Merge remote-tracking branch 'remotes/jasowang/tags/net-pull-request'…

… into staging

# gpg: Signature made Fri 04 Jun 2021 08:26:16 BST
# gpg:                using RSA key EF04965B398D6211
# gpg: Good signature from "Jason Wang (Jason Wang on RedHat) <jasowang@redhat.com>" [marginal]
# gpg: WARNING: This key is not certified with sufficiently trusted signatures!
# gpg:          It is not certain that the signature belongs to the owner.
# Primary key fingerprint: 215D 46F4 8246 689E C77F  3562 EF04 965B 398D 6211

* remotes/jasowang/tags/net-pull-request:
  MAINTAINERS: Added eBPF maintainers information.
  docs: Added eBPF documentation.
  virtio-net: Added eBPF RSS to virtio-net.
  ebpf: Added eBPF RSS loader.
  ebpf: Added eBPF RSS program.
  net: Added SetSteeringEBPF method for NetClientState.
  net/tap: Added TUNSETSTEERINGEBPF code.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

MAINTAINERS

@@ -3316,6 +3316,14 @@ F: include/hw/remote/proxy-memory-listener.h
 F: hw/remote/iohub.c
 F: include/hw/remote/iohub.h
 
+EBPF:
+M: Jason Wang <jasowang@redhat.com>
+R: Andrew Melnychenko <andrew@daynix.com>
+R: Yuri Benditovich <yuri.benditovich@daynix.com>
+S: Maintained
+F: ebpf/*
+F: tools/ebpf/*
+
 Build and test automation
 -------------------------
 Build and test automation, general continuous integration

configure

@@ -328,6 +328,7 @@ vhost_vsock="$default_feature"
 vhost_user="no"
 vhost_user_blk_server="auto"
 vhost_user_fs="$default_feature"
+bpf="auto"
 kvm="auto"
 hax="auto"
 hvf="auto"
@@ -1219,6 +1220,10 @@ for opt do
   ;;
   --enable-membarrier) membarrier="yes"
   ;;
+  --disable-bpf) bpf="disabled"
+  ;;
+  --enable-bpf) bpf="enabled"
+  ;;
   --disable-blobs) blobs="false"
   ;;
   --with-pkgversion=*) pkgversion="$optarg"
@@ -1879,6 +1884,7 @@ disabled with --disable-FEATURE, default is enabled if available
   vhost-user      vhost-user backend support
   vhost-user-blk-server    vhost-user-blk server support
   vhost-vdpa      vhost-vdpa kernel backend support
+  bpf             BPF kernel support
   spice           spice
   spice-protocol  spice-protocol
   rbd             rados block device (rbd)
@@ -6440,7 +6446,7 @@ if test "$skip_meson" = no; then
         -Dattr=$attr -Ddefault_devices=$default_devices \
         -Ddocs=$docs -Dsphinx_build=$sphinx_build -Dinstall_blobs=$blobs \
         -Dvhost_user_blk_server=$vhost_user_blk_server -Dmultiprocess=$multiprocess \
-        -Dfuse=$fuse -Dfuse_lseek=$fuse_lseek -Dguest_agent_msi=$guest_agent_msi \
+        -Dfuse=$fuse -Dfuse_lseek=$fuse_lseek -Dguest_agent_msi=$guest_agent_msi -Dbpf=$bpf\
         $(if test "$default_features" = no; then echo "-Dauto_features=disabled"; fi) \
 	-Dtcg_interpreter=$tcg_interpreter \
         $cross_arg \

docs/devel/ebpf_rss.rst

@@ -0,0 +1,125 @@
+===========================
+eBPF RSS virtio-net support
+===========================
+
+RSS(Receive Side Scaling) is used to distribute network packets to guest virtqueues
+by calculating packet hash. Usually every queue is processed then by a specific guest CPU core.
+
+For now there are 2 RSS implementations in qemu:
+- 'in-qemu' RSS (functions if qemu receives network packets, i.e. vhost=off)
+- eBPF RSS (can function with also with vhost=on)
+
+eBPF support (CONFIG_EBPF) is enabled by 'configure' script.
+To enable eBPF RSS support use './configure --enable-bpf'.
+
+If steering BPF is not set for kernel's TUN module, the TUN uses automatic selection
+of rx virtqueue based on lookup table built according to calculated symmetric hash
+of transmitted packets.
+If steering BPF is set for TUN the BPF code calculates the hash of packet header and
+returns the virtqueue number to place the packet to.
+
+Simplified decision formula:
+
+.. code:: C
+
+    queue_index = indirection_table[hash(<packet data>)%<indirection_table size>]
+
+
+Not for all packets, the hash can/should be calculated.
+
+Note: currently, eBPF RSS does not support hash reporting.
+
+eBPF RSS turned on by different combinations of vhost-net, vitrio-net and tap configurations:
+
+- eBPF is used:
+
+        tap,vhost=off & virtio-net-pci,rss=on,hash=off
+
+- eBPF is used:
+
+        tap,vhost=on & virtio-net-pci,rss=on,hash=off
+
+- 'in-qemu' RSS is used:
+
+        tap,vhost=off & virtio-net-pci,rss=on,hash=on
+
+- eBPF is used, hash population feature is not reported to the guest:
+
+        tap,vhost=on & virtio-net-pci,rss=on,hash=on
+
+If CONFIG_EBPF is not set then only 'in-qemu' RSS is supported.
+Also 'in-qemu' RSS, as a fallback, is used if the eBPF program failed to load or set to TUN.
+
+RSS eBPF program
+----------------
+
+RSS program located in ebpf/rss.bpf.skeleton.h generated by bpftool.
+So the program is part of the qemu binary.
+Initially, the eBPF program was compiled by clang and source code located at tools/ebpf/rss.bpf.c.
+Prerequisites to recompile the eBPF program (regenerate ebpf/rss.bpf.skeleton.h):
+
+        llvm, clang, kernel source tree, bpftool
+        Adjust Makefile.ebpf to reflect the location of the kernel source tree
+
+        $ cd tools/ebpf
+        $ make -f Makefile.ebpf
+
+Current eBPF RSS implementation uses 'bounded loops' with 'backward jump instructions' which present in the last kernels.
+Overall eBPF RSS works on kernels 5.8+.
+
+eBPF RSS implementation
+-----------------------
+
+eBPF RSS loading functionality located in ebpf/ebpf_rss.c and ebpf/ebpf_rss.h.
+
+The `struct EBPFRSSContext` structure that holds 4 file descriptors:
+
+- ctx - pointer of the libbpf context.
+- program_fd - file descriptor of the eBPF RSS program.
+- map_configuration - file descriptor of the 'configuration' map. This map contains one element of 'struct EBPFRSSConfig'. This configuration determines eBPF program behavior.
+- map_toeplitz_key - file descriptor of the 'Toeplitz key' map. One element of the 40byte key prepared for the hashing algorithm.
+- map_indirections_table - 128 elements of queue indexes.
+
+`struct EBPFRSSConfig` fields:
+
+- redirect - "boolean" value, should the hash be calculated, on false  - `default_queue` would be used as the final decision.
+- populate_hash - for now, not used. eBPF RSS doesn't support hash reporting.
+- hash_types - binary mask of different hash types. See `VIRTIO_NET_RSS_HASH_TYPE_*` defines. If for packet hash should not be calculated - `default_queue` would be used.
+- indirections_len - length of the indirections table, maximum 128.
+- default_queue - the queue index that used for packet that shouldn't be hashed. For some packets, the hash can't be calculated(g.e ARP).
+
+Functions:
+
+- `ebpf_rss_init()` - sets ctx to NULL, which indicates that EBPFRSSContext is not loaded.
+- `ebpf_rss_load()` - creates 3 maps and loads eBPF program from the rss.bpf.skeleton.h. Returns 'true' on success. After that, program_fd can be used to set steering for TAP.
+- `ebpf_rss_set_all()` - sets values for eBPF maps. `indirections_table` length is in EBPFRSSConfig. `toeplitz_key` is VIRTIO_NET_RSS_MAX_KEY_SIZE aka 40 bytes array.
+- `ebpf_rss_unload()` - close all file descriptors and set ctx to NULL.
+
+Simplified eBPF RSS workflow:
+
+.. code:: C
+
+    struct EBPFRSSConfig config;
+    config.redirect = 1;
+    config.hash_types = VIRTIO_NET_RSS_HASH_TYPE_UDPv4 | VIRTIO_NET_RSS_HASH_TYPE_TCPv4;
+    config.indirections_len = VIRTIO_NET_RSS_MAX_TABLE_LEN;
+    config.default_queue = 0;
+
+    uint16_t table[VIRTIO_NET_RSS_MAX_TABLE_LEN] = {...};
+    uint8_t key[VIRTIO_NET_RSS_MAX_KEY_SIZE] = {...};
+
+    struct EBPFRSSContext ctx;
+    ebpf_rss_init(&ctx);
+    ebpf_rss_load(&ctx);
+    ebpf_rss_set_all(&ctx, &config, table, key);
+    if (net_client->info->set_steering_ebpf != NULL) {
+        net_client->info->set_steering_ebpf(net_client, ctx->program_fd);
+    }
+    ...
+    ebpf_unload(&ctx);
+
+
+NetClientState SetSteeringEBPF()
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+For now, `set_steering_ebpf()` method supported by Linux TAP NetClientState. The method requires an eBPF program file descriptor as an argument.

docs/devel/index.rst

@@ -43,3 +43,4 @@ Contents:
    qom
    block-coroutine-wrapper
    multi-process
+   ebpf_rss

ebpf/ebpf_rss-stub.c

@@ -0,0 +1,40 @@
+/*
+ * eBPF RSS stub file
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Yuri Benditovich <yuri.benditovich@daynix.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "ebpf/ebpf_rss.h"
+
+void ebpf_rss_init(struct EBPFRSSContext *ctx)
+{
+
+}
+
+bool ebpf_rss_is_loaded(struct EBPFRSSContext *ctx)
+{
+    return false;
+}
+
+bool ebpf_rss_load(struct EBPFRSSContext *ctx)
+{
+    return false;
+}
+
+bool ebpf_rss_set_all(struct EBPFRSSContext *ctx, struct EBPFRSSConfig *config,
+                      uint16_t *indirections_table, uint8_t *toeplitz_key)
+{
+    return false;
+}
+
+void ebpf_rss_unload(struct EBPFRSSContext *ctx)
+{
+
+}

ebpf/ebpf_rss.c

@@ -0,0 +1,165 @@
+/*
+ * eBPF RSS loader
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko <andrew@daynix.com>
+ *  Yuri Benditovich <yuri.benditovich@daynix.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/error-report.h"
+
+#include <bpf/libbpf.h>
+#include <bpf/bpf.h>
+
+#include "hw/virtio/virtio-net.h" /* VIRTIO_NET_RSS_MAX_TABLE_LEN */
+
+#include "ebpf/ebpf_rss.h"
+#include "ebpf/rss.bpf.skeleton.h"
+#include "trace.h"
+
+void ebpf_rss_init(struct EBPFRSSContext *ctx)
+{
+    if (ctx != NULL) {
+        ctx->obj = NULL;
+    }
+}
+
+bool ebpf_rss_is_loaded(struct EBPFRSSContext *ctx)
+{
+    return ctx != NULL && ctx->obj != NULL;
+}
+
+bool ebpf_rss_load(struct EBPFRSSContext *ctx)
+{
+    struct rss_bpf *rss_bpf_ctx;
+
+    if (ctx == NULL) {
+        return false;
+    }
+
+    rss_bpf_ctx = rss_bpf__open();
+    if (rss_bpf_ctx == NULL) {
+        trace_ebpf_error("eBPF RSS", "can not open eBPF RSS object");
+        goto error;
+    }
+
+    bpf_program__set_socket_filter(rss_bpf_ctx->progs.tun_rss_steering_prog);
+
+    if (rss_bpf__load(rss_bpf_ctx)) {
+        trace_ebpf_error("eBPF RSS", "can not load RSS program");
+        goto error;
+    }
+
+    ctx->obj = rss_bpf_ctx;
+    ctx->program_fd = bpf_program__fd(
+            rss_bpf_ctx->progs.tun_rss_steering_prog);
+    ctx->map_configuration = bpf_map__fd(
+            rss_bpf_ctx->maps.tap_rss_map_configurations);
+    ctx->map_indirections_table = bpf_map__fd(
+            rss_bpf_ctx->maps.tap_rss_map_indirection_table);
+    ctx->map_toeplitz_key = bpf_map__fd(
+            rss_bpf_ctx->maps.tap_rss_map_toeplitz_key);
+
+    return true;
+error:
+    rss_bpf__destroy(rss_bpf_ctx);
+    ctx->obj = NULL;
+
+    return false;
+}
+
+static bool ebpf_rss_set_config(struct EBPFRSSContext *ctx,
+                                struct EBPFRSSConfig *config)
+{
+    uint32_t map_key = 0;
+
+    if (!ebpf_rss_is_loaded(ctx)) {
+        return false;
+    }
+    if (bpf_map_update_elem(ctx->map_configuration,
+                            &map_key, config, 0) < 0) {
+        return false;
+    }
+    return true;
+}
+
+static bool ebpf_rss_set_indirections_table(struct EBPFRSSContext *ctx,
+                                            uint16_t *indirections_table,
+                                            size_t len)
+{
+    uint32_t i = 0;
+
+    if (!ebpf_rss_is_loaded(ctx) || indirections_table == NULL ||
+       len > VIRTIO_NET_RSS_MAX_TABLE_LEN) {
+        return false;
+    }
+
+    for (; i < len; ++i) {
+        if (bpf_map_update_elem(ctx->map_indirections_table, &i,
+                                indirections_table + i, 0) < 0) {
+            return false;
+        }
+    }
+    return true;
+}
+
+static bool ebpf_rss_set_toepliz_key(struct EBPFRSSContext *ctx,
+                                     uint8_t *toeplitz_key)
+{
+    uint32_t map_key = 0;
+
+    /* prepare toeplitz key */
+    uint8_t toe[VIRTIO_NET_RSS_MAX_KEY_SIZE] = {};
+
+    if (!ebpf_rss_is_loaded(ctx) || toeplitz_key == NULL) {
+        return false;
+    }
+    memcpy(toe, toeplitz_key, VIRTIO_NET_RSS_MAX_KEY_SIZE);
+    *(uint32_t *)toe = ntohl(*(uint32_t *)toe);
+
+    if (bpf_map_update_elem(ctx->map_toeplitz_key, &map_key, toe,
+                            0) < 0) {
+        return false;
+    }
+    return true;
+}
+
+bool ebpf_rss_set_all(struct EBPFRSSContext *ctx, struct EBPFRSSConfig *config,
+                      uint16_t *indirections_table, uint8_t *toeplitz_key)
+{
+    if (!ebpf_rss_is_loaded(ctx) || config == NULL ||
+        indirections_table == NULL || toeplitz_key == NULL) {
+        return false;
+    }
+
+    if (!ebpf_rss_set_config(ctx, config)) {
+        return false;
+    }
+
+    if (!ebpf_rss_set_indirections_table(ctx, indirections_table,
+                                      config->indirections_len)) {
+        return false;
+    }
+
+    if (!ebpf_rss_set_toepliz_key(ctx, toeplitz_key)) {
+        return false;
+    }
+
+    return true;
+}
+
+void ebpf_rss_unload(struct EBPFRSSContext *ctx)
+{
+    if (!ebpf_rss_is_loaded(ctx)) {
+        return;
+    }
+
+    rss_bpf__destroy(ctx->obj);
+    ctx->obj = NULL;
+}