Merge tag 'net-pull-request' of https://github.com/jasowang/qemu into…

… staging

# -----BEGIN PGP SIGNATURE-----
# Version: GnuPG v1
#
# iQEcBAABAgAGBQJk+sEHAAoJEO8Ells5jWIRMjUH/i6Sv+19/kz2CFOsfNT6tK0O
# hcOo8Pn7WKvEvFgMM7+mZVYQTHj+78hXyen1XgvzZh7557vDAQNo9wwl0fmSRTR4
# qg/ocWg2K4zeTt/DChv3bTpJgOf31nIxffDfGt4QlMw6AZFJqAcr8JHuG7ezq259
# a5yy3b83HA7vexuz9p1UmFat4ps4yLcd/q7EGr0zqBkmUWPWg3fzJSRCTXG0p6GK
# +5TUzjZBzK1FuGBLAea8+ULJahSTM11fjCG11qcptOQ9lbFqEHTZYgwgTcOCDxFv
# hObNgRBHuqlK/rjw8d6m6oE+I4LMSXfbllgH4zuRNKm4YWhzAs6SXsLIo1+yJH0=
# =EXgN
# -----END PGP SIGNATURE-----
# gpg: Signature made Fri 08 Sep 2023 02:36:55 EDT
# gpg:                using RSA key EF04965B398D6211
# gpg: Good signature from "Jason Wang (Jason Wang on RedHat) <jasowang@redhat.com>" [full]
# Primary key fingerprint: 215D 46F4 8246 689E C77F  3562 EF04 965B 398D 6211

* tag 'net-pull-request' of https://github.com/jasowang/qemu:
  ebpf: Updated eBPF program and skeleton.
  qmp: Added new command to retrieve eBPF blob.
  virtio-net: Added property to load eBPF RSS with fds.
  ebpf: Added eBPF initialization by fds.
  ebpf: Added eBPF map update through mmap.
  net: add initial support for AF_XDP network backend
  e1000e: rename e1000e_ba_state and e1000e_write_hdr_to_rx_buffers
  igb: packet-split descriptors support
  igb: add IPv6 extended headers traffic detection
  igb: RX payload guest writting refactoring
  igb: RX descriptors guest writting refactoring
  igb: rename E1000E_RingInfo_st
  igb: remove TCP ACK detection
  virtio-net: Add support for USO features
  virtio-net: Add USO flags to vhost support.
  tap: Add check for USO features
  tap: Add USO support to tap device.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

MAINTAINERS

@@ -2947,6 +2947,10 @@ W: http://info.iet.unipi.it/~luigi/netmap/
 S: Maintained
 F: net/netmap.c
 
+AF_XDP network backend
+R: Ilya Maximets <i.maximets@ovn.org>
+F: net/af-xdp.c
+
 Host Memory Backends
 M: David Hildenbrand <david@redhat.com>
 M: Igor Mammedov <imammedo@redhat.com>

ebpf/ebpf.c

@@ -0,0 +1,70 @@
+/*
+ * QEMU eBPF binary declaration routine.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko <andrew@daynix.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or
+ * later.  See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/queue.h"
+#include "qapi/error.h"
+#include "qapi/qapi-commands-ebpf.h"
+#include "ebpf/ebpf.h"
+
+struct ElfBinaryDataEntry {
+    int id;
+    const void *data;
+    size_t datalen;
+
+    QSLIST_ENTRY(ElfBinaryDataEntry) node;
+};
+
+static QSLIST_HEAD(, ElfBinaryDataEntry) ebpf_elf_obj_list =
+                                            QSLIST_HEAD_INITIALIZER();
+
+void ebpf_register_binary_data(int id, const void *data, size_t datalen)
+{
+    struct ElfBinaryDataEntry *dataentry = NULL;
+
+    dataentry = g_new0(struct ElfBinaryDataEntry, 1);
+    dataentry->data = data;
+    dataentry->datalen = datalen;
+    dataentry->id = id;
+
+    QSLIST_INSERT_HEAD(&ebpf_elf_obj_list, dataentry, node);
+}
+
+const void *ebpf_find_binary_by_id(int id, size_t *sz, Error **errp)
+{
+    struct ElfBinaryDataEntry *it = NULL;
+    QSLIST_FOREACH(it, &ebpf_elf_obj_list, node) {
+        if (id == it->id) {
+            *sz = it->datalen;
+            return it->data;
+        }
+    }
+
+    error_setg(errp, "can't find eBPF object with id: %d", id);
+
+    return NULL;
+}
+
+EbpfObject *qmp_request_ebpf(EbpfProgramID id, Error **errp)
+{
+    EbpfObject *ret = NULL;
+    size_t size = 0;
+    const void *data = ebpf_find_binary_by_id(id, &size, errp);
+    if (!data) {
+        return NULL;
+    }
+
+    ret = g_new0(EbpfObject, 1);
+    ret->object = g_base64_encode(data, size);
+
+    return ret;
+}

ebpf/ebpf.h

@@ -0,0 +1,31 @@
+/*
+ * QEMU eBPF binary declaration routine.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko <andrew@daynix.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or
+ * later.  See the COPYING file in the top-level directory.
+ */
+
+#ifndef EBPF_H
+#define EBPF_H
+
+struct Error;
+
+void ebpf_register_binary_data(int id, const void *data,
+                               size_t datalen);
+const void *ebpf_find_binary_by_id(int id, size_t *sz,
+                                   struct Error **errp);
+
+#define ebpf_binary_init(id, fn)                                           \
+static void __attribute__((constructor)) ebpf_binary_init_ ## fn(void)     \
+{                                                                          \
+    size_t datalen = 0;                                                    \
+    const void *data = fn(&datalen);                                       \
+    ebpf_register_binary_data(id, data, datalen);                          \
+}
+
+#endif /* EBPF_H */

ebpf/ebpf_rss-stub.c

@@ -28,6 +28,12 @@ bool ebpf_rss_load(struct EBPFRSSContext *ctx)
     return false;
 }
 
+bool ebpf_rss_load_fds(struct EBPFRSSContext *ctx, int program_fd,
+                       int config_fd, int toeplitz_fd, int table_fd)
+{
+    return false;
+}
+
 bool ebpf_rss_set_all(struct EBPFRSSContext *ctx, struct EBPFRSSConfig *config,
                       uint16_t *indirections_table, uint8_t *toeplitz_key)
 {

ebpf/ebpf_rss.c

@@ -13,6 +13,8 @@
 
 #include "qemu/osdep.h"
 #include "qemu/error-report.h"
+#include "qapi/qapi-types-misc.h"
+#include "qapi/qapi-commands-ebpf.h"
 
 #include <bpf/libbpf.h>
 #include <bpf/bpf.h>
@@ -21,25 +23,91 @@
 
 #include "ebpf/ebpf_rss.h"
 #include "ebpf/rss.bpf.skeleton.h"
+#include "ebpf/ebpf.h"
+
 #include "trace.h"
 
 void ebpf_rss_init(struct EBPFRSSContext *ctx)
 {
     if (ctx != NULL) {
         ctx->obj = NULL;
+        ctx->program_fd = -1;
+        ctx->map_configuration = -1;
+        ctx->map_toeplitz_key = -1;
+        ctx->map_indirections_table = -1;
+
+        ctx->mmap_configuration = NULL;
+        ctx->mmap_toeplitz_key = NULL;
+        ctx->mmap_indirections_table = NULL;
     }
 }
 
 bool ebpf_rss_is_loaded(struct EBPFRSSContext *ctx)
 {
-    return ctx != NULL && ctx->obj != NULL;
+    return ctx != NULL && (ctx->obj != NULL || ctx->program_fd != -1);
+}
+
+static bool ebpf_rss_mmap(struct EBPFRSSContext *ctx)
+{
+    if (!ebpf_rss_is_loaded(ctx)) {
+        return false;
+    }
+
+    ctx->mmap_configuration = mmap(NULL, qemu_real_host_page_size(),
+                                   PROT_READ | PROT_WRITE, MAP_SHARED,
+                                   ctx->map_configuration, 0);
+    if (ctx->mmap_configuration == MAP_FAILED) {
+        trace_ebpf_error("eBPF RSS", "can not mmap eBPF configuration array");
+        return false;
+    }
+    ctx->mmap_toeplitz_key = mmap(NULL, qemu_real_host_page_size(),
+                                   PROT_READ | PROT_WRITE, MAP_SHARED,
+                                   ctx->map_toeplitz_key, 0);
+    if (ctx->mmap_toeplitz_key == MAP_FAILED) {
+        trace_ebpf_error("eBPF RSS", "can not mmap eBPF toeplitz key");
+        goto toeplitz_fail;
+    }
+    ctx->mmap_indirections_table = mmap(NULL, qemu_real_host_page_size(),
+                                   PROT_READ | PROT_WRITE, MAP_SHARED,
+                                   ctx->map_indirections_table, 0);
+    if (ctx->mmap_indirections_table == MAP_FAILED) {
+        trace_ebpf_error("eBPF RSS", "can not mmap eBPF indirection table");
+        goto indirection_fail;
+    }
+
+    return true;
+
+indirection_fail:
+    munmap(ctx->mmap_toeplitz_key, qemu_real_host_page_size());
+toeplitz_fail:
+    munmap(ctx->mmap_configuration, qemu_real_host_page_size());
+
+    ctx->mmap_configuration = NULL;
+    ctx->mmap_toeplitz_key = NULL;
+    ctx->mmap_indirections_table = NULL;
+    return false;
+}
+
+static void ebpf_rss_munmap(struct EBPFRSSContext *ctx)
+{
+    if (!ebpf_rss_is_loaded(ctx)) {
+        return;
+    }
+
+    munmap(ctx->mmap_indirections_table, qemu_real_host_page_size());
+    munmap(ctx->mmap_toeplitz_key, qemu_real_host_page_size());
+    munmap(ctx->mmap_configuration, qemu_real_host_page_size());
+
+    ctx->mmap_configuration = NULL;
+    ctx->mmap_toeplitz_key = NULL;
+    ctx->mmap_indirections_table = NULL;
 }
 
 bool ebpf_rss_load(struct EBPFRSSContext *ctx)
 {
     struct rss_bpf *rss_bpf_ctx;
 
-    if (ctx == NULL) {
+    if (ctx == NULL || ebpf_rss_is_loaded(ctx)) {
         return false;
     }
 
@@ -66,54 +134,77 @@ bool ebpf_rss_load(struct EBPFRSSContext *ctx)
     ctx->map_toeplitz_key = bpf_map__fd(
             rss_bpf_ctx->maps.tap_rss_map_toeplitz_key);
 
+    if (!ebpf_rss_mmap(ctx)) {
+        goto error;
+    }
+
     return true;
 error:
     rss_bpf__destroy(rss_bpf_ctx);
     ctx->obj = NULL;
+    ctx->program_fd = -1;
+    ctx->map_configuration = -1;
+    ctx->map_toeplitz_key = -1;
+    ctx->map_indirections_table = -1;
 
     return false;
 }
 
-static bool ebpf_rss_set_config(struct EBPFRSSContext *ctx,
-                                struct EBPFRSSConfig *config)
+bool ebpf_rss_load_fds(struct EBPFRSSContext *ctx, int program_fd,
+                       int config_fd, int toeplitz_fd, int table_fd)
 {
-    uint32_t map_key = 0;
+    if (ctx == NULL || ebpf_rss_is_loaded(ctx)) {
+        return false;
+    }
 
-    if (!ebpf_rss_is_loaded(ctx)) {
+    if (program_fd < 0 || config_fd < 0 || toeplitz_fd < 0 || table_fd < 0) {
+        return false;
+    }
+
+    ctx->program_fd = program_fd;
+    ctx->map_configuration = config_fd;
+    ctx->map_toeplitz_key = toeplitz_fd;
+    ctx->map_indirections_table = table_fd;
+
+    if (!ebpf_rss_mmap(ctx)) {
+        ctx->program_fd = -1;
+        ctx->map_configuration = -1;
+        ctx->map_toeplitz_key = -1;
+        ctx->map_indirections_table = -1;
         return false;
     }
-    if (bpf_map_update_elem(ctx->map_configuration,
-                            &map_key, config, 0) < 0) {
+
+    return true;
+}
+
+static bool ebpf_rss_set_config(struct EBPFRSSContext *ctx,
+                                struct EBPFRSSConfig *config)
+{
+    if (!ebpf_rss_is_loaded(ctx)) {
         return false;
     }
+
+    memcpy(ctx->mmap_configuration, config, sizeof(*config));
     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;
-        }
-    }
+    memcpy(ctx->mmap_indirections_table, indirections_table,
+            sizeof(*indirections_table) * len);
     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] = {};
 
@@ -123,10 +214,7 @@ static bool ebpf_rss_set_toepliz_key(struct EBPFRSSContext *ctx,
     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;
-    }
+    memcpy(ctx->mmap_toeplitz_key, toe, VIRTIO_NET_RSS_MAX_KEY_SIZE);
     return true;
 }
 
@@ -160,6 +248,22 @@ void ebpf_rss_unload(struct EBPFRSSContext *ctx)
         return;
     }
 
-    rss_bpf__destroy(ctx->obj);
+    ebpf_rss_munmap(ctx);
+
+    if (ctx->obj) {
+        rss_bpf__destroy(ctx->obj);
+    } else {
+        close(ctx->program_fd);
+        close(ctx->map_configuration);
+        close(ctx->map_toeplitz_key);
+        close(ctx->map_indirections_table);
+    }
+
     ctx->obj = NULL;
+    ctx->program_fd = -1;
+    ctx->map_configuration = -1;
+    ctx->map_toeplitz_key = -1;
+    ctx->map_indirections_table = -1;
 }
+
+ebpf_binary_init(EBPF_PROGRAMID_RSS, rss_bpf__elf_bytes)

ebpf/ebpf_rss.h

@@ -14,12 +14,19 @@
 #ifndef QEMU_EBPF_RSS_H
 #define QEMU_EBPF_RSS_H
 
+#define EBPF_RSS_MAX_FDS 4
+
 struct EBPFRSSContext {
     void *obj;
     int program_fd;
     int map_configuration;
     int map_toeplitz_key;
     int map_indirections_table;
+
+    /* mapped eBPF maps for direct access to omit bpf_map_update_elem() */
+    void *mmap_configuration;
+    void *mmap_toeplitz_key;
+    void *mmap_indirections_table;
 };
 
 struct EBPFRSSConfig {
@@ -36,6 +43,9 @@ bool ebpf_rss_is_loaded(struct EBPFRSSContext *ctx);
 
 bool ebpf_rss_load(struct EBPFRSSContext *ctx);
 
+bool ebpf_rss_load_fds(struct EBPFRSSContext *ctx, int program_fd,
+                       int config_fd, int toeplitz_fd, int table_fd);
+
 bool ebpf_rss_set_all(struct EBPFRSSContext *ctx, struct EBPFRSSConfig *config,
                       uint16_t *indirections_table, uint8_t *toeplitz_key);
 

ebpf/meson.build

@@ -1 +1 @@
-system_ss.add(when: libbpf, if_true: files('ebpf_rss.c'), if_false: files('ebpf_rss-stub.c'))
+common_ss.add(when: libbpf, if_true: files('ebpf.c', 'ebpf_rss.c'), if_false: files('ebpf_rss-stub.c'))