Skip to contentSkip to conversation

Drop vhost async (DMA-accelerated) datapath

RFC In review David Marchand 2 participants 43 messages Jul 23 – Oct 15 Arm/Amlogic Meson SoC support

lore
Share & tools
lore
#0 lore raw

cover Drop vhost async (DMA-accelerated) datapath

The integration of this feature in OVS has been postponed following feedback how the current API forced the complexity on the application side. There is no contributor working on making those changes.

The feature has no other identified opensource consumer.

On the other hand, this feature has been left unattended for some years now while the "normal" datapath is actively maintained.
It is highly likely the async datapath code, which never underwent a stabilisation phase, is riddled with bugs.

Given the craziness around finding security bugs with AI, and since the vhost library is a good target, I propose to drop this feature and reduce the library attack surface.

Signature · 29 lines
David Marchand

David Marchand (3):
  examples: stop using vhost async datapath
  vhost: refuse async datapath
  vhost: drop async datapath

 doc/guides/prog_guide/vhost_lib.rst    |  151 +-
 doc/guides/rel_notes/release_26_11.rst |   20 +
 examples/vhost/Makefile                |    2 -
 examples/vhost/main.c                  |  436 +---
 examples/vhost/main.h                  |   21 +-
 examples/vhost/meson.build             |    2 -
 examples/vhost_crypto/Makefile         |    1 -
 examples/vhost_crypto/main.c           |    3 +-
 examples/vhost_crypto/meson.build      |    1 -
 lib/vhost/meson.build                  |    3 +-
 lib/vhost/rte_vhost.h                  |    2 +-
 lib/vhost/rte_vhost_async.h            |  293 ---
 lib/vhost/socket.c                     |   27 +-
 lib/vhost/vhost.c                      |  434 ----
 lib/vhost/vhost.h                      |  115 -
 lib/vhost/vhost_user.c                 |  215 +-
 lib/vhost/virtio_net.c                 | 3275 +++++-------------------
 17 files changed, 708 insertions(+), 4293 deletions(-)
 delete mode 100644 lib/vhost/rte_vhost_async.h

-- 
2.54.0
#1 lore raw

RFC 1/3 examples: stop using vhost async datapath

Stop using vhost async as this feature will be removed in a next commit. The vhost-crypto example was requesting async copy for no identified reason.

Thanks to this, we can drop use of experimental api in those examples.

---
 examples/vhost/Makefile           |   2 -
 examples/vhost/main.c             | 436 +-----------------------------
 examples/vhost/main.h             |  21 +-
 examples/vhost/meson.build        |   2 -
 examples/vhost_crypto/Makefile    |   1 -
 examples/vhost_crypto/main.c      |   3 +-
 examples/vhost_crypto/meson.build |   1 -
 7 files changed, 13 insertions(+), 453 deletions(-)
examples/vhost/Makefile +0 -2
index 5b3cea0778..6e0114d094 100644
@@ -28,8 +28,6 @@ CFLAGS += -O3 $(shell $(PKGCONF) --cflags libdpdk)
 LDFLAGS_SHARED = $(shell $(PKGCONF) --libs libdpdk)
 LDFLAGS_STATIC = $(shell $(PKGCONF) --static --libs libdpdk)
 
-CFLAGS += -DALLOW_EXPERIMENTAL_API
-
 build/$(APP)-shared: $(SRCS-y) Makefile $(PC_FILE) | build
 	$(CC) $(CFLAGS) $(SRCS-y) -o $@ $(LDFLAGS) $(LDFLAGS_SHARED)
 
examples/vhost/main.c +10 -426

603 lines not on this page · raw message

examples/vhost/main.h +2 -19
index c986cbc5a9..3cf6bd7f07 100644
@@ -8,7 +8,6 @@
 #include <sys/queue.h>
 
 #include <rte_ether.h>
-#include <rte_pci.h>
 
 /* Macros for printing using RTE_LOG */
 #define RTE_LOGTYPE_VHOST_CONFIG RTE_LOGTYPE_USER1
@@ -92,17 +91,6 @@ struct lcore_info {
 	struct vhost_dev_tailq_list vdev_list;
 };
 
-struct dma_info {
-	struct rte_pci_addr addr;
-	int16_t dev_id;
-	bool async_enabled;
-};
-
-struct dma_for_vhost {
-	struct dma_info dmas[RTE_MAX_QUEUES_PER_PORT * 2];
-	uint32_t async_flag;
-};
-
 /* we implement non-extra virtio net features */
 #define VIRTIO_NET_FEATURES	0
 
@@ -116,14 +104,9 @@ uint16_t builtin_enqueue_pkts(struct vhost_dev *dev, uint16_t queue_id,
 uint16_t builtin_dequeue_pkts(struct vhost_dev *dev, uint16_t queue_id,
 			struct rte_mempool *mbuf_pool,
 			struct rte_mbuf **pkts, uint16_t count);
-uint16_t sync_enqueue_pkts(struct vhost_dev *dev, uint16_t queue_id,
-			 struct rte_mbuf **pkts, uint32_t count);
-uint16_t sync_dequeue_pkts(struct vhost_dev *dev, uint16_t queue_id,
-			struct rte_mempool *mbuf_pool,
-			struct rte_mbuf **pkts, uint16_t count);
-uint16_t async_enqueue_pkts(struct vhost_dev *dev, uint16_t queue_id,
+uint16_t enqueue_pkts(struct vhost_dev *dev, uint16_t queue_id,
 			 struct rte_mbuf **pkts, uint32_t count);
-uint16_t async_dequeue_pkts(struct vhost_dev *dev, uint16_t queue_id,
+uint16_t dequeue_pkts(struct vhost_dev *dev, uint16_t queue_id,
 			struct rte_mempool *mbuf_pool,
 			struct rte_mbuf **pkts, uint16_t count);
 #endif /* _MAIN_H_ */
examples/vhost/meson.build +0 -2
index e938be8f45..a04852bb2f 100644
@@ -12,8 +12,6 @@ if not is_linux
 endif
 
 deps += 'vhost'
-deps += 'dmadev'
-allow_experimental_apis = true
 sources = files(
         'main.c',
         'virtio_net.c',
examples/vhost_crypto/Makefile +0 -1
index cc7f2abb90..130953c38e 100644
@@ -6,7 +6,6 @@ APP = vhost-crypto
 
 # all source are stored in SRCS-y
 SRCS-y := main.c
-CFLAGS += -DALLOW_EXPERIMENTAL_API
 
 PKGCONF ?= pkg-config
 
examples/vhost_crypto/main.c +1 -2
index 8bdfc40c4b..e196221548 100644
@@ -622,8 +622,7 @@ main(int argc, char *argv[])
 		}
 
 		for (j = 0; j < lo->nb_sockets; j++) {
-			ret = rte_vhost_driver_register(lo->socket_files[j],
-				RTE_VHOST_USER_ASYNC_COPY);
+			ret = rte_vhost_driver_register(lo->socket_files[j], 0);
 			if (ret < 0) {
 				RTE_LOG(ERR, USER1, "socket %s already exists\n",
 					lo->socket_files[j]);
examples/vhost_crypto/meson.build +0 -1
index 1c294c286f..47c8fa829f 100644
@@ -6,7 +6,6 @@
 # To build this example as a standalone application with an already-installed
 # DPDK instance, use 'make'
 
-allow_experimental_apis = true
 deps += ['vhost', 'cryptodev']
 sources = files(
         'main.c',
Signature · 1 line
2.54.0
#2 lore raw

Re: [RFC 1/3] examples: stop using vhost async datapath

Hello Maxime,

Quoted 4 lines · David Marchand

Stop using vhost async as this feature will be removed in a next commit. The vhost-crypto example was requesting async copy for no identified reason.

Well, unfortunately, this was the tree hiding the forest... I'll need more changes to avoid breaking vhost crypto zero copy stuff.

My understanding is that a call to rte_vhost_crypto_set_zero_copy() could be used to detect guest pages mapping is needed.. does it look ok to you?

Signature · 1 line
David Marchand
#3 lore raw

RFC 2/3 vhost: refuse async datapath

In reply to David Marchand

As a first step for dropping the whole feature, refuse initialisation when RTE_VHOST_USER_ASYNC_COPY is passed.

This is mainly make more visible those changes and isolate them from dropping all the code in the next commit.

---
 doc/guides/prog_guide/vhost_lib.rst    |  15 --
 doc/guides/rel_notes/release_26_11.rst |   7 +
 lib/vhost/rte_vhost.h                  |   2 +-
 lib/vhost/socket.c                     |  27 +---
 lib/vhost/vhost_user.c                 | 210 +------------------------
 5 files changed, 17 insertions(+), 244 deletions(-)
doc/guides/prog_guide/vhost_lib.rst +0 -15
index 345a621716..25103eb49d 100644
@@ -103,21 +103,6 @@ The following is an overview of some key Vhost API functions:
 
     It is disabled by default.
 
-  - ``RTE_VHOST_USER_ASYNC_COPY``
-
-    Asynchronous data path will be enabled when this flag is set. Async
-    data path allows applications to enable DMA acceleration for vhost
-    queues. Vhost leverages the registered DMA channels to free CPU from
-    memory copy operations in data path. A set of async data path APIs are
-    defined for DPDK applications to make use of the async capability. Only
-    packets enqueued/dequeued by async APIs are processed through the async
-    data path.
-
-    Currently this feature is only implemented on split ring enqueue data
-    path.
-
-    It is disabled by default.
-
   - ``RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS``
 
     Since v16.04, the vhost library forwards checksum and gso requests for
doc/guides/rel_notes/release_26_11.rst +7 -0
index 938617ca75..b44d8cc4ad 100644
@@ -68,6 +68,13 @@ Removed Items
    Also, make sure to start the actual text at the margin.
    =======================================================
 
+* **Removed vhost async (DMA-accelerated) data path.**
+
+  The experimental async data path APIs have been removed from the vhost library.
+  The following functions and flag are no longer available:
+
+  - ``RTE_VHOST_USER_ASYNC_COPY``
+
 
 API Changes
 -----------
lib/vhost/rte_vhost.h +1 -1
index a7f9700538..e0789807d4 100644
@@ -38,7 +38,7 @@ extern "C" {
 #define RTE_VHOST_USER_EXTBUF_SUPPORT	(1ULL << 5)
 /* support only linear buffers (no chained mbufs) */
 #define RTE_VHOST_USER_LINEARBUF_SUPPORT	(1ULL << 6)
-#define RTE_VHOST_USER_ASYNC_COPY	(1ULL << 7)
+/* Bit 7 was RTE_VHOST_USER_ASYNC_COPY, now unsupported */
 #define RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS	(1ULL << 8)
 #define RTE_VHOST_USER_NET_STATS_ENABLE	(1ULL << 9)
 #define RTE_VHOST_USER_ASYNC_CONNECT	(1ULL << 10)
lib/vhost/socket.c +6 -21
index 70e582a18d..4f5f44d0a5 100644
@@ -210,7 +210,6 @@ vhost_user_add_connection(int fd, struct vhost_user_socket *vsocket)
 	size_t size;
 	struct vhost_user_connection *conn;
 	int ret;
-	struct virtio_net *dev;
 
 	if (vsocket == NULL)
 		return;
@@ -241,13 +240,6 @@ vhost_user_add_connection(int fd, struct vhost_user_socket *vsocket)
 	if (vsocket->linearbuf)
 		vhost_enable_linearbuf(vid);
 
-	if (vsocket->async_copy) {
-		dev = get_device(vid);
-
-		if (dev)
-			dev->async_copy = 1;
-	}
-
 	VHOST_CONFIG_LOG(vsocket->path, INFO, "new device, handle is %d", vid);
 
 	if (vsocket->notify_ops->new_connection) {
@@ -911,6 +903,11 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
 	if (!path)
 		return -1;
 
+	if (flags & (1ULL << 7)) {
+		VHOST_CONFIG_LOG(path, ERR, "async copy flag (bit 7) is no longer supported");
+		return -1;
+	}
+
 	pthread_mutex_lock(&vhost_user.mutex);
 
 	if (vhost_user.vsocket_cnt == MAX_VHOST_SOCKET) {
@@ -938,7 +935,7 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
 	vsocket->max_queue_pairs = VHOST_MAX_QUEUE_PAIRS;
 	vsocket->extbuf = flags & RTE_VHOST_USER_EXTBUF_SUPPORT;
 	vsocket->linearbuf = flags & RTE_VHOST_USER_LINEARBUF_SUPPORT;
-	vsocket->async_copy = flags & RTE_VHOST_USER_ASYNC_COPY;
+	vsocket->async_copy = false;
 	vsocket->net_compliant_ol_flags = flags & RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS;
 	vsocket->stats_enabled = flags & RTE_VHOST_USER_NET_STATS_ENABLE;
 	vsocket->async_connect = flags & RTE_VHOST_USER_ASYNC_CONNECT;
@@ -947,12 +944,6 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
 	else
 		vsocket->iommu_support = flags & RTE_VHOST_USER_IOMMU_SUPPORT;
 
-	if (vsocket->async_copy && (vsocket->iommu_support ||
-				(flags & RTE_VHOST_USER_POSTCOPY_SUPPORT))) {
-		VHOST_CONFIG_LOG(path, ERR, "async copy with IOMMU or post-copy not supported");
-		goto out_mutex;
-	}
-
 	/*
 	 * Set the supported features correctly for the builtin vhost-user
 	 * net driver.
@@ -975,12 +966,6 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
 		vsocket->protocol_features  = VHOST_USER_PROTOCOL_FEATURES;
 	}
 
-	if (vsocket->async_copy) {
-		vsocket->supported_features &= ~(1ULL << VHOST_F_LOG_ALL);
-		vsocket->features &= ~(1ULL << VHOST_F_LOG_ALL);
-		VHOST_CONFIG_LOG(path, INFO, "logging feature is disabled in async copy mode");
-	}
-
 	/*
 	 * We'll not be able to receive a buffer from guest in linear mode
 	 * without external buffer if it will not fit in a single mbuf, which is
lib/vhost/vhost_user.c +3 -207

287 lines not on this page · raw message

Signature · 1 line
2.54.0
#4 lore raw

RFC 3/3 vhost: drop async datapath

In reply to David Marchand

All the API related to this feature is experimental, allowing us by the project policy to drop the feature in one go.

---
 doc/guides/prog_guide/vhost_lib.rst    |  136 +-
 doc/guides/rel_notes/release_26_11.rst |   13 +
 lib/vhost/meson.build                  |    3 +-
 lib/vhost/rte_vhost_async.h            |  293 ---
 lib/vhost/socket.c                     |    2 -
 lib/vhost/vhost.c                      |  434 ----
 lib/vhost/vhost.h                      |  115 -
 lib/vhost/vhost_user.c                 |    5 -
 lib/vhost/virtio_net.c                 | 3275 +++++-------------------
 9 files changed, 679 insertions(+), 3597 deletions(-)
 delete mode 100644 lib/vhost/rte_vhost_async.h
doc/guides/prog_guide/vhost_lib.rst +5 -131
index 25103eb49d..d1596d5e0d 100644
@@ -212,76 +212,6 @@ The following is an overview of some key Vhost API functions:
 
   Enable or disable zero copy feature of the vhost crypto backend.
 
-* ``rte_vhost_async_dma_configure(dma_id, vchan_id)``
-
-  Tell vhost which DMA vChannel is going to use. This function needs to
-  be called before register async data-path for vring.
-
-* ``rte_vhost_async_channel_register(vid, queue_id)``
-
-  Register async DMA acceleration for a vhost queue after vring is enabled.
-
-* ``rte_vhost_async_channel_register_thread_unsafe(vid, queue_id)``
-
-  Register async DMA acceleration for a vhost queue without performing
-  any locking.
-
-  This function is only safe to call in vhost callback functions
-  (i.e., struct rte_vhost_device_ops).
-
-* ``rte_vhost_async_channel_unregister(vid, queue_id)``
-
-  Unregister the async DMA acceleration from a vhost queue.
-  Unregistration will fail, if the vhost queue has in-flight
-  packets that are not completed.
-
-  Unregister async DMA acceleration in vring_state_changed() may
-  fail, as this API tries to acquire the spinlock of vhost
-  queue. The recommended way is to unregister async copy
-  devices for all vhost queues in destroy_device(), when a
-  virtio device is paused or shut down.
-
-* ``rte_vhost_async_channel_unregister_thread_unsafe(vid, queue_id)``
-
-  Unregister async DMA acceleration for a vhost queue without performing
-  any locking.
-
-  This function is only safe to call in vhost callback functions
-  (i.e., struct rte_vhost_device_ops).
-
-* ``rte_vhost_submit_enqueue_burst(vid, queue_id, pkts, count, dma_id, vchan_id)``
-
-  Submit an enqueue request to transmit ``count`` packets from host to guest
-  by async data path. Applications must not free the packets submitted for
-  enqueue until the packets are completed.
-
-* ``rte_vhost_poll_enqueue_completed(vid, queue_id, pkts, count, dma_id, vchan_id)``
-
-  Poll enqueue completion status from async data path. Completed packets
-  are returned to applications through ``pkts``.
-
-* ``rte_vhost_async_get_inflight(vid, queue_id)``
-
-  This function returns the amount of in-flight packets for the vhost
-  queue using async acceleration.
-
- * ``rte_vhost_async_get_inflight_thread_unsafe(vid, queue_id)``
-
-  Get the number of inflight packets for a vhost queue without performing
-  any locking. It should only be used within the vhost ops, which already
-  holds the lock.
-
-* ``rte_vhost_clear_queue_thread_unsafe(vid, queue_id, **pkts, count, dma_id, vchan_id)``
-
-  Clear in-flight packets which are submitted to async channel in vhost
-  async data path without performing locking on virtqueue. Completed
-  packets are returned to applications through ``pkts``.
-
-* ``rte_vhost_clear_queue(vid, queue_id, **pkts, count, dma_id, vchan_id)``
-
-  Clear in-flight packets which are submitted to async channel in vhost async data
-  path. Completed packets are returned to applications through ``pkts``.
-
 * ``rte_vhost_vring_call_nonblock(int vid, uint16_t vring_idx)``
 
   Notify the guest that used descriptors have been added to the vring. This function
@@ -303,22 +233,11 @@ The following is an overview of some key Vhost API functions:
   This function resets the queue statistics. It requires statistics
   collection to be enabled at registration time.
 
-* ``rte_vhost_async_try_dequeue_burst(vid, queue_id, mbuf_pool, pkts, count,
-  nr_inflight, dma_id, vchan_id)``
-
-  Receive ``count`` packets from guest to host in async data path,
-  and store them at ``pkts``.
-
 * ``rte_vhost_driver_get_vdpa_dev_type(path, type)``
 
   Get device type of vDPA device, such as VDPA_DEVICE_TYPE_NET,
   VDPA_DEVICE_TYPE_BLK.
 
-* ``rte_vhost_async_dma_unconfigure(dma_id, vchan_id)``
-
-  Clean up a DMA vChannel after use is finished. After this function is called,
-  the specified DMA vChannel should no longer be used by the Vhost library.
-
 * ``rte_vhost_notify_guest(int vid, uint16_t queue_id)``
 
   Inject the offloaded interrupt received by the 'guest_notify' callback,
@@ -387,16 +306,11 @@ Guest memory requirement
 
 * Memory pre-allocation
 
-  For non-async data path guest memory pre-allocation is not a
-  must but can help save memory. To do this we can add option
-  ``-mem-prealloc`` when starting QEMU, or we can lock all memory at vhost
-  side which will force memory to be allocated when it calls mmap
-  (option --mlockall in ovs-dpdk is an example in hand).
-
-
-  For async data path, we force the VM memory to be pre-allocated at vhost
-  lib when mapping the guest memory; and also we need to lock the memory to
-  prevent pages being swapped out to disk.
+  Guest memory pre-allocation is not a must but can help save memory.
+  To do this we can add option ``-mem-prealloc`` when starting QEMU,
+  or we can lock all memory at vhost side which will force memory to
+  be allocated when it calls mmap (option --mlockall in ovs-dpdk is
+  an example in hand).
 
 * Memory sharing
 
@@ -467,43 +381,3 @@ Finally, a set of device ops is defined for device specific operations:
 * ``get_notify_area``
 
   Called to get the notify area info of the queue.
-
-Vhost asynchronous data path
-----------------------------
-
-Vhost asynchronous data path leverages DMA devices to offload memory
-copies from the CPU and it is implemented in an asynchronous way. It
-enables applications, like OVS, to save CPU cycles and hide memory copy
-overhead, thus achieving higher throughput.
-
-Vhost doesn't manage DMA devices and applications, like OVS, need to
-manage and configure DMA devices. Applications need to tell vhost what
-DMA devices to use in every data path function call. This design enables
-the flexibility for applications to dynamically use DMA channels in
-different function modules, not limited in vhost.
-
-In addition, vhost supports M:N mapping between vrings and DMA virtual
-channels. Specifically, one vring can use multiple different DMA channels
-and one DMA channel can be shared by multiple vrings at the same time.
-The reason of enabling one vring to use multiple DMA channels is that
-it's possible that more than one dataplane threads enqueue packets to
-the same vring with their own DMA virtual channels. Besides, the number
-of DMA devices is limited. For the purpose of scaling, it's necessary to
-support sharing DMA channels among vrings.
-
-* Async enqueue API usage
-
-  In async enqueue path, rte_vhost_poll_enqueue_completed() needs to be
-  called in time to notify the guest of DMA copy completed packets.
-  Moreover, calling rte_vhost_submit_enqueue_burst() all the time but
-  not poll completed will cause the DMA ring to be full, which will
-  result in packet loss eventually.
-
-* Recommended IOVA mode in async datapath
-
-  When DMA devices are bound to VFIO driver, VA mode is recommended.
-  For PA mode, page by page mapping may exceed IOMMU's max capability,
-  better to use 1G guest hugepage.
-
-  For UIO driver or kernel driver, any VFIO related error messages
-  can be ignored.
doc/guides/rel_notes/release_26_11.rst +13 -0
index b44d8cc4ad..71e9dab3e9 100644
@@ -73,6 +73,19 @@ Removed Items
   The experimental async data path APIs have been removed from the vhost library.
   The following functions and flag are no longer available:
 
+  - ``rte_vhost_async_channel_register``
+  - ``rte_vhost_async_channel_register_thread_unsafe``
+  - ``rte_vhost_async_channel_unregister``
+  - ``rte_vhost_async_channel_unregister_thread_unsafe``
+  - ``rte_vhost_async_dma_configure``
+  - ``rte_vhost_async_dma_unconfigure``
+  - ``rte_vhost_submit_enqueue_burst``
+  - ``rte_vhost_poll_enqueue_completed``
+  - ``rte_vhost_async_try_dequeue_burst``
+  - ``rte_vhost_async_get_inflight``
+  - ``rte_vhost_async_get_inflight_thread_unsafe``
+  - ``rte_vhost_clear_queue``
+  - ``rte_vhost_clear_queue_thread_unsafe``
   - ``RTE_VHOST_USER_ASYNC_COPY``
 
 
lib/vhost/meson.build +1 -2
index 6a24981d10..c7a8bf4673 100644
@@ -38,10 +38,9 @@ sources = files(
 headers = files(
         'rte_vdpa.h',
         'rte_vhost.h',
-        'rte_vhost_async.h',
         'rte_vhost_crypto.h',
 )
 driver_sdk_headers = files(
         'vdpa_driver.h',
 )
-deps += ['ethdev', 'cryptodev', 'hash', 'pci', 'dmadev']
+deps += ['ethdev', 'cryptodev', 'hash', 'pci']
lib/vhost/rte_vhost_async.h deleted +0 -293

293 lines not on this page · raw message

lib/vhost/socket.c +0 -2
index 4f5f44d0a5..8889ad5648 100644
@@ -43,7 +43,6 @@ struct vhost_user_socket {
 	bool use_builtin_virtio_net;
 	bool extbuf;
 	bool linearbuf;
-	bool async_copy;
 	bool net_compliant_ol_flags;
 	bool stats_enabled;
 	bool async_connect;
@@ -935,7 +934,6 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
 	vsocket->max_queue_pairs = VHOST_MAX_QUEUE_PAIRS;
 	vsocket->extbuf = flags & RTE_VHOST_USER_EXTBUF_SUPPORT;
 	vsocket->linearbuf = flags & RTE_VHOST_USER_LINEARBUF_SUPPORT;
-	vsocket->async_copy = false;
 	vsocket->net_compliant_ol_flags = flags & RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS;
 	vsocket->stats_enabled = flags & RTE_VHOST_USER_NET_STATS_ENABLE;
 	vsocket->async_connect = flags & RTE_VHOST_USER_ASYNC_CONNECT;
lib/vhost/vhost.c +0 -434

463 lines not on this page · raw message

lib/vhost/vhost.h +0 -115

150 lines not on this page · raw message

lib/vhost/vhost_user.c +0 -5
index 2b35f44b70..6924270c55 100644
@@ -2409,11 +2409,6 @@ vhost_user_set_vring_enable(struct virtio_net **pdev,
 	if (!(dev->flags & VIRTIO_DEV_VDPA_CONFIGURED)) {
 		/* vhost_user_lock_all_queue_pairs locked all qps */
 		VHOST_USER_ASSERT_LOCK(dev, vq, VHOST_USER_SET_VRING_ENABLE);
-		if (enable && vq->async && vq->async->pkts_inflight_n) {
-			VHOST_CONFIG_LOG(dev->ifname, ERR,
-				"failed to enable vring. Inflight packets must be completed first");
-			return RTE_VHOST_MSG_RESULT_ERR;
-		}
 	}
 
 	vq->enabled = enable;
lib/vhost/virtio_net.c +660 -2615

1,877 lines not on this page · raw message

The rest of this diff is not shown. View the raw message.

Signature · 1 line
2.54.0

Part of the diff is not shown here. View the raw message.

#5 lore raw
In reply to David Marchand

Hi David,

Quoted 6 lines · David Marchand

The integration of this feature in OVS has been postponed following feedback how the current API forced the complexity on the application side. There is no contributor working on making those changes.

The feature has no other identified opensource consumer.

I am not aware of any either.

Quoted 8 lines

On the other hand, this feature has been left unattended for some years now while the "normal" datapath is actively maintained.
It is highly likely the async datapath code, which never underwent a stabilisation phase, is riddled with bugs.

Given the craziness around finding security bugs with AI, and since the vhost library is a good target, I propose to drop this feature and reduce the library attack surface.

This feature was introduced by Intel a while back, so their acknowledgement that they have no ongoing work regarding Vhost async would be welcome.

Adding Bruce for intel (feel free to add relevant people), and tehcboard in case it requires a decision from it.

I favor dropping this feature.

Best regards,
Maxime

Quoted 32 lines

--
David Marchand

David Marchand (3):
examples: stop using vhost async datapath
vhost: refuse async datapath
vhost: drop async datapath

 doc/guides/prog_guide/vhost_lib.rst    |  151 +-
 doc/guides/rel_notes/release_26_11.rst |   20 +
 examples/vhost/Makefile                |    2 -
 examples/vhost/main.c                  |  436 +---
 examples/vhost/main.h                  |   21 +-
 examples/vhost/meson.build             |    2 -
 examples/vhost_crypto/Makefile         |    1 -
 examples/vhost_crypto/main.c           |    3 +-
 examples/vhost_crypto/meson.build      |    1 -
 lib/vhost/meson.build                  |    3 +-
 lib/vhost/rte_vhost.h                  |    2 +-
 lib/vhost/rte_vhost_async.h            |  293 ---
 lib/vhost/socket.c                     |   27 +-
 lib/vhost/vhost.c                      |  434 ----
 lib/vhost/vhost.h                      |  115 -
 lib/vhost/vhost_user.c                 |  215 +-
 lib/vhost/virtio_net.c                 | 3275 +++++-------------------
 17 files changed, 708 insertions(+), 4293 deletions(-)
 delete mode 100644 lib/vhost/rte_vhost_async.h

--
2.54.0

#6 lore raw

cover Drop vhost async (DMA-accelerated) datapath

In reply to David Marchand

The integration of this feature in OVS has been postponed following feedback how the current API forced the complexity on the application side. There is no contributor working on making those changes.

The feature has no other identified opensource consumer.

On the other hand, this feature has been left unattended for some years now while the "normal" datapath is actively maintained.
It is highly likely the async datapath code, which never underwent a stabilisation phase, is riddled with bugs.

Given the craziness around finding security bugs with AI, and since the vhost library is a good target, I propose to drop this feature and reduce the library attack surface.

There is one complication with the vhost_crypto and some external applications that seemed to rely on the async flag to track and populate guest pages, so a new flag replacing async is added by this series.

Signature · 36 lines
David Marchand

Changes since RFC:
- maintained guest pages population in a new flag (vhost_crypto/SPDK),
- removed remaining helpers which had sync_ in their names,


David Marchand (5):
  vhost: decouple guest pages population from async datapath
  examples/vhost: stop using async datapath
  vhost: drop async datapath
  vhost: rename packed layout helpers for batches
  vhost: simplify some descriptor handling

 doc/guides/prog_guide/vhost_lib.rst    |  152 +-
 doc/guides/rel_notes/release_26_11.rst |   20 +
 examples/vhost/Makefile                |    2 -
 examples/vhost/main.c                  |  436 +--
 examples/vhost/main.h                  |   21 +-
 examples/vhost/meson.build             |    2 -
 examples/vhost_crypto/Makefile         |    1 -
 examples/vhost_crypto/main.c           |    2 +-
 examples/vhost_crypto/meson.build      |    1 -
 lib/vhost/meson.build                  |    3 +-
 lib/vhost/rte_vhost.h                  |    2 +-
 lib/vhost/rte_vhost_async.h            |  293 ---
 lib/vhost/socket.c                     |   20 +-
 lib/vhost/vhost.c                      |  434 ---
 lib/vhost/vhost.h                      |  116 +-
 lib/vhost/vhost_user.c                 |  115 +-
 lib/vhost/virtio_net.c                 | 3343 +++++-------------------
 17 files changed, 736 insertions(+), 4227 deletions(-)
 delete mode 100644 lib/vhost/rte_vhost_async.h

-- 
2.54.0
#7 lore raw

PATCH 1/5 vhost: decouple guest pages population from async datapath

The vhost crypto zero-copy feature relies on the RTE_VHOST_USER_ASYNC_COPY flag to enable guest page tracking (guest_pages array population and MAP_POPULATE during mmap).

Introduce a RTE_VHOST_USER_MAP_POPULATE flag that maps to RTE_VHOST_USER_ASYNC_COPY at this point in time.

Adjust vhost_crypto example and remove the unnecessary ALLOW_EXPERIMENTAL_API flag as this example does not use any experimental APIs.

---
 doc/guides/prog_guide/vhost_lib.rst | 9 +++++++++
 examples/vhost_crypto/Makefile      | 1 -
 examples/vhost_crypto/main.c        | 2 +-
 examples/vhost_crypto/meson.build   | 1 -
 lib/vhost/rte_vhost.h               | 1 +
 lib/vhost/socket.c                  | 9 +++++++++
 lib/vhost/vhost.h                   | 1 +
 lib/vhost/vhost_user.c              | 4 ++--
 8 files changed, 23 insertions(+), 5 deletions(-)
doc/guides/prog_guide/vhost_lib.rst +9 -0
index 345a621716..2bea814a62 100644
@@ -118,6 +118,15 @@ The following is an overview of some key Vhost API functions:
 
     It is disabled by default.
 
+  - ``RTE_VHOST_USER_MAP_POPULATE``
+
+    Guest memory regions will be mapped with ``MAP_POPULATE`` when this flag
+    is set, pre-faulting pages into memory. This is useful for applications
+    requiring direct access to guest memory, such as vhost-crypto zero-copy
+    operations.
+
+    It is disabled by default.
+
   - ``RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS``
 
     Since v16.04, the vhost library forwards checksum and gso requests for
examples/vhost_crypto/Makefile +0 -1
index cc7f2abb90..130953c38e 100644
@@ -6,7 +6,6 @@ APP = vhost-crypto
 
 # all source are stored in SRCS-y
 SRCS-y := main.c
-CFLAGS += -DALLOW_EXPERIMENTAL_API
 
 PKGCONF ?= pkg-config
 
examples/vhost_crypto/main.c +1 -1
index 8bdfc40c4b..53bd8fa825 100644
@@ -623,7 +623,7 @@ main(int argc, char *argv[])
 
 		for (j = 0; j < lo->nb_sockets; j++) {
 			ret = rte_vhost_driver_register(lo->socket_files[j],
-				RTE_VHOST_USER_ASYNC_COPY);
+				RTE_VHOST_USER_MAP_POPULATE);
 			if (ret < 0) {
 				RTE_LOG(ERR, USER1, "socket %s already exists\n",
 					lo->socket_files[j]);
examples/vhost_crypto/meson.build +0 -1
index 1c294c286f..47c8fa829f 100644
@@ -6,7 +6,6 @@
 # To build this example as a standalone application with an already-installed
 # DPDK instance, use 'make'
 
-allow_experimental_apis = true
 deps += ['vhost', 'cryptodev']
 sources = files(
         'main.c',
lib/vhost/rte_vhost.h +1 -0
index a7f9700538..095f9b6d3c 100644
@@ -39,6 +39,7 @@ extern "C" {
 /* support only linear buffers (no chained mbufs) */
 #define RTE_VHOST_USER_LINEARBUF_SUPPORT	(1ULL << 6)
 #define RTE_VHOST_USER_ASYNC_COPY	(1ULL << 7)
+#define RTE_VHOST_USER_MAP_POPULATE	RTE_VHOST_USER_ASYNC_COPY
 #define RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS	(1ULL << 8)
 #define RTE_VHOST_USER_NET_STATS_ENABLE	(1ULL << 9)
 #define RTE_VHOST_USER_ASYNC_CONNECT	(1ULL << 10)
lib/vhost/socket.c +9 -0
index 70e582a18d..8b29271f97 100644
@@ -44,6 +44,7 @@ struct vhost_user_socket {
 	bool extbuf;
 	bool linearbuf;
 	bool async_copy;
+	bool map_populate;
 	bool net_compliant_ol_flags;
 	bool stats_enabled;
 	bool async_connect;
@@ -248,6 +249,13 @@ vhost_user_add_connection(int fd, struct vhost_user_socket *vsocket)
 			dev->async_copy = 1;
 	}
 
+	if (vsocket->map_populate) {
+		dev = get_device(vid);
+
+		if (dev)
+			dev->map_populate = 1;
+	}
+
 	VHOST_CONFIG_LOG(vsocket->path, INFO, "new device, handle is %d", vid);
 
 	if (vsocket->notify_ops->new_connection) {
@@ -939,6 +947,7 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
 	vsocket->extbuf = flags & RTE_VHOST_USER_EXTBUF_SUPPORT;
 	vsocket->linearbuf = flags & RTE_VHOST_USER_LINEARBUF_SUPPORT;
 	vsocket->async_copy = flags & RTE_VHOST_USER_ASYNC_COPY;
+	vsocket->map_populate = flags & RTE_VHOST_USER_MAP_POPULATE;
 	vsocket->net_compliant_ol_flags = flags & RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS;
 	vsocket->stats_enabled = flags & RTE_VHOST_USER_NET_STATS_ENABLE;
 	vsocket->async_connect = flags & RTE_VHOST_USER_ASYNC_CONNECT;
lib/vhost/vhost.h +1 -0
index ee61f7415e..8575a9bb1c 100644
@@ -499,6 +499,7 @@ struct __rte_cache_aligned virtio_net {
 	RTE_ATOMIC(int16_t)	broadcast_rarp;
 	uint32_t		nr_vring;
 	int			async_copy;
+	int			map_populate;
 
 	int			extbuf;
 	int			linearbuf;
lib/vhost/vhost_user.c +2 -2
index 020c993b29..e87ab82e63 100644
@@ -1384,7 +1384,7 @@ vhost_user_mmap_region(struct virtio_net *dev,
 		return -1;
 	}
 
-	populate = dev->async_copy ? MAP_POPULATE : 0;
+	populate = dev->map_populate ? MAP_POPULATE : 0;
 	mmap_addr = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE,
 			MAP_SHARED | populate, region->fd, 0);
 
@@ -1398,7 +1398,7 @@ vhost_user_mmap_region(struct virtio_net *dev,
 	region->host_user_addr = (uint64_t)(uintptr_t)mmap_addr + mmap_offset;
 	mem_set_dump(dev, mmap_addr, mmap_size, false, alignment);
 
-	if (dev->async_copy) {
+	if (dev->map_populate) {
 		if (add_guest_pages(dev, region, alignment) < 0) {
 			VHOST_CONFIG_LOG(dev->ifname, ERR,
 				"adding guest pages to region failed.");
Signature · 1 line
2.54.0
#8 lore raw

PATCH 2/5 examples/vhost: stop using async datapath

In reply to David Marchand

Stop using vhost async as this feature will be removed in a next commit. Thanks to this, we can drop use of experimental api.

---
Changes since RFC:
- dropped vhost_crypto changes (now handled in patch 1),

---
 examples/vhost/Makefile    |   2 -
 examples/vhost/main.c      | 436 +------------------------------------
 examples/vhost/main.h      |  21 +-
 examples/vhost/meson.build |   2 -
 4 files changed, 12 insertions(+), 449 deletions(-)
examples/vhost/Makefile +0 -2
index 5b3cea0778..6e0114d094 100644
@@ -28,8 +28,6 @@ CFLAGS += -O3 $(shell $(PKGCONF) --cflags libdpdk)
 LDFLAGS_SHARED = $(shell $(PKGCONF) --libs libdpdk)
 LDFLAGS_STATIC = $(shell $(PKGCONF) --static --libs libdpdk)
 
-CFLAGS += -DALLOW_EXPERIMENTAL_API
-
 build/$(APP)-shared: $(SRCS-y) Makefile $(PC_FILE) | build
 	$(CC) $(CFLAGS) $(SRCS-y) -o $@ $(LDFLAGS) $(LDFLAGS_SHARED)
 
examples/vhost/main.c +10 -426

603 lines not on this page · raw message

examples/vhost/main.h +2 -19
index c986cbc5a9..3cf6bd7f07 100644
@@ -8,7 +8,6 @@
 #include <sys/queue.h>
 
 #include <rte_ether.h>
-#include <rte_pci.h>
 
 /* Macros for printing using RTE_LOG */
 #define RTE_LOGTYPE_VHOST_CONFIG RTE_LOGTYPE_USER1
@@ -92,17 +91,6 @@ struct lcore_info {
 	struct vhost_dev_tailq_list vdev_list;
 };
 
-struct dma_info {
-	struct rte_pci_addr addr;
-	int16_t dev_id;
-	bool async_enabled;
-};
-
-struct dma_for_vhost {
-	struct dma_info dmas[RTE_MAX_QUEUES_PER_PORT * 2];
-	uint32_t async_flag;
-};
-
 /* we implement non-extra virtio net features */
 #define VIRTIO_NET_FEATURES	0
 
@@ -116,14 +104,9 @@ uint16_t builtin_enqueue_pkts(struct vhost_dev *dev, uint16_t queue_id,
 uint16_t builtin_dequeue_pkts(struct vhost_dev *dev, uint16_t queue_id,
 			struct rte_mempool *mbuf_pool,
 			struct rte_mbuf **pkts, uint16_t count);
-uint16_t sync_enqueue_pkts(struct vhost_dev *dev, uint16_t queue_id,
-			 struct rte_mbuf **pkts, uint32_t count);
-uint16_t sync_dequeue_pkts(struct vhost_dev *dev, uint16_t queue_id,
-			struct rte_mempool *mbuf_pool,
-			struct rte_mbuf **pkts, uint16_t count);
-uint16_t async_enqueue_pkts(struct vhost_dev *dev, uint16_t queue_id,
+uint16_t enqueue_pkts(struct vhost_dev *dev, uint16_t queue_id,
 			 struct rte_mbuf **pkts, uint32_t count);
-uint16_t async_dequeue_pkts(struct vhost_dev *dev, uint16_t queue_id,
+uint16_t dequeue_pkts(struct vhost_dev *dev, uint16_t queue_id,
 			struct rte_mempool *mbuf_pool,
 			struct rte_mbuf **pkts, uint16_t count);
 #endif /* _MAIN_H_ */
examples/vhost/meson.build +0 -2
index e938be8f45..a04852bb2f 100644
@@ -12,8 +12,6 @@ if not is_linux
 endif
 
 deps += 'vhost'
-deps += 'dmadev'
-allow_experimental_apis = true
 sources = files(
         'main.c',
         'virtio_net.c',
Signature · 1 line
2.54.0
#9 lore raw

PATCH 3/5 vhost: drop async datapath

In reply to David Marchand

All the API related to this feature is experimental, allowing us by the project policy to drop the feature in one go.

---
Changes since RFC:
- kept mmap populate behavior for vhost_crypto,

---
 doc/guides/prog_guide/vhost_lib.rst    |  151 +-
 doc/guides/rel_notes/release_26_11.rst |   20 +
 lib/vhost/meson.build                  |    3 +-
 lib/vhost/rte_vhost.h                  |    3 +-
 lib/vhost/rte_vhost_async.h            |  293 ---
 lib/vhost/socket.c                     |   21 -
 lib/vhost/vhost.c                      |  434 ----
 lib/vhost/vhost.h                      |  115 -
 lib/vhost/vhost_user.c                 |  111 -
 lib/vhost/virtio_net.c                 | 3275 +++++-------------------
 10 files changed, 687 insertions(+), 3739 deletions(-)
 delete mode 100644 lib/vhost/rte_vhost_async.h
doc/guides/prog_guide/vhost_lib.rst +5 -146
index 2bea814a62..81f6115483 100644
@@ -103,21 +103,6 @@ The following is an overview of some key Vhost API functions:
 
     It is disabled by default.
 
-  - ``RTE_VHOST_USER_ASYNC_COPY``
-
-    Asynchronous data path will be enabled when this flag is set. Async
-    data path allows applications to enable DMA acceleration for vhost
-    queues. Vhost leverages the registered DMA channels to free CPU from
-    memory copy operations in data path. A set of async data path APIs are
-    defined for DPDK applications to make use of the async capability. Only
-    packets enqueued/dequeued by async APIs are processed through the async
-    data path.
-
-    Currently this feature is only implemented on split ring enqueue data
-    path.
-
-    It is disabled by default.
-
   - ``RTE_VHOST_USER_MAP_POPULATE``
 
     Guest memory regions will be mapped with ``MAP_POPULATE`` when this flag
@@ -236,76 +221,6 @@ The following is an overview of some key Vhost API functions:
 
   Enable or disable zero copy feature of the vhost crypto backend.
 
-* ``rte_vhost_async_dma_configure(dma_id, vchan_id)``
-
-  Tell vhost which DMA vChannel is going to use. This function needs to
-  be called before register async data-path for vring.
-
-* ``rte_vhost_async_channel_register(vid, queue_id)``
-
-  Register async DMA acceleration for a vhost queue after vring is enabled.
-
-* ``rte_vhost_async_channel_register_thread_unsafe(vid, queue_id)``
-
-  Register async DMA acceleration for a vhost queue without performing
-  any locking.
-
-  This function is only safe to call in vhost callback functions
-  (i.e., struct rte_vhost_device_ops).
-
-* ``rte_vhost_async_channel_unregister(vid, queue_id)``
-
-  Unregister the async DMA acceleration from a vhost queue.
-  Unregistration will fail, if the vhost queue has in-flight
-  packets that are not completed.
-
-  Unregister async DMA acceleration in vring_state_changed() may
-  fail, as this API tries to acquire the spinlock of vhost
-  queue. The recommended way is to unregister async copy
-  devices for all vhost queues in destroy_device(), when a
-  virtio device is paused or shut down.
-
-* ``rte_vhost_async_channel_unregister_thread_unsafe(vid, queue_id)``
-
-  Unregister async DMA acceleration for a vhost queue without performing
-  any locking.
-
-  This function is only safe to call in vhost callback functions
-  (i.e., struct rte_vhost_device_ops).
-
-* ``rte_vhost_submit_enqueue_burst(vid, queue_id, pkts, count, dma_id, vchan_id)``
-
-  Submit an enqueue request to transmit ``count`` packets from host to guest
-  by async data path. Applications must not free the packets submitted for
-  enqueue until the packets are completed.
-
-* ``rte_vhost_poll_enqueue_completed(vid, queue_id, pkts, count, dma_id, vchan_id)``
-
-  Poll enqueue completion status from async data path. Completed packets
-  are returned to applications through ``pkts``.
-
-* ``rte_vhost_async_get_inflight(vid, queue_id)``
-
-  This function returns the amount of in-flight packets for the vhost
-  queue using async acceleration.
-
- * ``rte_vhost_async_get_inflight_thread_unsafe(vid, queue_id)``
-
-  Get the number of inflight packets for a vhost queue without performing
-  any locking. It should only be used within the vhost ops, which already
-  holds the lock.
-
-* ``rte_vhost_clear_queue_thread_unsafe(vid, queue_id, **pkts, count, dma_id, vchan_id)``
-
-  Clear in-flight packets which are submitted to async channel in vhost
-  async data path without performing locking on virtqueue. Completed
-  packets are returned to applications through ``pkts``.
-
-* ``rte_vhost_clear_queue(vid, queue_id, **pkts, count, dma_id, vchan_id)``
-
-  Clear in-flight packets which are submitted to async channel in vhost async data
-  path. Completed packets are returned to applications through ``pkts``.
-
 * ``rte_vhost_vring_call_nonblock(int vid, uint16_t vring_idx)``
 
   Notify the guest that used descriptors have been added to the vring. This function
@@ -327,22 +242,11 @@ The following is an overview of some key Vhost API functions:
   This function resets the queue statistics. It requires statistics
   collection to be enabled at registration time.
 
-* ``rte_vhost_async_try_dequeue_burst(vid, queue_id, mbuf_pool, pkts, count,
-  nr_inflight, dma_id, vchan_id)``
-
-  Receive ``count`` packets from guest to host in async data path,
-  and store them at ``pkts``.
-
 * ``rte_vhost_driver_get_vdpa_dev_type(path, type)``
 
   Get device type of vDPA device, such as VDPA_DEVICE_TYPE_NET,
   VDPA_DEVICE_TYPE_BLK.
 
-* ``rte_vhost_async_dma_unconfigure(dma_id, vchan_id)``
-
-  Clean up a DMA vChannel after use is finished. After this function is called,
-  the specified DMA vChannel should no longer be used by the Vhost library.
-
 * ``rte_vhost_notify_guest(int vid, uint16_t queue_id)``
 
   Inject the offloaded interrupt received by the 'guest_notify' callback,
@@ -411,16 +315,11 @@ Guest memory requirement
 
 * Memory pre-allocation
 
-  For non-async data path guest memory pre-allocation is not a
-  must but can help save memory. To do this we can add option
-  ``-mem-prealloc`` when starting QEMU, or we can lock all memory at vhost
-  side which will force memory to be allocated when it calls mmap
-  (option --mlockall in ovs-dpdk is an example in hand).
-
-
-  For async data path, we force the VM memory to be pre-allocated at vhost
-  lib when mapping the guest memory; and also we need to lock the memory to
-  prevent pages being swapped out to disk.
+  Guest memory pre-allocation is not a must but can help save memory.
+  To do this we can add option ``-mem-prealloc`` when starting QEMU,
+  or we can lock all memory at vhost side which will force memory to
+  be allocated when it calls mmap (option --mlockall in ovs-dpdk is
+  an example in hand).
 
 * Memory sharing
 
@@ -491,43 +390,3 @@ Finally, a set of device ops is defined for device specific operations:
 * ``get_notify_area``
 
   Called to get the notify area info of the queue.
-
-Vhost asynchronous data path
-----------------------------
-
-Vhost asynchronous data path leverages DMA devices to offload memory
-copies from the CPU and it is implemented in an asynchronous way. It
-enables applications, like OVS, to save CPU cycles and hide memory copy
-overhead, thus achieving higher throughput.
-
-Vhost doesn't manage DMA devices and applications, like OVS, need to
-manage and configure DMA devices. Applications need to tell vhost what
-DMA devices to use in every data path function call. This design enables
-the flexibility for applications to dynamically use DMA channels in
-different function modules, not limited in vhost.
-
-In addition, vhost supports M:N mapping between vrings and DMA virtual
-channels. Specifically, one vring can use multiple different DMA channels
-and one DMA channel can be shared by multiple vrings at the same time.
-The reason of enabling one vring to use multiple DMA channels is that
-it's possible that more than one dataplane threads enqueue packets to
-the same vring with their own DMA virtual channels. Besides, the number
-of DMA devices is limited. For the purpose of scaling, it's necessary to
-support sharing DMA channels among vrings.
-
-* Async enqueue API usage
-
-  In async enqueue path, rte_vhost_poll_enqueue_completed() needs to be
-  called in time to notify the guest of DMA copy completed packets.
-  Moreover, calling rte_vhost_submit_enqueue_burst() all the time but
-  not poll completed will cause the DMA ring to be full, which will
-  result in packet loss eventually.
-
-* Recommended IOVA mode in async datapath
-
-  When DMA devices are bound to VFIO driver, VA mode is recommended.
-  For PA mode, page by page mapping may exceed IOMMU's max capability,
-  better to use 1G guest hugepage.
-
-  For UIO driver or kernel driver, any VFIO related error messages
-  can be ignored.
doc/guides/rel_notes/release_26_11.rst +20 -0
index 87c7e81bde..7cf023454d 100644
@@ -79,6 +79,26 @@ Removed Items
     ``rte_rib6_is_equal``
   * table: ``RTE_LPM_IPV6_ADDR_SIZE``
 
+* **Removed vhost async (DMA-accelerated) data path.**
+
+  The experimental async data path APIs have been removed from the vhost library.
+  The following functions and flag are no longer available:
+
+  - ``rte_vhost_async_channel_register``
+  - ``rte_vhost_async_channel_register_thread_unsafe``
+  - ``rte_vhost_async_channel_unregister``
+  - ``rte_vhost_async_channel_unregister_thread_unsafe``
+  - ``rte_vhost_async_dma_configure``
+  - ``rte_vhost_async_dma_unconfigure``
+  - ``rte_vhost_submit_enqueue_burst``
+  - ``rte_vhost_poll_enqueue_completed``
+  - ``rte_vhost_async_try_dequeue_burst``
+  - ``rte_vhost_async_get_inflight``
+  - ``rte_vhost_async_get_inflight_thread_unsafe``
+  - ``rte_vhost_clear_queue``
+  - ``rte_vhost_clear_queue_thread_unsafe``
+  - ``RTE_VHOST_USER_ASYNC_COPY``
+
 
 API Changes
 -----------
lib/vhost/meson.build +1 -2
index 6a24981d10..c7a8bf4673 100644
@@ -38,10 +38,9 @@ sources = files(
 headers = files(
         'rte_vdpa.h',
         'rte_vhost.h',
-        'rte_vhost_async.h',
         'rte_vhost_crypto.h',
 )
 driver_sdk_headers = files(
         'vdpa_driver.h',
 )
-deps += ['ethdev', 'cryptodev', 'hash', 'pci', 'dmadev']
+deps += ['ethdev', 'cryptodev', 'hash', 'pci']
lib/vhost/rte_vhost.h +1 -2
index 095f9b6d3c..79a4138c62 100644
@@ -38,8 +38,7 @@ extern "C" {
 #define RTE_VHOST_USER_EXTBUF_SUPPORT	(1ULL << 5)
 /* support only linear buffers (no chained mbufs) */
 #define RTE_VHOST_USER_LINEARBUF_SUPPORT	(1ULL << 6)
-#define RTE_VHOST_USER_ASYNC_COPY	(1ULL << 7)
-#define RTE_VHOST_USER_MAP_POPULATE	RTE_VHOST_USER_ASYNC_COPY
+#define RTE_VHOST_USER_MAP_POPULATE	(1ULL << 7)
 #define RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS	(1ULL << 8)
 #define RTE_VHOST_USER_NET_STATS_ENABLE	(1ULL << 9)
 #define RTE_VHOST_USER_ASYNC_CONNECT	(1ULL << 10)
lib/vhost/rte_vhost_async.h deleted +0 -293

293 lines not on this page · raw message

lib/vhost/socket.c +0 -21
index 8b29271f97..cffec0fa54 100644
@@ -43,7 +43,6 @@ struct vhost_user_socket {
 	bool use_builtin_virtio_net;
 	bool extbuf;
 	bool linearbuf;
-	bool async_copy;
 	bool map_populate;
 	bool net_compliant_ol_flags;
 	bool stats_enabled;
@@ -242,13 +241,6 @@ vhost_user_add_connection(int fd, struct vhost_user_socket *vsocket)
 	if (vsocket->linearbuf)
 		vhost_enable_linearbuf(vid);
 
-	if (vsocket->async_copy) {
-		dev = get_device(vid);
-
-		if (dev)
-			dev->async_copy = 1;
-	}
-
 	if (vsocket->map_populate) {
 		dev = get_device(vid);
 
@@ -946,7 +938,6 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
 	vsocket->max_queue_pairs = VHOST_MAX_QUEUE_PAIRS;
 	vsocket->extbuf = flags & RTE_VHOST_USER_EXTBUF_SUPPORT;
 	vsocket->linearbuf = flags & RTE_VHOST_USER_LINEARBUF_SUPPORT;
-	vsocket->async_copy = flags & RTE_VHOST_USER_ASYNC_COPY;
 	vsocket->map_populate = flags & RTE_VHOST_USER_MAP_POPULATE;
 	vsocket->net_compliant_ol_flags = flags & RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS;
 	vsocket->stats_enabled = flags & RTE_VHOST_USER_NET_STATS_ENABLE;
@@ -956,12 +947,6 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
 	else
 		vsocket->iommu_support = flags & RTE_VHOST_USER_IOMMU_SUPPORT;
 
-	if (vsocket->async_copy && (vsocket->iommu_support ||
-				(flags & RTE_VHOST_USER_POSTCOPY_SUPPORT))) {
-		VHOST_CONFIG_LOG(path, ERR, "async copy with IOMMU or post-copy not supported");
-		goto out_mutex;
-	}
-
 	/*
 	 * Set the supported features correctly for the builtin vhost-user
 	 * net driver.
@@ -984,12 +969,6 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
 		vsocket->protocol_features  = VHOST_USER_PROTOCOL_FEATURES;
 	}
 
-	if (vsocket->async_copy) {
-		vsocket->supported_features &= ~(1ULL << VHOST_F_LOG_ALL);
-		vsocket->features &= ~(1ULL << VHOST_F_LOG_ALL);
-		VHOST_CONFIG_LOG(path, INFO, "logging feature is disabled in async copy mode");
-	}
-
 	/*
 	 * We'll not be able to receive a buffer from guest in linear mode
 	 * without external buffer if it will not fit in a single mbuf, which is
lib/vhost/vhost.c +0 -434

463 lines not on this page · raw message

lib/vhost/vhost.h +0 -115

150 lines not on this page · raw message

lib/vhost/vhost_user.c +0 -111

177 lines not on this page · raw message

lib/vhost/virtio_net.c +660 -2615

1,637 lines not on this page · raw message

The rest of this diff is not shown. View the raw message.

Signature · 1 line
2.54.0

Part of the diff is not shown here. View the raw message.

#10 lore raw

PATCH 4/5 vhost: rename packed layout helpers for batches

In reply to David Marchand

Now that the async datapath has been removed, the _sync in function names gives no useful information.

Besides, vhost_reserve_avail_batch_packed does not reserve anything and its name is confusing, rename it following the other rx/tx split/packed helpers convention.

---
 lib/vhost/virtio_net.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)
lib/vhost/virtio_net.c +6 -8
index 9ad7fa3295..79034ae036 100644
@@ -1111,7 +1111,7 @@ virtio_dev_rx_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
 }
 
 static __rte_always_inline int
-virtio_dev_rx_sync_batch_check(struct virtio_net *dev,
+virtio_dev_rx_batch_check(struct virtio_net *dev,
 			   struct vhost_virtqueue *vq,
 			   struct rte_mbuf **pkts,
 			   uint64_t *desc_addrs,
@@ -1213,7 +1213,7 @@ virtio_dev_rx_batch_packed_copy(struct virtio_net *dev,
 }
 
 static __rte_always_inline int
-virtio_dev_rx_sync_batch_packed(struct virtio_net *dev,
+virtio_dev_rx_batch_packed(struct virtio_net *dev,
 			   struct vhost_virtqueue *vq,
 			   struct rte_mbuf **pkts)
 	__rte_requires_shared_capability(&vq->iotlb_lock)
@@ -1221,7 +1221,7 @@ virtio_dev_rx_sync_batch_packed(struct virtio_net *dev,
 	uint64_t desc_addrs[PACKED_BATCH_SIZE];
 	uint64_t lens[PACKED_BATCH_SIZE];
 
-	if (virtio_dev_rx_sync_batch_check(dev, vq, pkts, desc_addrs, lens) == -1)
+	if (virtio_dev_rx_batch_check(dev, vq, pkts, desc_addrs, lens) == -1)
 		return -1;
 
 	if (vq->shadow_used_idx) {
@@ -1273,8 +1273,7 @@ virtio_dev_rx_packed(struct virtio_net *dev,
 		rte_prefetch0(&vq->desc_packed[vq->last_avail_idx]);
 
 		if (count - pkt_idx >= PACKED_BATCH_SIZE) {
-			if (!virtio_dev_rx_sync_batch_packed(dev, vq,
-							&pkts[pkt_idx])) {
+			if (!virtio_dev_rx_batch_packed(dev, vq, &pkts[pkt_idx])) {
 				pkt_idx += PACKED_BATCH_SIZE;
 				continue;
 			}
@@ -1971,7 +1970,7 @@ virtio_dev_tx_split_compliant(struct virtio_net *dev,
 }
 
 static __rte_always_inline int
-vhost_reserve_avail_batch_packed(struct virtio_net *dev,
+virtio_dev_tx_batch_packed_check(struct virtio_net *dev,
 				 struct vhost_virtqueue *vq,
 				 struct rte_mbuf **pkts,
 				 uint16_t avail_idx,
@@ -2055,8 +2054,7 @@ virtio_dev_tx_batch_packed(struct virtio_net *dev,
 	uint16_t ids[PACKED_BATCH_SIZE];
 	uint16_t i;
 
-	if (vhost_reserve_avail_batch_packed(dev, vq, pkts, avail_idx,
-					     desc_addrs, ids))
+	if (virtio_dev_tx_batch_packed_check(dev, vq, pkts, avail_idx, desc_addrs, ids))
 		return -1;
 
 	vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
Signature · 1 line
2.54.0
#11 lore raw

PATCH 5/5 vhost: simplify some descriptor handling

In reply to David Marchand

Now that the async datapath has been removed, move back the descriptors copy/filling code in desc_to_mbuf/mbuf_to_desc and eliminate an intermediate helper.

Tracking buf_iova is not needed in the descriptor to mbuf case.

---
 lib/vhost/virtio_net.c | 78 ++++++++++++++++--------------------------
 1 file changed, 30 insertions(+), 48 deletions(-)
lib/vhost/virtio_net.c +30 -48
index 79034ae036..9b1ef8f10c 100644
@@ -76,6 +76,12 @@ vhost_queue_stats_update(const struct virtio_net *dev, struct vhost_virtqueue *v
 	}
 }
 
+static __rte_always_inline bool
+vhost_can_batch_copy(struct vhost_virtqueue *vq, uint32_t cpy_len)
+{
+	return cpy_len <= MAX_BATCH_LEN && vq->batch_copy_nb_elems < vq->size;
+}
+
 static inline void
 do_data_copy_enqueue(struct virtio_net *dev, struct vhost_virtqueue *vq)
 	__rte_requires_shared_capability(&vq->iotlb_lock)
@@ -843,44 +849,6 @@ copy_vnet_hdr_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	}
 }
 
-static __rte_always_inline void
-sync_fill_seg(struct virtio_net *dev, struct vhost_virtqueue *vq,
-		struct rte_mbuf *m, uint32_t mbuf_offset,
-		uint64_t buf_addr, uint64_t buf_iova, uint32_t cpy_len, bool to_desc)
-	__rte_requires_shared_capability(&vq->iotlb_lock)
-{
-	struct batch_copy_elem *batch_copy = vq->batch_copy_elems;
-
-	if (likely(cpy_len > MAX_BATCH_LEN || vq->batch_copy_nb_elems >= vq->size)) {
-		if (to_desc) {
-			rte_memcpy((void *)((uintptr_t)(buf_addr)),
-				rte_pktmbuf_mtod_offset(m, void *, mbuf_offset),
-				cpy_len);
-			vhost_log_cache_write_iova(dev, vq, buf_iova, cpy_len);
-			PRINT_PACKET(dev, (uintptr_t)(buf_addr), cpy_len, 0);
-		} else {
-			rte_memcpy(rte_pktmbuf_mtod_offset(m, void *, mbuf_offset),
-				(void *)((uintptr_t)(buf_addr)),
-				cpy_len);
-		}
-	} else {
-		if (to_desc) {
-			batch_copy[vq->batch_copy_nb_elems].dst =
-				(void *)((uintptr_t)(buf_addr));
-			batch_copy[vq->batch_copy_nb_elems].src =
-				rte_pktmbuf_mtod_offset(m, void *, mbuf_offset);
-			batch_copy[vq->batch_copy_nb_elems].log_addr = buf_iova;
-		} else {
-			batch_copy[vq->batch_copy_nb_elems].dst =
-				rte_pktmbuf_mtod_offset(m, void *, mbuf_offset);
-			batch_copy[vq->batch_copy_nb_elems].src =
-				(void *)((uintptr_t)(buf_addr));
-		}
-		batch_copy[vq->batch_copy_nb_elems].len = cpy_len;
-		vq->batch_copy_nb_elems++;
-	}
-}
-
 static __rte_always_inline int
 mbuf_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
 		struct rte_mbuf *m, struct buf_vector *buf_vec,
@@ -976,9 +944,22 @@ mbuf_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
 
 		cpy_len = RTE_MIN(buf_avail, mbuf_avail);
 
-		sync_fill_seg(dev, vq, m, mbuf_offset,
-			      buf_addr + buf_offset,
-			      buf_iova + buf_offset, cpy_len, true);
+		if (likely(!vhost_can_batch_copy(vq, cpy_len))) {
+			rte_memcpy(RTE_PTR_ADD(buf_addr, buf_offset),
+				rte_pktmbuf_mtod_offset(m, void *, mbuf_offset),
+				cpy_len);
+			vhost_log_cache_write_iova(dev, vq, buf_iova + buf_offset, cpy_len);
+			PRINT_PACKET(dev, RTE_PTR_ADD(buf_addr, buf_offset), cpy_len, 0);
+		} else {
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].dst =
+				RTE_PTR_ADD(buf_addr, buf_offset);
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].src =
+				rte_pktmbuf_mtod_offset(m, void *, mbuf_offset);
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].log_addr =
+				buf_iova + buf_offset;
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].len = cpy_len;
+			vq->batch_copy_nb_elems++;
+		}
 
 		mbuf_avail  -= cpy_len;
 		mbuf_offset += cpy_len;
@@ -1679,7 +1660,7 @@ desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	__rte_requires_shared_capability(&vq->iotlb_lock)
 {
 	uint32_t buf_avail, buf_offset, buf_len;
-	uint64_t buf_addr, buf_iova;
+	uint64_t buf_addr;
 	uint32_t mbuf_avail, mbuf_offset;
 	uint32_t hdr_remain = dev->vhost_hlen;
 	uint32_t cpy_len;
@@ -1710,7 +1691,6 @@ desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	}
 
 	buf_addr = buf_vec[vec_idx].buf_addr;
-	buf_iova = buf_vec[vec_idx].buf_iova;
 	buf_len = buf_vec[vec_idx].buf_len;
 	buf_offset = hdr_remain;
 	buf_avail = buf_vec[vec_idx].buf_len - hdr_remain;
@@ -1725,14 +1705,17 @@ desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	while (1) {
 		cpy_len = RTE_MIN(buf_avail, mbuf_avail);
 
-		if (likely(hdr && cur == m)) {
+		if (likely((hdr && cur == m) || !vhost_can_batch_copy(vq, cpy_len))) {
 			rte_memcpy(rte_pktmbuf_mtod_offset(cur, void *, mbuf_offset),
 				(void *)((uintptr_t)(buf_addr + buf_offset)),
 				cpy_len);
 		} else {
-			sync_fill_seg(dev, vq, cur, mbuf_offset,
-				      buf_addr + buf_offset,
-				      buf_iova + buf_offset, cpy_len, false);
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].dst =
+				rte_pktmbuf_mtod_offset(cur, void *, mbuf_offset);
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].src =
+				RTE_PTR_ADD(buf_addr, buf_offset);
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].len = cpy_len;
+			vq->batch_copy_nb_elems++;
 		}
 
 		mbuf_avail  -= cpy_len;
@@ -1746,7 +1729,6 @@ desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
 				break;
 
 			buf_addr = buf_vec[vec_idx].buf_addr;
-			buf_iova = buf_vec[vec_idx].buf_iova;
 			buf_len = buf_vec[vec_idx].buf_len;
 
 			buf_offset = 0;
Signature · 1 line
2.54.0
#12 lore raw

v2 cover Drop vhost async (DMA-accelerated) datapath

In reply to David Marchand

The integration of this feature in OVS has been postponed following feedback how the current API forced the complexity on the application side. There is no contributor working on making those changes.

The feature has no other identified opensource consumer.

On the other hand, this feature has been left unattended for some years now while the "normal" datapath is actively maintained.
It is highly likely the async datapath code, which never underwent a stabilisation phase, is riddled with bugs.

Given the craziness around finding security bugs with AI, and since the vhost library is a good target, I propose to drop this feature and reduce the library attack surface.

There is one complication with the vhost_crypto and some external applications that seemed to rely on the async flag to track and populate guest pages, so a new flag replacing async is added by this series.

Signature · 41 lines
David Marchand

Changes since v1:
- removed unneeded dependencies on the PCI library,

Changes since RFC:
- maintained guest pages population in a new flag (vhost_crypto/SPDK),
- removed remaining helpers which had sync_ in their names,


David Marchand (6):
  vhost: decouple guest pages population from async datapath
  examples/vhost: stop using async datapath
  examples/vdpa: remove dependency on PCI library
  vhost: drop async datapath
  vhost: rename packed layout helpers for batches
  vhost: simplify some descriptor handling

 doc/guides/prog_guide/vhost_lib.rst    |  152 +-
 doc/guides/rel_notes/release_26_11.rst |   20 +
 examples/vdpa/main.c                   |    1 -
 examples/vhost/Makefile                |    2 -
 examples/vhost/main.c                  |  436 +--
 examples/vhost/main.h                  |   21 +-
 examples/vhost/meson.build             |    2 -
 examples/vhost_crypto/Makefile         |    1 -
 examples/vhost_crypto/main.c           |    2 +-
 examples/vhost_crypto/meson.build      |    1 -
 lib/vhost/meson.build                  |    3 +-
 lib/vhost/rte_vhost.h                  |    2 +-
 lib/vhost/rte_vhost_async.h            |  293 ---
 lib/vhost/socket.c                     |   20 +-
 lib/vhost/vhost.c                      |  434 ---
 lib/vhost/vhost.h                      |  116 +-
 lib/vhost/vhost_user.c                 |  115 +-
 lib/vhost/virtio_net.c                 | 3343 +++++-------------------
 18 files changed, 736 insertions(+), 4228 deletions(-)
 delete mode 100644 lib/vhost/rte_vhost_async.h

-- 
2.54.0
#13 lore raw

PATCH v2 1/6 vhost: decouple guest pages population from async datapath

The vhost crypto zero-copy feature relies on the RTE_VHOST_USER_ASYNC_COPY flag to enable guest page tracking (guest_pages array population and MAP_POPULATE during mmap).

Introduce a RTE_VHOST_USER_MAP_POPULATE flag that maps to RTE_VHOST_USER_ASYNC_COPY at this point in time.

Adjust vhost_crypto example and remove the unnecessary ALLOW_EXPERIMENTAL_API flag as this example does not use any experimental APIs.

---
 doc/guides/prog_guide/vhost_lib.rst | 9 +++++++++
 examples/vhost_crypto/Makefile      | 1 -
 examples/vhost_crypto/main.c        | 2 +-
 examples/vhost_crypto/meson.build   | 1 -
 lib/vhost/rte_vhost.h               | 1 +
 lib/vhost/socket.c                  | 9 +++++++++
 lib/vhost/vhost.h                   | 1 +
 lib/vhost/vhost_user.c              | 4 ++--
 8 files changed, 23 insertions(+), 5 deletions(-)
doc/guides/prog_guide/vhost_lib.rst +9 -0
index 345a621716..2bea814a62 100644
@@ -118,6 +118,15 @@ The following is an overview of some key Vhost API functions:
 
     It is disabled by default.
 
+  - ``RTE_VHOST_USER_MAP_POPULATE``
+
+    Guest memory regions will be mapped with ``MAP_POPULATE`` when this flag
+    is set, pre-faulting pages into memory. This is useful for applications
+    requiring direct access to guest memory, such as vhost-crypto zero-copy
+    operations.
+
+    It is disabled by default.
+
   - ``RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS``
 
     Since v16.04, the vhost library forwards checksum and gso requests for
examples/vhost_crypto/Makefile +0 -1
index cc7f2abb90..130953c38e 100644
@@ -6,7 +6,6 @@ APP = vhost-crypto
 
 # all source are stored in SRCS-y
 SRCS-y := main.c
-CFLAGS += -DALLOW_EXPERIMENTAL_API
 
 PKGCONF ?= pkg-config
 
examples/vhost_crypto/main.c +1 -1
index 8bdfc40c4b..53bd8fa825 100644
@@ -623,7 +623,7 @@ main(int argc, char *argv[])
 
 		for (j = 0; j < lo->nb_sockets; j++) {
 			ret = rte_vhost_driver_register(lo->socket_files[j],
-				RTE_VHOST_USER_ASYNC_COPY);
+				RTE_VHOST_USER_MAP_POPULATE);
 			if (ret < 0) {
 				RTE_LOG(ERR, USER1, "socket %s already exists\n",
 					lo->socket_files[j]);
examples/vhost_crypto/meson.build +0 -1
index 1c294c286f..47c8fa829f 100644
@@ -6,7 +6,6 @@
 # To build this example as a standalone application with an already-installed
 # DPDK instance, use 'make'
 
-allow_experimental_apis = true
 deps += ['vhost', 'cryptodev']
 sources = files(
         'main.c',
lib/vhost/rte_vhost.h +1 -0
index a7f9700538..095f9b6d3c 100644
@@ -39,6 +39,7 @@ extern "C" {
 /* support only linear buffers (no chained mbufs) */
 #define RTE_VHOST_USER_LINEARBUF_SUPPORT	(1ULL << 6)
 #define RTE_VHOST_USER_ASYNC_COPY	(1ULL << 7)
+#define RTE_VHOST_USER_MAP_POPULATE	RTE_VHOST_USER_ASYNC_COPY
 #define RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS	(1ULL << 8)
 #define RTE_VHOST_USER_NET_STATS_ENABLE	(1ULL << 9)
 #define RTE_VHOST_USER_ASYNC_CONNECT	(1ULL << 10)
lib/vhost/socket.c +9 -0
index 70e582a18d..8b29271f97 100644
@@ -44,6 +44,7 @@ struct vhost_user_socket {
 	bool extbuf;
 	bool linearbuf;
 	bool async_copy;
+	bool map_populate;
 	bool net_compliant_ol_flags;
 	bool stats_enabled;
 	bool async_connect;
@@ -248,6 +249,13 @@ vhost_user_add_connection(int fd, struct vhost_user_socket *vsocket)
 			dev->async_copy = 1;
 	}
 
+	if (vsocket->map_populate) {
+		dev = get_device(vid);
+
+		if (dev)
+			dev->map_populate = 1;
+	}
+
 	VHOST_CONFIG_LOG(vsocket->path, INFO, "new device, handle is %d", vid);
 
 	if (vsocket->notify_ops->new_connection) {
@@ -939,6 +947,7 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
 	vsocket->extbuf = flags & RTE_VHOST_USER_EXTBUF_SUPPORT;
 	vsocket->linearbuf = flags & RTE_VHOST_USER_LINEARBUF_SUPPORT;
 	vsocket->async_copy = flags & RTE_VHOST_USER_ASYNC_COPY;
+	vsocket->map_populate = flags & RTE_VHOST_USER_MAP_POPULATE;
 	vsocket->net_compliant_ol_flags = flags & RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS;
 	vsocket->stats_enabled = flags & RTE_VHOST_USER_NET_STATS_ENABLE;
 	vsocket->async_connect = flags & RTE_VHOST_USER_ASYNC_CONNECT;
lib/vhost/vhost.h +1 -0
index ee61f7415e..8575a9bb1c 100644
@@ -499,6 +499,7 @@ struct __rte_cache_aligned virtio_net {
 	RTE_ATOMIC(int16_t)	broadcast_rarp;
 	uint32_t		nr_vring;
 	int			async_copy;
+	int			map_populate;
 
 	int			extbuf;
 	int			linearbuf;
lib/vhost/vhost_user.c +2 -2
index 020c993b29..e87ab82e63 100644
@@ -1384,7 +1384,7 @@ vhost_user_mmap_region(struct virtio_net *dev,
 		return -1;
 	}
 
-	populate = dev->async_copy ? MAP_POPULATE : 0;
+	populate = dev->map_populate ? MAP_POPULATE : 0;
 	mmap_addr = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE,
 			MAP_SHARED | populate, region->fd, 0);
 
@@ -1398,7 +1398,7 @@ vhost_user_mmap_region(struct virtio_net *dev,
 	region->host_user_addr = (uint64_t)(uintptr_t)mmap_addr + mmap_offset;
 	mem_set_dump(dev, mmap_addr, mmap_size, false, alignment);
 
-	if (dev->async_copy) {
+	if (dev->map_populate) {
 		if (add_guest_pages(dev, region, alignment) < 0) {
 			VHOST_CONFIG_LOG(dev->ifname, ERR,
 				"adding guest pages to region failed.");
Signature · 1 line
2.54.0
Reviewed-by on v2 1/6
#14 lore raw

Re: [PATCH v2 1/6] vhost: decouple guest pages population from async datapath

Quoted 12 lines · David Marchand

The vhost crypto zero-copy feature relies on the RTE_VHOST_USER_ASYNC_COPY flag to enable guest page tracking (guest_pages array population and MAP_POPULATE during mmap).

Introduce a RTE_VHOST_USER_MAP_POPULATE flag that maps to RTE_VHOST_USER_ASYNC_COPY at this point in time.

Adjust vhost_crypto example and remove the unnecessary ALLOW_EXPERIMENTAL_API flag as this example does not use any experimental APIs.

Quoted 11 lines
---
  doc/guides/prog_guide/vhost_lib.rst | 9 +++++++++
  examples/vhost_crypto/Makefile      | 1 -
  examples/vhost_crypto/main.c        | 2 +-
  examples/vhost_crypto/meson.build   | 1 -
  lib/vhost/rte_vhost.h               | 1 +
  lib/vhost/socket.c                  | 9 +++++++++
  lib/vhost/vhost.h                   | 1 +
  lib/vhost/vhost_user.c              | 4 ++--
  8 files changed, 23 insertions(+), 5 deletions(-)

Sounds reasonable to keep the same value as RTE_VHOST_USER_ASYNC_COPY to not break compatibility for existing Vhsot-crypto applications.

Thanks,
Maxime

#15 lore raw

PATCH v2 2/6 examples/vhost: stop using async datapath

In reply to David Marchand

Stop using vhost async as this feature will be removed in a next commit. Thanks to this, we can drop use of experimental api.

---
Changes since RFC:
- dropped vhost_crypto changes (now handled in patch 1),

---
 examples/vhost/Makefile    |   2 -
 examples/vhost/main.c      | 436 +------------------------------------
 examples/vhost/main.h      |  21 +-
 examples/vhost/meson.build |   2 -
 4 files changed, 12 insertions(+), 449 deletions(-)
examples/vhost/Makefile +0 -2
index 5b3cea0778..6e0114d094 100644
@@ -28,8 +28,6 @@ CFLAGS += -O3 $(shell $(PKGCONF) --cflags libdpdk)
 LDFLAGS_SHARED = $(shell $(PKGCONF) --libs libdpdk)
 LDFLAGS_STATIC = $(shell $(PKGCONF) --static --libs libdpdk)
 
-CFLAGS += -DALLOW_EXPERIMENTAL_API
-
 build/$(APP)-shared: $(SRCS-y) Makefile $(PC_FILE) | build
 	$(CC) $(CFLAGS) $(SRCS-y) -o $@ $(LDFLAGS) $(LDFLAGS_SHARED)
 
examples/vhost/main.c +10 -426

603 lines not on this page · raw message

examples/vhost/main.h +2 -19
index c986cbc5a9..3cf6bd7f07 100644
@@ -8,7 +8,6 @@
 #include <sys/queue.h>
 
 #include <rte_ether.h>
-#include <rte_pci.h>
 
 /* Macros for printing using RTE_LOG */
 #define RTE_LOGTYPE_VHOST_CONFIG RTE_LOGTYPE_USER1
@@ -92,17 +91,6 @@ struct lcore_info {
 	struct vhost_dev_tailq_list vdev_list;
 };
 
-struct dma_info {
-	struct rte_pci_addr addr;
-	int16_t dev_id;
-	bool async_enabled;
-};
-
-struct dma_for_vhost {
-	struct dma_info dmas[RTE_MAX_QUEUES_PER_PORT * 2];
-	uint32_t async_flag;
-};
-
 /* we implement non-extra virtio net features */
 #define VIRTIO_NET_FEATURES	0
 
@@ -116,14 +104,9 @@ uint16_t builtin_enqueue_pkts(struct vhost_dev *dev, uint16_t queue_id,
 uint16_t builtin_dequeue_pkts(struct vhost_dev *dev, uint16_t queue_id,
 			struct rte_mempool *mbuf_pool,
 			struct rte_mbuf **pkts, uint16_t count);
-uint16_t sync_enqueue_pkts(struct vhost_dev *dev, uint16_t queue_id,
-			 struct rte_mbuf **pkts, uint32_t count);
-uint16_t sync_dequeue_pkts(struct vhost_dev *dev, uint16_t queue_id,
-			struct rte_mempool *mbuf_pool,
-			struct rte_mbuf **pkts, uint16_t count);
-uint16_t async_enqueue_pkts(struct vhost_dev *dev, uint16_t queue_id,
+uint16_t enqueue_pkts(struct vhost_dev *dev, uint16_t queue_id,
 			 struct rte_mbuf **pkts, uint32_t count);
-uint16_t async_dequeue_pkts(struct vhost_dev *dev, uint16_t queue_id,
+uint16_t dequeue_pkts(struct vhost_dev *dev, uint16_t queue_id,
 			struct rte_mempool *mbuf_pool,
 			struct rte_mbuf **pkts, uint16_t count);
 #endif /* _MAIN_H_ */
examples/vhost/meson.build +0 -2
index e938be8f45..a04852bb2f 100644
@@ -12,8 +12,6 @@ if not is_linux
 endif
 
 deps += 'vhost'
-deps += 'dmadev'
-allow_experimental_apis = true
 sources = files(
         'main.c',
         'virtio_net.c',
Signature · 1 line
2.54.0
Reviewed-by on v2 2/6
#16 lore raw

Re: [PATCH v2 2/6] examples/vhost: stop using async datapath

Quoted 8 lines · David Marchand

Stop using vhost async as this feature will be removed in a next commit. Thanks to this, we can drop use of experimental api.

---
Changes since RFC:
- dropped vhost_crypto changes (now handled in patch 1),

Quoted 7 lines
---
  examples/vhost/Makefile    |   2 -
  examples/vhost/main.c      | 436 +------------------------------------
  examples/vhost/main.h      |  21 +-
  examples/vhost/meson.build |   2 -
  4 files changed, 12 insertions(+), 449 deletions(-)

Thanks,
Maxime

#17 lore raw

PATCH v2 3/6 examples/vdpa: remove dependency on PCI library

In reply to David Marchand

This is some forgotten unneeded header include from a previous refactoring.

Fixes 38f8ab0bbc8d ("vhost: make vDPA framework bus agnostic")
---
 examples/vdpa/main.c | 1 -
 1 file changed, 1 deletion(-)
examples/vdpa/main.c +0 -1
index ac6da79b05..79bfe7022a 100644
@@ -13,7 +13,6 @@
 #include <rte_malloc.h>
 #include <rte_vhost.h>
 #include <rte_vdpa.h>
-#include <rte_pci.h>
 #include <rte_string_fns.h>
 
 #include <cmdline_socket.h>
Signature · 1 line
2.54.0
Reviewed-by on v2 3/6
#18 lore raw

Re: [PATCH v2 3/6] examples/vdpa: remove dependency on PCI library

Quoted 15 lines · David Marchand

This is some forgotten unneeded header include from a previous refactoring.

Fixes 38f8ab0bbc8d ("vhost: make vDPA framework bus agnostic")
---
  examples/vdpa/main.c | 1 -
  1 file changed, 1 deletion(-)
examples/vdpa/main.c +0 -0
index ac6da79b05..79bfe7022a 100644

examples/vdpa/main.c line 18

Quoted 7 lines
examples/vdpa/main.c +0 -1
@@ -13,7 +13,6 @@
  #include <rte_malloc.h>
  #include <rte_vhost.h>
  #include <rte_vdpa.h>
-#include <rte_pci.h>
  #include <rte_string_fns.h>
 
  #include <cmdline_socket.h>

Thanks,
Maxime

#19 lore raw

PATCH v2 4/6 vhost: drop async datapath

In reply to David Marchand

All the API related to this feature is experimental, allowing us by the project policy to drop the feature in one go.

---
Changes since v1:
- dropped dependency on PCI library,

Changes since RFC:
- kept mmap populate behavior for vhost_crypto,

---
 doc/guides/prog_guide/vhost_lib.rst    |  151 +-
 doc/guides/rel_notes/release_26_11.rst |   20 +
 lib/vhost/meson.build                  |    3 +-
 lib/vhost/rte_vhost.h                  |    3 +-
 lib/vhost/rte_vhost_async.h            |  293 ---
 lib/vhost/socket.c                     |   21 -
 lib/vhost/vhost.c                      |  434 ----
 lib/vhost/vhost.h                      |  115 -
 lib/vhost/vhost_user.c                 |  111 -
 lib/vhost/virtio_net.c                 | 3275 +++++-------------------
 10 files changed, 687 insertions(+), 3739 deletions(-)
 delete mode 100644 lib/vhost/rte_vhost_async.h
doc/guides/prog_guide/vhost_lib.rst +5 -146
index 2bea814a62..81f6115483 100644
@@ -103,21 +103,6 @@ The following is an overview of some key Vhost API functions:
 
     It is disabled by default.
 
-  - ``RTE_VHOST_USER_ASYNC_COPY``
-
-    Asynchronous data path will be enabled when this flag is set. Async
-    data path allows applications to enable DMA acceleration for vhost
-    queues. Vhost leverages the registered DMA channels to free CPU from
-    memory copy operations in data path. A set of async data path APIs are
-    defined for DPDK applications to make use of the async capability. Only
-    packets enqueued/dequeued by async APIs are processed through the async
-    data path.
-
-    Currently this feature is only implemented on split ring enqueue data
-    path.
-
-    It is disabled by default.
-
   - ``RTE_VHOST_USER_MAP_POPULATE``
 
     Guest memory regions will be mapped with ``MAP_POPULATE`` when this flag
@@ -236,76 +221,6 @@ The following is an overview of some key Vhost API functions:
 
   Enable or disable zero copy feature of the vhost crypto backend.
 
-* ``rte_vhost_async_dma_configure(dma_id, vchan_id)``
-
-  Tell vhost which DMA vChannel is going to use. This function needs to
-  be called before register async data-path for vring.
-
-* ``rte_vhost_async_channel_register(vid, queue_id)``
-
-  Register async DMA acceleration for a vhost queue after vring is enabled.
-
-* ``rte_vhost_async_channel_register_thread_unsafe(vid, queue_id)``
-
-  Register async DMA acceleration for a vhost queue without performing
-  any locking.
-
-  This function is only safe to call in vhost callback functions
-  (i.e., struct rte_vhost_device_ops).
-
-* ``rte_vhost_async_channel_unregister(vid, queue_id)``
-
-  Unregister the async DMA acceleration from a vhost queue.
-  Unregistration will fail, if the vhost queue has in-flight
-  packets that are not completed.
-
-  Unregister async DMA acceleration in vring_state_changed() may
-  fail, as this API tries to acquire the spinlock of vhost
-  queue. The recommended way is to unregister async copy
-  devices for all vhost queues in destroy_device(), when a
-  virtio device is paused or shut down.
-
-* ``rte_vhost_async_channel_unregister_thread_unsafe(vid, queue_id)``
-
-  Unregister async DMA acceleration for a vhost queue without performing
-  any locking.
-
-  This function is only safe to call in vhost callback functions
-  (i.e., struct rte_vhost_device_ops).
-
-* ``rte_vhost_submit_enqueue_burst(vid, queue_id, pkts, count, dma_id, vchan_id)``
-
-  Submit an enqueue request to transmit ``count`` packets from host to guest
-  by async data path. Applications must not free the packets submitted for
-  enqueue until the packets are completed.
-
-* ``rte_vhost_poll_enqueue_completed(vid, queue_id, pkts, count, dma_id, vchan_id)``
-
-  Poll enqueue completion status from async data path. Completed packets
-  are returned to applications through ``pkts``.
-
-* ``rte_vhost_async_get_inflight(vid, queue_id)``
-
-  This function returns the amount of in-flight packets for the vhost
-  queue using async acceleration.
-
- * ``rte_vhost_async_get_inflight_thread_unsafe(vid, queue_id)``
-
-  Get the number of inflight packets for a vhost queue without performing
-  any locking. It should only be used within the vhost ops, which already
-  holds the lock.
-
-* ``rte_vhost_clear_queue_thread_unsafe(vid, queue_id, **pkts, count, dma_id, vchan_id)``
-
-  Clear in-flight packets which are submitted to async channel in vhost
-  async data path without performing locking on virtqueue. Completed
-  packets are returned to applications through ``pkts``.
-
-* ``rte_vhost_clear_queue(vid, queue_id, **pkts, count, dma_id, vchan_id)``
-
-  Clear in-flight packets which are submitted to async channel in vhost async data
-  path. Completed packets are returned to applications through ``pkts``.
-
 * ``rte_vhost_vring_call_nonblock(int vid, uint16_t vring_idx)``
 
   Notify the guest that used descriptors have been added to the vring. This function
@@ -327,22 +242,11 @@ The following is an overview of some key Vhost API functions:
   This function resets the queue statistics. It requires statistics
   collection to be enabled at registration time.
 
-* ``rte_vhost_async_try_dequeue_burst(vid, queue_id, mbuf_pool, pkts, count,
-  nr_inflight, dma_id, vchan_id)``
-
-  Receive ``count`` packets from guest to host in async data path,
-  and store them at ``pkts``.
-
 * ``rte_vhost_driver_get_vdpa_dev_type(path, type)``
 
   Get device type of vDPA device, such as VDPA_DEVICE_TYPE_NET,
   VDPA_DEVICE_TYPE_BLK.
 
-* ``rte_vhost_async_dma_unconfigure(dma_id, vchan_id)``
-
-  Clean up a DMA vChannel after use is finished. After this function is called,
-  the specified DMA vChannel should no longer be used by the Vhost library.
-
 * ``rte_vhost_notify_guest(int vid, uint16_t queue_id)``
 
   Inject the offloaded interrupt received by the 'guest_notify' callback,
@@ -411,16 +315,11 @@ Guest memory requirement
 
 * Memory pre-allocation
 
-  For non-async data path guest memory pre-allocation is not a
-  must but can help save memory. To do this we can add option
-  ``-mem-prealloc`` when starting QEMU, or we can lock all memory at vhost
-  side which will force memory to be allocated when it calls mmap
-  (option --mlockall in ovs-dpdk is an example in hand).
-
-
-  For async data path, we force the VM memory to be pre-allocated at vhost
-  lib when mapping the guest memory; and also we need to lock the memory to
-  prevent pages being swapped out to disk.
+  Guest memory pre-allocation is not a must but can help save memory.
+  To do this we can add option ``-mem-prealloc`` when starting QEMU,
+  or we can lock all memory at vhost side which will force memory to
+  be allocated when it calls mmap (option --mlockall in ovs-dpdk is
+  an example in hand).
 
 * Memory sharing
 
@@ -491,43 +390,3 @@ Finally, a set of device ops is defined for device specific operations:
 * ``get_notify_area``
 
   Called to get the notify area info of the queue.
-
-Vhost asynchronous data path
-----------------------------
-
-Vhost asynchronous data path leverages DMA devices to offload memory
-copies from the CPU and it is implemented in an asynchronous way. It
-enables applications, like OVS, to save CPU cycles and hide memory copy
-overhead, thus achieving higher throughput.
-
-Vhost doesn't manage DMA devices and applications, like OVS, need to
-manage and configure DMA devices. Applications need to tell vhost what
-DMA devices to use in every data path function call. This design enables
-the flexibility for applications to dynamically use DMA channels in
-different function modules, not limited in vhost.
-
-In addition, vhost supports M:N mapping between vrings and DMA virtual
-channels. Specifically, one vring can use multiple different DMA channels
-and one DMA channel can be shared by multiple vrings at the same time.
-The reason of enabling one vring to use multiple DMA channels is that
-it's possible that more than one dataplane threads enqueue packets to
-the same vring with their own DMA virtual channels. Besides, the number
-of DMA devices is limited. For the purpose of scaling, it's necessary to
-support sharing DMA channels among vrings.
-
-* Async enqueue API usage
-
-  In async enqueue path, rte_vhost_poll_enqueue_completed() needs to be
-  called in time to notify the guest of DMA copy completed packets.
-  Moreover, calling rte_vhost_submit_enqueue_burst() all the time but
-  not poll completed will cause the DMA ring to be full, which will
-  result in packet loss eventually.
-
-* Recommended IOVA mode in async datapath
-
-  When DMA devices are bound to VFIO driver, VA mode is recommended.
-  For PA mode, page by page mapping may exceed IOMMU's max capability,
-  better to use 1G guest hugepage.
-
-  For UIO driver or kernel driver, any VFIO related error messages
-  can be ignored.
doc/guides/rel_notes/release_26_11.rst +20 -0
index 87c7e81bde..7cf023454d 100644
@@ -79,6 +79,26 @@ Removed Items
     ``rte_rib6_is_equal``
   * table: ``RTE_LPM_IPV6_ADDR_SIZE``
 
+* **Removed vhost async (DMA-accelerated) data path.**
+
+  The experimental async data path APIs have been removed from the vhost library.
+  The following functions and flag are no longer available:
+
+  - ``rte_vhost_async_channel_register``
+  - ``rte_vhost_async_channel_register_thread_unsafe``
+  - ``rte_vhost_async_channel_unregister``
+  - ``rte_vhost_async_channel_unregister_thread_unsafe``
+  - ``rte_vhost_async_dma_configure``
+  - ``rte_vhost_async_dma_unconfigure``
+  - ``rte_vhost_submit_enqueue_burst``
+  - ``rte_vhost_poll_enqueue_completed``
+  - ``rte_vhost_async_try_dequeue_burst``
+  - ``rte_vhost_async_get_inflight``
+  - ``rte_vhost_async_get_inflight_thread_unsafe``
+  - ``rte_vhost_clear_queue``
+  - ``rte_vhost_clear_queue_thread_unsafe``
+  - ``RTE_VHOST_USER_ASYNC_COPY``
+
 
 API Changes
 -----------
lib/vhost/meson.build +1 -2
index 6a24981d10..208992fa78 100644
@@ -38,10 +38,9 @@ sources = files(
 headers = files(
         'rte_vdpa.h',
         'rte_vhost.h',
-        'rte_vhost_async.h',
         'rte_vhost_crypto.h',
 )
 driver_sdk_headers = files(
         'vdpa_driver.h',
 )
-deps += ['ethdev', 'cryptodev', 'hash', 'pci', 'dmadev']
+deps += ['ethdev', 'cryptodev', 'hash']
lib/vhost/rte_vhost.h +1 -2
index 095f9b6d3c..79a4138c62 100644
@@ -38,8 +38,7 @@ extern "C" {
 #define RTE_VHOST_USER_EXTBUF_SUPPORT	(1ULL << 5)
 /* support only linear buffers (no chained mbufs) */
 #define RTE_VHOST_USER_LINEARBUF_SUPPORT	(1ULL << 6)
-#define RTE_VHOST_USER_ASYNC_COPY	(1ULL << 7)
-#define RTE_VHOST_USER_MAP_POPULATE	RTE_VHOST_USER_ASYNC_COPY
+#define RTE_VHOST_USER_MAP_POPULATE	(1ULL << 7)
 #define RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS	(1ULL << 8)
 #define RTE_VHOST_USER_NET_STATS_ENABLE	(1ULL << 9)
 #define RTE_VHOST_USER_ASYNC_CONNECT	(1ULL << 10)
lib/vhost/rte_vhost_async.h deleted +0 -293

293 lines not on this page · raw message

lib/vhost/socket.c +0 -21
index 8b29271f97..cffec0fa54 100644
@@ -43,7 +43,6 @@ struct vhost_user_socket {
 	bool use_builtin_virtio_net;
 	bool extbuf;
 	bool linearbuf;
-	bool async_copy;
 	bool map_populate;
 	bool net_compliant_ol_flags;
 	bool stats_enabled;
@@ -242,13 +241,6 @@ vhost_user_add_connection(int fd, struct vhost_user_socket *vsocket)
 	if (vsocket->linearbuf)
 		vhost_enable_linearbuf(vid);
 
-	if (vsocket->async_copy) {
-		dev = get_device(vid);
-
-		if (dev)
-			dev->async_copy = 1;
-	}
-
 	if (vsocket->map_populate) {
 		dev = get_device(vid);
 
@@ -946,7 +938,6 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
 	vsocket->max_queue_pairs = VHOST_MAX_QUEUE_PAIRS;
 	vsocket->extbuf = flags & RTE_VHOST_USER_EXTBUF_SUPPORT;
 	vsocket->linearbuf = flags & RTE_VHOST_USER_LINEARBUF_SUPPORT;
-	vsocket->async_copy = flags & RTE_VHOST_USER_ASYNC_COPY;
 	vsocket->map_populate = flags & RTE_VHOST_USER_MAP_POPULATE;
 	vsocket->net_compliant_ol_flags = flags & RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS;
 	vsocket->stats_enabled = flags & RTE_VHOST_USER_NET_STATS_ENABLE;
@@ -956,12 +947,6 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
 	else
 		vsocket->iommu_support = flags & RTE_VHOST_USER_IOMMU_SUPPORT;
 
-	if (vsocket->async_copy && (vsocket->iommu_support ||
-				(flags & RTE_VHOST_USER_POSTCOPY_SUPPORT))) {
-		VHOST_CONFIG_LOG(path, ERR, "async copy with IOMMU or post-copy not supported");
-		goto out_mutex;
-	}
-
 	/*
 	 * Set the supported features correctly for the builtin vhost-user
 	 * net driver.
@@ -984,12 +969,6 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
 		vsocket->protocol_features  = VHOST_USER_PROTOCOL_FEATURES;
 	}
 
-	if (vsocket->async_copy) {
-		vsocket->supported_features &= ~(1ULL << VHOST_F_LOG_ALL);
-		vsocket->features &= ~(1ULL << VHOST_F_LOG_ALL);
-		VHOST_CONFIG_LOG(path, INFO, "logging feature is disabled in async copy mode");
-	}
-
 	/*
 	 * We'll not be able to receive a buffer from guest in linear mode
 	 * without external buffer if it will not fit in a single mbuf, which is
lib/vhost/vhost.c +0 -434

463 lines not on this page · raw message

lib/vhost/vhost.h +0 -115

150 lines not on this page · raw message

lib/vhost/vhost_user.c +0 -111

177 lines not on this page · raw message

lib/vhost/virtio_net.c +660 -2615

1,637 lines not on this page · raw message

The rest of this diff is not shown. View the raw message.

Signature · 1 line
2.54.0

Part of the diff is not shown here. View the raw message.

#20 lore raw

PATCH v2 5/6 vhost: rename packed layout helpers for batches

In reply to David Marchand

Now that the async datapath has been removed, the _sync in function names gives no useful information.

Besides, vhost_reserve_avail_batch_packed does not reserve anything and its name is confusing, rename it following the other rx/tx split/packed helpers convention.

---
 lib/vhost/virtio_net.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)
lib/vhost/virtio_net.c +6 -8
index 9ad7fa3295..79034ae036 100644
@@ -1111,7 +1111,7 @@ virtio_dev_rx_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
 }
 
 static __rte_always_inline int
-virtio_dev_rx_sync_batch_check(struct virtio_net *dev,
+virtio_dev_rx_batch_check(struct virtio_net *dev,
 			   struct vhost_virtqueue *vq,
 			   struct rte_mbuf **pkts,
 			   uint64_t *desc_addrs,
@@ -1213,7 +1213,7 @@ virtio_dev_rx_batch_packed_copy(struct virtio_net *dev,
 }
 
 static __rte_always_inline int
-virtio_dev_rx_sync_batch_packed(struct virtio_net *dev,
+virtio_dev_rx_batch_packed(struct virtio_net *dev,
 			   struct vhost_virtqueue *vq,
 			   struct rte_mbuf **pkts)
 	__rte_requires_shared_capability(&vq->iotlb_lock)
@@ -1221,7 +1221,7 @@ virtio_dev_rx_sync_batch_packed(struct virtio_net *dev,
 	uint64_t desc_addrs[PACKED_BATCH_SIZE];
 	uint64_t lens[PACKED_BATCH_SIZE];
 
-	if (virtio_dev_rx_sync_batch_check(dev, vq, pkts, desc_addrs, lens) == -1)
+	if (virtio_dev_rx_batch_check(dev, vq, pkts, desc_addrs, lens) == -1)
 		return -1;
 
 	if (vq->shadow_used_idx) {
@@ -1273,8 +1273,7 @@ virtio_dev_rx_packed(struct virtio_net *dev,
 		rte_prefetch0(&vq->desc_packed[vq->last_avail_idx]);
 
 		if (count - pkt_idx >= PACKED_BATCH_SIZE) {
-			if (!virtio_dev_rx_sync_batch_packed(dev, vq,
-							&pkts[pkt_idx])) {
+			if (!virtio_dev_rx_batch_packed(dev, vq, &pkts[pkt_idx])) {
 				pkt_idx += PACKED_BATCH_SIZE;
 				continue;
 			}
@@ -1971,7 +1970,7 @@ virtio_dev_tx_split_compliant(struct virtio_net *dev,
 }
 
 static __rte_always_inline int
-vhost_reserve_avail_batch_packed(struct virtio_net *dev,
+virtio_dev_tx_batch_packed_check(struct virtio_net *dev,
 				 struct vhost_virtqueue *vq,
 				 struct rte_mbuf **pkts,
 				 uint16_t avail_idx,
@@ -2055,8 +2054,7 @@ virtio_dev_tx_batch_packed(struct virtio_net *dev,
 	uint16_t ids[PACKED_BATCH_SIZE];
 	uint16_t i;
 
-	if (vhost_reserve_avail_batch_packed(dev, vq, pkts, avail_idx,
-					     desc_addrs, ids))
+	if (virtio_dev_tx_batch_packed_check(dev, vq, pkts, avail_idx, desc_addrs, ids))
 		return -1;
 
 	vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
Signature · 1 line
2.54.0
#21 lore raw

PATCH v2 6/6 vhost: simplify some descriptor handling

In reply to David Marchand

Now that the async datapath has been removed, move back the descriptors copy/filling code in desc_to_mbuf/mbuf_to_desc and eliminate an intermediate helper.

Tracking buf_iova is not needed in the descriptor to mbuf case.

---
 lib/vhost/virtio_net.c | 78 ++++++++++++++++--------------------------
 1 file changed, 30 insertions(+), 48 deletions(-)
lib/vhost/virtio_net.c +30 -48
index 79034ae036..9b1ef8f10c 100644
@@ -76,6 +76,12 @@ vhost_queue_stats_update(const struct virtio_net *dev, struct vhost_virtqueue *v
 	}
 }
 
+static __rte_always_inline bool
+vhost_can_batch_copy(struct vhost_virtqueue *vq, uint32_t cpy_len)
+{
+	return cpy_len <= MAX_BATCH_LEN && vq->batch_copy_nb_elems < vq->size;
+}
+
 static inline void
 do_data_copy_enqueue(struct virtio_net *dev, struct vhost_virtqueue *vq)
 	__rte_requires_shared_capability(&vq->iotlb_lock)
@@ -843,44 +849,6 @@ copy_vnet_hdr_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	}
 }
 
-static __rte_always_inline void
-sync_fill_seg(struct virtio_net *dev, struct vhost_virtqueue *vq,
-		struct rte_mbuf *m, uint32_t mbuf_offset,
-		uint64_t buf_addr, uint64_t buf_iova, uint32_t cpy_len, bool to_desc)
-	__rte_requires_shared_capability(&vq->iotlb_lock)
-{
-	struct batch_copy_elem *batch_copy = vq->batch_copy_elems;
-
-	if (likely(cpy_len > MAX_BATCH_LEN || vq->batch_copy_nb_elems >= vq->size)) {
-		if (to_desc) {
-			rte_memcpy((void *)((uintptr_t)(buf_addr)),
-				rte_pktmbuf_mtod_offset(m, void *, mbuf_offset),
-				cpy_len);
-			vhost_log_cache_write_iova(dev, vq, buf_iova, cpy_len);
-			PRINT_PACKET(dev, (uintptr_t)(buf_addr), cpy_len, 0);
-		} else {
-			rte_memcpy(rte_pktmbuf_mtod_offset(m, void *, mbuf_offset),
-				(void *)((uintptr_t)(buf_addr)),
-				cpy_len);
-		}
-	} else {
-		if (to_desc) {
-			batch_copy[vq->batch_copy_nb_elems].dst =
-				(void *)((uintptr_t)(buf_addr));
-			batch_copy[vq->batch_copy_nb_elems].src =
-				rte_pktmbuf_mtod_offset(m, void *, mbuf_offset);
-			batch_copy[vq->batch_copy_nb_elems].log_addr = buf_iova;
-		} else {
-			batch_copy[vq->batch_copy_nb_elems].dst =
-				rte_pktmbuf_mtod_offset(m, void *, mbuf_offset);
-			batch_copy[vq->batch_copy_nb_elems].src =
-				(void *)((uintptr_t)(buf_addr));
-		}
-		batch_copy[vq->batch_copy_nb_elems].len = cpy_len;
-		vq->batch_copy_nb_elems++;
-	}
-}
-
 static __rte_always_inline int
 mbuf_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
 		struct rte_mbuf *m, struct buf_vector *buf_vec,
@@ -976,9 +944,22 @@ mbuf_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
 
 		cpy_len = RTE_MIN(buf_avail, mbuf_avail);
 
-		sync_fill_seg(dev, vq, m, mbuf_offset,
-			      buf_addr + buf_offset,
-			      buf_iova + buf_offset, cpy_len, true);
+		if (likely(!vhost_can_batch_copy(vq, cpy_len))) {
+			rte_memcpy(RTE_PTR_ADD(buf_addr, buf_offset),
+				rte_pktmbuf_mtod_offset(m, void *, mbuf_offset),
+				cpy_len);
+			vhost_log_cache_write_iova(dev, vq, buf_iova + buf_offset, cpy_len);
+			PRINT_PACKET(dev, RTE_PTR_ADD(buf_addr, buf_offset), cpy_len, 0);
+		} else {
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].dst =
+				RTE_PTR_ADD(buf_addr, buf_offset);
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].src =
+				rte_pktmbuf_mtod_offset(m, void *, mbuf_offset);
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].log_addr =
+				buf_iova + buf_offset;
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].len = cpy_len;
+			vq->batch_copy_nb_elems++;
+		}
 
 		mbuf_avail  -= cpy_len;
 		mbuf_offset += cpy_len;
@@ -1679,7 +1660,7 @@ desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	__rte_requires_shared_capability(&vq->iotlb_lock)
 {
 	uint32_t buf_avail, buf_offset, buf_len;
-	uint64_t buf_addr, buf_iova;
+	uint64_t buf_addr;
 	uint32_t mbuf_avail, mbuf_offset;
 	uint32_t hdr_remain = dev->vhost_hlen;
 	uint32_t cpy_len;
@@ -1710,7 +1691,6 @@ desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	}
 
 	buf_addr = buf_vec[vec_idx].buf_addr;
-	buf_iova = buf_vec[vec_idx].buf_iova;
 	buf_len = buf_vec[vec_idx].buf_len;
 	buf_offset = hdr_remain;
 	buf_avail = buf_vec[vec_idx].buf_len - hdr_remain;
@@ -1725,14 +1705,17 @@ desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	while (1) {
 		cpy_len = RTE_MIN(buf_avail, mbuf_avail);
 
-		if (likely(hdr && cur == m)) {
+		if (likely((hdr && cur == m) || !vhost_can_batch_copy(vq, cpy_len))) {
 			rte_memcpy(rte_pktmbuf_mtod_offset(cur, void *, mbuf_offset),
 				(void *)((uintptr_t)(buf_addr + buf_offset)),
 				cpy_len);
 		} else {
-			sync_fill_seg(dev, vq, cur, mbuf_offset,
-				      buf_addr + buf_offset,
-				      buf_iova + buf_offset, cpy_len, false);
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].dst =
+				rte_pktmbuf_mtod_offset(cur, void *, mbuf_offset);
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].src =
+				RTE_PTR_ADD(buf_addr, buf_offset);
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].len = cpy_len;
+			vq->batch_copy_nb_elems++;
 		}
 
 		mbuf_avail  -= cpy_len;
@@ -1746,7 +1729,6 @@ desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
 				break;
 
 			buf_addr = buf_vec[vec_idx].buf_addr;
-			buf_iova = buf_vec[vec_idx].buf_iova;
 			buf_len = buf_vec[vec_idx].buf_len;
 
 			buf_offset = 0;
Signature · 1 line
2.54.0
#22 lore raw

v3 cover Drop vhost async (DMA-accelerated) datapath

In reply to David Marchand

The integration of this feature in OVS has been postponed following feedback how the current API forced the complexity on the application side. There is no contributor working on making those changes.

The feature has no other identified opensource consumer.

On the other hand, this feature has been left unattended for some years now while the "normal" datapath is actively maintained.
It is highly likely the async datapath code, which never underwent a stabilisation phase, is riddled with bugs.

Given the craziness around finding security bugs with AI, and since the vhost library is a good target, I propose to drop this feature and reduce the library attack surface.

There is one complication with the vhost_crypto and some external applications that seemed to rely on the async flag to track and populate guest pages, so a new flag replacing async is added by this series.

Signature · 47 lines
David Marchand

Changes since v2:
- updated release notes and vhost example documentation,
- removed some async statistics missed in previous revisions,
- re-added checks on map populate and post copy or other virtio features,

Changes since v1:
- removed unneeded dependencies on the PCI library,

Changes since RFC:
- maintained guest pages population in a new flag (vhost_crypto/SPDK),
- removed remaining helpers which had sync_ in their names,


David Marchand (6):
  vhost: decouple guest pages population from async datapath
  examples/vhost: stop using async datapath
  examples/vdpa: remove dependency on PCI library
  vhost: drop async datapath
  vhost: rename packed layout helpers for batches
  vhost: simplify some descriptor handling

 doc/guides/prog_guide/vhost_lib.rst    |  152 +-
 doc/guides/rel_notes/release_26_11.rst |   24 +
 doc/guides/sample_app_ug/vhost.rst     |   10 -
 examples/vdpa/main.c                   |    1 -
 examples/vhost/Makefile                |    2 -
 examples/vhost/main.c                  |  437 +---
 examples/vhost/main.h                  |   21 +-
 examples/vhost/meson.build             |    2 -
 examples/vhost_crypto/Makefile         |    1 -
 examples/vhost_crypto/main.c           |    2 +-
 examples/vhost_crypto/meson.build      |    1 -
 lib/vhost/meson.build                  |    3 +-
 lib/vhost/rte_vhost.h                  |    2 +-
 lib/vhost/rte_vhost_async.h            |  293 ---
 lib/vhost/socket.c                     |   18 +-
 lib/vhost/vhost.c                      |  436 ----
 lib/vhost/vhost.h                      |  118 +-
 lib/vhost/vhost_user.c                 |  115 +-
 lib/vhost/virtio_net.c                 | 3317 +++++-------------------
 19 files changed, 729 insertions(+), 4226 deletions(-)
 delete mode 100644 lib/vhost/rte_vhost_async.h

-- 
2.54.0
#23 lore raw

PATCH v3 1/6 vhost: decouple guest pages population from async datapath

The vhost crypto zero-copy feature relies on the RTE_VHOST_USER_ASYNC_COPY flag to enable guest page tracking (guest_pages array population and MAP_POPULATE during mmap).

Introduce a RTE_VHOST_USER_MAP_POPULATE flag that maps to RTE_VHOST_USER_ASYNC_COPY at this point in time.

Adjust vhost_crypto example and remove the unnecessary ALLOW_EXPERIMENTAL_API flag as this example does not use any experimental APIs.

---
Changes since v2:
- updated release notes for new flag,
- fixed checks on map populate feature,

---
 doc/guides/prog_guide/vhost_lib.rst    |  9 +++++++++
 doc/guides/rel_notes/release_26_11.rst |  4 ++++
 examples/vhost_crypto/Makefile         |  1 -
 examples/vhost_crypto/main.c           |  2 +-
 examples/vhost_crypto/meson.build      |  1 -
 lib/vhost/rte_vhost.h                  |  1 +
 lib/vhost/socket.c                     | 19 +++++++++++++++----
 lib/vhost/vhost.h                      |  1 +
 lib/vhost/vhost_user.c                 |  4 ++--
 9 files changed, 33 insertions(+), 9 deletions(-)
doc/guides/prog_guide/vhost_lib.rst +9 -0
index 345a621716..2bea814a62 100644
@@ -118,6 +118,15 @@ The following is an overview of some key Vhost API functions:
 
     It is disabled by default.
 
+  - ``RTE_VHOST_USER_MAP_POPULATE``
+
+    Guest memory regions will be mapped with ``MAP_POPULATE`` when this flag
+    is set, pre-faulting pages into memory. This is useful for applications
+    requiring direct access to guest memory, such as vhost-crypto zero-copy
+    operations.
+
+    It is disabled by default.
+
   - ``RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS``
 
     Since v16.04, the vhost library forwards checksum and gso requests for
doc/guides/rel_notes/release_26_11.rst +4 -0
index 030bd84cea..ecc575ff09 100644
@@ -309,6 +309,10 @@ API Changes
     ``rte_event_port_profile_links_get`` and
     ``rte_event_port_profile_unlink``
 
+* vhost: Introduced ``RTE_VHOST_USER_MAP_POPULATE`` as a replacement of
+  ``RTE_VHOST_USER_ASYNC_COPY`` for users that did not rely on the vhost
+  async copy feature but expected guest pages to be prefaulted.
+
 * reorder: Promoted the following API from experimental to stable:
   ``rte_reorder_seqn``, ``rte_reorder_drain_up_to_seqn``,
   ``rte_reorder_min_seqn_set`` and ``rte_reorder_memory_footprint_get``.
examples/vhost_crypto/Makefile +0 -1
index cc7f2abb90..130953c38e 100644
@@ -6,7 +6,6 @@ APP = vhost-crypto
 
 # all source are stored in SRCS-y
 SRCS-y := main.c
-CFLAGS += -DALLOW_EXPERIMENTAL_API
 
 PKGCONF ?= pkg-config
 
examples/vhost_crypto/main.c +1 -1
index 8bdfc40c4b..53bd8fa825 100644
@@ -623,7 +623,7 @@ main(int argc, char *argv[])
 
 		for (j = 0; j < lo->nb_sockets; j++) {
 			ret = rte_vhost_driver_register(lo->socket_files[j],
-				RTE_VHOST_USER_ASYNC_COPY);
+				RTE_VHOST_USER_MAP_POPULATE);
 			if (ret < 0) {
 				RTE_LOG(ERR, USER1, "socket %s already exists\n",
 					lo->socket_files[j]);
examples/vhost_crypto/meson.build +0 -1
index 1c294c286f..47c8fa829f 100644
@@ -6,7 +6,6 @@
 # To build this example as a standalone application with an already-installed
 # DPDK instance, use 'make'
 
-allow_experimental_apis = true
 deps += ['vhost', 'cryptodev']
 sources = files(
         'main.c',
lib/vhost/rte_vhost.h +1 -0
index a7f9700538..095f9b6d3c 100644
@@ -39,6 +39,7 @@ extern "C" {
 /* support only linear buffers (no chained mbufs) */
 #define RTE_VHOST_USER_LINEARBUF_SUPPORT	(1ULL << 6)
 #define RTE_VHOST_USER_ASYNC_COPY	(1ULL << 7)
+#define RTE_VHOST_USER_MAP_POPULATE	RTE_VHOST_USER_ASYNC_COPY
 #define RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS	(1ULL << 8)
 #define RTE_VHOST_USER_NET_STATS_ENABLE	(1ULL << 9)
 #define RTE_VHOST_USER_ASYNC_CONNECT	(1ULL << 10)
lib/vhost/socket.c +15 -4
index 0943b3e9bb..956f3b2d71 100644
@@ -44,6 +44,7 @@ struct vhost_user_socket {
 	bool extbuf;
 	bool linearbuf;
 	bool async_copy;
+	bool map_populate;
 	bool net_compliant_ol_flags;
 	bool stats_enabled;
 	bool async_connect;
@@ -246,6 +247,13 @@ vhost_user_add_connection(int fd, struct vhost_user_socket *vsocket)
 			dev->async_copy = 1;
 	}
 
+	if (vsocket->map_populate) {
+		dev = get_device(vid);
+
+		if (dev)
+			dev->map_populate = 1;
+	}
+
 	VHOST_CONFIG_LOG(vsocket->path, INFO, "new device, handle is %d", vid);
 
 	if (vsocket->notify_ops->new_connection) {
@@ -937,6 +945,7 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
 	vsocket->extbuf = flags & RTE_VHOST_USER_EXTBUF_SUPPORT;
 	vsocket->linearbuf = flags & RTE_VHOST_USER_LINEARBUF_SUPPORT;
 	vsocket->async_copy = flags & RTE_VHOST_USER_ASYNC_COPY;
+	vsocket->map_populate = flags & RTE_VHOST_USER_MAP_POPULATE;
 	vsocket->net_compliant_ol_flags = flags & RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS;
 	vsocket->stats_enabled = flags & RTE_VHOST_USER_NET_STATS_ENABLE;
 	vsocket->async_connect = flags & RTE_VHOST_USER_ASYNC_CONNECT;
@@ -945,9 +954,10 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
 	else
 		vsocket->iommu_support = flags & RTE_VHOST_USER_IOMMU_SUPPORT;
 
-	if (vsocket->async_copy && (vsocket->iommu_support ||
+	if (vsocket->map_populate && (vsocket->iommu_support ||
 				(flags & RTE_VHOST_USER_POSTCOPY_SUPPORT))) {
-		VHOST_CONFIG_LOG(path, ERR, "async copy with IOMMU or post-copy not supported");
+		VHOST_CONFIG_LOG(path, ERR,
+			"guest pages prefaulting not supported with IOMMU or post-copy");
 		goto out_mutex;
 	}
 
@@ -973,10 +983,11 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
 		vsocket->protocol_features  = VHOST_USER_PROTOCOL_FEATURES;
 	}
 
-	if (vsocket->async_copy) {
+	if (vsocket->map_populate) {
 		vsocket->supported_features &= ~(1ULL << VHOST_F_LOG_ALL);
 		vsocket->features &= ~(1ULL << VHOST_F_LOG_ALL);
-		VHOST_CONFIG_LOG(path, INFO, "logging feature is disabled in async copy mode");
+		VHOST_CONFIG_LOG(path, INFO,
+			"logging feature is disabled with guest pages prefaulting");
 	}
 
 	/*
lib/vhost/vhost.h +1 -0
index bb4708aed5..7b5c6ccbe2 100644
@@ -499,6 +499,7 @@ struct __rte_cache_aligned virtio_net {
 	RTE_ATOMIC(int16_t)	broadcast_rarp;
 	uint32_t		nr_vring;
 	int			async_copy;
+	int			map_populate;
 
 	int			extbuf;
 	int			linearbuf;
lib/vhost/vhost_user.c +2 -2
index 020c993b29..e87ab82e63 100644
@@ -1384,7 +1384,7 @@ vhost_user_mmap_region(struct virtio_net *dev,
 		return -1;
 	}
 
-	populate = dev->async_copy ? MAP_POPULATE : 0;
+	populate = dev->map_populate ? MAP_POPULATE : 0;
 	mmap_addr = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE,
 			MAP_SHARED | populate, region->fd, 0);
 
@@ -1398,7 +1398,7 @@ vhost_user_mmap_region(struct virtio_net *dev,
 	region->host_user_addr = (uint64_t)(uintptr_t)mmap_addr + mmap_offset;
 	mem_set_dump(dev, mmap_addr, mmap_size, false, alignment);
 
-	if (dev->async_copy) {
+	if (dev->map_populate) {
 		if (add_guest_pages(dev, region, alignment) < 0) {
 			VHOST_CONFIG_LOG(dev->ifname, ERR,
 				"adding guest pages to region failed.");
Signature · 1 line
2.54.0
#24 lore raw

PATCH v3 2/6 examples/vhost: stop using async datapath

In reply to David Marchand

Stop using vhost async as this feature will be removed in a next commit. Thanks to this, we can drop use of experimental api.

---
Changes since v2:
- removed --dmas option in vhost example doc,

Changes since RFC:
- dropped vhost_crypto changes (now handled in patch 1),

---
 doc/guides/sample_app_ug/vhost.rst |  10 -
 examples/vhost/Makefile            |   2 -
 examples/vhost/main.c              | 437 +----------------------------
 examples/vhost/main.h              |  21 +-
 examples/vhost/meson.build         |   2 -
 5 files changed, 12 insertions(+), 460 deletions(-)
doc/guides/sample_app_ug/vhost.rst +0 -10
index 2726dba604..8e846eae31 100644
@@ -149,16 +149,6 @@ default value is 15.
 A very simple vhost-user net driver which demonstrates how to use the generic
 vhost APIs will be used when this option is given. It is disabled by default.
 
-**--dmas**
-This parameter is used to specify the assigned DMA device of a vhost device.
-Async vhost-user net driver will be used if --dmas is set. For example
---dmas [txd0@00:04.0,txd1@00:04.1,rxd0@00:04.2,rxd1@00:04.3] means use
-DMA channel 00:04.0/00:04.2 for vhost device 0 enqueue/dequeue operation
-and use DMA channel 00:04.1/00:04.3 for vhost device 1 enqueue/dequeue
-operation. The index of the device corresponds to the socket file in order,
-that means vhost device 0 is created through the first socket file, vhost
-device 1 is created through the second socket file, and so on.
-
 **--total-num-mbufs 0-N**
 This parameter sets the number of mbufs to be allocated in mbuf pools,
 the default value is 147456. This is can be used if launch of a port fails
examples/vhost/Makefile +0 -2
index 5b3cea0778..6e0114d094 100644
@@ -28,8 +28,6 @@ CFLAGS += -O3 $(shell $(PKGCONF) --cflags libdpdk)
 LDFLAGS_SHARED = $(shell $(PKGCONF) --libs libdpdk)
 LDFLAGS_STATIC = $(shell $(PKGCONF) --static --libs libdpdk)
 
-CFLAGS += -DALLOW_EXPERIMENTAL_API
-
 build/$(APP)-shared: $(SRCS-y) Makefile $(PC_FILE) | build
 	$(CC) $(CFLAGS) $(SRCS-y) -o $@ $(LDFLAGS) $(LDFLAGS_SHARED)
 
examples/vhost/main.c +10 -427

604 lines not on this page · raw message

examples/vhost/main.h +2 -19
index c986cbc5a9..3cf6bd7f07 100644
@@ -8,7 +8,6 @@
 #include <sys/queue.h>
 
 #include <rte_ether.h>
-#include <rte_pci.h>
 
 /* Macros for printing using RTE_LOG */
 #define RTE_LOGTYPE_VHOST_CONFIG RTE_LOGTYPE_USER1
@@ -92,17 +91,6 @@ struct lcore_info {
 	struct vhost_dev_tailq_list vdev_list;
 };
 
-struct dma_info {
-	struct rte_pci_addr addr;
-	int16_t dev_id;
-	bool async_enabled;
-};
-
-struct dma_for_vhost {
-	struct dma_info dmas[RTE_MAX_QUEUES_PER_PORT * 2];
-	uint32_t async_flag;
-};
-
 /* we implement non-extra virtio net features */
 #define VIRTIO_NET_FEATURES	0
 
@@ -116,14 +104,9 @@ uint16_t builtin_enqueue_pkts(struct vhost_dev *dev, uint16_t queue_id,
 uint16_t builtin_dequeue_pkts(struct vhost_dev *dev, uint16_t queue_id,
 			struct rte_mempool *mbuf_pool,
 			struct rte_mbuf **pkts, uint16_t count);
-uint16_t sync_enqueue_pkts(struct vhost_dev *dev, uint16_t queue_id,
-			 struct rte_mbuf **pkts, uint32_t count);
-uint16_t sync_dequeue_pkts(struct vhost_dev *dev, uint16_t queue_id,
-			struct rte_mempool *mbuf_pool,
-			struct rte_mbuf **pkts, uint16_t count);
-uint16_t async_enqueue_pkts(struct vhost_dev *dev, uint16_t queue_id,
+uint16_t enqueue_pkts(struct vhost_dev *dev, uint16_t queue_id,
 			 struct rte_mbuf **pkts, uint32_t count);
-uint16_t async_dequeue_pkts(struct vhost_dev *dev, uint16_t queue_id,
+uint16_t dequeue_pkts(struct vhost_dev *dev, uint16_t queue_id,
 			struct rte_mempool *mbuf_pool,
 			struct rte_mbuf **pkts, uint16_t count);
 #endif /* _MAIN_H_ */
examples/vhost/meson.build +0 -2
index e938be8f45..a04852bb2f 100644
@@ -12,8 +12,6 @@ if not is_linux
 endif
 
 deps += 'vhost'
-deps += 'dmadev'
-allow_experimental_apis = true
 sources = files(
         'main.c',
         'virtio_net.c',
Signature · 1 line
2.54.0
#25 lore raw

PATCH v3 3/6 examples/vdpa: remove dependency on PCI library

In reply to David Marchand

This is some forgotten unneeded header include from a previous refactoring.

Fixes 38f8ab0bbc8d ("vhost: make vDPA framework bus agnostic")
---
 examples/vdpa/main.c | 1 -
 1 file changed, 1 deletion(-)
examples/vdpa/main.c +0 -1
index ac6da79b05..79bfe7022a 100644
@@ -13,7 +13,6 @@
 #include <rte_malloc.h>
 #include <rte_vhost.h>
 #include <rte_vdpa.h>
-#include <rte_pci.h>
 #include <rte_string_fns.h>
 
 #include <cmdline_socket.h>
Signature · 1 line
2.54.0
#26 lore raw

PATCH v3 4/6 vhost: drop async datapath

In reply to David Marchand

All the API related to this feature is experimental, allowing us by the project policy to drop the feature in one go.

---
Changes since v2:
- removed inflight async statistics,

Changes since v1:
- dropped dependency on PCI library,

Changes since RFC:
- kept mmap populate behavior for vhost_crypto,

---
 doc/guides/prog_guide/vhost_lib.rst    |  151 +-
 doc/guides/rel_notes/release_26_11.rst |   20 +
 lib/vhost/meson.build                  |    3 +-
 lib/vhost/rte_vhost.h                  |    3 +-
 lib/vhost/rte_vhost_async.h            |  293 ---
 lib/vhost/socket.c                     |    9 -
 lib/vhost/vhost.c                      |  436 ----
 lib/vhost/vhost.h                      |  117 -
 lib/vhost/vhost_user.c                 |  111 -
 lib/vhost/virtio_net.c                 | 3275 +++++-------------------
 10 files changed, 687 insertions(+), 3731 deletions(-)
 delete mode 100644 lib/vhost/rte_vhost_async.h
doc/guides/prog_guide/vhost_lib.rst +5 -146
index 2bea814a62..81f6115483 100644
@@ -103,21 +103,6 @@ The following is an overview of some key Vhost API functions:
 
     It is disabled by default.
 
-  - ``RTE_VHOST_USER_ASYNC_COPY``
-
-    Asynchronous data path will be enabled when this flag is set. Async
-    data path allows applications to enable DMA acceleration for vhost
-    queues. Vhost leverages the registered DMA channels to free CPU from
-    memory copy operations in data path. A set of async data path APIs are
-    defined for DPDK applications to make use of the async capability. Only
-    packets enqueued/dequeued by async APIs are processed through the async
-    data path.
-
-    Currently this feature is only implemented on split ring enqueue data
-    path.
-
-    It is disabled by default.
-
   - ``RTE_VHOST_USER_MAP_POPULATE``
 
     Guest memory regions will be mapped with ``MAP_POPULATE`` when this flag
@@ -236,76 +221,6 @@ The following is an overview of some key Vhost API functions:
 
   Enable or disable zero copy feature of the vhost crypto backend.
 
-* ``rte_vhost_async_dma_configure(dma_id, vchan_id)``
-
-  Tell vhost which DMA vChannel is going to use. This function needs to
-  be called before register async data-path for vring.
-
-* ``rte_vhost_async_channel_register(vid, queue_id)``
-
-  Register async DMA acceleration for a vhost queue after vring is enabled.
-
-* ``rte_vhost_async_channel_register_thread_unsafe(vid, queue_id)``
-
-  Register async DMA acceleration for a vhost queue without performing
-  any locking.
-
-  This function is only safe to call in vhost callback functions
-  (i.e., struct rte_vhost_device_ops).
-
-* ``rte_vhost_async_channel_unregister(vid, queue_id)``
-
-  Unregister the async DMA acceleration from a vhost queue.
-  Unregistration will fail, if the vhost queue has in-flight
-  packets that are not completed.
-
-  Unregister async DMA acceleration in vring_state_changed() may
-  fail, as this API tries to acquire the spinlock of vhost
-  queue. The recommended way is to unregister async copy
-  devices for all vhost queues in destroy_device(), when a
-  virtio device is paused or shut down.
-
-* ``rte_vhost_async_channel_unregister_thread_unsafe(vid, queue_id)``
-
-  Unregister async DMA acceleration for a vhost queue without performing
-  any locking.
-
-  This function is only safe to call in vhost callback functions
-  (i.e., struct rte_vhost_device_ops).
-
-* ``rte_vhost_submit_enqueue_burst(vid, queue_id, pkts, count, dma_id, vchan_id)``
-
-  Submit an enqueue request to transmit ``count`` packets from host to guest
-  by async data path. Applications must not free the packets submitted for
-  enqueue until the packets are completed.
-
-* ``rte_vhost_poll_enqueue_completed(vid, queue_id, pkts, count, dma_id, vchan_id)``
-
-  Poll enqueue completion status from async data path. Completed packets
-  are returned to applications through ``pkts``.
-
-* ``rte_vhost_async_get_inflight(vid, queue_id)``
-
-  This function returns the amount of in-flight packets for the vhost
-  queue using async acceleration.
-
- * ``rte_vhost_async_get_inflight_thread_unsafe(vid, queue_id)``
-
-  Get the number of inflight packets for a vhost queue without performing
-  any locking. It should only be used within the vhost ops, which already
-  holds the lock.
-
-* ``rte_vhost_clear_queue_thread_unsafe(vid, queue_id, **pkts, count, dma_id, vchan_id)``
-
-  Clear in-flight packets which are submitted to async channel in vhost
-  async data path without performing locking on virtqueue. Completed
-  packets are returned to applications through ``pkts``.
-
-* ``rte_vhost_clear_queue(vid, queue_id, **pkts, count, dma_id, vchan_id)``
-
-  Clear in-flight packets which are submitted to async channel in vhost async data
-  path. Completed packets are returned to applications through ``pkts``.
-
 * ``rte_vhost_vring_call_nonblock(int vid, uint16_t vring_idx)``
 
   Notify the guest that used descriptors have been added to the vring. This function
@@ -327,22 +242,11 @@ The following is an overview of some key Vhost API functions:
   This function resets the queue statistics. It requires statistics
   collection to be enabled at registration time.
 
-* ``rte_vhost_async_try_dequeue_burst(vid, queue_id, mbuf_pool, pkts, count,
-  nr_inflight, dma_id, vchan_id)``
-
-  Receive ``count`` packets from guest to host in async data path,
-  and store them at ``pkts``.
-
 * ``rte_vhost_driver_get_vdpa_dev_type(path, type)``
 
   Get device type of vDPA device, such as VDPA_DEVICE_TYPE_NET,
   VDPA_DEVICE_TYPE_BLK.
 
-* ``rte_vhost_async_dma_unconfigure(dma_id, vchan_id)``
-
-  Clean up a DMA vChannel after use is finished. After this function is called,
-  the specified DMA vChannel should no longer be used by the Vhost library.
-
 * ``rte_vhost_notify_guest(int vid, uint16_t queue_id)``
 
   Inject the offloaded interrupt received by the 'guest_notify' callback,
@@ -411,16 +315,11 @@ Guest memory requirement
 
 * Memory pre-allocation
 
-  For non-async data path guest memory pre-allocation is not a
-  must but can help save memory. To do this we can add option
-  ``-mem-prealloc`` when starting QEMU, or we can lock all memory at vhost
-  side which will force memory to be allocated when it calls mmap
-  (option --mlockall in ovs-dpdk is an example in hand).
-
-
-  For async data path, we force the VM memory to be pre-allocated at vhost
-  lib when mapping the guest memory; and also we need to lock the memory to
-  prevent pages being swapped out to disk.
+  Guest memory pre-allocation is not a must but can help save memory.
+  To do this we can add option ``-mem-prealloc`` when starting QEMU,
+  or we can lock all memory at vhost side which will force memory to
+  be allocated when it calls mmap (option --mlockall in ovs-dpdk is
+  an example in hand).
 
 * Memory sharing
 
@@ -491,43 +390,3 @@ Finally, a set of device ops is defined for device specific operations:
 * ``get_notify_area``
 
   Called to get the notify area info of the queue.
-
-Vhost asynchronous data path
-----------------------------
-
-Vhost asynchronous data path leverages DMA devices to offload memory
-copies from the CPU and it is implemented in an asynchronous way. It
-enables applications, like OVS, to save CPU cycles and hide memory copy
-overhead, thus achieving higher throughput.
-
-Vhost doesn't manage DMA devices and applications, like OVS, need to
-manage and configure DMA devices. Applications need to tell vhost what
-DMA devices to use in every data path function call. This design enables
-the flexibility for applications to dynamically use DMA channels in
-different function modules, not limited in vhost.
-
-In addition, vhost supports M:N mapping between vrings and DMA virtual
-channels. Specifically, one vring can use multiple different DMA channels
-and one DMA channel can be shared by multiple vrings at the same time.
-The reason of enabling one vring to use multiple DMA channels is that
-it's possible that more than one dataplane threads enqueue packets to
-the same vring with their own DMA virtual channels. Besides, the number
-of DMA devices is limited. For the purpose of scaling, it's necessary to
-support sharing DMA channels among vrings.
-
-* Async enqueue API usage
-
-  In async enqueue path, rte_vhost_poll_enqueue_completed() needs to be
-  called in time to notify the guest of DMA copy completed packets.
-  Moreover, calling rte_vhost_submit_enqueue_burst() all the time but
-  not poll completed will cause the DMA ring to be full, which will
-  result in packet loss eventually.
-
-* Recommended IOVA mode in async datapath
-
-  When DMA devices are bound to VFIO driver, VA mode is recommended.
-  For PA mode, page by page mapping may exceed IOMMU's max capability,
-  better to use 1G guest hugepage.
-
-  For UIO driver or kernel driver, any VFIO related error messages
-  can be ignored.
doc/guides/rel_notes/release_26_11.rst +20 -0
index ecc575ff09..1b23c43b0d 100644
@@ -197,6 +197,26 @@ Removed Items
   The only remaining method for detecting LLDP packets is by using
   the mbuf packet type in conjunction with the ``enable_lldp`` devarg.
 
+* Removed vhost async (DMA-accelerated) data path.
+
+  The experimental async data path APIs have been removed from the vhost library.
+  The following functions and flag are no longer available:
+
+  - ``rte_vhost_async_channel_register``
+  - ``rte_vhost_async_channel_register_thread_unsafe``
+  - ``rte_vhost_async_channel_unregister``
+  - ``rte_vhost_async_channel_unregister_thread_unsafe``
+  - ``rte_vhost_async_dma_configure``
+  - ``rte_vhost_async_dma_unconfigure``
+  - ``rte_vhost_submit_enqueue_burst``
+  - ``rte_vhost_poll_enqueue_completed``
+  - ``rte_vhost_async_try_dequeue_burst``
+  - ``rte_vhost_async_get_inflight``
+  - ``rte_vhost_async_get_inflight_thread_unsafe``
+  - ``rte_vhost_clear_queue``
+  - ``rte_vhost_clear_queue_thread_unsafe``
+  - ``RTE_VHOST_USER_ASYNC_COPY``
+
 
 API Changes
 -----------
lib/vhost/meson.build +1 -2
index 6a24981d10..208992fa78 100644
@@ -38,10 +38,9 @@ sources = files(
 headers = files(
         'rte_vdpa.h',
         'rte_vhost.h',
-        'rte_vhost_async.h',
         'rte_vhost_crypto.h',
 )
 driver_sdk_headers = files(
         'vdpa_driver.h',
 )
-deps += ['ethdev', 'cryptodev', 'hash', 'pci', 'dmadev']
+deps += ['ethdev', 'cryptodev', 'hash']
lib/vhost/rte_vhost.h +1 -2
index 095f9b6d3c..79a4138c62 100644
@@ -38,8 +38,7 @@ extern "C" {
 #define RTE_VHOST_USER_EXTBUF_SUPPORT	(1ULL << 5)
 /* support only linear buffers (no chained mbufs) */
 #define RTE_VHOST_USER_LINEARBUF_SUPPORT	(1ULL << 6)
-#define RTE_VHOST_USER_ASYNC_COPY	(1ULL << 7)
-#define RTE_VHOST_USER_MAP_POPULATE	RTE_VHOST_USER_ASYNC_COPY
+#define RTE_VHOST_USER_MAP_POPULATE	(1ULL << 7)
 #define RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS	(1ULL << 8)
 #define RTE_VHOST_USER_NET_STATS_ENABLE	(1ULL << 9)
 #define RTE_VHOST_USER_ASYNC_CONNECT	(1ULL << 10)
lib/vhost/rte_vhost_async.h deleted +0 -293

293 lines not on this page · raw message

lib/vhost/socket.c +0 -9
index 956f3b2d71..2d3fe1fd53 100644
@@ -43,7 +43,6 @@ struct vhost_user_socket {
 	bool use_builtin_virtio_net;
 	bool extbuf;
 	bool linearbuf;
-	bool async_copy;
 	bool map_populate;
 	bool net_compliant_ol_flags;
 	bool stats_enabled;
@@ -240,13 +239,6 @@ vhost_user_add_connection(int fd, struct vhost_user_socket *vsocket)
 	if (vsocket->linearbuf)
 		vhost_enable_linearbuf(vid);
 
-	if (vsocket->async_copy) {
-		dev = get_device(vid);
-
-		if (dev)
-			dev->async_copy = 1;
-	}
-
 	if (vsocket->map_populate) {
 		dev = get_device(vid);
 
@@ -944,7 +936,6 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
 	vsocket->max_queue_pairs = VHOST_MAX_QUEUE_PAIRS;
 	vsocket->extbuf = flags & RTE_VHOST_USER_EXTBUF_SUPPORT;
 	vsocket->linearbuf = flags & RTE_VHOST_USER_LINEARBUF_SUPPORT;
-	vsocket->async_copy = flags & RTE_VHOST_USER_ASYNC_COPY;
 	vsocket->map_populate = flags & RTE_VHOST_USER_MAP_POPULATE;
 	vsocket->net_compliant_ol_flags = flags & RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS;
 	vsocket->stats_enabled = flags & RTE_VHOST_USER_NET_STATS_ENABLE;
lib/vhost/vhost.c +0 -436

471 lines not on this page · raw message

lib/vhost/vhost.h +0 -117

158 lines not on this page · raw message

lib/vhost/vhost_user.c +0 -111

177 lines not on this page · raw message

lib/vhost/virtio_net.c +660 -2615

1,645 lines not on this page · raw message

The rest of this diff is not shown. View the raw message.

Signature · 1 line
2.54.0

Part of the diff is not shown here. View the raw message.

Reviewed-by on v3 4/6
#27 lore raw

Re: [PATCH v3 4/6] vhost: drop async datapath

Quoted 26 lines · David Marchand

All the API related to this feature is experimental, allowing us by the project policy to drop the feature in one go.

---
Changes since v2:
- removed inflight async statistics,

Changes since v1:
- dropped dependency on PCI library,

Changes since RFC:
- kept mmap populate behavior for vhost_crypto,

---
  doc/guides/prog_guide/vhost_lib.rst    |  151 +-
  doc/guides/rel_notes/release_26_11.rst |   20 +
  lib/vhost/meson.build                  |    3 +-
  lib/vhost/rte_vhost.h                  |    3 +-
  lib/vhost/rte_vhost_async.h            |  293 ---
  lib/vhost/socket.c                     |    9 -
  lib/vhost/vhost.c                      |  436 ----
  lib/vhost/vhost.h                      |  117 -
  lib/vhost/vhost_user.c                 |  111 -
  lib/vhost/virtio_net.c                 | 3275 +++++-------------------
  10 files changed, 687 insertions(+), 3731 deletions(-)
Quoted 2 lines

delete mode 100644 lib/vhost/rte_vhost_async.h

Great, looks good to me:

Thanks,
Maxime

#28 lore raw

PATCH v3 5/6 vhost: rename packed layout helpers for batches

In reply to David Marchand

Now that the async datapath has been removed, the _sync in function names gives no useful information.

Besides, vhost_reserve_avail_batch_packed does not reserve anything and its name is confusing, rename it following the other rx/tx split/packed helpers convention.

---
Changes since v2:
- cleaned up indent,

---
 lib/vhost/virtio_net.c | 28 +++++++++-------------------
 1 file changed, 9 insertions(+), 19 deletions(-)
lib/vhost/virtio_net.c +9 -19
index 9ad7fa3295..3c9b4afb06 100644
@@ -1111,11 +1111,8 @@ virtio_dev_rx_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
 }
 
 static __rte_always_inline int
-virtio_dev_rx_sync_batch_check(struct virtio_net *dev,
-			   struct vhost_virtqueue *vq,
-			   struct rte_mbuf **pkts,
-			   uint64_t *desc_addrs,
-			   uint64_t *lens)
+virtio_dev_rx_batch_check(struct virtio_net *dev, struct vhost_virtqueue *vq,
+		struct rte_mbuf **pkts, uint64_t *desc_addrs, uint64_t *lens)
 	__rte_requires_shared_capability(&vq->iotlb_lock)
 {
 	bool wrap_counter = vq->avail_wrap_counter;
@@ -1213,15 +1210,14 @@ virtio_dev_rx_batch_packed_copy(struct virtio_net *dev,
 }
 
 static __rte_always_inline int
-virtio_dev_rx_sync_batch_packed(struct virtio_net *dev,
-			   struct vhost_virtqueue *vq,
-			   struct rte_mbuf **pkts)
+virtio_dev_rx_batch_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
+		struct rte_mbuf **pkts)
 	__rte_requires_shared_capability(&vq->iotlb_lock)
 {
 	uint64_t desc_addrs[PACKED_BATCH_SIZE];
 	uint64_t lens[PACKED_BATCH_SIZE];
 
-	if (virtio_dev_rx_sync_batch_check(dev, vq, pkts, desc_addrs, lens) == -1)
+	if (virtio_dev_rx_batch_check(dev, vq, pkts, desc_addrs, lens) == -1)
 		return -1;
 
 	if (vq->shadow_used_idx) {
@@ -1273,8 +1269,7 @@ virtio_dev_rx_packed(struct virtio_net *dev,
 		rte_prefetch0(&vq->desc_packed[vq->last_avail_idx]);
 
 		if (count - pkt_idx >= PACKED_BATCH_SIZE) {
-			if (!virtio_dev_rx_sync_batch_packed(dev, vq,
-							&pkts[pkt_idx])) {
+			if (!virtio_dev_rx_batch_packed(dev, vq, &pkts[pkt_idx])) {
 				pkt_idx += PACKED_BATCH_SIZE;
 				continue;
 			}
@@ -1971,12 +1966,8 @@ virtio_dev_tx_split_compliant(struct virtio_net *dev,
 }
 
 static __rte_always_inline int
-vhost_reserve_avail_batch_packed(struct virtio_net *dev,
-				 struct vhost_virtqueue *vq,
-				 struct rte_mbuf **pkts,
-				 uint16_t avail_idx,
-				 uintptr_t *desc_addrs,
-				 uint16_t *ids)
+virtio_dev_tx_batch_packed_check(struct virtio_net *dev, struct vhost_virtqueue *vq,
+		struct rte_mbuf **pkts, uint16_t avail_idx, uintptr_t *desc_addrs, uint16_t *ids)
 	__rte_requires_shared_capability(&vq->iotlb_lock)
 {
 	bool wrap = vq->avail_wrap_counter;
@@ -2055,8 +2046,7 @@ virtio_dev_tx_batch_packed(struct virtio_net *dev,
 	uint16_t ids[PACKED_BATCH_SIZE];
 	uint16_t i;
 
-	if (vhost_reserve_avail_batch_packed(dev, vq, pkts, avail_idx,
-					     desc_addrs, ids))
+	if (virtio_dev_tx_batch_packed_check(dev, vq, pkts, avail_idx, desc_addrs, ids))
 		return -1;
 
 	vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
Signature · 1 line
2.54.0
Reviewed-by on v3 5/6
#29 lore raw

Re: [PATCH v3 5/6] vhost: rename packed layout helpers for batches

Quoted 7 lines · David Marchand

Now that the async datapath has been removed, the _sync in function names gives no useful information.

Besides, vhost_reserve_avail_batch_packed does not reserve anything and its name is confusing, rename it following the other rx/tx split/packed helpers convention.

Quoted 9 lines

---
Changes since v2:
- cleaned up indent,

---
  lib/vhost/virtio_net.c | 28 +++++++++-------------------
  1 file changed, 9 insertions(+), 19 deletions(-)

Thanks,
Maxime

#30 lore raw

PATCH v3 6/6 vhost: simplify some descriptor handling

In reply to David Marchand

Now that the async datapath has been removed, move back the descriptors copy/filling code in desc_to_mbuf/mbuf_to_desc and eliminate an intermediate helper.

Tracking buf_iova is not needed in the descriptor to mbuf case.

---
Changes since v2:
- used RTE_PTR_ADD for consistency,

---
 lib/vhost/virtio_net.c | 80 ++++++++++++++++--------------------------
 1 file changed, 31 insertions(+), 49 deletions(-)
lib/vhost/virtio_net.c +31 -49
index 3c9b4afb06..1acaa81a1f 100644
@@ -76,6 +76,12 @@ vhost_queue_stats_update(const struct virtio_net *dev, struct vhost_virtqueue *v
 	}
 }
 
+static __rte_always_inline bool
+vhost_can_batch_copy(struct vhost_virtqueue *vq, uint32_t cpy_len)
+{
+	return cpy_len <= MAX_BATCH_LEN && vq->batch_copy_nb_elems < vq->size;
+}
+
 static inline void
 do_data_copy_enqueue(struct virtio_net *dev, struct vhost_virtqueue *vq)
 	__rte_requires_shared_capability(&vq->iotlb_lock)
@@ -843,44 +849,6 @@ copy_vnet_hdr_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	}
 }
 
-static __rte_always_inline void
-sync_fill_seg(struct virtio_net *dev, struct vhost_virtqueue *vq,
-		struct rte_mbuf *m, uint32_t mbuf_offset,
-		uint64_t buf_addr, uint64_t buf_iova, uint32_t cpy_len, bool to_desc)
-	__rte_requires_shared_capability(&vq->iotlb_lock)
-{
-	struct batch_copy_elem *batch_copy = vq->batch_copy_elems;
-
-	if (likely(cpy_len > MAX_BATCH_LEN || vq->batch_copy_nb_elems >= vq->size)) {
-		if (to_desc) {
-			rte_memcpy((void *)((uintptr_t)(buf_addr)),
-				rte_pktmbuf_mtod_offset(m, void *, mbuf_offset),
-				cpy_len);
-			vhost_log_cache_write_iova(dev, vq, buf_iova, cpy_len);
-			PRINT_PACKET(dev, (uintptr_t)(buf_addr), cpy_len, 0);
-		} else {
-			rte_memcpy(rte_pktmbuf_mtod_offset(m, void *, mbuf_offset),
-				(void *)((uintptr_t)(buf_addr)),
-				cpy_len);
-		}
-	} else {
-		if (to_desc) {
-			batch_copy[vq->batch_copy_nb_elems].dst =
-				(void *)((uintptr_t)(buf_addr));
-			batch_copy[vq->batch_copy_nb_elems].src =
-				rte_pktmbuf_mtod_offset(m, void *, mbuf_offset);
-			batch_copy[vq->batch_copy_nb_elems].log_addr = buf_iova;
-		} else {
-			batch_copy[vq->batch_copy_nb_elems].dst =
-				rte_pktmbuf_mtod_offset(m, void *, mbuf_offset);
-			batch_copy[vq->batch_copy_nb_elems].src =
-				(void *)((uintptr_t)(buf_addr));
-		}
-		batch_copy[vq->batch_copy_nb_elems].len = cpy_len;
-		vq->batch_copy_nb_elems++;
-	}
-}
-
 static __rte_always_inline int
 mbuf_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
 		struct rte_mbuf *m, struct buf_vector *buf_vec,
@@ -976,9 +944,22 @@ mbuf_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
 
 		cpy_len = RTE_MIN(buf_avail, mbuf_avail);
 
-		sync_fill_seg(dev, vq, m, mbuf_offset,
-			      buf_addr + buf_offset,
-			      buf_iova + buf_offset, cpy_len, true);
+		if (likely(!vhost_can_batch_copy(vq, cpy_len))) {
+			rte_memcpy(RTE_PTR_ADD(buf_addr, buf_offset),
+				rte_pktmbuf_mtod_offset(m, void *, mbuf_offset),
+				cpy_len);
+			vhost_log_cache_write_iova(dev, vq, buf_iova + buf_offset, cpy_len);
+			PRINT_PACKET(dev, RTE_PTR_ADD(buf_addr, buf_offset), cpy_len, 0);
+		} else {
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].dst =
+				RTE_PTR_ADD(buf_addr, buf_offset);
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].src =
+				rte_pktmbuf_mtod_offset(m, void *, mbuf_offset);
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].log_addr =
+				buf_iova + buf_offset;
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].len = cpy_len;
+			vq->batch_copy_nb_elems++;
+		}
 
 		mbuf_avail  -= cpy_len;
 		mbuf_offset += cpy_len;
@@ -1675,7 +1656,7 @@ desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	__rte_requires_shared_capability(&vq->iotlb_lock)
 {
 	uint32_t buf_avail, buf_offset, buf_len;
-	uint64_t buf_addr, buf_iova;
+	uint64_t buf_addr;
 	uint32_t mbuf_avail, mbuf_offset;
 	uint32_t hdr_remain = dev->vhost_hlen;
 	uint32_t cpy_len;
@@ -1706,7 +1687,6 @@ desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	}
 
 	buf_addr = buf_vec[vec_idx].buf_addr;
-	buf_iova = buf_vec[vec_idx].buf_iova;
 	buf_len = buf_vec[vec_idx].buf_len;
 	buf_offset = hdr_remain;
 	buf_avail = buf_vec[vec_idx].buf_len - hdr_remain;
@@ -1721,14 +1701,17 @@ desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	while (1) {
 		cpy_len = RTE_MIN(buf_avail, mbuf_avail);
 
-		if (likely(hdr && cur == m)) {
+		if (likely((hdr && cur == m) || !vhost_can_batch_copy(vq, cpy_len))) {
 			rte_memcpy(rte_pktmbuf_mtod_offset(cur, void *, mbuf_offset),
-				(void *)((uintptr_t)(buf_addr + buf_offset)),
+				RTE_PTR_ADD(buf_addr, buf_offset),
 				cpy_len);
 		} else {
-			sync_fill_seg(dev, vq, cur, mbuf_offset,
-				      buf_addr + buf_offset,
-				      buf_iova + buf_offset, cpy_len, false);
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].dst =
+				rte_pktmbuf_mtod_offset(cur, void *, mbuf_offset);
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].src =
+				RTE_PTR_ADD(buf_addr, buf_offset);
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].len = cpy_len;
+			vq->batch_copy_nb_elems++;
 		}
 
 		mbuf_avail  -= cpy_len;
@@ -1742,7 +1725,6 @@ desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
 				break;
 
 			buf_addr = buf_vec[vec_idx].buf_addr;
-			buf_iova = buf_vec[vec_idx].buf_iova;
 			buf_len = buf_vec[vec_idx].buf_len;
 
 			buf_offset = 0;
Signature · 1 line
2.54.0
Reviewed-by on v3 6/6
#31 lore raw

Re: [PATCH v3 6/6] vhost: simplify some descriptor handling

Quoted 6 lines · David Marchand

Now that the async datapath has been removed, move back the descriptors copy/filling code in desc_to_mbuf/mbuf_to_desc and eliminate an intermediate helper.

Tracking buf_iova is not needed in the descriptor to mbuf case.

Quoted 9 lines

---
Changes since v2:
- used RTE_PTR_ADD for consistency,

---
  lib/vhost/virtio_net.c | 80 ++++++++++++++++--------------------------
  1 file changed, 31 insertions(+), 49 deletions(-)

Thanks,
Maxime

#32 lore raw

v4 cover Drop vhost async (DMA-accelerated) datapath

In reply to David Marchand

The integration of this feature in OVS has been postponed following feedback how the current API forced the complexity on the application side. There is no contributor working on making those changes.

The feature has no other identified opensource consumer.

On the other hand, this feature has been left unattended for some years now while the "normal" datapath is actively maintained.
It is highly likely the async datapath code, which never underwent a stabilisation phase, is riddled with bugs.

Given the craziness around finding security bugs with AI, and since the vhost library is a good target, I propose to drop this feature and reduce the library attack surface.

There is one complication with the vhost_crypto and some external applications that seemed to rely on the async flag to track and populate guest pages, so a new flag replacing async is added by this series.

Signature · 51 lines
David Marchand

Changes since v3:
- rebased after CVE fixes and various changes: RTE_PTR_ADD, VFIO,
  signal cleanup in examples,

Changes since v2:
- updated release notes and vhost example documentation,
- removed some async statistics missed in previous revisions,
- re-added checks on map populate and post copy or other virtio features,

Changes since v1:
- removed unneeded dependencies on the PCI library,

Changes since RFC:
- maintained guest pages population in a new flag (vhost_crypto/SPDK),
- removed remaining helpers which had sync_ in their names,


David Marchand (6):
  vhost: decouple guest pages population from async datapath
  examples/vhost: stop using async datapath
  examples/vdpa: remove dependency on PCI library
  vhost: drop async datapath
  vhost: rename packed layout helpers for batches
  vhost: simplify some descriptor handling

 doc/guides/prog_guide/vhost_lib.rst    |  152 +-
 doc/guides/rel_notes/release_26_11.rst |   24 +
 doc/guides/sample_app_ug/vhost.rst     |   10 -
 examples/vdpa/main.c                   |    1 -
 examples/vhost/Makefile                |    2 -
 examples/vhost/main.c                  |  437 +---
 examples/vhost/main.h                  |   21 +-
 examples/vhost/meson.build             |    2 -
 examples/vhost_crypto/Makefile         |    1 -
 examples/vhost_crypto/main.c           |    2 +-
 examples/vhost_crypto/meson.build      |    1 -
 lib/vhost/meson.build                  |    3 +-
 lib/vhost/rte_vhost.h                  |    2 +-
 lib/vhost/rte_vhost_async.h            |  293 ---
 lib/vhost/socket.c                     |   23 +-
 lib/vhost/vhost.c                      |  436 ----
 lib/vhost/vhost.h                      |  119 +-
 lib/vhost/vhost_user.c                 |  115 +-
 lib/vhost/virtio_net.c                 | 3318 +++++-------------------
 19 files changed, 731 insertions(+), 4231 deletions(-)
 delete mode 100644 lib/vhost/rte_vhost_async.h

-- 
2.54.0
#33 lore raw

PATCH v4 1/6 vhost: decouple guest pages population from async datapath

The vhost crypto zero-copy feature relies on the RTE_VHOST_USER_ASYNC_COPY flag to enable guest page tracking (guest_pages array population and MAP_POPULATE during mmap).

Introduce a RTE_VHOST_USER_MAP_POPULATE flag that maps to RTE_VHOST_USER_ASYNC_COPY at this point in time.

Adjust vhost_crypto example and remove the unnecessary ALLOW_EXPERIMENTAL_API flag as this example does not use any experimental APIs.

---
Changes since v3:
- rebased after VFIO changes,

Changes since v2:
- updated release notes for new flag,
- fixed checks on map populate feature,

---
 doc/guides/prog_guide/vhost_lib.rst    |  9 +++++++++
 doc/guides/rel_notes/release_26_11.rst |  4 ++++
 examples/vhost_crypto/Makefile         |  1 -
 examples/vhost_crypto/main.c           |  2 +-
 examples/vhost_crypto/meson.build      |  1 -
 lib/vhost/rte_vhost.h                  |  1 +
 lib/vhost/socket.c                     | 19 +++++++++++++++----
 lib/vhost/vhost.h                      |  1 +
 lib/vhost/vhost_user.c                 |  4 ++--
 9 files changed, 33 insertions(+), 9 deletions(-)
doc/guides/prog_guide/vhost_lib.rst +9 -0
index 99355b8afd..09177b4697 100644
@@ -118,6 +118,15 @@ The following is an overview of some key Vhost API functions:
 
     It is disabled by default.
 
+  - ``RTE_VHOST_USER_MAP_POPULATE``
+
+    Guest memory regions will be mapped with ``MAP_POPULATE`` when this flag
+    is set, pre-faulting pages into memory. This is useful for applications
+    requiring direct access to guest memory, such as vhost-crypto zero-copy
+    operations.
+
+    It is disabled by default.
+
   - ``RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS``
 
     Since v16.04, the vhost library forwards checksum and gso requests for
doc/guides/rel_notes/release_26_11.rst +4 -0
index 03b4feae0f..8e9311eb3f 100644
@@ -448,6 +448,10 @@ API Changes
     ``rte_event_port_profile_links_get`` and
     ``rte_event_port_profile_unlink``
 
+* vhost: Introduced ``RTE_VHOST_USER_MAP_POPULATE`` as a replacement of
+  ``RTE_VHOST_USER_ASYNC_COPY`` for users that did not rely on the vhost
+  async copy feature but expected guest pages to be prefaulted.
+
 * reorder: Promoted the following API from experimental to stable:
   ``rte_reorder_seqn``, ``rte_reorder_drain_up_to_seqn``,
   ``rte_reorder_min_seqn_set`` and ``rte_reorder_memory_footprint_get``.
examples/vhost_crypto/Makefile +0 -1
index cc7f2abb90..130953c38e 100644
@@ -6,7 +6,6 @@ APP = vhost-crypto
 
 # all source are stored in SRCS-y
 SRCS-y := main.c
-CFLAGS += -DALLOW_EXPERIMENTAL_API
 
 PKGCONF ?= pkg-config
 
examples/vhost_crypto/main.c +1 -1
index 8bdfc40c4b..53bd8fa825 100644
@@ -623,7 +623,7 @@ main(int argc, char *argv[])
 
 		for (j = 0; j < lo->nb_sockets; j++) {
 			ret = rte_vhost_driver_register(lo->socket_files[j],
-				RTE_VHOST_USER_ASYNC_COPY);
+				RTE_VHOST_USER_MAP_POPULATE);
 			if (ret < 0) {
 				RTE_LOG(ERR, USER1, "socket %s already exists\n",
 					lo->socket_files[j]);
examples/vhost_crypto/meson.build +0 -1
index 1c294c286f..47c8fa829f 100644
@@ -6,7 +6,6 @@
 # To build this example as a standalone application with an already-installed
 # DPDK instance, use 'make'
 
-allow_experimental_apis = true
 deps += ['vhost', 'cryptodev']
 sources = files(
         'main.c',
lib/vhost/rte_vhost.h +1 -0
index a7f9700538..095f9b6d3c 100644
@@ -39,6 +39,7 @@ extern "C" {
 /* support only linear buffers (no chained mbufs) */
 #define RTE_VHOST_USER_LINEARBUF_SUPPORT	(1ULL << 6)
 #define RTE_VHOST_USER_ASYNC_COPY	(1ULL << 7)
+#define RTE_VHOST_USER_MAP_POPULATE	RTE_VHOST_USER_ASYNC_COPY
 #define RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS	(1ULL << 8)
 #define RTE_VHOST_USER_NET_STATS_ENABLE	(1ULL << 9)
 #define RTE_VHOST_USER_ASYNC_CONNECT	(1ULL << 10)
lib/vhost/socket.c +15 -4
index d30b34caa6..d4dc43b8cf 100644
@@ -45,6 +45,7 @@ struct vhost_user_socket {
 	bool extbuf;
 	bool linearbuf;
 	bool async_copy;
+	bool map_populate;
 	bool net_compliant_ol_flags;
 	bool stats_enabled;
 	bool async_connect;
@@ -249,6 +250,13 @@ vhost_user_add_connection(int fd, struct vhost_user_socket *vsocket)
 		}
 	}
 
+	if (vsocket->map_populate) {
+		dev = get_device(vid);
+
+		if (dev)
+			dev->map_populate = 1;
+	}
+
 	VHOST_CONFIG_LOG(vsocket->path, INFO, "new device, handle is %d", vid);
 
 	if (vsocket->notify_ops->new_connection) {
@@ -940,6 +948,7 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
 	vsocket->extbuf = flags & RTE_VHOST_USER_EXTBUF_SUPPORT;
 	vsocket->linearbuf = flags & RTE_VHOST_USER_LINEARBUF_SUPPORT;
 	vsocket->async_copy = flags & RTE_VHOST_USER_ASYNC_COPY;
+	vsocket->map_populate = flags & RTE_VHOST_USER_MAP_POPULATE;
 	vsocket->net_compliant_ol_flags = flags & RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS;
 	vsocket->stats_enabled = flags & RTE_VHOST_USER_NET_STATS_ENABLE;
 	vsocket->async_connect = flags & RTE_VHOST_USER_ASYNC_CONNECT;
@@ -948,9 +957,10 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
 	else
 		vsocket->iommu_support = flags & RTE_VHOST_USER_IOMMU_SUPPORT;
 
-	if (vsocket->async_copy && (vsocket->iommu_support ||
+	if (vsocket->map_populate && (vsocket->iommu_support ||
 				(flags & RTE_VHOST_USER_POSTCOPY_SUPPORT))) {
-		VHOST_CONFIG_LOG(path, ERR, "async copy with IOMMU or post-copy not supported");
+		VHOST_CONFIG_LOG(path, ERR,
+			"guest pages prefaulting not supported with IOMMU or post-copy");
 		goto out_mutex;
 	}
 
@@ -976,10 +986,11 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
 		vsocket->protocol_features  = VHOST_USER_PROTOCOL_FEATURES;
 	}
 
-	if (vsocket->async_copy) {
+	if (vsocket->map_populate) {
 		vsocket->supported_features &= ~(1ULL << VHOST_F_LOG_ALL);
 		vsocket->features &= ~(1ULL << VHOST_F_LOG_ALL);
-		VHOST_CONFIG_LOG(path, INFO, "logging feature is disabled in async copy mode");
+		VHOST_CONFIG_LOG(path, INFO,
+			"logging feature is disabled with guest pages prefaulting");
 	}
 
 	/*
lib/vhost/vhost.h +1 -0
index 1f0568dcb5..da85a1ef01 100644
@@ -500,6 +500,7 @@ struct __rte_cache_aligned virtio_net {
 	uint32_t		nr_vring;
 	int			async_copy;
 	bool			dma_map_available;
+	int			map_populate;
 
 	int			extbuf;
 	int			linearbuf;
lib/vhost/vhost_user.c +2 -2
index 0d09dfb041..89339ee8db 100644
@@ -1406,7 +1406,7 @@ vhost_user_mmap_region(struct virtio_net *dev,
 		return -1;
 	}
 
-	populate = dev->async_copy ? MAP_POPULATE : 0;
+	populate = dev->map_populate ? MAP_POPULATE : 0;
 	mmap_addr = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE,
 			MAP_SHARED | populate, region->fd, 0);
 
@@ -1420,7 +1420,7 @@ vhost_user_mmap_region(struct virtio_net *dev,
 	region->host_user_addr = (uint64_t)(uintptr_t)mmap_addr + mmap_offset;
 	mem_set_dump(dev, mmap_addr, mmap_size, false, alignment);
 
-	if (dev->async_copy) {
+	if (dev->map_populate) {
 		if (add_guest_pages(dev, region, alignment) < 0) {
 			VHOST_CONFIG_LOG(dev->ifname, ERR,
 				"adding guest pages to region failed.");
Signature · 1 line
2.54.0
#34 lore raw

PATCH v4 2/6 examples/vhost: stop using async datapath

In reply to David Marchand

Stop using vhost async as this feature will be removed in a next commit. Thanks to this, we can drop use of experimental api.

---
Changes since v3:
- rebased after signal cleanup changes,

Changes since v2:
- removed --dmas option in vhost example doc,

Changes since RFC:
- dropped vhost_crypto changes (now handled in patch 1),

---
 doc/guides/sample_app_ug/vhost.rst |  10 -
 examples/vhost/Makefile            |   2 -
 examples/vhost/main.c              | 437 +----------------------------
 examples/vhost/main.h              |  21 +-
 examples/vhost/meson.build         |   2 -
 5 files changed, 12 insertions(+), 460 deletions(-)
doc/guides/sample_app_ug/vhost.rst +0 -10
index 2726dba604..8e846eae31 100644
@@ -149,16 +149,6 @@ default value is 15.
 A very simple vhost-user net driver which demonstrates how to use the generic
 vhost APIs will be used when this option is given. It is disabled by default.
 
-**--dmas**
-This parameter is used to specify the assigned DMA device of a vhost device.
-Async vhost-user net driver will be used if --dmas is set. For example
---dmas [txd0@00:04.0,txd1@00:04.1,rxd0@00:04.2,rxd1@00:04.3] means use
-DMA channel 00:04.0/00:04.2 for vhost device 0 enqueue/dequeue operation
-and use DMA channel 00:04.1/00:04.3 for vhost device 1 enqueue/dequeue
-operation. The index of the device corresponds to the socket file in order,
-that means vhost device 0 is created through the first socket file, vhost
-device 1 is created through the second socket file, and so on.
-
 **--total-num-mbufs 0-N**
 This parameter sets the number of mbufs to be allocated in mbuf pools,
 the default value is 147456. This is can be used if launch of a port fails
examples/vhost/Makefile +0 -2
index 5b3cea0778..6e0114d094 100644
@@ -28,8 +28,6 @@ CFLAGS += -O3 $(shell $(PKGCONF) --cflags libdpdk)
 LDFLAGS_SHARED = $(shell $(PKGCONF) --libs libdpdk)
 LDFLAGS_STATIC = $(shell $(PKGCONF) --static --libs libdpdk)
 
-CFLAGS += -DALLOW_EXPERIMENTAL_API
-
 build/$(APP)-shared: $(SRCS-y) Makefile $(PC_FILE) | build
 	$(CC) $(CFLAGS) $(SRCS-y) -o $@ $(LDFLAGS) $(LDFLAGS_SHARED)
 
examples/vhost/main.c +10 -427

604 lines not on this page · raw message

examples/vhost/main.h +2 -19
index c986cbc5a9..3cf6bd7f07 100644
@@ -8,7 +8,6 @@
 #include <sys/queue.h>
 
 #include <rte_ether.h>
-#include <rte_pci.h>
 
 /* Macros for printing using RTE_LOG */
 #define RTE_LOGTYPE_VHOST_CONFIG RTE_LOGTYPE_USER1
@@ -92,17 +91,6 @@ struct lcore_info {
 	struct vhost_dev_tailq_list vdev_list;
 };
 
-struct dma_info {
-	struct rte_pci_addr addr;
-	int16_t dev_id;
-	bool async_enabled;
-};
-
-struct dma_for_vhost {
-	struct dma_info dmas[RTE_MAX_QUEUES_PER_PORT * 2];
-	uint32_t async_flag;
-};
-
 /* we implement non-extra virtio net features */
 #define VIRTIO_NET_FEATURES	0
 
@@ -116,14 +104,9 @@ uint16_t builtin_enqueue_pkts(struct vhost_dev *dev, uint16_t queue_id,
 uint16_t builtin_dequeue_pkts(struct vhost_dev *dev, uint16_t queue_id,
 			struct rte_mempool *mbuf_pool,
 			struct rte_mbuf **pkts, uint16_t count);
-uint16_t sync_enqueue_pkts(struct vhost_dev *dev, uint16_t queue_id,
-			 struct rte_mbuf **pkts, uint32_t count);
-uint16_t sync_dequeue_pkts(struct vhost_dev *dev, uint16_t queue_id,
-			struct rte_mempool *mbuf_pool,
-			struct rte_mbuf **pkts, uint16_t count);
-uint16_t async_enqueue_pkts(struct vhost_dev *dev, uint16_t queue_id,
+uint16_t enqueue_pkts(struct vhost_dev *dev, uint16_t queue_id,
 			 struct rte_mbuf **pkts, uint32_t count);
-uint16_t async_dequeue_pkts(struct vhost_dev *dev, uint16_t queue_id,
+uint16_t dequeue_pkts(struct vhost_dev *dev, uint16_t queue_id,
 			struct rte_mempool *mbuf_pool,
 			struct rte_mbuf **pkts, uint16_t count);
 #endif /* _MAIN_H_ */
examples/vhost/meson.build +0 -2
index e938be8f45..a04852bb2f 100644
@@ -12,8 +12,6 @@ if not is_linux
 endif
 
 deps += 'vhost'
-deps += 'dmadev'
-allow_experimental_apis = true
 sources = files(
         'main.c',
         'virtio_net.c',
Signature · 1 line
2.54.0
#35 lore raw

PATCH v4 3/6 examples/vdpa: remove dependency on PCI library

In reply to David Marchand

This is some forgotten unneeded header include from a previous refactoring.

Fixes 38f8ab0bbc8d ("vhost: make vDPA framework bus agnostic")
---
 examples/vdpa/main.c | 1 -
 1 file changed, 1 deletion(-)
examples/vdpa/main.c +0 -1
index 1b989fc6e5..c39cece15c 100644
@@ -13,7 +13,6 @@
 #include <rte_malloc.h>
 #include <rte_vhost.h>
 #include <rte_vdpa.h>
-#include <rte_pci.h>
 #include <rte_string_fns.h>
 
 #include <cmdline_socket.h>
Signature · 1 line
2.54.0
#36 lore raw

PATCH v4 4/6 vhost: drop async datapath

In reply to David Marchand

All the API related to this feature is experimental, allowing us by the project policy to drop the feature in one go.

---
Changes since v3:
- rebased after VFIO changes,

Changes since v2:
- removed inflight async statistics,

Changes since v1:
- dropped dependency on PCI library,

Changes since RFC:
- kept mmap populate behavior for vhost_crypto,

---
 doc/guides/prog_guide/vhost_lib.rst    |  151 +-
 doc/guides/rel_notes/release_26_11.rst |   20 +
 lib/vhost/meson.build                  |    3 +-
 lib/vhost/rte_vhost.h                  |    3 +-
 lib/vhost/rte_vhost_async.h            |  293 ---
 lib/vhost/socket.c                     |   12 -
 lib/vhost/vhost.c                      |  436 ----
 lib/vhost/vhost.h                      |  118 -
 lib/vhost/vhost_user.c                 |  111 -
 lib/vhost/virtio_net.c                 | 3275 +++++-------------------
 10 files changed, 687 insertions(+), 3735 deletions(-)
 delete mode 100644 lib/vhost/rte_vhost_async.h
doc/guides/prog_guide/vhost_lib.rst +5 -146
index 09177b4697..3dc16e44f4 100644
@@ -103,21 +103,6 @@ The following is an overview of some key Vhost API functions:
 
     It is disabled by default.
 
-  - ``RTE_VHOST_USER_ASYNC_COPY``
-
-    Asynchronous data path will be enabled when this flag is set. Async
-    data path allows applications to enable DMA acceleration for vhost
-    queues. Vhost leverages the registered DMA channels to free CPU from
-    memory copy operations in data path. A set of async data path APIs are
-    defined for DPDK applications to make use of the async capability. Only
-    packets enqueued/dequeued by async APIs are processed through the async
-    data path.
-
-    Currently this feature is only implemented on split ring enqueue data
-    path.
-
-    It is disabled by default.
-
   - ``RTE_VHOST_USER_MAP_POPULATE``
 
     Guest memory regions will be mapped with ``MAP_POPULATE`` when this flag
@@ -236,76 +221,6 @@ The following is an overview of some key Vhost API functions:
 
   Enable or disable zero copy feature of the vhost crypto backend.
 
-* ``rte_vhost_async_dma_configure(dma_id, vchan_id)``
-
-  Tell vhost which DMA vChannel is going to use. This function needs to
-  be called before register async data-path for vring.
-
-* ``rte_vhost_async_channel_register(vid, queue_id)``
-
-  Register async DMA acceleration for a vhost queue after vring is enabled.
-
-* ``rte_vhost_async_channel_register_thread_unsafe(vid, queue_id)``
-
-  Register async DMA acceleration for a vhost queue without performing
-  any locking.
-
-  This function is only safe to call in vhost callback functions
-  (i.e., struct rte_vhost_device_ops).
-
-* ``rte_vhost_async_channel_unregister(vid, queue_id)``
-
-  Unregister the async DMA acceleration from a vhost queue.
-  Unregistration will fail, if the vhost queue has in-flight
-  packets that are not completed.
-
-  Unregister async DMA acceleration in vring_state_changed() may
-  fail, as this API tries to acquire the spinlock of vhost
-  queue. The recommended way is to unregister async copy
-  devices for all vhost queues in destroy_device(), when a
-  virtio device is paused or shut down.
-
-* ``rte_vhost_async_channel_unregister_thread_unsafe(vid, queue_id)``
-
-  Unregister async DMA acceleration for a vhost queue without performing
-  any locking.
-
-  This function is only safe to call in vhost callback functions
-  (i.e., struct rte_vhost_device_ops).
-
-* ``rte_vhost_submit_enqueue_burst(vid, queue_id, pkts, count, dma_id, vchan_id)``
-
-  Submit an enqueue request to transmit ``count`` packets from host to guest
-  by async data path. Applications must not free the packets submitted for
-  enqueue until the packets are completed.
-
-* ``rte_vhost_poll_enqueue_completed(vid, queue_id, pkts, count, dma_id, vchan_id)``
-
-  Poll enqueue completion status from async data path. Completed packets
-  are returned to applications through ``pkts``.
-
-* ``rte_vhost_async_get_inflight(vid, queue_id)``
-
-  This function returns the amount of in-flight packets for the vhost
-  queue using async acceleration.
-
- * ``rte_vhost_async_get_inflight_thread_unsafe(vid, queue_id)``
-
-  Get the number of inflight packets for a vhost queue without performing
-  any locking. It should only be used within the vhost ops, which already
-  holds the lock.
-
-* ``rte_vhost_clear_queue_thread_unsafe(vid, queue_id, **pkts, count, dma_id, vchan_id)``
-
-  Clear in-flight packets which are submitted to async channel in vhost
-  async data path without performing locking on virtqueue. Completed
-  packets are returned to applications through ``pkts``.
-
-* ``rte_vhost_clear_queue(vid, queue_id, **pkts, count, dma_id, vchan_id)``
-
-  Clear in-flight packets which are submitted to async channel in vhost async data
-  path. Completed packets are returned to applications through ``pkts``.
-
 * ``rte_vhost_vring_call_nonblock(int vid, uint16_t vring_idx)``
 
   Notify the guest that used descriptors have been added to the vring. This function
@@ -327,22 +242,11 @@ The following is an overview of some key Vhost API functions:
   This function resets the queue statistics. It requires statistics
   collection to be enabled at registration time.
 
-* ``rte_vhost_async_try_dequeue_burst(vid, queue_id, mbuf_pool, pkts, count,
-  nr_inflight, dma_id, vchan_id)``
-
-  Receive ``count`` packets from guest to host in async data path,
-  and store them at ``pkts``.
-
 * ``rte_vhost_driver_get_vdpa_dev_type(path, type)``
 
   Get device type of vDPA device, such as VDPA_DEVICE_TYPE_NET,
   VDPA_DEVICE_TYPE_BLK.
 
-* ``rte_vhost_async_dma_unconfigure(dma_id, vchan_id)``
-
-  Clean up a DMA vChannel after use is finished. After this function is called,
-  the specified DMA vChannel should no longer be used by the Vhost library.
-
 * ``rte_vhost_notify_guest(int vid, uint16_t queue_id)``
 
   Inject the offloaded interrupt received by the 'guest_notify' callback,
@@ -411,16 +315,11 @@ Guest memory requirement
 
 * Memory pre-allocation
 
-  For non-async data path guest memory pre-allocation is not a
-  must but can help save memory. To do this we can add option
-  ``-mem-prealloc`` when starting QEMU, or we can lock all memory at vhost
-  side which will force memory to be allocated when it calls mmap
-  (option --mlockall in ovs-dpdk is an example in hand).
-
-
-  For async data path, we force the VM memory to be pre-allocated at vhost
-  lib when mapping the guest memory; and also we need to lock the memory to
-  prevent pages being swapped out to disk.
+  Guest memory pre-allocation is not a must but can help save memory.
+  To do this we can add option ``-mem-prealloc`` when starting QEMU,
+  or we can lock all memory at vhost side which will force memory to
+  be allocated when it calls mmap (option --mlockall in ovs-dpdk is
+  an example in hand).
 
 * Memory sharing
 
@@ -487,43 +386,3 @@ Finally, a set of device ops is defined for device specific operations:
 * ``get_notify_area``
 
   Called to get the notify area info of the queue.
-
-Vhost asynchronous data path
-----------------------------
-
-Vhost asynchronous data path leverages DMA devices to offload memory
-copies from the CPU and it is implemented in an asynchronous way. It
-enables applications, like OVS, to save CPU cycles and hide memory copy
-overhead, thus achieving higher throughput.
-
-Vhost doesn't manage DMA devices and applications, like OVS, need to
-manage and configure DMA devices. Applications need to tell vhost what
-DMA devices to use in every data path function call. This design enables
-the flexibility for applications to dynamically use DMA channels in
-different function modules, not limited in vhost.
-
-In addition, vhost supports M:N mapping between vrings and DMA virtual
-channels. Specifically, one vring can use multiple different DMA channels
-and one DMA channel can be shared by multiple vrings at the same time.
-The reason of enabling one vring to use multiple DMA channels is that
-it's possible that more than one dataplane threads enqueue packets to
-the same vring with their own DMA virtual channels. Besides, the number
-of DMA devices is limited. For the purpose of scaling, it's necessary to
-support sharing DMA channels among vrings.
-
-* Async enqueue API usage
-
-  In async enqueue path, rte_vhost_poll_enqueue_completed() needs to be
-  called in time to notify the guest of DMA copy completed packets.
-  Moreover, calling rte_vhost_submit_enqueue_burst() all the time but
-  not poll completed will cause the DMA ring to be full, which will
-  result in packet loss eventually.
-
-* Recommended IOVA mode in async datapath
-
-  When DMA devices are bound to VFIO driver, VA mode is recommended.
-  For PA mode, page by page mapping may exceed IOMMU's max capability,
-  better to use 1G guest hugepage.
-
-  For UIO driver or kernel driver, any VFIO related error messages
-  can be ignored.
doc/guides/rel_notes/release_26_11.rst +20 -0
index 8e9311eb3f..bd2ff12659 100644
@@ -294,6 +294,26 @@ Removed Items
   The only remaining method for detecting LLDP packets is by using
   the mbuf packet type in conjunction with the ``enable_lldp`` devarg.
 
+* Removed vhost async (DMA-accelerated) data path.
+
+  The experimental async data path APIs have been removed from the vhost library.
+  The following functions and flag are no longer available:
+
+  - ``rte_vhost_async_channel_register``
+  - ``rte_vhost_async_channel_register_thread_unsafe``
+  - ``rte_vhost_async_channel_unregister``
+  - ``rte_vhost_async_channel_unregister_thread_unsafe``
+  - ``rte_vhost_async_dma_configure``
+  - ``rte_vhost_async_dma_unconfigure``
+  - ``rte_vhost_submit_enqueue_burst``
+  - ``rte_vhost_poll_enqueue_completed``
+  - ``rte_vhost_async_try_dequeue_burst``
+  - ``rte_vhost_async_get_inflight``
+  - ``rte_vhost_async_get_inflight_thread_unsafe``
+  - ``rte_vhost_clear_queue``
+  - ``rte_vhost_clear_queue_thread_unsafe``
+  - ``RTE_VHOST_USER_ASYNC_COPY``
+
 
 API Changes
 -----------
lib/vhost/meson.build +1 -2
index 6a24981d10..208992fa78 100644
@@ -38,10 +38,9 @@ sources = files(
 headers = files(
         'rte_vdpa.h',
         'rte_vhost.h',
-        'rte_vhost_async.h',
         'rte_vhost_crypto.h',
 )
 driver_sdk_headers = files(
         'vdpa_driver.h',
 )
-deps += ['ethdev', 'cryptodev', 'hash', 'pci', 'dmadev']
+deps += ['ethdev', 'cryptodev', 'hash']
lib/vhost/rte_vhost.h +1 -2
index 095f9b6d3c..79a4138c62 100644
@@ -38,8 +38,7 @@ extern "C" {
 #define RTE_VHOST_USER_EXTBUF_SUPPORT	(1ULL << 5)
 /* support only linear buffers (no chained mbufs) */
 #define RTE_VHOST_USER_LINEARBUF_SUPPORT	(1ULL << 6)
-#define RTE_VHOST_USER_ASYNC_COPY	(1ULL << 7)
-#define RTE_VHOST_USER_MAP_POPULATE	RTE_VHOST_USER_ASYNC_COPY
+#define RTE_VHOST_USER_MAP_POPULATE	(1ULL << 7)
 #define RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS	(1ULL << 8)
 #define RTE_VHOST_USER_NET_STATS_ENABLE	(1ULL << 9)
 #define RTE_VHOST_USER_ASYNC_CONNECT	(1ULL << 10)
lib/vhost/rte_vhost_async.h deleted +0 -293

293 lines not on this page · raw message

lib/vhost/socket.c +0 -12
index d4dc43b8cf..2d3fe1fd53 100644
@@ -17,7 +17,6 @@
 #include <eal_export.h>
 #include <rte_thread.h>
 #include <rte_log.h>
-#include <dev_vfio.h>
 
 #include "fd_man.h"
 #include "vduse.h"
@@ -44,7 +43,6 @@ struct vhost_user_socket {
 	bool use_builtin_virtio_net;
 	bool extbuf;
 	bool linearbuf;
-	bool async_copy;
 	bool map_populate;
 	bool net_compliant_ol_flags;
 	bool stats_enabled;
@@ -241,15 +239,6 @@ vhost_user_add_connection(int fd, struct vhost_user_socket *vsocket)
 	if (vsocket->linearbuf)
 		vhost_enable_linearbuf(vid);
 
-	if (vsocket->async_copy) {
-		dev = get_device(vid);
-
-		if (dev != NULL) {
-			dev->async_copy = 1;
-			dev->dma_map_available = dev_vfio_is_enabled();
-		}
-	}
-
 	if (vsocket->map_populate) {
 		dev = get_device(vid);
 
@@ -947,7 +936,6 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
 	vsocket->max_queue_pairs = VHOST_MAX_QUEUE_PAIRS;
 	vsocket->extbuf = flags & RTE_VHOST_USER_EXTBUF_SUPPORT;
 	vsocket->linearbuf = flags & RTE_VHOST_USER_LINEARBUF_SUPPORT;
-	vsocket->async_copy = flags & RTE_VHOST_USER_ASYNC_COPY;
 	vsocket->map_populate = flags & RTE_VHOST_USER_MAP_POPULATE;
 	vsocket->net_compliant_ol_flags = flags & RTE_VHOST_USER_NET_COMPLIANT_OL_FLAGS;
 	vsocket->stats_enabled = flags & RTE_VHOST_USER_NET_STATS_ENABLE;
lib/vhost/vhost.c +0 -436

471 lines not on this page · raw message

lib/vhost/vhost.h +0 -118

159 lines not on this page · raw message

lib/vhost/vhost_user.c +0 -111

177 lines not on this page · raw message

lib/vhost/virtio_net.c +660 -2615

1,635 lines not on this page · raw message

The rest of this diff is not shown. View the raw message.

Signature · 1 line
2.54.0

Part of the diff is not shown here. View the raw message.

Reviewed-by on v4 4/6
#37 lore raw

Re: [PATCH v4 4/6] vhost: drop async datapath

Quoted 29 lines · David Marchand

All the API related to this feature is experimental, allowing us by the project policy to drop the feature in one go.

---
Changes since v3:
- rebased after VFIO changes,

Changes since v2:
- removed inflight async statistics,

Changes since v1:
- dropped dependency on PCI library,

Changes since RFC:
- kept mmap populate behavior for vhost_crypto,

---
  doc/guides/prog_guide/vhost_lib.rst    |  151 +-
  doc/guides/rel_notes/release_26_11.rst |   20 +
  lib/vhost/meson.build                  |    3 +-
  lib/vhost/rte_vhost.h                  |    3 +-
  lib/vhost/rte_vhost_async.h            |  293 ---
  lib/vhost/socket.c                     |   12 -
  lib/vhost/vhost.c                      |  436 ----
  lib/vhost/vhost.h                      |  118 -
  lib/vhost/vhost_user.c                 |  111 -
  lib/vhost/virtio_net.c                 | 3275 +++++-------------------
  10 files changed, 687 insertions(+), 3735 deletions(-)
Quoted 2 lines

delete mode 100644 lib/vhost/rte_vhost_async.h

Already provided my R-by on previous revision:

#38 lore raw

PATCH v4 5/6 vhost: rename packed layout helpers for batches

In reply to David Marchand

Now that the async datapath has been removed, the _sync in function names gives no useful information.

Besides, vhost_reserve_avail_batch_packed does not reserve anything and its name is confusing, rename it following the other rx/tx split/packed helpers convention.

---
Changes since v2:
- cleaned up indent,

---
 lib/vhost/virtio_net.c | 28 +++++++++-------------------
 1 file changed, 9 insertions(+), 19 deletions(-)
lib/vhost/virtio_net.c +9 -19
index 10bb924a91..6d8d788524 100644
@@ -1118,11 +1118,8 @@ virtio_dev_rx_split(struct virtio_net *dev, struct vhost_virtqueue *vq,
 }
 
 static __rte_always_inline int
-virtio_dev_rx_sync_batch_check(struct virtio_net *dev,
-			   struct vhost_virtqueue *vq,
-			   struct rte_mbuf **pkts,
-			   uint64_t *desc_addrs,
-			   uint64_t *lens)
+virtio_dev_rx_batch_check(struct virtio_net *dev, struct vhost_virtqueue *vq,
+		struct rte_mbuf **pkts, uint64_t *desc_addrs, uint64_t *lens)
 	__rte_requires_shared_capability(&vq->iotlb_lock)
 {
 	bool wrap_counter = vq->avail_wrap_counter;
@@ -1220,15 +1217,14 @@ virtio_dev_rx_batch_packed_copy(struct virtio_net *dev,
 }
 
 static __rte_always_inline int
-virtio_dev_rx_sync_batch_packed(struct virtio_net *dev,
-			   struct vhost_virtqueue *vq,
-			   struct rte_mbuf **pkts)
+virtio_dev_rx_batch_packed(struct virtio_net *dev, struct vhost_virtqueue *vq,
+		struct rte_mbuf **pkts)
 	__rte_requires_shared_capability(&vq->iotlb_lock)
 {
 	uint64_t desc_addrs[PACKED_BATCH_SIZE];
 	uint64_t lens[PACKED_BATCH_SIZE];
 
-	if (virtio_dev_rx_sync_batch_check(dev, vq, pkts, desc_addrs, lens) == -1)
+	if (virtio_dev_rx_batch_check(dev, vq, pkts, desc_addrs, lens) == -1)
 		return -1;
 
 	if (vq->shadow_used_idx) {
@@ -1280,8 +1276,7 @@ virtio_dev_rx_packed(struct virtio_net *dev,
 		rte_prefetch0(&vq->desc_packed[vq->last_avail_idx]);
 
 		if (count - pkt_idx >= PACKED_BATCH_SIZE) {
-			if (!virtio_dev_rx_sync_batch_packed(dev, vq,
-							&pkts[pkt_idx])) {
+			if (!virtio_dev_rx_batch_packed(dev, vq, &pkts[pkt_idx])) {
 				pkt_idx += PACKED_BATCH_SIZE;
 				continue;
 			}
@@ -1978,12 +1973,8 @@ virtio_dev_tx_split_compliant(struct virtio_net *dev,
 }
 
 static __rte_always_inline int
-vhost_reserve_avail_batch_packed(struct virtio_net *dev,
-				 struct vhost_virtqueue *vq,
-				 struct rte_mbuf **pkts,
-				 uint16_t avail_idx,
-				 uintptr_t *desc_addrs,
-				 uint16_t *ids)
+virtio_dev_tx_batch_packed_check(struct virtio_net *dev, struct vhost_virtqueue *vq,
+		struct rte_mbuf **pkts, uint16_t avail_idx, uintptr_t *desc_addrs, uint16_t *ids)
 	__rte_requires_shared_capability(&vq->iotlb_lock)
 {
 	bool wrap = vq->avail_wrap_counter;
@@ -2062,8 +2053,7 @@ virtio_dev_tx_batch_packed(struct virtio_net *dev,
 	uint16_t ids[PACKED_BATCH_SIZE];
 	uint16_t i;
 
-	if (vhost_reserve_avail_batch_packed(dev, vq, pkts, avail_idx,
-					     desc_addrs, ids))
+	if (virtio_dev_tx_batch_packed_check(dev, vq, pkts, avail_idx, desc_addrs, ids))
 		return -1;
 
 	vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE)
Signature · 1 line
2.54.0
Reviewed-by on v4 5/6
#39 lore raw

Re: [PATCH v4 5/6] vhost: rename packed layout helpers for batches

Quoted 7 lines · David Marchand

Now that the async datapath has been removed, the _sync in function names gives no useful information.

Besides, vhost_reserve_avail_batch_packed does not reserve anything and its name is confusing, rename it following the other rx/tx split/packed helpers convention.

Quoted 9 lines

---
Changes since v2:
- cleaned up indent,

---
  lib/vhost/virtio_net.c | 28 +++++++++-------------------
  1 file changed, 9 insertions(+), 19 deletions(-)

Already provided my R-by on previous revision:

#40 lore raw

PATCH v4 6/6 vhost: simplify some descriptor handling

In reply to David Marchand

Now that the async datapath has been removed, move back the descriptors copy/filling code in desc_to_mbuf/mbuf_to_desc and eliminate an intermediate helper.

Tracking buf_iova is not needed in the descriptor to mbuf case.

---
Changes since v3:
- rebased after RTE_PTR_ADD changes,

Changes since v2:
- used RTE_PTR_ADD for consistency,

---
 lib/vhost/virtio_net.c | 81 +++++++++++++++++-------------------------
 1 file changed, 32 insertions(+), 49 deletions(-)
lib/vhost/virtio_net.c +32 -49
index 6d8d788524..503b8907bc 100644
@@ -76,6 +76,12 @@ vhost_queue_stats_update(const struct virtio_net *dev, struct vhost_virtqueue *v
 	}
 }
 
+static __rte_always_inline bool
+vhost_can_batch_copy(struct vhost_virtqueue *vq, uint32_t cpy_len)
+{
+	return cpy_len <= MAX_BATCH_LEN && vq->batch_copy_nb_elems < vq->size;
+}
+
 static inline void
 do_data_copy_enqueue(struct virtio_net *dev, struct vhost_virtqueue *vq)
 	__rte_requires_shared_capability(&vq->iotlb_lock)
@@ -861,44 +867,6 @@ copy_vnet_hdr_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	return 0;
 }
 
-static __rte_always_inline void
-sync_fill_seg(struct virtio_net *dev, struct vhost_virtqueue *vq,
-		struct rte_mbuf *m, uint32_t mbuf_offset,
-		uint64_t buf_addr, uint64_t buf_iova, uint32_t cpy_len, bool to_desc)
-	__rte_requires_shared_capability(&vq->iotlb_lock)
-{
-	struct batch_copy_elem *batch_copy = vq->batch_copy_elems;
-
-	if (likely(cpy_len > MAX_BATCH_LEN || vq->batch_copy_nb_elems >= vq->size)) {
-		if (to_desc) {
-			rte_memcpy((void *)((uintptr_t)(buf_addr)),
-				rte_pktmbuf_mtod_offset(m, void *, mbuf_offset),
-				cpy_len);
-			vhost_log_cache_write_iova(dev, vq, buf_iova, cpy_len);
-			PRINT_PACKET(dev, (uintptr_t)(buf_addr), cpy_len, 0);
-		} else {
-			rte_memcpy(rte_pktmbuf_mtod_offset(m, void *, mbuf_offset),
-				(void *)((uintptr_t)(buf_addr)),
-				cpy_len);
-		}
-	} else {
-		if (to_desc) {
-			batch_copy[vq->batch_copy_nb_elems].dst =
-				(void *)((uintptr_t)(buf_addr));
-			batch_copy[vq->batch_copy_nb_elems].src =
-				rte_pktmbuf_mtod_offset(m, void *, mbuf_offset);
-			batch_copy[vq->batch_copy_nb_elems].log_addr = buf_iova;
-		} else {
-			batch_copy[vq->batch_copy_nb_elems].dst =
-				rte_pktmbuf_mtod_offset(m, void *, mbuf_offset);
-			batch_copy[vq->batch_copy_nb_elems].src =
-				(void *)((uintptr_t)(buf_addr));
-		}
-		batch_copy[vq->batch_copy_nb_elems].len = cpy_len;
-		vq->batch_copy_nb_elems++;
-	}
-}
-
 static __rte_always_inline int
 mbuf_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
 		struct rte_mbuf *m, struct buf_vector *buf_vec,
@@ -983,9 +951,23 @@ mbuf_to_desc(struct virtio_net *dev, struct vhost_virtqueue *vq,
 
 		cpy_len = RTE_MIN(buf_avail, mbuf_avail);
 
-		sync_fill_seg(dev, vq, m, mbuf_offset,
-			      buf_addr + buf_offset,
-			      buf_iova + buf_offset, cpy_len, true);
+		if (likely(!vhost_can_batch_copy(vq, cpy_len))) {
+			rte_memcpy(RTE_PTR_ADD(RTE_PTR_UNQUAL(buf_addr), buf_offset),
+				rte_pktmbuf_mtod_offset(m, void *, mbuf_offset),
+				cpy_len);
+			vhost_log_cache_write_iova(dev, vq, buf_iova + buf_offset, cpy_len);
+			PRINT_PACKET(dev, RTE_PTR_ADD(RTE_PTR_UNQUAL(buf_addr), buf_offset),
+				cpy_len, 0);
+		} else {
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].dst =
+				RTE_PTR_ADD(RTE_PTR_UNQUAL(buf_addr), buf_offset);
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].src =
+				rte_pktmbuf_mtod_offset(m, void *, mbuf_offset);
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].log_addr =
+				buf_iova + buf_offset;
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].len = cpy_len;
+			vq->batch_copy_nb_elems++;
+		}
 
 		mbuf_avail  -= cpy_len;
 		mbuf_offset += cpy_len;
@@ -1682,7 +1664,7 @@ desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	__rte_requires_shared_capability(&vq->iotlb_lock)
 {
 	uint32_t buf_avail, buf_offset, buf_len;
-	uint64_t buf_addr, buf_iova;
+	uint64_t buf_addr;
 	uint32_t mbuf_avail, mbuf_offset;
 	uint32_t hdr_remain = dev->vhost_hlen;
 	uint32_t cpy_len;
@@ -1713,7 +1695,6 @@ desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	}
 
 	buf_addr = buf_vec[vec_idx].buf_addr;
-	buf_iova = buf_vec[vec_idx].buf_iova;
 	buf_len = buf_vec[vec_idx].buf_len;
 	buf_offset = hdr_remain;
 	buf_avail = buf_vec[vec_idx].buf_len - hdr_remain;
@@ -1728,14 +1709,17 @@ desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
 	while (1) {
 		cpy_len = RTE_MIN(buf_avail, mbuf_avail);
 
-		if (likely(hdr && cur == m)) {
+		if (likely((hdr && cur == m) || !vhost_can_batch_copy(vq, cpy_len))) {
 			rte_memcpy(rte_pktmbuf_mtod_offset(cur, void *, mbuf_offset),
-				(void *)((uintptr_t)(buf_addr + buf_offset)),
+				RTE_PTR_ADD(RTE_PTR_UNQUAL(buf_addr), buf_offset),
 				cpy_len);
 		} else {
-			sync_fill_seg(dev, vq, cur, mbuf_offset,
-				      buf_addr + buf_offset,
-				      buf_iova + buf_offset, cpy_len, false);
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].dst =
+				rte_pktmbuf_mtod_offset(cur, void *, mbuf_offset);
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].src =
+				RTE_PTR_ADD(RTE_PTR_UNQUAL(buf_addr), buf_offset);
+			vq->batch_copy_elems[vq->batch_copy_nb_elems].len = cpy_len;
+			vq->batch_copy_nb_elems++;
 		}
 
 		mbuf_avail  -= cpy_len;
@@ -1749,7 +1733,6 @@ desc_to_mbuf(struct virtio_net *dev, struct vhost_virtqueue *vq,
 				break;
 
 			buf_addr = buf_vec[vec_idx].buf_addr;
-			buf_iova = buf_vec[vec_idx].buf_iova;
 			buf_len = buf_vec[vec_idx].buf_len;
 
 			buf_offset = 0;
Signature · 1 line
2.54.0
Reviewed-by on v4 6/6
#41 lore raw

Re: [PATCH v4 6/6] vhost: simplify some descriptor handling

Quoted 11 lines · David Marchand

Now that the async datapath has been removed, move back the descriptors copy/filling code in desc_to_mbuf/mbuf_to_desc and eliminate an intermediate helper.

Tracking buf_iova is not needed in the descriptor to mbuf case.

---
Changes since v3:
- rebased after RTE_PTR_ADD changes,

Quoted 7 lines

Changes since v2:
- used RTE_PTR_ADD for consistency,

---
  lib/vhost/virtio_net.c | 81 +++++++++++++++++-------------------------
  1 file changed, 32 insertions(+), 49 deletions(-)

Already provided my R-by on previous revision:

#42 lore raw
In reply to David Marchand
Quoted 11 lines · David Marchand

The integration of this feature in OVS has been postponed following feedback how the current API forced the complexity on the application side. There is no contributor working on making those changes.

The feature has no other identified opensource consumer.

On the other hand, this feature has been left unattended for some years now while the "normal" datapath is actively maintained.
It is highly likely the async datapath code, which never underwent a stabilisation phase, is riddled with bugs.

Quoted 9 lines

Given the craziness around finding security bugs with AI, and since the vhost library is a good target, I propose to drop this feature and reduce the library attack surface.

There is one complication with the vhost_crypto and some external applications that seemed to rely on the async flag to track and populate guest pages, so a new flag replacing async is added by this series.

Applied to next-virtio/for-next-net.

Thanks!
Maxime