vhost-user: add VHOST_USER_SET_LOG_BASE command

Sets logging shared memory space.

When the back-end has VHOST_USER_PROTOCOL_F_LOG_SHMFD protocol feature,
the log memory fd is provided in the ancillary data of
VHOST_USER_SET_LOG_BASE message, the size and offset of shared memory
area provided in the message.

Signed-off-by: Laurent Vivier <lvivier@redhat.com>

5 files changed, 168 insertions, 3 deletions

diff --git a/util.h b/util.h
index 3fa1d12..d02333d 100644
--- a/util.h
+++ b/util.h
@@ -152,6 +152,9 @@ static inline void barrier(void) { __asm__ __volatile__("" ::: "memory"); }
 #define smp_wmb()	smp_mb_release()
 #define smp_rmb()	smp_mb_acquire()
 
+#define qatomic_or(ptr, n) \
+	((void) __atomic_fetch_or(ptr, n, __ATOMIC_SEQ_CST))
+
 #define NS_FN_STACK_SIZE	(1024 * 1024) /* 1MiB */
 
 int do_clone(int (*fn)(void *), char *stack_area, size_t stack_size, int flags,
diff --git a/vhost_user.c b/vhost_user.c
index ce4373d..c2fac58 100644
--- a/vhost_user.c
+++ b/vhost_user.c
@@ -510,6 +510,12 @@ static bool vu_set_mem_table_exec(struct vu_dev *vdev,
  */
 static void vu_close_log(struct vu_dev *vdev)
 {
+	if (vdev->log_table) {
+		if (munmap(vdev->log_table, vdev->log_size) != 0)
+			die_perror("close log munmap() error");
+		vdev->log_table = NULL;
+	}
+
 	if (vdev->log_call_fd != -1) {
 		close(vdev->log_call_fd);
 		vdev->log_call_fd = -1;
@@ -520,7 +526,6 @@ static void vu_close_log(struct vu_dev *vdev)
  * vu_log_kick() - Inform the front-end that the log has been modified
  * @vdev:	vhost-user device
  */
-/* cppcheck-suppress unusedFunction */
 void vu_log_kick(const struct vu_dev *vdev)
 {
 	if (vdev->log_call_fd != -1) {
@@ -532,6 +537,84 @@ void vu_log_kick(const struct vu_dev *vdev)
 	}
 }
 
+
+/**
+ * vu_log_page() -- Update logging table
+ * @log_table:	Base address of the logging table
+ * @page:	Page number that has been updated
+ */
+/* NOLINTNEXTLINE(readability-non-const-parameter) */
+static void vu_log_page(uint8_t *log_table, uint64_t page)
+{
+	qatomic_or(&log_table[page / 8], 1 << (page % 8));
+}
+
+/**
+ * vu_log_write() -- Log memory write
+ * @dev:	Vhost-user device
+ * @address:	Memory address
+ * @length:	Memory size
+ */
+void vu_log_write(const struct vu_dev *vdev, uint64_t address, uint64_t length)
+{
+	uint64_t page;
+
+	if (!vdev->log_table || !length ||
+	    !vu_has_feature(vdev, VHOST_F_LOG_ALL))
+		return;
+
+	page = address / VHOST_LOG_PAGE;
+	while (page * VHOST_LOG_PAGE < address + length) {
+		vu_log_page(vdev->log_table, page);
+		page++;
+	}
+	vu_log_kick(vdev);
+}
+
+/**
+ * vu_set_log_base_exec() - Set the memory log base
+ * @vdev:	vhost-user device
+ * @vmsg:	vhost-user message
+ *
+ * Return: False as no reply is requested
+ *
+ * #syscalls:vu mmap munmap
+ */
+static bool vu_set_log_base_exec(struct vu_dev *vdev,
+				 struct vhost_user_msg *msg)
+{
+	uint64_t log_mmap_size, log_mmap_offset;
+	void *base;
+	int fd;
+
+	if (msg->fd_num != 1 || msg->hdr.size != sizeof(msg->payload.log))
+		die("Invalid log_base message");
+
+	fd = msg->fds[0];
+	log_mmap_offset = msg->payload.log.mmap_offset;
+	log_mmap_size = msg->payload.log.mmap_size;
+
+	debug("Log mmap_offset: %"PRId64, log_mmap_offset);
+	debug("Log mmap_size:   %"PRId64, log_mmap_size);
+
+	base = mmap(0, log_mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd,
+		    log_mmap_offset);
+	close(fd);
+	if (base == MAP_FAILED)
+		die("log mmap error");
+
+	if (vdev->log_table)
+		munmap(vdev->log_table, vdev->log_size);
+
+	vdev->log_table = base;
+	vdev->log_size = log_mmap_size;
+
+	msg->hdr.size = sizeof(msg->payload.u64);
+	msg->fd_num = 0;
+
+	return true;
+}
+
 /**
  * vu_set_log_fd_exec() -- Set the eventfd used to report logging update
  * @vdev:	vhost-user device
@@ -915,6 +998,7 @@ void vu_init(struct ctx *c)
 			.notification = true,
 		};
 	}
+	c->vdev->log_table = NULL;
 	c->vdev->log_call_fd = -1;
 }
 
@@ -984,6 +1068,7 @@ static bool (*vu_handle[VHOST_USER_MAX])(struct vu_dev *vdev,
 	[VHOST_USER_GET_QUEUE_NUM]	   = vu_get_queue_num_exec,
 	[VHOST_USER_SET_OWNER]		   = vu_set_owner_exec,
 	[VHOST_USER_SET_MEM_TABLE]	   = vu_set_mem_table_exec,
+	[VHOST_USER_SET_LOG_BASE]	   = vu_set_log_base_exec,
 	[VHOST_USER_SET_LOG_FD]		   = vu_set_log_fd_exec,
 	[VHOST_USER_SET_VRING_NUM]	   = vu_set_vring_num_exec,
 	[VHOST_USER_SET_VRING_ADDR]	   = vu_set_vring_addr_exec,
diff --git a/vhost_user.h b/vhost_user.h
index 2fc0342..22a5d05 100644
--- a/vhost_user.h
+++ b/vhost_user.h
@@ -15,6 +15,7 @@
 #include "iov.h"
 
 #define VHOST_USER_F_PROTOCOL_FEATURES 30
+#define VHOST_LOG_PAGE 4096
 
 #define VHOST_MEMORY_BASELINE_NREGIONS 8
 
@@ -241,5 +242,7 @@ void vu_print_capabilities(void);
 void vu_init(struct ctx *c);
 void vu_cleanup(struct vu_dev *vdev);
 void vu_log_kick(const struct vu_dev *vdev);
+void vu_log_write(const struct vu_dev *vdev, uint64_t address,
+		  uint64_t length);
 void vu_control_handler(struct vu_dev *vdev, int fd, uint32_t events);
 #endif /* VHOST_USER_H */
diff --git a/virtio.c b/virtio.c
index 52d5a4d..1383858 100644
--- a/virtio.c
+++ b/virtio.c
@@ -81,6 +81,7 @@
 
 #include "util.h"
 #include "virtio.h"
+#include "vhost_user.h"
 
 #define VIRTQUEUE_MAX_SIZE 1024
 
@@ -592,7 +593,72 @@ static inline void vring_used_write(const struct vu_dev *vdev,
 	struct vring_used *used = vq->vring.used;
 
 	used->ring[i] = *uelem;
-	(void)vdev;
+	vu_log_write(vdev, vq->vring.log_guest_addr +
+		     offsetof(struct vring_used, ring[i]),
+		     sizeof(used->ring[i]));
+}
+
+/**
+ * vu_log_queue_fill() -- Log virtqueue memory update
+ * @dev:	Vhost-user device
+ * @vq:		Virtqueue
+ * @index:	Descriptor ring index
+ * @len:	Size of the element
+ */
+static void vu_log_queue_fill(const struct vu_dev *vdev, struct vu_virtq *vq,
+			      unsigned int index, unsigned int len)
+{
+	struct vring_desc desc_buf[VIRTQUEUE_MAX_SIZE];
+	struct vring_desc *desc = vq->vring.desc;
+	unsigned int max, min;
+	unsigned num_bufs = 0;
+	uint64_t read_len;
+
+	if (!vdev->log_table || !len || !vu_has_feature(vdev, VHOST_F_LOG_ALL))
+		return;
+
+	max = vq->vring.num;
+
+	if (le16toh(desc[index].flags) & VRING_DESC_F_INDIRECT) {
+		unsigned int desc_len;
+		uint64_t desc_addr;
+
+		if (le32toh(desc[index].len) % sizeof(struct vring_desc))
+			die("Invalid size for indirect buffer table");
+
+		/* loop over the indirect descriptor table */
+		desc_addr = le64toh(desc[index].addr);
+		desc_len = le32toh(desc[index].len);
+		max = desc_len / sizeof(struct vring_desc);
+		read_len = desc_len;
+		desc = vu_gpa_to_va(vdev, &read_len, desc_addr);
+		if (desc && read_len != desc_len) {
+			/* Failed to use zero copy */
+			desc = NULL;
+			if (!virtqueue_read_indirect_desc(vdev, desc_buf,
+							  desc_addr,
+							  desc_len))
+				desc = desc_buf;
+		}
+
+		if (!desc)
+			die("Invalid indirect buffer table");
+
+		index = 0;
+	}
+
+	do {
+		if (++num_bufs > max)
+			die("Looped descriptor");
+
+		if (le16toh(desc[index].flags) & VRING_DESC_F_WRITE) {
+			min = MIN(le32toh(desc[index].len), len);
+			vu_log_write(vdev, le64toh(desc[index].addr), min);
+			len -= min;
+		}
+	} while (len > 0 &&
+		 (virtqueue_read_next_desc(desc, index, max, &index) ==
+		  VIRTQUEUE_READ_DESC_MORE));
 }
 
 
@@ -614,6 +680,8 @@ void vu_queue_fill_by_index(const struct vu_dev *vdev, struct vu_virtq *vq,
 	if (!vq->vring.avail)
 		return;
 
+	vu_log_queue_fill(vdev, vq, index, len);
+
 	idx = (idx + vq->used_idx) % vq->vring.num;
 
 	uelem.id = htole32(index);
@@ -646,7 +714,9 @@ static inline void vring_used_idx_set(const struct vu_dev *vdev,
 				      struct vu_virtq *vq, uint16_t val)
 {
 	vq->vring.used->idx = htole16(val);
-	(void)vdev;
+	vu_log_write(vdev, vq->vring.log_guest_addr +
+		     offsetof(struct vring_used, idx),
+		     sizeof(vq->vring.used->idx));
 
 	vq->used_idx = val;
 }
diff --git a/virtio.h b/virtio.h
index d95bb07..f572341 100644
--- a/virtio.h
+++ b/virtio.h
@@ -104,6 +104,8 @@ struct vu_dev_region {
  * @features:		Vhost-user features
  * @protocol_features:	Vhost-user protocol features
  * @log_call_fd:	Eventfd to report logging update
+ * @log_size:		Size of the logging memory region
+ * @log_table:		Base of the logging memory region
  */
 struct vu_dev {
 	struct ctx *context;
@@ -113,6 +115,8 @@ struct vu_dev {
 	uint64_t features;
 	uint64_t protocol_features;
 	int log_call_fd;
+	uint64_t log_size;
+	uint8_t *log_table;
 };
 
 /**