Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934042Ab3CHW6X (ORCPT ); Fri, 8 Mar 2013 17:58:23 -0500 Received: from aserp1040.oracle.com ([141.146.126.69]:36035 "EHLO aserp1040.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1758037Ab3CHWwq (ORCPT ); Fri, 8 Mar 2013 17:52:46 -0500 From: Dave Kleikamp To: Zach Brown Cc: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org, Dave Kleikamp Subject: [PATCH V7 -next 15/33] aio: add aio support for iov_iter arguments Date: Fri, 8 Mar 2013 16:52:10 -0600 Message-Id: <1362783148-22736-16-git-send-email-dave.kleikamp@oracle.com> X-Mailer: git-send-email 1.8.1.5 In-Reply-To: <1362783148-22736-1-git-send-email-dave.kleikamp@oracle.com> References: <1362783148-22736-1-git-send-email-dave.kleikamp@oracle.com> X-Source-IP: acsinet22.oracle.com [141.146.126.238] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4473 Lines: 154 This adds iocb cmds which specify that memory is held in iov_iter structures. This lets kernel callers specify memory that can be expressed in an iov_iter, which includes pages in bio_vec arrays. Only kernel callers can provide an iov_iter so it doesn't make a lot of sense to expose the IOCB_CMD values for this as part of the user space ABI. But kernel callers should also be able to perform the usual aio operations which suggests using the the existing operation namespace and support code. Signed-off-by: Dave Kleikamp Cc: Zach Brown --- fs/aio.c | 67 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/aio.h | 3 ++ include/uapi/linux/aio_abi.h | 2 ++ 3 files changed, 72 insertions(+) diff --git a/fs/aio.c b/fs/aio.c index 6dd3a4e..51d3afa 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -1144,6 +1144,48 @@ static ssize_t aio_setup_single_vector(int rw, struct kiocb *kiocb) return 0; } +static ssize_t aio_read_iter(struct kiocb *iocb) +{ + struct file *file = iocb->ki_filp; + ssize_t ret; + + if (unlikely(!is_kernel_kiocb(iocb))) + return -EINVAL; + + if (unlikely(!(file->f_mode & FMODE_READ))) + return -EBADF; + + ret = security_file_permission(file, MAY_READ); + if (unlikely(ret)) + return ret; + + if (!file->f_op->read_iter) + return -EINVAL; + + return file->f_op->read_iter(iocb, iocb->ki_iter, iocb->ki_pos); +} + +static ssize_t aio_write_iter(struct kiocb *iocb) +{ + struct file *file = iocb->ki_filp; + ssize_t ret; + + if (unlikely(!is_kernel_kiocb(iocb))) + return -EINVAL; + + if (unlikely(!(file->f_mode & FMODE_WRITE))) + return -EBADF; + + ret = security_file_permission(file, MAY_WRITE); + if (unlikely(ret)) + return ret; + + if (!file->f_op->write_iter) + return -EINVAL; + + return file->f_op->write_iter(iocb, iocb->ki_iter, iocb->ki_pos); +} + /* * aio_setup_iocb: * Performs the initial checks and aio retry method @@ -1195,6 +1237,14 @@ rw_common: ret = aio_rw_vect_retry(req, rw, rw_op); break; + case IOCB_CMD_READ_ITER: + ret = aio_read_iter(req); + break; + + case IOCB_CMD_WRITE_ITER: + ret = aio_write_iter(req); + break; + case IOCB_CMD_FDSYNC: if (!file->f_op->aio_fsync) return -EINVAL; @@ -1268,6 +1318,23 @@ void aio_kernel_init_rw(struct kiocb *iocb, struct file *filp, } EXPORT_SYMBOL_GPL(aio_kernel_init_rw); +/* + * The iter count must be set before calling here. Some filesystems uses + * iocb->ki_left as an indicator of the size of an IO. + */ +void aio_kernel_init_iter(struct kiocb *iocb, struct file *filp, + unsigned short op, struct iov_iter *iter, loff_t off) +{ + iocb->ki_filp = filp; + iocb->ki_iter = iter; + iocb->ki_opcode = op; + iocb->ki_pos = off; + iocb->ki_nbytes = iov_iter_count(iter); + iocb->ki_left = iocb->ki_nbytes; + iocb->ki_ctx = (void *)-1; +} +EXPORT_SYMBOL_GPL(aio_kernel_init_iter); + void aio_kernel_init_callback(struct kiocb *iocb, void (*complete)(u64 user_data, long res), u64 user_data) diff --git a/include/linux/aio.h b/include/linux/aio.h index eccf646..75942e1 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -72,6 +72,7 @@ struct kiocb { * this is the underlying eventfd context to deliver events to. */ struct eventfd_ctx *ki_eventfd; + struct iov_iter *ki_iter; }; static inline bool is_sync_kiocb(struct kiocb *kiocb) @@ -110,6 +111,8 @@ struct kiocb *aio_kernel_alloc(gfp_t gfp); void aio_kernel_free(struct kiocb *iocb); void aio_kernel_init_rw(struct kiocb *iocb, struct file *filp, unsigned short op, void *ptr, size_t nr, loff_t off); +void aio_kernel_init_iter(struct kiocb *iocb, struct file *filp, + unsigned short op, struct iov_iter *iter, loff_t off); void aio_kernel_init_callback(struct kiocb *iocb, void (*complete)(u64 user_data, long res), u64 user_data); diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h index 86fa7a7..bd39bb2 100644 --- a/include/uapi/linux/aio_abi.h +++ b/include/uapi/linux/aio_abi.h @@ -44,6 +44,8 @@ enum { IOCB_CMD_NOOP = 6, IOCB_CMD_PREADV = 7, IOCB_CMD_PWRITEV = 8, + IOCB_CMD_READ_ITER = 9, + IOCB_CMD_WRITE_ITER = 10, }; /* -- 1.8.1.5 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/