Changes since v3: - Return absolute append offset in bytes, in both io_uring and aio - Repurpose cqe's res/flags and introduce res64 to send 64bit append-offset - Change iov_iter_truncate to report whether it actually truncated - Prevent short write and return failure if zone-append is spanning beyond end-of-device - Change ki_complete(...,long ret2) interface to support 64bit ret2 v3: https://lore.kernel.org/lkml/1593974870-18919-1-git-send-email-joshi.k@xxxxxxxxxxx/ Changes since v2: - Use file append infra (O_APPEND/RWF_APPEND) to trigger zone-append (Christoph, Wilcox) - Added Block I/O path changes (Damien). Avoided append split into multi-bio. - Added patch to extend zone-append in block-layer to support bvec iov_iter. Append using io-uring fixed-buffer is enabled with this. - Made io-uring support code more concise, added changes mentioned by Pavel. v2: https://lore.kernel.org/io-uring/1593105349-19270-1-git-send-email-joshi.k@xxxxxxxxxxx/ Changes since v1: - No new opcodes in uring or aio. Use RWF_ZONE_APPEND flag instead. - linux-aio changes vanish because of no new opcode - Fixed the overflow and other issues mentioned by Damien - Simplified uring support code, fixed the issues mentioned by Pavel - Added error checks for io-uring fixed-buffer and sync kiocb v1: https://lore.kernel.org/io-uring/1592414619-5646-1-git-send-email-joshi.k@xxxxxxxxxxx/ Cover letter (updated): This patchset enables zone-append using io-uring/linux-aio, on block IO path. Purpose is to provide zone-append consumption ability to applications which are using zoned-block-device directly. Application can send write with existing O/RWF_APPEND;On a zoned-block-device this will trigger zone-append. On regular block device, existing file-append behavior is retained. However, infra allows zone-append to be triggered on any file if FMODE_ZONE_APPEND (new kernel-only fmode) is set during open. With zone-append, written-location within zone is known only after completion. So apart from the usual return value of write, additional means are needed to obtain the actual written-location. In aio, 64bit append-offset is returned to application using res2 field of io_event - struct io_event { __u64 data; /* the data field from the iocb */ __u64 obj; /* what iocb this event came from */ __s64 res; /* result code for this event */ __s64 res2; /* secondary result */ }; In io-uring, [cqe->res, cqq->flags] repurposed into res64 to return 64bit append-offset to user-space. struct io_uring_cqe { __u64 user_data; /* sqe->data submission passed back */ union { struct { __s32 res; /* result code for this event */ __u32 flags; }; __s64 res64; /* appending offset for zone append */ }; }; Zone-append write is ensured not to be a short-write. Kanchan Joshi (3): fs: introduce FMODE_ZONE_APPEND and IOCB_ZONE_APPEND block: add zone append handling for direct I/O path block: enable zone-append for iov_iter of bvec type SelvaKumar S (3): fs: change ki_complete interface to support 64bit ret2 uio: return status with iov truncation io_uring: add support for zone-append block/bio.c | 31 ++++++++++++++++++++--- drivers/block/loop.c | 2 +- drivers/nvme/target/io-cmd-file.c | 2 +- drivers/target/target_core_file.c | 2 +- fs/aio.c | 2 +- fs/block_dev.c | 51 +++++++++++++++++++++++++++++-------- fs/io_uring.c | 53 +++++++++++++++++++++++++++++++-------- fs/overlayfs/file.c | 2 +- include/linux/fs.h | 16 +++++++++--- include/linux/uio.h | 7 ++++-- include/uapi/linux/io_uring.h | 9 +++++-- 11 files changed, 142 insertions(+), 35 deletions(-) -- 2.7.4
