Export a zoned null_blk device through the NVMe target and verify that Zone Management Receive zeroes reserved and unused report bytes and rejects a transfer length inconsistent with NUMD. The test runs on every configured transport, with RDMA restricted to 4 KiB page kernels so that the preparatory write exceeds the default inline-data limit. Add a small passthrough helper because nvme-cli does not expose the reserved report bytes. The test fails on the unpatched kernel and passes with the fix applied. Assisted-by: LLM Signed-off-by: Andrea Parri --- src/.gitignore | 1 + src/Makefile | 1 + src/nvme-zone-report.c | 165 +++++++++++++++++++++++++++++++++++++++++ tests/nvme/072 | 68 +++++++++++++++++ tests/nvme/072.out | 2 + 5 files changed, 237 insertions(+) create mode 100644 src/nvme-zone-report.c create mode 100755 tests/nvme/072 create mode 100644 tests/nvme/072.out diff --git a/src/.gitignore b/src/.gitignore index 2429da9d9cf44..8119476416937 100644 --- a/src/.gitignore +++ b/src/.gitignore @@ -19,3 +19,4 @@ /nvme-passthru-admin-uring /nvme-delay-ioctl /nvme-sentinel-read +/nvme-zone-report diff --git a/src/Makefile b/src/Makefile index 78433f0762b4a..7c4fd600ace1d 100644 --- a/src/Makefile +++ b/src/Makefile @@ -25,6 +25,7 @@ C_TARGETS := \ nvme-delay-ioctl \ nvme-passthrough-meta \ nvme-sentinel-read \ + nvme-zone-report \ ioctl-lbmd-query \ nbdsetsize \ openclose \ diff --git a/src/nvme-zone-report.c b/src/nvme-zone-report.c new file mode 100644 index 0000000000000..951b1d03d4a75 --- /dev/null +++ b/src/nvme-zone-report.c @@ -0,0 +1,165 @@ +// SPDX-License-Identifier: GPL-3.0+ +// Copyright (C) 2026 Andrea Parri + +/* Check that unused bytes in an NVMe zone report are zeroed. */ +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define REPORT_LEN 4096 +/* + * Larger than the default RDMA in-capsule data size on 4 KiB page kernels. + * nvme/072 skips RDMA on other page sizes, where this write could stay + * inline rather than use buffers allocated and freed per command. + */ +#define POISON_LEN 8192 +#define WRITE_OPCODE 0x01 +#define ZONE_REPORT_OPCODE 0x7a +#define PARTIAL_REPORT (1U << 16) +#define ZONE_REPORT_HEADER 64 +#define ZONE_DESC_LEN 64 +#define ZONE_START_OFFSET 16 +#define NR_ATTEMPTS 64 + +static int poison_target(int fd, unsigned int iteration) +{ + unsigned char data[POISON_LEN]; + struct nvme_passthru_cmd cmd = { + .opcode = WRITE_OPCODE, + .nsid = 1, + .addr = (uintptr_t)data, + .data_len = sizeof(data), + .cdw10 = iteration * (POISON_LEN / 512), + .cdw12 = POISON_LEN / 512 - 1, + }; + + memset(data, 0x5a, sizeof(data)); + return ioctl(fd, NVME_IOCTL_IO_CMD, &cmd); +} + +static uint64_t read_le64(const unsigned char *p) +{ + uint64_t value; + + memcpy(&value, p, sizeof(value)); + return le64toh(value); +} + +int main(int argc, char **argv) +{ + unsigned char *report; + unsigned long long slba; + char *end; + void *p; + int fd, i, j, ret, rc = 0; + + if (argc != 3) { + fprintf(stderr, "usage: %s /dev/nvmeXnY last-zone-slba\n", + argv[0]); + return 2; + } + + errno = 0; + slba = strtoull(argv[2], &end, 0); + if (errno || *end) { + fprintf(stderr, "invalid SLBA: %s\n", argv[2]); + return 2; + } + + /* + * Page-align the report so that the kernel maps it for the transfer + * instead of bouncing it: a bounce buffer is zero-filled, which would + * hide the sentinel and any bytes the target left unwritten. + */ + ret = posix_memalign(&p, 4096, REPORT_LEN); + if (ret) { + fprintf(stderr, "posix_memalign: %s\n", strerror(ret)); + return 2; + } + report = p; + + fd = open(argv[1], O_RDWR); + if (fd < 0) { + perror(argv[1]); + free(report); + return 2; + } + + for (i = 0; i < NR_ATTEMPTS; i++) { + struct nvme_passthru_cmd cmd = { + .opcode = ZONE_REPORT_OPCODE, + .nsid = 1, + .addr = (uintptr_t)report, + .data_len = REPORT_LEN, + .cdw10 = (uint32_t)slba, + .cdw11 = (uint32_t)(slba >> 32), + .cdw12 = REPORT_LEN / 4 - 1, + .cdw13 = PARTIAL_REPORT, + }; + unsigned int nonzero = 0, stale = 0, poisoned = 0; + unsigned char sentinel = i & 1 ? 0xa5 : 0x3c; + + ret = poison_target(fd, i); + if (ret) { + if (ret < 0) + perror("poison_target"); + else + fprintf(stderr, "poison write status: %#x\n", ret); + rc = 2; + goto out; + } + + memset(report, sentinel, REPORT_LEN); + ret = ioctl(fd, NVME_IOCTL_IO_CMD, &cmd); + if (ret) { + if (ret < 0) + perror("NVME_IOCTL_IO_CMD"); + else + fprintf(stderr, "NVMe status: %#x\n", ret); + rc = 2; + goto out; + } + + if (read_le64(report) != 1 || + read_le64(report + ZONE_REPORT_HEADER + + ZONE_START_OFFSET) != slba) { + fprintf(stderr, "unexpected zone report header or SLBA\n"); + rc = 1; + goto out; + } + + for (j = 8; j < REPORT_LEN; j++) { + if (j >= ZONE_REPORT_HEADER && + j < ZONE_REPORT_HEADER + ZONE_DESC_LEN) + continue; + if (!report[j]) + continue; + nonzero++; + if (report[j] == sentinel) + stale++; + if (report[j] == 0x5a) + poisoned++; + } + + fprintf(stderr, "attempt %d: %u nonzero bytes " + "(%u poison, %u sentinel)\n", i + 1, nonzero, + poisoned, stale); + if (nonzero) { + rc = 1; + goto out; + } + } + +out: + close(fd); + free(report); + return rc; +} diff --git a/tests/nvme/072 b/tests/nvme/072 new file mode 100755 index 0000000000000..c7bcf93ab4d20 --- /dev/null +++ b/tests/nvme/072 @@ -0,0 +1,68 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-3.0+ +# Copyright (C) 2026 Andrea Parri +# +# Check that NVMe target zone reports are fully initialized and that their +# transfer length matches NUMD. +# +# Regression test for patch "nvmet: zns: don't leak stale memory in zone +# management receive". + +. tests/nvme/rc +. common/null_blk + +DESCRIPTION="check NVMe target zone report initialization and length" +QUICK=1 + +requires() { + _nvme_requires + _have_loop + _require_kernel_nvme_target + _have_module null_blk + _have_kernel_options BLK_DEV_ZONED + _have_src_program nvme-zone-report + + # RDMA defaults to PAGE_SIZE bytes of inline data. The helper's + # 8 KiB preparatory write must exceed that limit. + if [[ "$nvme_trtype" == "rdma" ]]; then + _page_size_equals 4096 + fi +} + +set_conditions() { + _set_nvme_trtype "$@" +} + +test() { + echo "Running ${TEST_NAME}" + + local block_size dev last_sector ret sectors slba zone_sectors + + _setup_nvmet + _register_test_cleanup _cleanup_nvmet_zoned_target + if ! _nvmet_zoned_target_setup; then + return 1 + fi + dev="/dev/$(_find_nvme_ns "$def_subsys_uuid")" + + sectors=$(cat /sys/block/nullb0/size) + zone_sectors=$(cat /sys/block/nullb0/queue/chunk_sectors) + block_size=$(cat /sys/block/nullb0/queue/logical_block_size) + last_sector=$(((sectors - 1) / zone_sectors * zone_sectors)) + slba=$((last_sector * 512 / block_size)) + + src/nvme-zone-report "$dev" "$slba" >>"$FULL" 2>&1 + ret=$? + case $ret in + 0) ;; + 1) echo "zone report contained stale data" ;; + *) echo "zone report checker failed" ;; + esac + + _check_zone_report "$dev" 4096 1023 0 + _check_zone_report "$dev" 8192 1023 15 + + _nvmet_zoned_target_cleanup + + echo "Test complete" +} diff --git a/tests/nvme/072.out b/tests/nvme/072.out new file mode 100644 index 0000000000000..3f765b30a22b0 --- /dev/null +++ b/tests/nvme/072.out @@ -0,0 +1,2 @@ +Running nvme/072 +Test complete -- 2.53.0