This adds a new io_uring interface to exchange meta along with read/write. Interface: Meta information is represented using a newly introduced 'struct io_uring_meta'. Application sets up a SQE128 ring, and prepares io_uring_meta within unused portion of SQE. Application populates 'struct io_uring_meta' fields as below: * meta_type: describes type of meta that is passed. Currently one type "Integrity" is supported. * meta_flags: these are meta-type specific flags. Three flags are exposed for integrity type, namely INTEGRITY_CHK_GUARD/APPTAG/REFTAG. * meta_len: length of the meta buffer * meta_addr: address of the meta buffer * apptag: optional application-specific 16b value; this goes along with INTEGRITY_CHK_APPTAG flag. Block path (direct IO) and NVMe driver are modified to support this. The first patch is borrowed from Mikulas series[1] to make the metadata split work correctly. Next 5 patches are enhancements in the block/nvme so that user meta buffer is handled correctly (mostly when it gets split). Patch 8 adds the io_uring support. Patch 9 adds the support for block direct IO, and patch 10 for NVMe. Example program on how to use the interface is appended below [2] Tree: https://github.com/SamsungDS/linux/tree/feat/pi_us_v2 Testing: has been done by modifying fio to use this interface. https://github.com/samsungds/fio/commits/feat/test-meta-v3 Changes since v1: https://lore.kernel.org/linux-block/20240425183943.6319-1-joshi.k@xxxxxxxxxxx/ - Do not use new opcode for meta, and also add the provision to introduce new meta types beyond integrity (Pavel) - Stuff IOCB_HAS_META check in need_complete_io (Jens) - Split meta handling in NVMe into a separate handler (Keith) - Add meta handling for __blkdev_direct_IO too (Keith) - Don't inherit BIP_COPY_USER flag for cloned bio's (Christoph) - Better commit descriptions (Christoph) Changes since RFC: - modify io_uring plumbing based on recent async handling state changes - fixes/enhancements to correctly handle the split for meta buffer - add flags to specify guard/reftag/apptag checks - add support to send apptag [1] https://lore.kernel.org/linux-block/719d2e-b0e6-663c-ec38-acf939e4a04b@xxxxxxxxxx/ [2] #define _GNU_SOURCE #include <stdio.h> #include <stdlib.h> #include <string.h> #include <linux/io_uring.h> #include <linux/types.h> #include "liburing.h" /* write data/meta. read both. compare. send apptag too. * prerequisite: * unprotected xfer: format namespace with 4KB + 8b, pi_type = 0 * protected xfer: format namespace with 4KB + 8b, pi_type = 1 */ #define DATA_LEN 4096 #define META_LEN 8 struct t10_pi_tuple { __be16 guard; __be16 apptag; __be32 reftag; }; int main(int argc, char *argv[]) { struct io_uring ring; struct io_uring_sqe *sqe = NULL; struct io_uring_cqe *cqe = NULL; void *wdb,*rdb; char wmb[META_LEN], rmb[META_LEN]; char *data_str = "data buffer"; char *meta_str = "meta"; int fd, ret, blksize; struct stat fstat; unsigned long long offset = DATA_LEN; struct t10_pi_tuple *pi; struct io_uring_meta *md; if (argc != 2) { fprintf(stderr, "Usage: %s <block-device>", argv[0]); return 1; }; if (stat(argv[1], &fstat) == 0) { blksize = (int)fstat.st_blksize; } else { perror("stat"); return 1; } if (posix_memalign(&wdb, blksize, DATA_LEN)) { perror("posix_memalign failed"); return 1; } if (posix_memalign(&rdb, blksize, DATA_LEN)) { perror("posix_memalign failed"); return 1; } strcpy(wdb, data_str); strcpy(wmb, meta_str); fd = open(argv[1], O_RDWR | O_DIRECT); if (fd < 0) { printf("Error in opening device\n"); return 0; } ret = io_uring_queue_init(8, &ring, IORING_SETUP_SQE128); if (ret) { fprintf(stderr, "ring setup failed: %d\n", ret); return 1; } /* write data + meta-buffer to device */ sqe = io_uring_get_sqe(&ring); if (!sqe) { fprintf(stderr, "get sqe failed\n"); return 1; } io_uring_prep_write(sqe, fd, wdb, DATA_LEN, offset); md = (struct io_uring_meta *) sqe->cmd; md->meta_type = META_TYPE_INTEGRITY; md->meta_addr = (__u64)wmb; md->meta_len = META_LEN; /* flags to ask for guard/reftag/apptag*/ md->meta_flags = INTEGRITY_CHK_APPTAG; md->apptag = 0x1234; pi = (struct t10_pi_tuple *)wmb; pi->apptag = 0x3412; ret = io_uring_submit(&ring); if (ret <= 0) { fprintf(stderr, "sqe submit failed: %d\n", ret); return 1; } ret = io_uring_wait_cqe(&ring, &cqe); if (!cqe) { fprintf(stderr, "cqe is NULL :%d\n", ret); return 1; } if (cqe->res < 0) { fprintf(stderr, "write cqe failure: %d", cqe->res); return 1; } io_uring_cqe_seen(&ring, cqe); /* read data + meta-buffer back from device */ sqe = io_uring_get_sqe(&ring); if (!sqe) { fprintf(stderr, "get sqe failed\n"); return 1; } io_uring_prep_read(sqe, fd, rdb, DATA_LEN, offset); md = (struct io_uring_meta *) sqe->cmd; md->meta_type = META_TYPE_INTEGRITY; md->meta_addr = (__u64)rmb; md->meta_len = META_LEN; md->meta_flags = INTEGRITY_CHK_APPTAG; md->apptag = 0x1234; ret = io_uring_submit(&ring); if (ret <= 0) { fprintf(stderr, "sqe submit failed: %d\n", ret); return 1; } ret = io_uring_wait_cqe(&ring, &cqe); if (!cqe) { fprintf(stderr, "cqe is NULL :%d\n", ret); return 1; } if (cqe->res < 0) { fprintf(stderr, "read cqe failure: %d", cqe->res); return 1; } io_uring_cqe_seen(&ring, cqe); if (strncmp(wmb, rmb, META_LEN)) printf("Failure: meta mismatch!, wmb=%s, rmb=%s\n", wmb, rmb); if (strncmp(wdb, rdb, DATA_LEN)) printf("Failure: data mismatch!\n"); io_uring_queue_exit(&ring); free(rdb); free(wdb); return 0; } Anuj Gupta (5): block: set bip_vcnt correctly block: copy bip_max_vcnt vecs instead of bip_vcnt during clone block: Handle meta bounce buffer correctly in case of split block: modify bio_integrity_map_user to accept iov_iter as argument io_uring/rw: add support to send meta along with read/write Kanchan Joshi (4): block: introduce BIP_CLONED flag block: define meta io descriptor block: add support to pass user meta buffer nvme: add handling for user integrity buffer Mikulas Patocka (1): block: change rq_integrity_vec to respect the iterator block/bio-integrity.c | 75 ++++++++++++++++++++++++++----- block/fops.c | 28 +++++++++++- block/t10-pi.c | 6 +++ drivers/nvme/host/core.c | 85 ++++++++++++++++++++++++----------- drivers/nvme/host/ioctl.c | 11 ++++- drivers/nvme/host/pci.c | 6 +-- include/linux/bio.h | 25 +++++++++-- include/linux/blk-integrity.h | 16 +++---- include/linux/fs.h | 1 + include/uapi/linux/io_uring.h | 30 ++++++++++++- io_uring/io_uring.c | 7 +++ io_uring/rw.c | 68 ++++++++++++++++++++++++++-- io_uring/rw.h | 9 +++- 13 files changed, 308 insertions(+), 59 deletions(-) -- 2.25.1
