from:"Andrew Melnychenko"

[PATCH v2 1/1] ebpf: Added traces back. Changed source set for eBPF to 'system'.

2024-04-22 Thread Andrew Melnychenko

There was an issue with Qemu build with "--disable-system".
The traces could be generated and the build fails.
The traces were 'cut out' for previous patches, and overall,
the 'system' source set should be used like in pre-'eBPF blob' patches.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf_rss.c  | 7 +++
 ebpf/meson.build | 2 +-
 ebpf/trace.h | 1 +
 3 files changed, 9 insertions(+), 1 deletion(-)
 create mode 100644 ebpf/trace.h

diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index d102f3dd092..87f0714910e 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -25,6 +25,8 @@
 #include "ebpf/rss.bpf.skeleton.h"
 #include "ebpf/ebpf.h"
 
+#include "trace.h"
+
 void ebpf_rss_init(struct EBPFRSSContext *ctx)
 {
 if (ctx != NULL) {
@@ -55,18 +57,21 @@ static bool ebpf_rss_mmap(struct EBPFRSSContext *ctx)
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;
 }
 
@@ -108,12 +113,14 @@ bool ebpf_rss_load(struct EBPFRSSContext *ctx)
 
 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_type(rss_bpf_ctx->progs.tun_rss_steering_prog, 
BPF_PROG_TYPE_SOCKET_FILTER);
 
 if (rss_bpf__load(rss_bpf_ctx)) {
+trace_ebpf_error("eBPF RSS", "can not load RSS program");
 goto error;
 }
 
diff --git a/ebpf/meson.build b/ebpf/meson.build
index c5bf9295a20..bff6156f518 100644
--- a/ebpf/meson.build
+++ b/ebpf/meson.build
@@ -1 +1 @@
-common_ss.add(when: libbpf, if_true: files('ebpf.c', 'ebpf_rss.c'), if_false: 
files('ebpf_rss-stub.c'))
+system_ss.add(when: libbpf, if_true: files('ebpf.c', 'ebpf_rss.c'), if_false: 
files('ebpf_rss-stub.c'))
diff --git a/ebpf/trace.h b/ebpf/trace.h
new file mode 100644
index 000..abefc46ab10
--- /dev/null
+++ b/ebpf/trace.h
@@ -0,0 +1 @@
+#include "trace/trace-ebpf.h"
-- 
2.44.0

[PATCH 1/1] ebpf: Added traces back. Changed source set for eBPF to 'system'.

2024-03-29 Thread Andrew Melnychenko

There was an issue with Qemu build with "--disable-system".
The traces could be generated and the build fails.
The traces were 'cut out' for previous patches, and overall,
the 'system' source set should be used like in pre-'eBPF blob' patches.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf_rss.c  | 7 +++
 ebpf/meson.build | 2 +-
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index 2e506f97435..c8a68da2c56 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -25,6 +25,8 @@
 #include "ebpf/rss.bpf.skeleton.h"
 #include "ebpf/ebpf.h"
 
+#include "trace.h"
+
 void ebpf_rss_init(struct EBPFRSSContext *ctx)
 {
 if (ctx != NULL) {
@@ -55,18 +57,21 @@ static bool ebpf_rss_mmap(struct EBPFRSSContext *ctx)
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;
 }
 
@@ -108,12 +113,14 @@ bool ebpf_rss_load(struct EBPFRSSContext *ctx)
 
 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_type(rss_bpf_ctx->progs.tun_rss_steering_prog, 
BPF_PROG_TYPE_SOCKET_FILTER);
 
 if (rss_bpf__load(rss_bpf_ctx)) {
+trace_ebpf_error("eBPF RSS", "can not load RSS program");
 goto error;
 }
 
diff --git a/ebpf/meson.build b/ebpf/meson.build
index c5bf9295a20..bff6156f518 100644
--- a/ebpf/meson.build
+++ b/ebpf/meson.build
@@ -1 +1 @@
-common_ss.add(when: libbpf, if_true: files('ebpf.c', 'ebpf_rss.c'), if_false: 
files('ebpf_rss-stub.c'))
+system_ss.add(when: libbpf, if_true: files('ebpf.c', 'ebpf_rss.c'), if_false: 
files('ebpf_rss-stub.c'))
-- 
2.43.0

[PATCH v9 4/5] qmp: Added new command to retrieve eBPF blob.

2024-02-05 Thread Andrew Melnychenko

Now, the binary objects may be retrieved by id.
It would require for future qmp commands that may require specific
eBPF blob.

Added command "request-ebpf". This command returns
eBPF program encoded base64. The program taken from the
skeleton and essentially is an ELF object that can be
loaded in the future with libbpf.

The reason to use the command to provide the eBPF object
instead of a separate artifact was to avoid issues related
to finding the eBPF itself. eBPF object is an ELF binary
that contains the eBPF program and eBPF map description(BTF).
Overall, eBPF object should contain the program and enough
metadata to create/load eBPF with libbpf. As the eBPF
maps/program should correspond to QEMU, the eBPF can't
be used from different QEMU build.

The first solution was a helper that comes with QEMU
and loads appropriate eBPF objects. And the issue is
to find a proper helper if the system has several
different QEMUs installed and/or built from the source,
which helpers may not be compatible.

Another issue is QEMU updating while there is a running
QEMU instance. With an updated helper, it may not be
possible to hotplug virtio-net device to the already
running QEMU. Overall, requesting the eBPF object from
QEMU itself solves possible failures with acceptable effort.

Links:
[PATCH 3/5] qmp: Added the helper stamp check.
https://lore.kernel.org/all/20230219162100.174318-4-and...@daynix.com/

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf.c   | 69 +++
 ebpf/ebpf.h   | 29 ++
 ebpf/ebpf_rss.c   |  6 
 ebpf/meson.build  |  2 +-
 qapi/ebpf.json| 66 +
 qapi/meson.build  |  1 +
 qapi/qapi-schema.json |  1 +
 7 files changed, 173 insertions(+), 1 deletion(-)
 create mode 100644 ebpf/ebpf.c
 create mode 100644 ebpf/ebpf.h
 create mode 100644 qapi/ebpf.json

diff --git a/ebpf/ebpf.c b/ebpf/ebpf.c
new file mode 100644
index 00..2d73beb479
--- /dev/null
+++ b/ebpf/ebpf.c
@@ -0,0 +1,69 @@
+/*
+ * QEMU eBPF binary declaration routine.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/queue.h"
+#include "qapi/error.h"
+#include "qapi/qapi-commands-ebpf.h"
+#include "ebpf/ebpf.h"
+
+typedef struct ElfBinaryDataEntry {
+int id;
+const void *data;
+size_t datalen;
+
+QSLIST_ENTRY(ElfBinaryDataEntry) node;
+} ElfBinaryDataEntry;
+
+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(_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, _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, , errp);
+if (!data) {
+return NULL;
+}
+
+ret = g_new0(EbpfObject, 1);
+ret->object = g_base64_encode(data, size);
+
+return ret;
+}
diff --git a/ebpf/ebpf.h b/ebpf/ebpf.h
new file mode 100644
index 00..378d4e9c70
--- /dev/null
+++ b/ebpf/ebpf.h
@@ -0,0 +1,29 @@
+/*
+ * QEMU eBPF binary declaration routine.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#ifndef EBPF_H
+#define EBPF_H
+
+
+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();   \
+ebpf_register_binary_data(id, data, datalen);  \
+}
+
+#endif /* EBPF_H */
diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index 150aa40813..c8a68d

[PATCH v9 2/5] ebpf: Added eBPF initialization by fds.

2024-02-05 Thread Andrew Melnychenko

It allows using file descriptors of eBPF provided
outside of QEMU.
QEMU may be run without capabilities for eBPF and run
RSS program provided by management tool(g.e. libvirt).

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf_rss-stub.c |  6 ++
 ebpf/ebpf_rss.c  | 27 +++
 ebpf/ebpf_rss.h  |  5 +
 3 files changed, 38 insertions(+)

diff --git a/ebpf/ebpf_rss-stub.c b/ebpf/ebpf_rss-stub.c
index e71e229190..8d7fae2ad9 100644
--- a/ebpf/ebpf_rss-stub.c
+++ b/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)
 {
diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index f774d9636b..150aa40813 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -146,6 +146,33 @@ error:
 return false;
 }
 
+bool ebpf_rss_load_fds(struct EBPFRSSContext *ctx, int program_fd,
+   int config_fd, int toeplitz_fd, int table_fd)
+{
+if (ebpf_rss_is_loaded(ctx)) {
+return false;
+}
+
+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;
+}
+
+return true;
+}
+
 static bool ebpf_rss_set_config(struct EBPFRSSContext *ctx,
 struct EBPFRSSConfig *config)
 {
diff --git a/ebpf/ebpf_rss.h b/ebpf/ebpf_rss.h
index ab08a7266d..239242b0d2 100644
--- a/ebpf/ebpf_rss.h
+++ b/ebpf/ebpf_rss.h
@@ -14,6 +14,8 @@
 #ifndef QEMU_EBPF_RSS_H
 #define QEMU_EBPF_RSS_H
 
+#define EBPF_RSS_MAX_FDS 4
+
 struct EBPFRSSContext {
 void *obj;
 int program_fd;
@@ -41,6 +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);
 
-- 
2.43.0

[PATCH v9 0/5] eBPF RSS through QMP support.

2024-02-05 Thread Andrew Melnychenko

This series of patches provides the ability to retrieve eBPF program
through qmp, so management application may load bpf blob with proper 
capabilities.
Now, virtio-net devices can accept eBPF programs and maps through properties
as external file descriptors. Access to the eBPF map is direct through mmap()
call, so it should not require additional capabilities to bpf* calls.
eBPF file descriptors can be passed to QEMU from parent process or by unix
socket with sendfd() qmp command.

Changes since v8:
 * rebased and refactored QMP interface
 * license SPDX id only for new files

Changes since v7:
 * rebased and refactored
 * used SPDX license identifier
 * used DEFINE_PROP_ARRAY() for virtio-net "ebpf-rss-fds" property

Changes since v6:
 * added comments to ebpf.json
 * added libbpf version requirements to meson script with BPF_F_MMAPABLE check

Changes since v5:
 * refactored ebpf.json

Changes since v4:
 * refactored commit hunks
 * added explicit BPF_F_MMAPABLE declaration

Changes since v3:
 * fixed issue with the build if bpf disabled
 * rebased to the last master
 * refactored according to review

Changes since v2:
 * moved/refactored QMP command
 * refactored virtio-net

Changes since v1:
 * refactored virtio-net
 * moved hunks for ebpf mmap()
 * added qmp enum for eBPF id.

Andrew Melnychenko (5):
  ebpf: Added eBPF map update through mmap.
  ebpf: Added eBPF initialization by fds.
  virtio-net: Added property to load eBPF RSS with fds.
  qmp: Added new command to retrieve eBPF blob.
  ebpf: Updated eBPF program and skeleton.

 ebpf/ebpf.c|   69 ++
 ebpf/ebpf.h|   29 +
 ebpf/ebpf_rss-stub.c   |6 +
 ebpf/ebpf_rss.c|  150 +++-
 ebpf/ebpf_rss.h|   10 +
 ebpf/meson.build   |2 +-
 ebpf/rss.bpf.skeleton.h| 1343 
 hw/net/virtio-net.c|   54 +-
 include/hw/virtio/virtio-net.h |2 +
 meson.build|   10 +-
 qapi/ebpf.json |   66 ++
 qapi/meson.build   |1 +
 qapi/qapi-schema.json  |1 +
 tools/ebpf/rss.bpf.c   |7 +-
 14 files changed, 1047 insertions(+), 703 deletions(-)
 create mode 100644 ebpf/ebpf.c
 create mode 100644 ebpf/ebpf.h
 create mode 100644 qapi/ebpf.json

-- 
2.43.0

[PATCH v9 5/5] ebpf: Updated eBPF program and skeleton.

2024-02-05 Thread Andrew Melnychenko

Updated section name, so libbpf should init/gues proper
program type without specifications during open/load.
Also, added map_flags with explicitly declared BPF_F_MMAPABLE.
Added check for BPF_F_MMAPABLE flag to meson script and
requirements to libbpf version.
Also changed fragmentation flag check - some TCP/UDP packets
may be considered fragmented if DF flag is set.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/rss.bpf.skeleton.h | 1343 ---
 meson.build |   10 +-
 tools/ebpf/rss.bpf.c|7 +-
 3 files changed, 687 insertions(+), 673 deletions(-)

diff --git a/ebpf/rss.bpf.skeleton.h b/ebpf/rss.bpf.skeleton.h
index 18eb2adb12..aed4ef9a03 100644
--- a/ebpf/rss.bpf.skeleton.h
+++ b/ebpf/rss.bpf.skeleton.h
@@ -176,642 +176,647 @@ err:
 
 static inline const void *rss_bpf__elf_bytes(size_t *sz)
 {
-   *sz = 20440;
+   *sz = 20600;
return (const void *)"\
 \x7f\x45\x4c\x46\x02\x01\x01\0\0\0\0\0\0\0\0\0\x01\0\xf7\0\x01\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\x98\x4c\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0d\0\
-\x01\0\xbf\x19\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\x54\xff\0\0\0\0\xbf\xa7\
-\0\0\0\0\0\0\x07\x07\0\0\x54\xff\xff\xff\x18\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\x38\x4d\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0d\0\
+\x01\0\xbf\x19\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\x4c\xff\0\0\0\0\xbf\xa7\
+\0\0\0\0\0\0\x07\x07\0\0\x4c\xff\xff\xff\x18\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
 \xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x06\0\0\0\0\0\0\x18\x01\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x08\0\0\0\0\0\0\
-\x18\0\0\0\xff\xff\xff\xff\0\0\0\0\0\0\0\0\x15\x06\x67\x02\0\0\0\0\xbf\x87\0\0\
-\0\0\0\0\x15\x07\x65\x02\0\0\0\0\x71\x61\0\0\0\0\0\0\x55\x01\x01\0\0\0\0\0\x05\
-\0\x5e\x02\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xc8\xff\0\0\0\0\x7b\x1a\xc0\xff\
-\0\0\0\0\x7b\x1a\xb8\xff\0\0\0\0\x7b\x1a\xb0\xff\0\0\0\0\x7b\x1a\xa8\xff\0\0\0\
-\0\x63\x1a\xa0\xff\0\0\0\0\x7b\x1a\x98\xff\0\0\0\0\x7b\x1a\x90\xff\0\0\0\0\x7b\
-\x1a\x88\xff\0\0\0\0\x7b\x1a\x80\xff\0\0\0\0\x7b\x1a\x78\xff\0\0\0\0\x7b\x1a\
-\x70\xff\0\0\0\0\x7b\x1a\x68\xff\0\0\0\0\x7b\x1a\x60\xff\0\0\0\0\x7b\x1a\x58\
-\xff\0\0\0\0\x15\x09\x4d\x02\0\0\0\0\x6b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\
-\0\x07\x03\0\0\xd0\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x02\0\0\x0c\0\0\0\xb7\
+\0\0\0\0\0\0\0\0\0\xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x07\0\0\0\0\0\0\
+\x18\0\0\0\xff\xff\xff\xff\0\0\0\0\0\0\0\0\x15\x06\x61\x02\0\0\0\0\xbf\x78\0\0\
+\0\0\0\0\x15\x08\x5f\x02\0\0\0\0\x71\x61\0\0\0\0\0\0\x55\x01\x01\0\0\0\0\0\x05\
+\0\x58\x02\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xc0\xff\0\0\0\0\x7b\x1a\xb8\xff\
+\0\0\0\0\x7b\x1a\xb0\xff\0\0\0\0\x7b\x1a\xa8\xff\0\0\0\0\x7b\x1a\xa0\xff\0\0\0\
+\0\x63\x1a\x98\xff\0\0\0\0\x7b\x1a\x90\xff\0\0\0\0\x7b\x1a\x88\xff\0\0\0\0\x7b\
+\x1a\x80\xff\0\0\0\0\x7b\x1a\x78\xff\0\0\0\0\x7b\x1a\x70\xff\0\0\0\0\x7b\x1a\
+\x68\xff\0\0\0\0\x7b\x1a\x60\xff\0\0\0\0\x7b\x1a\x58\xff\0\0\0\0\x7b\x1a\x50\
+\xff\0\0\0\0\x15\x09\x47\x02\0\0\0\0\x6b\x1a\xc8\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\
+\0\x07\x03\0\0\xc8\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x02\0\0\x0c\0\0\0\xb7\
 \x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\
-\x77\0\0\0\x20\0\0\0\x55\0\x42\x02\0\0\0\0\xb7\x02\0\0\x10\0\0\0\x69\xa1\xd0\
+\x77\0\0\0\x20\0\0\0\x55\0\x3c\x02\0\0\0\0\xb7\x02\0\0\x10\0\0\0\x69\xa1\xc8\
 \xff\0\0\0\0\xbf\x13\0\0\0\0\0\0\xdc\x03\0\0\x10\0\0\0\x15\x03\x02\0\0\x81\0\0\
 \x55\x03\x0b\0\xa8\x88\0\0\xb7\x02\0\0\x14\0\0\0\xbf\xa3\0\0\0\0\0\0\x07\x03\0\
-\0\xd0\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\
-\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\x77\0\0\0\x20\0\0\0\x55\0\x32\x02\0\
-\0\0\0\x69\xa1\xd0\xff\0\0\0\0\x15\x01\x30\x02\0\0\0\0\x7b\x7a\x38\xff\0\0\0\0\
-\x7b\x9a\x40\xff\0\0\0\0\x15\x01\x55\0\x86\xdd\0\0\x55\x01\x39\0\x08\0\0\0\xb7\
-\x07\0\0\x01\0\0\0\x73\x7a\x58\xff\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xe0\xff\
-\0\0\0\0\x7b\x1a\xd8\xff\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\0\
-\x07\x03\0\0\xd0\xff\xff\xff\x79\xa1\x40\xff\0\0\0\0\xb7\x02\0\0\0\0\0\0\xb7\
-\x04\0\0\x14\0\0\0\xb7\x05\0\0\x01\0\0\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\
-\0\x77\0\0\0\x20\0\0\0\x55\0\x1c\x02\0\0\0\0\x69\xa1\xd6\xff\0\0\0\0\x55\x01\
-\x01\0\0\0\0\0\xb7\x07\0\0\0\0\0\0\x61\xa1\xdc\xff\0\0\0\0\x63\x1a\x64\xff\0\0\
-\0\0\x61\xa1\xe0\xff\0\0\0\0\x63\x1a\x68\xff\0\0\0\0\x71\xa9\xd9\xff\0\0\0\0\
-\x73\x7a\x5e\xff\0\0\0\0\x71\xa1\xd0\xff\0\0\0\0\x67\x01\0\0\x02\0\0\0\x57\x01\
-\0\0\x3c\0\0\0\x7b\x1a\x48\xff\0\0\0\0\xbf\x91\0\0\0\0\0\0\x57\x01\0\0\xff\0\0\
-\0\x15\x01\x19\0\0\0\0\0\x57\x07\0\0\xff\0\0\0\x55\x07\x17\0\0\0\0\0\x57\x09\0\
-\0\xff\0\0\0\x15\x09\x5a\x01\x11\0\0\0\x55\x09\x14\0\x06\0\0\0\xb7\x01\0\0\x01\
-\0\0\0\x73\x1a\x5b\xff\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xe0\xff\0\0\0\0\x7b\
-\x1a\xd8\xff\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\0\x07\x03\0\0\
-\xd0\xff\xff\xff\x79\xa1\x40\xff\0\0\0\0\x7

[PATCH v9 3/5] virtio-net: Added property to load eBPF RSS with fds.

2024-02-05 Thread Andrew Melnychenko

eBPF RSS program and maps may now be passed during initialization.
Initially was implemented for libvirt to launch qemu without permissions,
and initialized eBPF program through the helper.

Signed-off-by: Andrew Melnychenko 
---
 hw/net/virtio-net.c| 54 ++
 include/hw/virtio/virtio-net.h |  2 ++
 2 files changed, 50 insertions(+), 6 deletions(-)

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 5a79bc3a3a..d6dc5ff2ea 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -42,6 +42,7 @@
 #include "sysemu/sysemu.h"
 #include "trace.h"
 #include "monitor/qdev.h"
+#include "monitor/monitor.h"
 #include "hw/pci/pci_device.h"
 #include "net_rx_pkt.h"
 #include "hw/virtio/vhost.h"
@@ -1328,14 +1329,53 @@ static void virtio_net_detach_epbf_rss(VirtIONet *n)
 virtio_net_attach_ebpf_to_backend(n->nic, -1);
 }
 
-static bool virtio_net_load_ebpf(VirtIONet *n)
+static bool virtio_net_load_ebpf_fds(VirtIONet *n, Error **errp)
 {
-if (!virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
-/* backend doesn't support steering ebpf */
-return false;
+int fds[EBPF_RSS_MAX_FDS] = { [0 ... EBPF_RSS_MAX_FDS - 1] = -1};
+int ret = true;
+int i = 0;
+
+ERRP_GUARD();
+
+if (n->nr_ebpf_rss_fds != EBPF_RSS_MAX_FDS) {
+error_setg(errp,
+  "Expected %d file descriptors but got %d",
+  EBPF_RSS_MAX_FDS, n->nr_ebpf_rss_fds);
+   return false;
+   }
+
+for (i = 0; i < n->nr_ebpf_rss_fds; i++) {
+fds[i] = monitor_fd_param(monitor_cur(), n->ebpf_rss_fds[i], errp);
+if (*errp) {
+ret = false;
+goto exit;
+}
+}
+
+ret = ebpf_rss_load_fds(>ebpf_rss, fds[0], fds[1], fds[2], fds[3]);
+
+exit:
+if (!ret || *errp) {
+for (i = 0; i < n->nr_ebpf_rss_fds && fds[i] != -1; i++) {
+close(fds[i]);
+}
 }
 
-return ebpf_rss_load(>ebpf_rss);
+return ret;
+}
+
+static bool virtio_net_load_ebpf(VirtIONet *n, Error **errp)
+{
+bool ret = false;
+
+if (virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
+if (!(n->ebpf_rss_fds
+&& virtio_net_load_ebpf_fds(n, errp))) {
+ret = ebpf_rss_load(>ebpf_rss);
+}
+}
+
+return ret;
 }
 
 static void virtio_net_unload_ebpf(VirtIONet *n)
@@ -3767,7 +3807,7 @@ static void virtio_net_device_realize(DeviceState *dev, 
Error **errp)
 net_rx_pkt_init(>rx_pkt);
 
 if (virtio_has_feature(n->host_features, VIRTIO_NET_F_RSS)) {
-virtio_net_load_ebpf(n);
+virtio_net_load_ebpf(n, errp);
 }
 }
 
@@ -3929,6 +3969,8 @@ static Property virtio_net_properties[] = {
 VIRTIO_NET_F_RSS, false),
 DEFINE_PROP_BIT64("hash", VirtIONet, host_features,
 VIRTIO_NET_F_HASH_REPORT, false),
+DEFINE_PROP_ARRAY("ebpf-rss-fds", VirtIONet, nr_ebpf_rss_fds,
+  ebpf_rss_fds, qdev_prop_string, char*),
 DEFINE_PROP_BIT64("guest_rsc_ext", VirtIONet, host_features,
 VIRTIO_NET_F_RSC_EXT, false),
 DEFINE_PROP_UINT32("rsc_interval", VirtIONet, rsc_timeout,
diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h
index 55977f01f0..566ec53e7e 100644
--- a/include/hw/virtio/virtio-net.h
+++ b/include/hw/virtio/virtio-net.h
@@ -225,6 +225,8 @@ struct VirtIONet {
 VirtioNetRssData rss_data;
 struct NetRxPkt *rx_pkt;
 struct EBPFRSSContext ebpf_rss;
+uint32_t nr_ebpf_rss_fds;
+char **ebpf_rss_fds;
 };
 
 size_t virtio_net_handle_ctrl_iov(VirtIODevice *vdev,
-- 
2.43.0

[PATCH v9 1/5] ebpf: Added eBPF map update through mmap.

2024-02-05 Thread Andrew Melnychenko

Changed eBPF map updates through mmaped array.
Mmaped arrays provide direct access to map data.
It should omit using bpf_map_update_elem() call,
which may require capabilities that are not present.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf_rss.c | 117 ++--
 ebpf/ebpf_rss.h |   5 +++
 2 files changed, 99 insertions(+), 23 deletions(-)

diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index cee658c158..f774d9636b 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -27,19 +27,83 @@ 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());
+ctx->mmap_toeplitz_key = NULL;
+toeplitz_fail:
+munmap(ctx->mmap_configuration, qemu_real_host_page_size());
+ctx->mmap_configuration = 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 (ebpf_rss_is_loaded(ctx)) {
 return false;
 }
 
@@ -66,10 +130,18 @@ 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;
 }
@@ -77,15 +149,11 @@ error:
 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,
-_key, config, 0) < 0) {
-return false;
-}
+
+memcpy(ctx->mmap_configuration, config, sizeof(*config));
 return true;
 }
 
@@ -93,27 +161,19 @@ 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, ,
-indirections_tabl

[PATCH v8 2/5] ebpf: Added eBPF initialization by fds.

2024-01-25 Thread Andrew Melnychenko

It allows using file descriptors of eBPF provided
outside of QEMU.
QEMU may be run without capabilities for eBPF and run
RSS program provided by management tool(g.e. libvirt).

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf_rss-stub.c |  9 +++--
 ebpf/ebpf_rss.c  | 27 +++
 ebpf/ebpf_rss.h  |  5 +
 3 files changed, 39 insertions(+), 2 deletions(-)

diff --git a/ebpf/ebpf_rss-stub.c b/ebpf/ebpf_rss-stub.c
index e71e229190..1c158b6e06 100644
--- a/ebpf/ebpf_rss-stub.c
+++ b/ebpf/ebpf_rss-stub.c
@@ -6,8 +6,7 @@
  * Authors:
  *  Yuri Benditovich 
  *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
+ * SPDX-License-Identifier: GPL-2.0-or-later
  */
 
 #include "qemu/osdep.h"
@@ -28,6 +27,12 @@ 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)
 {
diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index c6e10265a7..20c44f2baa 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -145,6 +145,33 @@ error:
 return false;
 }
 
+bool ebpf_rss_load_fds(struct EBPFRSSContext *ctx, int program_fd,
+   int config_fd, int toeplitz_fd, int table_fd)
+{
+if (ebpf_rss_is_loaded(ctx)) {
+return false;
+}
+
+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;
+}
+
+return true;
+}
+
 static bool ebpf_rss_set_config(struct EBPFRSSContext *ctx,
 struct EBPFRSSConfig *config)
 {
diff --git a/ebpf/ebpf_rss.h b/ebpf/ebpf_rss.h
index 404cf53613..39646aff6f 100644
--- a/ebpf/ebpf_rss.h
+++ b/ebpf/ebpf_rss.h
@@ -13,6 +13,8 @@
 #ifndef QEMU_EBPF_RSS_H
 #define QEMU_EBPF_RSS_H
 
+#define EBPF_RSS_MAX_FDS 4
+
 struct EBPFRSSContext {
 void *obj;
 int program_fd;
@@ -40,6 +42,9 @@ 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);
 
-- 
2.43.0

[PATCH v8 0/5] eBPF RSS through QMP support.

2024-01-25 Thread Andrew Melnychenko

This series of patches provides the ability to retrieve eBPF program
through qmp, so management application may load bpf blob with proper 
capabilities.
Now, virtio-net devices can accept eBPF programs and maps through properties
as external file descriptors. Access to the eBPF map is direct through mmap()
call, so it should not require additional capabilities to bpf* calls.
eBPF file descriptors can be passed to QEMU from parent process or by unix
socket with sendfd() qmp command.

Changes since v8:
 * rebased and refactored QMP interface

Changes since v7:
 * rebased and refactored
 * used SPDX license identifier
 * used DEFINE_PROP_ARRAY() for virtio-net "ebpf-rss-fds" property

Changes since v6:
 * added comments to ebpf.json
 * added libbpf version requirements to meson script with BPF_F_MMAPABLE check

Changes since v5:
 * refactored ebpf.json

Changes since v4:
 * refactored commit hunks
 * added explicit BPF_F_MMAPABLE declaration

Changes since v3:
 * fixed issue with the build if bpf disabled
 * rebased to the last master
 * refactored according to review

Changes since v2:
 * moved/refactored QMP command
 * refactored virtio-net

Changes since v1:
 * refactored virtio-net
 * moved hunks for ebpf mmap()
 * added qmp enum for eBPF id.
 
Andrew Melnychenko (5):
  ebpf: Added eBPF map update through mmap.
  ebpf: Added eBPF initialization by fds.
  virtio-net: Added property to load eBPF RSS with fds.
  qmp: Added new command to retrieve eBPF blob.
  ebpf: Updated eBPF program and skeleton.

 ebpf/ebpf.c|   69 ++
 ebpf/ebpf.h|   29 +
 ebpf/ebpf_rss-stub.c   |9 +-
 ebpf/ebpf_rss.c|  153 +++-
 ebpf/ebpf_rss.h|   13 +-
 ebpf/meson.build   |2 +-
 ebpf/rss.bpf.skeleton.h| 1343 
 hw/net/virtio-net.c|   63 +-
 include/hw/virtio/virtio-net.h |2 +
 meson.build|   10 +-
 qapi/ebpf.json |   66 ++
 qapi/meson.build   |1 +
 qapi/qapi-schema.json  |1 +
 tools/ebpf/rss.bpf.c   |7 +-
 14 files changed, 1059 insertions(+), 709 deletions(-)
 create mode 100644 ebpf/ebpf.c
 create mode 100644 ebpf/ebpf.h
 create mode 100644 qapi/ebpf.json

-- 
2.43.0

[PATCH v8 1/5] ebpf: Added eBPF map update through mmap.

2024-01-25 Thread Andrew Melnychenko

Changed eBPF map updates through mmaped array.
Mmaped arrays provide direct access to map data.
It should omit using bpf_map_update_elem() call,
which may require capabilities that are not present.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf_rss.c | 120 ++--
 ebpf/ebpf_rss.h |   8 +++-
 2 files changed, 101 insertions(+), 27 deletions(-)

diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index cee658c158..c6e10265a7 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -7,8 +7,7 @@
  *  Andrew Melnychenko 
  *  Yuri Benditovich 
  *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
+ * SPDX-License-Identifier: GPL-2.0-or-later
  */
 
 #include "qemu/osdep.h"
@@ -27,19 +26,83 @@ 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());
+ctx->mmap_toeplitz_key = NULL;
+toeplitz_fail:
+munmap(ctx->mmap_configuration, qemu_real_host_page_size());
+ctx->mmap_configuration = 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 (ebpf_rss_is_loaded(ctx)) {
 return false;
 }
 
@@ -66,10 +129,18 @@ 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;
 }
@@ -77,15 +148,11 @@ error:
 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,
-_key, config, 0) < 0) {
-return false;
-}
+
+memcpy(ctx->mmap_configuration, config, sizeof(*config));
 return true;
 }
 
@@ -93,27 +160,19 @@ static bool ebpf_rss_set_indirections_table(struct 
EBPFRSSContext *ctx,
 uint16_t *indirections_table,
 size_t len)
 {
-uint32_t i = 0;
-

[PATCH v8 5/5] ebpf: Updated eBPF program and skeleton.

2024-01-25 Thread Andrew Melnychenko

Updated section name, so libbpf should init/gues proper
program type without specifications during open/load.
Also, added map_flags with explicitly declared BPF_F_MMAPABLE.
Added check for BPF_F_MMAPABLE flag to meson script and
requirements to libbpf version.
Also changed fragmentation flag check - some TCP/UDP packets
may be considered fragmented if DF flag is set.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/rss.bpf.skeleton.h | 1343 ---
 meson.build |   10 +-
 tools/ebpf/rss.bpf.c|7 +-
 3 files changed, 687 insertions(+), 673 deletions(-)

diff --git a/ebpf/rss.bpf.skeleton.h b/ebpf/rss.bpf.skeleton.h
index 18eb2adb12..aed4ef9a03 100644
--- a/ebpf/rss.bpf.skeleton.h
+++ b/ebpf/rss.bpf.skeleton.h
@@ -176,642 +176,647 @@ err:
 
 static inline const void *rss_bpf__elf_bytes(size_t *sz)
 {
-   *sz = 20440;
+   *sz = 20600;
return (const void *)"\
 \x7f\x45\x4c\x46\x02\x01\x01\0\0\0\0\0\0\0\0\0\x01\0\xf7\0\x01\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\x98\x4c\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0d\0\
-\x01\0\xbf\x19\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\x54\xff\0\0\0\0\xbf\xa7\
-\0\0\0\0\0\0\x07\x07\0\0\x54\xff\xff\xff\x18\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\x38\x4d\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0d\0\
+\x01\0\xbf\x19\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\x4c\xff\0\0\0\0\xbf\xa7\
+\0\0\0\0\0\0\x07\x07\0\0\x4c\xff\xff\xff\x18\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
 \xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x06\0\0\0\0\0\0\x18\x01\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x08\0\0\0\0\0\0\
-\x18\0\0\0\xff\xff\xff\xff\0\0\0\0\0\0\0\0\x15\x06\x67\x02\0\0\0\0\xbf\x87\0\0\
-\0\0\0\0\x15\x07\x65\x02\0\0\0\0\x71\x61\0\0\0\0\0\0\x55\x01\x01\0\0\0\0\0\x05\
-\0\x5e\x02\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xc8\xff\0\0\0\0\x7b\x1a\xc0\xff\
-\0\0\0\0\x7b\x1a\xb8\xff\0\0\0\0\x7b\x1a\xb0\xff\0\0\0\0\x7b\x1a\xa8\xff\0\0\0\
-\0\x63\x1a\xa0\xff\0\0\0\0\x7b\x1a\x98\xff\0\0\0\0\x7b\x1a\x90\xff\0\0\0\0\x7b\
-\x1a\x88\xff\0\0\0\0\x7b\x1a\x80\xff\0\0\0\0\x7b\x1a\x78\xff\0\0\0\0\x7b\x1a\
-\x70\xff\0\0\0\0\x7b\x1a\x68\xff\0\0\0\0\x7b\x1a\x60\xff\0\0\0\0\x7b\x1a\x58\
-\xff\0\0\0\0\x15\x09\x4d\x02\0\0\0\0\x6b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\
-\0\x07\x03\0\0\xd0\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x02\0\0\x0c\0\0\0\xb7\
+\0\0\0\0\0\0\0\0\0\xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x07\0\0\0\0\0\0\
+\x18\0\0\0\xff\xff\xff\xff\0\0\0\0\0\0\0\0\x15\x06\x61\x02\0\0\0\0\xbf\x78\0\0\
+\0\0\0\0\x15\x08\x5f\x02\0\0\0\0\x71\x61\0\0\0\0\0\0\x55\x01\x01\0\0\0\0\0\x05\
+\0\x58\x02\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xc0\xff\0\0\0\0\x7b\x1a\xb8\xff\
+\0\0\0\0\x7b\x1a\xb0\xff\0\0\0\0\x7b\x1a\xa8\xff\0\0\0\0\x7b\x1a\xa0\xff\0\0\0\
+\0\x63\x1a\x98\xff\0\0\0\0\x7b\x1a\x90\xff\0\0\0\0\x7b\x1a\x88\xff\0\0\0\0\x7b\
+\x1a\x80\xff\0\0\0\0\x7b\x1a\x78\xff\0\0\0\0\x7b\x1a\x70\xff\0\0\0\0\x7b\x1a\
+\x68\xff\0\0\0\0\x7b\x1a\x60\xff\0\0\0\0\x7b\x1a\x58\xff\0\0\0\0\x7b\x1a\x50\
+\xff\0\0\0\0\x15\x09\x47\x02\0\0\0\0\x6b\x1a\xc8\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\
+\0\x07\x03\0\0\xc8\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x02\0\0\x0c\0\0\0\xb7\
 \x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\
-\x77\0\0\0\x20\0\0\0\x55\0\x42\x02\0\0\0\0\xb7\x02\0\0\x10\0\0\0\x69\xa1\xd0\
+\x77\0\0\0\x20\0\0\0\x55\0\x3c\x02\0\0\0\0\xb7\x02\0\0\x10\0\0\0\x69\xa1\xc8\
 \xff\0\0\0\0\xbf\x13\0\0\0\0\0\0\xdc\x03\0\0\x10\0\0\0\x15\x03\x02\0\0\x81\0\0\
 \x55\x03\x0b\0\xa8\x88\0\0\xb7\x02\0\0\x14\0\0\0\xbf\xa3\0\0\0\0\0\0\x07\x03\0\
-\0\xd0\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\
-\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\x77\0\0\0\x20\0\0\0\x55\0\x32\x02\0\
-\0\0\0\x69\xa1\xd0\xff\0\0\0\0\x15\x01\x30\x02\0\0\0\0\x7b\x7a\x38\xff\0\0\0\0\
-\x7b\x9a\x40\xff\0\0\0\0\x15\x01\x55\0\x86\xdd\0\0\x55\x01\x39\0\x08\0\0\0\xb7\
-\x07\0\0\x01\0\0\0\x73\x7a\x58\xff\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xe0\xff\
-\0\0\0\0\x7b\x1a\xd8\xff\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\0\
-\x07\x03\0\0\xd0\xff\xff\xff\x79\xa1\x40\xff\0\0\0\0\xb7\x02\0\0\0\0\0\0\xb7\
-\x04\0\0\x14\0\0\0\xb7\x05\0\0\x01\0\0\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\
-\0\x77\0\0\0\x20\0\0\0\x55\0\x1c\x02\0\0\0\0\x69\xa1\xd6\xff\0\0\0\0\x55\x01\
-\x01\0\0\0\0\0\xb7\x07\0\0\0\0\0\0\x61\xa1\xdc\xff\0\0\0\0\x63\x1a\x64\xff\0\0\
-\0\0\x61\xa1\xe0\xff\0\0\0\0\x63\x1a\x68\xff\0\0\0\0\x71\xa9\xd9\xff\0\0\0\0\
-\x73\x7a\x5e\xff\0\0\0\0\x71\xa1\xd0\xff\0\0\0\0\x67\x01\0\0\x02\0\0\0\x57\x01\
-\0\0\x3c\0\0\0\x7b\x1a\x48\xff\0\0\0\0\xbf\x91\0\0\0\0\0\0\x57\x01\0\0\xff\0\0\
-\0\x15\x01\x19\0\0\0\0\0\x57\x07\0\0\xff\0\0\0\x55\x07\x17\0\0\0\0\0\x57\x09\0\
-\0\xff\0\0\0\x15\x09\x5a\x01\x11\0\0\0\x55\x09\x14\0\x06\0\0\0\xb7\x01\0\0\x01\
-\0\0\0\x73\x1a\x5b\xff\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xe0\xff\0\0\0\0\x7b\
-\x1a\xd8\xff\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\0\x07\x03\0\0\
-\xd0\xff\xff\xff\x79\xa1\x40\xff\0\0\0\0\x7

[PATCH v8 4/5] qmp: Added new command to retrieve eBPF blob.

2024-01-25 Thread Andrew Melnychenko

Now, the binary objects may be retrieved by id.
It would require for future qmp commands that may require specific
eBPF blob.

Added command "request-ebpf". This command returns
eBPF program encoded base64. The program taken from the
skeleton and essentially is an ELF object that can be
loaded in the future with libbpf.

The reason to use the command to provide the eBPF object
instead of a separate artifact was to avoid issues related
to finding the eBPF itself. eBPF object is an ELF binary
that contains the eBPF program and eBPF map description(BTF).
Overall, eBPF object should contain the program and enough
metadata to create/load eBPF with libbpf. As the eBPF
maps/program should correspond to QEMU, the eBPF can't
be used from different QEMU build.

The first solution was a helper that comes with QEMU
and loads appropriate eBPF objects. And the issue is
to find a proper helper if the system has several
different QEMUs installed and/or built from the source,
which helpers may not be compatible.

Another issue is QEMU updating while there is a running
QEMU instance. With an updated helper, it may not be
possible to hotplug virtio-net device to the already
running QEMU. Overall, requesting the eBPF object from
QEMU itself solves possible failures with acceptable effort.

Links:
[PATCH 3/5] qmp: Added the helper stamp check.
https://lore.kernel.org/all/20230219162100.174318-4-and...@daynix.com/

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf.c   | 69 +++
 ebpf/ebpf.h   | 29 ++
 ebpf/ebpf_rss.c   |  6 
 ebpf/meson.build  |  2 +-
 qapi/ebpf.json| 66 +
 qapi/meson.build  |  1 +
 qapi/qapi-schema.json |  1 +
 7 files changed, 173 insertions(+), 1 deletion(-)
 create mode 100644 ebpf/ebpf.c
 create mode 100644 ebpf/ebpf.h
 create mode 100644 qapi/ebpf.json

diff --git a/ebpf/ebpf.c b/ebpf/ebpf.c
new file mode 100644
index 00..2d73beb479
--- /dev/null
+++ b/ebpf/ebpf.c
@@ -0,0 +1,69 @@
+/*
+ * QEMU eBPF binary declaration routine.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/queue.h"
+#include "qapi/error.h"
+#include "qapi/qapi-commands-ebpf.h"
+#include "ebpf/ebpf.h"
+
+typedef struct ElfBinaryDataEntry {
+int id;
+const void *data;
+size_t datalen;
+
+QSLIST_ENTRY(ElfBinaryDataEntry) node;
+} ElfBinaryDataEntry;
+
+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(_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, _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, , errp);
+if (!data) {
+return NULL;
+}
+
+ret = g_new0(EbpfObject, 1);
+ret->object = g_base64_encode(data, size);
+
+return ret;
+}
diff --git a/ebpf/ebpf.h b/ebpf/ebpf.h
new file mode 100644
index 00..378d4e9c70
--- /dev/null
+++ b/ebpf/ebpf.h
@@ -0,0 +1,29 @@
+/*
+ * QEMU eBPF binary declaration routine.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#ifndef EBPF_H
+#define EBPF_H
+
+
+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();   \
+ebpf_register_binary_data(id, data, datalen);  \
+}
+
+#endif /* EBPF_H */
diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index 20c44f2baa..2fa632

[PATCH v8 3/5] virtio-net: Added property to load eBPF RSS with fds.

2024-01-25 Thread Andrew Melnychenko

eBPF RSS program and maps may now be passed during initialization.
Initially was implemented for libvirt to launch qemu without permissions,
and initialized eBPF program through the helper.

Signed-off-by: Andrew Melnychenko 
---
 hw/net/virtio-net.c| 63 ++
 include/hw/virtio/virtio-net.h |  2 ++
 2 files changed, 59 insertions(+), 6 deletions(-)

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 7a2846fa1c..d7980d827a 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -42,6 +42,7 @@
 #include "sysemu/sysemu.h"
 #include "trace.h"
 #include "monitor/qdev.h"
+#include "monitor/monitor.h"
 #include "hw/pci/pci_device.h"
 #include "net_rx_pkt.h"
 #include "hw/virtio/vhost.h"
@@ -1323,14 +1324,53 @@ static void virtio_net_detach_epbf_rss(VirtIONet *n)
 virtio_net_attach_ebpf_to_backend(n->nic, -1);
 }
 
-static bool virtio_net_load_ebpf(VirtIONet *n)
+static bool virtio_net_load_ebpf_fds(VirtIONet *n, Error **errp)
 {
-if (!virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
-/* backend doesn't support steering ebpf */
-return false;
+int fds[EBPF_RSS_MAX_FDS] = { [0 ... EBPF_RSS_MAX_FDS - 1] = -1};
+int ret = true;
+int i = 0;
+
+ERRP_GUARD();
+
+if (n->nr_ebpf_rss_fds != EBPF_RSS_MAX_FDS) {
+error_setg(errp,
+  "Expected %d file descriptors but got %d",
+  EBPF_RSS_MAX_FDS, n->nr_ebpf_rss_fds);
+   return false;
+   }
+
+for (i = 0; i < n->nr_ebpf_rss_fds; i++) {
+fds[i] = monitor_fd_param(monitor_cur(), n->ebpf_rss_fds[i], errp);
+if (*errp) {
+ret = false;
+goto exit;
+}
 }
 
-return ebpf_rss_load(>ebpf_rss);
+ret = ebpf_rss_load_fds(>ebpf_rss, fds[0], fds[1], fds[2], fds[3]);
+
+exit:
+if (!ret || *errp) {
+for (i = 0; i < n->nr_ebpf_rss_fds && fds[i] != -1; i++) {
+close(fds[i]);
+}
+}
+
+return ret;
+}
+
+static bool virtio_net_load_ebpf(VirtIONet *n, Error **errp)
+{
+bool ret = false;
+
+if (virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
+if (!(n->ebpf_rss_fds
+&& virtio_net_load_ebpf_fds(n, errp))) {
+ret = ebpf_rss_load(>ebpf_rss);
+}
+}
+
+return ret;
 }
 
 static void virtio_net_unload_ebpf(VirtIONet *n)
@@ -3762,7 +3802,7 @@ static void virtio_net_device_realize(DeviceState *dev, 
Error **errp)
 net_rx_pkt_init(>rx_pkt);
 
 if (virtio_has_feature(n->host_features, VIRTIO_NET_F_RSS)) {
-virtio_net_load_ebpf(n);
+virtio_net_load_ebpf(n, errp);
 }
 }
 
@@ -3776,6 +3816,15 @@ static void virtio_net_device_unrealize(DeviceState *dev)
 virtio_net_unload_ebpf(n);
 }
 
+if (n->nr_ebpf_rss_fds) {
+for (i = 0; i < n->nr_ebpf_rss_fds; ++i) {
+g_free(n->ebpf_rss_fds[i]);
+}
+g_free(n->ebpf_rss_fds);
+n->ebpf_rss_fds = NULL;
+n->nr_ebpf_rss_fds = 0;
+}
+
 /* This will stop vhost backend if appropriate. */
 virtio_net_set_status(vdev, 0);
 
@@ -3924,6 +3973,8 @@ static Property virtio_net_properties[] = {
 VIRTIO_NET_F_RSS, false),
 DEFINE_PROP_BIT64("hash", VirtIONet, host_features,
 VIRTIO_NET_F_HASH_REPORT, false),
+DEFINE_PROP_ARRAY("ebpf-rss-fds", VirtIONet, nr_ebpf_rss_fds,
+  ebpf_rss_fds, qdev_prop_string, char*),
 DEFINE_PROP_BIT64("guest_rsc_ext", VirtIONet, host_features,
 VIRTIO_NET_F_RSC_EXT, false),
 DEFINE_PROP_UINT32("rsc_interval", VirtIONet, rsc_timeout,
diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h
index 55977f01f0..566ec53e7e 100644
--- a/include/hw/virtio/virtio-net.h
+++ b/include/hw/virtio/virtio-net.h
@@ -225,6 +225,8 @@ struct VirtIONet {
 VirtioNetRssData rss_data;
 struct NetRxPkt *rx_pkt;
 struct EBPFRSSContext ebpf_rss;
+uint32_t nr_ebpf_rss_fds;
+char **ebpf_rss_fds;
 };
 
 size_t virtio_net_handle_ctrl_iov(VirtIODevice *vdev,
-- 
2.43.0

[PATCH v7 5/5] ebpf: Updated eBPF program and skeleton.

2023-08-31 Thread Andrew Melnychenko

Updated section name, so libbpf should init/gues proper
program type without specifications during open/load.
Also, added map_flags with explicitly declared BPF_F_MMAPABLE.
Added check for BPF_F_MMAPABLE flag to meson script and
requirements to libbpf version.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/rss.bpf.skeleton.h | 1460 ---
 meson.build |   10 +-
 tools/ebpf/rss.bpf.c|5 +-
 3 files changed, 748 insertions(+), 727 deletions(-)

diff --git a/ebpf/rss.bpf.skeleton.h b/ebpf/rss.bpf.skeleton.h
index 18eb2adb12..446df248e1 100644
--- a/ebpf/rss.bpf.skeleton.h
+++ b/ebpf/rss.bpf.skeleton.h
@@ -176,162 +176,162 @@ err:
 
 static inline const void *rss_bpf__elf_bytes(size_t *sz)
 {
-   *sz = 20440;
+   *sz = 20824;
return (const void *)"\
 \x7f\x45\x4c\x46\x02\x01\x01\0\0\0\0\0\0\0\0\0\x01\0\xf7\0\x01\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\x98\x4c\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0d\0\
-\x01\0\xbf\x19\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\x54\xff\0\0\0\0\xbf\xa7\
-\0\0\0\0\0\0\x07\x07\0\0\x54\xff\xff\xff\x18\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\x18\x4e\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0d\0\
+\x01\0\xbf\x19\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\x4c\xff\0\0\0\0\xbf\xa7\
+\0\0\0\0\0\0\x07\x07\0\0\x4c\xff\xff\xff\x18\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
 \xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x06\0\0\0\0\0\0\x18\x01\0\0\0\0\0\
 \0\0\0\0\0\0\0\0\0\xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x08\0\0\0\0\0\0\
-\x18\0\0\0\xff\xff\xff\xff\0\0\0\0\0\0\0\0\x15\x06\x67\x02\0\0\0\0\xbf\x87\0\0\
-\0\0\0\0\x15\x07\x65\x02\0\0\0\0\x71\x61\0\0\0\0\0\0\x55\x01\x01\0\0\0\0\0\x05\
-\0\x5e\x02\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xc8\xff\0\0\0\0\x7b\x1a\xc0\xff\
-\0\0\0\0\x7b\x1a\xb8\xff\0\0\0\0\x7b\x1a\xb0\xff\0\0\0\0\x7b\x1a\xa8\xff\0\0\0\
-\0\x63\x1a\xa0\xff\0\0\0\0\x7b\x1a\x98\xff\0\0\0\0\x7b\x1a\x90\xff\0\0\0\0\x7b\
-\x1a\x88\xff\0\0\0\0\x7b\x1a\x80\xff\0\0\0\0\x7b\x1a\x78\xff\0\0\0\0\x7b\x1a\
-\x70\xff\0\0\0\0\x7b\x1a\x68\xff\0\0\0\0\x7b\x1a\x60\xff\0\0\0\0\x7b\x1a\x58\
-\xff\0\0\0\0\x15\x09\x4d\x02\0\0\0\0\x6b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\
-\0\x07\x03\0\0\xd0\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x02\0\0\x0c\0\0\0\xb7\
+\x18\0\0\0\xff\xff\xff\xff\0\0\0\0\0\0\0\0\x15\x06\x64\x02\0\0\0\0\xbf\x87\0\0\
+\0\0\0\0\x15\x07\x62\x02\0\0\0\0\x71\x61\0\0\0\0\0\0\x55\x01\x01\0\0\0\0\0\x05\
+\0\x5b\x02\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xc0\xff\0\0\0\0\x7b\x1a\xb8\xff\
+\0\0\0\0\x7b\x1a\xb0\xff\0\0\0\0\x7b\x1a\xa8\xff\0\0\0\0\x7b\x1a\xa0\xff\0\0\0\
+\0\x63\x1a\x98\xff\0\0\0\0\x7b\x1a\x90\xff\0\0\0\0\x7b\x1a\x88\xff\0\0\0\0\x7b\
+\x1a\x80\xff\0\0\0\0\x7b\x1a\x78\xff\0\0\0\0\x7b\x1a\x70\xff\0\0\0\0\x7b\x1a\
+\x68\xff\0\0\0\0\x7b\x1a\x60\xff\0\0\0\0\x7b\x1a\x58\xff\0\0\0\0\x7b\x1a\x50\
+\xff\0\0\0\0\x15\x09\x4a\x02\0\0\0\0\x6b\x1a\xc8\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\
+\0\x07\x03\0\0\xc8\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x02\0\0\x0c\0\0\0\xb7\
 \x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\
-\x77\0\0\0\x20\0\0\0\x55\0\x42\x02\0\0\0\0\xb7\x02\0\0\x10\0\0\0\x69\xa1\xd0\
+\x77\0\0\0\x20\0\0\0\x55\0\x3f\x02\0\0\0\0\xb7\x02\0\0\x10\0\0\0\x69\xa1\xc8\
 \xff\0\0\0\0\xbf\x13\0\0\0\0\0\0\xdc\x03\0\0\x10\0\0\0\x15\x03\x02\0\0\x81\0\0\
 \x55\x03\x0b\0\xa8\x88\0\0\xb7\x02\0\0\x14\0\0\0\xbf\xa3\0\0\0\0\0\0\x07\x03\0\
-\0\xd0\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\
-\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\x77\0\0\0\x20\0\0\0\x55\0\x32\x02\0\
-\0\0\0\x69\xa1\xd0\xff\0\0\0\0\x15\x01\x30\x02\0\0\0\0\x7b\x7a\x38\xff\0\0\0\0\
-\x7b\x9a\x40\xff\0\0\0\0\x15\x01\x55\0\x86\xdd\0\0\x55\x01\x39\0\x08\0\0\0\xb7\
-\x07\0\0\x01\0\0\0\x73\x7a\x58\xff\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xe0\xff\
-\0\0\0\0\x7b\x1a\xd8\xff\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\0\
-\x07\x03\0\0\xd0\xff\xff\xff\x79\xa1\x40\xff\0\0\0\0\xb7\x02\0\0\0\0\0\0\xb7\
+\0\xc8\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\
+\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\x77\0\0\0\x20\0\0\0\x55\0\x2f\x02\0\
+\0\0\0\x69\xa1\xc8\xff\0\0\0\0\x15\x01\x2d\x02\0\0\0\0\x7b\x7a\x30\xff\0\0\0\0\
+\x7b\x9a\x38\xff\0\0\0\0\x15\x01\x55\0\x86\xdd\0\0\x55\x01\x39\0\x08\0\0\0\xb7\
+\x07\0\0\x01\0\0\0\x73\x7a\x50\xff\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xd8\xff\
+\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\x7b\x1a\xc8\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\0\
+\x07\x03\0\0\xc8\xff\xff\xff\x79\xa1\x38\xff\0\0\0\0\xb7\x02\0\0\0\0\0\0\xb7\
 \x04\0\0\x14\0\0\0\xb7\x05\0\0\x01\0\0\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\
-\0\x77\0\0\0\x20\0\0\0\x55\0\x1c\x02\0\0\0\0\x69\xa1\xd6\xff\0\0\0\0\x55\x01\
-\x01\0\0\0\0\0\xb7\x07\0\0\0\0\0\0\x61\xa1\xdc\xff\0\0\0\0\x63\x1a\x64\xff\0\0\
-\0\0\x61\xa1\xe0\xff\0\0\0\0\x63\x1a\x68\xff\0\0\0\0\x71\xa9\xd9\xff\0\0\0\0\
-\x73\x7a\x5e\xff\0\0\0\0\x71\xa1\xd0\xff\0\0\0\0\x67\x01\0\0\x02\0\0\0\x57\x01\
-\0\0\x3c\0\0\0\x7b\x1a\x48\xff\0\0\0\0\xbf\x91\0\0\0\0\0\0\x57\x01\0\0\xf

[PATCH v7 2/5] ebpf: Added eBPF initialization by fds.

2023-08-31 Thread Andrew Melnychenko

It allows using file descriptors of eBPF provided
outside of QEMU.
QEMU may be run without capabilities for eBPF and run
RSS program provided by management tool(g.e. libvirt).

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf_rss-stub.c |  6 ++
 ebpf/ebpf_rss.c  | 27 +++
 ebpf/ebpf_rss.h  |  5 +
 3 files changed, 38 insertions(+)

diff --git a/ebpf/ebpf_rss-stub.c b/ebpf/ebpf_rss-stub.c
index e71e229190..8d7fae2ad9 100644
--- a/ebpf/ebpf_rss-stub.c
+++ b/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)
 {
diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index 247f5eee1b..24bc6cc409 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -146,6 +146,33 @@ error:
 return false;
 }
 
+bool ebpf_rss_load_fds(struct EBPFRSSContext *ctx, int program_fd,
+   int config_fd, int toeplitz_fd, int table_fd)
+{
+if (ctx == NULL || ebpf_rss_is_loaded(ctx)) {
+return false;
+}
+
+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;
+}
+
+return true;
+}
+
 static bool ebpf_rss_set_config(struct EBPFRSSContext *ctx,
 struct EBPFRSSConfig *config)
 {
diff --git a/ebpf/ebpf_rss.h b/ebpf/ebpf_rss.h
index ab08a7266d..239242b0d2 100644
--- a/ebpf/ebpf_rss.h
+++ b/ebpf/ebpf_rss.h
@@ -14,6 +14,8 @@
 #ifndef QEMU_EBPF_RSS_H
 #define QEMU_EBPF_RSS_H
 
+#define EBPF_RSS_MAX_FDS 4
+
 struct EBPFRSSContext {
 void *obj;
 int program_fd;
@@ -41,6 +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);
 
-- 
2.40.1

[PATCH v7 3/5] virtio-net: Added property to load eBPF RSS with fds.

2023-08-31 Thread Andrew Melnychenko

eBPF RSS program and maps may now be passed during initialization.
Initially was implemented for libvirt to launch qemu without permissions,
and initialized eBPF program through the helper.

Signed-off-by: Andrew Melnychenko 
---
 hw/net/virtio-net.c| 55 ++
 include/hw/virtio/virtio-net.h |  1 +
 2 files changed, 50 insertions(+), 6 deletions(-)

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 7102ec4817..f1894f2095 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -42,6 +42,7 @@
 #include "sysemu/sysemu.h"
 #include "trace.h"
 #include "monitor/qdev.h"
+#include "monitor/monitor.h"
 #include "hw/pci/pci_device.h"
 #include "net_rx_pkt.h"
 #include "hw/virtio/vhost.h"
@@ -1304,14 +1305,55 @@ static void virtio_net_detach_epbf_rss(VirtIONet *n)
 virtio_net_attach_ebpf_to_backend(n->nic, -1);
 }
 
-static bool virtio_net_load_ebpf(VirtIONet *n)
+static bool virtio_net_load_ebpf_fds(VirtIONet *n, Error **errp)
 {
-if (!virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
-/* backend does't support steering ebpf */
-return false;
+int fds[EBPF_RSS_MAX_FDS] = { [0 ... EBPF_RSS_MAX_FDS - 1] = -1};
+int nfds = 0;
+int ret = true;
+int i = 0;
+g_auto(GStrv) fds_strs = g_strsplit(n->ebpf_rss_fds, ":", 0);
+
+ERRP_GUARD();
+
+if (g_strv_length(fds_strs) != EBPF_RSS_MAX_FDS) {
+error_setg(errp,
+  "Expected %d file descriptors but got %d",
+  EBPF_RSS_MAX_FDS, g_strv_length(fds_strs));
+   return false;
+   }
+
+for (i = 0; i < nfds; i++) {
+fds[i] = monitor_fd_param(monitor_cur(), fds_strs[i], errp);
+if (*errp) {
+ret = false;
+goto exit;
+}
+}
+
+ret = ebpf_rss_load_fds(>ebpf_rss, fds[0], fds[1], fds[2], fds[3]);
+
+exit:
+if (!ret || *errp) {
+for (i = 0; i < nfds && fds[i] != -1; i++) {
+close(fds[i]);
+}
 }
 
-return ebpf_rss_load(>ebpf_rss);
+return ret;
+}
+
+static bool virtio_net_load_ebpf(VirtIONet *n, Error **errp)
+{
+bool ret = false;
+
+if (virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
+if (!(n->ebpf_rss_fds
+&& virtio_net_load_ebpf_fds(n, errp))) {
+ret = ebpf_rss_load(>ebpf_rss);
+}
+}
+
+return ret;
 }
 
 static void virtio_net_unload_ebpf(VirtIONet *n)
@@ -3741,7 +3783,7 @@ static void virtio_net_device_realize(DeviceState *dev, 
Error **errp)
 net_rx_pkt_init(>rx_pkt);
 
 if (virtio_has_feature(n->host_features, VIRTIO_NET_F_RSS)) {
-virtio_net_load_ebpf(n);
+virtio_net_load_ebpf(n, errp);
 }
 }
 
@@ -3903,6 +3945,7 @@ static Property virtio_net_properties[] = {
 VIRTIO_NET_F_RSS, false),
 DEFINE_PROP_BIT64("hash", VirtIONet, host_features,
 VIRTIO_NET_F_HASH_REPORT, false),
+DEFINE_PROP_STRING("ebpf_rss_fds", VirtIONet, ebpf_rss_fds),
 DEFINE_PROP_BIT64("guest_rsc_ext", VirtIONet, host_features,
 VIRTIO_NET_F_RSC_EXT, false),
 DEFINE_PROP_UINT32("rsc_interval", VirtIONet, rsc_timeout,
diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h
index 5f5dcb4572..44faf700b4 100644
--- a/include/hw/virtio/virtio-net.h
+++ b/include/hw/virtio/virtio-net.h
@@ -219,6 +219,7 @@ struct VirtIONet {
 VirtioNetRssData rss_data;
 struct NetRxPkt *rx_pkt;
 struct EBPFRSSContext ebpf_rss;
+char *ebpf_rss_fds;
 };
 
 size_t virtio_net_handle_ctrl_iov(VirtIODevice *vdev,
-- 
2.40.1

[PATCH v7 0/5] eBPF RSS through QMP support.

2023-08-31 Thread Andrew Melnychenko

This series of patches provides the ability to retrieve eBPF program
through qmp, so management application may load bpf blob with proper 
capabilities.
Now, virtio-net devices can accept eBPF programs and maps through properties
as external file descriptors. Access to the eBPF map is direct through mmap()
call, so it should not require additional capabilities to bpf* calls.
eBPF file descriptors can be passed to QEMU from parent process or by unix
socket with sendfd() qmp command.

Possible solution for libvirt may look like this: 
https://github.com/daynix/libvirt/tree/RSS_eBPF (WIP)

Changes since v6:
 * added comments to ebpf.json
 * added libbpf version requirements to meson script with BPF_F_MMAPABLE check 

Changes since v5:
 * refactored ebpf.json

Changes since v4:
 * refactored commit hunks
 * added explicit BPF_F_MMAPABLE declaration

Changes since v3:
 * fixed issue with the build if bpf disabled
 * rebased to the last master
 * refactored according to review

Changes since v2:
 * moved/refactored QMP command
 * refactored virtio-net

Changes since v1:
 * refactored virtio-net
 * moved hunks for ebpf mmap()
 * added qmp enum for eBPF id.

Andrew Melnychenko (5):
  ebpf: Added eBPF map update through mmap.
  ebpf: Added eBPF initialization by fds.
  virtio-net: Added property to load eBPF RSS with fds.
  qmp: Added new command to retrieve eBPF blob.
  ebpf: Updated eBPF program and skeleton.

 ebpf/ebpf.c|   70 ++
 ebpf/ebpf.h|   31 +
 ebpf/ebpf_rss-stub.c   |6 +
 ebpf/ebpf_rss.c|  150 +++-
 ebpf/ebpf_rss.h|   10 +
 ebpf/meson.build   |2 +-
 ebpf/rss.bpf.skeleton.h| 1460 
 hw/net/virtio-net.c|   55 +-
 include/hw/virtio/virtio-net.h |1 +
 meson.build|   10 +-
 qapi/ebpf.json |   66 ++
 qapi/meson.build   |1 +
 qapi/qapi-schema.json  |1 +
 tools/ebpf/rss.bpf.c   |5 +-
 14 files changed,  insertions(+), 757 deletions(-)
 create mode 100644 ebpf/ebpf.c
 create mode 100644 ebpf/ebpf.h
 create mode 100644 qapi/ebpf.json

-- 
2.40.1

[PATCH v7 1/5] ebpf: Added eBPF map update through mmap.

2023-08-31 Thread Andrew Melnychenko

Changed eBPF map updates through mmaped array.
Mmaped arrays provide direct access to map data.
It should omit using bpf_map_update_elem() call,
which may require capabilities that are not present.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf_rss.c | 117 ++--
 ebpf/ebpf_rss.h |   5 +++
 2 files changed, 99 insertions(+), 23 deletions(-)

diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index cee658c158..247f5eee1b 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -27,19 +27,83 @@ 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;
 }
 
@@ -66,10 +130,18 @@ 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;
 }
@@ -77,15 +149,11 @@ error:
 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,
-_key, config, 0) < 0) {
-return false;
-}
+
+memcpy(ctx->mmap_configuration, config, sizeof(*config));
 return true;
 }
 
@@ -93,27 +161,19 @@ 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, ,
-

[PATCH v7 4/5] qmp: Added new command to retrieve eBPF blob.

2023-08-31 Thread Andrew Melnychenko

Now, the binary objects may be retrieved by id.
It would require for future qmp commands that may require specific
eBPF blob.

Added command "request-ebpf". This command returns
eBPF program encoded base64. The program taken from the
skeleton and essentially is an ELF object that can be
loaded in the future with libbpf.

The reason to use the command to provide the eBPF object
instead of a separate artifact was to avoid issues related
to finding the eBPF itself. eBPF object is an ELF binary
that contains the eBPF program and eBPF map description(BTF).
Overall, eBPF object should contain the program and enough
metadata to create/load eBPF with libbpf. As the eBPF
maps/program should correspond to QEMU, the eBPF can't
be used from different QEMU build.

The first solution was a helper that comes with QEMU
and loads appropriate eBPF objects. And the issue is
to find a proper helper if the system has several
different QEMUs installed and/or built from the source,
which helpers may not be compatible.

Another issue is QEMU updating while there is a running
QEMU instance. With an updated helper, it may not be
possible to hotplug virtio-net device to the already
running QEMU. Overall, requesting the eBPF object from
QEMU itself solves possible failures with acceptable effort.

Links:
[PATCH 3/5] qmp: Added the helper stamp check.
https://lore.kernel.org/all/20230219162100.174318-4-and...@daynix.com/

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf.c   | 70 +++
 ebpf/ebpf.h   | 31 +++
 ebpf/ebpf_rss.c   |  6 
 ebpf/meson.build  |  2 +-
 qapi/ebpf.json| 66 
 qapi/meson.build  |  1 +
 qapi/qapi-schema.json |  1 +
 7 files changed, 176 insertions(+), 1 deletion(-)
 create mode 100644 ebpf/ebpf.c
 create mode 100644 ebpf/ebpf.h
 create mode 100644 qapi/ebpf.json

diff --git a/ebpf/ebpf.c b/ebpf/ebpf.c
new file mode 100644
index 00..ea97c0403e
--- /dev/null
+++ b/ebpf/ebpf.c
@@ -0,0 +1,70 @@
+/*
+ * QEMU eBPF binary declaration routine.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * 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(_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, _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, , errp);
+if (!data) {
+return NULL;
+}
+
+ret = g_new0(EbpfObject, 1);
+ret->object = g_base64_encode(data, size);
+
+return ret;
+}
diff --git a/ebpf/ebpf.h b/ebpf/ebpf.h
new file mode 100644
index 00..b6266b28b8
--- /dev/null
+++ b/ebpf/ebpf.h
@@ -0,0 +1,31 @@
+/*
+ * QEMU eBPF binary declaration routine.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * 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();   \
+ebpf_registe

[PATCH v6 1/5] ebpf: Added eBPF map update through mmap.

2023-08-08 Thread Andrew Melnychenko

Changed eBPF map updates through mmaped array.
Mmaped arrays provide direct access to map data.
It should omit using bpf_map_update_elem() call,
which may require capabilities that are not present.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf_rss.c | 117 ++--
 ebpf/ebpf_rss.h |   5 +++
 2 files changed, 99 insertions(+), 23 deletions(-)

diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index cee658c158..247f5eee1b 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -27,19 +27,83 @@ 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;
 }
 
@@ -66,10 +130,18 @@ 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;
 }
@@ -77,15 +149,11 @@ error:
 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,
-_key, config, 0) < 0) {
-return false;
-}
+
+memcpy(ctx->mmap_configuration, config, sizeof(*config));
 return true;
 }
 
@@ -93,27 +161,19 @@ 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, ,
-

[PATCH v6 5/5] ebpf: Updated eBPF program and skeleton.

2023-08-08 Thread Andrew Melnychenko

Updated section name, so libbpf should init/gues proper
program type without specifications during open/load.
Also, added map_flags with explicitly declared BPF_F_MMAPABLE.
Which would require kernel 5.5+.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/rss.bpf.skeleton.h | 1460 ---
 tools/ebpf/rss.bpf.c|5 +-
 2 files changed, 741 insertions(+), 724 deletions(-)

diff --git a/ebpf/rss.bpf.skeleton.h b/ebpf/rss.bpf.skeleton.h
index 18eb2adb12..446df248e1 100644
--- a/ebpf/rss.bpf.skeleton.h
+++ b/ebpf/rss.bpf.skeleton.h
@@ -176,162 +176,162 @@ err:
 
 static inline const void *rss_bpf__elf_bytes(size_t *sz)
 {
-   *sz = 20440;
+   *sz = 20824;
return (const void *)"\
 \x7f\x45\x4c\x46\x02\x01\x01\0\0\0\0\0\0\0\0\0\x01\0\xf7\0\x01\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\x98\x4c\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0d\0\
-\x01\0\xbf\x19\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\x54\xff\0\0\0\0\xbf\xa7\
-\0\0\0\0\0\0\x07\x07\0\0\x54\xff\xff\xff\x18\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\x18\x4e\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0d\0\
+\x01\0\xbf\x19\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\x4c\xff\0\0\0\0\xbf\xa7\
+\0\0\0\0\0\0\x07\x07\0\0\x4c\xff\xff\xff\x18\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
 \xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x06\0\0\0\0\0\0\x18\x01\0\0\0\0\0\
 \0\0\0\0\0\0\0\0\0\xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x08\0\0\0\0\0\0\
-\x18\0\0\0\xff\xff\xff\xff\0\0\0\0\0\0\0\0\x15\x06\x67\x02\0\0\0\0\xbf\x87\0\0\
-\0\0\0\0\x15\x07\x65\x02\0\0\0\0\x71\x61\0\0\0\0\0\0\x55\x01\x01\0\0\0\0\0\x05\
-\0\x5e\x02\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xc8\xff\0\0\0\0\x7b\x1a\xc0\xff\
-\0\0\0\0\x7b\x1a\xb8\xff\0\0\0\0\x7b\x1a\xb0\xff\0\0\0\0\x7b\x1a\xa8\xff\0\0\0\
-\0\x63\x1a\xa0\xff\0\0\0\0\x7b\x1a\x98\xff\0\0\0\0\x7b\x1a\x90\xff\0\0\0\0\x7b\
-\x1a\x88\xff\0\0\0\0\x7b\x1a\x80\xff\0\0\0\0\x7b\x1a\x78\xff\0\0\0\0\x7b\x1a\
-\x70\xff\0\0\0\0\x7b\x1a\x68\xff\0\0\0\0\x7b\x1a\x60\xff\0\0\0\0\x7b\x1a\x58\
-\xff\0\0\0\0\x15\x09\x4d\x02\0\0\0\0\x6b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\
-\0\x07\x03\0\0\xd0\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x02\0\0\x0c\0\0\0\xb7\
+\x18\0\0\0\xff\xff\xff\xff\0\0\0\0\0\0\0\0\x15\x06\x64\x02\0\0\0\0\xbf\x87\0\0\
+\0\0\0\0\x15\x07\x62\x02\0\0\0\0\x71\x61\0\0\0\0\0\0\x55\x01\x01\0\0\0\0\0\x05\
+\0\x5b\x02\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xc0\xff\0\0\0\0\x7b\x1a\xb8\xff\
+\0\0\0\0\x7b\x1a\xb0\xff\0\0\0\0\x7b\x1a\xa8\xff\0\0\0\0\x7b\x1a\xa0\xff\0\0\0\
+\0\x63\x1a\x98\xff\0\0\0\0\x7b\x1a\x90\xff\0\0\0\0\x7b\x1a\x88\xff\0\0\0\0\x7b\
+\x1a\x80\xff\0\0\0\0\x7b\x1a\x78\xff\0\0\0\0\x7b\x1a\x70\xff\0\0\0\0\x7b\x1a\
+\x68\xff\0\0\0\0\x7b\x1a\x60\xff\0\0\0\0\x7b\x1a\x58\xff\0\0\0\0\x7b\x1a\x50\
+\xff\0\0\0\0\x15\x09\x4a\x02\0\0\0\0\x6b\x1a\xc8\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\
+\0\x07\x03\0\0\xc8\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x02\0\0\x0c\0\0\0\xb7\
 \x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\
-\x77\0\0\0\x20\0\0\0\x55\0\x42\x02\0\0\0\0\xb7\x02\0\0\x10\0\0\0\x69\xa1\xd0\
+\x77\0\0\0\x20\0\0\0\x55\0\x3f\x02\0\0\0\0\xb7\x02\0\0\x10\0\0\0\x69\xa1\xc8\
 \xff\0\0\0\0\xbf\x13\0\0\0\0\0\0\xdc\x03\0\0\x10\0\0\0\x15\x03\x02\0\0\x81\0\0\
 \x55\x03\x0b\0\xa8\x88\0\0\xb7\x02\0\0\x14\0\0\0\xbf\xa3\0\0\0\0\0\0\x07\x03\0\
-\0\xd0\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\
-\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\x77\0\0\0\x20\0\0\0\x55\0\x32\x02\0\
-\0\0\0\x69\xa1\xd0\xff\0\0\0\0\x15\x01\x30\x02\0\0\0\0\x7b\x7a\x38\xff\0\0\0\0\
-\x7b\x9a\x40\xff\0\0\0\0\x15\x01\x55\0\x86\xdd\0\0\x55\x01\x39\0\x08\0\0\0\xb7\
-\x07\0\0\x01\0\0\0\x73\x7a\x58\xff\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xe0\xff\
-\0\0\0\0\x7b\x1a\xd8\xff\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\0\
-\x07\x03\0\0\xd0\xff\xff\xff\x79\xa1\x40\xff\0\0\0\0\xb7\x02\0\0\0\0\0\0\xb7\
+\0\xc8\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\
+\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\x77\0\0\0\x20\0\0\0\x55\0\x2f\x02\0\
+\0\0\0\x69\xa1\xc8\xff\0\0\0\0\x15\x01\x2d\x02\0\0\0\0\x7b\x7a\x30\xff\0\0\0\0\
+\x7b\x9a\x38\xff\0\0\0\0\x15\x01\x55\0\x86\xdd\0\0\x55\x01\x39\0\x08\0\0\0\xb7\
+\x07\0\0\x01\0\0\0\x73\x7a\x50\xff\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xd8\xff\
+\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\x7b\x1a\xc8\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\0\
+\x07\x03\0\0\xc8\xff\xff\xff\x79\xa1\x38\xff\0\0\0\0\xb7\x02\0\0\0\0\0\0\xb7\
 \x04\0\0\x14\0\0\0\xb7\x05\0\0\x01\0\0\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\
-\0\x77\0\0\0\x20\0\0\0\x55\0\x1c\x02\0\0\0\0\x69\xa1\xd6\xff\0\0\0\0\x55\x01\
-\x01\0\0\0\0\0\xb7\x07\0\0\0\0\0\0\x61\xa1\xdc\xff\0\0\0\0\x63\x1a\x64\xff\0\0\
-\0\0\x61\xa1\xe0\xff\0\0\0\0\x63\x1a\x68\xff\0\0\0\0\x71\xa9\xd9\xff\0\0\0\0\
-\x73\x7a\x5e\xff\0\0\0\0\x71\xa1\xd0\xff\0\0\0\0\x67\x01\0\0\x02\0\0\0\x57\x01\
-\0\0\x3c\0\0\0\x7b\x1a\x48\xff\0\0\0\0\xbf\x91\0\0\0\0\0\0\x57\x01\0\0\xff\0\0\
+\0\x77\0\0\0\x20\0\0\0\x55\0\x19\x02\0\0\0\0\x69\xa1\xce\xff\0\0\0\0\x55\x01\
+\x0

[PATCH v6 4/5] qmp: Added new command to retrieve eBPF blob.

2023-08-08 Thread Andrew Melnychenko

Now, the binary objects may be retrieved by id.
It would require for future qmp commands that may require specific
eBPF blob.

Added command "request-ebpf". This command returns
eBPF program encoded base64. The program taken from the
skeleton and essentially is an ELF object that can be
loaded in the future with libbpf.

The reason to use the command to provide the eBPF object
instead of a separate artifact was to avoid issues related
to finding the eBPF itself. eBPF object is an ELF binary
that contains the eBPF program and eBPF map description(BTF).
Overall, eBPF object should contain the program and enough
metadata to create/load eBPF with libbpf. As the eBPF
maps/program should correspond to QEMU, the eBPF can't
be used from different QEMU build.

The first solution was a helper that comes with QEMU
and loads appropriate eBPF objects. And the issue is
to find a proper helper if the system has several
different QEMUs installed and/or built from the source,
which helpers may not be compatible.

Another issue is QEMU updating while there is a running
QEMU instance. With an updated helper, it may not be
possible to hotplug virtio-net device to the already
running QEMU. Overall, requesting the eBPF object from
QEMU itself solves possible failures with acceptable effort.

Links:
[PATCH 3/5] qmp: Added the helper stamp check.
https://lore.kernel.org/all/20230219162100.174318-4-and...@daynix.com/

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf.c   | 70 +++
 ebpf/ebpf.h   | 31 +++
 ebpf/ebpf_rss.c   |  6 
 ebpf/meson.build  |  2 +-
 qapi/ebpf.json| 56 ++
 qapi/meson.build  |  1 +
 qapi/qapi-schema.json |  1 +
 7 files changed, 166 insertions(+), 1 deletion(-)
 create mode 100644 ebpf/ebpf.c
 create mode 100644 ebpf/ebpf.h
 create mode 100644 qapi/ebpf.json

diff --git a/ebpf/ebpf.c b/ebpf/ebpf.c
new file mode 100644
index 00..ea97c0403e
--- /dev/null
+++ b/ebpf/ebpf.c
@@ -0,0 +1,70 @@
+/*
+ * QEMU eBPF binary declaration routine.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * 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(_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, _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, , errp);
+if (!data) {
+return NULL;
+}
+
+ret = g_new0(EbpfObject, 1);
+ret->object = g_base64_encode(data, size);
+
+return ret;
+}
diff --git a/ebpf/ebpf.h b/ebpf/ebpf.h
new file mode 100644
index 00..b6266b28b8
--- /dev/null
+++ b/ebpf/ebpf.h
@@ -0,0 +1,31 @@
+/*
+ * QEMU eBPF binary declaration routine.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * 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();   \
+ebpf_register_bina

[PATCH v6 2/5] ebpf: Added eBPF initialization by fds.

2023-08-08 Thread Andrew Melnychenko

It allows using file descriptors of eBPF provided
outside of QEMU.
QEMU may be run without capabilities for eBPF and run
RSS program provided by management tool(g.e. libvirt).

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf_rss-stub.c |  6 ++
 ebpf/ebpf_rss.c  | 27 +++
 ebpf/ebpf_rss.h  |  5 +
 3 files changed, 38 insertions(+)

diff --git a/ebpf/ebpf_rss-stub.c b/ebpf/ebpf_rss-stub.c
index e71e229190..8d7fae2ad9 100644
--- a/ebpf/ebpf_rss-stub.c
+++ b/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)
 {
diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index 247f5eee1b..24bc6cc409 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -146,6 +146,33 @@ error:
 return false;
 }
 
+bool ebpf_rss_load_fds(struct EBPFRSSContext *ctx, int program_fd,
+   int config_fd, int toeplitz_fd, int table_fd)
+{
+if (ctx == NULL || ebpf_rss_is_loaded(ctx)) {
+return false;
+}
+
+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;
+}
+
+return true;
+}
+
 static bool ebpf_rss_set_config(struct EBPFRSSContext *ctx,
 struct EBPFRSSConfig *config)
 {
diff --git a/ebpf/ebpf_rss.h b/ebpf/ebpf_rss.h
index ab08a7266d..239242b0d2 100644
--- a/ebpf/ebpf_rss.h
+++ b/ebpf/ebpf_rss.h
@@ -14,6 +14,8 @@
 #ifndef QEMU_EBPF_RSS_H
 #define QEMU_EBPF_RSS_H
 
+#define EBPF_RSS_MAX_FDS 4
+
 struct EBPFRSSContext {
 void *obj;
 int program_fd;
@@ -41,6 +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);
 
-- 
2.40.1

[PATCH v6 0/5] eBPF RSS through QMP support.

2023-08-08 Thread Andrew Melnychenko

This series of patches provides the ability to retrieve eBPF program
through qmp, so management application may load bpf blob with proper 
capabilities.
Now, virtio-net devices can accept eBPF programs and maps through properties
as external file descriptors. Access to the eBPF map is direct through mmap()
call, so it should not require additional capabilities to bpf* calls.
eBPF file descriptors can be passed to QEMU from parent process or by unix
socket with sendfd() qmp command.

Possible solution for libvirt may look like this: 
https://github.com/daynix/libvirt/tree/RSS_eBPF (WIP)

Changes since v5:
 * Refactored ebpf.json

Changes since v4:
 * refactored commit hunks
 * added explicit BPF_F_MMAPABLE declaration

Changes since v3:
 * fixed issue with the build if bpf disabled
 * rebased to the last master
 * refactored according to review

Changes since v2:
 * moved/refactored QMP command
 * refactored virtio-net

Changes since v1:
 * refactored virtio-net
 * moved hunks for ebpf mmap()
 * added qmp enum for eBPF id.

Andrew Melnychenko (5):
  ebpf: Added eBPF map update through mmap.
  ebpf: Added eBPF initialization by fds.
  virtio-net: Added property to load eBPF RSS with fds.
  qmp: Added new command to retrieve eBPF blob.
  ebpf: Updated eBPF program and skeleton.

 ebpf/ebpf.c|   70 ++
 ebpf/ebpf.h|   31 +
 ebpf/ebpf_rss-stub.c   |6 +
 ebpf/ebpf_rss.c|  150 +++-
 ebpf/ebpf_rss.h|   10 +
 ebpf/meson.build   |2 +-
 ebpf/rss.bpf.skeleton.h| 1460 
 hw/net/virtio-net.c|   55 +-
 include/hw/virtio/virtio-net.h |1 +
 qapi/ebpf.json |   56 ++
 qapi/meson.build   |1 +
 qapi/qapi-schema.json  |1 +
 tools/ebpf/rss.bpf.c   |5 +-
 13 files changed, 1094 insertions(+), 754 deletions(-)
 create mode 100644 ebpf/ebpf.c
 create mode 100644 ebpf/ebpf.h
 create mode 100644 qapi/ebpf.json

-- 
2.40.1

[PATCH v6 3/5] virtio-net: Added property to load eBPF RSS with fds.

2023-08-08 Thread Andrew Melnychenko

eBPF RSS program and maps may now be passed during initialization.
Initially was implemented for libvirt to launch qemu without permissions,
and initialized eBPF program through the helper.

Signed-off-by: Andrew Melnychenko 
---
 hw/net/virtio-net.c| 55 ++
 include/hw/virtio/virtio-net.h |  1 +
 2 files changed, 50 insertions(+), 6 deletions(-)

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 7102ec4817..f1894f2095 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -42,6 +42,7 @@
 #include "sysemu/sysemu.h"
 #include "trace.h"
 #include "monitor/qdev.h"
+#include "monitor/monitor.h"
 #include "hw/pci/pci_device.h"
 #include "net_rx_pkt.h"
 #include "hw/virtio/vhost.h"
@@ -1304,14 +1305,55 @@ static void virtio_net_detach_epbf_rss(VirtIONet *n)
 virtio_net_attach_ebpf_to_backend(n->nic, -1);
 }
 
-static bool virtio_net_load_ebpf(VirtIONet *n)
+static bool virtio_net_load_ebpf_fds(VirtIONet *n, Error **errp)
 {
-if (!virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
-/* backend does't support steering ebpf */
-return false;
+int fds[EBPF_RSS_MAX_FDS] = { [0 ... EBPF_RSS_MAX_FDS - 1] = -1};
+int nfds = 0;
+int ret = true;
+int i = 0;
+g_auto(GStrv) fds_strs = g_strsplit(n->ebpf_rss_fds, ":", 0);
+
+ERRP_GUARD();
+
+if (g_strv_length(fds_strs) != EBPF_RSS_MAX_FDS) {
+error_setg(errp,
+  "Expected %d file descriptors but got %d",
+  EBPF_RSS_MAX_FDS, g_strv_length(fds_strs));
+   return false;
+   }
+
+for (i = 0; i < nfds; i++) {
+fds[i] = monitor_fd_param(monitor_cur(), fds_strs[i], errp);
+if (*errp) {
+ret = false;
+goto exit;
+}
+}
+
+ret = ebpf_rss_load_fds(>ebpf_rss, fds[0], fds[1], fds[2], fds[3]);
+
+exit:
+if (!ret || *errp) {
+for (i = 0; i < nfds && fds[i] != -1; i++) {
+close(fds[i]);
+}
 }
 
-return ebpf_rss_load(>ebpf_rss);
+return ret;
+}
+
+static bool virtio_net_load_ebpf(VirtIONet *n, Error **errp)
+{
+bool ret = false;
+
+if (virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
+if (!(n->ebpf_rss_fds
+&& virtio_net_load_ebpf_fds(n, errp))) {
+ret = ebpf_rss_load(>ebpf_rss);
+}
+}
+
+return ret;
 }
 
 static void virtio_net_unload_ebpf(VirtIONet *n)
@@ -3741,7 +3783,7 @@ static void virtio_net_device_realize(DeviceState *dev, 
Error **errp)
 net_rx_pkt_init(>rx_pkt);
 
 if (virtio_has_feature(n->host_features, VIRTIO_NET_F_RSS)) {
-virtio_net_load_ebpf(n);
+virtio_net_load_ebpf(n, errp);
 }
 }
 
@@ -3903,6 +3945,7 @@ static Property virtio_net_properties[] = {
 VIRTIO_NET_F_RSS, false),
 DEFINE_PROP_BIT64("hash", VirtIONet, host_features,
 VIRTIO_NET_F_HASH_REPORT, false),
+DEFINE_PROP_STRING("ebpf_rss_fds", VirtIONet, ebpf_rss_fds),
 DEFINE_PROP_BIT64("guest_rsc_ext", VirtIONet, host_features,
 VIRTIO_NET_F_RSC_EXT, false),
 DEFINE_PROP_UINT32("rsc_interval", VirtIONet, rsc_timeout,
diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h
index 5f5dcb4572..44faf700b4 100644
--- a/include/hw/virtio/virtio-net.h
+++ b/include/hw/virtio/virtio-net.h
@@ -219,6 +219,7 @@ struct VirtIONet {
 VirtioNetRssData rss_data;
 struct NetRxPkt *rx_pkt;
 struct EBPFRSSContext ebpf_rss;
+char *ebpf_rss_fds;
 };
 
 size_t virtio_net_handle_ctrl_iov(VirtIODevice *vdev,
-- 
2.40.1

[PATCH v5 5/5] ebpf: Updated eBPF program and skeleton.

2023-08-02 Thread Andrew Melnychenko

Updated section name, so libbpf should init/gues proper
program type without specifications during open/load.
Also, added map_flags with explicitly declared BPF_F_MMAPABLE.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/rss.bpf.skeleton.h | 1460 ---
 tools/ebpf/rss.bpf.c|5 +-
 2 files changed, 741 insertions(+), 724 deletions(-)

diff --git a/ebpf/rss.bpf.skeleton.h b/ebpf/rss.bpf.skeleton.h
index 18eb2adb12c..446df248e16 100644
--- a/ebpf/rss.bpf.skeleton.h
+++ b/ebpf/rss.bpf.skeleton.h
@@ -176,162 +176,162 @@ err:
 
 static inline const void *rss_bpf__elf_bytes(size_t *sz)
 {
-   *sz = 20440;
+   *sz = 20824;
return (const void *)"\
 \x7f\x45\x4c\x46\x02\x01\x01\0\0\0\0\0\0\0\0\0\x01\0\xf7\0\x01\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\x98\x4c\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0d\0\
-\x01\0\xbf\x19\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\x54\xff\0\0\0\0\xbf\xa7\
-\0\0\0\0\0\0\x07\x07\0\0\x54\xff\xff\xff\x18\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\x18\x4e\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0d\0\
+\x01\0\xbf\x19\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\x4c\xff\0\0\0\0\xbf\xa7\
+\0\0\0\0\0\0\x07\x07\0\0\x4c\xff\xff\xff\x18\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
 \xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x06\0\0\0\0\0\0\x18\x01\0\0\0\0\0\
 \0\0\0\0\0\0\0\0\0\xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x08\0\0\0\0\0\0\
-\x18\0\0\0\xff\xff\xff\xff\0\0\0\0\0\0\0\0\x15\x06\x67\x02\0\0\0\0\xbf\x87\0\0\
-\0\0\0\0\x15\x07\x65\x02\0\0\0\0\x71\x61\0\0\0\0\0\0\x55\x01\x01\0\0\0\0\0\x05\
-\0\x5e\x02\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xc8\xff\0\0\0\0\x7b\x1a\xc0\xff\
-\0\0\0\0\x7b\x1a\xb8\xff\0\0\0\0\x7b\x1a\xb0\xff\0\0\0\0\x7b\x1a\xa8\xff\0\0\0\
-\0\x63\x1a\xa0\xff\0\0\0\0\x7b\x1a\x98\xff\0\0\0\0\x7b\x1a\x90\xff\0\0\0\0\x7b\
-\x1a\x88\xff\0\0\0\0\x7b\x1a\x80\xff\0\0\0\0\x7b\x1a\x78\xff\0\0\0\0\x7b\x1a\
-\x70\xff\0\0\0\0\x7b\x1a\x68\xff\0\0\0\0\x7b\x1a\x60\xff\0\0\0\0\x7b\x1a\x58\
-\xff\0\0\0\0\x15\x09\x4d\x02\0\0\0\0\x6b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\
-\0\x07\x03\0\0\xd0\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x02\0\0\x0c\0\0\0\xb7\
+\x18\0\0\0\xff\xff\xff\xff\0\0\0\0\0\0\0\0\x15\x06\x64\x02\0\0\0\0\xbf\x87\0\0\
+\0\0\0\0\x15\x07\x62\x02\0\0\0\0\x71\x61\0\0\0\0\0\0\x55\x01\x01\0\0\0\0\0\x05\
+\0\x5b\x02\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xc0\xff\0\0\0\0\x7b\x1a\xb8\xff\
+\0\0\0\0\x7b\x1a\xb0\xff\0\0\0\0\x7b\x1a\xa8\xff\0\0\0\0\x7b\x1a\xa0\xff\0\0\0\
+\0\x63\x1a\x98\xff\0\0\0\0\x7b\x1a\x90\xff\0\0\0\0\x7b\x1a\x88\xff\0\0\0\0\x7b\
+\x1a\x80\xff\0\0\0\0\x7b\x1a\x78\xff\0\0\0\0\x7b\x1a\x70\xff\0\0\0\0\x7b\x1a\
+\x68\xff\0\0\0\0\x7b\x1a\x60\xff\0\0\0\0\x7b\x1a\x58\xff\0\0\0\0\x7b\x1a\x50\
+\xff\0\0\0\0\x15\x09\x4a\x02\0\0\0\0\x6b\x1a\xc8\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\
+\0\x07\x03\0\0\xc8\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x02\0\0\x0c\0\0\0\xb7\
 \x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\
-\x77\0\0\0\x20\0\0\0\x55\0\x42\x02\0\0\0\0\xb7\x02\0\0\x10\0\0\0\x69\xa1\xd0\
+\x77\0\0\0\x20\0\0\0\x55\0\x3f\x02\0\0\0\0\xb7\x02\0\0\x10\0\0\0\x69\xa1\xc8\
 \xff\0\0\0\0\xbf\x13\0\0\0\0\0\0\xdc\x03\0\0\x10\0\0\0\x15\x03\x02\0\0\x81\0\0\
 \x55\x03\x0b\0\xa8\x88\0\0\xb7\x02\0\0\x14\0\0\0\xbf\xa3\0\0\0\0\0\0\x07\x03\0\
-\0\xd0\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\
-\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\x77\0\0\0\x20\0\0\0\x55\0\x32\x02\0\
-\0\0\0\x69\xa1\xd0\xff\0\0\0\0\x15\x01\x30\x02\0\0\0\0\x7b\x7a\x38\xff\0\0\0\0\
-\x7b\x9a\x40\xff\0\0\0\0\x15\x01\x55\0\x86\xdd\0\0\x55\x01\x39\0\x08\0\0\0\xb7\
-\x07\0\0\x01\0\0\0\x73\x7a\x58\xff\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xe0\xff\
-\0\0\0\0\x7b\x1a\xd8\xff\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\0\
-\x07\x03\0\0\xd0\xff\xff\xff\x79\xa1\x40\xff\0\0\0\0\xb7\x02\0\0\0\0\0\0\xb7\
+\0\xc8\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\
+\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\x77\0\0\0\x20\0\0\0\x55\0\x2f\x02\0\
+\0\0\0\x69\xa1\xc8\xff\0\0\0\0\x15\x01\x2d\x02\0\0\0\0\x7b\x7a\x30\xff\0\0\0\0\
+\x7b\x9a\x38\xff\0\0\0\0\x15\x01\x55\0\x86\xdd\0\0\x55\x01\x39\0\x08\0\0\0\xb7\
+\x07\0\0\x01\0\0\0\x73\x7a\x50\xff\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xd8\xff\
+\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\x7b\x1a\xc8\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\0\
+\x07\x03\0\0\xc8\xff\xff\xff\x79\xa1\x38\xff\0\0\0\0\xb7\x02\0\0\0\0\0\0\xb7\
 \x04\0\0\x14\0\0\0\xb7\x05\0\0\x01\0\0\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\
-\0\x77\0\0\0\x20\0\0\0\x55\0\x1c\x02\0\0\0\0\x69\xa1\xd6\xff\0\0\0\0\x55\x01\
-\x01\0\0\0\0\0\xb7\x07\0\0\0\0\0\0\x61\xa1\xdc\xff\0\0\0\0\x63\x1a\x64\xff\0\0\
-\0\0\x61\xa1\xe0\xff\0\0\0\0\x63\x1a\x68\xff\0\0\0\0\x71\xa9\xd9\xff\0\0\0\0\
-\x73\x7a\x5e\xff\0\0\0\0\x71\xa1\xd0\xff\0\0\0\0\x67\x01\0\0\x02\0\0\0\x57\x01\
-\0\0\x3c\0\0\0\x7b\x1a\x48\xff\0\0\0\0\xbf\x91\0\0\0\0\0\0\x57\x01\0\0\xff\0\0\
+\0\x77\0\0\0\x20\0\0\0\x55\0\x19\x02\0\0\0\0\x69\xa1\xce\xff\0\0\0\0\x55\x01\
+\x01\0\0\0\0\0\xb7\x07\0\0\0\0\0\

[PATCH v5 3/5] virtio-net: Added property to load eBPF RSS with fds.

2023-08-02 Thread Andrew Melnychenko

eBPF RSS program and maps may now be passed during initialization.
Initially was implemented for libvirt to launch qemu without permissions,
and initialized eBPF program through the helper.

Signed-off-by: Andrew Melnychenko 
---
 hw/net/virtio-net.c| 55 ++
 include/hw/virtio/virtio-net.h |  1 +
 2 files changed, 50 insertions(+), 6 deletions(-)

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 7102ec4817f..f1894f20950 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -42,6 +42,7 @@
 #include "sysemu/sysemu.h"
 #include "trace.h"
 #include "monitor/qdev.h"
+#include "monitor/monitor.h"
 #include "hw/pci/pci_device.h"
 #include "net_rx_pkt.h"
 #include "hw/virtio/vhost.h"
@@ -1304,14 +1305,55 @@ static void virtio_net_detach_epbf_rss(VirtIONet *n)
 virtio_net_attach_ebpf_to_backend(n->nic, -1);
 }
 
-static bool virtio_net_load_ebpf(VirtIONet *n)
+static bool virtio_net_load_ebpf_fds(VirtIONet *n, Error **errp)
 {
-if (!virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
-/* backend does't support steering ebpf */
-return false;
+int fds[EBPF_RSS_MAX_FDS] = { [0 ... EBPF_RSS_MAX_FDS - 1] = -1};
+int nfds = 0;
+int ret = true;
+int i = 0;
+g_auto(GStrv) fds_strs = g_strsplit(n->ebpf_rss_fds, ":", 0);
+
+ERRP_GUARD();
+
+if (g_strv_length(fds_strs) != EBPF_RSS_MAX_FDS) {
+error_setg(errp,
+  "Expected %d file descriptors but got %d",
+  EBPF_RSS_MAX_FDS, g_strv_length(fds_strs));
+   return false;
+   }
+
+for (i = 0; i < nfds; i++) {
+fds[i] = monitor_fd_param(monitor_cur(), fds_strs[i], errp);
+if (*errp) {
+ret = false;
+goto exit;
+}
+}
+
+ret = ebpf_rss_load_fds(>ebpf_rss, fds[0], fds[1], fds[2], fds[3]);
+
+exit:
+if (!ret || *errp) {
+for (i = 0; i < nfds && fds[i] != -1; i++) {
+close(fds[i]);
+}
 }
 
-return ebpf_rss_load(>ebpf_rss);
+return ret;
+}
+
+static bool virtio_net_load_ebpf(VirtIONet *n, Error **errp)
+{
+bool ret = false;
+
+if (virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
+if (!(n->ebpf_rss_fds
+&& virtio_net_load_ebpf_fds(n, errp))) {
+ret = ebpf_rss_load(>ebpf_rss);
+}
+}
+
+return ret;
 }
 
 static void virtio_net_unload_ebpf(VirtIONet *n)
@@ -3741,7 +3783,7 @@ static void virtio_net_device_realize(DeviceState *dev, 
Error **errp)
 net_rx_pkt_init(>rx_pkt);
 
 if (virtio_has_feature(n->host_features, VIRTIO_NET_F_RSS)) {
-virtio_net_load_ebpf(n);
+virtio_net_load_ebpf(n, errp);
 }
 }
 
@@ -3903,6 +3945,7 @@ static Property virtio_net_properties[] = {
 VIRTIO_NET_F_RSS, false),
 DEFINE_PROP_BIT64("hash", VirtIONet, host_features,
 VIRTIO_NET_F_HASH_REPORT, false),
+DEFINE_PROP_STRING("ebpf_rss_fds", VirtIONet, ebpf_rss_fds),
 DEFINE_PROP_BIT64("guest_rsc_ext", VirtIONet, host_features,
 VIRTIO_NET_F_RSC_EXT, false),
 DEFINE_PROP_UINT32("rsc_interval", VirtIONet, rsc_timeout,
diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h
index 5f5dcb4572b..44faf700b4d 100644
--- a/include/hw/virtio/virtio-net.h
+++ b/include/hw/virtio/virtio-net.h
@@ -219,6 +219,7 @@ struct VirtIONet {
 VirtioNetRssData rss_data;
 struct NetRxPkt *rx_pkt;
 struct EBPFRSSContext ebpf_rss;
+char *ebpf_rss_fds;
 };
 
 size_t virtio_net_handle_ctrl_iov(VirtIODevice *vdev,
-- 
2.41.0

[PATCH v5 2/5] ebpf: Added eBPF initialization by fds.

2023-08-02 Thread Andrew Melnychenko

It allows using file descriptors of eBPF provided
outside of QEMU.
QEMU may be run without capabilities for eBPF and run
RSS program provided by management tool(g.e. libvirt).

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf_rss-stub.c |  6 ++
 ebpf/ebpf_rss.c  | 27 +++
 ebpf/ebpf_rss.h  |  5 +
 3 files changed, 38 insertions(+)

diff --git a/ebpf/ebpf_rss-stub.c b/ebpf/ebpf_rss-stub.c
index e71e229190d..8d7fae2ad92 100644
--- a/ebpf/ebpf_rss-stub.c
+++ b/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)
 {
diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index 247f5eee1b6..24bc6cc409e 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -146,6 +146,33 @@ error:
 return false;
 }
 
+bool ebpf_rss_load_fds(struct EBPFRSSContext *ctx, int program_fd,
+   int config_fd, int toeplitz_fd, int table_fd)
+{
+if (ctx == NULL || ebpf_rss_is_loaded(ctx)) {
+return false;
+}
+
+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;
+}
+
+return true;
+}
+
 static bool ebpf_rss_set_config(struct EBPFRSSContext *ctx,
 struct EBPFRSSConfig *config)
 {
diff --git a/ebpf/ebpf_rss.h b/ebpf/ebpf_rss.h
index ab08a7266d0..239242b0d26 100644
--- a/ebpf/ebpf_rss.h
+++ b/ebpf/ebpf_rss.h
@@ -14,6 +14,8 @@
 #ifndef QEMU_EBPF_RSS_H
 #define QEMU_EBPF_RSS_H
 
+#define EBPF_RSS_MAX_FDS 4
+
 struct EBPFRSSContext {
 void *obj;
 int program_fd;
@@ -41,6 +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);
 
-- 
2.41.0

[PATCH v5 4/5] qmp: Added new command to retrieve eBPF blob.

2023-08-02 Thread Andrew Melnychenko

Now, the binary objects may be retrieved by id.
It would require for future qmp commands that may require specific
eBPF blob.

Added command "request-ebpf". This command returns
eBPF program encoded base64. The program taken from the
skeleton and essentially is an ELF object that can be
loaded in the future with libbpf.

The reason to use the command to provide the eBPF object
instead of a separate artifact was to avoid issues related
to finding the eBPF itself. eBPF object is an ELF binary
that contains the eBPF program and eBPF map description(BTF).
Overall, eBPF object should contain the program and enough
metadata to create/load eBPF with libbpf. As the eBPF
maps/program should correspond to QEMU, the eBPF can't
be used from different QEMU build.

The first solution was a helper that comes with QEMU
and loads appropriate eBPF objects. And the issue is
to find a proper helper if the system has several
different QEMUs installed and/or built from the source,
which helpers may not be compatible.

Another issue is QEMU updating while there is a running
QEMU instance. With an updated helper, it may not be
possible to hotplug virtio-net device to the already
running QEMU. Overall, requesting the eBPF object from
QEMU itself solves possible failures with acceptable effort.

Links:
[PATCH 3/5] qmp: Added the helper stamp check.
https://lore.kernel.org/all/20230219162100.174318-4-and...@daynix.com/

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf.c   | 70 +++
 ebpf/ebpf.h   | 31 +++
 ebpf/ebpf_rss.c   |  6 
 ebpf/meson.build  |  2 +-
 qapi/ebpf.json| 57 +++
 qapi/meson.build  |  1 +
 qapi/qapi-schema.json |  1 +
 7 files changed, 167 insertions(+), 1 deletion(-)
 create mode 100644 ebpf/ebpf.c
 create mode 100644 ebpf/ebpf.h
 create mode 100644 qapi/ebpf.json

diff --git a/ebpf/ebpf.c b/ebpf/ebpf.c
new file mode 100644
index 000..ea97c0403ee
--- /dev/null
+++ b/ebpf/ebpf.c
@@ -0,0 +1,70 @@
+/*
+ * QEMU eBPF binary declaration routine.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * 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(_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, _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, , errp);
+if (!data) {
+return NULL;
+}
+
+ret = g_new0(EbpfObject, 1);
+ret->object = g_base64_encode(data, size);
+
+return ret;
+}
diff --git a/ebpf/ebpf.h b/ebpf/ebpf.h
new file mode 100644
index 000..b6266b28b8c
--- /dev/null
+++ b/ebpf/ebpf.h
@@ -0,0 +1,31 @@
+/*
+ * QEMU eBPF binary declaration routine.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * 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();   \
+ebpf_registe

[PATCH v5 1/5] ebpf: Added eBPF map update through mmap.

2023-08-02 Thread Andrew Melnychenko

Changed eBPF map updates through mmaped array.
Mmaped arrays provide direct access to map data.
It should omit using bpf_map_update_elem() call,
which may require capabilities that are not present.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf_rss.c | 117 ++--
 ebpf/ebpf_rss.h |   5 +++
 2 files changed, 99 insertions(+), 23 deletions(-)

diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index cee658c158b..247f5eee1b6 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -27,19 +27,83 @@ 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;
 }
 
@@ -66,10 +130,18 @@ 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;
 }
@@ -77,15 +149,11 @@ error:
 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,
-_key, config, 0) < 0) {
-return false;
-}
+
+memcpy(ctx->mmap_configuration, config, sizeof(*config));
 return true;
 }
 
@@ -93,27 +161,19 @@ 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, ,
-

[PATCH v5 0/5] eBPF RSS through QMP support.

2023-08-02 Thread Andrew Melnychenko

This series of patches provides the ability to retrieve eBPF program
through qmp, so management application may load bpf blob with proper 
capabilities.
Now, virtio-net devices can accept eBPF programs and maps through properties
as external file descriptors. Access to the eBPF map is direct through mmap()
call, so it should not require additional capabilities to bpf* calls.
eBPF file descriptors can be passed to QEMU from parent process or by unix
socket with sendfd() qmp command.

Possible solution for libvirt may look like this: 
https://github.com/daynix/libvirt/tree/RSS_eBPF (WIP)

Changes since v4:
 * refactored commit hunks
 * added explicit BPF_F_MMAPABLE declaration

Changes since v3:
 * fixed issue with the build if bpf disabled
 * rebased to the last master
 * refactored according to review

Changes since v2:
 * moved/refactored QMP command
 * refactored virtio-net

Changes since v1:
 * refactored virtio-net
 * moved hunks for ebpf mmap()
 * added qmp enum for eBPF id.

Andrew Melnychenko (5):
  ebpf: Added eBPF map update through mmap.
  ebpf: Added eBPF initialization by fds.
  virtio-net: Added property to load eBPF RSS with fds.
  qmp: Added new command to retrieve eBPF blob.
  ebpf: Updated eBPF program and skeleton.

 ebpf/ebpf.c|   70 ++
 ebpf/ebpf.h|   31 +
 ebpf/ebpf_rss-stub.c   |6 +
 ebpf/ebpf_rss.c|  150 +++-
 ebpf/ebpf_rss.h|   10 +
 ebpf/meson.build   |2 +-
 ebpf/rss.bpf.skeleton.h| 1460 
 hw/net/virtio-net.c|   55 +-
 include/hw/virtio/virtio-net.h |1 +
 qapi/ebpf.json |   57 ++
 qapi/meson.build   |1 +
 qapi/qapi-schema.json  |1 +
 tools/ebpf/rss.bpf.c   |5 +-
 13 files changed, 1095 insertions(+), 754 deletions(-)
 create mode 100644 ebpf/ebpf.c
 create mode 100644 ebpf/ebpf.h
 create mode 100644 qapi/ebpf.json

-- 
2.41.0

[PATCH v4 5/6] qmp: Added new command to retrieve eBPF blob.

2023-07-13 Thread Andrew Melnychenko

Added command "request-ebpf". This command returns
eBPF program encoded base64. The program taken from the
skeleton and essentially is an ELF object that can be
loaded in the future with libbpf.

The reason to use the command to provide the eBPF object
instead of a separate artifact was to avoid issues related
to finding the eBPF itself. As the eBPF maps/program should
correspond to QEMU, the eBPF cant be used from different
QEMU build.
The first solution was a helper that comes with QEMU
and loads appropriate eBPF objects. And the issue is
to find a proper helper if the system has several
different QEMUs installed and/or built from the source,
which helpers may not be compatible.
Another issue is QEMU updating while there is a running
QEMU instance. With an updated helper, it may not be
possible to hotplug virtio-net device to the already
running QEMU. Overall, requesting the eBPF object from
QEMU itself solves possible failures with very little effort.

Links:
[PATCH 3/5] qmp: Added the helper stamp check.
https://lore.kernel.org/all/20230219162100.174318-4-and...@daynix.com/

Signed-off-by: Andrew Melnychenko 
---
 qapi/ebpf.json| 58 +++
 qapi/meson.build  |  1 +
 qapi/qapi-schema.json |  1 +
 3 files changed, 60 insertions(+)
 create mode 100644 qapi/ebpf.json

diff --git a/qapi/ebpf.json b/qapi/ebpf.json
new file mode 100644
index 00..3237da69a7
--- /dev/null
+++ b/qapi/ebpf.json
@@ -0,0 +1,58 @@
+# -*- Mode: Python -*-
+# vim: filetype=python
+#
+# This work is licensed under the terms of the GNU GPL, version 2 or later.
+# See the COPYING file in the top-level directory.
+
+##
+# = eBPF Objects
+##
+
+{ 'include': 'common.json' }
+
+##
+# @EbpfObject:
+#
+# Structure that holds eBPF ELF object encoded in base64.
+#
+# Since: 8.3
+#
+##
+{ 'struct': 'EbpfObject',
+  'data': {'object': 'str'},
+  'if': 'CONFIG_EBPF' }
+
+##
+# @EbpfProgramID:
+#
+# The eBPF programs that can be gotten with request-ebpf.
+#
+# @rss: Receive side scaling, technology that allows steering traffic
+# between queues by calculation hash. Users may set up indirection table
+# and hash/packet types configurations. Used with virtio-net.
+#
+# Since: 8.3
+##
+{ 'enum': 'EbpfProgramID',
+  'if': 'CONFIG_EBPF',
+  'data': [ { 'name': 'rss' } ] }
+
+##
+# @request-ebpf:
+#
+# Returns eBPF object that can be loaded with libbpf.
+# Management applications (g.e. libvirt) may load it and pass file
+# descriptors to QEMU. Which allows running QEMU without BPF capabilities.
+# It's crucial that eBPF program/map is compatible with QEMU, so it's
+# provided through QMP.
+#
+# Returns: RSS eBPF object encoded in base64.
+#
+# Since: 8.3
+#
+##
+{ 'command': 'request-ebpf',
+  'data': { 'id': 'EbpfProgramID' },
+  'returns': 'EbpfObject',
+  'if': 'CONFIG_EBPF' }
+
diff --git a/qapi/meson.build b/qapi/meson.build
index 60a668b343..90047dae1c 100644
--- a/qapi/meson.build
+++ b/qapi/meson.build
@@ -33,6 +33,7 @@ qapi_all_modules = [
   'crypto',
   'cxl',
   'dump',
+  'ebpf',
   'error',
   'introspect',
   'job',
diff --git a/qapi/qapi-schema.json b/qapi/qapi-schema.json
index 6594afba31..2c82a49bae 100644
--- a/qapi/qapi-schema.json
+++ b/qapi/qapi-schema.json
@@ -53,6 +53,7 @@
 { 'include': 'char.json' }
 { 'include': 'dump.json' }
 { 'include': 'net.json' }
+{ 'include': 'ebpf.json' }
 { 'include': 'rdma.json' }
 { 'include': 'rocker.json' }
 { 'include': 'tpm.json' }
-- 
2.40.1

[PATCH v4 4/6] ebpf: Added declaration/initialization routines.

2023-07-13 Thread Andrew Melnychenko

Now, the binary objects may be retrieved by id.
It would require for future qmp commands that may require specific
eBPF blob.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf.c  | 70 
 ebpf/ebpf.h  | 31 +
 ebpf/ebpf_rss.c  |  6 +
 ebpf/meson.build |  2 +-
 4 files changed, 108 insertions(+), 1 deletion(-)
 create mode 100644 ebpf/ebpf.c
 create mode 100644 ebpf/ebpf.h

diff --git a/ebpf/ebpf.c b/ebpf/ebpf.c
new file mode 100644
index 00..ea97c0403e
--- /dev/null
+++ b/ebpf/ebpf.c
@@ -0,0 +1,70 @@
+/*
+ * QEMU eBPF binary declaration routine.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * 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(_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, _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, , errp);
+if (!data) {
+return NULL;
+}
+
+ret = g_new0(EbpfObject, 1);
+ret->object = g_base64_encode(data, size);
+
+return ret;
+}
diff --git a/ebpf/ebpf.h b/ebpf/ebpf.h
new file mode 100644
index 00..b6266b28b8
--- /dev/null
+++ b/ebpf/ebpf.h
@@ -0,0 +1,31 @@
+/*
+ * QEMU eBPF binary declaration routine.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * 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();   \
+ebpf_register_binary_data(id, data, datalen);  \
+}
+
+#endif /* EBPF_H */
diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index 24bc6cc409..8679dc452d 100644
--- a/ebpf/ebpf_rss.c
+++ b/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 
 #include 
@@ -21,6 +23,8 @@
 
 #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)
@@ -261,3 +265,5 @@ void ebpf_rss_unload(struct EBPFRSSContext *ctx)
 ctx->map_toeplitz_key = -1;
 ctx->map_indirections_table = -1;
 }
+
+ebpf_binary_init(EBPF_PROGRAMID_RSS, rss_bpf__elf_bytes)
diff --git a/ebpf/meson.build b/ebpf/meson.build
index 2f627d6c7d..c9bbaa7c90 100644
--- a/ebpf/meson.build
+++ b/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'))
\ No newline at end of file
-- 
2.40.1

[PATCH v4 2/6] ebpf: Added eBPF initialization by fds.

2023-07-13 Thread Andrew Melnychenko

It allows using file descriptors of eBPF provided
outside of QEMU.
QEMU may be run without capabilities for eBPF and run
RSS program provided by management tool(g.e. libvirt).

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf_rss-stub.c |  6 ++
 ebpf/ebpf_rss.c  | 27 +++
 ebpf/ebpf_rss.h  |  5 +
 3 files changed, 38 insertions(+)

diff --git a/ebpf/ebpf_rss-stub.c b/ebpf/ebpf_rss-stub.c
index e71e229190..8d7fae2ad9 100644
--- a/ebpf/ebpf_rss-stub.c
+++ b/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)
 {
diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index 247f5eee1b..24bc6cc409 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -146,6 +146,33 @@ error:
 return false;
 }
 
+bool ebpf_rss_load_fds(struct EBPFRSSContext *ctx, int program_fd,
+   int config_fd, int toeplitz_fd, int table_fd)
+{
+if (ctx == NULL || ebpf_rss_is_loaded(ctx)) {
+return false;
+}
+
+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;
+}
+
+return true;
+}
+
 static bool ebpf_rss_set_config(struct EBPFRSSContext *ctx,
 struct EBPFRSSConfig *config)
 {
diff --git a/ebpf/ebpf_rss.h b/ebpf/ebpf_rss.h
index ab08a7266d..239242b0d2 100644
--- a/ebpf/ebpf_rss.h
+++ b/ebpf/ebpf_rss.h
@@ -14,6 +14,8 @@
 #ifndef QEMU_EBPF_RSS_H
 #define QEMU_EBPF_RSS_H
 
+#define EBPF_RSS_MAX_FDS 4
+
 struct EBPFRSSContext {
 void *obj;
 int program_fd;
@@ -41,6 +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);
 
-- 
2.40.1

[PATCH v4 1/6] ebpf: Added eBPF map update through mmap.

2023-07-13 Thread Andrew Melnychenko

Changed eBPF map updates through mmaped array.
Mmaped arrays provide direct access to map data.
It should omit using bpf_map_update_elem() call,
which may require capabilities that are not present.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf_rss.c | 117 ++--
 ebpf/ebpf_rss.h |   5 +++
 2 files changed, 99 insertions(+), 23 deletions(-)

diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index cee658c158..247f5eee1b 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -27,19 +27,83 @@ 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;
 }
 
@@ -66,10 +130,18 @@ 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;
 }
@@ -77,15 +149,11 @@ error:
 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,
-_key, config, 0) < 0) {
-return false;
-}
+
+memcpy(ctx->mmap_configuration, config, sizeof(*config));
 return true;
 }
 
@@ -93,27 +161,19 @@ 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, ,
-

[PATCH v4 6/6] ebpf: Updated eBPF program and skeleton.

2023-07-13 Thread Andrew Melnychenko

Updated section name, so libbpf should init/gues proper
program type without specifications during open/load.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/rss.bpf.skeleton.h | 1469 ---
 tools/ebpf/rss.bpf.c|2 +-
 2 files changed, 741 insertions(+), 730 deletions(-)

diff --git a/ebpf/rss.bpf.skeleton.h b/ebpf/rss.bpf.skeleton.h
index 18eb2adb12..41b84aea44 100644
--- a/ebpf/rss.bpf.skeleton.h
+++ b/ebpf/rss.bpf.skeleton.h
@@ -176,162 +176,162 @@ err:
 
 static inline const void *rss_bpf__elf_bytes(size_t *sz)
 {
-   *sz = 20440;
+   *sz = 20720;
return (const void *)"\
 \x7f\x45\x4c\x46\x02\x01\x01\0\0\0\0\0\0\0\0\0\x01\0\xf7\0\x01\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\x98\x4c\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0d\0\
-\x01\0\xbf\x19\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\x54\xff\0\0\0\0\xbf\xa7\
-\0\0\0\0\0\0\x07\x07\0\0\x54\xff\xff\xff\x18\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\xb0\x4d\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0d\0\
+\x01\0\xbf\x19\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\x4c\xff\0\0\0\0\xbf\xa7\
+\0\0\0\0\0\0\x07\x07\0\0\x4c\xff\xff\xff\x18\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
 \xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x06\0\0\0\0\0\0\x18\x01\0\0\0\0\0\
 \0\0\0\0\0\0\0\0\0\xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x08\0\0\0\0\0\0\
-\x18\0\0\0\xff\xff\xff\xff\0\0\0\0\0\0\0\0\x15\x06\x67\x02\0\0\0\0\xbf\x87\0\0\
-\0\0\0\0\x15\x07\x65\x02\0\0\0\0\x71\x61\0\0\0\0\0\0\x55\x01\x01\0\0\0\0\0\x05\
-\0\x5e\x02\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xc8\xff\0\0\0\0\x7b\x1a\xc0\xff\
-\0\0\0\0\x7b\x1a\xb8\xff\0\0\0\0\x7b\x1a\xb0\xff\0\0\0\0\x7b\x1a\xa8\xff\0\0\0\
-\0\x63\x1a\xa0\xff\0\0\0\0\x7b\x1a\x98\xff\0\0\0\0\x7b\x1a\x90\xff\0\0\0\0\x7b\
-\x1a\x88\xff\0\0\0\0\x7b\x1a\x80\xff\0\0\0\0\x7b\x1a\x78\xff\0\0\0\0\x7b\x1a\
-\x70\xff\0\0\0\0\x7b\x1a\x68\xff\0\0\0\0\x7b\x1a\x60\xff\0\0\0\0\x7b\x1a\x58\
-\xff\0\0\0\0\x15\x09\x4d\x02\0\0\0\0\x6b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\
-\0\x07\x03\0\0\xd0\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x02\0\0\x0c\0\0\0\xb7\
+\x18\0\0\0\xff\xff\xff\xff\0\0\0\0\0\0\0\0\x15\x06\x64\x02\0\0\0\0\xbf\x87\0\0\
+\0\0\0\0\x15\x07\x62\x02\0\0\0\0\x71\x61\0\0\0\0\0\0\x55\x01\x01\0\0\0\0\0\x05\
+\0\x5b\x02\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xc0\xff\0\0\0\0\x7b\x1a\xb8\xff\
+\0\0\0\0\x7b\x1a\xb0\xff\0\0\0\0\x7b\x1a\xa8\xff\0\0\0\0\x7b\x1a\xa0\xff\0\0\0\
+\0\x63\x1a\x98\xff\0\0\0\0\x7b\x1a\x90\xff\0\0\0\0\x7b\x1a\x88\xff\0\0\0\0\x7b\
+\x1a\x80\xff\0\0\0\0\x7b\x1a\x78\xff\0\0\0\0\x7b\x1a\x70\xff\0\0\0\0\x7b\x1a\
+\x68\xff\0\0\0\0\x7b\x1a\x60\xff\0\0\0\0\x7b\x1a\x58\xff\0\0\0\0\x7b\x1a\x50\
+\xff\0\0\0\0\x15\x09\x4a\x02\0\0\0\0\x6b\x1a\xc8\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\
+\0\x07\x03\0\0\xc8\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x02\0\0\x0c\0\0\0\xb7\
 \x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\
-\x77\0\0\0\x20\0\0\0\x55\0\x42\x02\0\0\0\0\xb7\x02\0\0\x10\0\0\0\x69\xa1\xd0\
+\x77\0\0\0\x20\0\0\0\x55\0\x3f\x02\0\0\0\0\xb7\x02\0\0\x10\0\0\0\x69\xa1\xc8\
 \xff\0\0\0\0\xbf\x13\0\0\0\0\0\0\xdc\x03\0\0\x10\0\0\0\x15\x03\x02\0\0\x81\0\0\
 \x55\x03\x0b\0\xa8\x88\0\0\xb7\x02\0\0\x14\0\0\0\xbf\xa3\0\0\0\0\0\0\x07\x03\0\
-\0\xd0\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\
-\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\x77\0\0\0\x20\0\0\0\x55\0\x32\x02\0\
-\0\0\0\x69\xa1\xd0\xff\0\0\0\0\x15\x01\x30\x02\0\0\0\0\x7b\x7a\x38\xff\0\0\0\0\
-\x7b\x9a\x40\xff\0\0\0\0\x15\x01\x55\0\x86\xdd\0\0\x55\x01\x39\0\x08\0\0\0\xb7\
-\x07\0\0\x01\0\0\0\x73\x7a\x58\xff\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xe0\xff\
-\0\0\0\0\x7b\x1a\xd8\xff\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\0\
-\x07\x03\0\0\xd0\xff\xff\xff\x79\xa1\x40\xff\0\0\0\0\xb7\x02\0\0\0\0\0\0\xb7\
+\0\xc8\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\
+\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\x77\0\0\0\x20\0\0\0\x55\0\x2f\x02\0\
+\0\0\0\x69\xa1\xc8\xff\0\0\0\0\x15\x01\x2d\x02\0\0\0\0\x7b\x7a\x30\xff\0\0\0\0\
+\x7b\x9a\x38\xff\0\0\0\0\x15\x01\x55\0\x86\xdd\0\0\x55\x01\x39\0\x08\0\0\0\xb7\
+\x07\0\0\x01\0\0\0\x73\x7a\x50\xff\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xd8\xff\
+\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\x7b\x1a\xc8\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\0\
+\x07\x03\0\0\xc8\xff\xff\xff\x79\xa1\x38\xff\0\0\0\0\xb7\x02\0\0\0\0\0\0\xb7\
 \x04\0\0\x14\0\0\0\xb7\x05\0\0\x01\0\0\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\
-\0\x77\0\0\0\x20\0\0\0\x55\0\x1c\x02\0\0\0\0\x69\xa1\xd6\xff\0\0\0\0\x55\x01\
-\x01\0\0\0\0\0\xb7\x07\0\0\0\0\0\0\x61\xa1\xdc\xff\0\0\0\0\x63\x1a\x64\xff\0\0\
-\0\0\x61\xa1\xe0\xff\0\0\0\0\x63\x1a\x68\xff\0\0\0\0\x71\xa9\xd9\xff\0\0\0\0\
-\x73\x7a\x5e\xff\0\0\0\0\x71\xa1\xd0\xff\0\0\0\0\x67\x01\0\0\x02\0\0\0\x57\x01\
-\0\0\x3c\0\0\0\x7b\x1a\x48\xff\0\0\0\0\xbf\x91\0\0\0\0\0\0\x57\x01\0\0\xff\0\0\
+\0\x77\0\0\0\x20\0\0\0\x55\0\x19\x02\0\0\0\0\x69\xa1\xce\xff\0\0\0\0\x55\x01\
+\x01\0\0\0\0\0\xb7\x07\0\0\0\0\0\0\x61\xa1\xd4\xff\0\0\0\0\x63\x1a\x5c\xff\0\0\
+\0\0\x61\xa1\xd8\xf

[PATCH v4 0/6] eBPF RSS through QMP support.

2023-07-13 Thread Andrew Melnychenko

This series of patches provides the ability to retrieve eBPF program
through qmp, so management application may load bpf blob with proper 
capabilities.
Now, virtio-net devices can accept eBPF programs and maps through properties
as external file descriptors. Access to the eBPF map is direct through mmap()
call, so it should not require additional capabilities to bpf* calls.
eBPF file descriptors can be passed to QEMU from parent process or by unix
socket with sendfd() qmp command.

Possible solution for libvirt may look like this: 
https://github.com/daynix/libvirt/tree/RSS_eBPF (WIP)

Changes since v3:
 * fixed issue with the build if bpf disabled
 * rebased to the last master
 * refactored according to review

Changes since v2:
 * moved/refactored QMP command
 * refactored virtio-net

Changes since v1:
 * refactored virtio-net
 * moved hunks for ebpf mmap()
 * added qmp enum for eBPF id.
 
Andrew Melnychenko (6):
  ebpf: Added eBPF map update through mmap.
  ebpf: Added eBPF initialization by fds.
  virtio-net: Added property to load eBPF RSS with fds.
  ebpf: Added declaration/initialization routines.
  qmp: Added new command to retrieve eBPF blob.
  ebpf: Updated eBPF program and skeleton.

 ebpf/ebpf.c|   70 ++
 ebpf/ebpf.h|   31 +
 ebpf/ebpf_rss-stub.c   |6 +
 ebpf/ebpf_rss.c|  150 +++-
 ebpf/ebpf_rss.h|   10 +
 ebpf/meson.build   |2 +-
 ebpf/rss.bpf.skeleton.h| 1469 
 hw/net/virtio-net.c|   55 +-
 include/hw/virtio/virtio-net.h |1 +
 qapi/ebpf.json |   58 ++
 qapi/meson.build   |1 +
 qapi/qapi-schema.json  |1 +
 tools/ebpf/rss.bpf.c   |2 +-
 13 files changed, 1096 insertions(+), 760 deletions(-)
 create mode 100644 ebpf/ebpf.c
 create mode 100644 ebpf/ebpf.h
 create mode 100644 qapi/ebpf.json

-- 
2.40.1

[PATCH v4 3/6] virtio-net: Added property to load eBPF RSS with fds.

2023-07-13 Thread Andrew Melnychenko

eBPF RSS program and maps may now be passed during initialization.
Initially was implemented for libvirt to launch qemu without permissions,
and initialized eBPF program through the helper.

Signed-off-by: Andrew Melnychenko 
---
 hw/net/virtio-net.c| 55 ++
 include/hw/virtio/virtio-net.h |  1 +
 2 files changed, 50 insertions(+), 6 deletions(-)

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 7102ec4817..f1894f2095 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -42,6 +42,7 @@
 #include "sysemu/sysemu.h"
 #include "trace.h"
 #include "monitor/qdev.h"
+#include "monitor/monitor.h"
 #include "hw/pci/pci_device.h"
 #include "net_rx_pkt.h"
 #include "hw/virtio/vhost.h"
@@ -1304,14 +1305,55 @@ static void virtio_net_detach_epbf_rss(VirtIONet *n)
 virtio_net_attach_ebpf_to_backend(n->nic, -1);
 }
 
-static bool virtio_net_load_ebpf(VirtIONet *n)
+static bool virtio_net_load_ebpf_fds(VirtIONet *n, Error **errp)
 {
-if (!virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
-/* backend does't support steering ebpf */
-return false;
+int fds[EBPF_RSS_MAX_FDS] = { [0 ... EBPF_RSS_MAX_FDS - 1] = -1};
+int nfds = 0;
+int ret = true;
+int i = 0;
+g_auto(GStrv) fds_strs = g_strsplit(n->ebpf_rss_fds, ":", 0);
+
+ERRP_GUARD();
+
+if (g_strv_length(fds_strs) != EBPF_RSS_MAX_FDS) {
+error_setg(errp,
+  "Expected %d file descriptors but got %d",
+  EBPF_RSS_MAX_FDS, g_strv_length(fds_strs));
+   return false;
+   }
+
+for (i = 0; i < nfds; i++) {
+fds[i] = monitor_fd_param(monitor_cur(), fds_strs[i], errp);
+if (*errp) {
+ret = false;
+goto exit;
+}
+}
+
+ret = ebpf_rss_load_fds(>ebpf_rss, fds[0], fds[1], fds[2], fds[3]);
+
+exit:
+if (!ret || *errp) {
+for (i = 0; i < nfds && fds[i] != -1; i++) {
+close(fds[i]);
+}
 }
 
-return ebpf_rss_load(>ebpf_rss);
+return ret;
+}
+
+static bool virtio_net_load_ebpf(VirtIONet *n, Error **errp)
+{
+bool ret = false;
+
+if (virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
+if (!(n->ebpf_rss_fds
+&& virtio_net_load_ebpf_fds(n, errp))) {
+ret = ebpf_rss_load(>ebpf_rss);
+}
+}
+
+return ret;
 }
 
 static void virtio_net_unload_ebpf(VirtIONet *n)
@@ -3741,7 +3783,7 @@ static void virtio_net_device_realize(DeviceState *dev, 
Error **errp)
 net_rx_pkt_init(>rx_pkt);
 
 if (virtio_has_feature(n->host_features, VIRTIO_NET_F_RSS)) {
-virtio_net_load_ebpf(n);
+virtio_net_load_ebpf(n, errp);
 }
 }
 
@@ -3903,6 +3945,7 @@ static Property virtio_net_properties[] = {
 VIRTIO_NET_F_RSS, false),
 DEFINE_PROP_BIT64("hash", VirtIONet, host_features,
 VIRTIO_NET_F_HASH_REPORT, false),
+DEFINE_PROP_STRING("ebpf_rss_fds", VirtIONet, ebpf_rss_fds),
 DEFINE_PROP_BIT64("guest_rsc_ext", VirtIONet, host_features,
 VIRTIO_NET_F_RSC_EXT, false),
 DEFINE_PROP_UINT32("rsc_interval", VirtIONet, rsc_timeout,
diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h
index 5f5dcb4572..44faf700b4 100644
--- a/include/hw/virtio/virtio-net.h
+++ b/include/hw/virtio/virtio-net.h
@@ -219,6 +219,7 @@ struct VirtIONet {
 VirtioNetRssData rss_data;
 struct NetRxPkt *rx_pkt;
 struct EBPFRSSContext ebpf_rss;
+char *ebpf_rss_fds;
 };
 
 size_t virtio_net_handle_ctrl_iov(VirtIODevice *vdev,
-- 
2.40.1

[PATCH v3 2/6] ebpf: Added eBPF initialization by fds.

2023-06-14 Thread Andrew Melnychenko

It allows using file descriptors of eBPF provided
outside of QEMU.
QEMU may be run without capabilities for eBPF and run
RSS program provided by management tool(g.e. libvirt).

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf_rss-stub.c |  6 ++
 ebpf/ebpf_rss.c  | 27 +++
 ebpf/ebpf_rss.h  |  5 +
 3 files changed, 38 insertions(+)

diff --git a/ebpf/ebpf_rss-stub.c b/ebpf/ebpf_rss-stub.c
index e71e229190d..8d7fae2ad92 100644
--- a/ebpf/ebpf_rss-stub.c
+++ b/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)
 {
diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index 247f5eee1b6..24bc6cc409e 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -146,6 +146,33 @@ error:
 return false;
 }
 
+bool ebpf_rss_load_fds(struct EBPFRSSContext *ctx, int program_fd,
+   int config_fd, int toeplitz_fd, int table_fd)
+{
+if (ctx == NULL || ebpf_rss_is_loaded(ctx)) {
+return false;
+}
+
+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;
+}
+
+return true;
+}
+
 static bool ebpf_rss_set_config(struct EBPFRSSContext *ctx,
 struct EBPFRSSConfig *config)
 {
diff --git a/ebpf/ebpf_rss.h b/ebpf/ebpf_rss.h
index ab08a7266d0..239242b0d26 100644
--- a/ebpf/ebpf_rss.h
+++ b/ebpf/ebpf_rss.h
@@ -14,6 +14,8 @@
 #ifndef QEMU_EBPF_RSS_H
 #define QEMU_EBPF_RSS_H
 
+#define EBPF_RSS_MAX_FDS 4
+
 struct EBPFRSSContext {
 void *obj;
 int program_fd;
@@ -41,6 +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);
 
-- 
2.39.1

[PATCH v3 1/6] ebpf: Added eBPF map update through mmap.

2023-06-14 Thread Andrew Melnychenko

Changed eBPF map updates through mmaped array.
Mmaped arrays provide direct access to map data.
It should omit using bpf_map_update_elem() call,
which may require capabilities that are not present.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf_rss.c | 117 ++--
 ebpf/ebpf_rss.h |   5 +++
 2 files changed, 99 insertions(+), 23 deletions(-)

diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index cee658c158b..247f5eee1b6 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -27,19 +27,83 @@ 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;
 }
 
@@ -66,10 +130,18 @@ 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;
 }
@@ -77,15 +149,11 @@ error:
 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,
-_key, config, 0) < 0) {
-return false;
-}
+
+memcpy(ctx->mmap_configuration, config, sizeof(*config));
 return true;
 }
 
@@ -93,27 +161,19 @@ 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, ,
-

[PATCH v3 3/6] virtio-net: Added property to load eBPF RSS with fds.

2023-06-14 Thread Andrew Melnychenko

eBPF RSS program and maps may now be passed during initialization.
Initially was implemented for libvirt to launch qemu without permissions,
and initialized eBPF program through the helper.

Signed-off-by: Andrew Melnychenko 
---
 hw/net/virtio-net.c| 55 ++
 include/hw/virtio/virtio-net.h |  1 +
 2 files changed, 50 insertions(+), 6 deletions(-)

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 6df6b7329d2..9a5443aaef1 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -42,6 +42,7 @@
 #include "sysemu/sysemu.h"
 #include "trace.h"
 #include "monitor/qdev.h"
+#include "monitor/monitor.h"
 #include "hw/pci/pci_device.h"
 #include "net_rx_pkt.h"
 #include "hw/virtio/vhost.h"
@@ -1304,14 +1305,55 @@ static void virtio_net_detach_epbf_rss(VirtIONet *n)
 virtio_net_attach_ebpf_to_backend(n->nic, -1);
 }
 
-static bool virtio_net_load_ebpf(VirtIONet *n)
+static bool virtio_net_load_ebpf_fds(VirtIONet *n, Error **errp)
 {
-if (!virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
-/* backend does't support steering ebpf */
-return false;
+int fds[EBPF_RSS_MAX_FDS] = { [0 ... EBPF_RSS_MAX_FDS - 1] = -1};
+int nfds = 0;
+int ret = true;
+int i = 0;
+g_auto(GStrv) fds_strs = g_strsplit(n->ebpf_rss_fds, ":", 0);
+
+ERRP_GUARD();
+
+if (g_strv_length(fds_strs) != EBPF_RSS_MAX_FDS) {
+error_setg(errp,
+  "Expected %d file descriptors but got %d",
+  EBPF_RSS_MAX_FDS, g_strv_length(fds_strs));
+   return false;
+   }
+
+for (i = 0; i < nfds; i++) {
+fds[i] = monitor_fd_param(monitor_cur(), fds_strs[i], errp);
+if (*errp) {
+ret = false;
+goto exit;
+}
+}
+
+ret = ebpf_rss_load_fds(>ebpf_rss, fds[0], fds[1], fds[2], fds[3]);
+
+exit:
+if (!ret || *errp) {
+for (i = 0; i < nfds && fds[i] != -1; i++) {
+close(fds[i]);
+}
 }
 
-return ebpf_rss_load(>ebpf_rss);
+return ret;
+}
+
+static bool virtio_net_load_ebpf(VirtIONet *n, Error **errp)
+{
+bool ret = false;
+
+if (virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
+if (!(n->ebpf_rss_fds
+&& virtio_net_load_ebpf_fds(n, errp))) {
+ret = ebpf_rss_load(>ebpf_rss);
+}
+}
+
+return ret;
 }
 
 static void virtio_net_unload_ebpf(VirtIONet *n)
@@ -3741,7 +3783,7 @@ static void virtio_net_device_realize(DeviceState *dev, 
Error **errp)
 net_rx_pkt_init(>rx_pkt);
 
 if (virtio_has_feature(n->host_features, VIRTIO_NET_F_RSS)) {
-virtio_net_load_ebpf(n);
+virtio_net_load_ebpf(n, errp);
 }
 }
 
@@ -3903,6 +3945,7 @@ static Property virtio_net_properties[] = {
 VIRTIO_NET_F_RSS, false),
 DEFINE_PROP_BIT64("hash", VirtIONet, host_features,
 VIRTIO_NET_F_HASH_REPORT, false),
+DEFINE_PROP_STRING("ebpf_rss_fds", VirtIONet, ebpf_rss_fds),
 DEFINE_PROP_BIT64("guest_rsc_ext", VirtIONet, host_features,
 VIRTIO_NET_F_RSC_EXT, false),
 DEFINE_PROP_UINT32("rsc_interval", VirtIONet, rsc_timeout,
diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h
index ef234ffe7ef..e10ce88f918 100644
--- a/include/hw/virtio/virtio-net.h
+++ b/include/hw/virtio/virtio-net.h
@@ -219,6 +219,7 @@ struct VirtIONet {
 VirtioNetRssData rss_data;
 struct NetRxPkt *rx_pkt;
 struct EBPFRSSContext ebpf_rss;
+char *ebpf_rss_fds;
 };
 
 size_t virtio_net_handle_ctrl_iov(VirtIODevice *vdev,
-- 
2.39.1

[PATCH v3 4/6] ebpf: Added declaration/initialization routines.

2023-06-14 Thread Andrew Melnychenko

Now, the binary objects may be retrieved by id.
It would require for future qmp commands that may require specific
eBPF blob.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf.c  | 70 
 ebpf/ebpf.h  | 31 +
 ebpf/ebpf_rss.c  |  6 +
 ebpf/meson.build |  2 +-
 4 files changed, 108 insertions(+), 1 deletion(-)
 create mode 100644 ebpf/ebpf.c
 create mode 100644 ebpf/ebpf.h

diff --git a/ebpf/ebpf.c b/ebpf/ebpf.c
new file mode 100644
index 000..ea97c0403ee
--- /dev/null
+++ b/ebpf/ebpf.c
@@ -0,0 +1,70 @@
+/*
+ * QEMU eBPF binary declaration routine.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * 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(_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, _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, , errp);
+if (!data) {
+return NULL;
+}
+
+ret = g_new0(EbpfObject, 1);
+ret->object = g_base64_encode(data, size);
+
+return ret;
+}
diff --git a/ebpf/ebpf.h b/ebpf/ebpf.h
new file mode 100644
index 000..b6266b28b8c
--- /dev/null
+++ b/ebpf/ebpf.h
@@ -0,0 +1,31 @@
+/*
+ * QEMU eBPF binary declaration routine.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * 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();   \
+ebpf_register_binary_data(id, data, datalen);  \
+}
+
+#endif /* EBPF_H */
diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index 24bc6cc409e..8679dc452df 100644
--- a/ebpf/ebpf_rss.c
+++ b/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 
 #include 
@@ -21,6 +23,8 @@
 
 #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)
@@ -261,3 +265,5 @@ void ebpf_rss_unload(struct EBPFRSSContext *ctx)
 ctx->map_toeplitz_key = -1;
 ctx->map_indirections_table = -1;
 }
+
+ebpf_binary_init(EBPF_PROGRAMID_RSS, rss_bpf__elf_bytes)
diff --git a/ebpf/meson.build b/ebpf/meson.build
index 2dd0fd89480..272ec2d5311 100644
--- a/ebpf/meson.build
+++ b/ebpf/meson.build
@@ -1 +1 @@
-softmmu_ss.add(when: libbpf, if_true: files('ebpf_rss.c'), if_false: 
files('ebpf_rss-stub.c'))
+softmmu_ss.add(when: libbpf, if_true: files('ebpf.c', 'ebpf_rss.c'), if_false: 
files('ebpf_rss-stub.c'))
-- 
2.39.1

[PATCH v3 6/6] ebpf: Updated eBPF program and skeleton.

2023-06-14 Thread Andrew Melnychenko

Updated section name, so libbpf should init/gues proper
program type without specifications during open/load.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/rss.bpf.skeleton.h | 1469 ---
 tools/ebpf/rss.bpf.c|2 +-
 2 files changed, 741 insertions(+), 730 deletions(-)

diff --git a/ebpf/rss.bpf.skeleton.h b/ebpf/rss.bpf.skeleton.h
index 18eb2adb12c..41b84aea44c 100644
--- a/ebpf/rss.bpf.skeleton.h
+++ b/ebpf/rss.bpf.skeleton.h
@@ -176,162 +176,162 @@ err:
 
 static inline const void *rss_bpf__elf_bytes(size_t *sz)
 {
-   *sz = 20440;
+   *sz = 20720;
return (const void *)"\
 \x7f\x45\x4c\x46\x02\x01\x01\0\0\0\0\0\0\0\0\0\x01\0\xf7\0\x01\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\x98\x4c\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0d\0\
-\x01\0\xbf\x19\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\x54\xff\0\0\0\0\xbf\xa7\
-\0\0\0\0\0\0\x07\x07\0\0\x54\xff\xff\xff\x18\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\xb0\x4d\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0d\0\
+\x01\0\xbf\x19\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\x4c\xff\0\0\0\0\xbf\xa7\
+\0\0\0\0\0\0\x07\x07\0\0\x4c\xff\xff\xff\x18\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
 \xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x06\0\0\0\0\0\0\x18\x01\0\0\0\0\0\
 \0\0\0\0\0\0\0\0\0\xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x08\0\0\0\0\0\0\
-\x18\0\0\0\xff\xff\xff\xff\0\0\0\0\0\0\0\0\x15\x06\x67\x02\0\0\0\0\xbf\x87\0\0\
-\0\0\0\0\x15\x07\x65\x02\0\0\0\0\x71\x61\0\0\0\0\0\0\x55\x01\x01\0\0\0\0\0\x05\
-\0\x5e\x02\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xc8\xff\0\0\0\0\x7b\x1a\xc0\xff\
-\0\0\0\0\x7b\x1a\xb8\xff\0\0\0\0\x7b\x1a\xb0\xff\0\0\0\0\x7b\x1a\xa8\xff\0\0\0\
-\0\x63\x1a\xa0\xff\0\0\0\0\x7b\x1a\x98\xff\0\0\0\0\x7b\x1a\x90\xff\0\0\0\0\x7b\
-\x1a\x88\xff\0\0\0\0\x7b\x1a\x80\xff\0\0\0\0\x7b\x1a\x78\xff\0\0\0\0\x7b\x1a\
-\x70\xff\0\0\0\0\x7b\x1a\x68\xff\0\0\0\0\x7b\x1a\x60\xff\0\0\0\0\x7b\x1a\x58\
-\xff\0\0\0\0\x15\x09\x4d\x02\0\0\0\0\x6b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\
-\0\x07\x03\0\0\xd0\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x02\0\0\x0c\0\0\0\xb7\
+\x18\0\0\0\xff\xff\xff\xff\0\0\0\0\0\0\0\0\x15\x06\x64\x02\0\0\0\0\xbf\x87\0\0\
+\0\0\0\0\x15\x07\x62\x02\0\0\0\0\x71\x61\0\0\0\0\0\0\x55\x01\x01\0\0\0\0\0\x05\
+\0\x5b\x02\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xc0\xff\0\0\0\0\x7b\x1a\xb8\xff\
+\0\0\0\0\x7b\x1a\xb0\xff\0\0\0\0\x7b\x1a\xa8\xff\0\0\0\0\x7b\x1a\xa0\xff\0\0\0\
+\0\x63\x1a\x98\xff\0\0\0\0\x7b\x1a\x90\xff\0\0\0\0\x7b\x1a\x88\xff\0\0\0\0\x7b\
+\x1a\x80\xff\0\0\0\0\x7b\x1a\x78\xff\0\0\0\0\x7b\x1a\x70\xff\0\0\0\0\x7b\x1a\
+\x68\xff\0\0\0\0\x7b\x1a\x60\xff\0\0\0\0\x7b\x1a\x58\xff\0\0\0\0\x7b\x1a\x50\
+\xff\0\0\0\0\x15\x09\x4a\x02\0\0\0\0\x6b\x1a\xc8\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\
+\0\x07\x03\0\0\xc8\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x02\0\0\x0c\0\0\0\xb7\
 \x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\
-\x77\0\0\0\x20\0\0\0\x55\0\x42\x02\0\0\0\0\xb7\x02\0\0\x10\0\0\0\x69\xa1\xd0\
+\x77\0\0\0\x20\0\0\0\x55\0\x3f\x02\0\0\0\0\xb7\x02\0\0\x10\0\0\0\x69\xa1\xc8\
 \xff\0\0\0\0\xbf\x13\0\0\0\0\0\0\xdc\x03\0\0\x10\0\0\0\x15\x03\x02\0\0\x81\0\0\
 \x55\x03\x0b\0\xa8\x88\0\0\xb7\x02\0\0\x14\0\0\0\xbf\xa3\0\0\0\0\0\0\x07\x03\0\
-\0\xd0\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\
-\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\x77\0\0\0\x20\0\0\0\x55\0\x32\x02\0\
-\0\0\0\x69\xa1\xd0\xff\0\0\0\0\x15\x01\x30\x02\0\0\0\0\x7b\x7a\x38\xff\0\0\0\0\
-\x7b\x9a\x40\xff\0\0\0\0\x15\x01\x55\0\x86\xdd\0\0\x55\x01\x39\0\x08\0\0\0\xb7\
-\x07\0\0\x01\0\0\0\x73\x7a\x58\xff\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xe0\xff\
-\0\0\0\0\x7b\x1a\xd8\xff\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\0\
-\x07\x03\0\0\xd0\xff\xff\xff\x79\xa1\x40\xff\0\0\0\0\xb7\x02\0\0\0\0\0\0\xb7\
+\0\xc8\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\
+\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\x77\0\0\0\x20\0\0\0\x55\0\x2f\x02\0\
+\0\0\0\x69\xa1\xc8\xff\0\0\0\0\x15\x01\x2d\x02\0\0\0\0\x7b\x7a\x30\xff\0\0\0\0\
+\x7b\x9a\x38\xff\0\0\0\0\x15\x01\x55\0\x86\xdd\0\0\x55\x01\x39\0\x08\0\0\0\xb7\
+\x07\0\0\x01\0\0\0\x73\x7a\x50\xff\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xd8\xff\
+\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\x7b\x1a\xc8\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\0\
+\x07\x03\0\0\xc8\xff\xff\xff\x79\xa1\x38\xff\0\0\0\0\xb7\x02\0\0\0\0\0\0\xb7\
 \x04\0\0\x14\0\0\0\xb7\x05\0\0\x01\0\0\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\
-\0\x77\0\0\0\x20\0\0\0\x55\0\x1c\x02\0\0\0\0\x69\xa1\xd6\xff\0\0\0\0\x55\x01\
-\x01\0\0\0\0\0\xb7\x07\0\0\0\0\0\0\x61\xa1\xdc\xff\0\0\0\0\x63\x1a\x64\xff\0\0\
-\0\0\x61\xa1\xe0\xff\0\0\0\0\x63\x1a\x68\xff\0\0\0\0\x71\xa9\xd9\xff\0\0\0\0\
-\x73\x7a\x5e\xff\0\0\0\0\x71\xa1\xd0\xff\0\0\0\0\x67\x01\0\0\x02\0\0\0\x57\x01\
-\0\0\x3c\0\0\0\x7b\x1a\x48\xff\0\0\0\0\xbf\x91\0\0\0\0\0\0\x57\x01\0\0\xff\0\0\
+\0\x77\0\0\0\x20\0\0\0\x55\0\x19\x02\0\0\0\0\x69\xa1\xce\xff\0\0\0\0\x55\x01\
+\x01\0\0\0\0\0\xb7\x07\0\0\0\0\0\0\x61\xa1\xd4\xff\0\0\0\0\x63\x1a\x5c\xff\0\0\
+\0\0\x61\xa1\xd8\

[PATCH v3 5/6] qmp: Added new command to retrieve eBPF blob.

2023-06-14 Thread Andrew Melnychenko

Added command "request-ebpf". This command returns
eBPF program encoded base64. The program taken from the
skeleton and essentially is an ELF object that can be
loaded in the future with libbpf.

Signed-off-by: Andrew Melnychenko 
---
 qapi/ebpf.json| 55 +++
 qapi/meson.build  |  1 +
 qapi/qapi-schema.json |  1 +
 3 files changed, 57 insertions(+)
 create mode 100644 qapi/ebpf.json

diff --git a/qapi/ebpf.json b/qapi/ebpf.json
new file mode 100644
index 000..6f9a1f1a0c9
--- /dev/null
+++ b/qapi/ebpf.json
@@ -0,0 +1,55 @@
+# -*- Mode: Python -*-
+# vim: filetype=python
+#
+# This work is licensed under the terms of the GNU GPL, version 2 or later.
+# See the COPYING file in the top-level directory.
+
+##
+# = Machines
+##
+
+{ 'include': 'common.json' }
+
+##
+# @EbpfObject:
+#
+# Structure that holds eBPF ELF object encoded in base64.
+#
+# Since: 8.1
+#
+##
+{ 'struct': 'EbpfObject',
+  'data': {'object': 'str'} }
+
+##
+# @EbpfProgramID:
+#
+# An enumeration of the eBPF programs. Currently, only RSS is presented.
+# RSS - Receive side scaling, technology that allows steering traffic
+# between queues by calculation hash. Users may set up indirection table
+# and hash/packet types configurations. Used with virtio-net.
+#
+# Since: 8.1
+##
+{ 'enum': 'EbpfProgramID',
+  'data': [ { 'name': 'rss', 'if': 'CONFIG_EBPF' } ] }
+
+##
+# @request-ebpf:
+#
+# Returns eBPF object that can be loaded with libbpf.
+# Management applications (g.e. libvirt) may load it and pass file
+# descriptors to QEMU. Which allows running QEMU without BPF capabilities.
+# It's crucial that eBPF program/map is compatible with QEMU, so it's
+# provided through QMP.
+#
+# Returns: RSS eBPF object encoded in base64.
+#
+# Since: 8.1
+#
+##
+{ 'command': 'request-ebpf',
+  'data': { 'id': 'EbpfProgramID' },
+  'returns': 'EbpfObject',
+  'if': 'CONFIG_EBPF' }
+
diff --git a/qapi/meson.build b/qapi/meson.build
index 9fd480c4d81..12a1cb1f9c2 100644
--- a/qapi/meson.build
+++ b/qapi/meson.build
@@ -52,6 +52,7 @@ qapi_all_modules = [
   'transaction',
   'virtio',
   'yank',
+  'ebpf',
 ]
 if have_system
   qapi_all_modules += [
diff --git a/qapi/qapi-schema.json b/qapi/qapi-schema.json
index 6594afba312..169cfe8d386 100644
--- a/qapi/qapi-schema.json
+++ b/qapi/qapi-schema.json
@@ -79,3 +79,4 @@
 { 'include': 'virtio.json' }
 { 'include': 'cryptodev.json' }
 { 'include': 'cxl.json' }
+{ 'include': 'ebpf.json' }
-- 
2.39.1

[PATCH v3 0/6] eBPF RSS through QMP support.

2023-06-14 Thread Andrew Melnychenko

This series of patches provides the ability to retrieve eBPF program
through qmp, so management application may load bpf blob with proper 
capabilities.
Now, virtio-net devices can accept eBPF programs and maps through properties
as external file descriptors. Access to the eBPF map is direct through mmap()
call, so it should not require additional capabilities to bpf* calls.
eBPF file descriptors can be passed to QEMU from parent process or by unix
socket with sendfd() qmp command.

Possible solution for libvirt may look like this: 
https://github.com/daynix/libvirt/tree/RSS_eBPF (WIP)

Changes since v2:
 * moved/refactored QMP command
 * refactored virtio-net

Changes since v1:
 * refactored virtio-net
 * moved hunks for ebpf mmap()
 * added qmp enum for eBPF id.

Andrew Melnychenko (6):
  ebpf: Added eBPF map update through mmap.
  ebpf: Added eBPF initialization by fds.
  virtio-net: Added property to load eBPF RSS with fds.
  ebpf: Added declaration/initialization routines.
  qmp: Added new command to retrieve eBPF blob.
  ebpf: Updated eBPF program and skeleton.

 ebpf/ebpf.c|   70 ++
 ebpf/ebpf.h|   31 +
 ebpf/ebpf_rss-stub.c   |6 +
 ebpf/ebpf_rss.c|  150 +++-
 ebpf/ebpf_rss.h|   10 +
 ebpf/meson.build   |2 +-
 ebpf/rss.bpf.skeleton.h| 1469 
 hw/net/virtio-net.c|   55 +-
 include/hw/virtio/virtio-net.h |1 +
 qapi/ebpf.json |   55 ++
 qapi/meson.build   |1 +
 qapi/qapi-schema.json  |1 +
 tools/ebpf/rss.bpf.c   |2 +-
 13 files changed, 1093 insertions(+), 760 deletions(-)
 create mode 100644 ebpf/ebpf.c
 create mode 100644 ebpf/ebpf.h
 create mode 100644 qapi/ebpf.json

-- 
2.39.1

[PATCH v2 1/6] ebpf: Added eBPF map update through mmap.

2023-05-12 Thread Andrew Melnychenko

Changed eBPF map updates through mmaped array.
Mmaped arrays provide direct access to map data.
It should omit using bpf_map_update_elem() call,
which may require capabilities that are not present.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf_rss.c | 117 ++--
 ebpf/ebpf_rss.h |   5 +++
 2 files changed, 99 insertions(+), 23 deletions(-)

diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index cee658c158b..247f5eee1b6 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -27,19 +27,83 @@ 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;
 }
 
@@ -66,10 +130,18 @@ 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;
 }
@@ -77,15 +149,11 @@ error:
 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,
-_key, config, 0) < 0) {
-return false;
-}
+
+memcpy(ctx->mmap_configuration, config, sizeof(*config));
 return true;
 }
 
@@ -93,27 +161,19 @@ 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, ,
-

[PATCH v2 6/6] ebpf: Updated eBPF program and skeleton.

2023-05-12 Thread Andrew Melnychenko

Updated section name, so libbpf should init/gues proper
program type without specifications during open/load.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/rss.bpf.skeleton.h | 1469 ---
 tools/ebpf/rss.bpf.c|2 +-
 2 files changed, 741 insertions(+), 730 deletions(-)

diff --git a/ebpf/rss.bpf.skeleton.h b/ebpf/rss.bpf.skeleton.h
index 18eb2adb12c..41b84aea44c 100644
--- a/ebpf/rss.bpf.skeleton.h
+++ b/ebpf/rss.bpf.skeleton.h
@@ -176,162 +176,162 @@ err:
 
 static inline const void *rss_bpf__elf_bytes(size_t *sz)
 {
-   *sz = 20440;
+   *sz = 20720;
return (const void *)"\
 \x7f\x45\x4c\x46\x02\x01\x01\0\0\0\0\0\0\0\0\0\x01\0\xf7\0\x01\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\x98\x4c\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0d\0\
-\x01\0\xbf\x19\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\x54\xff\0\0\0\0\xbf\xa7\
-\0\0\0\0\0\0\x07\x07\0\0\x54\xff\xff\xff\x18\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\xb0\x4d\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0d\0\
+\x01\0\xbf\x19\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\x4c\xff\0\0\0\0\xbf\xa7\
+\0\0\0\0\0\0\x07\x07\0\0\x4c\xff\xff\xff\x18\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
 \xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x06\0\0\0\0\0\0\x18\x01\0\0\0\0\0\
 \0\0\0\0\0\0\0\0\0\xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x08\0\0\0\0\0\0\
-\x18\0\0\0\xff\xff\xff\xff\0\0\0\0\0\0\0\0\x15\x06\x67\x02\0\0\0\0\xbf\x87\0\0\
-\0\0\0\0\x15\x07\x65\x02\0\0\0\0\x71\x61\0\0\0\0\0\0\x55\x01\x01\0\0\0\0\0\x05\
-\0\x5e\x02\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xc8\xff\0\0\0\0\x7b\x1a\xc0\xff\
-\0\0\0\0\x7b\x1a\xb8\xff\0\0\0\0\x7b\x1a\xb0\xff\0\0\0\0\x7b\x1a\xa8\xff\0\0\0\
-\0\x63\x1a\xa0\xff\0\0\0\0\x7b\x1a\x98\xff\0\0\0\0\x7b\x1a\x90\xff\0\0\0\0\x7b\
-\x1a\x88\xff\0\0\0\0\x7b\x1a\x80\xff\0\0\0\0\x7b\x1a\x78\xff\0\0\0\0\x7b\x1a\
-\x70\xff\0\0\0\0\x7b\x1a\x68\xff\0\0\0\0\x7b\x1a\x60\xff\0\0\0\0\x7b\x1a\x58\
-\xff\0\0\0\0\x15\x09\x4d\x02\0\0\0\0\x6b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\
-\0\x07\x03\0\0\xd0\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x02\0\0\x0c\0\0\0\xb7\
+\x18\0\0\0\xff\xff\xff\xff\0\0\0\0\0\0\0\0\x15\x06\x64\x02\0\0\0\0\xbf\x87\0\0\
+\0\0\0\0\x15\x07\x62\x02\0\0\0\0\x71\x61\0\0\0\0\0\0\x55\x01\x01\0\0\0\0\0\x05\
+\0\x5b\x02\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xc0\xff\0\0\0\0\x7b\x1a\xb8\xff\
+\0\0\0\0\x7b\x1a\xb0\xff\0\0\0\0\x7b\x1a\xa8\xff\0\0\0\0\x7b\x1a\xa0\xff\0\0\0\
+\0\x63\x1a\x98\xff\0\0\0\0\x7b\x1a\x90\xff\0\0\0\0\x7b\x1a\x88\xff\0\0\0\0\x7b\
+\x1a\x80\xff\0\0\0\0\x7b\x1a\x78\xff\0\0\0\0\x7b\x1a\x70\xff\0\0\0\0\x7b\x1a\
+\x68\xff\0\0\0\0\x7b\x1a\x60\xff\0\0\0\0\x7b\x1a\x58\xff\0\0\0\0\x7b\x1a\x50\
+\xff\0\0\0\0\x15\x09\x4a\x02\0\0\0\0\x6b\x1a\xc8\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\
+\0\x07\x03\0\0\xc8\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x02\0\0\x0c\0\0\0\xb7\
 \x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\
-\x77\0\0\0\x20\0\0\0\x55\0\x42\x02\0\0\0\0\xb7\x02\0\0\x10\0\0\0\x69\xa1\xd0\
+\x77\0\0\0\x20\0\0\0\x55\0\x3f\x02\0\0\0\0\xb7\x02\0\0\x10\0\0\0\x69\xa1\xc8\
 \xff\0\0\0\0\xbf\x13\0\0\0\0\0\0\xdc\x03\0\0\x10\0\0\0\x15\x03\x02\0\0\x81\0\0\
 \x55\x03\x0b\0\xa8\x88\0\0\xb7\x02\0\0\x14\0\0\0\xbf\xa3\0\0\0\0\0\0\x07\x03\0\
-\0\xd0\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\
-\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\x77\0\0\0\x20\0\0\0\x55\0\x32\x02\0\
-\0\0\0\x69\xa1\xd0\xff\0\0\0\0\x15\x01\x30\x02\0\0\0\0\x7b\x7a\x38\xff\0\0\0\0\
-\x7b\x9a\x40\xff\0\0\0\0\x15\x01\x55\0\x86\xdd\0\0\x55\x01\x39\0\x08\0\0\0\xb7\
-\x07\0\0\x01\0\0\0\x73\x7a\x58\xff\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xe0\xff\
-\0\0\0\0\x7b\x1a\xd8\xff\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\0\
-\x07\x03\0\0\xd0\xff\xff\xff\x79\xa1\x40\xff\0\0\0\0\xb7\x02\0\0\0\0\0\0\xb7\
+\0\xc8\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\
+\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\x77\0\0\0\x20\0\0\0\x55\0\x2f\x02\0\
+\0\0\0\x69\xa1\xc8\xff\0\0\0\0\x15\x01\x2d\x02\0\0\0\0\x7b\x7a\x30\xff\0\0\0\0\
+\x7b\x9a\x38\xff\0\0\0\0\x15\x01\x55\0\x86\xdd\0\0\x55\x01\x39\0\x08\0\0\0\xb7\
+\x07\0\0\x01\0\0\0\x73\x7a\x50\xff\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xd8\xff\
+\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\x7b\x1a\xc8\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\0\
+\x07\x03\0\0\xc8\xff\xff\xff\x79\xa1\x38\xff\0\0\0\0\xb7\x02\0\0\0\0\0\0\xb7\
 \x04\0\0\x14\0\0\0\xb7\x05\0\0\x01\0\0\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\
-\0\x77\0\0\0\x20\0\0\0\x55\0\x1c\x02\0\0\0\0\x69\xa1\xd6\xff\0\0\0\0\x55\x01\
-\x01\0\0\0\0\0\xb7\x07\0\0\0\0\0\0\x61\xa1\xdc\xff\0\0\0\0\x63\x1a\x64\xff\0\0\
-\0\0\x61\xa1\xe0\xff\0\0\0\0\x63\x1a\x68\xff\0\0\0\0\x71\xa9\xd9\xff\0\0\0\0\
-\x73\x7a\x5e\xff\0\0\0\0\x71\xa1\xd0\xff\0\0\0\0\x67\x01\0\0\x02\0\0\0\x57\x01\
-\0\0\x3c\0\0\0\x7b\x1a\x48\xff\0\0\0\0\xbf\x91\0\0\0\0\0\0\x57\x01\0\0\xff\0\0\
+\0\x77\0\0\0\x20\0\0\0\x55\0\x19\x02\0\0\0\0\x69\xa1\xce\xff\0\0\0\0\x55\x01\
+\x01\0\0\0\0\0\xb7\x07\0\0\0\0\0\0\x61\xa1\xd4\xff\0\0\0\0\x63\x1a\x5c\xff\0\0\
+\0\0\x61\xa1\xd8\

[PATCH v2 4/6] ebpf: Added declaration/initialization routines.

2023-05-12 Thread Andrew Melnychenko

Now, the binary objects may be retrieved by id.
It would require for future qmp commands that may require specific
eBPF blob.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf.c  | 54 
 ebpf/ebpf.h  | 31 +++
 ebpf/ebpf_rss.c  |  5 +
 ebpf/meson.build |  1 +
 4 files changed, 91 insertions(+)
 create mode 100644 ebpf/ebpf.c
 create mode 100644 ebpf/ebpf.h

diff --git a/ebpf/ebpf.c b/ebpf/ebpf.c
new file mode 100644
index 000..8870a9b3f50
--- /dev/null
+++ b/ebpf/ebpf.c
@@ -0,0 +1,54 @@
+/*
+ * QEMU eBPF binary declaration routine.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * 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 "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(_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, _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;
+}
diff --git a/ebpf/ebpf.h b/ebpf/ebpf.h
new file mode 100644
index 000..b6266b28b8c
--- /dev/null
+++ b/ebpf/ebpf.h
@@ -0,0 +1,31 @@
+/*
+ * QEMU eBPF binary declaration routine.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * 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();   \
+ebpf_register_binary_data(id, data, datalen);  \
+}
+
+#endif /* EBPF_H */
diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index 24bc6cc409e..213a8ac79ad 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -13,6 +13,7 @@
 
 #include "qemu/osdep.h"
 #include "qemu/error-report.h"
+#include "qapi/qapi-types-misc.h"
 
 #include 
 #include 
@@ -21,6 +22,8 @@
 
 #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)
@@ -261,3 +264,5 @@ void ebpf_rss_unload(struct EBPFRSSContext *ctx)
 ctx->map_toeplitz_key = -1;
 ctx->map_indirections_table = -1;
 }
+
+ebpf_binary_init(EBPF_PROGRAMID_RSS, rss_bpf__elf_bytes)
diff --git a/ebpf/meson.build b/ebpf/meson.build
index 2dd0fd89480..67c3f53aa9d 100644
--- a/ebpf/meson.build
+++ b/ebpf/meson.build
@@ -1 +1,2 @@
+softmmu_ss.add(files('ebpf.c'))
 softmmu_ss.add(when: libbpf, if_true: files('ebpf_rss.c'), if_false: 
files('ebpf_rss-stub.c'))
-- 
2.39.1

[PATCH v2 0/6] eBPF RSS through QMP support.

2023-05-12 Thread Andrew Melnychenko

This series of patches provides the ability to retrieve eBPF program
through qmp, so management application may load bpf blob with proper 
capabilities.
Now, virtio-net devices can accept eBPF programs and maps through properties
as external file descriptors. Access to the eBPF map is direct through mmap()
call, so it should not require additional capabilities to bpf* calls.
eBPF file descriptors can be passed to QEMU from parent process or by unix
socket with sendfd() qmp command.

Changes since v1:
 * refactored code.
 * eBPF program ids implemented as enums

Andrew Melnychenko (6):
  ebpf: Added eBPF map update through mmap.
  ebpf: Added eBPF initialization by fds.
  virtio-net: Added property to load eBPF RSS with fds.
  ebpf: Added declaration/initialization routines.
  qmp: Added new command to retrieve eBPF blob.
  ebpf: Updated eBPF program and skeleton.

 ebpf/ebpf.c|   54 ++
 ebpf/ebpf.h|   31 +
 ebpf/ebpf_rss-stub.c   |6 +
 ebpf/ebpf_rss.c|  149 +++-
 ebpf/ebpf_rss.h|   10 +
 ebpf/meson.build   |1 +
 ebpf/rss.bpf.skeleton.h| 1469 
 hw/net/virtio-net.c|   55 +-
 include/hw/virtio/virtio-net.h |1 +
 monitor/qmp-cmds.c |   16 +
 qapi/misc.json |   38 +
 tools/ebpf/rss.bpf.c   |2 +-
 12 files changed, 1073 insertions(+), 759 deletions(-)
 create mode 100644 ebpf/ebpf.c
 create mode 100644 ebpf/ebpf.h

-- 
2.39.1

[PATCH v2 5/6] qmp: Added new command to retrieve eBPF blob.

2023-05-12 Thread Andrew Melnychenko

Added command "request-ebpf". This command returns
eBPF program encoded base64. The program taken from the
skeleton and essentially is an ELF object that can be
loaded in the future with libbpf.

Signed-off-by: Andrew Melnychenko 
---
 monitor/qmp-cmds.c | 16 
 qapi/misc.json | 38 ++
 2 files changed, 54 insertions(+)

diff --git a/monitor/qmp-cmds.c b/monitor/qmp-cmds.c
index b0f948d3376..259bc87ccb1 100644
--- a/monitor/qmp-cmds.c
+++ b/monitor/qmp-cmds.c
@@ -32,6 +32,7 @@
 #include "hw/mem/memory-device.h"
 #include "hw/intc/intc.h"
 #include "hw/rdma/rdma.h"
+#include "ebpf/ebpf.h"
 
 NameInfo *qmp_query_name(Error **errp)
 {
@@ -209,3 +210,18 @@ static void __attribute__((__constructor__)) 
monitor_init_qmp_commands(void)
  qmp_marshal_qmp_capabilities,
  QCO_ALLOW_PRECONFIG, 0);
 }
+
+EbpfObject *qmp_request_ebpf(EbpfProgramID id, Error **errp)
+{
+EbpfObject *ret = NULL;
+size_t size = 0;
+const void *data = ebpf_find_binary_by_id(id, , errp);
+if (!data) {
+return NULL;
+}
+
+ret = g_new0(EbpfObject, 1);
+ret->object = g_base64_encode(data, size);
+
+return ret;
+}
diff --git a/qapi/misc.json b/qapi/misc.json
index 6ddd16ea283..e96dac8482b 100644
--- a/qapi/misc.json
+++ b/qapi/misc.json
@@ -618,3 +618,41 @@
 { 'event': 'VFU_CLIENT_HANGUP',
   'data': { 'vfu-id': 'str', 'vfu-qom-path': 'str',
 'dev-id': 'str', 'dev-qom-path': 'str' } }
+
+##
+# @EbpfObject:
+#
+# Structure that holds eBPF ELF object encoded in base64.
+#
+# Since: 8.1
+#
+##
+{ 'struct': 'EbpfObject',
+  'data': {'object': 'str'} }
+
+##
+# @EbpfProgramID:
+#
+# An enumeration of the eBPF programs. Currently, only RSS is presented.
+#
+# Since: 8.1
+##
+{ 'enum': 'EbpfProgramID',
+  'data': [ { 'name': 'rss', 'if': 'CONFIG_EBPF' } ] }
+
+##
+# @request-ebpf:
+#
+# Function returns eBPF object that can be loaded with libbpf.
+# Management applications (g.e. libvirt) may load it and pass file
+# descriptors to QEMU. Which allows running QEMU without BPF capabilities.
+#
+# Returns: RSS eBPF object encoded in base64.
+#
+# Since: 8.1
+#
+##
+{ 'command': 'request-ebpf',
+  'data': { 'id': 'EbpfProgramID' },
+  'returns': 'EbpfObject' }
+
-- 
2.39.1

[PATCH v2 2/6] ebpf: Added eBPF initialization by fds.

2023-05-12 Thread Andrew Melnychenko

It allows using file descriptors of eBPF provided
outside of QEMU.
QEMU may be run without capabilities for eBPF and run
RSS program provided by management tool(g.e. libvirt).

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf_rss-stub.c |  6 ++
 ebpf/ebpf_rss.c  | 27 +++
 ebpf/ebpf_rss.h  |  5 +
 3 files changed, 38 insertions(+)

diff --git a/ebpf/ebpf_rss-stub.c b/ebpf/ebpf_rss-stub.c
index e71e229190d..8d7fae2ad92 100644
--- a/ebpf/ebpf_rss-stub.c
+++ b/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)
 {
diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index 247f5eee1b6..24bc6cc409e 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -146,6 +146,33 @@ error:
 return false;
 }
 
+bool ebpf_rss_load_fds(struct EBPFRSSContext *ctx, int program_fd,
+   int config_fd, int toeplitz_fd, int table_fd)
+{
+if (ctx == NULL || ebpf_rss_is_loaded(ctx)) {
+return false;
+}
+
+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;
+}
+
+return true;
+}
+
 static bool ebpf_rss_set_config(struct EBPFRSSContext *ctx,
 struct EBPFRSSConfig *config)
 {
diff --git a/ebpf/ebpf_rss.h b/ebpf/ebpf_rss.h
index ab08a7266d0..239242b0d26 100644
--- a/ebpf/ebpf_rss.h
+++ b/ebpf/ebpf_rss.h
@@ -14,6 +14,8 @@
 #ifndef QEMU_EBPF_RSS_H
 #define QEMU_EBPF_RSS_H
 
+#define EBPF_RSS_MAX_FDS 4
+
 struct EBPFRSSContext {
 void *obj;
 int program_fd;
@@ -41,6 +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);
 
-- 
2.39.1

[PATCH v2 3/6] virtio-net: Added property to load eBPF RSS with fds.

2023-05-12 Thread Andrew Melnychenko

eBPF RSS program and maps may now be passed during initialization.
Initially was implemented for libvirt to launch qemu without permissions,
and initialized eBPF program through the helper.

Signed-off-by: Andrew Melnychenko 
---
 hw/net/virtio-net.c| 55 ++
 include/hw/virtio/virtio-net.h |  1 +
 2 files changed, 50 insertions(+), 6 deletions(-)

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 53e1c326433..a62d7936948 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -42,6 +42,7 @@
 #include "sysemu/sysemu.h"
 #include "trace.h"
 #include "monitor/qdev.h"
+#include "monitor/monitor.h"
 #include "hw/pci/pci_device.h"
 #include "net_rx_pkt.h"
 #include "hw/virtio/vhost.h"
@@ -1305,14 +1306,55 @@ static void virtio_net_detach_epbf_rss(VirtIONet *n)
 virtio_net_attach_ebpf_to_backend(n->nic, -1);
 }
 
-static bool virtio_net_load_ebpf(VirtIONet *n)
+static bool virtio_net_load_ebpf_fds(VirtIONet *n, Error **errp)
 {
-if (!virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
-/* backend does't support steering ebpf */
-return false;
+int fds[EBPF_RSS_MAX_FDS] = { [0 ... EBPF_RSS_MAX_FDS - 1] = -1};
+int nfds = 0;
+int ret = true;
+int i = 0;
+g_autofree char **fds_strs = g_strsplit(n->ebpf_rss_fds, ":", 0);
+
+ERRP_GUARD();
+
+if (g_strv_length(fds_strs) != EBPF_RSS_MAX_FDS) {
+error_setg(errp,
+  "Expected %d file descriptors but got %d",
+  EBPF_RSS_MAX_FDS, g_strv_length(fds_strs));
+   return false;
+   }
+
+for (i = 0; i < nfds; i++) {
+fds[i] = monitor_fd_param(monitor_cur(), fds_strs[i], errp);
+if (*errp) {
+ret = false;
+goto exit;
+}
+}
+
+ret = ebpf_rss_load_fds(>ebpf_rss, fds[0], fds[1], fds[2], fds[3]);
+
+exit:
+if (!ret || *errp) {
+for (i = 0; i < nfds && fds[i] != -1; i++) {
+close(fds[i]);
+}
 }
 
-return ebpf_rss_load(>ebpf_rss);
+return ret;
+}
+
+static bool virtio_net_load_ebpf(VirtIONet *n, Error **errp)
+{
+bool ret = false;
+
+if (virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
+if (!(n->ebpf_rss_fds
+&& virtio_net_load_ebpf_fds(n, errp))) {
+ret = ebpf_rss_load(>ebpf_rss);
+}
+}
+
+return ret;
 }
 
 static void virtio_net_unload_ebpf(VirtIONet *n)
@@ -3738,7 +3780,7 @@ static void virtio_net_device_realize(DeviceState *dev, 
Error **errp)
 net_rx_pkt_init(>rx_pkt);
 
 if (virtio_has_feature(n->host_features, VIRTIO_NET_F_RSS)) {
-virtio_net_load_ebpf(n);
+virtio_net_load_ebpf(n, errp);
 }
 }
 
@@ -3900,6 +3942,7 @@ static Property virtio_net_properties[] = {
 VIRTIO_NET_F_RSS, false),
 DEFINE_PROP_BIT64("hash", VirtIONet, host_features,
 VIRTIO_NET_F_HASH_REPORT, false),
+DEFINE_PROP_STRING("ebpf_rss_fds", VirtIONet, ebpf_rss_fds),
 DEFINE_PROP_BIT64("guest_rsc_ext", VirtIONet, host_features,
 VIRTIO_NET_F_RSC_EXT, false),
 DEFINE_PROP_UINT32("rsc_interval", VirtIONet, rsc_timeout,
diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h
index ef234ffe7ef..e10ce88f918 100644
--- a/include/hw/virtio/virtio-net.h
+++ b/include/hw/virtio/virtio-net.h
@@ -219,6 +219,7 @@ struct VirtIONet {
 VirtioNetRssData rss_data;
 struct NetRxPkt *rx_pkt;
 struct EBPFRSSContext ebpf_rss;
+char *ebpf_rss_fds;
 };
 
 size_t virtio_net_handle_ctrl_iov(VirtIODevice *vdev,
-- 
2.39.1

[PATCH 3/5] ebpf: Added declaration/initialization routines.

2023-05-01 Thread Andrew Melnychenko

Now, the binary objects may be retrieved by id/name.
It would require for future qmp commands that may require specific
eBPF blob.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf.c  | 54 
 ebpf/ebpf.h  | 31 +++
 ebpf/ebpf_rss.c  |  4 
 ebpf/meson.build |  1 +
 4 files changed, 90 insertions(+)
 create mode 100644 ebpf/ebpf.c
 create mode 100644 ebpf/ebpf.h

diff --git a/ebpf/ebpf.c b/ebpf/ebpf.c
new file mode 100644
index 000..fd96f2b42f9
--- /dev/null
+++ b/ebpf/ebpf.c
@@ -0,0 +1,54 @@
+/*
+ * QEMU eBPF binary declaration routine.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * 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 "ebpf/ebpf.h"
+
+struct ElfBinaryDataEntry {
+const char *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(const char *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(_elf_obj_list, dataentry, node);
+}
+
+const void *ebpf_find_binary_by_id(const char *id, size_t *sz, Error **errp)
+{
+struct ElfBinaryDataEntry *it = NULL;
+QSLIST_FOREACH(it, _elf_obj_list, node) {
+if (strcmp(id, it->id) == 0) {
+*sz = it->datalen;
+return it->data;
+}
+}
+
+error_setg(errp, "can't find eBPF object with id: %s", id);
+
+return NULL;
+}
diff --git a/ebpf/ebpf.h b/ebpf/ebpf.h
new file mode 100644
index 000..36c5d455b4b
--- /dev/null
+++ b/ebpf/ebpf.h
@@ -0,0 +1,31 @@
+/*
+ * QEMU eBPF binary declaration routine.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * 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(const char *id, const void *data,
+   size_t datalen);
+const void *ebpf_find_binary_by_id(const char *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();   \
+ebpf_register_binary_data(id, data, datalen);  \
+}
+
+#endif /* EBPF_H */
diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index 08015fecb18..b4038725f23 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -21,6 +21,8 @@
 
 #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)
@@ -237,3 +239,5 @@ void ebpf_rss_unload(struct EBPFRSSContext *ctx)
 ctx->obj = NULL;
 ctx->program_fd = -1;
 }
+
+ebpf_binary_init("rss", rss_bpf__elf_bytes)
diff --git a/ebpf/meson.build b/ebpf/meson.build
index 2dd0fd89480..67c3f53aa9d 100644
--- a/ebpf/meson.build
+++ b/ebpf/meson.build
@@ -1 +1,2 @@
+softmmu_ss.add(files('ebpf.c'))
 softmmu_ss.add(when: libbpf, if_true: files('ebpf_rss.c'), if_false: 
files('ebpf_rss-stub.c'))
-- 
2.39.1

[PATCH 4/5] qmp: Added new command to retrieve eBPF blob.

2023-05-01 Thread Andrew Melnychenko

Added command "request-ebpf". This command returns
eBPF program encoded base64. The program taken from the
skeleton and essentially is an ELF object that can be
loaded in the future with libbpf.

Signed-off-by: Andrew Melnychenko 
---
 monitor/qmp-cmds.c | 16 
 qapi/misc.json | 28 
 2 files changed, 44 insertions(+)

diff --git a/monitor/qmp-cmds.c b/monitor/qmp-cmds.c
index b0f948d3376..f7641bb55b9 100644
--- a/monitor/qmp-cmds.c
+++ b/monitor/qmp-cmds.c
@@ -32,6 +32,7 @@
 #include "hw/mem/memory-device.h"
 #include "hw/intc/intc.h"
 #include "hw/rdma/rdma.h"
+#include "ebpf/ebpf.h"
 
 NameInfo *qmp_query_name(Error **errp)
 {
@@ -209,3 +210,18 @@ static void __attribute__((__constructor__)) 
monitor_init_qmp_commands(void)
  qmp_marshal_qmp_capabilities,
  QCO_ALLOW_PRECONFIG, 0);
 }
+
+EbpfObject *qmp_request_ebpf(const char *id, Error **errp)
+{
+EbpfObject *ret = NULL;
+size_t size = 0;
+const void *data = ebpf_find_binary_by_id(id, , errp);
+if (!data) {
+return NULL;
+}
+
+ret = g_new0(EbpfObject, 1);
+ret->object = g_base64_encode(data, size);
+
+return ret;
+}
diff --git a/qapi/misc.json b/qapi/misc.json
index 6ddd16ea283..81613fd1b13 100644
--- a/qapi/misc.json
+++ b/qapi/misc.json
@@ -618,3 +618,31 @@
 { 'event': 'VFU_CLIENT_HANGUP',
   'data': { 'vfu-id': 'str', 'vfu-qom-path': 'str',
 'dev-id': 'str', 'dev-qom-path': 'str' } }
+
+##
+# @EbpfObject:
+#
+# Structure that holds eBPF ELF object encoded in base64.
+#
+# Since: 8.1
+#
+##
+{ 'struct': 'EbpfObject',
+  'data': {'object': 'str'} }
+
+##
+# @request-ebpf:
+#
+# Function returns eBPF object that can be loaded with libbpf.
+# Management applications (g.e. libvirt) may load it and pass file
+# descriptors to QEMU. Which allows running QEMU without BPF capabilities.
+#
+# Returns: RSS eBPF object encoded in base64.
+#
+# Since: 8.1
+#
+##
+{ 'command': 'request-ebpf',
+  'data': { 'id': 'str' },
+  'returns': 'EbpfObject' }
+
-- 
2.39.1

[PATCH 5/5] ebpf: Updated eBPF program and skeleton.

2023-05-01 Thread Andrew Melnychenko

Updated section name, so libbpf should init/gues proper
program type without specifications during open/load.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/rss.bpf.skeleton.h | 1469 ---
 tools/ebpf/rss.bpf.c|2 +-
 2 files changed, 741 insertions(+), 730 deletions(-)

diff --git a/ebpf/rss.bpf.skeleton.h b/ebpf/rss.bpf.skeleton.h
index 18eb2adb12c..41b84aea44c 100644
--- a/ebpf/rss.bpf.skeleton.h
+++ b/ebpf/rss.bpf.skeleton.h
@@ -176,162 +176,162 @@ err:
 
 static inline const void *rss_bpf__elf_bytes(size_t *sz)
 {
-   *sz = 20440;
+   *sz = 20720;
return (const void *)"\
 \x7f\x45\x4c\x46\x02\x01\x01\0\0\0\0\0\0\0\0\0\x01\0\xf7\0\x01\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\x98\x4c\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0d\0\
-\x01\0\xbf\x19\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\x54\xff\0\0\0\0\xbf\xa7\
-\0\0\0\0\0\0\x07\x07\0\0\x54\xff\xff\xff\x18\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\xb0\x4d\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0d\0\
+\x01\0\xbf\x19\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\x4c\xff\0\0\0\0\xbf\xa7\
+\0\0\0\0\0\0\x07\x07\0\0\x4c\xff\xff\xff\x18\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
 \xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x06\0\0\0\0\0\0\x18\x01\0\0\0\0\0\
 \0\0\0\0\0\0\0\0\0\xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x08\0\0\0\0\0\0\
-\x18\0\0\0\xff\xff\xff\xff\0\0\0\0\0\0\0\0\x15\x06\x67\x02\0\0\0\0\xbf\x87\0\0\
-\0\0\0\0\x15\x07\x65\x02\0\0\0\0\x71\x61\0\0\0\0\0\0\x55\x01\x01\0\0\0\0\0\x05\
-\0\x5e\x02\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xc8\xff\0\0\0\0\x7b\x1a\xc0\xff\
-\0\0\0\0\x7b\x1a\xb8\xff\0\0\0\0\x7b\x1a\xb0\xff\0\0\0\0\x7b\x1a\xa8\xff\0\0\0\
-\0\x63\x1a\xa0\xff\0\0\0\0\x7b\x1a\x98\xff\0\0\0\0\x7b\x1a\x90\xff\0\0\0\0\x7b\
-\x1a\x88\xff\0\0\0\0\x7b\x1a\x80\xff\0\0\0\0\x7b\x1a\x78\xff\0\0\0\0\x7b\x1a\
-\x70\xff\0\0\0\0\x7b\x1a\x68\xff\0\0\0\0\x7b\x1a\x60\xff\0\0\0\0\x7b\x1a\x58\
-\xff\0\0\0\0\x15\x09\x4d\x02\0\0\0\0\x6b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\
-\0\x07\x03\0\0\xd0\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x02\0\0\x0c\0\0\0\xb7\
+\x18\0\0\0\xff\xff\xff\xff\0\0\0\0\0\0\0\0\x15\x06\x64\x02\0\0\0\0\xbf\x87\0\0\
+\0\0\0\0\x15\x07\x62\x02\0\0\0\0\x71\x61\0\0\0\0\0\0\x55\x01\x01\0\0\0\0\0\x05\
+\0\x5b\x02\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xc0\xff\0\0\0\0\x7b\x1a\xb8\xff\
+\0\0\0\0\x7b\x1a\xb0\xff\0\0\0\0\x7b\x1a\xa8\xff\0\0\0\0\x7b\x1a\xa0\xff\0\0\0\
+\0\x63\x1a\x98\xff\0\0\0\0\x7b\x1a\x90\xff\0\0\0\0\x7b\x1a\x88\xff\0\0\0\0\x7b\
+\x1a\x80\xff\0\0\0\0\x7b\x1a\x78\xff\0\0\0\0\x7b\x1a\x70\xff\0\0\0\0\x7b\x1a\
+\x68\xff\0\0\0\0\x7b\x1a\x60\xff\0\0\0\0\x7b\x1a\x58\xff\0\0\0\0\x7b\x1a\x50\
+\xff\0\0\0\0\x15\x09\x4a\x02\0\0\0\0\x6b\x1a\xc8\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\
+\0\x07\x03\0\0\xc8\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x02\0\0\x0c\0\0\0\xb7\
 \x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\
-\x77\0\0\0\x20\0\0\0\x55\0\x42\x02\0\0\0\0\xb7\x02\0\0\x10\0\0\0\x69\xa1\xd0\
+\x77\0\0\0\x20\0\0\0\x55\0\x3f\x02\0\0\0\0\xb7\x02\0\0\x10\0\0\0\x69\xa1\xc8\
 \xff\0\0\0\0\xbf\x13\0\0\0\0\0\0\xdc\x03\0\0\x10\0\0\0\x15\x03\x02\0\0\x81\0\0\
 \x55\x03\x0b\0\xa8\x88\0\0\xb7\x02\0\0\x14\0\0\0\xbf\xa3\0\0\0\0\0\0\x07\x03\0\
-\0\xd0\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\
-\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\x77\0\0\0\x20\0\0\0\x55\0\x32\x02\0\
-\0\0\0\x69\xa1\xd0\xff\0\0\0\0\x15\x01\x30\x02\0\0\0\0\x7b\x7a\x38\xff\0\0\0\0\
-\x7b\x9a\x40\xff\0\0\0\0\x15\x01\x55\0\x86\xdd\0\0\x55\x01\x39\0\x08\0\0\0\xb7\
-\x07\0\0\x01\0\0\0\x73\x7a\x58\xff\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xe0\xff\
-\0\0\0\0\x7b\x1a\xd8\xff\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\0\
-\x07\x03\0\0\xd0\xff\xff\xff\x79\xa1\x40\xff\0\0\0\0\xb7\x02\0\0\0\0\0\0\xb7\
+\0\xc8\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\
+\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\x77\0\0\0\x20\0\0\0\x55\0\x2f\x02\0\
+\0\0\0\x69\xa1\xc8\xff\0\0\0\0\x15\x01\x2d\x02\0\0\0\0\x7b\x7a\x30\xff\0\0\0\0\
+\x7b\x9a\x38\xff\0\0\0\0\x15\x01\x55\0\x86\xdd\0\0\x55\x01\x39\0\x08\0\0\0\xb7\
+\x07\0\0\x01\0\0\0\x73\x7a\x50\xff\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xd8\xff\
+\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\x7b\x1a\xc8\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\0\
+\x07\x03\0\0\xc8\xff\xff\xff\x79\xa1\x38\xff\0\0\0\0\xb7\x02\0\0\0\0\0\0\xb7\
 \x04\0\0\x14\0\0\0\xb7\x05\0\0\x01\0\0\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\
-\0\x77\0\0\0\x20\0\0\0\x55\0\x1c\x02\0\0\0\0\x69\xa1\xd6\xff\0\0\0\0\x55\x01\
-\x01\0\0\0\0\0\xb7\x07\0\0\0\0\0\0\x61\xa1\xdc\xff\0\0\0\0\x63\x1a\x64\xff\0\0\
-\0\0\x61\xa1\xe0\xff\0\0\0\0\x63\x1a\x68\xff\0\0\0\0\x71\xa9\xd9\xff\0\0\0\0\
-\x73\x7a\x5e\xff\0\0\0\0\x71\xa1\xd0\xff\0\0\0\0\x67\x01\0\0\x02\0\0\0\x57\x01\
-\0\0\x3c\0\0\0\x7b\x1a\x48\xff\0\0\0\0\xbf\x91\0\0\0\0\0\0\x57\x01\0\0\xff\0\0\
+\0\x77\0\0\0\x20\0\0\0\x55\0\x19\x02\0\0\0\0\x69\xa1\xce\xff\0\0\0\0\x55\x01\
+\x01\0\0\0\0\0\xb7\x07\0\0\0\0\0\0\x61\xa1\xd4\xff\0\0\0\0\x63\x1a\x5c\xff\0\0\
+\0\0\x61\xa1\xd8\

[PATCH 1/5] ebpf: Added eBPF initialization by fds and map update.

2023-05-01 Thread Andrew Melnychenko

Changed eBPF map updates through mmaped array.
Mmaped arrays provide direct access to map data.
It should omit using bpf_map_update_elem() call,
which may require capabilities that are not present.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf_rss-stub.c |   6 +++
 ebpf/ebpf_rss.c  | 120 ++-
 ebpf/ebpf_rss.h  |  10 
 3 files changed, 113 insertions(+), 23 deletions(-)

diff --git a/ebpf/ebpf_rss-stub.c b/ebpf/ebpf_rss-stub.c
index e71e229190d..8d7fae2ad92 100644
--- a/ebpf/ebpf_rss-stub.c
+++ b/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)
 {
diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index cee658c158b..08015fecb18 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -27,19 +27,68 @@ void ebpf_rss_init(struct EBPFRSSContext *ctx)
 {
 if (ctx != NULL) {
 ctx->obj = NULL;
+ctx->program_fd = -1;
 }
 }
 
 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());
+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());
 }
 
 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;
 }
 
@@ -66,26 +115,51 @@ 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;
 
 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;
 }
-if (bpf_map_update_elem(ctx->map_configuration,
-_key, config, 0) < 0) {
+
+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;
 return false;
 }
+
+return true;
+}
+
+static bool ebpf_rss_set_config(struct EBPFRSSContext *ctx,
+str

[PATCH 2/5] virtio-net: Added property to load eBPF RSS with fds.

2023-05-01 Thread Andrew Melnychenko

eBPF RSS program and maps may now be passed during initialization.
Initially was implemented for libvirt to launch qemu without permissions,
and initialized eBPF program through the helper.

Signed-off-by: Andrew Melnychenko 
---
 hw/net/virtio-net.c| 96 +++---
 include/hw/virtio/virtio-net.h |  1 +
 2 files changed, 91 insertions(+), 6 deletions(-)

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 53e1c326433..9b3a997d872 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -42,6 +42,7 @@
 #include "sysemu/sysemu.h"
 #include "trace.h"
 #include "monitor/qdev.h"
+#include "monitor/monitor.h"
 #include "hw/pci/pci_device.h"
 #include "net_rx_pkt.h"
 #include "hw/virtio/vhost.h"
@@ -1305,14 +1306,96 @@ static void virtio_net_detach_epbf_rss(VirtIONet *n)
 virtio_net_attach_ebpf_to_backend(n->nic, -1);
 }
 
-static bool virtio_net_load_ebpf(VirtIONet *n)
+static int virtio_net_get_ebpf_rss_fds(char *str, char *fds[], int nfds,
+   Error **errp)
 {
-if (!virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
-/* backend does't support steering ebpf */
-return false;
+char *ptr = str;
+char *cur = NULL;
+size_t len = strlen(str);
+int i = 0;
+
+for (; i < nfds && ptr < str + len;) {
+cur = strchr(ptr, ':');
+
+if (cur == NULL) {
+fds[i] = g_strdup(ptr);
+} else {
+fds[i] = g_strndup(ptr, cur - ptr);
+}
+
+i++;
+if (cur == NULL) {
+break;
+} else {
+ptr = cur + 1;
+}
+}
+
+if (cur != NULL) {
+/* the string contains more arguments */
+error_setg(errp,
+   "Too many eBPF file descriptors for RSS provided.");
+} else if (i < nfds) {
+error_setg(errp,
+   "Not enough eBPF file descriptors for RSS were provided.");
+}
+
+return i;
+}
+
+static bool virtio_net_load_ebpf_fds(VirtIONet *n, Error **errp)
+{
+char *fds_strs[EBPF_RSS_MAX_FDS];
+int fds[EBPF_RSS_MAX_FDS];
+int nfds;
+int ret = true;
+int i = 0;
+
+ERRP_GUARD();
+
+nfds = virtio_net_get_ebpf_rss_fds(n->ebpf_rss_fds,
+   fds_strs, EBPF_RSS_MAX_FDS, errp);
+if (*errp) {
+ret = false;
+goto exit;
 }
 
-return ebpf_rss_load(>ebpf_rss);
+for (i = 0; i < nfds; i++) {
+fds[i] = monitor_fd_param(monitor_cur(), fds_strs[i], errp);
+if (*errp) {
+ret = false;
+goto exit;
+}
+}
+
+ret = ebpf_rss_load_fds(>ebpf_rss, fds[0], fds[1], fds[2], fds[3]);
+
+exit:
+if (!ret || *errp) {
+for (i = 0; i < nfds; i++) {
+close(fds[i]);
+}
+}
+
+for (i = 0; i < nfds; i++) {
+g_free(fds_strs[i]);
+}
+
+return ret;
+}
+
+static bool virtio_net_load_ebpf(VirtIONet *n, Error **errp)
+{
+bool ret = false;
+
+if (virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
+if (!(n->ebpf_rss_fds
+&& virtio_net_load_ebpf_fds(n, errp))) {
+ret = ebpf_rss_load(>ebpf_rss);
+}
+}
+
+return ret;
 }
 
 static void virtio_net_unload_ebpf(VirtIONet *n)
@@ -3738,7 +3821,7 @@ static void virtio_net_device_realize(DeviceState *dev, 
Error **errp)
 net_rx_pkt_init(>rx_pkt);
 
 if (virtio_has_feature(n->host_features, VIRTIO_NET_F_RSS)) {
-virtio_net_load_ebpf(n);
+virtio_net_load_ebpf(n, errp);
 }
 }
 
@@ -3900,6 +3983,7 @@ static Property virtio_net_properties[] = {
 VIRTIO_NET_F_RSS, false),
 DEFINE_PROP_BIT64("hash", VirtIONet, host_features,
 VIRTIO_NET_F_HASH_REPORT, false),
+DEFINE_PROP_STRING("ebpf_rss_fds", VirtIONet, ebpf_rss_fds),
 DEFINE_PROP_BIT64("guest_rsc_ext", VirtIONet, host_features,
 VIRTIO_NET_F_RSC_EXT, false),
 DEFINE_PROP_UINT32("rsc_interval", VirtIONet, rsc_timeout,
diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h
index ef234ffe7ef..e10ce88f918 100644
--- a/include/hw/virtio/virtio-net.h
+++ b/include/hw/virtio/virtio-net.h
@@ -219,6 +219,7 @@ struct VirtIONet {
 VirtioNetRssData rss_data;
 struct NetRxPkt *rx_pkt;
 struct EBPFRSSContext ebpf_rss;
+char *ebpf_rss_fds;
 };
 
 size_t virtio_net_handle_ctrl_iov(VirtIODevice *vdev,
-- 
2.39.1

[PATCH 0/5] eBPF RSS through QMP support.

2023-05-01 Thread Andrew Melnychenko

This series of patches provides the ability to retrieve eBPF program
through qmp, so management application may load bpf blob with proper 
capabilities.
Now, virtio-net devices can accept eBPF programs and maps through properties
as external file descriptors. Access to the eBPF map is direct through mmap()
call, so it should not require additional capabilities to bpf* calls.
eBPF file descriptors can be passed to QEMU from parent process or by unix
socket with sendfd() qmp command.

Possible solution for libvirt may look like this: 
https://github.com/daynix/libvirt/tree/RSS_eBPF (WIP)

Andrew Melnychenko (5):
  ebpf: Added eBPF initialization by fds and map update.
  virtio-net: Added property to load eBPF RSS with fds.
  ebpf: Added declaration/initialization routines.
  qmp: Added new command to retrieve eBPF blob.
  ebpf: Updated eBPF program and skeleton.

 ebpf/ebpf.c|   54 ++
 ebpf/ebpf.h|   31 +
 ebpf/ebpf_rss-stub.c   |6 +
 ebpf/ebpf_rss.c|  124 ++-
 ebpf/ebpf_rss.h|   10 +
 ebpf/meson.build   |1 +
 ebpf/rss.bpf.skeleton.h| 1469 
 hw/net/virtio-net.c|   96 ++-
 include/hw/virtio/virtio-net.h |1 +
 monitor/qmp-cmds.c |   16 +
 qapi/misc.json |   28 +
 tools/ebpf/rss.bpf.c   |2 +-
 12 files changed, 1079 insertions(+), 759 deletions(-)
 create mode 100644 ebpf/ebpf.c
 create mode 100644 ebpf/ebpf.h

-- 
2.39.1

[RFC PATCH 3/5] ebpf: Added declaration/initialization routines.

2023-03-29 Thread Andrew Melnychenko

Now, the binary objects may be retrieved by id/name.
It would require for future qmp commands that may require specific
eBPF blob.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf.c  | 48 
 ebpf/ebpf.h  | 25 +
 ebpf/ebpf_rss.c  |  4 
 ebpf/meson.build |  1 +
 4 files changed, 78 insertions(+)
 create mode 100644 ebpf/ebpf.c
 create mode 100644 ebpf/ebpf.h

diff --git a/ebpf/ebpf.c b/ebpf/ebpf.c
new file mode 100644
index 00..86320d72f5
--- /dev/null
+++ b/ebpf/ebpf.c
@@ -0,0 +1,48 @@
+/*
+ * QEMU eBPF binary declaration routine.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * 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 "ebpf/ebpf.h"
+
+struct ElfBinaryDataEntry {
+const char *id;
+const void * (*fn)(size_t *);
+
+QSLIST_ENTRY(ElfBinaryDataEntry) node;
+};
+
+static QSLIST_HEAD(, ElfBinaryDataEntry) ebpf_elf_obj_list =
+QSLIST_HEAD_INITIALIZER();
+
+void ebpf_register_binary_data(const char *id, const void * (*fn)(size_t *))
+{
+struct ElfBinaryDataEntry *data = NULL;
+
+data = g_malloc0(sizeof(*data));
+data->fn = fn;
+data->id = id;
+
+QSLIST_INSERT_HEAD(_elf_obj_list, data, node);
+}
+
+const void *ebpf_find_binary_by_id(const char *id, size_t *sz)
+{
+struct ElfBinaryDataEntry *it = NULL;
+QSLIST_FOREACH(it, _elf_obj_list, node) {
+if (strcmp(id, it->id) == 0) {
+return it->fn(sz);
+}
+}
+
+return NULL;
+}
diff --git a/ebpf/ebpf.h b/ebpf/ebpf.h
new file mode 100644
index 00..fd705cb73e
--- /dev/null
+++ b/ebpf/ebpf.h
@@ -0,0 +1,25 @@
+/*
+ * QEMU eBPF binary declaration routine.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * 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
+
+void ebpf_register_binary_data(const char *id, const void * (*fn)(size_t *));
+const void *ebpf_find_binary_by_id(const char *id, size_t *sz);
+
+#define ebpf_binary_init(id, fn)   \
+static void __attribute__((constructor)) ebpf_binary_init_ ## fn(void) \
+{  \
+ebpf_register_binary_data(id, fn); \
+}
+
+#endif /* EBPF_H */
diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index 08015fecb1..b4038725f2 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -21,6 +21,8 @@
 
 #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)
@@ -237,3 +239,5 @@ void ebpf_rss_unload(struct EBPFRSSContext *ctx)
 ctx->obj = NULL;
 ctx->program_fd = -1;
 }
+
+ebpf_binary_init("rss", rss_bpf__elf_bytes)
diff --git a/ebpf/meson.build b/ebpf/meson.build
index 2dd0fd8948..67c3f53aa9 100644
--- a/ebpf/meson.build
+++ b/ebpf/meson.build
@@ -1 +1,2 @@
+softmmu_ss.add(files('ebpf.c'))
 softmmu_ss.add(when: libbpf, if_true: files('ebpf_rss.c'), if_false: 
files('ebpf_rss-stub.c'))
-- 
2.39.1

[RFC PATCH 2/5] virtio-net: Added property to load eBPF RSS with fds.

2023-03-29 Thread Andrew Melnychenko

eBPF RSS program and maps may now be passed during initialization.
Initially was implemented for libvirt to launch qemu without permissions,
and initialized eBPF program through the helper.

Signed-off-by: Andrew Melnychenko 
---
 hw/net/virtio-net.c| 77 --
 include/hw/virtio/virtio-net.h |  1 +
 2 files changed, 74 insertions(+), 4 deletions(-)

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 53e1c32643..45d448a83d 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -42,6 +42,7 @@
 #include "sysemu/sysemu.h"
 #include "trace.h"
 #include "monitor/qdev.h"
+#include "monitor/monitor.h"
 #include "hw/pci/pci_device.h"
 #include "net_rx_pkt.h"
 #include "hw/virtio/vhost.h"
@@ -1305,14 +1306,81 @@ static void virtio_net_detach_epbf_rss(VirtIONet *n)
 virtio_net_attach_ebpf_to_backend(n->nic, -1);
 }
 
-static bool virtio_net_load_ebpf(VirtIONet *n)
+static int virtio_net_get_ebpf_rss_fds(char *str, char *fds[], int nfds)
+{
+char *ptr = str;
+char *cur = NULL;
+size_t len = strlen(str);
+int i = 0;
+
+for (; i < nfds && ptr < str + len;) {
+cur = strchr(ptr, ':');
+
+if (cur == NULL) {
+fds[i] = g_strdup(ptr);
+} else {
+fds[i] = g_strndup(ptr, cur - ptr);
+}
+
+i++;
+if (cur == NULL) {
+break;
+} else {
+ptr = cur + 1;
+}
+}
+
+return i;
+}
+
+static bool virtio_net_load_ebpf_fds(VirtIONet *n)
 {
-if (!virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
-/* backend does't support steering ebpf */
+char *fds_strs[EBPF_RSS_MAX_FDS];
+int fds[EBPF_RSS_MAX_FDS];
+int nfds;
+int ret = false;
+Error *errp;
+int i = 0;
+
+if (n == NULL || !n->ebpf_rss_fds) {
 return false;
 }
 
-return ebpf_rss_load(>ebpf_rss);
+nfds = virtio_net_get_ebpf_rss_fds(n->ebpf_rss_fds,
+   fds_strs, EBPF_RSS_MAX_FDS);
+for (i = 0; i < nfds; i++) {
+fds[i] = monitor_fd_param(monitor_cur(), fds_strs[i], );
+}
+
+if (nfds == EBPF_RSS_MAX_FDS) {
+ret = ebpf_rss_load_fds(>ebpf_rss, fds[0], fds[1], fds[2], fds[3]);
+}
+
+if (!ret) {
+for (i = 0; i < nfds; i++) {
+close(fds[i]);
+}
+}
+
+for (i = 0; i < nfds; i++) {
+g_free(fds_strs[i]);
+}
+
+return ret;
+}
+
+static bool virtio_net_load_ebpf(VirtIONet *n)
+{
+bool ret = true;
+
+if (virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
+if (!(n->ebpf_rss_fds
+&& virtio_net_load_ebpf_fds(n))) {
+ret = ebpf_rss_load(>ebpf_rss);
+}
+}
+
+return ret;
 }
 
 static void virtio_net_unload_ebpf(VirtIONet *n)
@@ -3900,6 +3968,7 @@ static Property virtio_net_properties[] = {
 VIRTIO_NET_F_RSS, false),
 DEFINE_PROP_BIT64("hash", VirtIONet, host_features,
 VIRTIO_NET_F_HASH_REPORT, false),
+DEFINE_PROP_STRING("ebpf_rss_fds", VirtIONet, ebpf_rss_fds),
 DEFINE_PROP_BIT64("guest_rsc_ext", VirtIONet, host_features,
 VIRTIO_NET_F_RSC_EXT, false),
 DEFINE_PROP_UINT32("rsc_interval", VirtIONet, rsc_timeout,
diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h
index ef234ffe7e..e10ce88f91 100644
--- a/include/hw/virtio/virtio-net.h
+++ b/include/hw/virtio/virtio-net.h
@@ -219,6 +219,7 @@ struct VirtIONet {
 VirtioNetRssData rss_data;
 struct NetRxPkt *rx_pkt;
 struct EBPFRSSContext ebpf_rss;
+char *ebpf_rss_fds;
 };
 
 size_t virtio_net_handle_ctrl_iov(VirtIODevice *vdev,
-- 
2.39.1

[RFC PATCH 5/5] ebpf: Updated eBPF program and skeleton.

2023-03-29 Thread Andrew Melnychenko

Updated section name, so libbpf should init/gues proper
program type without specifications during open/load.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/rss.bpf.skeleton.h | 1469 ---
 tools/ebpf/rss.bpf.c|2 +-
 2 files changed, 741 insertions(+), 730 deletions(-)

diff --git a/ebpf/rss.bpf.skeleton.h b/ebpf/rss.bpf.skeleton.h
index 18eb2adb12..41b84aea44 100644
--- a/ebpf/rss.bpf.skeleton.h
+++ b/ebpf/rss.bpf.skeleton.h
@@ -176,162 +176,162 @@ err:
 
 static inline const void *rss_bpf__elf_bytes(size_t *sz)
 {
-   *sz = 20440;
+   *sz = 20720;
return (const void *)"\
 \x7f\x45\x4c\x46\x02\x01\x01\0\0\0\0\0\0\0\0\0\x01\0\xf7\0\x01\0\0\0\0\0\0\0\0\
-\0\0\0\0\0\0\0\0\0\0\0\x98\x4c\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0d\0\
-\x01\0\xbf\x19\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\x54\xff\0\0\0\0\xbf\xa7\
-\0\0\0\0\0\0\x07\x07\0\0\x54\xff\xff\xff\x18\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
+\0\0\0\0\0\0\0\0\0\0\0\xb0\x4d\0\0\0\0\0\0\0\0\0\0\x40\0\0\0\0\0\x40\0\x0d\0\
+\x01\0\xbf\x19\0\0\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\x4c\xff\0\0\0\0\xbf\xa7\
+\0\0\0\0\0\0\x07\x07\0\0\x4c\xff\xff\xff\x18\x01\0\0\0\0\0\0\0\0\0\0\0\0\0\0\
 \xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x06\0\0\0\0\0\0\x18\x01\0\0\0\0\0\
 \0\0\0\0\0\0\0\0\0\xbf\x72\0\0\0\0\0\0\x85\0\0\0\x01\0\0\0\xbf\x08\0\0\0\0\0\0\
-\x18\0\0\0\xff\xff\xff\xff\0\0\0\0\0\0\0\0\x15\x06\x67\x02\0\0\0\0\xbf\x87\0\0\
-\0\0\0\0\x15\x07\x65\x02\0\0\0\0\x71\x61\0\0\0\0\0\0\x55\x01\x01\0\0\0\0\0\x05\
-\0\x5e\x02\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xc8\xff\0\0\0\0\x7b\x1a\xc0\xff\
-\0\0\0\0\x7b\x1a\xb8\xff\0\0\0\0\x7b\x1a\xb0\xff\0\0\0\0\x7b\x1a\xa8\xff\0\0\0\
-\0\x63\x1a\xa0\xff\0\0\0\0\x7b\x1a\x98\xff\0\0\0\0\x7b\x1a\x90\xff\0\0\0\0\x7b\
-\x1a\x88\xff\0\0\0\0\x7b\x1a\x80\xff\0\0\0\0\x7b\x1a\x78\xff\0\0\0\0\x7b\x1a\
-\x70\xff\0\0\0\0\x7b\x1a\x68\xff\0\0\0\0\x7b\x1a\x60\xff\0\0\0\0\x7b\x1a\x58\
-\xff\0\0\0\0\x15\x09\x4d\x02\0\0\0\0\x6b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\
-\0\x07\x03\0\0\xd0\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x02\0\0\x0c\0\0\0\xb7\
+\x18\0\0\0\xff\xff\xff\xff\0\0\0\0\0\0\0\0\x15\x06\x64\x02\0\0\0\0\xbf\x87\0\0\
+\0\0\0\0\x15\x07\x62\x02\0\0\0\0\x71\x61\0\0\0\0\0\0\x55\x01\x01\0\0\0\0\0\x05\
+\0\x5b\x02\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xc0\xff\0\0\0\0\x7b\x1a\xb8\xff\
+\0\0\0\0\x7b\x1a\xb0\xff\0\0\0\0\x7b\x1a\xa8\xff\0\0\0\0\x7b\x1a\xa0\xff\0\0\0\
+\0\x63\x1a\x98\xff\0\0\0\0\x7b\x1a\x90\xff\0\0\0\0\x7b\x1a\x88\xff\0\0\0\0\x7b\
+\x1a\x80\xff\0\0\0\0\x7b\x1a\x78\xff\0\0\0\0\x7b\x1a\x70\xff\0\0\0\0\x7b\x1a\
+\x68\xff\0\0\0\0\x7b\x1a\x60\xff\0\0\0\0\x7b\x1a\x58\xff\0\0\0\0\x7b\x1a\x50\
+\xff\0\0\0\0\x15\x09\x4a\x02\0\0\0\0\x6b\x1a\xc8\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\
+\0\x07\x03\0\0\xc8\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x02\0\0\x0c\0\0\0\xb7\
 \x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\
-\x77\0\0\0\x20\0\0\0\x55\0\x42\x02\0\0\0\0\xb7\x02\0\0\x10\0\0\0\x69\xa1\xd0\
+\x77\0\0\0\x20\0\0\0\x55\0\x3f\x02\0\0\0\0\xb7\x02\0\0\x10\0\0\0\x69\xa1\xc8\
 \xff\0\0\0\0\xbf\x13\0\0\0\0\0\0\xdc\x03\0\0\x10\0\0\0\x15\x03\x02\0\0\x81\0\0\
 \x55\x03\x0b\0\xa8\x88\0\0\xb7\x02\0\0\x14\0\0\0\xbf\xa3\0\0\0\0\0\0\x07\x03\0\
-\0\xd0\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\
-\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\x77\0\0\0\x20\0\0\0\x55\0\x32\x02\0\
-\0\0\0\x69\xa1\xd0\xff\0\0\0\0\x15\x01\x30\x02\0\0\0\0\x7b\x7a\x38\xff\0\0\0\0\
-\x7b\x9a\x40\xff\0\0\0\0\x15\x01\x55\0\x86\xdd\0\0\x55\x01\x39\0\x08\0\0\0\xb7\
-\x07\0\0\x01\0\0\0\x73\x7a\x58\xff\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xe0\xff\
-\0\0\0\0\x7b\x1a\xd8\xff\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\0\
-\x07\x03\0\0\xd0\xff\xff\xff\x79\xa1\x40\xff\0\0\0\0\xb7\x02\0\0\0\0\0\0\xb7\
+\0\xc8\xff\xff\xff\xbf\x91\0\0\0\0\0\0\xb7\x04\0\0\x02\0\0\0\xb7\x05\0\0\0\0\0\
+\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\0\x77\0\0\0\x20\0\0\0\x55\0\x2f\x02\0\
+\0\0\0\x69\xa1\xc8\xff\0\0\0\0\x15\x01\x2d\x02\0\0\0\0\x7b\x7a\x30\xff\0\0\0\0\
+\x7b\x9a\x38\xff\0\0\0\0\x15\x01\x55\0\x86\xdd\0\0\x55\x01\x39\0\x08\0\0\0\xb7\
+\x07\0\0\x01\0\0\0\x73\x7a\x50\xff\0\0\0\0\xb7\x01\0\0\0\0\0\0\x63\x1a\xd8\xff\
+\0\0\0\0\x7b\x1a\xd0\xff\0\0\0\0\x7b\x1a\xc8\xff\0\0\0\0\xbf\xa3\0\0\0\0\0\0\
+\x07\x03\0\0\xc8\xff\xff\xff\x79\xa1\x38\xff\0\0\0\0\xb7\x02\0\0\0\0\0\0\xb7\
 \x04\0\0\x14\0\0\0\xb7\x05\0\0\x01\0\0\0\x85\0\0\0\x44\0\0\0\x67\0\0\0\x20\0\0\
-\0\x77\0\0\0\x20\0\0\0\x55\0\x1c\x02\0\0\0\0\x69\xa1\xd6\xff\0\0\0\0\x55\x01\
-\x01\0\0\0\0\0\xb7\x07\0\0\0\0\0\0\x61\xa1\xdc\xff\0\0\0\0\x63\x1a\x64\xff\0\0\
-\0\0\x61\xa1\xe0\xff\0\0\0\0\x63\x1a\x68\xff\0\0\0\0\x71\xa9\xd9\xff\0\0\0\0\
-\x73\x7a\x5e\xff\0\0\0\0\x71\xa1\xd0\xff\0\0\0\0\x67\x01\0\0\x02\0\0\0\x57\x01\
-\0\0\x3c\0\0\0\x7b\x1a\x48\xff\0\0\0\0\xbf\x91\0\0\0\0\0\0\x57\x01\0\0\xff\0\0\
+\0\x77\0\0\0\x20\0\0\0\x55\0\x19\x02\0\0\0\0\x69\xa1\xce\xff\0\0\0\0\x55\x01\
+\x01\0\0\0\0\0\xb7\x07\0\0\0\0\0\0\x61\xa1\xd4\xff\0\0\0\0\x63\x1a\x5c\xff\0\0\
+\0\0\x61\xa1\xd8\xf

[RFC PATCH 4/5] qmp: Added new command to retrieve eBPF blob.

2023-03-29 Thread Andrew Melnychenko

Added command "request-ebpf". This command returns
eBPF program encoded base64. The program taken from the
skeleton and essentially is an ELF object that can be
loaded in the future with libbpf.

Signed-off-by: Andrew Melnychenko 
---
 monitor/qmp-cmds.c | 17 +
 qapi/misc.json | 25 +
 2 files changed, 42 insertions(+)

diff --git a/monitor/qmp-cmds.c b/monitor/qmp-cmds.c
index b0f948d337..8f2fc3e7ec 100644
--- a/monitor/qmp-cmds.c
+++ b/monitor/qmp-cmds.c
@@ -32,6 +32,7 @@
 #include "hw/mem/memory-device.h"
 #include "hw/intc/intc.h"
 #include "hw/rdma/rdma.h"
+#include "ebpf/ebpf.h"
 
 NameInfo *qmp_query_name(Error **errp)
 {
@@ -209,3 +210,19 @@ static void __attribute__((__constructor__)) 
monitor_init_qmp_commands(void)
  qmp_marshal_qmp_capabilities,
  QCO_ALLOW_PRECONFIG, 0);
 }
+
+EbpfObject *qmp_request_ebpf(const char *id, Error **errp)
+{
+EbpfObject *ret = NULL;
+size_t size = 0;
+const guchar *data = ebpf_find_binary_by_id(id, );
+
+if (data) {
+ret = g_new0(EbpfObject, 1);
+ret->object = g_base64_encode(data, size);
+} else {
+error_setg(errp, "can't find eBPF object with id: %s", id);
+}
+
+return ret;
+}
diff --git a/qapi/misc.json b/qapi/misc.json
index 6ddd16ea28..4689802460 100644
--- a/qapi/misc.json
+++ b/qapi/misc.json
@@ -618,3 +618,28 @@
 { 'event': 'VFU_CLIENT_HANGUP',
   'data': { 'vfu-id': 'str', 'vfu-qom-path': 'str',
 'dev-id': 'str', 'dev-qom-path': 'str' } }
+
+##
+# @EbpfObject:
+#
+# Structure that holds eBPF ELF object encoded in base64.
+##
+{ 'struct': 'EbpfObject',
+  'data': {'object': 'str'} }
+
+##
+# @request-ebpf:
+#
+# Function returns eBPF object that can be loaded with libbpf.
+# Management applications (g.e. libvirt) may load it and pass file
+# descriptors to QEMU. Which allows running QEMU without BPF capabilities.
+#
+# Returns: RSS eBPF object encoded in base64.
+#
+# Since: 7.3
+#
+##
+{ 'command': 'request-ebpf',
+  'data': { 'id': 'str' },
+  'returns': 'EbpfObject' }
+
-- 
2.39.1

[RFC PATCH 1/5] ebpf: Added eBPF initialization by fds and map update.

2023-03-29 Thread Andrew Melnychenko

Changed eBPF map updates through mmaped array.
Mmaped arrays provide direct access to map data.
It should omit using bpf_map_update_elem() call,
which may require capabilities that are not present.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf_rss-stub.c |   6 +++
 ebpf/ebpf_rss.c  | 120 ++-
 ebpf/ebpf_rss.h  |  10 
 3 files changed, 113 insertions(+), 23 deletions(-)

diff --git a/ebpf/ebpf_rss-stub.c b/ebpf/ebpf_rss-stub.c
index e71e229190..8d7fae2ad9 100644
--- a/ebpf/ebpf_rss-stub.c
+++ b/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)
 {
diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index cee658c158..08015fecb1 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -27,19 +27,68 @@ void ebpf_rss_init(struct EBPFRSSContext *ctx)
 {
 if (ctx != NULL) {
 ctx->obj = NULL;
+ctx->program_fd = -1;
 }
 }
 
 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());
+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());
 }
 
 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;
 }
 
@@ -66,26 +115,51 @@ 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;
 
 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;
 }
-if (bpf_map_update_elem(ctx->map_configuration,
-_key, config, 0) < 0) {
+
+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;
 return false;
 }
+
+return true;
+}
+
+static bool ebpf_rss_set_config(struct EBPFRSSContext *ctx,
+str

[RFC PATCH 0/4] eBPF RSS through QMP support.

2023-03-29 Thread Andrew Melnychenko

This series of patches provides the ability to retrieve eBPF program
through qmp, so management application may load bpf blob with proper 
capabilities.
Now, virtio-net devices can accept eBPF programs and maps through properties
as external file descriptors. Access to the eBPF map is direct through mmap()
call, so it should not require additional capabilities to bpf* calls.
eBPF file descriptors can be passed to QEMU from parent process or by unix
socket with sendfd() qmp command.

Overall, the basic scenario of using the helper looks like this:
 * Libvirt checks for ebpf_fds property.
 * Libvirt requests eBPF blob through QMP.
 * Libvirt loads blob for virtio-net.
 * Libvirt launches the QEMU with eBPF fds passed.
 
Andrew Melnychenko (4):
  ebpf: Added eBPF initialization by fds and map update.
  virtio-net: Added property to load eBPF RSS with fds.
  ebpf: Added declaration/initialization routines.
  qmp: Added new command to retrieve eBPF blob.

 ebpf/ebpf.c|  48 +
 ebpf/ebpf.h|  25 +++
 ebpf/ebpf_rss-stub.c   |   6 ++
 ebpf/ebpf_rss.c| 124 +++--
 ebpf/ebpf_rss.h|  10 +++
 ebpf/meson.build   |   1 +
 hw/net/virtio-net.c|  77 ++--
 include/hw/virtio/virtio-net.h |   1 +
 monitor/qmp-cmds.c |  17 +
 qapi/misc.json |  25 +++
 10 files changed, 307 insertions(+), 27 deletions(-)
 create mode 100644 ebpf/ebpf.c
 create mode 100644 ebpf/ebpf.h

-- 
2.39.1

[PATCH 2/5] virtio-net: Added property to load eBPF RSS with fds.

2023-02-19 Thread Andrew Melnychenko

eBPF RSS program and maps may now be passed during initialization.
Initially was implemented for libvirt to launch qemu without permissions,
and initialized eBPF program through the helper.

Signed-off-by: Andrew Melnychenko 
---
 hw/net/virtio-net.c| 77 --
 include/hw/virtio/virtio-net.h |  1 +
 2 files changed, 74 insertions(+), 4 deletions(-)

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 3ae909041a..0ab2cf33f9 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -42,6 +42,7 @@
 #include "sysemu/sysemu.h"
 #include "trace.h"
 #include "monitor/qdev.h"
+#include "monitor/monitor.h"
 #include "hw/pci/pci_device.h"
 #include "net_rx_pkt.h"
 #include "hw/virtio/vhost.h"
@@ -1290,14 +1291,81 @@ static void virtio_net_detach_epbf_rss(VirtIONet *n)
 virtio_net_attach_ebpf_to_backend(n->nic, -1);
 }
 
-static bool virtio_net_load_ebpf(VirtIONet *n)
+static int virtio_net_get_ebpf_rss_fds(char *str, char *fds[], int nfds)
+{
+char *ptr = str;
+char *cur = NULL;
+size_t len = strlen(str);
+int i = 0;
+
+for (; i < nfds && ptr < str + len;) {
+cur = strchr(ptr, ':');
+
+if (cur == NULL) {
+fds[i] = g_strdup(ptr);
+} else {
+fds[i] = g_strndup(ptr, cur - ptr);
+}
+
+i++;
+if (cur == NULL) {
+break;
+} else {
+ptr = cur + 1;
+}
+}
+
+return i;
+}
+
+static bool virtio_net_load_ebpf_fds(VirtIONet *n)
 {
-if (!virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
-/* backend does't support steering ebpf */
+char *fds_strs[EBPF_RSS_MAX_FDS];
+int fds[EBPF_RSS_MAX_FDS];
+int nfds;
+int ret = false;
+Error *errp;
+int i = 0;
+
+if (n == NULL || !n->ebpf_rss_fds) {
 return false;
 }
 
-return ebpf_rss_load(>ebpf_rss);
+nfds = virtio_net_get_ebpf_rss_fds(n->ebpf_rss_fds,
+   fds_strs, EBPF_RSS_MAX_FDS);
+for (i = 0; i < nfds; i++) {
+fds[i] = monitor_fd_param(monitor_cur(), fds_strs[i], );
+}
+
+if (nfds == EBPF_RSS_MAX_FDS) {
+ret = ebpf_rss_load_fds(>ebpf_rss, fds[0], fds[1], fds[2], fds[3]);
+}
+
+if (!ret) {
+for (i = 0; i < nfds; i++) {
+close(fds[i]);
+}
+}
+
+for (i = 0; i < nfds; i++) {
+g_free(fds_strs[i]);
+}
+
+return ret;
+}
+
+static bool virtio_net_load_ebpf(VirtIONet *n)
+{
+bool ret = true;
+
+if (virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
+if (!(n->ebpf_rss_fds
+&& virtio_net_load_ebpf_fds(n))) {
+ret = ebpf_rss_load(>ebpf_rss);
+}
+}
+
+return ret;
 }
 
 static void virtio_net_unload_ebpf(VirtIONet *n)
@@ -3868,6 +3936,7 @@ static Property virtio_net_properties[] = {
 VIRTIO_NET_F_RSS, false),
 DEFINE_PROP_BIT64("hash", VirtIONet, host_features,
 VIRTIO_NET_F_HASH_REPORT, false),
+DEFINE_PROP_STRING("ebpf_rss_fds", VirtIONet, ebpf_rss_fds),
 DEFINE_PROP_BIT64("guest_rsc_ext", VirtIONet, host_features,
 VIRTIO_NET_F_RSC_EXT, false),
 DEFINE_PROP_UINT32("rsc_interval", VirtIONet, rsc_timeout,
diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h
index ef234ffe7e..e10ce88f91 100644
--- a/include/hw/virtio/virtio-net.h
+++ b/include/hw/virtio/virtio-net.h
@@ -219,6 +219,7 @@ struct VirtIONet {
 VirtioNetRssData rss_data;
 struct NetRxPkt *rx_pkt;
 struct EBPFRSSContext ebpf_rss;
+char *ebpf_rss_fds;
 };
 
 size_t virtio_net_handle_ctrl_iov(VirtIODevice *vdev,
-- 
2.39.1

[PATCH 1/5] ebpf: Added eBPF initialization by fds and map update.

2023-02-19 Thread Andrew Melnychenko

Changed eBPF map updates through mmaped array.
Mmaped arrays provide direct access to map data.
It should omit using bpf_map_update_elem() call,
which may require capabilities that are not present.
Also, eBPF RSS context may be initialized by file descriptors.
virtio-net may provide fds passed by libvirt.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf_rss-stub.c |   6 +++
 ebpf/ebpf_rss.c  | 120 ++-
 ebpf/ebpf_rss.h  |  10 
 3 files changed, 113 insertions(+), 23 deletions(-)

diff --git a/ebpf/ebpf_rss-stub.c b/ebpf/ebpf_rss-stub.c
index e71e229190..8d7fae2ad9 100644
--- a/ebpf/ebpf_rss-stub.c
+++ b/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)
 {
diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index cee658c158..08015fecb1 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -27,19 +27,68 @@ void ebpf_rss_init(struct EBPFRSSContext *ctx)
 {
 if (ctx != NULL) {
 ctx->obj = NULL;
+ctx->program_fd = -1;
 }
 }
 
 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());
+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());
 }
 
 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;
 }
 
@@ -66,26 +115,51 @@ 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;
 
 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;
 }
-if (bpf_map_update_elem(ctx->map_configuration,
-_key, config, 0) < 0) {
+
+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;
 return false;
 }
+
+

[PATCH 5/5] qmp: Added find-ebpf-rss-helper command.

2023-02-19 Thread Andrew Melnychenko

New qmp command to query ebpf helper.
It's crucial that QEMU and helper are in sync.
Technically helper should pass eBPF fds that QEMU may accept.
And different QEMU's builds may have different eBPF programs.
QEMU returns helper that should "fit" to virtio-net.
QEMU would check the stamp of the helper to make sure
that eBPF program is valid.

Signed-off-by: Andrew Melnychenko 
---
 monitor/qmp-cmds.c | 28 
 qapi/misc.json | 42 ++
 2 files changed, 70 insertions(+)

diff --git a/monitor/qmp-cmds.c b/monitor/qmp-cmds.c
index 859012aef4..2f91c34bbb 100644
--- a/monitor/qmp-cmds.c
+++ b/monitor/qmp-cmds.c
@@ -31,6 +31,7 @@
 #include "hw/mem/memory-device.h"
 #include "hw/intc/intc.h"
 #include "hw/rdma/rdma.h"
+#include "qemu-ebpf-rss-helper-stamp-utils.h"
 
 NameInfo *qmp_query_name(Error **errp)
 {
@@ -202,3 +203,30 @@ static void __attribute__((__constructor__)) 
monitor_init_qmp_commands(void)
  qmp_marshal_qmp_capabilities,
  QCO_ALLOW_PRECONFIG, 0);
 }
+
+HelperPath *qmp_find_ebpf_rss_helper(bool has_path,
+ strList *path, Error **errp)
+{
+HelperPath *ret = NULL;
+char *helperbin = NULL;
+
+/* Look for helper in the suggested pathes */
+if (has_path) {
+strList *str_list = NULL;
+for (str_list = path;
+ str_list && !helperbin;
+ str_list = str_list->next) {
+helperbin = qemu_check_suggested_ebpf_rss_helper(str_list->value);
+}
+}
+
+if (helperbin == NULL) {
+helperbin = qemu_find_default_ebpf_rss_helper();
+}
+
+if (helperbin) {
+ret = g_new0(HelperPath, 1);
+ret->path = helperbin;
+}
+return ret;
+}
diff --git a/qapi/misc.json b/qapi/misc.json
index 27ef5a2b20..1dfb3c132e 100644
--- a/qapi/misc.json
+++ b/qapi/misc.json
@@ -584,3 +584,45 @@
 { 'event': 'VFU_CLIENT_HANGUP',
   'data': { 'vfu-id': 'str', 'vfu-qom-path': 'str',
 'dev-id': 'str', 'dev-qom-path': 'str' } }
+
+##
+# @HelperPath:
+#
+# Name of the helper and binary location.
+##
+{ 'struct': 'HelperPath',
+  'data': {'path': 'str'} }
+
+##
+# @find-ebpf-rss-helper:
+#
+# Query helper paths to find qemu-ebpf-rss-helper.
+# The qemu would check "the stamp" and
+# returns the proper helper.
+# It's possible to provide paths where to look for a helper.
+# If the path is provided to a file - qemu would check the file for the stamp.
+# If the path is provided to a directory - qemu would look for
+# a file "qemu-ebpf-rss-helper" and check its stamp.
+#
+# Returns: path to the helper with a valid stamp.
+#
+# Note: Provided path arguments have the highest priority where to look
+#   for a helper. Then, default "helper directory" and then
+#   near the qemu binary.
+#
+# Since: 7.2
+#
+# Example:
+#
+# -> { "execute": "find-ebpf-rss-helper", "arguments": { "path": 
"/opt/qemu_helpers/" } }
+# <- { "return": [
+#{
+#  "path": "/usr/local/libexec/qemu-ebpf-rss-helper"
+#}
+#  ]
+#}
+#
+##
+{ 'command': 'find-ebpf-rss-helper',
+  'data': {'*path': ['str']},
+  'returns': 'HelperPath' }
-- 
2.39.1

[PATCH 0/5] eBPF RSS Helper support.

2023-02-19 Thread Andrew Melnychenko

This series of patches provides the ability to initialize eBPF RSS steering
with the helper.
Now, virtio-net devices can accept eBPF programs and maps through properties
as external file descriptors. Access to the eBPF map is direct through mmap()
call, so it should not require additional capabilities to bpf* calls.
eBPF file descriptors can be passed to QEMU from parent process or by unix
socket with sendfd() qmp command.
The helper is provided that would load eBPF RSS program/maps and pass fd to
the called process(in future - Libvirtd) through unix socket.
Because of structures stored in the maps, it's crucial that the helper provides 
a proper eBPF program. That's why the stamp was added to the helper and
QEMU may check the binary. Also, additional qmp command was added for checking
the stamp.
Overall, the basic scenario of using the helper looks like this:
 * Libvirt checks for ebpf_fds property.
 * Libvirt ask QEMU for the proper helper(where is located and proper stamp)
 * Libvirt calls the helper with BPF capabilities and retrieves fds.
 * Libvirt launches the QEMU with eBPF fds passed.

Changes since RFC:
 * refactored/rebased code.
 * changed qmp command.
 * refactored helper.
 
Andrew Melnychenko (5):
  ebpf: Added eBPF initialization by fds and map update.
  virtio-net: Added property to load eBPF RSS with fds.
  qmp: Added the helper stamp check.
  ebpf_rss_helper: Added helper for eBPF RSS.
  qmp: Added find-ebpf-rss-helper command.

 ebpf/ebpf_rss-stub.c   |   6 +
 ebpf/ebpf_rss.c| 120 ++--
 ebpf/ebpf_rss.h|  10 +
 ebpf/qemu-ebpf-rss-helper.c| 132 +
 hw/net/virtio-net.c|  77 -
 include/hw/virtio/virtio-net.h |   1 +
 meson.build|  47 ++-
 monitor/meson.build|   1 +
 monitor/qemu-ebpf-rss-helper-stamp-utils.c | 322 +
 monitor/qemu-ebpf-rss-helper-stamp-utils.h |  39 +++
 monitor/qmp-cmds.c |  28 ++
 qapi/misc.json |  42 +++
 12 files changed, 785 insertions(+), 40 deletions(-)
 create mode 100644 ebpf/qemu-ebpf-rss-helper.c
 create mode 100644 monitor/qemu-ebpf-rss-helper-stamp-utils.c
 create mode 100644 monitor/qemu-ebpf-rss-helper-stamp-utils.h

-- 
2.39.1

[PATCH 3/5] qmp: Added the helper stamp check.

2023-02-19 Thread Andrew Melnychenko

Added a function to check the stamp in the helper.
eBPF helper should have a special symbol that generates during the build.
QEMU checks the helper and determines that it fits, so the helper
will produce proper output.

Signed-off-by: Andrew Melnychenko 
---
 meson.build|  10 +
 monitor/meson.build|   1 +
 monitor/qemu-ebpf-rss-helper-stamp-utils.c | 322 +
 monitor/qemu-ebpf-rss-helper-stamp-utils.h |  39 +++
 4 files changed, 372 insertions(+)
 create mode 100644 monitor/qemu-ebpf-rss-helper-stamp-utils.c
 create mode 100644 monitor/qemu-ebpf-rss-helper-stamp-utils.h

diff --git a/meson.build b/meson.build
index a76c855312..b409912aed 100644
--- a/meson.build
+++ b/meson.build
@@ -2868,6 +2868,16 @@ foreach d : hx_headers
 endforeach
 genh += hxdep
 
+ebpf_rss_helper_stamp = custom_target(
+'qemu-ebpf-rss-helper-stamp.h',
+output : 'qemu-ebpf-rss-helper-stamp.h',
+input : 'ebpf/rss.bpf.skeleton.h',
+command : [python, '-c', 'import hashlib; print(\'#define 
QEMU_EBPF_RSS_HELPER_STAMP 
qemuEbpfRssHelperStamp_{}\'.format(hashlib.sha1(open(\'@INPUT@\', 
\'rb\').read()).hexdigest()))'],
+capture: true,
+)
+
+genh += ebpf_rss_helper_stamp
+
 ###
 # Collect sources #
 ###
diff --git a/monitor/meson.build b/monitor/meson.build
index ccb4d1a8e6..36de73414b 100644
--- a/monitor/meson.build
+++ b/monitor/meson.build
@@ -6,6 +6,7 @@ softmmu_ss.add(files(
   'hmp.c',
 ))
 softmmu_ss.add([spice_headers, files('qmp-cmds.c')])
+softmmu_ss.add(files('qemu-ebpf-rss-helper-stamp-utils.c'))
 
 specific_ss.add(when: 'CONFIG_SOFTMMU',
if_true: [files( 'hmp-cmds-target.c', 'hmp-target.c'), spice])
diff --git a/monitor/qemu-ebpf-rss-helper-stamp-utils.c 
b/monitor/qemu-ebpf-rss-helper-stamp-utils.c
new file mode 100644
index 00..23efc36ef0
--- /dev/null
+++ b/monitor/qemu-ebpf-rss-helper-stamp-utils.c
@@ -0,0 +1,322 @@
+/*
+ * QEMU helper stamp check utils.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ * Description: This file mostly implements helper stamp checking.
+ *  The stamp is implemented in a similar way as in qemu modules.
+ *  The helper should contain a specific symbol.
+ *  Not in a similar way is symbol checking - here we parse
+ *  the ELF file. For now, only eBPF helper contains
+ *  the stamp, and the stamp is generated from
+ *  sha1 ebpf/rss.bpf.skeleton.h (see meson.build).
+ */
+
+#include "qemu/osdep.h"
+#include "elf.h"
+#include "qemu-ebpf-rss-helper-stamp-utils.h"
+
+#include 
+
+#ifdef CONFIG_LINUX
+
+static void *file_allocate_and_read(int fd, off_t off, size_t size)
+{
+void *data;
+int err;
+
+if (fd < 0) {
+return NULL;
+}
+
+err = lseek(fd, off, SEEK_SET);
+if (err < 0) {
+return NULL;
+}
+
+data = g_new0(char, size);
+if (data == NULL) {
+return NULL;
+}
+
+err = read(fd, data, size);
+if (err < 0) {
+g_free(data);
+return NULL;
+}
+
+return data;
+}
+
+static Elf64_Shdr *elf64_get_section_table(int fd, Elf64_Ehdr *elf_header)
+{
+if (elf_header == NULL) {
+return NULL;
+}
+return (Elf64_Shdr *)file_allocate_and_read(fd, elf_header->e_shoff,
+ elf_header->e_shnum * elf_header->e_shentsize);
+}
+
+static Elf32_Shdr *elf32_get_section_table(int fd, Elf32_Ehdr *elf_header)
+{
+if (elf_header == NULL) {
+return NULL;
+}
+return (Elf32_Shdr *)file_allocate_and_read(fd, elf_header->e_shoff,
+ elf_header->e_shnum * elf_header->e_shentsize);
+}
+
+static void *elf64_get_section_data(int fd, const Elf64_Shdr* section_header)
+{
+if (fd < 0 || section_header == NULL) {
+return NULL;
+}
+return file_allocate_and_read(fd, section_header->sh_offset,
+  section_header->sh_size);
+}
+
+static void *elf32_get_section_data(int fd, const Elf32_Shdr* section_header)
+{
+if (fd < 0 || section_header == NULL) {
+return NULL;
+}
+return file_allocate_and_read(fd, section_header->sh_offset,
+  section_header->sh_size);
+}
+
+static bool elf64_check_symbol_in_symbol_table(int fd,
+   Elf64_Shdr *section_table,
+   Elf64_Shdr *symbol_section,
+   const char *symbol)
+{
+Elf64_Sym *symbol_table;
+char *string_table;
+uint32_t i;
+bool ret = false;
+
+symbol_table = (Elf64_Sym *) elf64_get_section

[PATCH 4/5] ebpf_rss_helper: Added helper for eBPF RSS.

2023-02-19 Thread Andrew Melnychenko

Helper program. Loads eBPF RSS program and maps and passes them through unix 
socket.
Libvirt may launch this helper and pass eBPF fds to qemu virtio-net.
Also, libbpf dependency for now is exclusively for Linux.
Libbpf is used for eBPF RSS steering, which is supported only by Linux TAP.
There is no reason yet to build eBPF loader and helper for non-Linux systems,
even if libbpf is present.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/qemu-ebpf-rss-helper.c | 132 
 meson.build |  37 ++
 2 files changed, 156 insertions(+), 13 deletions(-)
 create mode 100644 ebpf/qemu-ebpf-rss-helper.c

diff --git a/ebpf/qemu-ebpf-rss-helper.c b/ebpf/qemu-ebpf-rss-helper.c
new file mode 100644
index 00..348d26bcdd
--- /dev/null
+++ b/ebpf/qemu-ebpf-rss-helper.c
@@ -0,0 +1,132 @@
+/*
+ * eBPF RSS Helper
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ * Description: This is helper program for libvirtd.
+ *  It loads eBPF RSS program and passes fds through unix socket.
+ *  Built by meson, target - 'qemu-ebpf-rss-helper'.
+ */
+
+#include 
+#include 
+#include 
+#include 
+#include 
+#include 
+#include 
+#include 
+
+#include "ebpf_rss.h"
+
+#include "qemu-ebpf-rss-helper-stamp.h"
+
+void QEMU_EBPF_RSS_HELPER_STAMP(void) {}
+
+static int send_fds(int socket, int *fds, int n)
+{
+struct msghdr msg = {};
+struct cmsghdr *cmsg = NULL;
+char buf[CMSG_SPACE(n * sizeof(int))];
+char dummy_buffer = 0;
+struct iovec io = { .iov_base = _buffer,
+.iov_len = sizeof(dummy_buffer) };
+
+memset(buf, 0, sizeof(buf));
+
+msg.msg_iov = 
+msg.msg_iovlen = 1;
+msg.msg_control = buf;
+msg.msg_controllen = sizeof(buf);
+
+cmsg = CMSG_FIRSTHDR();
+cmsg->cmsg_level = SOL_SOCKET;
+cmsg->cmsg_type = SCM_RIGHTS;
+cmsg->cmsg_len = CMSG_LEN(n * sizeof(int));
+
+memcpy(CMSG_DATA(cmsg), fds, n * sizeof(int));
+
+return sendmsg(socket, , 0);
+}
+
+static void print_help_and_exit(const char *prog, int exitcode)
+{
+fprintf(stderr, "%s - load eBPF RSS program for qemu and pass eBPF fds"
+" through unix socket.\n", prog);
+fprintf(stderr, "\t--fd , -f  - unix socket file descriptor"
+" used to pass eBPF fds.\n");
+fprintf(stderr, "\t--help, -h - this help.\n");
+exit(exitcode);
+}
+
+int main(int argc, char **argv)
+{
+char *fd_string = NULL;
+int unix_fd = 0;
+struct EBPFRSSContext ctx = {};
+int fds[EBPF_RSS_MAX_FDS] = {};
+int ret = -1;
+
+for (;;) {
+int c;
+static struct option long_options[] = {
+{"help",  no_argument, 0, 'h'},
+{"fd",  required_argument, 0, 'f'},
+{0, 0, 0, 0}
+};
+c = getopt_long(argc, argv, "hf:",
+long_options, NULL);
+
+if (c == -1) {
+break;
+}
+
+switch (c) {
+case 'f':
+fd_string = optarg;
+break;
+case 'h':
+default:
+print_help_and_exit(argv[0],
+c == 'h' ? EXIT_SUCCESS : EXIT_FAILURE);
+}
+}
+
+if (!fd_string) {
+fprintf(stderr, "Unix file descriptor not present.\n");
+print_help_and_exit(argv[0], EXIT_FAILURE);
+}
+
+unix_fd = atoi(fd_string);
+
+if (!unix_fd) {
+fprintf(stderr, "Unix file descriptor is invalid.\n");
+return EXIT_FAILURE;
+}
+
+ebpf_rss_init();
+if (!ebpf_rss_load()) {
+fprintf(stderr, "Can't load ebpf.\n");
+return EXIT_FAILURE;
+}
+fds[0] = ctx.program_fd;
+fds[1] = ctx.map_configuration;
+fds[2] = ctx.map_toeplitz_key;
+fds[3] = ctx.map_indirections_table;
+
+ret = send_fds(unix_fd, fds, EBPF_RSS_MAX_FDS);
+if (ret < 0) {
+fprintf(stderr, "Issue while sending fds: %s.\n", strerror(errno));
+}
+
+ebpf_rss_unload();
+
+return ret < 0 ? EXIT_FAILURE : EXIT_SUCCESS;
+}
+
diff --git a/meson.build b/meson.build
index b409912aed..6e6e2f3e40 100644
--- a/meson.build
+++ b/meson.build
@@ -1632,19 +1632,22 @@ elif get_option('vduse_blk_export').disabled()
 endif
 
 # libbpf
-libbpf = dependency('libbpf', required: get_option('bpf'), method: 
'pkg-config')
-if libbpf.found() and not cc.links('''
-   #include 
-   int main(void)
-   {
- bpf_object__destroy_skeleton(NULL);
- return 0;
-   }''', dependencies: libbpf)
-  libbpf = not_found
-  if get_option('bpf').enabled()
-error('libbpf skeleton test failed')
-  else
-warning('libbpf skeleton test failed, disabling')
+libbpf = n

[PATCH] e1000e: Added ICR clearing by corresponding IMS bit.

2021-08-18 Thread Andrew Melnychenko

Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=1707441

The issue is in LSC clearing. So, after "link up"(during initialization),
the next LSC event is masked and can't be processed.
Technically, the event should be 'cleared' during ICR read.
On Windows guest, everything works well, mostly because of
different interrupt routines(ICR clears during register write).
So, added ICR clearing during reading, according to the note by
section 13.3.27 of the 8257X developers manual.

Signed-off-by: Andrew Melnychenko 
---
 hw/net/e1000e_core.c | 10 ++
 hw/net/trace-events  |  1 +
 2 files changed, 11 insertions(+)

diff --git a/hw/net/e1000e_core.c b/hw/net/e1000e_core.c
index b75f2ab8fc..288897a975 100644
--- a/hw/net/e1000e_core.c
+++ b/hw/net/e1000e_core.c
@@ -2617,6 +2617,16 @@ e1000e_mac_icr_read(E1000ECore *core, int index)
 e1000e_clear_ims_bits(core, core->mac[IAM]);
 }
 
+/*
+ * PCIe* GbE Controllers Open Source Software Developer's Manual
+ * 13.3.27 Interrupt Cause Read Register
+ */
+if ((core->mac[ICR] & E1000_ICR_ASSERTED) &&
+(core->mac[ICR] & core->mac[IMS])) {
+trace_e1000e_irq_icr_clear_icr_bit_ims(core->mac[ICR], core->mac[IMS]);
+core->mac[ICR] = 0;
+}
+
 trace_e1000e_irq_icr_read_exit(core->mac[ICR]);
 e1000e_update_interrupt_state(core);
 return ret;
diff --git a/hw/net/trace-events b/hw/net/trace-events
index c28b91ee1a..15fd09aa1c 100644
--- a/hw/net/trace-events
+++ b/hw/net/trace-events
@@ -225,6 +225,7 @@ e1000e_irq_icr_read_entry(uint32_t icr) "Starting ICR read. 
Current ICR: 0x%x"
 e1000e_irq_icr_read_exit(uint32_t icr) "Ending ICR read. Current ICR: 0x%x"
 e1000e_irq_icr_clear_zero_ims(void) "Clearing ICR on read due to zero IMS"
 e1000e_irq_icr_clear_iame(void) "Clearing ICR on read due to IAME"
+e1000e_irq_icr_clear_icr_bit_ims(uint32_t icr, uint32_t ims) "Clearing ICR on 
read due corresponding IMS bit: 0x%x & 0x%x"
 e1000e_irq_iam_clear_eiame(uint32_t iam, uint32_t cause) "Clearing IMS due to 
EIAME, IAM: 0x%X, cause: 0x%X"
 e1000e_irq_icr_clear_eiac(uint32_t icr, uint32_t eiac) "Clearing ICR bits due 
to EIAC, ICR: 0x%X, EIAC: 0x%X"
 e1000e_irq_ims_clear_set_imc(uint32_t val) "Clearing IMS bits due to IMC write 
0x%x"
-- 
2.31.1

[PATCH 1/5] ebpf: Added eBPF initialization by fds and map update.

2021-07-13 Thread Andrew Melnychenko

RSS maps are combined into one array map.
Changed eBPF map updates through mmaped array.
eBPF RSS context may be initialized by program fd and map fd.
virtio-net may provide fds passed by libvirt.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf_rss-stub.c|   6 +
 ebpf/ebpf_rss.c | 120 +
 ebpf/ebpf_rss.h |   8 +-
 ebpf/rss.bpf.skeleton.h | 557 +++-
 tools/ebpf/rss.bpf.c|  67 ++---
 5 files changed, 365 insertions(+), 393 deletions(-)

diff --git a/ebpf/ebpf_rss-stub.c b/ebpf/ebpf_rss-stub.c
index e71e229190..8d7fae2ad9 100644
--- a/ebpf/ebpf_rss-stub.c
+++ b/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)
 {
diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index 118c68da83..bfed0b446e 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -27,19 +27,21 @@ void ebpf_rss_init(struct EBPFRSSContext *ctx)
 {
 if (ctx != NULL) {
 ctx->obj = NULL;
+ctx->program_fd = -1;
+ctx->mmap_configuration = 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);
 }
 
 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;
 }
 
@@ -61,72 +63,43 @@ bool ebpf_rss_load(struct EBPFRSSContext *ctx)
 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);
+
+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");
+goto error;
+}
 
 return true;
 error:
 rss_bpf__destroy(rss_bpf_ctx);
 ctx->obj = NULL;
+ctx->program_fd = -1;
+ctx->mmap_configuration = NULL;
 
 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 (!ebpf_rss_is_loaded(ctx)) {
+if (ctx == NULL || ebpf_rss_is_loaded(ctx)) {
 return false;
 }
-if (bpf_map_update_elem(ctx->map_configuration,
-_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;
+ctx->program_fd = program_fd;
+ctx->map_configuration = config_fd;
 
-if (!ebpf_rss_is_loaded(ctx) || indirections_table == NULL ||
-   len > VIRTIO_NET_RSS_MAX_TABLE_LEN) {
+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;
 }
 
-for (; i < len; ++i) {
-if (bpf_map_update_elem(ctx->map_indirections_table, ,
-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, _key

[PATCH 5/5] qmp: Added qemu-ebpf-rss-path command.

2021-07-13 Thread Andrew Melnychenko

New qmp command to query ebpf helper.
It's crucial that qemu and helper are in sync and in touch.
Technically helper should pass eBPF fds that qemu may accept.
And different qemu's builds may have different eBPF programs and helpers.
Qemu returns helper that should "fit" to virtio-net.

Signed-off-by: Andrew Melnychenko 
---
 monitor/qmp-cmds.c | 32 
 qapi/misc.json | 33 +
 2 files changed, 65 insertions(+)

diff --git a/monitor/qmp-cmds.c b/monitor/qmp-cmds.c
index f7d64a6457..c042ab5466 100644
--- a/monitor/qmp-cmds.c
+++ b/monitor/qmp-cmds.c
@@ -40,6 +40,7 @@
 #include "qapi/qmp/qerror.h"
 #include "hw/mem/memory-device.h"
 #include "hw/acpi/acpi_dev_interface.h"
+#include "qemu-helper-stamp-utils.h"
 
 NameInfo *qmp_query_name(Error **errp)
 {
@@ -351,3 +352,34 @@ void qmp_display_reload(DisplayReloadOptions *arg, Error 
**errp)
 abort();
 }
 }
+
+HelperPathList *qmp_query_helper_paths(Error **errp)
+{
+HelperPathList *ret = NULL;
+struct {
+const char *helper;
+bool check_stamp;
+} helpers_list[] = {
+#ifdef CONFIG_EBPF
+{ "qemu-ebpf-rss-helper", true },
+#endif
+{ "qemu-pr-helper", false },
+{ "qemu-bridge-helper", false },
+{ NULL, false },
+}, *helper_iter;
+helper_iter = helpers_list;
+
+for (; helper_iter->helper != NULL; ++helper_iter) {
+char *path = qemu_find_helper(helper_iter->helper,
+  helper_iter->check_stamp);
+if (path) {
+HelperPath *helper = g_new0(HelperPath, 1);
+helper->name = g_strdup(helper_iter->helper);
+helper->path = path;
+
+QAPI_LIST_PREPEND(ret, helper);
+}
+}
+
+return ret;
+}
diff --git a/qapi/misc.json b/qapi/misc.json
index 156f98203e..9aaf8fbcca 100644
--- a/qapi/misc.json
+++ b/qapi/misc.json
@@ -519,3 +519,36 @@
  'data': { '*option': 'str' },
  'returns': ['CommandLineOptionInfo'],
  'allow-preconfig': true }
+
+##
+# @HelperPath:
+#
+# Name of the helper and binary location.
+##
+{ 'struct': 'HelperPath',
+  'data': {'name': 'str', 'path': 'str'} }
+
+##
+# @query-helper-paths:
+#
+# Query helper paths. Initially, this command was added for
+# qemu-ebpf-rss-helper. The qemu would check "the stamp" and
+# returns proper helper.
+#
+# Returns: list of object that contains name and path for helper.
+#
+# Since: 6.1
+#
+# Example:
+#
+# -> { "execute": "query-helper-paths" }
+# <- { "return": [
+#{
+#  "name": "qemu-ebpf-rss-helper",
+#  "path": "/usr/local/libexec/qemu-ebpf-rss-helper"
+#}
+#  ]
+#}
+#
+##
+{ 'command': 'query-helper-paths', 'returns': ['HelperPath'] }
-- 
2.31.1

[PATCH 4/5] ebpf_rss_helper: Added helper for eBPF RSS.

2021-07-13 Thread Andrew Melnychenko

Helper program. Loads eBPF RSS program and maps and passes them through unix 
socket.
Libvirt may launch this helper and pass eBPF fds to qemu virtio-net.
Also, libbpf dependency now exclusively for Linux.
Libbpf is used for eBPF RSS steering, which is supported only by Linux TAP.
There is no reason yet to build eBPF loader and helper for non Linux systems,
even if libbpf is present.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/qemu-ebpf-rss-helper.c | 130 
 meson.build |  37 ++
 2 files changed, 154 insertions(+), 13 deletions(-)
 create mode 100644 ebpf/qemu-ebpf-rss-helper.c

diff --git a/ebpf/qemu-ebpf-rss-helper.c b/ebpf/qemu-ebpf-rss-helper.c
new file mode 100644
index 00..fe68758f57
--- /dev/null
+++ b/ebpf/qemu-ebpf-rss-helper.c
@@ -0,0 +1,130 @@
+/*
+ * eBPF RSS Helper
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ * Description: This is helper program for libvirtd.
+ *  It loads eBPF RSS program and passes fds through unix socket.
+ *  Built by meson, target - 'qemu-ebpf-rss-helper'.
+ */
+
+#include 
+#include 
+#include 
+#include 
+#include 
+#include 
+#include 
+#include 
+
+#include "ebpf_rss.h"
+
+#include "qemu-helper-stamp.h"
+
+void QEMU_HELPER_STAMP(void) {}
+
+static int send_fds(int socket, int *fds, int n)
+{
+struct msghdr msg = {};
+struct cmsghdr *cmsg = NULL;
+char buf[CMSG_SPACE(n * sizeof(int))];
+char dummy_buffer = 0;
+struct iovec io = { .iov_base = _buffer,
+.iov_len = sizeof(dummy_buffer) };
+
+memset(buf, 0, sizeof(buf));
+
+msg.msg_iov = 
+msg.msg_iovlen = 1;
+msg.msg_control = buf;
+msg.msg_controllen = sizeof(buf);
+
+cmsg = CMSG_FIRSTHDR();
+cmsg->cmsg_level = SOL_SOCKET;
+cmsg->cmsg_type = SCM_RIGHTS;
+cmsg->cmsg_len = CMSG_LEN(n * sizeof(int));
+
+memcpy(CMSG_DATA(cmsg), fds, n * sizeof(int));
+
+return sendmsg(socket, , 0);
+}
+
+static void print_help_and_exit(const char *prog, int exitcode)
+{
+fprintf(stderr, "%s - load eBPF RSS program for qemu and pass eBPF fds"
+" through unix socket.\n", prog);
+fprintf(stderr, "\t--fd , -f  - unix socket file descriptor"
+" used to pass eBPF fds.\n");
+fprintf(stderr, "\t--help, -h - this help.\n");
+exit(exitcode);
+}
+
+int main(int argc, char **argv)
+{
+char *fd_string = NULL;
+int unix_fd = 0;
+struct EBPFRSSContext ctx = {};
+int fds[EBPF_RSS_MAX_FDS] = {};
+int ret = -1;
+
+for (;;) {
+int c;
+static struct option long_options[] = {
+{"help",  no_argument, 0, 'h'},
+{"fd",  required_argument, 0, 'f'},
+{0, 0, 0, 0}
+};
+c = getopt_long(argc, argv, "hf:",
+long_options, NULL);
+
+if (c == -1) {
+break;
+}
+
+switch (c) {
+case 'f':
+fd_string = optarg;
+break;
+case 'h':
+default:
+print_help_and_exit(argv[0],
+c == 'h' ? EXIT_SUCCESS : EXIT_FAILURE);
+}
+}
+
+if (!fd_string) {
+fprintf(stderr, "Unix file descriptor not present.\n");
+print_help_and_exit(argv[0], EXIT_FAILURE);
+}
+
+unix_fd = atoi(fd_string);
+
+if (!unix_fd) {
+fprintf(stderr, "Unix file descriptor is invalid.\n");
+return EXIT_FAILURE;
+}
+
+ebpf_rss_init();
+if (!ebpf_rss_load()) {
+fprintf(stderr, "Can't load ebpf.\n");
+return EXIT_FAILURE;
+}
+fds[0] = ctx.program_fd;
+fds[1] = ctx.map_configuration;
+
+ret = send_fds(unix_fd, fds, EBPF_RSS_MAX_FDS);
+if (ret < 0) {
+fprintf(stderr, "Issue while sending fds: %s.\n", strerror(errno));
+}
+
+ebpf_rss_unload();
+
+return ret < 0 ? EXIT_FAILURE : EXIT_SUCCESS;
+}
+
diff --git a/meson.build b/meson.build
index 257e51d91b..913aa1fee5 100644
--- a/meson.build
+++ b/meson.build
@@ -1033,19 +1033,22 @@ if not get_option('fuse_lseek').disabled()
 endif
 
 # libbpf
-libbpf = dependency('libbpf', required: get_option('bpf'), method: 
'pkg-config')
-if libbpf.found() and not cc.links('''
-   #include 
-   int main(void)
-   {
- bpf_object__destroy_skeleton(NULL);
- return 0;
-   }''', dependencies: libbpf)
-  libbpf = not_found
-  if get_option('bpf').enabled()
-error('libbpf skeleton test failed')
-  else
-warning('libbpf skeleton test failed, disabling')
+libbpf = not_found
+if targetos == 'linux'
+  libbpf = dependency('libbpf', required: get_option('bpf'), method: 
'

[PATCH 3/5] qmp: Added the helper stamp check.

2021-07-13 Thread Andrew Melnychenko

Added function to check the stamp in the helper.
eBPF helper should have a special symbol that generates during build.
QEMU checks the helper and determinates that it fits, so the helper
will produce proper output.

Signed-off-by: Andrew Melnychenko 
---
 meson.build   |  10 +
 monitor/meson.build   |   1 +
 monitor/qemu-helper-stamp-utils.c | 297 ++
 monitor/qemu-helper-stamp-utils.h |  24 +++
 4 files changed, 332 insertions(+)
 create mode 100644 monitor/qemu-helper-stamp-utils.c
 create mode 100644 monitor/qemu-helper-stamp-utils.h

diff --git a/meson.build b/meson.build
index 626cf932c1..257e51d91b 100644
--- a/meson.build
+++ b/meson.build
@@ -1757,6 +1757,16 @@ foreach d : hx_headers
 endforeach
 genh += hxdep
 
+helper_stamp = custom_target(
+'qemu-helper-stamp.h',
+output : 'qemu-helper-stamp.h',
+input : 'ebpf/rss.bpf.skeleton.h',
+command : [python, '-c', 'import hashlib; print(\'#define 
QEMU_HELPER_STAMP qemuHelperStamp_{}\'.format(hashlib.sha1(open(\'@INPUT@\', 
\'rb\').read()).hexdigest()))'],
+capture: true,
+)
+
+genh += helper_stamp
+
 ###
 # Collect sources #
 ###
diff --git a/monitor/meson.build b/monitor/meson.build
index 6d00985ace..2b6b39549b 100644
--- a/monitor/meson.build
+++ b/monitor/meson.build
@@ -5,5 +5,6 @@ softmmu_ss.add(files(
   'hmp.c',
 ))
 softmmu_ss.add([spice_headers, files('qmp-cmds.c')])
+softmmu_ss.add(files('qemu-helper-stamp-utils.c'))
 
 specific_ss.add(when: 'CONFIG_SOFTMMU', if_true: [files('misc.c'), spice])
diff --git a/monitor/qemu-helper-stamp-utils.c 
b/monitor/qemu-helper-stamp-utils.c
new file mode 100644
index 00..d34c3b94c5
--- /dev/null
+++ b/monitor/qemu-helper-stamp-utils.c
@@ -0,0 +1,297 @@
+/*
+ * QEMU helper stamp check utils.
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ * Description: This file mostly implements helper stamp checking.
+ *  The stamp is implemented in a similar way as in qemu modules.
+ *  The helper should contain a specific symbol.
+ *  Not in a similar way is symbol checking - here we parse
+ *  the ELF file. For now(10.07.2021), only eBPF helper contains
+ *  the stamp, and the stamp is generated from
+ *  sha1 ebpf/rss.bpf.skeleton.h (see meson.build).
+ */
+
+#include "qemu/osdep.h"
+#include "elf.h"
+#include "qemu-helper-stamp-utils.h"
+
+#include 
+
+#ifdef CONFIG_LINUX
+
+static void *file_allocate_and_read(int fd, off_t off, size_t size)
+{
+void *data;
+int err;
+
+if (fd < 0) {
+return NULL;
+}
+
+err = lseek(fd, off, SEEK_SET);
+if (err < 0) {
+return NULL;
+}
+
+data = g_new0(char, size);
+if (data == NULL) {
+return NULL;
+}
+
+err = read(fd, data, size);
+if (err < 0) {
+g_free(data);
+return NULL;
+}
+
+return data;
+}
+
+static Elf64_Shdr *elf64_get_section_table(int fd, Elf64_Ehdr *elf_header)
+{
+if (elf_header == NULL) {
+return NULL;
+}
+return (Elf64_Shdr *)file_allocate_and_read(fd, elf_header->e_shoff,
+ elf_header->e_shnum * elf_header->e_shentsize);
+}
+
+static Elf32_Shdr *elf32_get_section_table(int fd, Elf32_Ehdr *elf_header)
+{
+if (elf_header == NULL) {
+return NULL;
+}
+return (Elf32_Shdr *)file_allocate_and_read(fd, elf_header->e_shoff,
+ elf_header->e_shnum * elf_header->e_shentsize);
+}
+
+static void *elf64_get_section_data(int fd, const Elf64_Shdr* section_header)
+{
+if (fd < 0 || section_header == NULL) {
+return NULL;
+}
+return file_allocate_and_read(fd, section_header->sh_offset,
+  section_header->sh_size);
+}
+
+static void *elf32_get_section_data(int fd, const Elf32_Shdr* section_header)
+{
+if (fd < 0 || section_header == NULL) {
+return NULL;
+}
+return file_allocate_and_read(fd, section_header->sh_offset,
+  section_header->sh_size);
+}
+
+static bool elf64_check_symbol_in_symbol_table(int fd,
+   Elf64_Shdr *section_table,
+   Elf64_Shdr *symbol_section,
+   const char *symbol)
+{
+Elf64_Sym *symbol_table;
+char *string_table;
+uint32_t i;
+bool ret = false;
+
+symbol_table = (Elf64_Sym *) elf64_get_section_data(fd, symbol_section);
+if (symbol_table == NULL) {
+return false;
+}
+
+string_table = (char *) elf64_get_section_data(
+fd, section_table +

[PATCH 2/5] virtio-net: Added property to load eBPF RSS with fds.

2021-07-13 Thread Andrew Melnychenko

eBPF RSS program and maps now may be passed during initialization.
Initially was implemented for libvirt to launch qemu without permissions.

Signed-off-by: Andrew Melnychenko 
---
 hw/net/virtio-net.c| 77 --
 include/hw/virtio/virtio-net.h |  1 +
 2 files changed, 74 insertions(+), 4 deletions(-)

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index bd7958b9f0..0602b1772e 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -41,6 +41,7 @@
 #include "sysemu/sysemu.h"
 #include "trace.h"
 #include "monitor/qdev.h"
+#include "monitor/monitor.h"
 #include "hw/pci/pci.h"
 #include "net_rx_pkt.h"
 #include "hw/virtio/vhost.h"
@@ -1223,14 +1224,81 @@ static void virtio_net_detach_epbf_rss(VirtIONet *n)
 virtio_net_attach_ebpf_to_backend(n->nic, -1);
 }
 
-static bool virtio_net_load_ebpf(VirtIONet *n)
+static int virtio_net_get_ebpf_rss_fds(char *str, char *fds[], int nfds)
 {
-if (!virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
-/* backend does't support steering ebpf */
+char *ptr = str;
+char *cur = NULL;
+size_t len = strlen(str);
+int i = 0;
+
+for (; i < nfds && ptr < str + len;) {
+cur = strchr(ptr, ':');
+
+if (cur == NULL) {
+fds[i] = g_strdup(ptr);
+} else {
+fds[i] = g_strndup(ptr, cur - ptr);
+}
+
+i++;
+if (cur == NULL) {
+break;
+} else {
+ptr = cur + 1;
+}
+}
+
+return i;
+}
+
+static bool virtio_net_load_ebpf_fds(VirtIONet *n)
+{
+char *fds_strs[EBPF_RSS_MAX_FDS];
+int fds[EBPF_RSS_MAX_FDS];
+int nfds;
+int ret = false;
+Error *errp;
+int i = 0;
+
+if (n == NULL || !n->ebpf_rss_fds) {
 return false;
 }
 
-return ebpf_rss_load(>ebpf_rss);
+nfds = virtio_net_get_ebpf_rss_fds(n->ebpf_rss_fds,
+   fds_strs, EBPF_RSS_MAX_FDS);
+for (i = 0; i < nfds; i++) {
+fds[i] = monitor_fd_param(monitor_cur(), fds_strs[i], );
+}
+
+if (nfds == EBPF_RSS_MAX_FDS) {
+ret = ebpf_rss_load_fds(>ebpf_rss, fds[0], fds[1], fds[2], fds[3]);
+}
+
+if (!ret) {
+for (i = 0; i < nfds; i++) {
+close(fds[i]);
+}
+}
+
+for (i = 0; i < nfds; i++) {
+g_free(fds_strs[i]);
+}
+
+return ret;
+}
+
+static bool virtio_net_load_ebpf(VirtIONet *n)
+{
+bool ret = true;
+
+if (virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
+if (!(n->ebpf_rss_fds
+&& virtio_net_load_ebpf_fds(n))) {
+ret = ebpf_rss_load(>ebpf_rss);
+}
+}
+
+return ret;
 }
 
 static void virtio_net_unload_ebpf(VirtIONet *n)
@@ -3605,6 +3673,7 @@ static Property virtio_net_properties[] = {
 VIRTIO_NET_F_RSS, false),
 DEFINE_PROP_BIT64("hash", VirtIONet, host_features,
 VIRTIO_NET_F_HASH_REPORT, false),
+DEFINE_PROP_STRING("ebpf_rss_fds", VirtIONet, ebpf_rss_fds),
 DEFINE_PROP_BIT64("guest_rsc_ext", VirtIONet, host_features,
 VIRTIO_NET_F_RSC_EXT, false),
 DEFINE_PROP_UINT32("rsc_interval", VirtIONet, rsc_timeout,
diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h
index 824a69c23f..993f2f3036 100644
--- a/include/hw/virtio/virtio-net.h
+++ b/include/hw/virtio/virtio-net.h
@@ -213,6 +213,7 @@ struct VirtIONet {
 VirtioNetRssData rss_data;
 struct NetRxPkt *rx_pkt;
 struct EBPFRSSContext ebpf_rss;
+char *ebpf_rss_fds;
 };
 
 void virtio_net_set_netclient_name(VirtIONet *n, const char *name,
-- 
2.31.1

[PATCH 0/5] ebpf: Added ebpf helper for libvirtd.

2021-07-13 Thread Andrew Melnychenko

Libvirt usually launches qemu with strict permissions.
To enable eBPF RSS steering, qemu-ebpf-rss-helper was added.

Added property "ebpf_rss_fds" for "virtio-net" that allows to
initialize eBPF RSS context with passed program & maps fds.

Added qemu-ebpf-rss-helper - simple helper that loads eBPF
context and passes fds through unix socket.
Libvirt should call the helper and pass fds to qemu through
"ebpf_rss_fds" property.

Added explicit target OS check for libbpf dependency in meson.
eBPF RSS works only with Linux TAP, so there is no reason to
build eBPF loader/helper for non-Linux.

Changed Qemu updates eBPF maps to array mmaping. Mmaping allows
bypassing unprivileged BPF map update. Also, instead of 3 maps
(config, key and indirection table) there is one map that
combines everything.

Added helper stamp. To check that helper was build with qemu,
qemu would check helper symbols that should contain the stamp.
It was done similar to qemu modules, but checking was performed
by the helper's ELF parsing.

Overall, libvirt process should not be aware of the "interface"
of eBPF RSS, it will not be aware of eBPF maps/program "type" and
their quantity. That's why qemu and the helper should be from
the same build and be "synchronized". Technically each qemu may
have its own helper. That's why "query-helper-paths" qmp command
was added. Qemu should return the path to the helper that suits
and libvirt should use "that" helper for "that" emulator.

qmp sample:
C: { "execute": "query-helper-paths" }
S: { "return": [
 {
   "name": "qemu-ebpf-rss-helper",
   "path": "/usr/local/libexec/qemu-ebpf-rss-helper"
 }
]
   }

Changes since v1:
* Mmap() used instead if bpf_map_update_elem().
* Added helper stamp.

Andrew Melnychenko (5):
  ebpf: Added eBPF initialization by fds and map update.
  virtio-net: Added property to load eBPF RSS with fds.
  qmp: Added the helper stamp check.
  ebpf_rss_helper: Added helper for eBPF RSS.
  qmp: Added qemu-ebpf-rss-path command.

 ebpf/ebpf_rss-stub.c  |   6 +
 ebpf/ebpf_rss.c   | 120 ---
 ebpf/ebpf_rss.h   |   8 +-
 ebpf/qemu-ebpf-rss-helper.c   | 130 +++
 ebpf/rss.bpf.skeleton.h   | 557 +++---
 hw/net/virtio-net.c   |  77 -
 include/hw/virtio/virtio-net.h|   1 +
 meson.build   |  47 ++-
 monitor/meson.build   |   1 +
 monitor/qemu-helper-stamp-utils.c | 297 
 monitor/qemu-helper-stamp-utils.h |  24 ++
 monitor/qmp-cmds.c|  32 ++
 qapi/misc.json|  33 ++
 tools/ebpf/rss.bpf.c  |  67 ++--
 14 files changed, 990 insertions(+), 410 deletions(-)
 create mode 100644 ebpf/qemu-ebpf-rss-helper.c
 create mode 100644 monitor/qemu-helper-stamp-utils.c
 create mode 100644 monitor/qemu-helper-stamp-utils.h

-- 
2.31.1

[RFC PATCH 4/5] qmp: Added qemu-ebpf-rss-path command.

2021-06-09 Thread Andrew Melnychenko

New qmp command to query ebpf helper.
It's crucial that qemu and helper are in sync and in touch.
Technically helper should pass eBPF fds that qemu may accept.
And different qemu's builds may have different eBPF programs and helpers.
Qemu returns helper that should "fit" to virtio-net.

Signed-off-by: Andrew Melnychenko 
---
 monitor/qmp-cmds.c | 78 ++
 qapi/misc.json | 29 +
 2 files changed, 107 insertions(+)

diff --git a/monitor/qmp-cmds.c b/monitor/qmp-cmds.c
index f7d64a6457..5dd2a58ea2 100644
--- a/monitor/qmp-cmds.c
+++ b/monitor/qmp-cmds.c
@@ -351,3 +351,81 @@ void qmp_display_reload(DisplayReloadOptions *arg, Error 
**errp)
 abort();
 }
 }
+
+#ifdef CONFIG_LINUX
+
+static const char *get_dirname(char *path)
+{
+char *sep;
+
+sep = strrchr(path, '/');
+if (sep == path) {
+return "/";
+} else if (sep) {
+*sep = 0;
+return path;
+}
+return ".";
+}
+
+static char *find_helper(const char *name)
+{
+char qemu_exec[PATH_MAX];
+const char *qemu_dir = NULL;
+char *helper = NULL;
+
+if (name == NULL) {
+return NULL;
+}
+
+if (readlink("/proc/self/exe", qemu_exec, PATH_MAX) > 0) {
+qemu_dir = get_dirname(qemu_exec);
+
+helper = g_strdup_printf("%s/%s", qemu_dir, name);
+if (access(helper, F_OK) == 0) {
+return helper;
+}
+g_free(helper);
+}
+
+helper = g_strdup_printf("%s/%s", CONFIG_QEMU_HELPERDIR, name);
+if (access(helper, F_OK) == 0) {
+return helper;
+}
+g_free(helper);
+
+return NULL;
+}
+
+HelperPathList *qmp_query_helper_paths(Error **errp)
+{
+HelperPathList *ret = NULL;
+const char *helpers_list[] = {
+#ifdef CONFIG_EBPF
+"qemu-ebpf-rss-helper",
+#endif
+NULL
+};
+const char **helper_iter = helpers_list;
+
+for (; *helper_iter != NULL; ++helper_iter) {
+char *path = find_helper(*helper_iter);
+if (path) {
+HelperPath *helper = g_new0(HelperPath, 1);
+helper->name = g_strdup(*helper_iter);
+helper->path = path;
+
+QAPI_LIST_PREPEND(ret, helper);
+}
+}
+
+return ret;
+}
+#else
+
+HelperPathList *qmp_query_helper_paths(Error **errp)
+{
+return NULL;
+}
+
+#endif
diff --git a/qapi/misc.json b/qapi/misc.json
index 156f98203e..023bd2120d 100644
--- a/qapi/misc.json
+++ b/qapi/misc.json
@@ -519,3 +519,32 @@
  'data': { '*option': 'str' },
  'returns': ['CommandLineOptionInfo'],
  'allow-preconfig': true }
+
+##
+# @HelperPath:
+#
+# Name of the helper and binary location.
+##
+{ 'struct': 'HelperPath',
+  'data': {'name': 'str', 'path': 'str'} }
+
+##
+# @query-helper-paths:
+#
+# Query specific eBPF RSS helper for current qemu binary.
+#
+# Returns: list of object that contains name and path for helper.
+#
+# Example:
+#
+# -> { "execute": "query-helper-paths" }
+# <- { "return": [
+#{
+#  "name": "qemu-ebpf-rss-helper",
+#  "path": "/usr/local/libexec/qemu-ebpf-rss-helper"
+#}
+#  ]
+#}
+#
+##
+{ 'command': 'query-helper-paths', 'returns': ['HelperPath'] }
-- 
2.31.1

[RFC PATCH 1/5] ebpf: Added eBPF initialization by fds.

2021-06-09 Thread Andrew Melnychenko

eBPF RSS context may be initialized by program fd and map fds.
virtio-net may provide fds passed by libvirt.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/ebpf_rss-stub.c |  6 ++
 ebpf/ebpf_rss.c  | 31 ---
 ebpf/ebpf_rss.h  |  5 +
 3 files changed, 39 insertions(+), 3 deletions(-)

diff --git a/ebpf/ebpf_rss-stub.c b/ebpf/ebpf_rss-stub.c
index e71e229190..8d7fae2ad9 100644
--- a/ebpf/ebpf_rss-stub.c
+++ b/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)
 {
diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
index 118c68da83..6e9b88efed 100644
--- a/ebpf/ebpf_rss.c
+++ b/ebpf/ebpf_rss.c
@@ -27,19 +27,20 @@ void ebpf_rss_init(struct EBPFRSSContext *ctx)
 {
 if (ctx != NULL) {
 ctx->obj = NULL;
+ctx->program_fd = -1;
 }
 }
 
 bool ebpf_rss_is_loaded(struct EBPFRSSContext *ctx)
 {
-return ctx != NULL && ctx->obj != NULL;
+return ctx != NULL && (ctx->obj != NULL || ctx->program_fd != -1);
 }
 
 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;
 }
 
@@ -70,10 +71,26 @@ bool ebpf_rss_load(struct EBPFRSSContext *ctx)
 error:
 rss_bpf__destroy(rss_bpf_ctx);
 ctx->obj = NULL;
+ctx->program_fd = -1;
 
 return false;
 }
 
+bool ebpf_rss_load_fds(struct EBPFRSSContext *ctx, int program_fd,
+   int config_fd, int toeplitz_fd, int table_fd)
+{
+if (ctx == NULL || ebpf_rss_is_loaded(ctx)) {
+return false;
+}
+
+ctx->program_fd = program_fd;
+ctx->map_configuration = config_fd;
+ctx->map_toeplitz_key = toeplitz_fd;
+ctx->map_indirections_table = table_fd;
+
+return true;
+}
+
 static bool ebpf_rss_set_config(struct EBPFRSSContext *ctx,
 struct EBPFRSSConfig *config)
 {
@@ -160,6 +177,14 @@ void ebpf_rss_unload(struct EBPFRSSContext *ctx)
 return;
 }
 
-rss_bpf__destroy(ctx->obj);
+if (ctx->obj != NULL) {
+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;
 }
diff --git a/ebpf/ebpf_rss.h b/ebpf/ebpf_rss.h
index bf3f2572c7..363859c8bb 100644
--- a/ebpf/ebpf_rss.h
+++ b/ebpf/ebpf_rss.h
@@ -14,6 +14,8 @@
 #ifndef QEMU_EBPF_RSS_H
 #define QEMU_EBPF_RSS_H
 
+#define EBPF_RSS_MAX_FDS 4
+
 struct EBPFRSSContext {
 void *obj;
 int program_fd;
@@ -36,6 +38,9 @@ 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);
 
-- 
2.31.1

[RFC PATCH 5/5] meson: libbpf dependency now exclusively for Linux.

2021-06-09 Thread Andrew Melnychenko

Libbpf is used for eBPF RSS steering, which is
supported only by Linux TAP.
There is no reason yet to build eBPF loader and
helper for non Linux systems, even if libbpf is
present.

Signed-off-by: Andrew Melnychenko 
---
 meson.build | 29 -
 1 file changed, 16 insertions(+), 13 deletions(-)

diff --git a/meson.build b/meson.build
index ce26bddead..fa6c48fb86 100644
--- a/meson.build
+++ b/meson.build
@@ -1033,19 +1033,22 @@ if not get_option('fuse_lseek').disabled()
 endif
 
 # libbpf
-libbpf = dependency('libbpf', required: get_option('bpf'), method: 
'pkg-config')
-if libbpf.found() and not cc.links('''
-   #include 
-   int main(void)
-   {
- bpf_object__destroy_skeleton(NULL);
- return 0;
-   }''', dependencies: libbpf)
-  libbpf = not_found
-  if get_option('bpf').enabled()
-error('libbpf skeleton test failed')
-  else
-warning('libbpf skeleton test failed, disabling')
+libbpf = not_found
+if targetos == 'linux'
+  libbpf = dependency('libbpf', required: get_option('bpf'), method: 
'pkg-config')
+  if libbpf.found() and not cc.links('''
+#include 
+int main(void)
+{
+  bpf_object__destroy_skeleton(NULL);
+  return 0;
+}''', dependencies: libbpf)
+libbpf = not_found
+if get_option('bpf').enabled()
+  error('libbpf skeleton test failed')
+else
+  warning('libbpf skeleton test failed, disabling')
+endif
   endif
 endif
 
-- 
2.31.1

[PATCH 1/3] virtio-pci: Added check for virtio device presence in mm callbacks.

2021-06-09 Thread Andrew Melnychenko

During unplug the virtio device is unplugged from virtio-bus on pci. In some 
cases,
requests to virtio-pci mm may acquire during/after unplug. Added check that 
virtio
device is on the bus, for "common" memory region.

Signed-off-by: Andrew Melnychenko 
---
 hw/virtio/virtio-pci.c | 8 
 1 file changed, 8 insertions(+)

diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
index b321604d9b..05865b1fcb 100644
--- a/hw/virtio/virtio-pci.c
+++ b/hw/virtio/virtio-pci.c
@@ -1146,6 +1146,10 @@ static uint64_t virtio_pci_common_read(void *opaque, 
hwaddr addr,
 uint32_t val = 0;
 int i;
 
+if (vdev == NULL) {
+return UINT64_MAX;
+}
+
 switch (addr) {
 case VIRTIO_PCI_COMMON_DFSELECT:
 val = proxy->dfselect;
@@ -1229,6 +1233,10 @@ static void virtio_pci_common_write(void *opaque, hwaddr 
addr,
 VirtIOPCIProxy *proxy = opaque;
 VirtIODevice *vdev = virtio_bus_get_device(>bus);
 
+if (vdev == NULL) {
+return;
+}
+
 switch (addr) {
 case VIRTIO_PCI_COMMON_DFSELECT:
 proxy->dfselect = val;
-- 
2.31.1

[PATCH 3/3] virtio-pci: Changed return values for "notify", "device" and "isr" read.

2021-06-09 Thread Andrew Melnychenko

Added check for "notify" memory region. Now reads will return "-1" if a virtio
device is not present on a virtio bus.

Signed-off-by: Andrew Melnychenko 
---
 hw/virtio/virtio-pci.c | 9 +++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
index 186b7bc0f6..447f13beae 100644
--- a/hw/virtio/virtio-pci.c
+++ b/hw/virtio/virtio-pci.c
@@ -1348,6 +1348,11 @@ static void virtio_pci_common_write(void *opaque, hwaddr 
addr,
 static uint64_t virtio_pci_notify_read(void *opaque, hwaddr addr,
unsigned size)
 {
+VirtIOPCIProxy *proxy = opaque;
+if (virtio_bus_get_device(>bus) == NULL) {
+return UINT64_MAX;
+}
+
 return 0;
 }
 
@@ -1385,7 +1390,7 @@ static uint64_t virtio_pci_isr_read(void *opaque, hwaddr 
addr,
 uint64_t val;
 
 if (vdev == NULL) {
-return 0;
+return UINT64_MAX;
 }
 
 val = qatomic_xchg(>isr, 0);
@@ -1406,7 +1411,7 @@ static uint64_t virtio_pci_device_read(void *opaque, 
hwaddr addr,
 uint64_t val;
 
 if (vdev == NULL) {
-return 0;
+return UINT64_MAX;
 }
 
 switch (size) {
-- 
2.31.1

[RFC PATCH 3/5] ebpf_rss_helper: Added helper for eBPF RSS.

2021-06-09 Thread Andrew Melnychenko

Helper program. Loads eBPF RSS program and maps and passes them through unix 
socket.
Libvirt may launch this helper and pass eBPF fds to qemu virtio-net.

Signed-off-by: Andrew Melnychenko 
---
 ebpf/qemu-ebpf-rss-helper.c | 130 
 meson.build |   8 +++
 2 files changed, 138 insertions(+)
 create mode 100644 ebpf/qemu-ebpf-rss-helper.c

diff --git a/ebpf/qemu-ebpf-rss-helper.c b/ebpf/qemu-ebpf-rss-helper.c
new file mode 100644
index 00..f0379dddf2
--- /dev/null
+++ b/ebpf/qemu-ebpf-rss-helper.c
@@ -0,0 +1,130 @@
+/*
+ * eBPF RSS Helper
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ * Description: This is helper program for libvirtd.
+ *  It loads eBPF RSS program and passes fds through unix socket.
+ *  Built by meson, target - 'qemu-ebpf-rss-helper'.
+ */
+
+#include 
+#include 
+#include 
+#include 
+#include 
+#include 
+#include 
+#include 
+
+#include "ebpf_rss.h"
+
+static int send_fds(int socket, int *fds, int n)
+{
+struct msghdr msg = {};
+struct cmsghdr *cmsg = NULL;
+char buf[CMSG_SPACE(n * sizeof(int))];
+char dummy_buffer = 0;
+struct iovec io = { .iov_base = _buffer,
+.iov_len = sizeof(dummy_buffer) };
+
+memset(buf, 0, sizeof(buf));
+
+msg.msg_iov = 
+msg.msg_iovlen = 1;
+msg.msg_control = buf;
+msg.msg_controllen = sizeof(buf);
+
+cmsg = CMSG_FIRSTHDR();
+cmsg->cmsg_level = SOL_SOCKET;
+cmsg->cmsg_type = SCM_RIGHTS;
+cmsg->cmsg_len = CMSG_LEN(n * sizeof(int));
+
+memcpy(CMSG_DATA(cmsg), fds, n * sizeof(int));
+
+return sendmsg(socket, , 0);
+}
+
+static void print_help_and_exit(const char *prog, int exitcode)
+{
+fprintf(stderr, "%s - load eBPF RSS program for qemu and pass eBPF fds"
+" through unix socket.\n", prog);
+fprintf(stderr, "\t--fd , -f  - unix socket file descriptor"
+" used to pass eBPF fds.\n");
+fprintf(stderr, "\t--help, -h - this help.\n");
+exit(exitcode);
+}
+
+int main(int argc, char **argv)
+{
+char *fd_string = NULL;
+int unix_fd = 0;
+struct EBPFRSSContext ctx = {};
+int fds[EBPF_RSS_MAX_FDS] = {};
+int ret = -1;
+
+for (;;) {
+int c;
+static struct option long_options[] = {
+{"help",  no_argument, 0, 'h'},
+{"fd",  required_argument, 0, 'f'},
+{0, 0, 0, 0}
+};
+c = getopt_long(argc, argv, "hf:",
+long_options, NULL);
+
+if (c == -1) {
+break;
+}
+
+switch (c) {
+case 'f':
+fd_string = optarg;
+break;
+case 'h':
+default:
+print_help_and_exit(argv[0],
+c == 'h' ? EXIT_SUCCESS : EXIT_FAILURE);
+}
+}
+
+if (!fd_string) {
+fprintf(stderr, "Unix file descriptor not present.\n");
+print_help_and_exit(argv[0], EXIT_FAILURE);
+}
+
+fprintf(stderr, "FD %s\n", fd_string);
+
+unix_fd = atoi(fd_string);
+
+if (!unix_fd) {
+fprintf(stderr, "Unix file descriptor is invalid.\n");
+return EXIT_FAILURE;
+}
+
+ebpf_rss_init();
+if (!ebpf_rss_load()) {
+fprintf(stderr, "Can't load ebpf.\n");
+return EXIT_FAILURE;
+}
+fds[0] = ctx.program_fd;
+fds[1] = ctx.map_configuration;
+fds[2] = ctx.map_toeplitz_key;
+fds[3] = ctx.map_indirections_table;
+
+ret = send_fds(unix_fd, fds, EBPF_RSS_MAX_FDS);
+if (ret < 0) {
+fprintf(stderr, "Issue while sending fds: %s.\n", strerror(errno));
+}
+
+ebpf_rss_unload();
+
+return ret < 0 ? EXIT_FAILURE : EXIT_SUCCESS;
+}
+
diff --git a/meson.build b/meson.build
index 626cf932c1..ce26bddead 100644
--- a/meson.build
+++ b/meson.build
@@ -2413,6 +2413,14 @@ if have_tools
dependencies: [authz, crypto, io, qom, qemuutil,
   libcap_ng, mpathpersist],
install: true)
+
+if libbpf.found()
+executable('qemu-ebpf-rss-helper', files(
+   'ebpf/qemu-ebpf-rss-helper.c', 'ebpf/ebpf_rss.c'),
+   dependencies: [qemuutil, libbpf, glib],
+   install: true,
+   install_dir: get_option('libexecdir'))
+endif
   endif
 
   if 'CONFIG_IVSHMEM' in config_host
-- 
2.31.1

[RFC PATCH 0/5] ebpf: Added ebpf helper for libvirtd.

2021-06-09 Thread Andrew Melnychenko

Libvirt usually launches qemu with strict permissions.
To enable eBPF RSS steering, qemu-ebpf-rss-helper was added.

Added property "ebpf_rss_fds" for "virtio-net" that allows to
initialize eBPF RSS context with passed program & maps fds.

Added qemu-ebpf-rss-helper - simple helper that loads eBPF
context and passes fds through unix socket.
Libvirt should call the helper and pass fds to qemu through
"ebpf_rss_fds" property.

Added explicit target OS check for libbpf dependency in meson.
eBPF RSS works only with Linux TAP, so there is no reason to
build eBPF loader/helper for non-Linux.

Overall, libvirt process should not be aware of the "interface"
of eBPF RSS, it will not be aware of eBPF maps/program "type" and
their quantity. That's why qemu and the helper should be from
the same build and be "synchronized". Technically each qemu may
have its own helper. That's why "query-helper-paths" qmp command
was added. Qemu should return the path to the helper that suits
and libvirt should use "that" helper for "that" emulator.

qmp sample:
C: { "execute": "query-helper-paths" }
S: { "return": [
 {
   "name": "qemu-ebpf-rss-helper",
   "path": "/usr/local/libexec/qemu-ebpf-rss-helper"
 }
]
   }

Andrew Melnychenko (5):
  ebpf: Added eBPF initialization by fds.
  virtio-net: Added property to load eBPF RSS with fds.
  ebpf_rss_helper: Added helper for eBPF RSS.
  qmp: Added qemu-ebpf-rss-path command.
  meson: libbpf dependency now exclusively for Linux.

 ebpf/ebpf_rss-stub.c   |   6 ++
 ebpf/ebpf_rss.c|  31 +++-
 ebpf/ebpf_rss.h|   5 ++
 ebpf/qemu-ebpf-rss-helper.c| 130 +
 hw/net/virtio-net.c|  77 ++-
 include/hw/virtio/virtio-net.h |   1 +
 meson.build|  37 ++
 monitor/qmp-cmds.c |  78 
 qapi/misc.json |  29 
 9 files changed, 374 insertions(+), 20 deletions(-)
 create mode 100644 ebpf/qemu-ebpf-rss-helper.c

-- 
2.31.1

[RFC PATCH 2/5] virtio-net: Added property to load eBPF RSS with fds.

2021-06-09 Thread Andrew Melnychenko

eBPF RSS program and maps now may be passed during initialization.
Initially was implemented for libvirt to launch qemu without permissions.

Signed-off-by: Andrew Melnychenko 
---
 hw/net/virtio-net.c| 77 --
 include/hw/virtio/virtio-net.h |  1 +
 2 files changed, 74 insertions(+), 4 deletions(-)

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index bd7958b9f0..0602b1772e 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -41,6 +41,7 @@
 #include "sysemu/sysemu.h"
 #include "trace.h"
 #include "monitor/qdev.h"
+#include "monitor/monitor.h"
 #include "hw/pci/pci.h"
 #include "net_rx_pkt.h"
 #include "hw/virtio/vhost.h"
@@ -1223,14 +1224,81 @@ static void virtio_net_detach_epbf_rss(VirtIONet *n)
 virtio_net_attach_ebpf_to_backend(n->nic, -1);
 }
 
-static bool virtio_net_load_ebpf(VirtIONet *n)
+static int virtio_net_get_ebpf_rss_fds(char *str, char *fds[], int nfds)
 {
-if (!virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
-/* backend does't support steering ebpf */
+char *ptr = str;
+char *cur = NULL;
+size_t len = strlen(str);
+int i = 0;
+
+for (; i < nfds && ptr < str + len;) {
+cur = strchr(ptr, ':');
+
+if (cur == NULL) {
+fds[i] = g_strdup(ptr);
+} else {
+fds[i] = g_strndup(ptr, cur - ptr);
+}
+
+i++;
+if (cur == NULL) {
+break;
+} else {
+ptr = cur + 1;
+}
+}
+
+return i;
+}
+
+static bool virtio_net_load_ebpf_fds(VirtIONet *n)
+{
+char *fds_strs[EBPF_RSS_MAX_FDS];
+int fds[EBPF_RSS_MAX_FDS];
+int nfds;
+int ret = false;
+Error *errp;
+int i = 0;
+
+if (n == NULL || !n->ebpf_rss_fds) {
 return false;
 }
 
-return ebpf_rss_load(>ebpf_rss);
+nfds = virtio_net_get_ebpf_rss_fds(n->ebpf_rss_fds,
+   fds_strs, EBPF_RSS_MAX_FDS);
+for (i = 0; i < nfds; i++) {
+fds[i] = monitor_fd_param(monitor_cur(), fds_strs[i], );
+}
+
+if (nfds == EBPF_RSS_MAX_FDS) {
+ret = ebpf_rss_load_fds(>ebpf_rss, fds[0], fds[1], fds[2], fds[3]);
+}
+
+if (!ret) {
+for (i = 0; i < nfds; i++) {
+close(fds[i]);
+}
+}
+
+for (i = 0; i < nfds; i++) {
+g_free(fds_strs[i]);
+}
+
+return ret;
+}
+
+static bool virtio_net_load_ebpf(VirtIONet *n)
+{
+bool ret = true;
+
+if (virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
+if (!(n->ebpf_rss_fds
+&& virtio_net_load_ebpf_fds(n))) {
+ret = ebpf_rss_load(>ebpf_rss);
+}
+}
+
+return ret;
 }
 
 static void virtio_net_unload_ebpf(VirtIONet *n)
@@ -3605,6 +3673,7 @@ static Property virtio_net_properties[] = {
 VIRTIO_NET_F_RSS, false),
 DEFINE_PROP_BIT64("hash", VirtIONet, host_features,
 VIRTIO_NET_F_HASH_REPORT, false),
+DEFINE_PROP_STRING("ebpf_rss_fds", VirtIONet, ebpf_rss_fds),
 DEFINE_PROP_BIT64("guest_rsc_ext", VirtIONet, host_features,
 VIRTIO_NET_F_RSC_EXT, false),
 DEFINE_PROP_UINT32("rsc_interval", VirtIONet, rsc_timeout,
diff --git a/include/hw/virtio/virtio-net.h b/include/hw/virtio/virtio-net.h
index 824a69c23f..993f2f3036 100644
--- a/include/hw/virtio/virtio-net.h
+++ b/include/hw/virtio/virtio-net.h
@@ -213,6 +213,7 @@ struct VirtIONet {
 VirtioNetRssData rss_data;
 struct NetRxPkt *rx_pkt;
 struct EBPFRSSContext ebpf_rss;
+char *ebpf_rss_fds;
 };
 
 void virtio_net_set_netclient_name(VirtIONet *n, const char *name,
-- 
2.31.1

[PATCH 2/3] virtio-pci: Added check for virtio device in PCI config cbs.

2021-06-09 Thread Andrew Melnychenko

Now, if virtio device is not present on virtio-bus - pci config callbacks
will not lead to possible crush. The read will return "-1" which should be
interpreted by a driver that pci device may be unplugged.

Signed-off-by: Andrew Melnychenko 
---
 hw/virtio/virtio-pci.c | 10 ++
 1 file changed, 10 insertions(+)

diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
index 05865b1fcb..186b7bc0f6 100644
--- a/hw/virtio/virtio-pci.c
+++ b/hw/virtio/virtio-pci.c
@@ -423,6 +423,11 @@ static uint64_t virtio_pci_config_read(void *opaque, 
hwaddr addr,
 VirtIODevice *vdev = virtio_bus_get_device(>bus);
 uint32_t config = VIRTIO_PCI_CONFIG_SIZE(>pci_dev);
 uint64_t val = 0;
+
+if (vdev == NULL) {
+return UINT64_MAX;
+}
+
 if (addr < config) {
 return virtio_ioport_read(proxy, addr);
 }
@@ -454,6 +459,11 @@ static void virtio_pci_config_write(void *opaque, hwaddr 
addr,
 VirtIOPCIProxy *proxy = opaque;
 uint32_t config = VIRTIO_PCI_CONFIG_SIZE(>pci_dev);
 VirtIODevice *vdev = virtio_bus_get_device(>bus);
+
+if (vdev == NULL) {
+return;
+}
+
 if (addr < config) {
 virtio_ioport_write(proxy, addr, val);
 return;
-- 
2.31.1

[PATCH 0/3] virtio-pci: Checks for virtio device presence on the bus.

2021-06-09 Thread Andrew Melnychenko

At some point, after unplugging virtio-pci the virtio device may be unrealised,
but the memory regions may be present in flatview. So, it's a possible situation
when memory region's callbacks are called for "unplugged" device.

In patches were added checks for virtio device presence on virtio-bus.
Added checks in PCI config callbacks. Also changed return values in memory
regions read if virtio not present.

BZ link https://bugzilla.redhat.com/show_bug.cgi?id=1938042
The issue similar to https://bugzilla.redhat.com/show_bug.cgi?id=1743098

Backtrace:
at ../hw/virtio/virtio-pci.c:1271
proxy = 0x560b535f8bf0
vdev = 0x0
(mr=, addr=, value=, 
size=, shift=, mask=, attrs=...) 
at ../softmmu/memory.c:491
tmp = 
(addr=addr@entry=22, value=value@entry=0x7fd743dfe518, size=size@entry=2, 
access_size_min=, access_size_max=, 
access_fn=0x560b513fc500 , mr=0x560b535f95d0, 
attrs=...) at ../softmmu/memory.c:552
access_mask = 65535
access_size = 2
i = 
r = 0
(mr=mr@entry=0x560b535f95d0, addr=22, data=, op=, attrs=attrs@entry=...) at ../softmmu/memory.c:1501
size = 2
(fv=fv@entry=0x7fd6f005d3b0, addr=addr@entry=4246716438, attrs=..., 
ptr=ptr@entry=0x7fe69b2b0028, len=len@entry=2, addr1=, 
l=, mr=0x560b535f95d0)
at 
/usr/src/debug/qemu-kvm-5.2.0-11.module+el8.4.0+10268+62bcbbed.x86_64/include/qemu/host-utils.h:164
ram_ptr = 
val = 
result = 0
release_lock = true
buf = 0x7fe69b2b0028 ""
at ../softmmu/physmem.c:2799
l = 2
addr1 = 22
mr = 
result = 0
_rcu_read_auto = 0x1
result = 0
fv = 
attrs = {unspecified = 0, secure = 0, user = 0, requester_id = 0, 
byte_swap = 0, target_tlb_bit0 = 0, target_tlb_bit1 = 0, target_tlb_bit2 = 0}
run = 
ret = 
run_ret = 0
cpu = 0x560b522738d0
r = 
__clframe = {__cancel_routine = , __cancel_arg = 0x0, 
__do_it = 1, __cancel_type = }
qemu_thread_args = 0x560b5229a6f0
start_routine = 0x560b513faeb0 
arg = 0x560b522738d0
    r = 
    
Andrew Melnychenko (3):
  virtio-pci: Added check for virtio device presence in mm callbacks.
  virtio-pci: Added check for virtio device in PCI config cbs.
  virtio-pci: Changed return values for "notify", "device" and "isr"
read.

 hw/virtio/virtio-pci.c | 27 +--
 1 file changed, 25 insertions(+), 2 deletions(-)

-- 
2.31.1

[PATCH v8 4/7] ebpf: Added eBPF RSS loader.

2021-05-14 Thread Andrew Melnychenko

Added function that loads RSS eBPF program.
Added stub functions for RSS eBPF loader.
Added meson and configuration options.

By default, eBPF feature enabled if libbpf is present in the build system.
libbpf checked in configuration shell script and meson script.

Signed-off-by: Yuri Benditovich 
Signed-off-by: Andrew Melnychenko 
---
 configure   |   8 +-
 ebpf/ebpf_rss-stub.c|  40 
 ebpf/ebpf_rss.c | 165 +++
 ebpf/ebpf_rss.h |  44 
 ebpf/meson.build|   1 +
 ebpf/rss.bpf.skeleton.h | 431 
 ebpf/trace-events   |   4 +
 ebpf/trace.h|   2 +
 meson.build |  23 +++
 meson_options.txt   |   2 +
 10 files changed, 719 insertions(+), 1 deletion(-)
 create mode 100644 ebpf/ebpf_rss-stub.c
 create mode 100644 ebpf/ebpf_rss.c
 create mode 100644 ebpf/ebpf_rss.h
 create mode 100644 ebpf/meson.build
 create mode 100644 ebpf/rss.bpf.skeleton.h
 create mode 100644 ebpf/trace-events
 create mode 100644 ebpf/trace.h

diff --git a/configure b/configure
index 4f374b4889..7d9e0391a0 100755
--- a/configure
+++ b/configure
@@ -348,6 +348,7 @@ 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"
@@ -1228,6 +1229,10 @@ for opt do
   ;;
   --enable-membarrier) membarrier="yes"
   ;;
+  --disable-bpf) bpf="disabled"
+  ;;
+  --enable-bpf) bpf="enabled"
+  ;;
   --disable-blobs) blobs="false"
   ;;
   --with-pkgversion=*) pkgversion="$optarg"
@@ -1865,6 +1870,7 @@ disabled with --disable-FEATURE, default is enabled if 
available
   vhost-user  vhost-user backend support
   vhost-user-blk-servervhost-user-blk server support
   vhost-vdpa  vhost-vdpa kernel backend support
+  bpf BPF kernel support
   spice   spice
   rbd rados block device (rbd)
   libiscsiiscsi support
@@ -6423,7 +6429,7 @@ NINJA=$ninja $meson setup \
 -Dattr=$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 \
diff --git a/ebpf/ebpf_rss-stub.c b/ebpf/ebpf_rss-stub.c
new file mode 100644
index 00..e71e229190
--- /dev/null
+++ b/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 
+ *
+ * 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)
+{
+
+}
diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
new file mode 100644
index 00..118c68da83
--- /dev/null
+++ b/ebpf/ebpf_rss.c
@@ -0,0 +1,165 @@
+/*
+ * eBPF RSS loader
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *  Yuri Benditovich 
+ *
+ * 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 
+#include 
+
+#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;
+}
+
+

[PATCH v8 7/7] MAINTAINERS: Added eBPF maintainers information.

2021-05-14 Thread Andrew Melnychenko

Signed-off-by: Yuri Benditovich 
Signed-off-by: Andrew Melnychenko 
---
 MAINTAINERS | 8 
 1 file changed, 8 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 36055f14c5..c7e9a57cd9 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3312,6 +3312,14 @@ F: include/hw/remote/proxy-memory-listener.h
 F: hw/remote/iohub.c
 F: include/hw/remote/iohub.h
 
+EBPF:
+M: Jason Wang 
+R: Andrew Melnychenko 
+R: Yuri Benditovich 
+S: Maintained
+F: ebpf/*
+F: tools/ebpf/*
+
 Build and test automation
 -
 Build and test automation, general continuous integration
-- 
2.31.1

[PATCH v8 5/7] virtio-net: Added eBPF RSS to virtio-net.

2021-05-14 Thread Andrew Melnychenko

When RSS is enabled the device tries to load the eBPF program
to select RX virtqueue in the TUN. If eBPF can be loaded
the RSS will function also with vhost (works with kernel 5.8 and later).
Software RSS is used as a fallback with vhost=off when eBPF can't be loaded
or when hash population requested by the guest.

Signed-off-by: Yuri Benditovich 
Signed-off-by: Andrew Melnychenko 
---
 hw/net/vhost_net.c |   3 +
 hw/net/virtio-net.c| 116 -
 include/hw/virtio/virtio-net.h |   4 ++
 net/vhost-vdpa.c   |   2 +
 4 files changed, 122 insertions(+), 3 deletions(-)

diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c
index 24d555e764..44c1ed92dc 100644
--- a/hw/net/vhost_net.c
+++ b/hw/net/vhost_net.c
@@ -45,6 +45,7 @@ static const int kernel_feature_bits[] = {
 VIRTIO_NET_F_MTU,
 VIRTIO_F_IOMMU_PLATFORM,
 VIRTIO_F_RING_PACKED,
+VIRTIO_NET_F_HASH_REPORT,
 VHOST_INVALID_FEATURE_BIT
 };
 
@@ -71,6 +72,8 @@ static const int user_feature_bits[] = {
 VIRTIO_NET_F_MTU,
 VIRTIO_F_IOMMU_PLATFORM,
 VIRTIO_F_RING_PACKED,
+VIRTIO_NET_F_RSS,
+VIRTIO_NET_F_HASH_REPORT,
 
 /* This bit implies RARP isn't sent by QEMU out of band */
 VIRTIO_NET_F_GUEST_ANNOUNCE,
diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 66b9ff4511..88287caf73 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -737,8 +737,9 @@ static uint64_t virtio_net_get_features(VirtIODevice *vdev, 
uint64_t features,
 return features;
 }
 
-virtio_clear_feature(, VIRTIO_NET_F_RSS);
-virtio_clear_feature(, VIRTIO_NET_F_HASH_REPORT);
+if (!ebpf_rss_is_loaded(>ebpf_rss)) {
+virtio_clear_feature(, VIRTIO_NET_F_RSS);
+}
 features = vhost_net_get_features(get_vhost_net(nc->peer), features);
 vdev->backend_features = features;
 
@@ -1163,12 +1164,79 @@ static int virtio_net_handle_announce(VirtIONet *n, 
uint8_t cmd,
 }
 }
 
+static void virtio_net_detach_epbf_rss(VirtIONet *n);
+
 static void virtio_net_disable_rss(VirtIONet *n)
 {
 if (n->rss_data.enabled) {
 trace_virtio_net_rss_disable();
 }
 n->rss_data.enabled = false;
+
+virtio_net_detach_epbf_rss(n);
+}
+
+static bool virtio_net_attach_ebpf_to_backend(NICState *nic, int prog_fd)
+{
+NetClientState *nc = qemu_get_peer(qemu_get_queue(nic), 0);
+if (nc == NULL || nc->info->set_steering_ebpf == NULL) {
+return false;
+}
+
+return nc->info->set_steering_ebpf(nc, prog_fd);
+}
+
+static void rss_data_to_rss_config(struct VirtioNetRssData *data,
+   struct EBPFRSSConfig *config)
+{
+config->redirect = data->redirect;
+config->populate_hash = data->populate_hash;
+config->hash_types = data->hash_types;
+config->indirections_len = data->indirections_len;
+config->default_queue = data->default_queue;
+}
+
+static bool virtio_net_attach_epbf_rss(VirtIONet *n)
+{
+struct EBPFRSSConfig config = {};
+
+if (!ebpf_rss_is_loaded(>ebpf_rss)) {
+return false;
+}
+
+rss_data_to_rss_config(>rss_data, );
+
+if (!ebpf_rss_set_all(>ebpf_rss, ,
+  n->rss_data.indirections_table, n->rss_data.key)) {
+return false;
+}
+
+if (!virtio_net_attach_ebpf_to_backend(n->nic, n->ebpf_rss.program_fd)) {
+return false;
+}
+
+return true;
+}
+
+static void virtio_net_detach_epbf_rss(VirtIONet *n)
+{
+virtio_net_attach_ebpf_to_backend(n->nic, -1);
+}
+
+static bool virtio_net_load_ebpf(VirtIONet *n)
+{
+if (!virtio_net_attach_ebpf_to_backend(n->nic, -1)) {
+/* backend does't support steering ebpf */
+return false;
+}
+
+return ebpf_rss_load(>ebpf_rss);
+}
+
+static void virtio_net_unload_ebpf(VirtIONet *n)
+{
+virtio_net_attach_ebpf_to_backend(n->nic, -1);
+ebpf_rss_unload(>ebpf_rss);
 }
 
 static uint16_t virtio_net_handle_rss(VirtIONet *n,
@@ -1283,6 +1351,25 @@ static uint16_t virtio_net_handle_rss(VirtIONet *n,
 goto error;
 }
 n->rss_data.enabled = true;
+
+if (!n->rss_data.populate_hash) {
+if (!virtio_net_attach_epbf_rss(n)) {
+/* EBPF must be loaded for vhost */
+if (get_vhost_net(qemu_get_queue(n->nic)->peer)) {
+warn_report("Can't load eBPF RSS for vhost");
+goto error;
+}
+/* fallback to software RSS */
+warn_report("Can't load eBPF RSS - fallback to software RSS");
+n->rss_data.enabled_software_rss = true;
+}
+} else {
+/* use software RSS for hash populating */
+/* and detach eBPF if was loaded before */
+virtio_net_detach_epbf_rss(n);
+n->rss_data.enabled_software_rss = true;
+}
+
 trace_virtio_net_rss_enable(n->rss_data.h

[PATCH v8 3/7] ebpf: Added eBPF RSS program.

2021-05-14 Thread Andrew Melnychenko

RSS program and Makefile to build it.
The bpftool used to generate '.h' file.
The data in that file may be loaded by libbpf.
EBPF compilation is not required for building qemu.
You can use Makefile if you need to regenerate rss.bpf.skeleton.h.

Signed-off-by: Yuri Benditovich 
Signed-off-by: Andrew Melnychenko 
---
 tools/ebpf/Makefile.ebpf |  22 ++
 tools/ebpf/rss.bpf.c | 571 +++
 2 files changed, 593 insertions(+)
 create mode 100755 tools/ebpf/Makefile.ebpf
 create mode 100644 tools/ebpf/rss.bpf.c

diff --git a/tools/ebpf/Makefile.ebpf b/tools/ebpf/Makefile.ebpf
new file mode 100755
index 00..45b5551fc7
--- /dev/null
+++ b/tools/ebpf/Makefile.ebpf
@@ -0,0 +1,22 @@
+OBJS = rss.bpf.o
+
+LLC ?= llc
+CLANG ?= clang
+INC_FLAGS = `$(CLANG) -print-file-name=include`
+EXTRA_CFLAGS ?= -O2 -emit-llvm -fno-stack-protector
+
+all: $(OBJS)
+
+.PHONY: clean
+
+clean:
+   rm -f $(OBJS)
+
+$(OBJS):  %.o:%.c
+   $(CLANG) $(INC_FLAGS) \
+-D__KERNEL__ -D__ASM_SYSREG_H \
+-I../include $(LINUXINCLUDE) \
+$(EXTRA_CFLAGS) -c $< -o -| $(LLC) -march=bpf -filetype=obj -o 
$@
+   bpftool gen skeleton rss.bpf.o > rss.bpf.skeleton.h
+   cp rss.bpf.skeleton.h ../../ebpf/
+
diff --git a/tools/ebpf/rss.bpf.c b/tools/ebpf/rss.bpf.c
new file mode 100644
index 00..e85ec55f9b
--- /dev/null
+++ b/tools/ebpf/rss.bpf.c
@@ -0,0 +1,571 @@
+/*
+ * eBPF RSS program
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *  Yuri Benditovich 
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ * Prepare:
+ * Requires llvm, clang, bpftool, linux kernel tree
+ *
+ * Build rss.bpf.skeleton.h:
+ * make -f Makefile.ebpf clean all
+ */
+
+#include 
+#include 
+#include 
+
+#include 
+#include 
+#include 
+#include 
+
+#include 
+#include 
+
+#include 
+#include 
+#include 
+
+#define INDIRECTION_TABLE_SIZE 128
+#define HASH_CALCULATION_BUFFER_SIZE 36
+
+struct rss_config_t {
+__u8 redirect;
+__u8 populate_hash;
+__u32 hash_types;
+__u16 indirections_len;
+__u16 default_queue;
+} __attribute__((packed));
+
+struct toeplitz_key_data_t {
+__u32 leftmost_32_bits;
+__u8 next_byte[HASH_CALCULATION_BUFFER_SIZE];
+};
+
+struct packet_hash_info_t {
+__u8 is_ipv4;
+__u8 is_ipv6;
+__u8 is_udp;
+__u8 is_tcp;
+__u8 is_ipv6_ext_src;
+__u8 is_ipv6_ext_dst;
+__u8 is_fragmented;
+
+__u16 src_port;
+__u16 dst_port;
+
+union {
+struct {
+__be32 in_src;
+__be32 in_dst;
+};
+
+struct {
+struct in6_addr in6_src;
+struct in6_addr in6_dst;
+struct in6_addr in6_ext_src;
+struct in6_addr in6_ext_dst;
+};
+};
+};
+
+struct bpf_map_def SEC("maps")
+tap_rss_map_configurations = {
+.type= BPF_MAP_TYPE_ARRAY,
+.key_size= sizeof(__u32),
+.value_size  = sizeof(struct rss_config_t),
+.max_entries = 1,
+};
+
+struct bpf_map_def SEC("maps")
+tap_rss_map_toeplitz_key = {
+.type= BPF_MAP_TYPE_ARRAY,
+.key_size= sizeof(__u32),
+.value_size  = sizeof(struct toeplitz_key_data_t),
+.max_entries = 1,
+};
+
+struct bpf_map_def SEC("maps")
+tap_rss_map_indirection_table = {
+.type= BPF_MAP_TYPE_ARRAY,
+.key_size= sizeof(__u32),
+.value_size  = sizeof(__u16),
+.max_entries = INDIRECTION_TABLE_SIZE,
+};
+
+static inline void net_rx_rss_add_chunk(__u8 *rss_input, size_t *bytes_written,
+const void *ptr, size_t size) {
+__builtin_memcpy(_input[*bytes_written], ptr, size);
+*bytes_written += size;
+}
+
+static inline
+void net_toeplitz_add(__u32 *result,
+  __u8 *input,
+  __u32 len
+, struct toeplitz_key_data_t *key) {
+
+__u32 accumulator = *result;
+__u32 leftmost_32_bits = key->leftmost_32_bits;
+__u32 byte;
+
+for (byte = 0; byte < HASH_CALCULATION_BUFFER_SIZE; byte++) {
+__u8 input_byte = input[byte];
+__u8 key_byte = key->next_byte[byte];
+__u8 bit;
+
+for (bit = 0; bit < 8; bit++) {
+if (input_byte & (1 << 7)) {
+accumulator ^= leftmost_32_bits;
+}
+
+leftmost_32_bits =
+(leftmost_32_bits << 1) | ((key_byte & (1 << 7)) >> 7);
+
+input_byte <<= 1;
+key_byte <<= 1;
+}
+}
+
+*result = accumulator;
+}
+
+
+static inline int ip6_extension_header_type(__u8 hdr_type)
+{
+switch (hdr_type) {
+case IPPROTO_HOPOPTS:
+case IPPROTO_ROUTING:
+case IPPROTO_FRAGMENT:
+case IPPROTO_ICMPV6

[PATCH v8 2/7] net: Added SetSteeringEBPF method for NetClientState.

2021-05-14 Thread Andrew Melnychenko

For now, that method supported only by Linux TAP.
Linux TAP uses TUNSETSTEERINGEBPF ioctl.

Signed-off-by: Andrew Melnychenko 
---
 include/net/net.h |  2 ++
 net/tap-bsd.c |  5 +
 net/tap-linux.c   | 13 +
 net/tap-solaris.c |  5 +
 net/tap-stub.c|  5 +
 net/tap.c |  9 +
 net/tap_int.h |  1 +
 7 files changed, 40 insertions(+)

diff --git a/include/net/net.h b/include/net/net.h
index 1ef536d771..5d1508081f 100644
--- a/include/net/net.h
+++ b/include/net/net.h
@@ -61,6 +61,7 @@ typedef int (SetVnetBE)(NetClientState *, bool);
 typedef struct SocketReadState SocketReadState;
 typedef void (SocketReadStateFinalize)(SocketReadState *rs);
 typedef void (NetAnnounce)(NetClientState *);
+typedef bool (SetSteeringEBPF)(NetClientState *, int);
 
 typedef struct NetClientInfo {
 NetClientDriver type;
@@ -82,6 +83,7 @@ typedef struct NetClientInfo {
 SetVnetLE *set_vnet_le;
 SetVnetBE *set_vnet_be;
 NetAnnounce *announce;
+SetSteeringEBPF *set_steering_ebpf;
 } NetClientInfo;
 
 struct NetClientState {
diff --git a/net/tap-bsd.c b/net/tap-bsd.c
index 77aaf674b1..4f64f31e98 100644
--- a/net/tap-bsd.c
+++ b/net/tap-bsd.c
@@ -259,3 +259,8 @@ int tap_fd_get_ifname(int fd, char *ifname)
 {
 return -1;
 }
+
+int tap_fd_set_steering_ebpf(int fd, int prog_fd)
+{
+return -1;
+}
diff --git a/net/tap-linux.c b/net/tap-linux.c
index b0635e9e32..9584769740 100644
--- a/net/tap-linux.c
+++ b/net/tap-linux.c
@@ -316,3 +316,16 @@ int tap_fd_get_ifname(int fd, char *ifname)
 pstrcpy(ifname, sizeof(ifr.ifr_name), ifr.ifr_name);
 return 0;
 }
+
+int tap_fd_set_steering_ebpf(int fd, int prog_fd)
+{
+if (ioctl(fd, TUNSETSTEERINGEBPF, (void *) _fd) != 0) {
+error_report("Issue while setting TUNSETSTEERINGEBPF:"
+" %s with fd: %d, prog_fd: %d",
+strerror(errno), fd, prog_fd);
+
+   return -1;
+}
+
+return 0;
+}
diff --git a/net/tap-solaris.c b/net/tap-solaris.c
index 0475a58207..d85224242b 100644
--- a/net/tap-solaris.c
+++ b/net/tap-solaris.c
@@ -255,3 +255,8 @@ int tap_fd_get_ifname(int fd, char *ifname)
 {
 return -1;
 }
+
+int tap_fd_set_steering_ebpf(int fd, int prog_fd)
+{
+return -1;
+}
diff --git a/net/tap-stub.c b/net/tap-stub.c
index de525a2e69..a0fa25804b 100644
--- a/net/tap-stub.c
+++ b/net/tap-stub.c
@@ -85,3 +85,8 @@ int tap_fd_get_ifname(int fd, char *ifname)
 {
 return -1;
 }
+
+int tap_fd_set_steering_ebpf(int fd, int prog_fd)
+{
+return -1;
+}
diff --git a/net/tap.c b/net/tap.c
index bae895e287..f5686bbf77 100644
--- a/net/tap.c
+++ b/net/tap.c
@@ -347,6 +347,14 @@ static void tap_poll(NetClientState *nc, bool enable)
 tap_write_poll(s, enable);
 }
 
+static bool tap_set_steering_ebpf(NetClientState *nc, int prog_fd)
+{
+TAPState *s = DO_UPCAST(TAPState, nc, nc);
+assert(nc->info->type == NET_CLIENT_DRIVER_TAP);
+
+return tap_fd_set_steering_ebpf(s->fd, prog_fd) == 0;
+}
+
 int tap_get_fd(NetClientState *nc)
 {
 TAPState *s = DO_UPCAST(TAPState, nc, nc);
@@ -372,6 +380,7 @@ static NetClientInfo net_tap_info = {
 .set_vnet_hdr_len = tap_set_vnet_hdr_len,
 .set_vnet_le = tap_set_vnet_le,
 .set_vnet_be = tap_set_vnet_be,
+.set_steering_ebpf = tap_set_steering_ebpf,
 };
 
 static TAPState *net_tap_fd_init(NetClientState *peer,
diff --git a/net/tap_int.h b/net/tap_int.h
index 225a49ea48..547f8a5a28 100644
--- a/net/tap_int.h
+++ b/net/tap_int.h
@@ -44,5 +44,6 @@ int tap_fd_set_vnet_be(int fd, int vnet_is_be);
 int tap_fd_enable(int fd);
 int tap_fd_disable(int fd);
 int tap_fd_get_ifname(int fd, char *ifname);
+int tap_fd_set_steering_ebpf(int fd, int prog_fd);
 
 #endif /* NET_TAP_INT_H */
-- 
2.31.1

[PATCH v8 6/7] docs: Added eBPF documentation.

2021-05-14 Thread Andrew Melnychenko

Signed-off-by: Yuri Benditovich 
Signed-off-by: Andrew Melnychenko 
---
 docs/devel/ebpf_rss.rst | 125 
 docs/devel/index.rst|   1 +
 2 files changed, 126 insertions(+)
 create mode 100644 docs/devel/ebpf_rss.rst

diff --git a/docs/devel/ebpf_rss.rst b/docs/devel/ebpf_rss.rst
new file mode 100644
index 00..e00962577a
--- /dev/null
+++ b/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()%]
+
+
+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 = VI

[PATCH v8 1/7] net/tap: Added TUNSETSTEERINGEBPF code.

2021-05-14 Thread Andrew Melnychenko

Additional code that will be used for eBPF setting steering routine.

Signed-off-by: Andrew Melnychenko 
---
 net/tap-linux.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/tap-linux.h b/net/tap-linux.h
index 2f36d100fc..1d06fe0de6 100644
--- a/net/tap-linux.h
+++ b/net/tap-linux.h
@@ -31,6 +31,7 @@
 #define TUNSETQUEUE  _IOW('T', 217, int)
 #define TUNSETVNETLE _IOW('T', 220, int)
 #define TUNSETVNETBE _IOW('T', 222, int)
+#define TUNSETSTEERINGEBPF _IOR('T', 224, int)
 
 #endif
 
-- 
2.31.1

[PATCH v8 0/7] eBPF RSS support for virtio-net.

2021-05-14 Thread Andrew Melnychenko

This set of patches introduces the usage of eBPF for packet steering
and RSS hash calculation:
* RSS(Receive Side Scaling) is used to distribute network packets to
guest virtqueues by calculating packet hash
* Additionally adding support for the usage of RSS with vhost

The eBPF works on kernels 5.8+
On earlier kerneld it fails to load and the RSS feature is reported
only without vhost and implemented in 'in-qemu' software.

Implementation notes:
Linux TAP TUNSETSTEERINGEBPF ioctl was used to set the eBPF program.
Added libbpf dependency and eBPF support.
The eBPF program is part of the qemu and presented as an array
of BPF ELF file data. The eBPF array file initially generated by bpftool.
The compilation of eBPF is not part of QEMU build and can be done
using provided Makefile.ebpf.
Added changes to virtio-net and vhost, primary eBPF RSS is used.
'in-qemu' RSS used in the case of hash population and as a fallback option.
For vhost, the hash population feature is not reported to the guest.

Please also see the documentation in PATCH 6/7.

Known issues:
* hash population not supported by eBPF RSS: 'in-qemu' RSS used
as a fallback, also, hash population feature is not reported to guests
with vhost.
* IPv6 extensions still in progress.

Changes since v1:
* using libbpf instead of direct 'bpf' system call.
* added libbpf dependency to the configure/meson scripts.
* changed python script for eBPF .h file generation.
* changed eBPF program - reading L3 proto from ethernet frame.
* added TUNSETSTEERINGEBPF define for TUN.
* changed the maintainer's info.
* added license headers.
* refactored code.

Changes since v2:
* using bpftool for eBPF skeleton generation.
* ebpf_rss is refactored to use skeleton generated by bpftool.
* added/adjasted license in comment sections and in eBPF file.
* rss.bpf.c and Makefile.ebpf moved to the tool/ebpf folder.
* virtio-net eBPF rss refactored. Now eBPF initialized during realize().

Changes since v3:
* rebased to last master.
* fixed issue with failed build without libbpf.
* fixed ebpf loading without rss option.
* refactored labels in ebpf_rss.c

Changes since v4:
* refactored configure/meson script.
* added checks for load_bytes in ebpf.
* documentation added to the index.
* refactored Makefile and rss.bpf.c.
* rebased to last master.

Changes since v5:
* fixed issue with dstopt parsing in the eBPF program.
* added fragment packet parsing to skip L4.

Changes since v6:
* Added eBPF skeleton check to the meson.build file.

Changes since v7:
* Refactored code style and fixed warnings.
* Added explicit pkg-config method for libbpf dependency.

Andrew Melnychenko (7):
  net/tap: Added TUNSETSTEERINGEBPF code.
  net: Added SetSteeringEBPF method for NetClientState.
  ebpf: Added eBPF RSS program.
  ebpf: Added eBPF RSS loader.
  virtio-net: Added eBPF RSS to virtio-net.
  docs: Added eBPF documentation.
  MAINTAINERS: Added eBPF maintainers information.

 MAINTAINERS|   8 +
 configure  |   8 +-
 docs/devel/ebpf_rss.rst| 125 
 docs/devel/index.rst   |   1 +
 ebpf/ebpf_rss-stub.c   |  40 +++
 ebpf/ebpf_rss.c| 165 ++
 ebpf/ebpf_rss.h|  44 +++
 ebpf/meson.build   |   1 +
 ebpf/rss.bpf.skeleton.h| 431 +
 ebpf/trace-events  |   4 +
 ebpf/trace.h   |   2 +
 hw/net/vhost_net.c |   3 +
 hw/net/virtio-net.c| 116 ++-
 include/hw/virtio/virtio-net.h |   4 +
 include/net/net.h  |   2 +
 meson.build|  23 ++
 meson_options.txt  |   2 +
 net/tap-bsd.c  |   5 +
 net/tap-linux.c|  13 +
 net/tap-linux.h|   1 +
 net/tap-solaris.c  |   5 +
 net/tap-stub.c |   5 +
 net/tap.c  |   9 +
 net/tap_int.h  |   1 +
 net/vhost-vdpa.c   |   2 +
 tools/ebpf/Makefile.ebpf   |  22 ++
 tools/ebpf/rss.bpf.c   | 571 +
 27 files changed, 1609 insertions(+), 4 deletions(-)
 create mode 100644 docs/devel/ebpf_rss.rst
 create mode 100644 ebpf/ebpf_rss-stub.c
 create mode 100644 ebpf/ebpf_rss.c
 create mode 100644 ebpf/ebpf_rss.h
 create mode 100644 ebpf/meson.build
 create mode 100644 ebpf/rss.bpf.skeleton.h
 create mode 100644 ebpf/trace-events
 create mode 100644 ebpf/trace.h
 create mode 100755 tools/ebpf/Makefile.ebpf
 create mode 100644 tools/ebpf/rss.bpf.c

-- 
2.31.1

[PATCH v7 4/7] ebpf: Added eBPF RSS loader.

2021-04-28 Thread Andrew Melnychenko

Added function that loads RSS eBPF program.
Added stub functions for RSS eBPF loader.
Added meson and configuration options.

By default, eBPF feature enabled if libbpf is present in the build system.
libbpf checked in configuration shell script and meson script.

Signed-off-by: Yuri Benditovich 
Signed-off-by: Andrew Melnychenko 
---
 configure   |   8 +-
 ebpf/ebpf_rss-stub.c|  40 
 ebpf/ebpf_rss.c | 165 +++
 ebpf/ebpf_rss.h |  44 
 ebpf/meson.build|   1 +
 ebpf/rss.bpf.skeleton.h | 431 
 ebpf/trace-events   |   4 +
 ebpf/trace.h|   2 +
 meson.build |  23 +++
 meson_options.txt   |   2 +
 10 files changed, 719 insertions(+), 1 deletion(-)
 create mode 100644 ebpf/ebpf_rss-stub.c
 create mode 100644 ebpf/ebpf_rss.c
 create mode 100644 ebpf/ebpf_rss.h
 create mode 100644 ebpf/meson.build
 create mode 100644 ebpf/rss.bpf.skeleton.h
 create mode 100644 ebpf/trace-events
 create mode 100644 ebpf/trace.h

diff --git a/configure b/configure
index 4f374b4889..7d9e0391a0 100755
--- a/configure
+++ b/configure
@@ -348,6 +348,7 @@ 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"
@@ -1228,6 +1229,10 @@ for opt do
   ;;
   --enable-membarrier) membarrier="yes"
   ;;
+  --disable-bpf) bpf="disabled"
+  ;;
+  --enable-bpf) bpf="enabled"
+  ;;
   --disable-blobs) blobs="false"
   ;;
   --with-pkgversion=*) pkgversion="$optarg"
@@ -1865,6 +1870,7 @@ disabled with --disable-FEATURE, default is enabled if 
available
   vhost-user  vhost-user backend support
   vhost-user-blk-servervhost-user-blk server support
   vhost-vdpa  vhost-vdpa kernel backend support
+  bpf BPF kernel support
   spice   spice
   rbd rados block device (rbd)
   libiscsiiscsi support
@@ -6423,7 +6429,7 @@ NINJA=$ninja $meson setup \
 -Dattr=$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 \
diff --git a/ebpf/ebpf_rss-stub.c b/ebpf/ebpf_rss-stub.c
new file mode 100644
index 00..e71e229190
--- /dev/null
+++ b/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 
+ *
+ * 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)
+{
+
+}
diff --git a/ebpf/ebpf_rss.c b/ebpf/ebpf_rss.c
new file mode 100644
index 00..118c68da83
--- /dev/null
+++ b/ebpf/ebpf_rss.c
@@ -0,0 +1,165 @@
+/*
+ * eBPF RSS loader
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *  Yuri Benditovich 
+ *
+ * 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 
+#include 
+
+#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;
+}
+
+

[PATCH v7 7/7] MAINTAINERS: Added eBPF maintainers information.

2021-04-28 Thread Andrew Melnychenko

Signed-off-by: Yuri Benditovich 
Signed-off-by: Andrew Melnychenko 
---
 MAINTAINERS | 8 
 1 file changed, 8 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 36055f14c5..c7e9a57cd9 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3312,6 +3312,14 @@ F: include/hw/remote/proxy-memory-listener.h
 F: hw/remote/iohub.c
 F: include/hw/remote/iohub.h
 
+EBPF:
+M: Jason Wang 
+R: Andrew Melnychenko 
+R: Yuri Benditovich 
+S: Maintained
+F: ebpf/*
+F: tools/ebpf/*
+
 Build and test automation
 -
 Build and test automation, general continuous integration
-- 
2.31.1

[PATCH v7 6/7] docs: Added eBPF documentation.

2021-04-28 Thread Andrew Melnychenko

Signed-off-by: Yuri Benditovich 
Signed-off-by: Andrew Melnychenko 
---
 docs/devel/ebpf_rss.rst | 125 
 docs/devel/index.rst|   1 +
 2 files changed, 126 insertions(+)
 create mode 100644 docs/devel/ebpf_rss.rst

diff --git a/docs/devel/ebpf_rss.rst b/docs/devel/ebpf_rss.rst
new file mode 100644
index 00..e00962577a
--- /dev/null
+++ b/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()%]
+
+
+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 = VI

[PATCH v7 3/7] ebpf: Added eBPF RSS program.

2021-04-28 Thread Andrew Melnychenko

RSS program and Makefile to build it.
The bpftool used to generate '.h' file.
The data in that file may be loaded by libbpf.
EBPF compilation is not required for building qemu.
You can use Makefile if you need to regenerate rss.bpf.skeleton.h.

Signed-off-by: Yuri Benditovich 
Signed-off-by: Andrew Melnychenko 
---
 tools/ebpf/Makefile.ebpf |  22 ++
 tools/ebpf/rss.bpf.c | 569 +++
 2 files changed, 591 insertions(+)
 create mode 100755 tools/ebpf/Makefile.ebpf
 create mode 100644 tools/ebpf/rss.bpf.c

diff --git a/tools/ebpf/Makefile.ebpf b/tools/ebpf/Makefile.ebpf
new file mode 100755
index 00..45b5551fc7
--- /dev/null
+++ b/tools/ebpf/Makefile.ebpf
@@ -0,0 +1,22 @@
+OBJS = rss.bpf.o
+
+LLC ?= llc
+CLANG ?= clang
+INC_FLAGS = `$(CLANG) -print-file-name=include`
+EXTRA_CFLAGS ?= -O2 -emit-llvm -fno-stack-protector
+
+all: $(OBJS)
+
+.PHONY: clean
+
+clean:
+   rm -f $(OBJS)
+
+$(OBJS):  %.o:%.c
+   $(CLANG) $(INC_FLAGS) \
+-D__KERNEL__ -D__ASM_SYSREG_H \
+-I../include $(LINUXINCLUDE) \
+$(EXTRA_CFLAGS) -c $< -o -| $(LLC) -march=bpf -filetype=obj -o 
$@
+   bpftool gen skeleton rss.bpf.o > rss.bpf.skeleton.h
+   cp rss.bpf.skeleton.h ../../ebpf/
+
diff --git a/tools/ebpf/rss.bpf.c b/tools/ebpf/rss.bpf.c
new file mode 100644
index 00..9d57ab4212
--- /dev/null
+++ b/tools/ebpf/rss.bpf.c
@@ -0,0 +1,569 @@
+/*
+ * eBPF RSS program
+ *
+ * Developed by Daynix Computing LTD (http://www.daynix.com)
+ *
+ * Authors:
+ *  Andrew Melnychenko 
+ *  Yuri Benditovich 
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ * Prepare:
+ * Requires llvm, clang, bpftool, linux kernel tree
+ *
+ * Build rss.bpf.skeleton.h:
+ * make -f Makefile.ebpf clean all
+ */
+
+#include 
+#include 
+#include 
+
+#include 
+#include 
+#include 
+#include 
+
+#include 
+#include 
+
+#include 
+#include 
+#include 
+
+#define INDIRECTION_TABLE_SIZE 128
+#define HASH_CALCULATION_BUFFER_SIZE 36
+
+struct rss_config_t {
+__u8 redirect;
+__u8 populate_hash;
+__u32 hash_types;
+__u16 indirections_len;
+__u16 default_queue;
+} __attribute__((packed));
+
+struct toeplitz_key_data_t {
+__u32 leftmost_32_bits;
+__u8 next_byte[HASH_CALCULATION_BUFFER_SIZE];
+};
+
+struct packet_hash_info_t {
+__u8 is_ipv4;
+__u8 is_ipv6;
+__u8 is_udp;
+__u8 is_tcp;
+__u8 is_ipv6_ext_src;
+__u8 is_ipv6_ext_dst;
+__u8 is_fragmented;
+
+__u16 src_port;
+__u16 dst_port;
+
+union {
+struct {
+__be32 in_src;
+__be32 in_dst;
+};
+
+struct {
+struct in6_addr in6_src;
+struct in6_addr in6_dst;
+struct in6_addr in6_ext_src;
+struct in6_addr in6_ext_dst;
+};
+};
+};
+
+struct bpf_map_def SEC("maps")
+tap_rss_map_configurations = {
+.type= BPF_MAP_TYPE_ARRAY,
+.key_size= sizeof(__u32),
+.value_size  = sizeof(struct rss_config_t),
+.max_entries = 1,
+};
+
+struct bpf_map_def SEC("maps")
+tap_rss_map_toeplitz_key = {
+.type= BPF_MAP_TYPE_ARRAY,
+.key_size= sizeof(__u32),
+.value_size  = sizeof(struct toeplitz_key_data_t),
+.max_entries = 1,
+};
+
+struct bpf_map_def SEC("maps")
+tap_rss_map_indirection_table = {
+.type= BPF_MAP_TYPE_ARRAY,
+.key_size= sizeof(__u32),
+.value_size  = sizeof(__u16),
+.max_entries = INDIRECTION_TABLE_SIZE,
+};
+
+static inline void net_rx_rss_add_chunk(__u8 *rss_input, size_t *bytes_written,
+const void *ptr, size_t size) {
+__builtin_memcpy(_input[*bytes_written], ptr, size);
+*bytes_written += size;
+}
+
+static inline
+void net_toeplitz_add(__u32 *result,
+  __u8 *input,
+  __u32 len
+, struct toeplitz_key_data_t *key) {
+
+__u32 accumulator = *result;
+__u32 leftmost_32_bits = key->leftmost_32_bits;
+__u32 byte;
+
+for (byte = 0; byte < HASH_CALCULATION_BUFFER_SIZE; byte++) {
+__u8 input_byte = input[byte];
+__u8 key_byte = key->next_byte[byte];
+__u8 bit;
+
+for (bit = 0; bit < 8; bit++) {
+if (input_byte & (1 << 7)) {
+accumulator ^= leftmost_32_bits;
+}
+
+leftmost_32_bits =
+(leftmost_32_bits << 1) | ((key_byte & (1 << 7)) >> 7);
+
+input_byte <<= 1;
+key_byte <<= 1;
+}
+}
+
+*result = accumulator;
+}
+
+
+static inline int ip6_extension_header_type(__u8 hdr_type)
+{
+switch (hdr_type) {
+case IPPROTO_HOPOPTS:
+case IPPROTO_ROUTING:
+case IPPROTO_FRAGMENT:
+case IPPROTO_ICMPV6

1 2 >

1 - 100 of 153 matches

Mail list logo