_t result = -EINVAL; size_t requested_bytes = 0; @@ -411,7 +392,7 @@ static ssize_t nfs_direct_do_schedule_read_iovec( for (seg = 0; seg < nr_segs; seg++) { const struct iovec *vec = &iov[seg]; - result = nfs_direct_read_schedule_segment(desc, vec, pos, uio); + result = nfs_direct_read_schedule_segment(desc, vec, pos); if (result < 0) break; requested_bytes += result; @@ -468,8 +449,7 @@ static ssize_t nfs_direct_do_schedule_read_bvec( #endif /* CONFIG_BLOCK */ static ssize_t nfs_direct_read_schedule(struct nfs_direct_req *dreq, - struct iov_iter *iter, loff_t pos, - bool uio) + struct iov_iter *iter, loff_t pos) { struct nfs_pageio_descriptor desc; ssize_t result; @@ -480,10 +460,8 @@ static ssize_t nfs_direct_read_schedule(struct nfs_direct_req *dreq, desc.pg_dreq = dreq; if (iov_iter_has_iovec(iter)) { - if (uio) - dreq->flags = NFS_ODIRECT_MARK_DIRTY; result = nfs_direct_do_schedule_read_iovec(&desc, - iov_iter_iovec(iter), iter->nr_segs, pos, uio); + iov_iter_iovec(iter), iter->nr_segs, pos); #ifdef CONFIG_BLOCK } else if (iov_iter_has_bvec(iter)) { result = nfs_direct_do_schedule_read_bvec(&desc, @@ -509,7 +487,7 @@ static ssize_t nfs_direct_read_schedule(struct nfs_direct_req *dreq, } static ssize_t nfs_direct_read(struct kiocb *iocb, struct iov_iter *iter, - loff_t pos, bool uio) + loff_t pos) { ssize_t result = -ENOMEM; struct inode *inode = iocb->ki_filp->f_mapping->host; @@ -533,7 +511,7 @@ static ssize_t nfs_direct_read(struct kiocb *iocb, struct iov_iter *iter, dreq->iocb = iocb; NFS_I(inode)->read_io += iov_iter_count(iter); - result = nfs_direct_read_schedule(dreq, iter, pos, uio); + result = nfs_direct_read_schedule(dreq, iter, pos); if (!result) result = nfs_direct_wait(dreq); out_release: @@ -698,7 +676,7 @@ static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode */ static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *desc, const struct iovec *iov, - loff_t pos, bool uio) + loff_t pos) { struct nfs_direct_req *dreq = desc->pg_dreq; struct nfs_open_context *ctx = dreq->ctx; @@ -726,19 +704,12 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *d if (!pagevec) break; - if (uio) { - down_read(¤t->mm->mmap_sem); - result = get_user_pages(current, current->mm, user_addr, - npages, 0, 0, pagevec, NULL); - up_read(¤t->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; - } + down_read(¤t->mm->mmap_sem); + result = get_user_pages(current, current->mm, user_addr, + npages, 0, 0, pagevec, NULL); + up_read(¤t->mm->mmap_sem); + if (result < 0) + break; if ((unsigned)result < npages) { bytes = result * PAGE_SIZE; @@ -869,7 +840,7 @@ static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = { static ssize_t nfs_direct_do_schedule_write_iovec( struct nfs_pageio_descriptor *desc, const struct iovec *iov, - unsigned long nr_segs, loff_t pos, bool uio) + unsigned long nr_segs, loff_t pos) { ssize_t result = -EINVAL; size_t requested_bytes = 0; @@ -878,7 +849,7 @@ static ssize_t nfs_direct_do_schedule_write_iovec( for (seg = 0; seg < nr_segs; seg++) { const struct iovec *vec = &iov[seg]; result = nfs_direct_write_schedule_segment(desc, vec, - pos, uio); + pos); if (result < 0) break; requested_bytes += result; @@ -936,8 +907,7 @@ static ssize_t nfs_direct_do_schedule_write_bvec( #endif /* CONFIG_BLOCK */ static ssize_t nfs_direct_write_schedule(struct nfs_direct_req *dreq, - struct iov_iter *iter, loff_t pos, - bool uio) + struct iov_iter *iter, loff_t pos) { struct nfs_pageio_descriptor desc; struct inode *inode = dreq->inode; @@ -953,7 +923,7 @@ static ssize_t nfs_direct_write_schedule(struct nfs_direct_req *dreq, if (iov_iter_has_iovec(iter)) { result = nfs_direct_do_schedule_write_iovec(&desc, - iov_iter_iovec(iter), iter->nr_segs, pos, uio); + iov_iter_iovec(iter), iter->nr_segs, pos); #ifdef CONFIG_BLOCK } else if (iov_iter_has_bvec(iter)) { result = nfs_direct_do_schedule_write_bvec(&desc, @@ -980,7 +950,7 @@ static ssize_t nfs_direct_write_schedule(struct nfs_direct_req *dreq, } static ssize_t nfs_direct_write(struct kiocb *iocb, struct iov_iter *iter, - loff_t pos, bool uio) + loff_t pos) { ssize_t result = -ENOMEM; struct inode *inode = iocb->ki_filp->f_mapping->host; @@ -1003,7 +973,7 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, struct iov_iter *iter, if (!is_sync_kiocb(iocb)) dreq->iocb = iocb; - result = nfs_direct_write_schedule(dreq, iter, pos, uio); + result = nfs_direct_write_schedule(dreq, iter, pos); if (!result) result = nfs_direct_wait(dreq); out_release: @@ -1033,7 +1003,7 @@ out: * cache. */ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, - loff_t pos, bool uio) + loff_t pos) { ssize_t retval = -EINVAL; struct file *file = iocb->ki_filp; @@ -1058,7 +1028,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, task_io_account_read(count); - retval = nfs_direct_read(iocb, iter, pos, uio); + retval = nfs_direct_read(iocb, iter, pos); if (retval > 0) iocb->ki_pos = pos + retval; @@ -1088,7 +1058,7 @@ out: * is no atomic O_APPEND write facility in the NFS protocol. */ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter, - loff_t pos, bool uio) + loff_t pos) { ssize_t retval = -EINVAL; struct file *file = iocb->ki_filp; @@ -1120,7 +1090,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter, task_io_account_write(count); - retval = nfs_direct_write(iocb, iter, pos, uio); + retval = nfs_direct_write(iocb, iter, pos); if (retval > 0) { struct inode *inode = mapping->host; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 28119c5..83cbc6c 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -179,7 +179,7 @@ nfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter, loff_t pos) ssize_t result; if (iocb->ki_filp->f_flags & O_DIRECT) - return nfs_file_direct_read(iocb, iter, pos, true); + return nfs_file_direct_read(iocb, iter, pos); dprintk("NFS: read_iter(%s/%s, %lu@%lu)\n", dentry->d_parent->d_name.name, dentry->d_name.name, @@ -619,7 +619,7 @@ ssize_t nfs_file_write_iter(struct kiocb *iocb, struct iov_iter *iter, size_t count = iov_iter_count(iter); if (iocb->ki_filp->f_flags & O_DIRECT) - return nfs_file_direct_write(iocb, iter, pos, true); + return nfs_file_direct_write(iocb, iter, pos); dprintk("NFS: write_iter(%s/%s, %lu@%lld)\n", dentry->d_parent->d_name.name, dentry->d_name.name, diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index cdf1119..3134079 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -174,7 +174,6 @@ enum rq_flag_bits { __REQ_FLUSH_SEQ, /* request for flush sequence */ __REQ_IO_STAT, /* account I/O stat */ __REQ_MIXED_MERGE, /* merge of different types, fail separately */ - __REQ_KERNEL, /* direct IO to kernel pages */ __REQ_NR_BITS, /* stops here */ }; @@ -222,6 +221,5 @@ enum rq_flag_bits { #define REQ_IO_STAT (1 << __REQ_IO_STAT) #define REQ_MIXED_MERGE (1 << __REQ_MIXED_MERGE) #define REQ_SECURE (1 << __REQ_SECURE) -#define REQ_KERNEL (1 << __REQ_KERNEL) #endif /* __LINUX_BLK_TYPES_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 31d2e17..679c7cc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -180,8 +180,6 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define READ 0 #define WRITE RW_MASK #define READA RWA_MASK -#define KERNEL_READ (READ|REQ_KERNEL) -#define KERNEL_WRITE (WRITE|REQ_KERNEL) #define READ_SYNC (READ | REQ_SYNC) #define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE) diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 9f8e8a9..6033367 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -446,9 +446,9 @@ extern int nfs3_removexattr (struct dentry *, const char *name); */ extern ssize_t nfs_direct_IO(int, struct kiocb *, struct iov_iter *, loff_t); extern ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, - loff_t pos, bool uio); + loff_t pos); extern ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter, - loff_t pos, bool uio); + loff_t pos); /* * linux/fs/nfs/dir.c diff --git a/mm/page_io.c b/mm/page_io.c index 33da274..60a5503 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -203,14 +203,14 @@ int swap_writepage(struct page *page, struct writeback_control *wbc) if (sis->flags & SWP_FILE) { struct kiocb kiocb; struct file *swap_file = sis->swap_file; - struct address_space *mapping = swap_file->f_mapping; - struct iovec iov = { - .iov_base = kmap(page), - .iov_len = PAGE_SIZE, + struct bio_vec bvec = { + .bv_page = kmap(page), + .bv_len = PAGE_SIZE, + .bv_offset = 0, }; struct iov_iter iter; - iov_iter_init(&iter, &iov, 1, PAGE_SIZE, 0); + iov_iter_init_bvec(&iter, &bvec, 1, PAGE_SIZE, 0); init_sync_kiocb(&kiocb, swap_file); kiocb.ki_pos = page_file_offset(page); @@ -218,8 +218,7 @@ int swap_writepage(struct page *page, struct writeback_control *wbc) kiocb.ki_nbytes = PAGE_SIZE; unlock_page(page); - ret = mapping->a_ops->direct_IO(KERNEL_WRITE, &kiocb, &iter, - kiocb.ki_pos); + ret = swap_file->f_op->write_iter(&kiocb, &iter, kiocb.ki_pos); kunmap(page); if (ret == PAGE_SIZE) { count_vm_event(PSWPOUT); -- 1.8.1