selftests/ublk: add read-only buffer registration test

Add --rdonly_shmem_buf option to kublk that registers shared memory
buffers with UBLK_SHMEM_BUF_READ_ONLY (read-only pinning without
FOLL_WRITE) and mmaps with PROT_READ only.

Add test_shmemzc_04.sh which exercises the new flag with a null target,
hugetlbfs buffer, and write workload. Write I/O works because the
server only reads from the shared buffer — the data flows from client
to kernel to the shared pages, and the server reads them out.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://patch.msgid.link/20260331153207.3635125-11-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Author: Ming Lei

tools/testing/selftests/ublk/Makefile

@@ -55,6 +55,7 @@ TEST_PROGS += test_part_02.sh
 TEST_PROGS += test_shmemzc_01.sh
 TEST_PROGS += test_shmemzc_02.sh
 TEST_PROGS += test_shmemzc_03.sh
+TEST_PROGS += test_shmemzc_04.sh
 
 TEST_PROGS += test_stress_01.sh
 TEST_PROGS += test_stress_02.sh

tools/testing/selftests/ublk/kublk.c

@@ -1219,11 +1219,13 @@ static void ublk_shmem_unregister_all(void)
 	shmem_count = 0;
 }
 
-static int ublk_ctrl_reg_buf(struct ublk_dev *dev, void *addr, size_t size)
+static int ublk_ctrl_reg_buf(struct ublk_dev *dev, void *addr, size_t size,
+			     __u32 flags)
 {
 	struct ublk_shmem_buf_reg buf_reg = {
 		.addr = (unsigned long)addr,
 		.len = size,
+		.flags = flags,
 	};
 	struct ublk_ctrl_cmd_data data = {
 		.cmd_op = UBLK_U_CMD_REG_BUF,
@@ -1272,7 +1274,7 @@ static void ublk_shmem_handle_client(int sock_fd, struct ublk_dev *dev)
 	}
 
 	/* Register server's VA range with kernel for PFN matching */
-	ret = ublk_ctrl_reg_buf(dev, base, size);
+	ret = ublk_ctrl_reg_buf(dev, base, size, 0);
 	if (ret < 0) {
 		ublk_dbg(UBLK_DBG_DEV,
 			 "shmem_zc: kernel reg failed %d\n", ret);
@@ -1357,15 +1359,17 @@ static int ublk_shmem_htlb_setup(const struct dev_ctx *ctx,
 		return -EINVAL;
 	}
 
-	base = mmap(NULL, st.st_size, PROT_READ | PROT_WRITE,
+	base = mmap(NULL, st.st_size,
+		    ctx->rdonly_shmem_buf ? PROT_READ : PROT_READ | PROT_WRITE,
 		    MAP_SHARED | MAP_POPULATE, fd, 0);
 	if (base == MAP_FAILED) {
 		ublk_err("htlb: mmap failed\n");
 		close(fd);
 		return -ENOMEM;
 	}
 
-	ret = ublk_ctrl_reg_buf(dev, base, st.st_size);
+	ret = ublk_ctrl_reg_buf(dev, base, st.st_size,
+			       ctx->rdonly_shmem_buf ? UBLK_SHMEM_BUF_READ_ONLY : 0);
 	if (ret < 0) {
 		ublk_err("htlb: reg_buf failed: %d\n", ret);
 		munmap(base, st.st_size);
@@ -2129,6 +2133,7 @@ int main(int argc, char *argv[])
 		{ "no_auto_part_scan",	0,	NULL,  0 },
 		{ "shmem_zc",		0,	NULL,  0  },
 		{ "htlb",		1,	NULL,  0  },
+		{ "rdonly_shmem_buf",	0,	NULL,  0  },
 		{ 0, 0, 0, 0 }
 	};
 	const struct ublk_tgt_ops *ops = NULL;
@@ -2248,6 +2253,8 @@ int main(int argc, char *argv[])
 				ctx.flags |= UBLK_F_SHMEM_ZC;
 			if (!strcmp(longopts[option_idx].name, "htlb"))
 				ctx.htlb_path = strdup(optarg);
+			if (!strcmp(longopts[option_idx].name, "rdonly_shmem_buf"))
+				ctx.rdonly_shmem_buf = 1;
 			break;
 		case '?':
 			/*

tools/testing/selftests/ublk/kublk.h

@@ -81,6 +81,7 @@ struct dev_ctx {
 	unsigned int	no_ublk_fixed_fd:1;
 	unsigned int	safe_stop:1;
 	unsigned int	no_auto_part_scan:1;
+	unsigned int	rdonly_shmem_buf:1;
 	__u32 integrity_flags;
 	__u8 metadata_size;
 	__u8 pi_offset;

tools/testing/selftests/ublk/test_shmemzc_04.sh

@@ -0,0 +1,72 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Test: shmem_zc with read-only buffer registration on null target
+#
+# Same as test_shmemzc_01 but with --rdonly_shmem_buf: pages are pinned
+# without FOLL_WRITE (UBLK_BUF_F_READ).  Write I/O works because
+# the server only reads from the shared buffer.
+
+. "$(cd "$(dirname "$0")" && pwd)"/test_common.sh
+
+ERR_CODE=0
+
+_prep_test "shmem_zc" "null target hugetlbfs shmem zero-copy rdonly_buf test"
+
+if ! _have_program fio; then
+	echo "SKIP: fio not available"
+	exit "$UBLK_SKIP_CODE"
+fi
+
+if ! grep -q hugetlbfs /proc/filesystems; then
+	echo "SKIP: hugetlbfs not supported"
+	exit "$UBLK_SKIP_CODE"
+fi
+
+# Allocate hugepages
+OLD_NR_HP=$(cat /proc/sys/vm/nr_hugepages)
+echo 10 > /proc/sys/vm/nr_hugepages
+NR_HP=$(cat /proc/sys/vm/nr_hugepages)
+if [ "$NR_HP" -lt 2 ]; then
+	echo "SKIP: cannot allocate hugepages"
+	echo "$OLD_NR_HP" > /proc/sys/vm/nr_hugepages
+	exit "$UBLK_SKIP_CODE"
+fi
+
+# Mount hugetlbfs
+HTLB_MNT=$(mktemp -d "${UBLK_TEST_DIR}/htlb_mnt_XXXXXX")
+if ! mount -t hugetlbfs none "$HTLB_MNT"; then
+	echo "SKIP: cannot mount hugetlbfs"
+	rmdir "$HTLB_MNT"
+	echo "$OLD_NR_HP" > /proc/sys/vm/nr_hugepages
+	exit "$UBLK_SKIP_CODE"
+fi
+
+HTLB_FILE="$HTLB_MNT/ublk_buf"
+fallocate -l 4M "$HTLB_FILE"
+
+dev_id=$(_add_ublk_dev -t null --shmem_zc --htlb "$HTLB_FILE" --rdonly_shmem_buf)
+_check_add_dev $TID $?
+
+fio --name=htlb_zc_rdonly \
+	--filename=/dev/ublkb"${dev_id}" \
+	--ioengine=io_uring \
+	--rw=randwrite \
+	--direct=1 \
+	--bs=4k \
+	--size=4M \
+	--iodepth=32 \
+	--mem=mmaphuge:"$HTLB_FILE" \
+	> /dev/null 2>&1
+ERR_CODE=$?
+
+# Delete device first so daemon releases the htlb mmap
+_ublk_del_dev "${dev_id}"
+
+rm -f "$HTLB_FILE"
+umount "$HTLB_MNT"
+rmdir "$HTLB_MNT"
+echo "$OLD_NR_HP" > /proc/sys/vm/nr_hugepages
+
+_cleanup_test "shmem_zc"
+
+_show_result $TID $ERR_CODE