um: drivers: Add virtio vhost-user driver

This module allows virtio devices to be used over a vhost-user socket.

Signed-off-by: Erel Geron <erelx.geron@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Richard Weinberger <richard@nod.at>

arch/um/drivers/Kconfig

@@ -335,3 +335,10 @@ config UML_NET_SLIRP
 	  Startup example: "eth0=slirp,FE:FD:01:02:03:04,/usr/local/bin/slirp"
 
 endmenu
+
+config VIRTIO_UML
+	tristate "UML driver for virtio devices"
+	select VIRTIO
+	help
+	  This driver provides support for virtio based paravirtual device
+	  drivers over vhost-user sockets.

arch/um/drivers/Makefile

@@ -61,6 +61,7 @@ obj-$(CONFIG_XTERM_CHAN) += xterm.o xterm_kern.o
 obj-$(CONFIG_UML_WATCHDOG) += harddog.o
 obj-$(CONFIG_BLK_DEV_COW_COMMON) += cow_user.o
 obj-$(CONFIG_UML_RANDOM) += random.o
+obj-$(CONFIG_VIRTIO_UML) += virtio_uml.o
 
 # pcap_user.o must be added explicitly.
 USER_OBJS := fd.o null.o pty.o tty.o xterm.o slip_common.o pcap_user.o vde_user.o vector_user.o

arch/um/drivers/vhost_user.h

@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Vhost-user protocol */
+
+#ifndef __VHOST_USER_H__
+#define __VHOST_USER_H__
+
+/* Message flags */
+#define VHOST_USER_FLAG_REPLY		BIT(2)
+/* Feature bits */
+#define VHOST_USER_F_PROTOCOL_FEATURES	30
+/* Protocol feature bits */
+#define VHOST_USER_PROTOCOL_F_CONFIG	9
+/* Vring state index masks */
+#define VHOST_USER_VRING_INDEX_MASK	0xff
+#define VHOST_USER_VRING_POLL_MASK	BIT(8)
+
+/* Supported version */
+#define VHOST_USER_VERSION		1
+/* Supported transport features */
+#define VHOST_USER_SUPPORTED_F		BIT_ULL(VHOST_USER_F_PROTOCOL_FEATURES)
+/* Supported protocol features */
+#define VHOST_USER_SUPPORTED_PROTOCOL_F	BIT_ULL(VHOST_USER_PROTOCOL_F_CONFIG)
+
+enum vhost_user_request {
+	VHOST_USER_GET_FEATURES = 1,
+	VHOST_USER_SET_FEATURES = 2,
+	VHOST_USER_SET_OWNER = 3,
+	VHOST_USER_RESET_OWNER = 4,
+	VHOST_USER_SET_MEM_TABLE = 5,
+	VHOST_USER_SET_LOG_BASE = 6,
+	VHOST_USER_SET_LOG_FD = 7,
+	VHOST_USER_SET_VRING_NUM = 8,
+	VHOST_USER_SET_VRING_ADDR = 9,
+	VHOST_USER_SET_VRING_BASE = 10,
+	VHOST_USER_GET_VRING_BASE = 11,
+	VHOST_USER_SET_VRING_KICK = 12,
+	VHOST_USER_SET_VRING_CALL = 13,
+	VHOST_USER_SET_VRING_ERR = 14,
+	VHOST_USER_GET_PROTOCOL_FEATURES = 15,
+	VHOST_USER_SET_PROTOCOL_FEATURES = 16,
+	VHOST_USER_GET_QUEUE_NUM = 17,
+	VHOST_USER_SET_VRING_ENABLE = 18,
+	VHOST_USER_SEND_RARP = 19,
+	VHOST_USER_NET_SEND_MTU = 20,
+	VHOST_USER_SET_SLAVE_REQ_FD = 21,
+	VHOST_USER_IOTLB_MSG = 22,
+	VHOST_USER_SET_VRING_ENDIAN = 23,
+	VHOST_USER_GET_CONFIG = 24,
+	VHOST_USER_SET_CONFIG = 25,
+};
+
+struct vhost_user_header {
+	u32 request; /* Use enum vhost_user_request */
+	u32 flags;
+	u32 size;
+} __packed;
+
+struct vhost_user_config {
+	u32 offset;
+	u32 size;
+	u32 flags;
+	u8 payload[0]; /* Variable length */
+} __packed;
+
+struct vhost_user_vring_state {
+	u32 index;
+	u32 num;
+} __packed;
+
+struct vhost_user_vring_addr {
+	u32 index;
+	u32 flags;
+	u64 desc, used, avail, log;
+} __packed;
+
+struct vhost_user_mem_region {
+	u64 guest_addr;
+	u64 size;
+	u64 user_addr;
+	u64 mmap_offset;
+} __packed;
+
+struct vhost_user_mem_regions {
+	u32 num;
+	u32 padding;
+	struct vhost_user_mem_region regions[2]; /* Currently supporting 2 */
+} __packed;
+
+union vhost_user_payload {
+	u64 integer;
+	struct vhost_user_config config;
+	struct vhost_user_vring_state vring_state;
+	struct vhost_user_vring_addr vring_addr;
+	struct vhost_user_mem_regions mem_regions;
+};
+
+struct vhost_user_msg {
+	struct vhost_user_header header;
+	union vhost_user_payload payload;
+} __packed;
+
+#endif

arch/um/include/asm/irq.h

@@ -17,17 +17,18 @@
 #define TELNETD_IRQ 		12
 #define XTERM_IRQ 		13
 #define RANDOM_IRQ 		14
+#define VIRTIO_IRQ		15
 
 #ifdef CONFIG_UML_NET_VECTOR
 
-#define VECTOR_BASE_IRQ		15
+#define VECTOR_BASE_IRQ		(VIRTIO_IRQ + 1)
 #define VECTOR_IRQ_SPACE	8
 
 #define LAST_IRQ (VECTOR_IRQ_SPACE + VECTOR_BASE_IRQ - 1)
 
 #else
 
-#define LAST_IRQ RANDOM_IRQ
+#define LAST_IRQ VIRTIO_IRQ
 
 #endif
 

arch/um/include/shared/os.h

@@ -36,6 +36,8 @@
 #define OS_LIB_PATH	"/usr/lib/"
 #endif
 
+#define OS_SENDMSG_MAX_FDS 8
+
 /*
  * types taken from stat_file() in hostfs_user.c
  * (if they are wrong here, they are wrong there...).
@@ -176,6 +178,9 @@ extern unsigned os_major(unsigned long long dev);
 extern unsigned os_minor(unsigned long long dev);
 extern unsigned long long os_makedev(unsigned major, unsigned minor);
 extern int os_falloc_punch(int fd, unsigned long long offset, int count);
+extern int os_eventfd(unsigned int initval, int flags);
+extern int os_sendmsg_fds(int fd, const void *buf, unsigned int len,
+			  const int *fds, unsigned int fds_num);
 
 /* start_up.c */
 extern void os_early_checks(void);

arch/um/kernel/ksyms.c

@@ -38,6 +38,8 @@ EXPORT_SYMBOL(run_helper);
 EXPORT_SYMBOL(os_major);
 EXPORT_SYMBOL(os_minor);
 EXPORT_SYMBOL(os_makedev);
+EXPORT_SYMBOL(os_eventfd);
+EXPORT_SYMBOL(os_sendmsg_fds);
 
 EXPORT_SYMBOL(add_sigio_fd);
 EXPORT_SYMBOL(ignore_sigio_fd);

arch/um/kernel/mem.c

@@ -31,6 +31,7 @@ pgd_t swapper_pg_dir[PTRS_PER_PGD];
 
 /* Initialized at boot time, and readonly after that */
 unsigned long long highmem;
+EXPORT_SYMBOL(highmem);
 int kmalloc_ok = 0;
 
 /* Used during early boot */

arch/um/kernel/physmem.c

@@ -143,6 +143,7 @@ int phys_mapping(unsigned long phys, unsigned long long *offset_out)
 
 	return fd;
 }
+EXPORT_SYMBOL(phys_mapping);
 
 static int __init uml_mem_setup(char *line, int *add)
 {

arch/um/kernel/um_arch.c

@@ -113,6 +113,7 @@ static int have_root __initdata = 0;
 
 /* Set in uml_mem_setup and modified in linux_main */
 long long physmem_size = 32 * 1024 * 1024;
+EXPORT_SYMBOL(physmem_size);
 
 static const char *usage_string =
 "User Mode Linux v%s\n"

arch/um/os-Linux/file.c

@@ -15,6 +15,7 @@
 #include <sys/sysmacros.h>
 #include <sys/un.h>
 #include <sys/types.h>
+#include <sys/eventfd.h>
 #include <os.h>
 
 static void copy_stat(struct uml_stat *dst, const struct stat64 *src)
@@ -620,3 +621,46 @@ int os_falloc_punch(int fd, unsigned long long offset, int len)
 	return n;
 }
 
+int os_eventfd(unsigned int initval, int flags)
+{
+	int fd = eventfd(initval, flags);
+
+	if (fd < 0)
+		return -errno;
+	return fd;
+}
+
+int os_sendmsg_fds(int fd, const void *buf, unsigned int len, const int *fds,
+		   unsigned int fds_num)
+{
+	struct iovec iov = {
+		.iov_base = (void *) buf,
+		.iov_len = len,
+	};
+	union {
+		char control[CMSG_SPACE(sizeof(*fds) * OS_SENDMSG_MAX_FDS)];
+		struct cmsghdr align;
+	} u;
+	unsigned int fds_size = sizeof(*fds) * fds_num;
+	struct msghdr msg = {
+		.msg_iov = &iov,
+		.msg_iovlen = 1,
+		.msg_control = u.control,
+		.msg_controllen = CMSG_SPACE(fds_size),
+	};
+	struct cmsghdr *cmsg = CMSG_FIRSTHDR(&msg);
+	int err;
+
+	if (fds_num > OS_SENDMSG_MAX_FDS)
+		return -EINVAL;
+	memset(u.control, 0, sizeof(u.control));
+	cmsg->cmsg_level = SOL_SOCKET;
+	cmsg->cmsg_type = SCM_RIGHTS;
+	cmsg->cmsg_len = CMSG_LEN(fds_size);
+	memcpy(CMSG_DATA(cmsg), fds, fds_size);
+	err = sendmsg(fd, &msg, 0);
+
+	if (err < 0)
+		return -errno;
+	return err;
+}