Merge tag 'for-6.7/io_uring-sockopt-2023-10-30' of git://git.kernel.dk/linux

Pull io_uring {get,set}sockopt support from Jens Axboe:
 "This adds support for using getsockopt and setsockopt via io_uring.

  The main use cases for this is to enable use of direct descriptors,
  rather than first instantiating a normal file descriptor, doing the
  option tweaking needed, then turning it into a direct descriptor. With
  this support, we can avoid needing a regular file descriptor
  completely.

  The net and bpf bits have been signed off on their side"

* tag 'for-6.7/io_uring-sockopt-2023-10-30' of git://git.kernel.dk/linux:
  selftests/bpf/sockopt: Add io_uring support
  io_uring/cmd: Introduce SOCKET_URING_OP_SETSOCKOPT
  io_uring/cmd: Introduce SOCKET_URING_OP_GETSOCKOPT
  io_uring/cmd: return -EOPNOTSUPP if net is disabled
  selftests/net: Extract uring helpers to be reusable
  tools headers: Grab copy of io_uring.h
  io_uring/cmd: Pass compat mode in issue_flags
  net/socket: Break down __sys_getsockopt
  net/socket: Break down __sys_setsockopt
  bpf: Add sockptr support for setsockopt
  bpf: Add sockptr support for getsockopt

3 files changed, 110 insertions, 272 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt.c b/tools/testing/selftests/bpf/prog_tests/sockopt.c
index 9e6a5e3ed4de..5a4491d4edfe 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 ====================  */
@@ -251,7 +253,9 @@ static struct sockopt_test {
 		.attach_type = BPF_CGROUP_GETSOCKOPT,
 		.expected_attach_type = BPF_CGROUP_GETSOCKOPT,
 
+		.get_level = SOL_SOCKET,
 		.get_optlen = 64,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "getsockopt: deny bigger ctx->optlen",
@@ -276,6 +280,7 @@ static struct sockopt_test {
 		.get_optlen = 64,
 
 		.error = EFAULT_GETSOCKOPT,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "getsockopt: ignore >PAGE_SIZE optlen",
@@ -318,6 +323,7 @@ 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",
@@ -337,8 +343,10 @@ static struct sockopt_test {
 		.attach_type = BPF_CGROUP_GETSOCKOPT,
 		.expected_attach_type = BPF_CGROUP_GETSOCKOPT,
 
+		.get_level = SOL_SOCKET,
 		.get_optlen = 64,
 		.get_optlen_ret = 32,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "getsockopt: deny writing to ctx->optval",
@@ -518,6 +526,7 @@ static struct sockopt_test {
 		.set_level = 123,
 
 		.set_optlen = 1,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: allow changing ctx->level",
@@ -572,6 +581,7 @@ static struct sockopt_test {
 		.set_optname = 123,
 
 		.set_optlen = 1,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: allow changing ctx->optname",
@@ -624,6 +634,7 @@ 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 +651,7 @@ 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 +670,7 @@ static struct sockopt_test {
 		.set_optlen = 4,
 
 		.error = EFAULT_SETSOCKOPT,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: deny ctx->optlen > input optlen",
@@ -675,6 +688,7 @@ static struct sockopt_test {
 		.set_optlen = 64,
 
 		.error = EFAULT_SETSOCKOPT,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: ignore >PAGE_SIZE optlen",
@@ -940,7 +954,89 @@ 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 (!ASSERT_OK(err, "io_uring initialization"))
+		return err;
+
+	sqe = io_uring_get_sqe(&ring);
+	if (!ASSERT_NEQ(sqe, NULL, "Get an SQE")) {
+		err = -1;
+		goto fail;
+	}
+
+	io_uring_prep_cmd(sqe, op, fd, level, optname, optval, optlen);
+
+	err = io_uring_submit(&ring);
+	if (!ASSERT_EQ(err, 1, "Submit SQE"))
+		goto fail;
+
+	err = io_uring_wait_cqe(&ring, &cqe);
+	if (!ASSERT_OK(err, "Wait for CQE"))
+		goto fail;
+
+	err = cqe->res;
+
+fail:
+	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 +1076,9 @@ 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 +1105,8 @@ 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 +1160,11 @@ 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);
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index b9804ceb9494..5b2aca4c5f10 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -100,6 +100,7 @@ $(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;