Skip to contentSkip to conversation

vhost: support inflight share memory protocol feature

PATCH Superseded Jin Yu 1 participant 20 messages Oct 9, 2019 1 message not in the archive Arm/Amlogic Meson SoC support

v10 of 11 Superseded Latest is v11 →

lore
Share & tools
lore

A message that is not in the archive (sent off-list or not yet received): 20191008153341.22228

Jin Yu

author
#1 lore raw

v10 cover vhost: support inflight share memory protocol feature

This patches introduces two new messages VHOST_USER_GET_INFLIGHT_FD and VHOST_USER_SET_INFLIGHT_FD to support transferring a shared buffer between qemu and backend.
Now It can both support split and packed ring. The example code show how these API work. The test has passed.

How to test the example:
1, Qemu need two patches.
https://patchwork.kernel.org/patch/10766813/
https://patchwork.kernel.org/patch/10861411/(QEMU merged) it also needs some manual modifications:
we should confirm that before we send get inflight we have already sent the set features but it seems Qemu didn't do like this. So we manually revise this, we can add below code in vhost_dev_get_inflight

    int r;

    r = vhost_dev_set_features(dev, dev->log_enabled);
    if (r < 0) {
        return -errno;
    }

before get_inflight_fd.
2, Guest OS version >= 5.0
3, run the example
4, run the qemu with vhost-user-blk-pci.
eg:

        -chardev socket,id=spdk_vhost_blk0,reconnect=1,path=xxxx\
        -device vhost-user-blk-pci,ring_packed=on,chardev=spdk_vhost_blk0,num-queues=1\

5, run fio in the guest
6, kill the example and run again.
7, the fio in the guest should continue run without errors.

Jin Yu (9):
vhost: add the inflight description
vhost: add packed ring
vhost: add the inflight structure
vhost: add two new messages to support a shared buffer
vhost: checkout the resubmit inflight information
vhost: add the APIs to operate inflight ring
vhost: add APIs for user getting inflight ring
vhost: add vring functions packed ring support
vhost: add vhost-user-blk example which support inflight

 examples/vhost_blk/Makefile            |   68 ++
 examples/vhost_blk/blk.c               |  125 +++
 examples/vhost_blk/blk_spec.h          |   95 +++
 examples/vhost_blk/meson.build         |   21 +
 examples/vhost_blk/vhost_blk.c         | 1092 ++++++++++++++++++++++++
 examples/vhost_blk/vhost_blk.h         |  128 +++
 examples/vhost_blk/vhost_blk_compat.c  |  195 +++++
 lib/librte_vhost/rte_vhost.h           |  237 ++++-
 lib/librte_vhost/rte_vhost_version.map |    8 +
 lib/librte_vhost/vhost.c               |  407 ++++++++-
 lib/librte_vhost/vhost.h               |   16 +
 lib/librte_vhost/vhost_user.c          |  456 +++++++++-
 lib/librte_vhost/vhost_user.h          |   12 +-
 13 files changed, 2847 insertions(+), 13 deletions(-)
 create mode 100644 examples/vhost_blk/Makefile
 create mode 100644 examples/vhost_blk/blk.c
 create mode 100644 examples/vhost_blk/blk_spec.h
 create mode 100644 examples/vhost_blk/meson.build
 create mode 100644 examples/vhost_blk/vhost_blk.c
 create mode 100644 examples/vhost_blk/vhost_blk.h
 create mode 100644 examples/vhost_blk/vhost_blk_compat.c
Signature · 1 line
2.17.2
author
#2 lore raw

PATCH v10 1/9 vhost: add the inflight description

This patch add the inflight message description and the inflight share fd protocol feature flag.

Signed-off-by Lin Li <[email protected]>
Signed-off-by Xun Ni <[email protected]>
Signed-off-by Yu Zhang <[email protected]>
Signed-off-by Jin Yu <[email protected]>
Reviewed-by Maxime Coquelin <[email protected]>

---
v1 - specify the APIs are split-ring only
v2 - fix APIs and judge split or packed
v3 - add rte_vhost_ prefix and fix one issue
v4 - add the packed ring support
v5 - revise get_vring_base func depend on Tiwei's suggestion v6 - divide patch into small patches
v7 - updated base on Maxime's comments
v8 - updated base on Tiwei's comments

---
 lib/librte_vhost/rte_vhost.h  | 4 ++++
 lib/librte_vhost/vhost_user.h | 8 ++++++++
 2 files changed, 12 insertions(+)
lib/librte_vhost/rte_vhost.h +4 -0
index 0226b3eff..9943575ce 100644
@@ -71,6 +71,10 @@ extern "C" {
 #define VHOST_USER_PROTOCOL_F_HOST_NOTIFIER 11
 #endif
 
+#ifndef VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD
+#define VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD 12
+#endif
+
 /** Indicate whether protocol features negotiation is supported. */
 #ifndef VHOST_USER_F_PROTOCOL_FEATURES
 #define VHOST_USER_F_PROTOCOL_FEATURES	30
lib/librte_vhost/vhost_user.h +8 -0
index 2a650fe4b..17a1d7bca 100644
@@ -112,6 +112,13 @@ typedef struct VhostUserVringArea {
 	uint64_t offset;
 } VhostUserVringArea;
 
+typedef struct VhostUserInflight {
+	uint64_t mmap_size;
+	uint64_t mmap_offset;
+	uint16_t num_queues;
+	uint16_t queue_size;
+} VhostUserInflight;
+
 typedef struct VhostUserMsg {
 	union {
 		uint32_t master; /* a VhostUserRequest value */

@@ -134,6 +141,7 @@ typedef struct VhostUserMsg {
 		struct vhost_iotlb_msg iotlb;
 		VhostUserCryptoSessionParam crypto_session;
 		VhostUserVringArea area;
+		VhostUserInflight inflight;
 	} payload;
 	int fds[VHOST_MEMORY_MAX_NREGIONS];
 	int fd_num;
Signature · 1 line
2.17.2
author
#3 lore raw

PATCH v10 2/9 vhost: add packed ring

In reply to Jin Yu

This patch add the packed ring in the rte_vhost_vring.

Signed-off-by Lin Li <[email protected]>
Signed-off-by Xun Ni <[email protected]>
Signed-off-by Yu Zhang <[email protected]>
Signed-off-by Jin Yu <[email protected]>
Reviewed-by Maxime Coquelin <[email protected]>
---
 lib/librte_vhost/rte_vhost.h | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)
lib/librte_vhost/rte_vhost.h +12 -3
index 9943575ce..7257f0965 100644
@@ -103,9 +103,18 @@ struct rte_vhost_memory {
 };
 
 struct rte_vhost_vring {
-	struct vring_desc	*desc;
-	struct vring_avail	*avail;
-	struct vring_used	*used;
+	union {
+		struct vring_desc *desc;
+		struct vring_packed_desc *desc_packed;
+	};
+	union {
+		struct vring_avail *avail;
+		struct vring_packed_desc_event *driver_event;
+	};
+	union {
+		struct vring_used *used;
+		struct vring_packed_desc_event *device_event;
+	};
 	uint64_t		log_guest_addr;
 
 	/** Deprecated, use rte_vhost_vring_call() instead. */
Signature · 1 line
2.17.2
author
#4 lore raw

PATCH v10 3/9 vhost: add the inflight structure

In reply to Jin Yu

This patch adds the inflight queue region structure include the split and packed.

Signed-off-by Lin Li <[email protected]>
Signed-off-by Xun Ni <[email protected]>
Signed-off-by Yu Zhang <[email protected]>
Signed-off-by Jin Yu <[email protected]>
---
 lib/librte_vhost/rte_vhost.h | 43 ++++++++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)
lib/librte_vhost/rte_vhost.h +43 -0
index 7257f0965..5241e36e8 100644
@@ -102,6 +102,49 @@ struct rte_vhost_memory {
 	struct rte_vhost_mem_region regions[];
 };
 
+struct rte_vhost_inflight_desc_split {
+	uint8_t inflight;
+	uint8_t padding[5];
+	uint16_t next;
+	uint64_t counter;
+};
+
+struct rte_vhost_inflight_info_split {
+	uint64_t features;
+	uint16_t version;
+	uint16_t desc_num;
+	uint16_t last_inflight_io;
+	uint16_t used_idx;
+	struct rte_vhost_inflight_desc_split desc[0];
+};
+
+struct rte_vhost_inflight_desc_packed {
+	uint8_t inflight;
+	uint8_t padding;
+	uint16_t next;
+	uint16_t last;
+	uint16_t num;
+	uint64_t counter;
+	uint16_t id;
+	uint16_t flags;
+	uint32_t len;
+	uint64_t addr;
+};
+
+struct rte_vhost_inflight_info_packed {
+	uint64_t features;
+	uint16_t version;
+	uint16_t desc_num;
+	uint16_t free_head;
+	uint16_t old_free_head;
+	uint16_t used_idx;
+	uint16_t old_used_idx;
+	uint8_t used_wrap_counter;
+	uint8_t old_used_wrap_counter;
+	uint8_t padding[7];
+	struct rte_vhost_inflight_desc_packed desc[0];
+};
+
 struct rte_vhost_vring {
 	union {
 		struct vring_desc *desc;
Signature · 1 line
2.17.2
author
#5 lore raw

PATCH v10 4/9 vhost: add two new messages to support a shared buffer

In reply to Jin Yu

This patch introduces two new messages VHOST_USER_GET_INFLIGHT_FD and VHOST_USER_SET_INFLIGHT_FD to support transferring a shared buffer between qemu and backend.

Signed-off-by Lin Li <[email protected]>
Signed-off-by Xun Ni <[email protected]>
Signed-off-by Yu Zhang <[email protected]>
Signed-off-by Jin Yu <[email protected]>
---
 lib/librte_vhost/vhost.h      |   7 +
 lib/librte_vhost/vhost_user.c | 243 +++++++++++++++++++++++++++++++++-
 lib/librte_vhost/vhost_user.h |   4 +-
 3 files changed, 252 insertions(+), 2 deletions(-)
lib/librte_vhost/vhost.h +7 -0
index 884befa85..d67ba849a 100644
@@ -286,6 +286,12 @@ struct guest_page {
 	uint64_t size;
 };
 
+struct inflight_mem_info {
+	int		fd;
+	void		*addr;
+	uint64_t	size;
+};
+
 /**
  * Device structure contains all configuration information relating
  * to the device.

@@ -303,6 +309,7 @@ struct virtio_net {
 	uint32_t		nr_vring;
 	int			dequeue_zero_copy;
 	struct vhost_virtqueue	*virtqueue[VHOST_MAX_QUEUE_PAIRS * 2];
+	struct inflight_mem_info *inflight_info;
 #define IF_NAME_SZ (PATH_MAX > IFNAMSIZ ? PATH_MAX : IFNAMSIZ)
 	char			ifname[IF_NAME_SZ];
 	uint64_t		log_size;
lib/librte_vhost/vhost_user.c +242 -1

281 lines not on this page · raw message

lib/librte_vhost/vhost_user.h +3 -1
index 17a1d7bca..6563f7315 100644
@@ -54,7 +54,9 @@ typedef enum VhostUserRequest {
 	VHOST_USER_POSTCOPY_ADVISE = 28,
 	VHOST_USER_POSTCOPY_LISTEN = 29,
 	VHOST_USER_POSTCOPY_END = 30,
-	VHOST_USER_MAX = 31
+	VHOST_USER_GET_INFLIGHT_FD = 31,
+	VHOST_USER_SET_INFLIGHT_FD = 32,
+	VHOST_USER_MAX = 33
 } VhostUserRequest;
 
 typedef enum VhostUserSlaveRequest {
Signature · 1 line
2.17.2
author
#6 lore raw

PATCH v10 5/9 vhost: checkout the resubmit inflight information

In reply to Jin Yu

This patch shows how to checkout the inflight ring and construct the resubmit information also include destroying resubmit info.

Signed-off-by Lin Li <[email protected]>
Signed-off-by Xun Ni <[email protected]>
Signed-off-by Yu Zhang <[email protected]>
Signed-off-by Jin Yu <[email protected]>
---
 lib/librte_vhost/rte_vhost.h  |  19 +++
 lib/librte_vhost/vhost.c      |  29 ++++-
 lib/librte_vhost/vhost.h      |   9 ++
 lib/librte_vhost/vhost_user.c | 217 +++++++++++++++++++++++++++++++++-
 4 files changed, 271 insertions(+), 3 deletions(-)
lib/librte_vhost/rte_vhost.h +19 -0
index 5241e36e8..95e4d720e 100644
@@ -145,6 +145,25 @@ struct rte_vhost_inflight_info_packed {
 	struct rte_vhost_inflight_desc_packed desc[0];
 };
 
+struct rte_vhost_resubmit_desc {
+	uint16_t index;
+	uint64_t counter;
+};
+
+struct rte_vhost_resubmit_info {
+	struct rte_vhost_resubmit_desc *resubmit_list;
+	uint16_t resubmit_num;
+};
+
+struct rte_vhost_ring_inflight {
+	union {
+		struct rte_vhost_inflight_info_split *inflight_split;
+		struct rte_vhost_inflight_info_packed *inflight_packed;
+	};
+
+	struct rte_vhost_resubmit_info *resubmit_inflight;
+};
+
 struct rte_vhost_vring {
 	union {
 		struct vring_desc *desc;
lib/librte_vhost/vhost.c +28 -1
index 981837b5d..f8660edbf 100644
@@ -242,6 +242,31 @@ cleanup_vq(struct vhost_virtqueue *vq, int destroy)
 		close(vq->kickfd);
 }
 
+void
+cleanup_vq_inflight(struct virtio_net *dev, struct vhost_virtqueue *vq)
+{
+	if (!(dev->protocol_features &
+	    (1ULL << VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD)))
+		return;
+
+	if (vq_is_packed(dev)) {
+		if (vq->inflight_packed)
+			vq->inflight_packed = NULL;
+	} else {
+		if (vq->inflight_split)
+			vq->inflight_split = NULL;
+	}
+
+	if (vq->resubmit_inflight) {
+		if (vq->resubmit_inflight->resubmit_list) {
+			free(vq->resubmit_inflight->resubmit_list);
+			vq->resubmit_inflight->resubmit_list = NULL;
+		}
+		free(vq->resubmit_inflight);
+		vq->resubmit_inflight = NULL;
+	}
+}
+
 /*
  * Unmap any memory, close any file descriptors and
  * free any memory owned by a device.

@@ -253,8 +278,10 @@ cleanup_device(struct virtio_net *dev, int destroy)
 
 	vhost_backend_cleanup(dev);
 
-	for (i = 0; i < dev->nr_vring; i++)
+	for (i = 0; i < dev->nr_vring; i++) {
 		cleanup_vq(dev->virtqueue[i], destroy);
+		cleanup_vq_inflight(dev, dev->virtqueue[i]);
+	}
 }
 
 void
lib/librte_vhost/vhost.h +9 -0
index d67ba849a..ab95999c4 100644
@@ -128,6 +128,14 @@ struct vhost_virtqueue {
 	/* Physical address of used ring, for logging */
 	uint64_t		log_guest_addr;
 
+	/* inflight share memory info */
+	union {
+		struct rte_vhost_inflight_info_split *inflight_split;
+		struct rte_vhost_inflight_info_packed *inflight_packed;
+	};
+	struct rte_vhost_resubmit_info *resubmit_inflight;
+	uint64_t		global_counter;
+
 	uint16_t		nr_zmbuf;
 	uint16_t		zmbuf_size;
 	uint16_t		last_zmbuf_idx;

@@ -474,6 +482,7 @@ void vhost_destroy_device(int);
 void vhost_destroy_device_notify(struct virtio_net *dev);
 
 void cleanup_vq(struct vhost_virtqueue *vq, int destroy);
+void cleanup_vq_inflight(struct virtio_net *dev, struct vhost_virtqueue *vq);
 void free_vq(struct virtio_net *dev, struct vhost_virtqueue *vq);
 
 int alloc_vring_queue(struct virtio_net *dev, uint32_t vring_idx);
lib/librte_vhost/vhost_user.c +215 -2

249 lines not on this page · raw message

Signature · 1 line
2.17.2
author
#7 lore raw

PATCH v10 6/9 vhost: add the APIs to operate inflight ring

In reply to Jin Yu

This patch introduces three APIs to operate the inflight ring. Three APIs are set, set last and clear. It includes split and packed ring.

Signed-off-by Lin Li <[email protected]>
Signed-off-by Xun Ni <[email protected]>
Signed-off-by Yu Zhang <[email protected]>
Signed-off-by Jin Yu <[email protected]>
---
 lib/librte_vhost/rte_vhost.h           | 116 +++++++++++
 lib/librte_vhost/rte_vhost_version.map |   6 +
 lib/librte_vhost/vhost.c               | 273 +++++++++++++++++++++++++
 3 files changed, 395 insertions(+)
lib/librte_vhost/rte_vhost.h +116 -0
index 95e4d720e..15d7e67cd 100644
@@ -693,6 +693,122 @@ int rte_vhost_get_mem_table(int vid, struct rte_vhost_memory **mem);
 int rte_vhost_get_vhost_vring(int vid, uint16_t vring_idx,
 			      struct rte_vhost_vring *vring);
 
+/**
+ * Set split inflight descriptor.
+ *
+ * This function save descriptors that has been comsumed in available
+ * ring
+ *
+ * @param vid
+ *  vhost device ID
+ * @param vring_idx
+ *  vring index
+ * @param idx
+ *  inflight entry index
+ * @return
+ *  0 on success, -1 on failure
+ */
+__rte_experimental
+int
+rte_vhost_set_inflight_desc_split(int vid, uint16_t vring_idx,
+	uint16_t idx);
+
+/**
+ * Set packed inflight descriptor and get corresponding inflight entry
+ *
+ * This function save descriptors that has been comsumed
+ *
+ * @param vid
+ *  vhost device ID
+ * @param vring_idx
+ *  vring index
+ * @param head
+ *  head of descriptors
+ * @param last
+ *  last of descriptors
+ * @param inflight_entry
+ *  corresponding inflight entry
+ * @return
+ *  0 on success, -1 on failure
+ */
+__rte_experimental
+int
+rte_vhost_set_inflight_desc_packed(int vid, uint16_t vring_idx,
+	uint16_t head, uint16_t last, uint16_t *inflight_entry);
+
+/**
+ * Save the head of list that the last batch of used descriptors.
+ *
+ * @param vid
+ *  vhost device ID
+ * @param vring_idx
+ *  vring index
+ * @param idx
+ *  descriptor entry index
+ * @return
+ *  0 on success, -1 on failure
+ */
+__rte_experimental
+int
+rte_vhost_set_last_inflight_io_split(int vid,
+	uint16_t vring_idx, uint16_t idx);
+
+/**
+ * Update the inflight free_head, used_idx and used_wrap_counter.
+ *
+ * This function will update status first before updating descriptors
+ * to used
+ *
+ * @param vid
+ *  vhost device ID
+ * @param vring_idx
+ *  vring index
+ * @param head
+ *  head of descriptors
+ * @return
+ *  0 on success, -1 on failure
+ */
+__rte_experimental
+int
+rte_vhost_set_last_inflight_io_packed(int vid,
+	uint16_t vring_idx, uint16_t head);
+
+/**
+ * Clear the split inflight status.
+ *
+ * @param vid
+ *  vhost device ID
+ * @param vring_idx
+ *  vring index
+ * @param last_used_idx
+ *  last used idx of used ring
+ * @param idx
+ *  inflight entry index
+ * @return
+ *  0 on success, -1 on failure
+ */
+__rte_experimental
+int
+rte_vhost_clr_inflight_desc_split(int vid, uint16_t vring_idx,
+	uint16_t last_used_idx, uint16_t idx);
+
+/**
+ * Clear the packed inflight status.
+ *
+ * @param vid
+ *  vhost device ID
+ * @param vring_idx
+ *  vring index
+ * @param head
+ *  inflight entry index
+ * @return
+ *  0 on success, -1 on failure
+ */
+__rte_experimental
+int
+rte_vhost_clr_inflight_desc_packed(int vid, uint16_t vring_idx,
+	uint16_t head);
+
 /**
  * Notify the guest that used descriptors have been added to the vring.  This
  * function acts as a memory barrier.
lib/librte_vhost/rte_vhost_version.map +6 -0
index 5f1d4a75c..bc70bfaa5 100644
@@ -87,4 +87,10 @@ EXPERIMENTAL {
 	rte_vdpa_relay_vring_used;
 	rte_vhost_extern_callback_register;
 	rte_vhost_driver_set_protocol_features;
+	rte_vhost_set_inflight_desc_split;
+	rte_vhost_set_inflight_desc_packed;
+	rte_vhost_set_last_inflight_io_split;
+	rte_vhost_set_last_inflight_io_packed;
+	rte_vhost_clr_inflight_desc_split;
+	rte_vhost_clr_inflight_desc_packed;
 };
lib/librte_vhost/vhost.c +273 -0

279 lines not on this page · raw message

Signature · 1 line
2.17.2
author
#8 lore raw

PATCH v10 7/9 vhost: add APIs for user getting inflight ring

In reply to Jin Yu

This patch introduces two APIs. one is for getting inflgiht ring and the other is for getting base.

Signed-off-by Lin Li <[email protected]>
Signed-off-by Xun Ni <[email protected]>
Signed-off-by Yu Zhang <[email protected]>
Signed-off-by Jin Yu <[email protected]>
---
 lib/librte_vhost/rte_vhost.h           | 40 +++++++++++++++++
 lib/librte_vhost/rte_vhost_version.map |  2 +
 lib/librte_vhost/vhost.c               | 61 ++++++++++++++++++++++++++
 3 files changed, 103 insertions(+)
lib/librte_vhost/rte_vhost.h +40 -0
index 15d7e67cd..1e1e13d71 100644
@@ -693,6 +693,23 @@ int rte_vhost_get_mem_table(int vid, struct rte_vhost_memory **mem);
 int rte_vhost_get_vhost_vring(int vid, uint16_t vring_idx,
 			      struct rte_vhost_vring *vring);
 
+/**
+ * Get guest inflight vring info, including inflight ring and resubmit list.
+ *
+ * @param vid
+ *  vhost device ID
+ * @param vring_idx
+ *  vring index
+ * @param vring
+ *  the structure to hold the requested inflight vring info
+ * @return
+ *  0 on success, -1 on failure
+ */
+__rte_experimental
+int
+rte_vhost_get_vhost_ring_inflight(int vid, uint16_t vring_idx,
+	struct rte_vhost_ring_inflight *vring);
+
 /**
  * Set split inflight descriptor.
  *

@@ -867,6 +884,29 @@ int __rte_experimental
 rte_vhost_get_vring_base(int vid, uint16_t queue_id,
 		uint16_t *last_avail_idx, uint16_t *last_used_idx);
 
+/**
+ * Get last_avail/last_used of the vhost virtqueue
+ *
+ * This function is designed for the reconnection and it's specific for
+ * the packed ring as we can get the two parameters from the inflight
+ * queueregion
+ *
+ * @param vid
+ *  vhost device ID
+ * @param queue_id
+ *  vhost queue index
+ * @param last_avail_idx
+ *  vhost last_avail_idx to get
+ * @param last_used_idx
+ *  vhost last_used_idx to get
+ * @return
+ *  0 on success, -1 on failure
+ */
+__rte_experimental
+int
+rte_vhost_get_vring_base_from_inflight(int vid,
+	uint16_t queue_id, uint16_t *last_avail_idx, uint16_t *last_used_idx);
+
 /**
  * Set last_avail/used_idx of the vhost virtqueue
  *
lib/librte_vhost/rte_vhost_version.map +2 -0
index bc70bfaa5..ce517b127 100644
@@ -93,4 +93,6 @@ EXPERIMENTAL {
 	rte_vhost_set_last_inflight_io_packed;
 	rte_vhost_clr_inflight_desc_split;
 	rte_vhost_clr_inflight_desc_packed;
+	rte_vhost_get_vhost_ring_inflight;
+	rte_vhost_get_vring_base_from_inflight;
 };
lib/librte_vhost/vhost.c +61 -0

73 lines not on this page · raw message

Signature · 1 line
2.17.2
author
#9 lore raw

PATCH v10 8/9 vhost: add vring functions packed ring support

In reply to Jin Yu

This patch add packed ring support in two APIs so user can get the packed ring`.

Signed-off-by Lin Li <[email protected]>
Signed-off-by Xun Ni <[email protected]>
Signed-off-by Yu Zhang <[email protected]>
Signed-off-by Jin Yu <[email protected]>
---
 lib/librte_vhost/vhost.c | 68 +++++++++++++++++++++++++++++-----------
 1 file changed, 49 insertions(+), 19 deletions(-)
lib/librte_vhost/vhost.c +49 -19
index f7ed37261..fd3445207 100644
@@ -771,9 +771,15 @@ rte_vhost_get_vhost_vring(int vid, uint16_t vring_idx,
 	if (!vq)
 		return -1;
 
-	vring->desc  = vq->desc;
-	vring->avail = vq->avail;
-	vring->used  = vq->used;
+	if (vq_is_packed(dev)) {
+		vring->desc_packed = vq->desc_packed;
+		vring->driver_event = vq->driver_event;
+		vring->device_event = vq->device_event;
+	} else {
+		vring->desc = vq->desc;
+		vring->avail = vq->avail;
+		vring->used = vq->used;
+	}
 	vring->log_guest_addr  = vq->log_guest_addr;
 
 	vring->callfd  = vq->callfd;

@@ -1274,13 +1280,51 @@ int rte_vhost_get_log_base(int vid, uint64_t *log_base,
 int rte_vhost_get_vring_base(int vid, uint16_t queue_id,
 		uint16_t *last_avail_idx, uint16_t *last_used_idx)
 {
+	struct vhost_virtqueue *vq;
 	struct virtio_net *dev = get_device(vid);
 
 	if (dev == NULL || last_avail_idx == NULL || last_used_idx == NULL)
 		return -1;
 
-	*last_avail_idx = dev->virtqueue[queue_id]->last_avail_idx;
-	*last_used_idx = dev->virtqueue[queue_id]->last_used_idx;
+	vq = dev->virtqueue[queue_id];
+	if (!vq)
+		return -1;
+
+	if (vq_is_packed(dev)) {
+		*last_avail_idx = (vq->avail_wrap_counter << 15) |
+				  vq->last_avail_idx;
+		*last_used_idx = (vq->used_wrap_counter << 15) |
+				 vq->last_used_idx;
+	} else {
+		*last_avail_idx = vq->last_avail_idx;
+		*last_used_idx = vq->last_used_idx;
+	}
+
+	return 0;
+}
+
+int rte_vhost_set_vring_base(int vid, uint16_t queue_id,
+		uint16_t last_avail_idx, uint16_t last_used_idx)
+{
+	struct vhost_virtqueue *vq;
+	struct virtio_net *dev = get_device(vid);
+
+	if (!dev)
+		return -1;
+
+	vq = dev->virtqueue[queue_id];
+	if (!vq)
+		return -1;
+
+	if (vq_is_packed(dev)) {
+		vq->last_avail_idx = last_avail_idx & 0x7fff;
+		vq->avail_wrap_counter = !!(last_avail_idx & (1 << 15));
+		vq->last_used_idx = last_used_idx & 0x7fff;
+		vq->used_wrap_counter = !!(last_used_idx & (1 << 15));
+	} else {
+		vq->last_avail_idx = last_avail_idx;
+		vq->last_used_idx = last_used_idx;
+	}
 
 	return 0;
 }

@@ -1311,20 +1355,6 @@ rte_vhost_get_vring_base_from_inflight(int vid,
 	return 0;
 }
 
-int rte_vhost_set_vring_base(int vid, uint16_t queue_id,
-		uint16_t last_avail_idx, uint16_t last_used_idx)
-{
-	struct virtio_net *dev = get_device(vid);
-
-	if (!dev)
-		return -1;
-
-	dev->virtqueue[queue_id]->last_avail_idx = last_avail_idx;
-	dev->virtqueue[queue_id]->last_used_idx = last_used_idx;
-
-	return 0;
-}
-
 int rte_vhost_extern_callback_register(int vid,
 		struct rte_vhost_user_extern_ops const * const ops, void *ctx)
 {
Signature · 1 line
2.17.2
author
#10 lore raw

PATCH v10 9/9 vhost: add vhost-user-blk example which support inflight

In reply to Jin Yu

A vhost-user-blk example that support inflight feature. It uses the new APIs that introduced in the first patch, so it can show how these APIs work to support inflight feature.

Signed-off-by Jin Yu <[email protected]>

---
V1 - add the case.
V2 - add the rte_vhost prefix.
V3 - add packed ring support

---
 examples/vhost_blk/Makefile           |   68 ++
 examples/vhost_blk/blk.c              |  125 +++
 examples/vhost_blk/blk_spec.h         |   95 +++
 examples/vhost_blk/meson.build        |   21 +
 examples/vhost_blk/vhost_blk.c        | 1092 +++++++++++++++++++++++++
 examples/vhost_blk/vhost_blk.h        |  128 +++
 examples/vhost_blk/vhost_blk_compat.c |  195 +++++
 7 files changed, 1724 insertions(+)
 create mode 100644 examples/vhost_blk/Makefile
 create mode 100644 examples/vhost_blk/blk.c
 create mode 100644 examples/vhost_blk/blk_spec.h
 create mode 100644 examples/vhost_blk/meson.build
 create mode 100644 examples/vhost_blk/vhost_blk.c
 create mode 100644 examples/vhost_blk/vhost_blk.h
 create mode 100644 examples/vhost_blk/vhost_blk_compat.c
examples/vhost_blk/Makefile new file +68 -0
new file mode 100644
index 000000000..a10a90071
@@ -0,0 +1,68 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2010-2014 Intel Corporation
+
+# binary name
+APP = vhost-blk
+
+# all source are stored in SRCS-y
+SRCS-y := blk.c vhost_blk.c vhost_blk_compat.c
+
+# Build using pkg-config variables if possible
+$(shell pkg-config --exists libdpdk)
+ifeq ($(.SHELLSTATUS),0)
+
+all: shared
+.PHONY: shared static
+shared: build/$(APP)-shared
+	ln -sf $(APP)-shared build/$(APP)
+static: build/$(APP)-static
+	ln -sf $(APP)-static build/$(APP)
+
+LDFLAGS += -pthread
+
+PC_FILE := $(shell pkg-config --path libdpdk)
+CFLAGS += -O3 $(shell pkg-config --cflags libdpdk)
+LDFLAGS_SHARED = $(shell pkg-config --libs libdpdk)
+LDFLAGS_STATIC = -Wl,-Bstatic $(shell pkg-config --static --libs libdpdk)
+
+CFLAGS += -DALLOW_EXPERIMENTAL_API
+
+build/$(APP)-shared: $(SRCS-y) Makefile $(PC_FILE) | build
+	$(CC) $(CFLAGS) $(SRCS-y) -o $@ $(LDFLAGS) $(LDFLAGS_SHARED)
+
+build/$(APP)-static: $(SRCS-y) Makefile $(PC_FILE) | build
+	$(CC) $(CFLAGS) $(SRCS-y) -o $@ $(LDFLAGS) $(LDFLAGS_STATIC)
+
+build:
+	@mkdir -p $@
+
+.PHONY: clean
+clean:
+	rm -f build/$(APP) build/$(APP)-static build/$(APP)-shared
+	test -d build && rmdir -p build || true
+
+else # Build using legacy build system
+
+ifeq ($(RTE_SDK),)
+$(error "Please define RTE_SDK environment variable")
+endif
+
+# Default target, detect a build directory, by looking for a path with a .config
+RTE_TARGET ?= $(notdir $(abspath $(dir $(firstword $(wildcard $(RTE_SDK)/*/.config)))))
+
+include $(RTE_SDK)/mk/rte.vars.mk
+
+ifneq ($(CONFIG_RTE_EXEC_ENV_LINUX),y)
+$(info This application can only operate in a linux environment, \
+please change the definition of the RTE_TARGET environment variable)
+all:
+else
+
+CFLAGS += -DALLOW_EXPERIMENTAL_API
+CFLAGS += -O2 -D_FILE_OFFSET_BITS=64
+CFLAGS += $(WERROR_FLAGS)
+
+include $(RTE_SDK)/mk/rte.extapp.mk
+
+endif
+endif
examples/vhost_blk/blk.c new file +125 -0

125 lines not on this page · raw message

examples/vhost_blk/blk_spec.h new file +95 -0

95 lines not on this page · raw message

examples/vhost_blk/meson.build new file +21 -0
new file mode 100644
index 000000000..857367192
@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2017 Intel Corporation
+
+# meson file, for building this example as part of a main DPDK build.
+#
+# To build this example as a standalone application with an already-installed
+# DPDK instance, use 'make'
+
+if not is_linux
+	build = false
+endif
+
+if not cc.has_header('linux/virtio_blk.h')
+	build = false
+endif
+
+deps += 'vhost'
+allow_experimental_apis = true
+sources = files(
+	'blk.c', 'vhost_blk.c', 'vhost_blk_compat.c'
+)
examples/vhost_blk/vhost_blk.c new file +1092 -0

1,092 lines not on this page · raw message

examples/vhost_blk/vhost_blk.h new file +128 -0

128 lines not on this page · raw message

examples/vhost_blk/vhost_blk_compat.c new file +195 -0

195 lines not on this page · raw message

Signature · 1 line
2.17.2
author
#11 lore raw

v10 cover vhost: support inflight share memory protocol feature

In reply to a message not in the archive

v2:
- specify the APIs are split-ring only

v3:
- fix APIs issues and judge split or packed

v4:
- add rte_vhost_ prefix and fix issues

v5:
- add the packed ring support and add the vhost_blk example

v6:
- revise get_vring_base func depend on Tiwei's suggestion

v7:
- divide patch into small patches

v8:
- updated base on Maxime's comments

v9:
- updated base on Tiwei's comments

v10:
- fix code style and update some misleading log

This patches introduces two new messages VHOST_USER_GET_INFLIGHT_FD and VHOST_USER_SET_INFLIGHT_FD to support transferring a shared buffer between qemu and backend.
Now It can both support split and packed ring. The example code show how these API work. The test has passed.

How to test the example:
1, Qemu need two patches.
https://patchwork.kernel.org/patch/10766813/
https://patchwork.kernel.org/patch/10861411/(QEMU merged) it also needs some manual modifications:
we should confirm that before we send get inflight we have already sent the set features but it seems Qemu didn't do like this. So we manually revise this, we can add below code in vhost_dev_get_inflight

    int r;

    r = vhost_dev_set_features(dev, dev->log_enabled);
    if (r < 0) {
        return -errno;
    }

before get_inflight_fd.
2, Guest OS version >= 5.0
3, run the example
4, run the qemu with vhost-user-blk-pci.
eg:

        -chardev socket,id=spdk_vhost_blk0,reconnect=1,path=xxxx\
        -device vhost-user-blk-pci,ring_packed=on,chardev=spdk_vhost_blk0,num-queues=1\

5, run fio in the guest
6, kill the example and run again.
7, the fio in the guest should continue run without errors.

Jin Yu (9):
vhost: add the inflight description
vhost: add packed ring
vhost: add the inflight structure
vhost: add two new messages to support a shared buffer
vhost: checkout the resubmit inflight information
vhost: add the APIs to operate inflight ring
vhost: add APIs for user getting inflight ring
vhost: add vring functions packed ring support
vhost: add vhost-user-blk example which support inflight

 examples/vhost_blk/Makefile            |   68 ++
 examples/vhost_blk/blk.c               |  125 +++
 examples/vhost_blk/blk_spec.h          |   95 +++
 examples/vhost_blk/meson.build         |   21 +
 examples/vhost_blk/vhost_blk.c         | 1092 ++++++++++++++++++++++++
 examples/vhost_blk/vhost_blk.h         |  128 +++
 examples/vhost_blk/vhost_blk_compat.c  |  195 +++++
 lib/librte_vhost/rte_vhost.h           |  237 ++++-
 lib/librte_vhost/rte_vhost_version.map |    8 +
 lib/librte_vhost/vhost.c               |  407 ++++++++-
 lib/librte_vhost/vhost.h               |   16 +
 lib/librte_vhost/vhost_user.c          |  456 +++++++++-
 lib/librte_vhost/vhost_user.h          |   12 +-
 13 files changed, 2847 insertions(+), 13 deletions(-)
 create mode 100644 examples/vhost_blk/Makefile
 create mode 100644 examples/vhost_blk/blk.c
 create mode 100644 examples/vhost_blk/blk_spec.h
 create mode 100644 examples/vhost_blk/meson.build
 create mode 100644 examples/vhost_blk/vhost_blk.c
 create mode 100644 examples/vhost_blk/vhost_blk.h
 create mode 100644 examples/vhost_blk/vhost_blk_compat.c
Signature · 1 line
2.17.2
author
#12 lore raw

PATCH v10 1/9 vhost: add the inflight description

This patch add the inflight message description and the inflight share fd protocol feature flag.

Signed-off-by Lin Li <[email protected]>
Signed-off-by Xun Ni <[email protected]>
Signed-off-by Yu Zhang <[email protected]>
Signed-off-by Jin Yu <[email protected]>
Reviewed-by Maxime Coquelin <[email protected]>

---
v1 - specify the APIs are split-ring only
v2 - fix APIs and judge split or packed
v3 - add rte_vhost_ prefix and fix one issue
v4 - add the packed ring support
v5 - revise get_vring_base func depend on Tiwei's suggestion v6 - divide patch into small patches
v7 - updated base on Maxime's comments
v8 - updated base on Tiwei's comments

---
 lib/librte_vhost/rte_vhost.h  | 4 ++++
 lib/librte_vhost/vhost_user.h | 8 ++++++++
 2 files changed, 12 insertions(+)
lib/librte_vhost/rte_vhost.h +4 -0
index 0226b3eff..9943575ce 100644
@@ -71,6 +71,10 @@ extern "C" {
 #define VHOST_USER_PROTOCOL_F_HOST_NOTIFIER 11
 #endif
 
+#ifndef VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD
+#define VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD 12
+#endif
+
 /** Indicate whether protocol features negotiation is supported. */
 #ifndef VHOST_USER_F_PROTOCOL_FEATURES
 #define VHOST_USER_F_PROTOCOL_FEATURES	30
lib/librte_vhost/vhost_user.h +8 -0
index 2a650fe4b..17a1d7bca 100644
@@ -112,6 +112,13 @@ typedef struct VhostUserVringArea {
 	uint64_t offset;
 } VhostUserVringArea;
 
+typedef struct VhostUserInflight {
+	uint64_t mmap_size;
+	uint64_t mmap_offset;
+	uint16_t num_queues;
+	uint16_t queue_size;
+} VhostUserInflight;
+
 typedef struct VhostUserMsg {
 	union {
 		uint32_t master; /* a VhostUserRequest value */

@@ -134,6 +141,7 @@ typedef struct VhostUserMsg {
 		struct vhost_iotlb_msg iotlb;
 		VhostUserCryptoSessionParam crypto_session;
 		VhostUserVringArea area;
+		VhostUserInflight inflight;
 	} payload;
 	int fds[VHOST_MEMORY_MAX_NREGIONS];
 	int fd_num;
Signature · 1 line
2.17.2
author
#13 lore raw

PATCH v10 2/9 vhost: add packed ring

In reply to Jin Yu

This patch add the packed ring in the rte_vhost_vring.

Signed-off-by Lin Li <[email protected]>
Signed-off-by Xun Ni <[email protected]>
Signed-off-by Yu Zhang <[email protected]>
Signed-off-by Jin Yu <[email protected]>
Reviewed-by Maxime Coquelin <[email protected]>
---
 lib/librte_vhost/rte_vhost.h | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)
lib/librte_vhost/rte_vhost.h +12 -3
index 9943575ce..7257f0965 100644
@@ -103,9 +103,18 @@ struct rte_vhost_memory {
 };
 
 struct rte_vhost_vring {
-	struct vring_desc	*desc;
-	struct vring_avail	*avail;
-	struct vring_used	*used;
+	union {
+		struct vring_desc *desc;
+		struct vring_packed_desc *desc_packed;
+	};
+	union {
+		struct vring_avail *avail;
+		struct vring_packed_desc_event *driver_event;
+	};
+	union {
+		struct vring_used *used;
+		struct vring_packed_desc_event *device_event;
+	};
 	uint64_t		log_guest_addr;
 
 	/** Deprecated, use rte_vhost_vring_call() instead. */
Signature · 1 line
2.17.2
author
#14 lore raw

PATCH v10 3/9 vhost: add the inflight structure

In reply to Jin Yu

This patch adds the inflight queue region structure include the split and packed.

Signed-off-by Lin Li <[email protected]>
Signed-off-by Xun Ni <[email protected]>
Signed-off-by Yu Zhang <[email protected]>
Signed-off-by Jin Yu <[email protected]>
---
 lib/librte_vhost/rte_vhost.h | 43 ++++++++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)
lib/librte_vhost/rte_vhost.h +43 -0
index 7257f0965..5241e36e8 100644
@@ -102,6 +102,49 @@ struct rte_vhost_memory {
 	struct rte_vhost_mem_region regions[];
 };
 
+struct rte_vhost_inflight_desc_split {
+	uint8_t inflight;
+	uint8_t padding[5];
+	uint16_t next;
+	uint64_t counter;
+};
+
+struct rte_vhost_inflight_info_split {
+	uint64_t features;
+	uint16_t version;
+	uint16_t desc_num;
+	uint16_t last_inflight_io;
+	uint16_t used_idx;
+	struct rte_vhost_inflight_desc_split desc[0];
+};
+
+struct rte_vhost_inflight_desc_packed {
+	uint8_t inflight;
+	uint8_t padding;
+	uint16_t next;
+	uint16_t last;
+	uint16_t num;
+	uint64_t counter;
+	uint16_t id;
+	uint16_t flags;
+	uint32_t len;
+	uint64_t addr;
+};
+
+struct rte_vhost_inflight_info_packed {
+	uint64_t features;
+	uint16_t version;
+	uint16_t desc_num;
+	uint16_t free_head;
+	uint16_t old_free_head;
+	uint16_t used_idx;
+	uint16_t old_used_idx;
+	uint8_t used_wrap_counter;
+	uint8_t old_used_wrap_counter;
+	uint8_t padding[7];
+	struct rte_vhost_inflight_desc_packed desc[0];
+};
+
 struct rte_vhost_vring {
 	union {
 		struct vring_desc *desc;
Signature · 1 line
2.17.2
author
#15 lore raw

PATCH v10 4/9 vhost: add two new messages to support a shared buffer

In reply to Jin Yu

This patch introduces two new messages VHOST_USER_GET_INFLIGHT_FD and VHOST_USER_SET_INFLIGHT_FD to support transferring a shared buffer between qemu and backend.

Signed-off-by Lin Li <[email protected]>
Signed-off-by Xun Ni <[email protected]>
Signed-off-by Yu Zhang <[email protected]>
Signed-off-by Jin Yu <[email protected]>
---
 lib/librte_vhost/vhost.h      |   7 +
 lib/librte_vhost/vhost_user.c | 243 +++++++++++++++++++++++++++++++++-
 lib/librte_vhost/vhost_user.h |   4 +-
 3 files changed, 252 insertions(+), 2 deletions(-)
lib/librte_vhost/vhost.h +7 -0
index 884befa85..d67ba849a 100644
@@ -286,6 +286,12 @@ struct guest_page {
 	uint64_t size;
 };
 
+struct inflight_mem_info {
+	int		fd;
+	void		*addr;
+	uint64_t	size;
+};
+
 /**
  * Device structure contains all configuration information relating
  * to the device.

@@ -303,6 +309,7 @@ struct virtio_net {
 	uint32_t		nr_vring;
 	int			dequeue_zero_copy;
 	struct vhost_virtqueue	*virtqueue[VHOST_MAX_QUEUE_PAIRS * 2];
+	struct inflight_mem_info *inflight_info;
 #define IF_NAME_SZ (PATH_MAX > IFNAMSIZ ? PATH_MAX : IFNAMSIZ)
 	char			ifname[IF_NAME_SZ];
 	uint64_t		log_size;
lib/librte_vhost/vhost_user.c +242 -1

281 lines not on this page · raw message

lib/librte_vhost/vhost_user.h +3 -1
index 17a1d7bca..6563f7315 100644
@@ -54,7 +54,9 @@ typedef enum VhostUserRequest {
 	VHOST_USER_POSTCOPY_ADVISE = 28,
 	VHOST_USER_POSTCOPY_LISTEN = 29,
 	VHOST_USER_POSTCOPY_END = 30,
-	VHOST_USER_MAX = 31
+	VHOST_USER_GET_INFLIGHT_FD = 31,
+	VHOST_USER_SET_INFLIGHT_FD = 32,
+	VHOST_USER_MAX = 33
 } VhostUserRequest;
 
 typedef enum VhostUserSlaveRequest {
Signature · 1 line
2.17.2
author
#16 lore raw

PATCH v10 5/9 vhost: checkout the resubmit inflight information

In reply to Jin Yu

This patch shows how to checkout the inflight ring and construct the resubmit information also include destroying resubmit info.

Signed-off-by Lin Li <[email protected]>
Signed-off-by Xun Ni <[email protected]>
Signed-off-by Yu Zhang <[email protected]>
Signed-off-by Jin Yu <[email protected]>
---
 lib/librte_vhost/rte_vhost.h  |  19 +++
 lib/librte_vhost/vhost.c      |  29 ++++-
 lib/librte_vhost/vhost.h      |   9 ++
 lib/librte_vhost/vhost_user.c | 217 +++++++++++++++++++++++++++++++++-
 4 files changed, 271 insertions(+), 3 deletions(-)
lib/librte_vhost/rte_vhost.h +19 -0
index 5241e36e8..95e4d720e 100644
@@ -145,6 +145,25 @@ struct rte_vhost_inflight_info_packed {
 	struct rte_vhost_inflight_desc_packed desc[0];
 };
 
+struct rte_vhost_resubmit_desc {
+	uint16_t index;
+	uint64_t counter;
+};
+
+struct rte_vhost_resubmit_info {
+	struct rte_vhost_resubmit_desc *resubmit_list;
+	uint16_t resubmit_num;
+};
+
+struct rte_vhost_ring_inflight {
+	union {
+		struct rte_vhost_inflight_info_split *inflight_split;
+		struct rte_vhost_inflight_info_packed *inflight_packed;
+	};
+
+	struct rte_vhost_resubmit_info *resubmit_inflight;
+};
+
 struct rte_vhost_vring {
 	union {
 		struct vring_desc *desc;
lib/librte_vhost/vhost.c +28 -1
index 981837b5d..f8660edbf 100644
@@ -242,6 +242,31 @@ cleanup_vq(struct vhost_virtqueue *vq, int destroy)
 		close(vq->kickfd);
 }
 
+void
+cleanup_vq_inflight(struct virtio_net *dev, struct vhost_virtqueue *vq)
+{
+	if (!(dev->protocol_features &
+	    (1ULL << VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD)))
+		return;
+
+	if (vq_is_packed(dev)) {
+		if (vq->inflight_packed)
+			vq->inflight_packed = NULL;
+	} else {
+		if (vq->inflight_split)
+			vq->inflight_split = NULL;
+	}
+
+	if (vq->resubmit_inflight) {
+		if (vq->resubmit_inflight->resubmit_list) {
+			free(vq->resubmit_inflight->resubmit_list);
+			vq->resubmit_inflight->resubmit_list = NULL;
+		}
+		free(vq->resubmit_inflight);
+		vq->resubmit_inflight = NULL;
+	}
+}
+
 /*
  * Unmap any memory, close any file descriptors and
  * free any memory owned by a device.

@@ -253,8 +278,10 @@ cleanup_device(struct virtio_net *dev, int destroy)
 
 	vhost_backend_cleanup(dev);
 
-	for (i = 0; i < dev->nr_vring; i++)
+	for (i = 0; i < dev->nr_vring; i++) {
 		cleanup_vq(dev->virtqueue[i], destroy);
+		cleanup_vq_inflight(dev, dev->virtqueue[i]);
+	}
 }
 
 void
lib/librte_vhost/vhost.h +9 -0
index d67ba849a..ab95999c4 100644
@@ -128,6 +128,14 @@ struct vhost_virtqueue {
 	/* Physical address of used ring, for logging */
 	uint64_t		log_guest_addr;
 
+	/* inflight share memory info */
+	union {
+		struct rte_vhost_inflight_info_split *inflight_split;
+		struct rte_vhost_inflight_info_packed *inflight_packed;
+	};
+	struct rte_vhost_resubmit_info *resubmit_inflight;
+	uint64_t		global_counter;
+
 	uint16_t		nr_zmbuf;
 	uint16_t		zmbuf_size;
 	uint16_t		last_zmbuf_idx;

@@ -474,6 +482,7 @@ void vhost_destroy_device(int);
 void vhost_destroy_device_notify(struct virtio_net *dev);
 
 void cleanup_vq(struct vhost_virtqueue *vq, int destroy);
+void cleanup_vq_inflight(struct virtio_net *dev, struct vhost_virtqueue *vq);
 void free_vq(struct virtio_net *dev, struct vhost_virtqueue *vq);
 
 int alloc_vring_queue(struct virtio_net *dev, uint32_t vring_idx);
lib/librte_vhost/vhost_user.c +215 -2

249 lines not on this page · raw message

Signature · 1 line
2.17.2
author
#17 lore raw

PATCH v10 6/9 vhost: add the APIs to operate inflight ring

In reply to Jin Yu

This patch introduces three APIs to operate the inflight ring. Three APIs are set, set last and clear. It includes split and packed ring.

Signed-off-by Lin Li <[email protected]>
Signed-off-by Xun Ni <[email protected]>
Signed-off-by Yu Zhang <[email protected]>
Signed-off-by Jin Yu <[email protected]>
---
 lib/librte_vhost/rte_vhost.h           | 116 +++++++++++
 lib/librte_vhost/rte_vhost_version.map |   6 +
 lib/librte_vhost/vhost.c               | 273 +++++++++++++++++++++++++
 3 files changed, 395 insertions(+)
lib/librte_vhost/rte_vhost.h +116 -0
index 95e4d720e..15d7e67cd 100644
@@ -693,6 +693,122 @@ int rte_vhost_get_mem_table(int vid, struct rte_vhost_memory **mem);
 int rte_vhost_get_vhost_vring(int vid, uint16_t vring_idx,
 			      struct rte_vhost_vring *vring);
 
+/**
+ * Set split inflight descriptor.
+ *
+ * This function save descriptors that has been comsumed in available
+ * ring
+ *
+ * @param vid
+ *  vhost device ID
+ * @param vring_idx
+ *  vring index
+ * @param idx
+ *  inflight entry index
+ * @return
+ *  0 on success, -1 on failure
+ */
+__rte_experimental
+int
+rte_vhost_set_inflight_desc_split(int vid, uint16_t vring_idx,
+	uint16_t idx);
+
+/**
+ * Set packed inflight descriptor and get corresponding inflight entry
+ *
+ * This function save descriptors that has been comsumed
+ *
+ * @param vid
+ *  vhost device ID
+ * @param vring_idx
+ *  vring index
+ * @param head
+ *  head of descriptors
+ * @param last
+ *  last of descriptors
+ * @param inflight_entry
+ *  corresponding inflight entry
+ * @return
+ *  0 on success, -1 on failure
+ */
+__rte_experimental
+int
+rte_vhost_set_inflight_desc_packed(int vid, uint16_t vring_idx,
+	uint16_t head, uint16_t last, uint16_t *inflight_entry);
+
+/**
+ * Save the head of list that the last batch of used descriptors.
+ *
+ * @param vid
+ *  vhost device ID
+ * @param vring_idx
+ *  vring index
+ * @param idx
+ *  descriptor entry index
+ * @return
+ *  0 on success, -1 on failure
+ */
+__rte_experimental
+int
+rte_vhost_set_last_inflight_io_split(int vid,
+	uint16_t vring_idx, uint16_t idx);
+
+/**
+ * Update the inflight free_head, used_idx and used_wrap_counter.
+ *
+ * This function will update status first before updating descriptors
+ * to used
+ *
+ * @param vid
+ *  vhost device ID
+ * @param vring_idx
+ *  vring index
+ * @param head
+ *  head of descriptors
+ * @return
+ *  0 on success, -1 on failure
+ */
+__rte_experimental
+int
+rte_vhost_set_last_inflight_io_packed(int vid,
+	uint16_t vring_idx, uint16_t head);
+
+/**
+ * Clear the split inflight status.
+ *
+ * @param vid
+ *  vhost device ID
+ * @param vring_idx
+ *  vring index
+ * @param last_used_idx
+ *  last used idx of used ring
+ * @param idx
+ *  inflight entry index
+ * @return
+ *  0 on success, -1 on failure
+ */
+__rte_experimental
+int
+rte_vhost_clr_inflight_desc_split(int vid, uint16_t vring_idx,
+	uint16_t last_used_idx, uint16_t idx);
+
+/**
+ * Clear the packed inflight status.
+ *
+ * @param vid
+ *  vhost device ID
+ * @param vring_idx
+ *  vring index
+ * @param head
+ *  inflight entry index
+ * @return
+ *  0 on success, -1 on failure
+ */
+__rte_experimental
+int
+rte_vhost_clr_inflight_desc_packed(int vid, uint16_t vring_idx,
+	uint16_t head);
+
 /**
  * Notify the guest that used descriptors have been added to the vring.  This
  * function acts as a memory barrier.
lib/librte_vhost/rte_vhost_version.map +6 -0
index 5f1d4a75c..bc70bfaa5 100644
@@ -87,4 +87,10 @@ EXPERIMENTAL {
 	rte_vdpa_relay_vring_used;
 	rte_vhost_extern_callback_register;
 	rte_vhost_driver_set_protocol_features;
+	rte_vhost_set_inflight_desc_split;
+	rte_vhost_set_inflight_desc_packed;
+	rte_vhost_set_last_inflight_io_split;
+	rte_vhost_set_last_inflight_io_packed;
+	rte_vhost_clr_inflight_desc_split;
+	rte_vhost_clr_inflight_desc_packed;
 };
lib/librte_vhost/vhost.c +273 -0

279 lines not on this page · raw message

Signature · 1 line
2.17.2
author
#18 lore raw

PATCH v10 7/9 vhost: add APIs for user getting inflight ring

In reply to Jin Yu

This patch introduces two APIs. one is for getting inflgiht ring and the other is for getting base.

Signed-off-by Lin Li <[email protected]>
Signed-off-by Xun Ni <[email protected]>
Signed-off-by Yu Zhang <[email protected]>
Signed-off-by Jin Yu <[email protected]>
---
 lib/librte_vhost/rte_vhost.h           | 40 +++++++++++++++++
 lib/librte_vhost/rte_vhost_version.map |  2 +
 lib/librte_vhost/vhost.c               | 61 ++++++++++++++++++++++++++
 3 files changed, 103 insertions(+)
lib/librte_vhost/rte_vhost.h +40 -0
index 15d7e67cd..1e1e13d71 100644
@@ -693,6 +693,23 @@ int rte_vhost_get_mem_table(int vid, struct rte_vhost_memory **mem);
 int rte_vhost_get_vhost_vring(int vid, uint16_t vring_idx,
 			      struct rte_vhost_vring *vring);
 
+/**
+ * Get guest inflight vring info, including inflight ring and resubmit list.
+ *
+ * @param vid
+ *  vhost device ID
+ * @param vring_idx
+ *  vring index
+ * @param vring
+ *  the structure to hold the requested inflight vring info
+ * @return
+ *  0 on success, -1 on failure
+ */
+__rte_experimental
+int
+rte_vhost_get_vhost_ring_inflight(int vid, uint16_t vring_idx,
+	struct rte_vhost_ring_inflight *vring);
+
 /**
  * Set split inflight descriptor.
  *

@@ -867,6 +884,29 @@ int __rte_experimental
 rte_vhost_get_vring_base(int vid, uint16_t queue_id,
 		uint16_t *last_avail_idx, uint16_t *last_used_idx);
 
+/**
+ * Get last_avail/last_used of the vhost virtqueue
+ *
+ * This function is designed for the reconnection and it's specific for
+ * the packed ring as we can get the two parameters from the inflight
+ * queueregion
+ *
+ * @param vid
+ *  vhost device ID
+ * @param queue_id
+ *  vhost queue index
+ * @param last_avail_idx
+ *  vhost last_avail_idx to get
+ * @param last_used_idx
+ *  vhost last_used_idx to get
+ * @return
+ *  0 on success, -1 on failure
+ */
+__rte_experimental
+int
+rte_vhost_get_vring_base_from_inflight(int vid,
+	uint16_t queue_id, uint16_t *last_avail_idx, uint16_t *last_used_idx);
+
 /**
  * Set last_avail/used_idx of the vhost virtqueue
  *
lib/librte_vhost/rte_vhost_version.map +2 -0
index bc70bfaa5..ce517b127 100644
@@ -93,4 +93,6 @@ EXPERIMENTAL {
 	rte_vhost_set_last_inflight_io_packed;
 	rte_vhost_clr_inflight_desc_split;
 	rte_vhost_clr_inflight_desc_packed;
+	rte_vhost_get_vhost_ring_inflight;
+	rte_vhost_get_vring_base_from_inflight;
 };
lib/librte_vhost/vhost.c +61 -0

73 lines not on this page · raw message

Signature · 1 line
2.17.2
author
#19 lore raw

PATCH v10 8/9 vhost: add vring functions packed ring support

In reply to Jin Yu

This patch add packed ring support in two APIs so user can get the packed ring`.

Signed-off-by Lin Li <[email protected]>
Signed-off-by Xun Ni <[email protected]>
Signed-off-by Yu Zhang <[email protected]>
Signed-off-by Jin Yu <[email protected]>
---
 lib/librte_vhost/vhost.c | 68 +++++++++++++++++++++++++++++-----------
 1 file changed, 49 insertions(+), 19 deletions(-)
lib/librte_vhost/vhost.c +49 -19
index f7ed37261..fd3445207 100644
@@ -771,9 +771,15 @@ rte_vhost_get_vhost_vring(int vid, uint16_t vring_idx,
 	if (!vq)
 		return -1;
 
-	vring->desc  = vq->desc;
-	vring->avail = vq->avail;
-	vring->used  = vq->used;
+	if (vq_is_packed(dev)) {
+		vring->desc_packed = vq->desc_packed;
+		vring->driver_event = vq->driver_event;
+		vring->device_event = vq->device_event;
+	} else {
+		vring->desc = vq->desc;
+		vring->avail = vq->avail;
+		vring->used = vq->used;
+	}
 	vring->log_guest_addr  = vq->log_guest_addr;
 
 	vring->callfd  = vq->callfd;

@@ -1274,13 +1280,51 @@ int rte_vhost_get_log_base(int vid, uint64_t *log_base,
 int rte_vhost_get_vring_base(int vid, uint16_t queue_id,
 		uint16_t *last_avail_idx, uint16_t *last_used_idx)
 {
+	struct vhost_virtqueue *vq;
 	struct virtio_net *dev = get_device(vid);
 
 	if (dev == NULL || last_avail_idx == NULL || last_used_idx == NULL)
 		return -1;
 
-	*last_avail_idx = dev->virtqueue[queue_id]->last_avail_idx;
-	*last_used_idx = dev->virtqueue[queue_id]->last_used_idx;
+	vq = dev->virtqueue[queue_id];
+	if (!vq)
+		return -1;
+
+	if (vq_is_packed(dev)) {
+		*last_avail_idx = (vq->avail_wrap_counter << 15) |
+				  vq->last_avail_idx;
+		*last_used_idx = (vq->used_wrap_counter << 15) |
+				 vq->last_used_idx;
+	} else {
+		*last_avail_idx = vq->last_avail_idx;
+		*last_used_idx = vq->last_used_idx;
+	}
+
+	return 0;
+}
+
+int rte_vhost_set_vring_base(int vid, uint16_t queue_id,
+		uint16_t last_avail_idx, uint16_t last_used_idx)
+{
+	struct vhost_virtqueue *vq;
+	struct virtio_net *dev = get_device(vid);
+
+	if (!dev)
+		return -1;
+
+	vq = dev->virtqueue[queue_id];
+	if (!vq)
+		return -1;
+
+	if (vq_is_packed(dev)) {
+		vq->last_avail_idx = last_avail_idx & 0x7fff;
+		vq->avail_wrap_counter = !!(last_avail_idx & (1 << 15));
+		vq->last_used_idx = last_used_idx & 0x7fff;
+		vq->used_wrap_counter = !!(last_used_idx & (1 << 15));
+	} else {
+		vq->last_avail_idx = last_avail_idx;
+		vq->last_used_idx = last_used_idx;
+	}
 
 	return 0;
 }

@@ -1311,20 +1355,6 @@ rte_vhost_get_vring_base_from_inflight(int vid,
 	return 0;
 }
 
-int rte_vhost_set_vring_base(int vid, uint16_t queue_id,
-		uint16_t last_avail_idx, uint16_t last_used_idx)
-{
-	struct virtio_net *dev = get_device(vid);
-
-	if (!dev)
-		return -1;
-
-	dev->virtqueue[queue_id]->last_avail_idx = last_avail_idx;
-	dev->virtqueue[queue_id]->last_used_idx = last_used_idx;
-
-	return 0;
-}
-
 int rte_vhost_extern_callback_register(int vid,
 		struct rte_vhost_user_extern_ops const * const ops, void *ctx)
 {
Signature · 1 line
2.17.2
author
#20 lore raw

PATCH v10 9/9 vhost: add vhost-user-blk example which support inflight

In reply to Jin Yu

A vhost-user-blk example that support inflight feature. It uses the new APIs that introduced in the first patch, so it can show how these APIs work to support inflight feature.

Signed-off-by Jin Yu <[email protected]>

---
V1 - add the case.
V2 - add the rte_vhost prefix.
V3 - add packed ring support

---
 examples/vhost_blk/Makefile           |   68 ++
 examples/vhost_blk/blk.c              |  125 +++
 examples/vhost_blk/blk_spec.h         |   95 +++
 examples/vhost_blk/meson.build        |   21 +
 examples/vhost_blk/vhost_blk.c        | 1092 +++++++++++++++++++++++++
 examples/vhost_blk/vhost_blk.h        |  128 +++
 examples/vhost_blk/vhost_blk_compat.c |  195 +++++
 7 files changed, 1724 insertions(+)
 create mode 100644 examples/vhost_blk/Makefile
 create mode 100644 examples/vhost_blk/blk.c
 create mode 100644 examples/vhost_blk/blk_spec.h
 create mode 100644 examples/vhost_blk/meson.build
 create mode 100644 examples/vhost_blk/vhost_blk.c
 create mode 100644 examples/vhost_blk/vhost_blk.h
 create mode 100644 examples/vhost_blk/vhost_blk_compat.c
examples/vhost_blk/Makefile new file +68 -0
new file mode 100644
index 000000000..a10a90071
@@ -0,0 +1,68 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2010-2014 Intel Corporation
+
+# binary name
+APP = vhost-blk
+
+# all source are stored in SRCS-y
+SRCS-y := blk.c vhost_blk.c vhost_blk_compat.c
+
+# Build using pkg-config variables if possible
+$(shell pkg-config --exists libdpdk)
+ifeq ($(.SHELLSTATUS),0)
+
+all: shared
+.PHONY: shared static
+shared: build/$(APP)-shared
+	ln -sf $(APP)-shared build/$(APP)
+static: build/$(APP)-static
+	ln -sf $(APP)-static build/$(APP)
+
+LDFLAGS += -pthread
+
+PC_FILE := $(shell pkg-config --path libdpdk)
+CFLAGS += -O3 $(shell pkg-config --cflags libdpdk)
+LDFLAGS_SHARED = $(shell pkg-config --libs libdpdk)
+LDFLAGS_STATIC = -Wl,-Bstatic $(shell pkg-config --static --libs libdpdk)
+
+CFLAGS += -DALLOW_EXPERIMENTAL_API
+
+build/$(APP)-shared: $(SRCS-y) Makefile $(PC_FILE) | build
+	$(CC) $(CFLAGS) $(SRCS-y) -o $@ $(LDFLAGS) $(LDFLAGS_SHARED)
+
+build/$(APP)-static: $(SRCS-y) Makefile $(PC_FILE) | build
+	$(CC) $(CFLAGS) $(SRCS-y) -o $@ $(LDFLAGS) $(LDFLAGS_STATIC)
+
+build:
+	@mkdir -p $@
+
+.PHONY: clean
+clean:
+	rm -f build/$(APP) build/$(APP)-static build/$(APP)-shared
+	test -d build && rmdir -p build || true
+
+else # Build using legacy build system
+
+ifeq ($(RTE_SDK),)
+$(error "Please define RTE_SDK environment variable")
+endif
+
+# Default target, detect a build directory, by looking for a path with a .config
+RTE_TARGET ?= $(notdir $(abspath $(dir $(firstword $(wildcard $(RTE_SDK)/*/.config)))))
+
+include $(RTE_SDK)/mk/rte.vars.mk
+
+ifneq ($(CONFIG_RTE_EXEC_ENV_LINUX),y)
+$(info This application can only operate in a linux environment, \
+please change the definition of the RTE_TARGET environment variable)
+all:
+else
+
+CFLAGS += -DALLOW_EXPERIMENTAL_API
+CFLAGS += -O2 -D_FILE_OFFSET_BITS=64
+CFLAGS += $(WERROR_FLAGS)
+
+include $(RTE_SDK)/mk/rte.extapp.mk
+
+endif
+endif
examples/vhost_blk/blk.c new file +125 -0

125 lines not on this page · raw message

examples/vhost_blk/blk_spec.h new file +95 -0

95 lines not on this page · raw message

examples/vhost_blk/meson.build new file +21 -0
new file mode 100644
index 000000000..857367192
@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2017 Intel Corporation
+
+# meson file, for building this example as part of a main DPDK build.
+#
+# To build this example as a standalone application with an already-installed
+# DPDK instance, use 'make'
+
+if not is_linux
+	build = false
+endif
+
+if not cc.has_header('linux/virtio_blk.h')
+	build = false
+endif
+
+deps += 'vhost'
+allow_experimental_apis = true
+sources = files(
+	'blk.c', 'vhost_blk.c', 'vhost_blk_compat.c'
+)
examples/vhost_blk/vhost_blk.c new file +1092 -0

1,092 lines not on this page · raw message

examples/vhost_blk/vhost_blk.h new file +128 -0

128 lines not on this page · raw message

examples/vhost_blk/vhost_blk_compat.c new file +195 -0

195 lines not on this page · raw message

Signature · 1 line
2.17.2