Backport: TCP Devmem

Documentation/netlink/specs/netdev.yaml

@@ -676,6 +676,18 @@ operations:
         reply:
           attributes:
             - id
+    -
+      name: bind-tx
+      doc: Bind dmabuf to netdev for TX
+      attribute-set: dmabuf
+      do:
+        request:
+          attributes:
+            - ifindex
+            - fd
+        reply:
+          attributes:
+            - id
 
 kernel-family:
   headers: [ "linux/list.h"]

Documentation/networking/devmem.rst

@@ -62,7 +62,7 @@ More Info
     https://lore.kernel.org/netdev/[email protected]/
 
 
-Interface
+Rx Interface
 =========
 
 
@@ -235,6 +235,147 @@ can be less than the tokens provided by the user in case of:
 (a) an internal kernel leak bug.
 (b) the user passed more than 1024 frags.
 
+TX Interface
+============
+
+
+Example
+-------
+
+./tools/testing/selftests/drivers/net/hw/ncdevmem:do_client shows an example of
+setting up the TX path of this API.
+
+
+NIC Setup
+---------
+
+The user must bind a TX dmabuf to a given NIC using the netlink API::
+
+        struct netdev_bind_tx_req *req = NULL;
+        struct netdev_bind_tx_rsp *rsp = NULL;
+        struct ynl_error yerr;
+
+        *ys = ynl_sock_create(&ynl_netdev_family, &yerr);
+
+        req = netdev_bind_tx_req_alloc();
+        netdev_bind_tx_req_set_ifindex(req, ifindex);
+        netdev_bind_tx_req_set_fd(req, dmabuf_fd);
+
+        rsp = netdev_bind_tx(*ys, req);
+
+        tx_dmabuf_id = rsp->id;
+
+
+The netlink API returns a dmabuf_id: a unique ID that refers to this dmabuf
+that has been bound.
+
+The user can unbind the dmabuf from the netdevice by closing the netlink socket
+that established the binding. We do this so that the binding is automatically
+unbound even if the userspace process crashes.
+
+Note that any reasonably well-behaved dmabuf from any exporter should work with
+devmem TCP, even if the dmabuf is not actually backed by devmem. An example of
+this is udmabuf, which wraps user memory (non-devmem) in a dmabuf.
+
+Socket Setup
+------------
+
+The user application must use MSG_ZEROCOPY flag when sending devmem TCP. Devmem
+cannot be copied by the kernel, so the semantics of the devmem TX are similar
+to the semantics of MSG_ZEROCOPY::
+
+	setsockopt(socket_fd, SOL_SOCKET, SO_ZEROCOPY, &opt, sizeof(opt));
+
+It is also recommended that the user binds the TX socket to the same interface
+the dma-buf has been bound to via SO_BINDTODEVICE::
+
+	setsockopt(socket_fd, SOL_SOCKET, SO_BINDTODEVICE, ifname, strlen(ifname) + 1);
+
+
+Sending data
+------------
+
+Devmem data is sent using the SCM_DEVMEM_DMABUF cmsg.
+
+The user should create a msghdr where,
+
+* iov_base is set to the offset into the dmabuf to start sending from
+* iov_len is set to the number of bytes to be sent from the dmabuf
+
+The user passes the dma-buf id to send from via the dmabuf_tx_cmsg.dmabuf_id.
+
+The example below sends 1024 bytes from offset 100 into the dmabuf, and 2048
+from offset 2000 into the dmabuf. The dmabuf to send from is tx_dmabuf_id::
+
+       char ctrl_data[CMSG_SPACE(sizeof(struct dmabuf_tx_cmsg))];
+       struct dmabuf_tx_cmsg ddmabuf;
+       struct msghdr msg = {};
+       struct cmsghdr *cmsg;
+       struct iovec iov[2];
+
+       iov[0].iov_base = (void*)100;
+       iov[0].iov_len = 1024;
+       iov[1].iov_base = (void*)2000;
+       iov[1].iov_len = 2048;
+
+       msg.msg_iov = iov;
+       msg.msg_iovlen = 2;
+
+       msg.msg_control = ctrl_data;
+       msg.msg_controllen = sizeof(ctrl_data);
+
+       cmsg = CMSG_FIRSTHDR(&msg);
+       cmsg->cmsg_level = SOL_SOCKET;
+       cmsg->cmsg_type = SCM_DEVMEM_DMABUF;
+       cmsg->cmsg_len = CMSG_LEN(sizeof(struct dmabuf_tx_cmsg));
+
+       ddmabuf.dmabuf_id = tx_dmabuf_id;
+
+       *((struct dmabuf_tx_cmsg *)CMSG_DATA(cmsg)) = ddmabuf;
+
+       sendmsg(socket_fd, &msg, MSG_ZEROCOPY);
+
+
+Reusing TX dmabufs
+------------------
+
+Similar to MSG_ZEROCOPY with regular memory, the user should not modify the
+contents of the dma-buf while a send operation is in progress. This is because
+the kernel does not keep a copy of the dmabuf contents. Instead, the kernel
+will pin and send data from the buffer available to the userspace.
+
+Just as in MSG_ZEROCOPY, the kernel notifies the userspace of send completions
+using MSG_ERRQUEUE::
+
+        int64_t tstop = gettimeofday_ms() + waittime_ms;
+        char control[CMSG_SPACE(100)] = {};
+        struct sock_extended_err *serr;
+        struct msghdr msg = {};
+        struct cmsghdr *cm;
+        int retries = 10;
+        __u32 hi, lo;
+
+        msg.msg_control = control;
+        msg.msg_controllen = sizeof(control);
+
+        while (gettimeofday_ms() < tstop) {
+                if (!do_poll(fd)) continue;
+
+                ret = recvmsg(fd, &msg, MSG_ERRQUEUE);
+
+                for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) {
+                        serr = (void *)CMSG_DATA(cm);
+
+                        hi = serr->ee_data;
+                        lo = serr->ee_info;
+
+                        fprintf(stdout, "tx complete [%d,%d]\n", lo, hi);
+                }
+        }
+
+After the associated sendmsg has been completed, the dmabuf can be reused by
+the userspace.
+
 Implementation & Caveats
 ========================
 

Documentation/networking/index.rst

@@ -85,6 +85,7 @@ Contents:
    netdevices
    netfilter-sysctl
    netif-msg
+   netmem
    nexthop-group-resilient
    nf_conntrack-sysctl
    nf_flowtable

Documentation/networking/net_cachelines/net_device.rst

@@ -9,6 +9,7 @@ Type                                Name                    fastpath_tx_access
 ..struct                            ..net_device                                                    
 unsigned_long:32                    priv_flags              read_mostly         -                   __dev_queue_xmit(tx)
 unsigned_long:1                     lltx                    read_mostly         -                   HARD_TX_LOCK,HARD_TX_TRYLOCK,HARD_TX_UNLOCK(tx)
+unsigned long:1                     netmem_tx:1;            read_mostly
 char                                name[16]                -                   -                   
 struct_netdev_name_node*            name_node                                                       
 struct_dev_ifalias*                 ifalias                                                         

Documentation/networking/netdev-features.rst

@@ -188,3 +188,8 @@ Redundancy) frames from one port to another in hardware.
 This should be set for devices which duplicate outgoing HSR (High-availability
 Seamless Redundancy) or PRP (Parallel Redundancy Protocol) tags automatically
 frames in hardware.
+
+* netmem-tx
+
+This should be set for devices which support netmem TX. See
+Documentation/networking/netmem.rst

Documentation/networking/netmem.rst

@@ -0,0 +1,98 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==================================
+Netmem Support for Network Drivers
+==================================
+
+This document outlines the requirements for network drivers to support netmem,
+an abstract memory type that enables features like device memory TCP. By
+supporting netmem, drivers can work with various underlying memory types
+with little to no modification.
+
+Benefits of Netmem :
+
+* Flexibility: Netmem can be backed by different memory types (e.g., struct
+  page, DMA-buf), allowing drivers to support various use cases such as device
+  memory TCP.
+* Future-proof: Drivers with netmem support are ready for upcoming
+  features that rely on it.
+* Simplified Development: Drivers interact with a consistent API,
+  regardless of the underlying memory implementation.
+
+Driver Rx Requirements
+======================
+
+1. The driver must support page_pool.
+
+2. The driver must support the tcp-data-split ethtool option.
+
+3. The driver must use the page_pool netmem APIs for payload memory. The netmem
+   APIs currently 1-to-1 correspond with page APIs. Conversion to netmem should
+   be achievable by switching the page APIs to netmem APIs and tracking memory
+   via netmem_refs in the driver rather than struct page * :
+
+   - page_pool_alloc -> page_pool_alloc_netmem
+   - page_pool_get_dma_addr -> page_pool_get_dma_addr_netmem
+   - page_pool_put_page -> page_pool_put_netmem
+
+   Not all page APIs have netmem equivalents at the moment. If your driver
+   relies on a missing netmem API, feel free to add and propose to netdev@, or
+   reach out to the maintainers and/or [email protected] for help adding
+   the netmem API.
+
+4. The driver must use the following PP_FLAGS:
+
+   - PP_FLAG_DMA_MAP: netmem is not dma-mappable by the driver. The driver
+     must delegate the dma mapping to the page_pool, which knows when
+     dma-mapping is (or is not) appropriate.
+   - PP_FLAG_DMA_SYNC_DEV: netmem dma addr is not necessarily dma-syncable
+     by the driver. The driver must delegate the dma syncing to the page_pool,
+     which knows when dma-syncing is (or is not) appropriate.
+   - PP_FLAG_ALLOW_UNREADABLE_NETMEM. The driver must specify this flag iff
+     tcp-data-split is enabled.
+
+5. The driver must not assume the netmem is readable and/or backed by pages.
+   The netmem returned by the page_pool may be unreadable, in which case
+   netmem_address() will return NULL. The driver must correctly handle
+   unreadable netmem, i.e. don't attempt to handle its contents when
+   netmem_address() is NULL.
+
+   Ideally, drivers should not have to check the underlying netmem type via
+   helpers like netmem_is_net_iov() or convert the netmem to any of its
+   underlying types via netmem_to_page() or netmem_to_net_iov(). In most cases,
+   netmem or page_pool helpers that abstract this complexity are provided
+   (and more can be added).
+
+6. The driver must use page_pool_dma_sync_netmem_for_cpu() in lieu of
+   dma_sync_single_range_for_cpu(). For some memory providers, dma_syncing for
+   CPU will be done by the page_pool, for others (particularly dmabuf memory
+   provider), dma syncing for CPU is the responsibility of the userspace using
+   dmabuf APIs. The driver must delegate the entire dma-syncing operation to
+   the page_pool which will do it correctly.
+
+7. Avoid implementing driver-specific recycling on top of the page_pool. Drivers
+   cannot hold onto a struct page to do their own recycling as the netmem may
+   not be backed by a struct page. However, you may hold onto a page_pool
+   reference with page_pool_fragment_netmem() or page_pool_ref_netmem() for
+   that purpose, but be mindful that some netmem types might have longer
+   circulation times, such as when userspace holds a reference in zerocopy
+   scenarios.
+
+Driver TX Requirements
+======================
+
+1. The Driver must not pass the netmem dma_addr to any of the dma-mapping APIs
+   directly. This is because netmem dma_addrs may come from a source like
+   dma-buf that is not compatible with the dma-mapping APIs.
+
+   Helpers like netmem_dma_unmap_page_attrs() & netmem_dma_unmap_addr_set()
+   should be used in lieu of dma_unmap_page[_attrs](), dma_unmap_addr_set().
+   The netmem variants will handle netmem dma_addrs correctly regardless of the
+   source, delegating to the dma-mapping APIs when appropriate.
+
+   Not all dma-mapping APIs have netmem equivalents at the moment. If your
+   driver relies on a missing netmem API, feel free to add and propose to
+   netdev@, or reach out to the maintainers and/or [email protected] for
+   help adding the netmem API.
+
+2. Driver should declare support by setting `netdev->netmem_tx = true`

drivers/net/ethernet/google/Kconfig

@@ -18,6 +18,7 @@ if NET_VENDOR_GOOGLE
 config GVE
 	tristate "Google Virtual NIC (gVNIC) support"
 	depends on (PCI_MSI && (X86 || CPU_LITTLE_ENDIAN))
+	select PAGE_POOL
 	help
 	  This driver supports Google Virtual NIC (gVNIC)"
 

drivers/net/ethernet/google/gve/Makefile

@@ -1,4 +1,5 @@
 # Makefile for the Google virtual Ethernet (gve) driver
 
 obj-$(CONFIG_GVE) += gve.o
-gve-objs := gve_main.o gve_tx.o gve_tx_dqo.o gve_rx.o gve_rx_dqo.o gve_ethtool.o gve_adminq.o gve_utils.o gve_flow_rule.o
+gve-objs := gve_main.o gve_tx.o gve_tx_dqo.o gve_rx.o gve_rx_dqo.o gve_ethtool.o gve_adminq.o gve_utils.o gve_flow_rule.o \
+	    gve_buffer_mgmt_dqo.o