[PATCH v3 5/9] selftests/net: Extract uring helpers to be reusable

[PATCH v3 5/9] selftests/net: Extract uring helpers to be reusable

[Breno Leitao]

Instead of defining basic io_uring functions in the test case, move them
to a common directory, so, other tests can use them.

This simplify the test code and reuse the common liburing
infrastructure. This is basically a copy of what we have in
io_uring_zerocopy_tx with some minor improvements to make checkpatch
happy.

A follow-up test will use the same helpers in a BPF sockopt test.

Signed-off-by: Breno Leitao <leitao@debian.org>
---
 tools/include/io_uring/mini_liburing.h        | 282 ++++++++++++++++++
 tools/testing/selftests/net/Makefile          |   1 +
 .../selftests/net/io_uring_zerocopy_tx.c      | 268 +----------------
 3 files changed, 285 insertions(+), 266 deletions(-)
 create mode 100644 tools/include/io_uring/mini_liburing.h

diff --git a/tools/include/io_uring/mini_liburing.h b/tools/include/io_uring/mini_liburing.h
new file mode 100644
index 000000000000..9ccb16074eb5
--- /dev/null
+++ b/tools/include/io_uring/mini_liburing.h
@@ -0,0 +1,282 @@
+/* SPDX-License-Identifier: MIT */
+
+#include <linux/io_uring.h>
+#include <sys/mman.h>
+#include <sys/syscall.h>
+#include <stdio.h>
+#include <string.h>
+#include <unistd.h>
+
+struct io_sq_ring {
+	unsigned int *head;
+	unsigned int *tail;
+	unsigned int *ring_mask;
+	unsigned int *ring_entries;
+	unsigned int *flags;
+	unsigned int *array;
+};
+
+struct io_cq_ring {
+	unsigned int *head;
+	unsigned int *tail;
+	unsigned int *ring_mask;
+	unsigned int *ring_entries;
+	struct io_uring_cqe *cqes;
+};
+
+struct io_uring_sq {
+	unsigned int *khead;
+	unsigned int *ktail;
+	unsigned int *kring_mask;
+	unsigned int *kring_entries;
+	unsigned int *kflags;
+	unsigned int *kdropped;
+	unsigned int *array;
+	struct io_uring_sqe *sqes;
+
+	unsigned int sqe_head;
+	unsigned int sqe_tail;
+
+	size_t ring_sz;
+};
+
+struct io_uring_cq {
+	unsigned int *khead;
+	unsigned int *ktail;
+	unsigned int *kring_mask;
+	unsigned int *kring_entries;
+	unsigned int *koverflow;
+	struct io_uring_cqe *cqes;
+
+	size_t ring_sz;
+};
+
+struct io_uring {
+	struct io_uring_sq sq;
+	struct io_uring_cq cq;
+	int ring_fd;
+};
+
+#if defined(__x86_64) || defined(__i386__)
+#define read_barrier()	__asm__ __volatile__("":::"memory")
+#define write_barrier()	__asm__ __volatile__("":::"memory")
+#else
+#define read_barrier()	__sync_synchronize()
+#define write_barrier()	__sync_synchronize()
+#endif
+
+static inline int io_uring_mmap(int fd, struct io_uring_params *p,
+				struct io_uring_sq *sq, struct io_uring_cq *cq)
+{
+	size_t size;
+	void *ptr;
+	int ret;
+
+	sq->ring_sz = p->sq_off.array + p->sq_entries * sizeof(unsigned int);
+	ptr = mmap(0, sq->ring_sz, PROT_READ | PROT_WRITE,
+		   MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_SQ_RING);
+	if (ptr == MAP_FAILED)
+		return -errno;
+	sq->khead = ptr + p->sq_off.head;
+	sq->ktail = ptr + p->sq_off.tail;
+	sq->kring_mask = ptr + p->sq_off.ring_mask;
+	sq->kring_entries = ptr + p->sq_off.ring_entries;
+	sq->kflags = ptr + p->sq_off.flags;
+	sq->kdropped = ptr + p->sq_off.dropped;
+	sq->array = ptr + p->sq_off.array;
+
+	size = p->sq_entries * sizeof(struct io_uring_sqe);
+	sq->sqes = mmap(0, size, PROT_READ | PROT_WRITE,
+			MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_SQES);
+	if (sq->sqes == MAP_FAILED) {
+		ret = -errno;
+err:
+		munmap(sq->khead, sq->ring_sz);
+		return ret;
+	}
+
+	cq->ring_sz = p->cq_off.cqes + p->cq_entries * sizeof(struct io_uring_cqe);
+	ptr = mmap(0, cq->ring_sz, PROT_READ | PROT_WRITE,
+		   MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_CQ_RING);
+	if (ptr == MAP_FAILED) {
+		ret = -errno;
+		munmap(sq->sqes, p->sq_entries * sizeof(struct io_uring_sqe));
+		goto err;
+	}
+	cq->khead = ptr + p->cq_off.head;
+	cq->ktail = ptr + p->cq_off.tail;
+	cq->kring_mask = ptr + p->cq_off.ring_mask;
+	cq->kring_entries = ptr + p->cq_off.ring_entries;
+	cq->koverflow = ptr + p->cq_off.overflow;
+	cq->cqes = ptr + p->cq_off.cqes;
+	return 0;
+}
+
+static inline int io_uring_setup(unsigned int entries,
+				 struct io_uring_params *p)
+{
+	return syscall(__NR_io_uring_setup, entries, p);
+}
+
+static inline int io_uring_enter(int fd, unsigned int to_submit,
+				 unsigned int min_complete,
+				 unsigned int flags, sigset_t *sig)
+{
+	return syscall(__NR_io_uring_enter, fd, to_submit, min_complete,
+		       flags, sig, _NSIG / 8);
+}
+
+static inline int io_uring_queue_init(unsigned int entries,
+				      struct io_uring *ring,
+				      unsigned int flags)
+{
+	struct io_uring_params p;
+	int fd, ret;
+
+	memset(ring, 0, sizeof(*ring));
+	memset(&p, 0, sizeof(p));
+	p.flags = flags;
+
+	fd = io_uring_setup(entries, &p);
+	if (fd < 0)
+		return fd;
+	ret = io_uring_mmap(fd, &p, &ring->sq, &ring->cq);
+	if (!ret)
+		ring->ring_fd = fd;
+	else
+		close(fd);
+	return ret;
+}
+
+/* Get a sqe */
+static inline struct io_uring_sqe *io_uring_get_sqe(struct io_uring *ring)
+{
+	struct io_uring_sq *sq = &ring->sq;
+
+	if (sq->sqe_tail + 1 - sq->sqe_head > *sq->kring_entries)
+		return NULL;
+	return &sq->sqes[sq->sqe_tail++ & *sq->kring_mask];
+}
+
+static inline int io_uring_wait_cqe(struct io_uring *ring,
+				    struct io_uring_cqe **cqe_ptr)
+{
+	struct io_uring_cq *cq = &ring->cq;
+	const unsigned int mask = *cq->kring_mask;
+	unsigned int head = *cq->khead;
+	int ret;
+
+	*cqe_ptr = NULL;
+	do {
+		read_barrier();
+		if (head != *cq->ktail) {
+			*cqe_ptr = &cq->cqes[head & mask];
+			break;
+		}
+		ret = io_uring_enter(ring->ring_fd, 0, 1,
+				     IORING_ENTER_GETEVENTS, NULL);
+		if (ret < 0)
+			return -errno;
+	} while (1);
+
+	return 0;
+}
+
+static inline int io_uring_submit(struct io_uring *ring)
+{
+	struct io_uring_sq *sq = &ring->sq;
+	const unsigned int mask = *sq->kring_mask;
+	unsigned int ktail, submitted, to_submit;
+	int ret;
+
+	read_barrier();
+	if (*sq->khead != *sq->ktail) {
+		submitted = *sq->kring_entries;
+		goto submit;
+	}
+	if (sq->sqe_head == sq->sqe_tail)
+		return 0;
+
+	ktail = *sq->ktail;
+	to_submit = sq->sqe_tail - sq->sqe_head;
+	for (submitted = 0; submitted < to_submit; submitted++) {
+		read_barrier();
+		sq->array[ktail++ & mask] = sq->sqe_head++ & mask;
+	}
+	if (!submitted)
+		return 0;
+
+	if (*sq->ktail != ktail) {
+		write_barrier();
+		*sq->ktail = ktail;
+		write_barrier();
+	}
+submit:
+	ret = io_uring_enter(ring->ring_fd, submitted, 0,
+			     IORING_ENTER_GETEVENTS, NULL);
+	return ret < 0 ? -errno : ret;
+}
+
+static inline void io_uring_queue_exit(struct io_uring *ring)
+{
+	struct io_uring_sq *sq = &ring->sq;
+
+	munmap(sq->sqes, *sq->kring_entries * sizeof(struct io_uring_sqe));
+	munmap(sq->khead, sq->ring_sz);
+	close(ring->ring_fd);
+}
+
+/* Prepare and send the SQE */
+static inline void io_uring_prep_cmd(struct io_uring_sqe *sqe, int op,
+				     int sockfd,
+				     int level, int optname,
+				     const void *optval,
+				     int optlen)
+{
+	memset(sqe, 0, sizeof(*sqe));
+	sqe->opcode = (__u8)IORING_OP_URING_CMD;
+	sqe->fd = sockfd;
+	sqe->cmd_op = op;
+
+	sqe->level = level;
+	sqe->optname = optname;
+	sqe->optval = (unsigned long long)optval;
+	sqe->optlen = optlen;
+}
+
+static inline int io_uring_register_buffers(struct io_uring *ring,
+					    const struct iovec *iovecs,
+					    unsigned int nr_iovecs)
+{
+	int ret;
+
+	ret = syscall(__NR_io_uring_register, ring->ring_fd,
+		      IORING_REGISTER_BUFFERS, iovecs, nr_iovecs);
+	return (ret < 0) ? -errno : ret;
+}
+
+static inline void io_uring_prep_send(struct io_uring_sqe *sqe, int sockfd,
+				      const void *buf, size_t len, int flags)
+{
+	memset(sqe, 0, sizeof(*sqe));
+	sqe->opcode = (__u8)IORING_OP_SEND;
+	sqe->fd = sockfd;
+	sqe->addr = (unsigned long)buf;
+	sqe->len = len;
+	sqe->msg_flags = (__u32)flags;
+}
+
+static inline void io_uring_prep_sendzc(struct io_uring_sqe *sqe, int sockfd,
+					const void *buf, size_t len, int flags,
+					unsigned int zc_flags)
+{
+	io_uring_prep_send(sqe, sockfd, buf, len, flags);
+	sqe->opcode = (__u8)IORING_OP_SEND_ZC;
+	sqe->ioprio = zc_flags;
+}
+
+static inline void io_uring_cqe_seen(struct io_uring *ring)
+{
+	*(&ring->cq)->khead += 1;
+	write_barrier();
+}
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 7f3ab2a93ed6..70f4a5982b01 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -94,6 +94,7 @@ $(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma
 $(OUTPUT)/tcp_mmap: LDLIBS += -lpthread -lcrypto
 $(OUTPUT)/tcp_inq: LDLIBS += -lpthread
 $(OUTPUT)/bind_bhash: LDLIBS += -lpthread
+$(OUTPUT)/io_uring_zerocopy_tx: CFLAGS += -I../../../include/
 
 # Rules to generate bpf obj nat6to4.o
 CLANG ?= clang
diff --git a/tools/testing/selftests/net/io_uring_zerocopy_tx.c b/tools/testing/selftests/net/io_uring_zerocopy_tx.c
index 154287740172..76e604e4810e 100644
--- a/tools/testing/selftests/net/io_uring_zerocopy_tx.c
+++ b/tools/testing/selftests/net/io_uring_zerocopy_tx.c
@@ -36,6 +36,8 @@
 #include <sys/un.h>
 #include <sys/wait.h>
 
+#include <io_uring/mini_liburing.h>
+
 #define NOTIF_TAG 0xfffffffULL
 #define NONZC_TAG 0
 #define ZC_TAG 1
@@ -60,272 +62,6 @@ static struct sockaddr_storage cfg_dst_addr;
 
 static char payload[IP_MAXPACKET] __attribute__((aligned(4096)));
 
-struct io_sq_ring {
-	unsigned *head;
-	unsigned *tail;
-	unsigned *ring_mask;
-	unsigned *ring_entries;
-	unsigned *flags;
-	unsigned *array;
-};
-
-struct io_cq_ring {
-	unsigned *head;
-	unsigned *tail;
-	unsigned *ring_mask;
-	unsigned *ring_entries;
-	struct io_uring_cqe *cqes;
-};
-
-struct io_uring_sq {
-	unsigned *khead;
-	unsigned *ktail;
-	unsigned *kring_mask;
-	unsigned *kring_entries;
-	unsigned *kflags;
-	unsigned *kdropped;
-	unsigned *array;
-	struct io_uring_sqe *sqes;
-
-	unsigned sqe_head;
-	unsigned sqe_tail;
-
-	size_t ring_sz;
-};
-
-struct io_uring_cq {
-	unsigned *khead;
-	unsigned *ktail;
-	unsigned *kring_mask;
-	unsigned *kring_entries;
-	unsigned *koverflow;
-	struct io_uring_cqe *cqes;
-
-	size_t ring_sz;
-};
-
-struct io_uring {
-	struct io_uring_sq sq;
-	struct io_uring_cq cq;
-	int ring_fd;
-};
-
-#ifdef __alpha__
-# ifndef __NR_io_uring_setup
-#  define __NR_io_uring_setup		535
-# endif
-# ifndef __NR_io_uring_enter
-#  define __NR_io_uring_enter		536
-# endif
-# ifndef __NR_io_uring_register
-#  define __NR_io_uring_register	537
-# endif
-#else /* !__alpha__ */
-# ifndef __NR_io_uring_setup
-#  define __NR_io_uring_setup		425
-# endif
-# ifndef __NR_io_uring_enter
-#  define __NR_io_uring_enter		426
-# endif
-# ifndef __NR_io_uring_register
-#  define __NR_io_uring_register	427
-# endif
-#endif
-
-#if defined(__x86_64) || defined(__i386__)
-#define read_barrier()	__asm__ __volatile__("":::"memory")
-#define write_barrier()	__asm__ __volatile__("":::"memory")
-#else
-
-#define read_barrier()	__sync_synchronize()
-#define write_barrier()	__sync_synchronize()
-#endif
-
-static int io_uring_setup(unsigned int entries, struct io_uring_params *p)
-{
-	return syscall(__NR_io_uring_setup, entries, p);
-}
-
-static int io_uring_enter(int fd, unsigned int to_submit,
-			  unsigned int min_complete,
-			  unsigned int flags, sigset_t *sig)
-{
-	return syscall(__NR_io_uring_enter, fd, to_submit, min_complete,
-			flags, sig, _NSIG / 8);
-}
-
-static int io_uring_register_buffers(struct io_uring *ring,
-				     const struct iovec *iovecs,
-				     unsigned nr_iovecs)
-{
-	int ret;
-
-	ret = syscall(__NR_io_uring_register, ring->ring_fd,
-		      IORING_REGISTER_BUFFERS, iovecs, nr_iovecs);
-	return (ret < 0) ? -errno : ret;
-}
-
-static int io_uring_mmap(int fd, struct io_uring_params *p,
-			 struct io_uring_sq *sq, struct io_uring_cq *cq)
-{
-	size_t size;
-	void *ptr;
-	int ret;
-
-	sq->ring_sz = p->sq_off.array + p->sq_entries * sizeof(unsigned);
-	ptr = mmap(0, sq->ring_sz, PROT_READ | PROT_WRITE,
-		   MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_SQ_RING);
-	if (ptr == MAP_FAILED)
-		return -errno;
-	sq->khead = ptr + p->sq_off.head;
-	sq->ktail = ptr + p->sq_off.tail;
-	sq->kring_mask = ptr + p->sq_off.ring_mask;
-	sq->kring_entries = ptr + p->sq_off.ring_entries;
-	sq->kflags = ptr + p->sq_off.flags;
-	sq->kdropped = ptr + p->sq_off.dropped;
-	sq->array = ptr + p->sq_off.array;
-
-	size = p->sq_entries * sizeof(struct io_uring_sqe);
-	sq->sqes = mmap(0, size, PROT_READ | PROT_WRITE,
-			MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_SQES);
-	if (sq->sqes == MAP_FAILED) {
-		ret = -errno;
-err:
-		munmap(sq->khead, sq->ring_sz);
-		return ret;
-	}
-
-	cq->ring_sz = p->cq_off.cqes + p->cq_entries * sizeof(struct io_uring_cqe);
-	ptr = mmap(0, cq->ring_sz, PROT_READ | PROT_WRITE,
-			MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_CQ_RING);
-	if (ptr == MAP_FAILED) {
-		ret = -errno;
-		munmap(sq->sqes, p->sq_entries * sizeof(struct io_uring_sqe));
-		goto err;
-	}
-	cq->khead = ptr + p->cq_off.head;
-	cq->ktail = ptr + p->cq_off.tail;
-	cq->kring_mask = ptr + p->cq_off.ring_mask;
-	cq->kring_entries = ptr + p->cq_off.ring_entries;
-	cq->koverflow = ptr + p->cq_off.overflow;
-	cq->cqes = ptr + p->cq_off.cqes;
-	return 0;
-}
-
-static int io_uring_queue_init(unsigned entries, struct io_uring *ring,
-			       unsigned flags)
-{
-	struct io_uring_params p;
-	int fd, ret;
-
-	memset(ring, 0, sizeof(*ring));
-	memset(&p, 0, sizeof(p));
-	p.flags = flags;
-
-	fd = io_uring_setup(entries, &p);
-	if (fd < 0)
-		return fd;
-	ret = io_uring_mmap(fd, &p, &ring->sq, &ring->cq);
-	if (!ret)
-		ring->ring_fd = fd;
-	else
-		close(fd);
-	return ret;
-}
-
-static int io_uring_submit(struct io_uring *ring)
-{
-	struct io_uring_sq *sq = &ring->sq;
-	const unsigned mask = *sq->kring_mask;
-	unsigned ktail, submitted, to_submit;
-	int ret;
-
-	read_barrier();
-	if (*sq->khead != *sq->ktail) {
-		submitted = *sq->kring_entries;
-		goto submit;
-	}
-	if (sq->sqe_head == sq->sqe_tail)
-		return 0;
-
-	ktail = *sq->ktail;
-	to_submit = sq->sqe_tail - sq->sqe_head;
-	for (submitted = 0; submitted < to_submit; submitted++) {
-		read_barrier();
-		sq->array[ktail++ & mask] = sq->sqe_head++ & mask;
-	}
-	if (!submitted)
-		return 0;
-
-	if (*sq->ktail != ktail) {
-		write_barrier();
-		*sq->ktail = ktail;
-		write_barrier();
-	}
-submit:
-	ret = io_uring_enter(ring->ring_fd, submitted, 0,
-				IORING_ENTER_GETEVENTS, NULL);
-	return ret < 0 ? -errno : ret;
-}
-
-static inline void io_uring_prep_send(struct io_uring_sqe *sqe, int sockfd,
-				      const void *buf, size_t len, int flags)
-{
-	memset(sqe, 0, sizeof(*sqe));
-	sqe->opcode = (__u8) IORING_OP_SEND;
-	sqe->fd = sockfd;
-	sqe->addr = (unsigned long) buf;
-	sqe->len = len;
-	sqe->msg_flags = (__u32) flags;
-}
-
-static inline void io_uring_prep_sendzc(struct io_uring_sqe *sqe, int sockfd,
-				        const void *buf, size_t len, int flags,
-				        unsigned zc_flags)
-{
-	io_uring_prep_send(sqe, sockfd, buf, len, flags);
-	sqe->opcode = (__u8) IORING_OP_SEND_ZC;
-	sqe->ioprio = zc_flags;
-}
-
-static struct io_uring_sqe *io_uring_get_sqe(struct io_uring *ring)
-{
-	struct io_uring_sq *sq = &ring->sq;
-
-	if (sq->sqe_tail + 1 - sq->sqe_head > *sq->kring_entries)
-		return NULL;
-	return &sq->sqes[sq->sqe_tail++ & *sq->kring_mask];
-}
-
-static int io_uring_wait_cqe(struct io_uring *ring, struct io_uring_cqe **cqe_ptr)
-{
-	struct io_uring_cq *cq = &ring->cq;
-	const unsigned mask = *cq->kring_mask;
-	unsigned head = *cq->khead;
-	int ret;
-
-	*cqe_ptr = NULL;
-	do {
-		read_barrier();
-		if (head != *cq->ktail) {
-			*cqe_ptr = &cq->cqes[head & mask];
-			break;
-		}
-		ret = io_uring_enter(ring->ring_fd, 0, 1,
-					IORING_ENTER_GETEVENTS, NULL);
-		if (ret < 0)
-			return -errno;
-	} while (1);
-
-	return 0;
-}
-
-static inline void io_uring_cqe_seen(struct io_uring *ring)
-{
-	*(&ring->cq)->khead += 1;
-	write_barrier();
-}
-
 static unsigned long gettimeofday_ms(void)
 {
 	struct timeval tv;
-- 
2.34.1

[PATCH v3 9/9] selftests/bpf/sockopt: Add io_uring support

[Breno Leitao]

Expand the sockopt test to use also check for io_uring {g,s}etsockopt
commands operations.

This patch starts by marking marks each test if they support io_uring
support or not. Right now, io_uring cmd getsockopt() has a limitation of
only accepting level == SOL_SOCKET, otherwise it returns -EOPNOTSUPP.

Later, each test runs using regular {g,s}etsockopt systemcalls, and, if
liburing is supported, execute the same test (again), but calling
liburing {g,s}setsockopt commands.

For that, leverage the mini liburing to do basic io_uring operations.

Signed-off-by: Breno Leitao <leitao@debian.org>
---
 tools/testing/selftests/bpf/Makefile          |   1 +
 .../selftests/bpf/prog_tests/sockopt.c        | 129 +++++++++++++++++-
 2 files changed, 124 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 538df8fb8c42..4da04242b848 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -362,6 +362,7 @@ CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \
 
 $(OUTPUT)/test_l4lb_noinline.o: BPF_CFLAGS += -fno-inline
 $(OUTPUT)/test_xdp_noinline.o: BPF_CFLAGS += -fno-inline
+$(OUTPUT)/test_progs.o: CFLAGS += -I../../../include/
 
 $(OUTPUT)/flow_dissector_load.o: flow_dissector_load.h
 $(OUTPUT)/cgroup_getset_retval_hooks.o: cgroup_getset_retval_hooks.h
diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt.c b/tools/testing/selftests/bpf/prog_tests/sockopt.c
index 9e6a5e3ed4de..4693ad8bfe8f 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <io_uring/mini_liburing.h>
 #include "cgroup_helpers.h"
 
 static char bpf_log_buf[4096];
@@ -38,6 +39,7 @@ static struct sockopt_test {
 	socklen_t			get_optlen_ret;
 
 	enum sockopt_test_error		error;
+	bool				io_uring_support;
 } tests[] = {
 
 	/* ==================== getsockopt ====================  */
@@ -53,6 +55,7 @@ static struct sockopt_test {
 		.attach_type = BPF_CGROUP_GETSOCKOPT,
 		.expected_attach_type = 0,
 		.error = DENY_LOAD,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "getsockopt: wrong expected_attach_type",
@@ -65,6 +68,7 @@ static struct sockopt_test {
 		.attach_type = BPF_CGROUP_GETSOCKOPT,
 		.expected_attach_type = BPF_CGROUP_SETSOCKOPT,
 		.error = DENY_ATTACH,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "getsockopt: bypass bpf hook",
@@ -121,6 +125,7 @@ static struct sockopt_test {
 		.attach_type = BPF_CGROUP_GETSOCKOPT,
 		.expected_attach_type = BPF_CGROUP_GETSOCKOPT,
 		.error = DENY_LOAD,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "getsockopt: read ctx->level",
@@ -164,6 +169,7 @@ static struct sockopt_test {
 		.expected_attach_type = BPF_CGROUP_GETSOCKOPT,
 
 		.error = DENY_LOAD,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "getsockopt: read ctx->optname",
@@ -225,6 +231,7 @@ static struct sockopt_test {
 		.expected_attach_type = BPF_CGROUP_GETSOCKOPT,
 
 		.error = DENY_LOAD,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "getsockopt: read ctx->optlen",
@@ -252,6 +259,7 @@ static struct sockopt_test {
 		.expected_attach_type = BPF_CGROUP_GETSOCKOPT,
 
 		.get_optlen = 64,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "getsockopt: deny bigger ctx->optlen",
@@ -276,6 +284,7 @@ static struct sockopt_test {
 		.get_optlen = 64,
 
 		.error = EFAULT_GETSOCKOPT,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "getsockopt: ignore >PAGE_SIZE optlen",
@@ -318,6 +327,7 @@ static struct sockopt_test {
 		.get_optval = {}, /* the changes are ignored */
 		.get_optlen = PAGE_SIZE + 1,
 		.error = EOPNOTSUPP_GETSOCKOPT,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "getsockopt: support smaller ctx->optlen",
@@ -339,6 +349,7 @@ static struct sockopt_test {
 
 		.get_optlen = 64,
 		.get_optlen_ret = 32,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "getsockopt: deny writing to ctx->optval",
@@ -353,6 +364,7 @@ static struct sockopt_test {
 		.expected_attach_type = BPF_CGROUP_GETSOCKOPT,
 
 		.error = DENY_LOAD,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "getsockopt: deny writing to ctx->optval_end",
@@ -367,6 +379,7 @@ static struct sockopt_test {
 		.expected_attach_type = BPF_CGROUP_GETSOCKOPT,
 
 		.error = DENY_LOAD,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "getsockopt: rewrite value",
@@ -421,6 +434,7 @@ static struct sockopt_test {
 		.attach_type = BPF_CGROUP_SETSOCKOPT,
 		.expected_attach_type = 0,
 		.error = DENY_LOAD,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: wrong expected_attach_type",
@@ -433,6 +447,7 @@ static struct sockopt_test {
 		.attach_type = BPF_CGROUP_SETSOCKOPT,
 		.expected_attach_type = BPF_CGROUP_GETSOCKOPT,
 		.error = DENY_ATTACH,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: bypass bpf hook",
@@ -518,6 +533,7 @@ static struct sockopt_test {
 		.set_level = 123,
 
 		.set_optlen = 1,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: allow changing ctx->level",
@@ -572,6 +588,7 @@ static struct sockopt_test {
 		.set_optname = 123,
 
 		.set_optlen = 1,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: allow changing ctx->optname",
@@ -624,6 +641,7 @@ static struct sockopt_test {
 		.expected_attach_type = BPF_CGROUP_SETSOCKOPT,
 
 		.set_optlen = 64,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: ctx->optlen == -1 is ok",
@@ -640,6 +658,7 @@ static struct sockopt_test {
 		.expected_attach_type = BPF_CGROUP_SETSOCKOPT,
 
 		.set_optlen = 64,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: deny ctx->optlen < 0 (except -1)",
@@ -658,6 +677,7 @@ static struct sockopt_test {
 		.set_optlen = 4,
 
 		.error = EFAULT_SETSOCKOPT,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: deny ctx->optlen > input optlen",
@@ -675,6 +695,7 @@ static struct sockopt_test {
 		.set_optlen = 64,
 
 		.error = EFAULT_SETSOCKOPT,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: ignore >PAGE_SIZE optlen",
@@ -775,6 +796,7 @@ static struct sockopt_test {
 		.expected_attach_type = BPF_CGROUP_SETSOCKOPT,
 
 		.error = DENY_LOAD,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: deny read ctx->retval",
@@ -791,6 +813,7 @@ static struct sockopt_test {
 		.expected_attach_type = BPF_CGROUP_SETSOCKOPT,
 
 		.error = DENY_LOAD,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: deny writing to ctx->optval",
@@ -805,6 +828,7 @@ static struct sockopt_test {
 		.expected_attach_type = BPF_CGROUP_SETSOCKOPT,
 
 		.error = DENY_LOAD,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: deny writing to ctx->optval_end",
@@ -819,6 +843,7 @@ static struct sockopt_test {
 		.expected_attach_type = BPF_CGROUP_SETSOCKOPT,
 
 		.error = DENY_LOAD,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: allow IP_TOS <= 128",
@@ -940,7 +965,94 @@ static int load_prog(const struct bpf_insn *insns,
 	return fd;
 }
 
-static int run_test(int cgroup_fd, struct sockopt_test *test)
+/* Core function that handles io_uring ring initialization,
+ * sending SQE with sockopt command and waiting for the CQE.
+ */
+static int uring_sockopt(int op, int fd, int level, int optname,
+			 const void *optval, socklen_t optlen)
+{
+	struct io_uring_cqe *cqe;
+	struct io_uring_sqe *sqe;
+	struct io_uring ring;
+	int err;
+
+	err = io_uring_queue_init(1, &ring, 0);
+	if (err) {
+		log_err("Failed to initialize io_uring ring");
+		return err;
+	}
+
+	sqe = io_uring_get_sqe(&ring);
+	if (!sqe) {
+		log_err("Failed to get an SQE");
+		return -1;
+	}
+
+	io_uring_prep_cmd(sqe, op, fd, level, optname, optval, optlen);
+
+	err = io_uring_submit(&ring);
+	if (err != 1) {
+		log_err("Failed to submit SQE");
+		return err;
+	}
+
+	err = io_uring_wait_cqe(&ring, &cqe);
+	if (err) {
+		log_err("Failed to wait for CQE");
+		return err;
+	}
+
+	err = cqe->res;
+
+	io_uring_queue_exit(&ring);
+
+	return err;
+}
+
+static int uring_setsockopt(int fd, int level, int optname, const void *optval,
+			    socklen_t optlen)
+{
+	return uring_sockopt(SOCKET_URING_OP_SETSOCKOPT, fd, level, optname,
+			     optval, optlen);
+}
+
+static int uring_getsockopt(int fd, int level, int optname, void *optval,
+			    socklen_t *optlen)
+{
+	int ret = uring_sockopt(SOCKET_URING_OP_GETSOCKOPT, fd, level, optname,
+				optval, *optlen);
+	if (ret < 0)
+		return ret;
+
+	/* Populate optlen back to be compatible with systemcall interface,
+	 * and simplify the test.
+	 */
+	*optlen = ret;
+
+	return 0;
+}
+
+/* Execute the setsocktopt operation */
+static int call_setsockopt(bool use_io_uring, int fd, int level, int optname,
+			   const void *optval, socklen_t optlen)
+{
+	if (use_io_uring)
+		return uring_setsockopt(fd, level, optname, optval, optlen);
+
+	return setsockopt(fd, level, optname, optval, optlen);
+}
+
+/* Execute the getsocktopt operation */
+static int call_getsockopt(bool use_io_uring, int fd, int level, int optname,
+			   void *optval, socklen_t *optlen)
+{
+	if (use_io_uring)
+		return uring_getsockopt(fd, level, optname, optval, optlen);
+
+	return getsockopt(fd, level, optname, optval, optlen);
+}
+
+static int run_test(int cgroup_fd, struct sockopt_test *test, bool use_io_uring)
 {
 	int sock_fd, err, prog_fd;
 	void *optval = NULL;
@@ -980,8 +1092,9 @@ static int run_test(int cgroup_fd, struct sockopt_test *test)
 			test->set_optlen = num_pages * sysconf(_SC_PAGESIZE) + remainder;
 		}
 
-		err = setsockopt(sock_fd, test->set_level, test->set_optname,
-				 test->set_optval, test->set_optlen);
+		err = call_setsockopt(use_io_uring, sock_fd, test->set_level,
+				      test->set_optname, test->set_optval,
+				      test->set_optlen);
 		if (err) {
 			if (errno == EPERM && test->error == EPERM_SETSOCKOPT)
 				goto close_sock_fd;
@@ -1008,8 +1121,8 @@ static int run_test(int cgroup_fd, struct sockopt_test *test)
 		socklen_t expected_get_optlen = test->get_optlen_ret ?:
 			test->get_optlen;
 
-		err = getsockopt(sock_fd, test->get_level, test->get_optname,
-				 optval, &optlen);
+		err = call_getsockopt(use_io_uring, sock_fd, test->get_level,
+				      test->get_optname, optval, &optlen);
 		if (err) {
 			if (errno == EOPNOTSUPP && test->error == EOPNOTSUPP_GETSOCKOPT)
 				goto free_optval;
@@ -1063,7 +1176,11 @@ void test_sockopt(void)
 		if (!test__start_subtest(tests[i].descr))
 			continue;
 
-		ASSERT_OK(run_test(cgroup_fd, &tests[i]), tests[i].descr);
+		ASSERT_OK(run_test(cgroup_fd, &tests[i], false),
+			  tests[i].descr);
+		if (tests[i].io_uring_support)
+			ASSERT_OK(run_test(cgroup_fd, &tests[i], true),
+				  tests[i].descr);
 	}
 
 	close(cgroup_fd);
-- 
2.34.1

Re: [PATCH v3 9/9] selftests/bpf/sockopt: Add io_uring support

[Martin KaFai Lau]

On 8/17/23 7:55 AM, Breno Leitao wrote:
> diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
> index 538df8fb8c42..4da04242b848 100644
> --- a/tools/testing/selftests/bpf/Makefile
> +++ b/tools/testing/selftests/bpf/Makefile
> @@ -362,6 +362,7 @@ CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \
>   
>   $(OUTPUT)/test_l4lb_noinline.o: BPF_CFLAGS += -fno-inline
>   $(OUTPUT)/test_xdp_noinline.o: BPF_CFLAGS += -fno-inline
> +$(OUTPUT)/test_progs.o: CFLAGS += -I../../../include/

This is the tools/include? Is it really needed? iirc, some of the prog_tests/*.c 
has already been using files from tools/include.

>   
>   $(OUTPUT)/flow_dissector_load.o: flow_dissector_load.h
>   $(OUTPUT)/cgroup_getset_retval_hooks.o: cgroup_getset_retval_hooks.h
> diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt.c b/tools/testing/selftests/bpf/prog_tests/sockopt.c
> index 9e6a5e3ed4de..4693ad8bfe8f 100644
> --- a/tools/testing/selftests/bpf/prog_tests/sockopt.c
> +++ b/tools/testing/selftests/bpf/prog_tests/sockopt.c
> @@ -1,5 +1,6 @@
>   // SPDX-License-Identifier: GPL-2.0
>   #include <test_progs.h>
> +#include <io_uring/mini_liburing.h>
>   #include "cgroup_helpers.h"
>   
>   static char bpf_log_buf[4096];
> @@ -38,6 +39,7 @@ static struct sockopt_test {
>   	socklen_t			get_optlen_ret;
>   
>   	enum sockopt_test_error		error;
> +	bool				io_uring_support;
>   } tests[] = {
>   
>   	/* ==================== getsockopt ====================  */
> @@ -53,6 +55,7 @@ static struct sockopt_test {
>   		.attach_type = BPF_CGROUP_GETSOCKOPT,
>   		.expected_attach_type = 0,
>   		.error = DENY_LOAD,
> +		.io_uring_support = true,

DENY_LOAD probably won't be an intersting test. The set/getsockopt won't be called.

The existing test does not seem to have SOL_SOCKET for getsockopt also.

> -static int run_test(int cgroup_fd, struct sockopt_test *test)
> +/* Core function that handles io_uring ring initialization,
> + * sending SQE with sockopt command and waiting for the CQE.
> + */
> +static int uring_sockopt(int op, int fd, int level, int optname,
> +			 const void *optval, socklen_t optlen)
> +{
> +	struct io_uring_cqe *cqe;
> +	struct io_uring_sqe *sqe;
> +	struct io_uring ring;
> +	int err;
> +
> +	err = io_uring_queue_init(1, &ring, 0);
> +	if (err) {
> +		log_err("Failed to initialize io_uring ring");
> +		return err;
> +	}
> +
> +	sqe = io_uring_get_sqe(&ring);
> +	if (!sqe) {
> +		log_err("Failed to get an SQE");
> +		return -1;

No need to io_uring_queue_exit() on the error path?


> +	}
> +
> +	io_uring_prep_cmd(sqe, op, fd, level, optname, optval, optlen);
> +
> +	err = io_uring_submit(&ring);
> +	if (err != 1) {
> +		log_err("Failed to submit SQE");

Use ASSERT_* instead.

Regarding how to land this set,
it will be useful to have the selftest running in the bpf CI. While there is 
iouring changes, some of the changes is in bpf and/or netdev also. eg. Patch 3 
already has a conflict with the net-next and bpf-next tree because of a recent 
commit in socket.c on Aug 9.

May be Alexi and Daniel can advise how was similar patch managed before ?

Re: [PATCH v3 9/9] selftests/bpf/sockopt: Add io_uring support

[Breno Leitao]

On Mon, Aug 21, 2023 at 01:59:12PM -0700, Martin KaFai Lau wrote:
> On 8/17/23 7:55 AM, Breno Leitao wrote:
> > diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
> > index 538df8fb8c42..4da04242b848 100644
> > --- a/tools/testing/selftests/bpf/Makefile
> > +++ b/tools/testing/selftests/bpf/Makefile
> > @@ -362,6 +362,7 @@ CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \
> >   $(OUTPUT)/test_l4lb_noinline.o: BPF_CFLAGS += -fno-inline
> >   $(OUTPUT)/test_xdp_noinline.o: BPF_CFLAGS += -fno-inline
> > +$(OUTPUT)/test_progs.o: CFLAGS += -I../../../include/
> 
> This is the tools/include? Is it really needed? iirc, some of the
> prog_tests/*.c has already been using files from tools/include.

You are right, we don't need it.

> >   $(OUTPUT)/flow_dissector_load.o: flow_dissector_load.h
> >   $(OUTPUT)/cgroup_getset_retval_hooks.o: cgroup_getset_retval_hooks.h
> > diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt.c b/tools/testing/selftests/bpf/prog_tests/sockopt.c
> > index 9e6a5e3ed4de..4693ad8bfe8f 100644
> > --- a/tools/testing/selftests/bpf/prog_tests/sockopt.c
> > +++ b/tools/testing/selftests/bpf/prog_tests/sockopt.c
> > @@ -1,5 +1,6 @@
> >   // SPDX-License-Identifier: GPL-2.0
> >   #include <test_progs.h>
> > +#include <io_uring/mini_liburing.h>
> >   #include "cgroup_helpers.h"
> >   static char bpf_log_buf[4096];
> > @@ -38,6 +39,7 @@ static struct sockopt_test {
> >   	socklen_t			get_optlen_ret;
> >   	enum sockopt_test_error		error;
> > +	bool				io_uring_support;
> >   } tests[] = {
> >   	/* ==================== getsockopt ====================  */
> > @@ -53,6 +55,7 @@ static struct sockopt_test {
> >   		.attach_type = BPF_CGROUP_GETSOCKOPT,
> >   		.expected_attach_type = 0,
> >   		.error = DENY_LOAD,
> > +		.io_uring_support = true,
> 
> DENY_LOAD probably won't be an intersting test. The set/getsockopt won't be called.

Yea, I will remove all the DENY_LOAD and DENY_ATTACH tests.

> The existing test does not seem to have SOL_SOCKET for getsockopt also.

I am planning to move two tests to use SOL_SOCKET so we can also
exercise the io_uring tests. This is what I have in mind right now:

 * getsockopt: read ctx->optlen
 * getsockopt: support smaller ctx->optlen

> > -static int run_test(int cgroup_fd, struct sockopt_test *test)
> > +/* Core function that handles io_uring ring initialization,
> > + * sending SQE with sockopt command and waiting for the CQE.
> > + */
> > +static int uring_sockopt(int op, int fd, int level, int optname,
> > +			 const void *optval, socklen_t optlen)
> > +{
> > +	struct io_uring_cqe *cqe;
> > +	struct io_uring_sqe *sqe;
> > +	struct io_uring ring;
> > +	int err;
> > +
> > +	err = io_uring_queue_init(1, &ring, 0);
> > +	if (err) {
> > +		log_err("Failed to initialize io_uring ring");
> > +		return err;
> > +	}
> > +
> > +	sqe = io_uring_get_sqe(&ring);
> > +	if (!sqe) {
> > +		log_err("Failed to get an SQE");
> > +		return -1;
> 
> No need to io_uring_queue_exit() on the error path?

Good idea. updating it.

> > +	}
> > +
> > +	io_uring_prep_cmd(sqe, op, fd, level, optname, optval, optlen);
> > +
> > +	err = io_uring_submit(&ring);
> > +	if (err != 1) {
> > +		log_err("Failed to submit SQE");
> 
> Use ASSERT_* instead.
> 
> Regarding how to land this set,
> it will be useful to have the selftest running in the bpf CI. While there is
> iouring changes, some of the changes is in bpf and/or netdev also. eg. Patch
> 3 already has a conflict with the net-next and bpf-next tree because of a
> recent commit in socket.c on Aug 9.
> 
> May be Alexi and Daniel can advise how was similar patch managed before ?
> 
>