Initial commit: Linux kernel 4.19 for Unplugged OS

This commit is contained in:
ziv committed 2025-10-06 13:52:42 +00:00
commit d30235b04c
80519 files changed
+35800681

No files matched your search

+167
View File
@@ -0,0 +1,167 @@
# SPDX-License-Identifier: GPL-2.0
TARGETS = android
TARGETS += bpf
TARGETS += breakpoints
TARGETS += capabilities
TARGETS += cgroup
TARGETS += cpufreq
TARGETS += cpu-hotplug
TARGETS += efivarfs
TARGETS += exec
TARGETS += filesystems
TARGETS += firmware
TARGETS += ftrace
TARGETS += futex
TARGETS += gpio
TARGETS += intel_pstate
TARGETS += ipc
TARGETS += kcmp
TARGETS += kvm
TARGETS += lib
TARGETS += membarrier
TARGETS += memfd
TARGETS += memory-hotplug
TARGETS += mount
TARGETS += mqueue
TARGETS += net
TARGETS += netfilter
TARGETS += nsfs
TARGETS += powerpc
TARGETS += proc
TARGETS += pstore
TARGETS += ptrace
TARGETS += rseq
TARGETS += rtc
TARGETS += seccomp
TARGETS += sigaltstack
TARGETS += size
TARGETS += sparc64
TARGETS += splice
TARGETS += static_keys
TARGETS += sync
TARGETS += sysctl
ifneq (1, $(quicktest))
TARGETS += timers
endif
TARGETS += user
TARGETS += vm
TARGETS += x86
TARGETS += zram
#Please keep the TARGETS list alphabetically sorted
# Run "make quicktest=1 run_tests" or
# "make quicktest=1 kselftest" from top level Makefile
TARGETS_HOTPLUG = cpu-hotplug
TARGETS_HOTPLUG += memory-hotplug
# Clear LDFLAGS and MAKEFLAGS if called from main
# Makefile to avoid test build failures when test
# Makefile doesn't have explicit build rules.
ifeq (1,$(MAKELEVEL))
override LDFLAGS =
override MAKEFLAGS =
endif
ifneq ($(KBUILD_SRC),)
override LDFLAGS =
endif
BUILD := $(O)
ifndef BUILD
BUILD := $(KBUILD_OUTPUT)
endif
ifndef BUILD
BUILD := $(shell pwd)
endif
# KSFT_TAP_LEVEL is used from KSFT framework to prevent nested TAP header
# printing from tests. Applicable to run_tests case where run_tests adds
# TAP header prior running tests and when a test program invokes another
# with system() call. Export it here to cover override RUN_TESTS defines.
export KSFT_TAP_LEVEL=`echo 1`
export BUILD
all:
@for TARGET in $(TARGETS); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
mkdir $$BUILD_TARGET -p; \
make OUTPUT=$$BUILD_TARGET -C $$TARGET;\
done;
run_tests: all
@for TARGET in $(TARGETS); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
make OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\
done;
hotplug:
@for TARGET in $(TARGETS_HOTPLUG); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
make OUTPUT=$$BUILD_TARGET -C $$TARGET;\
done;
run_hotplug: hotplug
@for TARGET in $(TARGETS_HOTPLUG); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
make OUTPUT=$$BUILD_TARGET -C $$TARGET run_full_test;\
done;
clean_hotplug:
@for TARGET in $(TARGETS_HOTPLUG); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
make OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\
done;
run_pstore_crash:
make -C pstore run_crash
INSTALL_PATH ?= install
INSTALL_PATH := $(abspath $(INSTALL_PATH))
ALL_SCRIPT := $(INSTALL_PATH)/run_kselftest.sh
install:
ifdef INSTALL_PATH
@# Ask all targets to install their files
mkdir -p $(INSTALL_PATH)
@for TARGET in $(TARGETS); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
make OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \
done;
@# Ask all targets to emit their test scripts
echo "#!/bin/sh" > $(ALL_SCRIPT)
echo "BASE_DIR=\$$(realpath \$$(dirname \$$0))" >> $(ALL_SCRIPT)
echo "cd \$$BASE_DIR" >> $(ALL_SCRIPT)
echo "ROOT=\$$PWD" >> $(ALL_SCRIPT)
echo "if [ \"\$$1\" = \"--summary\" ]; then" >> $(ALL_SCRIPT)
echo " OUTPUT=\$$BASE_DIR/output.log" >> $(ALL_SCRIPT)
echo " cat /dev/null > \$$OUTPUT" >> $(ALL_SCRIPT)
echo "else" >> $(ALL_SCRIPT)
echo " OUTPUT=/dev/stdout" >> $(ALL_SCRIPT)
echo "fi" >> $(ALL_SCRIPT)
echo "export KSFT_TAP_LEVEL=1" >> $(ALL_SCRIPT)
echo "export skip=4" >> $(ALL_SCRIPT)
for TARGET in $(TARGETS); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
echo "echo ; echo TAP version 13" >> $(ALL_SCRIPT); \
echo "echo Running tests in $$TARGET" >> $(ALL_SCRIPT); \
echo "echo ========================================" >> $(ALL_SCRIPT); \
echo "[ -w /dev/kmsg ] && echo \"kselftest: Running tests in $$TARGET\" >> /dev/kmsg" >> $(ALL_SCRIPT); \
echo "cd $$TARGET" >> $(ALL_SCRIPT); \
make -s --no-print-directory OUTPUT=$$BUILD_TARGET -C $$TARGET emit_tests >> $(ALL_SCRIPT); \
echo "cd \$$ROOT" >> $(ALL_SCRIPT); \
done;
chmod u+x $(ALL_SCRIPT)
else
$(error Error: set INSTALL_PATH to use install)
endif
clean:
@for TARGET in $(TARGETS); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
make OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\
done;
.PHONY: all run_tests hotplug run_hotplug clean_hotplug run_pstore_crash install clean
+38
View File
@@ -0,0 +1,38 @@
SUBDIRS := ion
TEST_PROGS := run.sh
.PHONY: all clean
include ../lib.mk
all:
@for DIR in $(SUBDIRS); do \
BUILD_TARGET=$(OUTPUT)/$$DIR; \
mkdir $$BUILD_TARGET -p; \
make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
#SUBDIR test prog name should be in the form: SUBDIR_test.sh \
TEST=$$DIR"_test.sh"; \
if [ -e $$DIR/$$TEST ]; then \
rsync -a $$DIR/$$TEST $$BUILD_TARGET/; \
fi \
done
override define INSTALL_RULE
mkdir -p $(INSTALL_PATH)
install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)
@for SUBDIR in $(SUBDIRS); do \
BUILD_TARGET=$(OUTPUT)/$$SUBDIR; \
mkdir $$BUILD_TARGET -p; \
$(MAKE) OUTPUT=$$BUILD_TARGET -C $$SUBDIR INSTALL_PATH=$(INSTALL_PATH)/$$SUBDIR install; \
done;
endef
override define CLEAN
@for DIR in $(SUBDIRS); do \
BUILD_TARGET=$(OUTPUT)/$$DIR; \
mkdir $$BUILD_TARGET -p; \
make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
done
endef
+5
View File
@@ -0,0 +1,5 @@
CONFIG_ANDROID=y
CONFIG_STAGING=y
CONFIG_ION=y
CONFIG_ION_SYSTEM_HEAP=y
CONFIG_DRM_VGEM=y
@@ -0,0 +1,19 @@
INCLUDEDIR := -I. -I../../../../../drivers/staging/android/uapi/ -I../../../../../usr/include/
CFLAGS := $(CFLAGS) $(INCLUDEDIR) -Wall -O2 -g
TEST_GEN_FILES := ionapp_export ionapp_import ionmap_test
all: $(TEST_GEN_FILES)
$(TEST_GEN_FILES): ipcsocket.c ionutils.c
TEST_PROGS := ion_test.sh
KSFT_KHDR_INSTALL := 1
top_srcdir = ../../../../..
include ../../lib.mk
$(OUTPUT)/ionapp_export: ionapp_export.c ipcsocket.c ionutils.c
$(OUTPUT)/ionapp_import: ionapp_import.c ipcsocket.c ionutils.c
$(OUTPUT)/ionmap_test: ionmap_test.c ionutils.c
+101
View File
@@ -0,0 +1,101 @@
ION BUFFER SHARING UTILITY
==========================
File: ion_test.sh : Utility to test ION driver buffer sharing mechanism.
Author: Pintu Kumar <pintu.ping@gmail.com>
Introduction:
-------------
This is a test utility to verify ION buffer sharing in user space
between 2 independent processes.
It uses unix domain socket (with SCM_RIGHTS) as IPC to transfer an FD to
another process to share the same buffer.
This utility demonstrates how ION buffer sharing can be implemented between
two user space processes, using various heap types.
The following heap types are supported by ION driver.
ION_HEAP_TYPE_SYSTEM (0)
ION_HEAP_TYPE_SYSTEM_CONTIG (1)
ION_HEAP_TYPE_CARVEOUT (2)
ION_HEAP_TYPE_CHUNK (3)
ION_HEAP_TYPE_DMA (4)
By default only the SYSTEM and SYSTEM_CONTIG heaps are supported.
Each heap is associated with the respective heap id.
This utility is designed in the form of client/server program.
The server part (ionapp_export) is the exporter of the buffer.
It is responsible for creating an ION client, allocating the buffer based on
the heap id, writing some data to this buffer and then exporting the FD
(associated with this buffer) to another process using socket IPC.
This FD is called as buffer FD (which is different than the ION client FD).
The client part (ionapp_import) is the importer of the buffer.
It retrives the FD from the socket data and installs into its address space.
This new FD internally points to the same kernel buffer.
So first it reads the data that is stored in this buffer and prints it.
Then it writes the different size of data (it could be different data) to the
same buffer.
Finally the buffer FD must be closed by both the exporter and importer.
Thus the same kernel buffer is shared among two user space processes using
ION driver and only one time allocation.
Prerequisite:
-------------
This utility works only if /dev/ion interface is present.
The following configs needs to be enabled in kernel to include ion driver.
CONFIG_ANDROID=y
CONFIG_STAGING=y
CONFIG_ION=y
CONFIG_ION_SYSTEM_HEAP=y
This utility requires to be run as root user.
Compile and test:
-----------------
This utility is made to be run as part of kselftest framework in kernel.
To compile and run using kselftest you can simply do the following from the
kernel top directory.
linux$ make TARGETS=android kselftest
Or you can also use:
linux$ make -C tools/testing/selftests TARGETS=android run_tests
Using the selftest it can directly execute the ion_test.sh script to test the
buffer sharing using ion system heap.
Currently the heap size is hard coded as just 10 bytes inside this script.
You need to be a root user to run under selftest.
You can also compile and test manually using the following steps:
ion$ make
These will generate 2 executable: ionapp_export, ionapp_import
Now you can run the export and import manually by specifying the heap type
and the heap size.
You can also directly execute the shell script to run the test automatically.
Simply use the following command to run the test.
ion$ sudo ./ion_test.sh
Test Results:
-------------
The utility is verified on Ubuntu-32 bit system with Linux Kernel 4.14.
Here is the snapshot of the test result using kselftest.
linux# make TARGETS=android kselftest
heap_type: 0, heap_size: 10
--------------------------------------
heap type: 0
heap id: 1
heap name: ion_system_heap
--------------------------------------
Fill buffer content:
0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd
Sharing fd: 6, Client fd: 5
<ion_close_buffer_fd>: buffer release successfully....
Received buffer fd: 4
Read buffer content:
0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0x0 0x0 0x0 0x0 0x0 0x0
0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0
Fill buffer content:
0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd
0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd
0xfd 0xfd
<ion_close_buffer_fd>: buffer release successfully....
ion_test.sh: heap_type: 0 - [PASS]
ion_test.sh: done
+143
View File
@@ -0,0 +1,143 @@
/*
* ion.h
*
* Copyright (C) 2011 Google, Inc.
*
* This software is licensed under the terms of the GNU General Public
* License version 2, as published by the Free Software Foundation, and
* may be copied, distributed, and modified under those terms.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
*/
/* This file is copied from drivers/staging/android/uapi/ion.h
* This local copy is required for the selftest to pass, when build
* outside the kernel source tree.
* Please keep this file in sync with its original file until the
* ion driver is moved outside the staging tree.
*/
#ifndef _UAPI_LINUX_ION_H
#define _UAPI_LINUX_ION_H
#include <linux/ioctl.h>
#include <linux/types.h>
/**
* enum ion_heap_types - list of all possible types of heaps
* @ION_HEAP_TYPE_SYSTEM: memory allocated via vmalloc
* @ION_HEAP_TYPE_SYSTEM_CONTIG: memory allocated via kmalloc
* @ION_HEAP_TYPE_CARVEOUT: memory allocated from a prereserved
* carveout heap, allocations are physically
* contiguous
* @ION_HEAP_TYPE_DMA: memory allocated via DMA API
* @ION_NUM_HEAPS: helper for iterating over heaps, a bit mask
* is used to identify the heaps, so only 32
* total heap types are supported
*/
enum ion_heap_type {
ION_HEAP_TYPE_SYSTEM,
ION_HEAP_TYPE_SYSTEM_CONTIG,
ION_HEAP_TYPE_CARVEOUT,
ION_HEAP_TYPE_CHUNK,
ION_HEAP_TYPE_DMA,
ION_HEAP_TYPE_CUSTOM, /*
* must be last so device specific heaps always
* are at the end of this enum
*/
};
#define ION_NUM_HEAP_IDS (sizeof(unsigned int) * 8)
/**
* allocation flags - the lower 16 bits are used by core ion, the upper 16
* bits are reserved for use by the heaps themselves.
*/
/*
* mappings of this buffer should be cached, ion will do cache maintenance
* when the buffer is mapped for dma
*/
#define ION_FLAG_CACHED 1
/**
* DOC: Ion Userspace API
*
* create a client by opening /dev/ion
* most operations handled via following ioctls
*
*/
/**
* struct ion_allocation_data - metadata passed from userspace for allocations
* @len: size of the allocation
* @heap_id_mask: mask of heap ids to allocate from
* @flags: flags passed to heap
* @handle: pointer that will be populated with a cookie to use to
* refer to this allocation
*
* Provided by userspace as an argument to the ioctl
*/
struct ion_allocation_data {
__u64 len;
__u32 heap_id_mask;
__u32 flags;
__u32 fd;
__u32 unused;
};
#define MAX_HEAP_NAME 32
/**
* struct ion_heap_data - data about a heap
* @name - first 32 characters of the heap name
* @type - heap type
* @heap_id - heap id for the heap
*/
struct ion_heap_data {
char name[MAX_HEAP_NAME];
__u32 type;
__u32 heap_id;
__u32 reserved0;
__u32 reserved1;
__u32 reserved2;
};
/**
* struct ion_heap_query - collection of data about all heaps
* @cnt - total number of heaps to be copied
* @heaps - buffer to copy heap data
*/
struct ion_heap_query {
__u32 cnt; /* Total number of heaps to be copied */
__u32 reserved0; /* align to 64bits */
__u64 heaps; /* buffer to be populated */
__u32 reserved1;
__u32 reserved2;
};
#define ION_IOC_MAGIC 'I'
/**
* DOC: ION_IOC_ALLOC - allocate memory
*
* Takes an ion_allocation_data struct and returns it with the handle field
* populated with the opaque handle for the allocation.
*/
#define ION_IOC_ALLOC _IOWR(ION_IOC_MAGIC, 0, \
struct ion_allocation_data)
/**
* DOC: ION_IOC_HEAP_QUERY - information about available heaps
*
* Takes an ion_heap_query structure and populates information about
* available Ion heaps.
*/
#define ION_IOC_HEAP_QUERY _IOWR(ION_IOC_MAGIC, 8, \
struct ion_heap_query)
#endif /* _UAPI_LINUX_ION_H */
+58
View File
@@ -0,0 +1,58 @@
#!/bin/bash
heapsize=4096
TCID="ion_test.sh"
errcode=0
# Kselftest framework requirement - SKIP code is 4.
ksft_skip=4
run_test()
{
heaptype=$1
./ionapp_export -i $heaptype -s $heapsize &
sleep 1
./ionapp_import
if [ $? -ne 0 ]; then
echo "$TCID: heap_type: $heaptype - [FAIL]"
errcode=1
else
echo "$TCID: heap_type: $heaptype - [PASS]"
fi
sleep 1
echo ""
}
check_root()
{
uid=$(id -u)
if [ $uid -ne 0 ]; then
echo $TCID: must be run as root >&2
exit $ksft_skip
fi
}
check_device()
{
DEVICE=/dev/ion
if [ ! -e $DEVICE ]; then
echo $TCID: No $DEVICE device found >&2
echo $TCID: May be CONFIG_ION is not set >&2
exit $ksft_skip
fi
}
main_function()
{
check_device
check_root
# ION_SYSTEM_HEAP TEST
run_test 0
# ION_SYSTEM_CONTIG_HEAP TEST
run_test 1
}
main_function
echo "$TCID: done"
exit $errcode
@@ -0,0 +1,136 @@
/*
* ionapp_export.c
*
* It is a user space utility to create and export android
* ion memory buffer fd to another process using unix domain socket as IPC.
* This acts like a server for ionapp_import(client).
* So, this server has to be started first before the client.
*
* Copyright (C) 2017 Pintu Kumar <pintu.ping@gmail.com>
*
* This software is licensed under the terms of the GNU General Public
* License version 2, as published by the Free Software Foundation, and
* may be copied, distributed, and modified under those terms.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
*/
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <errno.h>
#include <sys/time.h>
#include "ionutils.h"
#include "ipcsocket.h"
void print_usage(int argc, char *argv[])
{
printf("Usage: %s [-h <help>] [-i <heap id>] [-s <size in bytes>]\n",
argv[0]);
}
int main(int argc, char *argv[])
{
int opt, ret, status, heapid;
int sockfd, client_fd, shared_fd;
unsigned char *map_buf;
unsigned long map_len, heap_type, heap_size, flags;
struct ion_buffer_info info;
struct socket_info skinfo;
if (argc < 2) {
print_usage(argc, argv);
return -1;
}
heap_size = 0;
flags = 0;
heap_type = ION_HEAP_TYPE_SYSTEM;
while ((opt = getopt(argc, argv, "hi:s:")) != -1) {
switch (opt) {
case 'h':
print_usage(argc, argv);
exit(0);
break;
case 'i':
heapid = atoi(optarg);
switch (heapid) {
case 0:
heap_type = ION_HEAP_TYPE_SYSTEM;
break;
case 1:
heap_type = ION_HEAP_TYPE_SYSTEM_CONTIG;
break;
default:
printf("ERROR: heap type not supported\n");
exit(1);
}
break;
case 's':
heap_size = atoi(optarg);
break;
default:
print_usage(argc, argv);
exit(1);
break;
}
}
if (heap_size <= 0) {
printf("heap_size cannot be 0\n");
print_usage(argc, argv);
exit(1);
}
printf("heap_type: %ld, heap_size: %ld\n", heap_type, heap_size);
info.heap_type = heap_type;
info.heap_size = heap_size;
info.flag_type = flags;
/* This is server: open the socket connection first */
/* Here; 1 indicates server or exporter */
status = opensocket(&sockfd, SOCKET_NAME, 1);
if (status < 0) {
fprintf(stderr, "<%s>: Failed opensocket.\n", __func__);
goto err_socket;
}
skinfo.sockfd = sockfd;
ret = ion_export_buffer_fd(&info);
if (ret < 0) {
fprintf(stderr, "FAILED: ion_get_buffer_fd\n");
goto err_export;
}
client_fd = info.ionfd;
shared_fd = info.buffd;
map_buf = info.buffer;
map_len = info.buflen;
write_buffer(map_buf, map_len);
/* share ion buf fd with other user process */
printf("Sharing fd: %d, Client fd: %d\n", shared_fd, client_fd);
skinfo.datafd = shared_fd;
skinfo.buflen = map_len;
ret = socket_send_fd(&skinfo);
if (ret < 0) {
fprintf(stderr, "FAILED: socket_send_fd\n");
goto err_send;
}
err_send:
err_export:
ion_close_buffer_fd(&info);
err_socket:
closesocket(sockfd, SOCKET_NAME);
return 0;
}
@@ -0,0 +1,88 @@
/*
* ionapp_import.c
*
* It is a user space utility to receive android ion memory buffer fd
* over unix domain socket IPC that can be exported by ionapp_export.
* This acts like a client for ionapp_export.
*
* Copyright (C) 2017 Pintu Kumar <pintu.ping@gmail.com>
*
* This software is licensed under the terms of the GNU General Public
* License version 2, as published by the Free Software Foundation, and
* may be copied, distributed, and modified under those terms.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
*/
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <string.h>
#include "ionutils.h"
#include "ipcsocket.h"
int main(void)
{
int ret, status;
int sockfd, shared_fd;
unsigned char *map_buf;
unsigned long map_len;
struct ion_buffer_info info;
struct socket_info skinfo;
/* This is the client part. Here 0 means client or importer */
status = opensocket(&sockfd, SOCKET_NAME, 0);
if (status < 0) {
fprintf(stderr, "No exporter exists...\n");
ret = status;
goto err_socket;
}
skinfo.sockfd = sockfd;
ret = socket_receive_fd(&skinfo);
if (ret < 0) {
fprintf(stderr, "Failed: socket_receive_fd\n");
goto err_recv;
}
shared_fd = skinfo.datafd;
printf("Received buffer fd: %d\n", shared_fd);
if (shared_fd <= 0) {
fprintf(stderr, "ERROR: improper buf fd\n");
ret = -1;
goto err_fd;
}
memset(&info, 0, sizeof(info));
info.buffd = shared_fd;
info.buflen = ION_BUFFER_LEN;
ret = ion_import_buffer_fd(&info);
if (ret < 0) {
fprintf(stderr, "Failed: ion_use_buffer_fd\n");
goto err_import;
}
map_buf = info.buffer;
map_len = info.buflen;
read_buffer(map_buf, map_len);
/* Write probably new data to the same buffer again */
map_len = ION_BUFFER_LEN;
write_buffer(map_buf, map_len);
err_import:
ion_close_buffer_fd(&info);
err_fd:
err_recv:
err_socket:
closesocket(sockfd, SOCKET_NAME);
return ret;
}
@@ -0,0 +1,136 @@
#include <errno.h>
#include <fcntl.h>
#include <stdio.h>
#include <stdint.h>
#include <string.h>
#include <unistd.h>
#include <sys/ioctl.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <linux/dma-buf.h>
#include <drm/drm.h>
#include "ion.h"
#include "ionutils.h"
int check_vgem(int fd)
{
drm_version_t version = { 0 };
char name[5];
int ret;
version.name_len = 4;
version.name = name;
ret = ioctl(fd, DRM_IOCTL_VERSION, &version);
if (ret)
return 1;
return strcmp(name, "vgem");
}
int open_vgem(void)
{
int i, fd;
const char *drmstr = "/dev/dri/card";
fd = -1;
for (i = 0; i < 16; i++) {
char name[80];
sprintf(name, "%s%u", drmstr, i);
fd = open(name, O_RDWR);
if (fd < 0)
continue;
if (check_vgem(fd)) {
close(fd);
continue;
} else {
break;
}
}
return fd;
}
int import_vgem_fd(int vgem_fd, int dma_buf_fd, uint32_t *handle)
{
struct drm_prime_handle import_handle = { 0 };
int ret;
import_handle.fd = dma_buf_fd;
import_handle.flags = 0;
import_handle.handle = 0;
ret = ioctl(vgem_fd, DRM_IOCTL_PRIME_FD_TO_HANDLE, &import_handle);
if (ret == 0)
*handle = import_handle.handle;
return ret;
}
void close_handle(int vgem_fd, uint32_t handle)
{
struct drm_gem_close close = { 0 };
close.handle = handle;
ioctl(vgem_fd, DRM_IOCTL_GEM_CLOSE, &close);
}
int main()
{
int ret, vgem_fd;
struct ion_buffer_info info;
uint32_t handle = 0;
struct dma_buf_sync sync = { 0 };
info.heap_type = ION_HEAP_TYPE_SYSTEM;
info.heap_size = 4096;
info.flag_type = ION_FLAG_CACHED;
ret = ion_export_buffer_fd(&info);
if (ret < 0) {
printf("ion buffer alloc failed\n");
return -1;
}
vgem_fd = open_vgem();
if (vgem_fd < 0) {
ret = vgem_fd;
printf("Failed to open vgem\n");
goto out_ion;
}
ret = import_vgem_fd(vgem_fd, info.buffd, &handle);
if (ret < 0) {
printf("Failed to import buffer\n");
goto out_vgem;
}
sync.flags = DMA_BUF_SYNC_START | DMA_BUF_SYNC_RW;
ret = ioctl(info.buffd, DMA_BUF_IOCTL_SYNC, &sync);
if (ret)
printf("sync start failed %d\n", errno);
memset(info.buffer, 0xff, 4096);
sync.flags = DMA_BUF_SYNC_END | DMA_BUF_SYNC_RW;
ret = ioctl(info.buffd, DMA_BUF_IOCTL_SYNC, &sync);
if (ret)
printf("sync end failed %d\n", errno);
close_handle(vgem_fd, handle);
ret = 0;
out_vgem:
close(vgem_fd);
out_ion:
ion_close_buffer_fd(&info);
printf("done.\n");
return ret;
}
@@ -0,0 +1,253 @@
#include <stdio.h>
#include <string.h>
#include <unistd.h>
#include <fcntl.h>
#include <errno.h>
//#include <stdint.h>
#include <sys/ioctl.h>
#include <sys/mman.h>
#include "ionutils.h"
#include "ipcsocket.h"
void write_buffer(void *buffer, unsigned long len)
{
int i;
unsigned char *ptr = (unsigned char *)buffer;
if (!ptr) {
fprintf(stderr, "<%s>: Invalid buffer...\n", __func__);
return;
}
printf("Fill buffer content:\n");
memset(ptr, 0xfd, len);
for (i = 0; i < len; i++)
printf("0x%x ", ptr[i]);
printf("\n");
}
void read_buffer(void *buffer, unsigned long len)
{
int i;
unsigned char *ptr = (unsigned char *)buffer;
if (!ptr) {
fprintf(stderr, "<%s>: Invalid buffer...\n", __func__);
return;
}
printf("Read buffer content:\n");
for (i = 0; i < len; i++)
printf("0x%x ", ptr[i]);
printf("\n");
}
int ion_export_buffer_fd(struct ion_buffer_info *ion_info)
{
int i, ret, ionfd, buffer_fd;
unsigned int heap_id;
unsigned long maplen;
unsigned char *map_buffer;
struct ion_allocation_data alloc_data;
struct ion_heap_query query;
struct ion_heap_data heap_data[MAX_HEAP_COUNT];
if (!ion_info) {
fprintf(stderr, "<%s>: Invalid ion info\n", __func__);
return -1;
}
/* Create an ION client */
ionfd = open(ION_DEVICE, O_RDWR);
if (ionfd < 0) {
fprintf(stderr, "<%s>: Failed to open ion client: %s\n",
__func__, strerror(errno));
return -1;
}
memset(&query, 0, sizeof(query));
query.cnt = MAX_HEAP_COUNT;
query.heaps = (unsigned long int)&heap_data[0];
/* Query ION heap_id_mask from ION heap */
ret = ioctl(ionfd, ION_IOC_HEAP_QUERY, &query);
if (ret < 0) {
fprintf(stderr, "<%s>: Failed: ION_IOC_HEAP_QUERY: %s\n",
__func__, strerror(errno));
goto err_query;
}
heap_id = MAX_HEAP_COUNT + 1;
for (i = 0; i < query.cnt; i++) {
if (heap_data[i].type == ion_info->heap_type) {
heap_id = heap_data[i].heap_id;
break;
}
}
if (heap_id > MAX_HEAP_COUNT) {
fprintf(stderr, "<%s>: ERROR: heap type does not exists\n",
__func__);
goto err_heap;
}
alloc_data.len = ion_info->heap_size;
alloc_data.heap_id_mask = 1 << heap_id;
alloc_data.flags = ion_info->flag_type;
/* Allocate memory for this ION client as per heap_type */
ret = ioctl(ionfd, ION_IOC_ALLOC, &alloc_data);
if (ret < 0) {
fprintf(stderr, "<%s>: Failed: ION_IOC_ALLOC: %s\n",
__func__, strerror(errno));
goto err_alloc;
}
/* This will return a valid buffer fd */
buffer_fd = alloc_data.fd;
maplen = alloc_data.len;
if (buffer_fd < 0 || maplen <= 0) {
fprintf(stderr, "<%s>: Invalid map data, fd: %d, len: %ld\n",
__func__, buffer_fd, maplen);
goto err_fd_data;
}
/* Create memory mapped buffer for the buffer fd */
map_buffer = (unsigned char *)mmap(NULL, maplen, PROT_READ|PROT_WRITE,
MAP_SHARED, buffer_fd, 0);
if (map_buffer == MAP_FAILED) {
fprintf(stderr, "<%s>: Failed: mmap: %s\n",
__func__, strerror(errno));
goto err_mmap;
}
ion_info->ionfd = ionfd;
ion_info->buffd = buffer_fd;
ion_info->buffer = map_buffer;
ion_info->buflen = maplen;
return 0;
munmap(map_buffer, maplen);
err_fd_data:
err_mmap:
/* in case of error: close the buffer fd */
if (buffer_fd)
close(buffer_fd);
err_query:
err_heap:
err_alloc:
/* In case of error: close the ion client fd */
if (ionfd)
close(ionfd);
return -1;
}
int ion_import_buffer_fd(struct ion_buffer_info *ion_info)
{
int buffd;
unsigned char *map_buf;
unsigned long map_len;
if (!ion_info) {
fprintf(stderr, "<%s>: Invalid ion info\n", __func__);
return -1;
}
map_len = ion_info->buflen;
buffd = ion_info->buffd;
if (buffd < 0 || map_len <= 0) {
fprintf(stderr, "<%s>: Invalid map data, fd: %d, len: %ld\n",
__func__, buffd, map_len);
goto err_buffd;
}
map_buf = (unsigned char *)mmap(NULL, map_len, PROT_READ|PROT_WRITE,
MAP_SHARED, buffd, 0);
if (map_buf == MAP_FAILED) {
printf("<%s>: Failed - mmap: %s\n",
__func__, strerror(errno));
goto err_mmap;
}
ion_info->buffer = map_buf;
ion_info->buflen = map_len;
return 0;
err_mmap:
if (buffd)
close(buffd);
err_buffd:
return -1;
}
void ion_close_buffer_fd(struct ion_buffer_info *ion_info)
{
if (ion_info) {
/* unmap the buffer properly in the end */
munmap(ion_info->buffer, ion_info->buflen);
/* close the buffer fd */
if (ion_info->buffd > 0)
close(ion_info->buffd);
/* Finally, close the client fd */
if (ion_info->ionfd > 0)
close(ion_info->ionfd);
}
}
int socket_send_fd(struct socket_info *info)
{
int status;
int fd, sockfd;
struct socketdata skdata;
if (!info) {
fprintf(stderr, "<%s>: Invalid socket info\n", __func__);
return -1;
}
sockfd = info->sockfd;
fd = info->datafd;
memset(&skdata, 0, sizeof(skdata));
skdata.data = fd;
skdata.len = sizeof(skdata.data);
status = sendtosocket(sockfd, &skdata);
if (status < 0) {
fprintf(stderr, "<%s>: Failed: sendtosocket\n", __func__);
return -1;
}
return 0;
}
int socket_receive_fd(struct socket_info *info)
{
int status;
int fd, sockfd;
struct socketdata skdata;
if (!info) {
fprintf(stderr, "<%s>: Invalid socket info\n", __func__);
return -1;
}
sockfd = info->sockfd;
memset(&skdata, 0, sizeof(skdata));
status = receivefromsocket(sockfd, &skdata);
if (status < 0) {
fprintf(stderr, "<%s>: Failed: receivefromsocket\n", __func__);
return -1;
}
fd = (int)skdata.data;
info->datafd = fd;
return status;
}
@@ -0,0 +1,55 @@
#ifndef __ION_UTILS_H
#define __ION_UTILS_H
#include "ion.h"
#define SOCKET_NAME "ion_socket"
#define ION_DEVICE "/dev/ion"
#define ION_BUFFER_LEN 4096
#define MAX_HEAP_COUNT ION_HEAP_TYPE_CUSTOM
struct socket_info {
int sockfd;
int datafd;
unsigned long buflen;
};
struct ion_buffer_info {
int ionfd;
int buffd;
unsigned int heap_type;
unsigned int flag_type;
unsigned long heap_size;
unsigned long buflen;
unsigned char *buffer;
};
/* This is used to fill the data into the mapped buffer */
void write_buffer(void *buffer, unsigned long len);
/* This is used to read the data from the exported buffer */
void read_buffer(void *buffer, unsigned long len);
/* This is used to create an ION buffer FD for the kernel buffer
* So you can export this same buffer to others in the form of FD
*/
int ion_export_buffer_fd(struct ion_buffer_info *ion_info);
/* This is used to import or map an exported FD.
* So we point to same buffer without making a copy. Hence zero-copy.
*/
int ion_import_buffer_fd(struct ion_buffer_info *ion_info);
/* This is used to close all references for the ION client */
void ion_close_buffer_fd(struct ion_buffer_info *ion_info);
/* This is used to send FD to another process using socket IPC */
int socket_send_fd(struct socket_info *skinfo);
/* This is used to receive FD from another process using socket IPC */
int socket_receive_fd(struct socket_info *skinfo);
#endif
@@ -0,0 +1,227 @@
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <sys/time.h>
#include <sys/un.h>
#include <errno.h>
#include "ipcsocket.h"
int opensocket(int *sockfd, const char *name, int connecttype)
{
int ret, temp = 1;
if (!name || strlen(name) > MAX_SOCK_NAME_LEN) {
fprintf(stderr, "<%s>: Invalid socket name.\n", __func__);
return -1;
}
ret = socket(PF_LOCAL, SOCK_STREAM, 0);
if (ret < 0) {
fprintf(stderr, "<%s>: Failed socket: <%s>\n",
__func__, strerror(errno));
return ret;
}
*sockfd = ret;
if (setsockopt(*sockfd, SOL_SOCKET, SO_REUSEADDR,
(char *)&temp, sizeof(int)) < 0) {
fprintf(stderr, "<%s>: Failed setsockopt: <%s>\n",
__func__, strerror(errno));
goto err;
}
sprintf(sock_name, "/tmp/%s", name);
if (connecttype == 1) {
/* This is for Server connection */
struct sockaddr_un skaddr;
int clientfd;
socklen_t sklen;
unlink(sock_name);
memset(&skaddr, 0, sizeof(skaddr));
skaddr.sun_family = AF_LOCAL;
strcpy(skaddr.sun_path, sock_name);
ret = bind(*sockfd, (struct sockaddr *)&skaddr,
SUN_LEN(&skaddr));
if (ret < 0) {
fprintf(stderr, "<%s>: Failed bind: <%s>\n",
__func__, strerror(errno));
goto err;
}
ret = listen(*sockfd, 5);
if (ret < 0) {
fprintf(stderr, "<%s>: Failed listen: <%s>\n",
__func__, strerror(errno));
goto err;
}
memset(&skaddr, 0, sizeof(skaddr));
sklen = sizeof(skaddr);
ret = accept(*sockfd, (struct sockaddr *)&skaddr,
(socklen_t *)&sklen);
if (ret < 0) {
fprintf(stderr, "<%s>: Failed accept: <%s>\n",
__func__, strerror(errno));
goto err;
}
clientfd = ret;
*sockfd = clientfd;
} else {
/* This is for client connection */
struct sockaddr_un skaddr;
memset(&skaddr, 0, sizeof(skaddr));
skaddr.sun_family = AF_LOCAL;
strcpy(skaddr.sun_path, sock_name);
ret = connect(*sockfd, (struct sockaddr *)&skaddr,
SUN_LEN(&skaddr));
if (ret < 0) {
fprintf(stderr, "<%s>: Failed connect: <%s>\n",
__func__, strerror(errno));
goto err;
}
}
return 0;
err:
if (*sockfd)
close(*sockfd);
return ret;
}
int sendtosocket(int sockfd, struct socketdata *skdata)
{
int ret, buffd;
unsigned int len;
char cmsg_b[CMSG_SPACE(sizeof(int))];
struct cmsghdr *cmsg;
struct msghdr msgh;
struct iovec iov;
struct timeval timeout;
fd_set selFDs;
if (!skdata) {
fprintf(stderr, "<%s>: socketdata is NULL\n", __func__);
return -1;
}
FD_ZERO(&selFDs);
FD_SET(0, &selFDs);
FD_SET(sockfd, &selFDs);
timeout.tv_sec = 20;
timeout.tv_usec = 0;
ret = select(sockfd+1, NULL, &selFDs, NULL, &timeout);
if (ret < 0) {
fprintf(stderr, "<%s>: Failed select: <%s>\n",
__func__, strerror(errno));
return -1;
}
if (FD_ISSET(sockfd, &selFDs)) {
buffd = skdata->data;
len = skdata->len;
memset(&msgh, 0, sizeof(msgh));
msgh.msg_control = &cmsg_b;
msgh.msg_controllen = CMSG_LEN(len);
iov.iov_base = "OK";
iov.iov_len = 2;
msgh.msg_iov = &iov;
msgh.msg_iovlen = 1;
cmsg = CMSG_FIRSTHDR(&msgh);
cmsg->cmsg_level = SOL_SOCKET;
cmsg->cmsg_type = SCM_RIGHTS;
cmsg->cmsg_len = CMSG_LEN(len);
memcpy(CMSG_DATA(cmsg), &buffd, len);
ret = sendmsg(sockfd, &msgh, MSG_DONTWAIT);
if (ret < 0) {
fprintf(stderr, "<%s>: Failed sendmsg: <%s>\n",
__func__, strerror(errno));
return -1;
}
}
return 0;
}
int receivefromsocket(int sockfd, struct socketdata *skdata)
{
int ret, buffd;
unsigned int len = 0;
char cmsg_b[CMSG_SPACE(sizeof(int))];
struct cmsghdr *cmsg;
struct msghdr msgh;
struct iovec iov;
fd_set recvFDs;
char data[32];
if (!skdata) {
fprintf(stderr, "<%s>: socketdata is NULL\n", __func__);
return -1;
}
FD_ZERO(&recvFDs);
FD_SET(0, &recvFDs);
FD_SET(sockfd, &recvFDs);
ret = select(sockfd+1, &recvFDs, NULL, NULL, NULL);
if (ret < 0) {
fprintf(stderr, "<%s>: Failed select: <%s>\n",
__func__, strerror(errno));
return -1;
}
if (FD_ISSET(sockfd, &recvFDs)) {
len = sizeof(buffd);
memset(&msgh, 0, sizeof(msgh));
msgh.msg_control = &cmsg_b;
msgh.msg_controllen = CMSG_LEN(len);
iov.iov_base = data;
iov.iov_len = sizeof(data)-1;
msgh.msg_iov = &iov;
msgh.msg_iovlen = 1;
cmsg = CMSG_FIRSTHDR(&msgh);
cmsg->cmsg_level = SOL_SOCKET;
cmsg->cmsg_type = SCM_RIGHTS;
cmsg->cmsg_len = CMSG_LEN(len);
ret = recvmsg(sockfd, &msgh, MSG_DONTWAIT);
if (ret < 0) {
fprintf(stderr, "<%s>: Failed recvmsg: <%s>\n",
__func__, strerror(errno));
return -1;
}
memcpy(&buffd, CMSG_DATA(cmsg), len);
skdata->data = buffd;
skdata->len = len;
}
return 0;
}
int closesocket(int sockfd, char *name)
{
char sockname[MAX_SOCK_NAME_LEN];
if (sockfd)
close(sockfd);
sprintf(sockname, "/tmp/%s", name);
unlink(sockname);
shutdown(sockfd, 2);
return 0;
}
@@ -0,0 +1,35 @@
#ifndef _IPCSOCKET_H
#define _IPCSOCKET_H
#define MAX_SOCK_NAME_LEN 64
char sock_name[MAX_SOCK_NAME_LEN];
/* This structure is responsible for holding the IPC data
* data: hold the buffer fd
* len: just the length of 32-bit integer fd
*/
struct socketdata {
int data;
unsigned int len;
};
/* This API is used to open the IPC socket connection
* name: implies a unique socket name in the system
* connecttype: implies server(0) or client(1)
*/
int opensocket(int *sockfd, const char *name, int connecttype);
/* This is the API to send socket data over IPC socket */
int sendtosocket(int sockfd, struct socketdata *data);
/* This is the API to receive socket data over IPC socket */
int receivefromsocket(int sockfd, struct socketdata *data);
/* This is the API to close the socket connection */
int closesocket(int sockfd, char *name);
#endif
+3
View File
@@ -0,0 +1,3 @@
#!/bin/sh
(cd ion; ./ion_test.sh)
+12
View File
@@ -0,0 +1,12 @@
# SPDX-License-Identifier: GPL-2.0
# ARCH can be overridden by the user for cross compiling
ARCH ?= $(shell uname -m 2>/dev/null || echo not)
ifneq (,$(filter $(ARCH),aarch64 arm64))
CFLAGS += -I../../../../usr/include/
TEST_GEN_PROGS := tags_test
TEST_PROGS := run_tags_test.sh
endif
include ../lib.mk
+12
View File
@@ -0,0 +1,12 @@
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
echo "--------------------"
echo "running tags test"
echo "--------------------"
./tags_test
if [ $? -ne 0 ]; then
echo "[FAIL]"
else
echo "[PASS]"
fi
+31
View File
@@ -0,0 +1,31 @@
// SPDX-License-Identifier: GPL-2.0
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <stdint.h>
#include <sys/prctl.h>
#include <sys/utsname.h>
#define SHIFT_TAG(tag) ((uint64_t)(tag) << 56)
#define SET_TAG(ptr, tag) (((uint64_t)(ptr) & ~SHIFT_TAG(0xff)) | \
SHIFT_TAG(tag))
int main(void)
{
static int tbi_enabled = 0;
unsigned long tag = 0;
struct utsname *ptr;
int err;
if (prctl(PR_SET_TAGGED_ADDR_CTRL, PR_TAGGED_ADDR_ENABLE, 0, 0, 0) == 0)
tbi_enabled = 1;
ptr = (struct utsname *)malloc(sizeof(*ptr));
if (tbi_enabled)
tag = 0x42;
ptr = (struct utsname *)SET_TAG(ptr, tag);
err = uname(ptr);
free(ptr);
return err;
}
+145
View File
@@ -0,0 +1,145 @@
# SPDX-License-Identifier: GPL-2.0
LIBDIR := ../../../lib
BPFDIR := $(LIBDIR)/bpf
APIDIR := ../../../include/uapi
GENDIR := ../../../../include/generated
GENHDR := $(GENDIR)/autoconf.h
ifneq ($(wildcard $(GENHDR)),)
GENFLAGS := -DHAVE_GENHDR
endif
CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(BPFDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include
LDLIBS += -lcap -lelf -lrt -lpthread
TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read
all: $(TEST_CUSTOM_PROGS)
$(TEST_CUSTOM_PROGS): $(OUTPUT)/%: %.c
$(CC) -o $(TEST_CUSTOM_PROGS) -static $< -Wl,--build-id
# Order correspond to 'make run_tests' order
TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user \
test_socket_cookie test_cgroup_storage test_select_reuseport
TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \
sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o \
test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \
sample_map_ret0.o test_tcpbpf_kern.o test_stacktrace_build_id.o \
sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o test_adjust_tail.o \
test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o \
test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \
test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
test_skb_cgroup_id_kern.o
# Order correspond to 'make run_tests' order
TEST_PROGS := test_kmod.sh \
test_libbpf.sh \
test_xdp_redirect.sh \
test_xdp_meta.sh \
test_offload.py \
test_sock_addr.sh \
test_tunnel.sh \
test_lwt_seg6local.sh \
test_lirc_mode2.sh \
test_skb_cgroup_id.sh
# Compile but not part of 'make run_tests'
TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr test_skb_cgroup_id_user
include ../lib.mk
BPFOBJ := $(OUTPUT)/libbpf.a
$(TEST_GEN_PROGS): $(BPFOBJ)
$(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/libbpf.a
$(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
$(OUTPUT)/test_skb_cgroup_id_user: cgroup_helpers.c
$(OUTPUT)/test_sock: cgroup_helpers.c
$(OUTPUT)/test_sock_addr: cgroup_helpers.c
$(OUTPUT)/test_socket_cookie: cgroup_helpers.c
$(OUTPUT)/test_sockmap: cgroup_helpers.c
$(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c
$(OUTPUT)/test_progs: trace_helpers.c
$(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c
$(OUTPUT)/test_cgroup_storage: cgroup_helpers.c
.PHONY: force
# force a rebuild of BPFOBJ when its dependencies are updated
force:
$(BPFOBJ): force
$(MAKE) -C $(BPFDIR) OUTPUT=$(OUTPUT)/
CLANG ?= clang
LLC ?= llc
LLVM_OBJCOPY ?= llvm-objcopy
BTF_PAHOLE ?= pahole
PROBE := $(shell $(LLC) -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1)
# Let newer LLVM versions transparently probe the kernel for availability
# of full BPF instruction set.
ifeq ($(PROBE),)
CPU ?= probe
else
CPU ?= generic
endif
# Get Clang's default includes on this system, as opposed to those seen by
# '-target bpf'. This fixes "missing" files on some architectures/distros,
# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
#
# Use '-idirafter': Don't interfere with include mechanics except where the
# build would have failed anyways.
CLANG_SYS_INCLUDES := $(shell $(CLANG) -v -E - </dev/null 2>&1 \
| sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }')
CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \
$(CLANG_SYS_INCLUDES) \
-Wno-compare-distinct-pointer-types
$(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline
$(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline
BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris)
BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF)
BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm')
ifneq ($(BTF_LLC_PROBE),)
ifneq ($(BTF_PAHOLE_PROBE),)
ifneq ($(BTF_OBJCOPY_PROBE),)
CLANG_FLAGS += -g
LLC_FLAGS += -mattr=dwarfris
DWARF2BTF = y
endif
endif
endif
# Have one program compiled without "-target bpf" to test whether libbpf loads
# it successfully
$(OUTPUT)/test_xdp.o: test_xdp.c
$(CLANG) $(CLANG_FLAGS) \
-O2 -emit-llvm -c $< -o - | \
$(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
ifeq ($(DWARF2BTF),y)
$(BTF_PAHOLE) -J $@
endif
$(OUTPUT)/%.o: %.c
$(CLANG) $(CLANG_FLAGS) \
-O2 -target bpf -emit-llvm -c $< -o - | \
$(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
ifeq ($(DWARF2BTF),y)
$(BTF_PAHOLE) -J $@
endif
EXTRA_CLEAN := $(TEST_CUSTOM_PROGS)
+57
View File
@@ -0,0 +1,57 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __BPF_ENDIAN__
#define __BPF_ENDIAN__
#include <linux/swab.h>
/* LLVM's BPF target selects the endianness of the CPU
* it compiles on, or the user specifies (bpfel/bpfeb),
* respectively. The used __BYTE_ORDER__ is defined by
* the compiler, we cannot rely on __BYTE_ORDER from
* libc headers, since it doesn't reflect the actual
* requested byte order.
*
* Note, LLVM's BPF target has different __builtin_bswapX()
* semantics. It does map to BPF_ALU | BPF_END | BPF_TO_BE
* in bpfel and bpfeb case, which means below, that we map
* to cpu_to_be16(). We could use it unconditionally in BPF
* case, but better not rely on it, so that this header here
* can be used from application and BPF program side, which
* use different targets.
*/
#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
# define __bpf_ntohs(x) __builtin_bswap16(x)
# define __bpf_htons(x) __builtin_bswap16(x)
# define __bpf_constant_ntohs(x) ___constant_swab16(x)
# define __bpf_constant_htons(x) ___constant_swab16(x)
# define __bpf_ntohl(x) __builtin_bswap32(x)
# define __bpf_htonl(x) __builtin_bswap32(x)
# define __bpf_constant_ntohl(x) ___constant_swab32(x)
# define __bpf_constant_htonl(x) ___constant_swab32(x)
#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
# define __bpf_ntohs(x) (x)
# define __bpf_htons(x) (x)
# define __bpf_constant_ntohs(x) (x)
# define __bpf_constant_htons(x) (x)
# define __bpf_ntohl(x) (x)
# define __bpf_htonl(x) (x)
# define __bpf_constant_ntohl(x) (x)
# define __bpf_constant_htonl(x) (x)
#else
# error "Fix your compiler's __BYTE_ORDER__?!"
#endif
#define bpf_htons(x) \
(__builtin_constant_p(x) ? \
__bpf_constant_htons(x) : __bpf_htons(x))
#define bpf_ntohs(x) \
(__builtin_constant_p(x) ? \
__bpf_constant_ntohs(x) : __bpf_ntohs(x))
#define bpf_htonl(x) \
(__builtin_constant_p(x) ? \
__bpf_constant_htonl(x) : __bpf_htonl(x))
#define bpf_ntohl(x) \
(__builtin_constant_p(x) ? \
__bpf_constant_ntohl(x) : __bpf_ntohl(x))
#endif /* __BPF_ENDIAN__ */
+336
View File
@@ -0,0 +1,336 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __BPF_HELPERS_H
#define __BPF_HELPERS_H
/* helper macro to place programs, maps, license in
* different sections in elf_bpf file. Section names
* are interpreted by elf_bpf loader
*/
#define SEC(NAME) __attribute__((section(NAME), used))
/* helper functions called from eBPF programs written in C */
static void *(*bpf_map_lookup_elem)(void *map, void *key) =
(void *) BPF_FUNC_map_lookup_elem;
static int (*bpf_map_update_elem)(void *map, void *key, void *value,
unsigned long long flags) =
(void *) BPF_FUNC_map_update_elem;
static int (*bpf_map_delete_elem)(void *map, void *key) =
(void *) BPF_FUNC_map_delete_elem;
static int (*bpf_probe_read)(void *dst, int size, void *unsafe_ptr) =
(void *) BPF_FUNC_probe_read;
static unsigned long long (*bpf_ktime_get_ns)(void) =
(void *) BPF_FUNC_ktime_get_ns;
static int (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) =
(void *) BPF_FUNC_trace_printk;
static void (*bpf_tail_call)(void *ctx, void *map, int index) =
(void *) BPF_FUNC_tail_call;
static unsigned long long (*bpf_get_smp_processor_id)(void) =
(void *) BPF_FUNC_get_smp_processor_id;
static unsigned long long (*bpf_get_current_pid_tgid)(void) =
(void *) BPF_FUNC_get_current_pid_tgid;
static unsigned long long (*bpf_get_current_uid_gid)(void) =
(void *) BPF_FUNC_get_current_uid_gid;
static int (*bpf_get_current_comm)(void *buf, int buf_size) =
(void *) BPF_FUNC_get_current_comm;
static unsigned long long (*bpf_perf_event_read)(void *map,
unsigned long long flags) =
(void *) BPF_FUNC_perf_event_read;
static int (*bpf_clone_redirect)(void *ctx, int ifindex, int flags) =
(void *) BPF_FUNC_clone_redirect;
static int (*bpf_redirect)(int ifindex, int flags) =
(void *) BPF_FUNC_redirect;
static int (*bpf_redirect_map)(void *map, int key, int flags) =
(void *) BPF_FUNC_redirect_map;
static int (*bpf_perf_event_output)(void *ctx, void *map,
unsigned long long flags, void *data,
int size) =
(void *) BPF_FUNC_perf_event_output;
static int (*bpf_get_stackid)(void *ctx, void *map, int flags) =
(void *) BPF_FUNC_get_stackid;
static int (*bpf_probe_write_user)(void *dst, void *src, int size) =
(void *) BPF_FUNC_probe_write_user;
static int (*bpf_current_task_under_cgroup)(void *map, int index) =
(void *) BPF_FUNC_current_task_under_cgroup;
static int (*bpf_skb_get_tunnel_key)(void *ctx, void *key, int size, int flags) =
(void *) BPF_FUNC_skb_get_tunnel_key;
static int (*bpf_skb_set_tunnel_key)(void *ctx, void *key, int size, int flags) =
(void *) BPF_FUNC_skb_set_tunnel_key;
static int (*bpf_skb_get_tunnel_opt)(void *ctx, void *md, int size) =
(void *) BPF_FUNC_skb_get_tunnel_opt;
static int (*bpf_skb_set_tunnel_opt)(void *ctx, void *md, int size) =
(void *) BPF_FUNC_skb_set_tunnel_opt;
static unsigned long long (*bpf_get_prandom_u32)(void) =
(void *) BPF_FUNC_get_prandom_u32;
static int (*bpf_xdp_adjust_head)(void *ctx, int offset) =
(void *) BPF_FUNC_xdp_adjust_head;
static int (*bpf_xdp_adjust_meta)(void *ctx, int offset) =
(void *) BPF_FUNC_xdp_adjust_meta;
static int (*bpf_get_socket_cookie)(void *ctx) =
(void *) BPF_FUNC_get_socket_cookie;
static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval,
int optlen) =
(void *) BPF_FUNC_setsockopt;
static int (*bpf_getsockopt)(void *ctx, int level, int optname, void *optval,
int optlen) =
(void *) BPF_FUNC_getsockopt;
static int (*bpf_sock_ops_cb_flags_set)(void *ctx, int flags) =
(void *) BPF_FUNC_sock_ops_cb_flags_set;
static int (*bpf_sk_redirect_map)(void *ctx, void *map, int key, int flags) =
(void *) BPF_FUNC_sk_redirect_map;
static int (*bpf_sk_redirect_hash)(void *ctx, void *map, void *key, int flags) =
(void *) BPF_FUNC_sk_redirect_hash;
static int (*bpf_sock_map_update)(void *map, void *key, void *value,
unsigned long long flags) =
(void *) BPF_FUNC_sock_map_update;
static int (*bpf_sock_hash_update)(void *map, void *key, void *value,
unsigned long long flags) =
(void *) BPF_FUNC_sock_hash_update;
static int (*bpf_perf_event_read_value)(void *map, unsigned long long flags,
void *buf, unsigned int buf_size) =
(void *) BPF_FUNC_perf_event_read_value;
static int (*bpf_perf_prog_read_value)(void *ctx, void *buf,
unsigned int buf_size) =
(void *) BPF_FUNC_perf_prog_read_value;
static int (*bpf_override_return)(void *ctx, unsigned long rc) =
(void *) BPF_FUNC_override_return;
static int (*bpf_msg_redirect_map)(void *ctx, void *map, int key, int flags) =
(void *) BPF_FUNC_msg_redirect_map;
static int (*bpf_msg_redirect_hash)(void *ctx,
void *map, void *key, int flags) =
(void *) BPF_FUNC_msg_redirect_hash;
static int (*bpf_msg_apply_bytes)(void *ctx, int len) =
(void *) BPF_FUNC_msg_apply_bytes;
static int (*bpf_msg_cork_bytes)(void *ctx, int len) =
(void *) BPF_FUNC_msg_cork_bytes;
static int (*bpf_msg_pull_data)(void *ctx, int start, int end, int flags) =
(void *) BPF_FUNC_msg_pull_data;
static int (*bpf_bind)(void *ctx, void *addr, int addr_len) =
(void *) BPF_FUNC_bind;
static int (*bpf_xdp_adjust_tail)(void *ctx, int offset) =
(void *) BPF_FUNC_xdp_adjust_tail;
static int (*bpf_skb_get_xfrm_state)(void *ctx, int index, void *state,
int size, int flags) =
(void *) BPF_FUNC_skb_get_xfrm_state;
static int (*bpf_sk_select_reuseport)(void *ctx, void *map, void *key, __u32 flags) =
(void *) BPF_FUNC_sk_select_reuseport;
static int (*bpf_get_stack)(void *ctx, void *buf, int size, int flags) =
(void *) BPF_FUNC_get_stack;
static int (*bpf_fib_lookup)(void *ctx, struct bpf_fib_lookup *params,
int plen, __u32 flags) =
(void *) BPF_FUNC_fib_lookup;
static int (*bpf_lwt_push_encap)(void *ctx, unsigned int type, void *hdr,
unsigned int len) =
(void *) BPF_FUNC_lwt_push_encap;
static int (*bpf_lwt_seg6_store_bytes)(void *ctx, unsigned int offset,
void *from, unsigned int len) =
(void *) BPF_FUNC_lwt_seg6_store_bytes;
static int (*bpf_lwt_seg6_action)(void *ctx, unsigned int action, void *param,
unsigned int param_len) =
(void *) BPF_FUNC_lwt_seg6_action;
static int (*bpf_lwt_seg6_adjust_srh)(void *ctx, unsigned int offset,
unsigned int len) =
(void *) BPF_FUNC_lwt_seg6_adjust_srh;
static int (*bpf_rc_repeat)(void *ctx) =
(void *) BPF_FUNC_rc_repeat;
static int (*bpf_rc_keydown)(void *ctx, unsigned int protocol,
unsigned long long scancode, unsigned int toggle) =
(void *) BPF_FUNC_rc_keydown;
static unsigned long long (*bpf_get_current_cgroup_id)(void) =
(void *) BPF_FUNC_get_current_cgroup_id;
static void *(*bpf_get_local_storage)(void *map, unsigned long long flags) =
(void *) BPF_FUNC_get_local_storage;
static unsigned long long (*bpf_skb_cgroup_id)(void *ctx) =
(void *) BPF_FUNC_skb_cgroup_id;
static unsigned long long (*bpf_skb_ancestor_cgroup_id)(void *ctx, int level) =
(void *) BPF_FUNC_skb_ancestor_cgroup_id;
/* llvm builtin functions that eBPF C program may use to
* emit BPF_LD_ABS and BPF_LD_IND instructions
*/
struct sk_buff;
unsigned long long load_byte(void *skb,
unsigned long long off) asm("llvm.bpf.load.byte");
unsigned long long load_half(void *skb,
unsigned long long off) asm("llvm.bpf.load.half");
unsigned long long load_word(void *skb,
unsigned long long off) asm("llvm.bpf.load.word");
/* a helper structure used by eBPF C program
* to describe map attributes to elf_bpf loader
*/
struct bpf_map_def {
unsigned int type;
unsigned int key_size;
unsigned int value_size;
unsigned int max_entries;
unsigned int map_flags;
unsigned int inner_map_idx;
unsigned int numa_node;
};
#define BPF_ANNOTATE_KV_PAIR(name, type_key, type_val) \
struct ____btf_map_##name { \
type_key key; \
type_val value; \
}; \
struct ____btf_map_##name \
__attribute__ ((section(".maps." #name), used)) \
____btf_map_##name = { }
static int (*bpf_skb_load_bytes)(void *ctx, int off, void *to, int len) =
(void *) BPF_FUNC_skb_load_bytes;
static int (*bpf_skb_load_bytes_relative)(void *ctx, int off, void *to, int len, __u32 start_header) =
(void *) BPF_FUNC_skb_load_bytes_relative;
static int (*bpf_skb_store_bytes)(void *ctx, int off, void *from, int len, int flags) =
(void *) BPF_FUNC_skb_store_bytes;
static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flags) =
(void *) BPF_FUNC_l3_csum_replace;
static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flags) =
(void *) BPF_FUNC_l4_csum_replace;
static int (*bpf_csum_diff)(void *from, int from_size, void *to, int to_size, int seed) =
(void *) BPF_FUNC_csum_diff;
static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) =
(void *) BPF_FUNC_skb_under_cgroup;
static int (*bpf_skb_change_head)(void *, int len, int flags) =
(void *) BPF_FUNC_skb_change_head;
static int (*bpf_skb_pull_data)(void *, int len) =
(void *) BPF_FUNC_skb_pull_data;
/* Scan the ARCH passed in from ARCH env variable (see Makefile) */
#if defined(__TARGET_ARCH_x86)
#define bpf_target_x86
#define bpf_target_defined
#elif defined(__TARGET_ARCH_s930x)
#define bpf_target_s930x
#define bpf_target_defined
#elif defined(__TARGET_ARCH_arm64)
#define bpf_target_arm64
#define bpf_target_defined
#elif defined(__TARGET_ARCH_mips)
#define bpf_target_mips
#define bpf_target_defined
#elif defined(__TARGET_ARCH_powerpc)
#define bpf_target_powerpc
#define bpf_target_defined
#elif defined(__TARGET_ARCH_sparc)
#define bpf_target_sparc
#define bpf_target_defined
#else
#undef bpf_target_defined
#endif
/* Fall back to what the compiler says */
#ifndef bpf_target_defined
#if defined(__x86_64__)
#define bpf_target_x86
#elif defined(__s390x__)
#define bpf_target_s930x
#elif defined(__aarch64__)
#define bpf_target_arm64
#elif defined(__mips__)
#define bpf_target_mips
#elif defined(__powerpc__)
#define bpf_target_powerpc
#elif defined(__sparc__)
#define bpf_target_sparc
#endif
#endif
#if defined(bpf_target_x86)
#define PT_REGS_PARM1(x) ((x)->di)
#define PT_REGS_PARM2(x) ((x)->si)
#define PT_REGS_PARM3(x) ((x)->dx)
#define PT_REGS_PARM4(x) ((x)->cx)
#define PT_REGS_PARM5(x) ((x)->r8)
#define PT_REGS_RET(x) ((x)->sp)
#define PT_REGS_FP(x) ((x)->bp)
#define PT_REGS_RC(x) ((x)->ax)
#define PT_REGS_SP(x) ((x)->sp)
#define PT_REGS_IP(x) ((x)->ip)
#elif defined(bpf_target_s390x)
#define PT_REGS_PARM1(x) ((x)->gprs[2])
#define PT_REGS_PARM2(x) ((x)->gprs[3])
#define PT_REGS_PARM3(x) ((x)->gprs[4])
#define PT_REGS_PARM4(x) ((x)->gprs[5])
#define PT_REGS_PARM5(x) ((x)->gprs[6])
#define PT_REGS_RET(x) ((x)->gprs[14])
#define PT_REGS_FP(x) ((x)->gprs[11]) /* Works only with CONFIG_FRAME_POINTER */
#define PT_REGS_RC(x) ((x)->gprs[2])
#define PT_REGS_SP(x) ((x)->gprs[15])
#define PT_REGS_IP(x) ((x)->psw.addr)
#elif defined(bpf_target_arm64)
#define PT_REGS_PARM1(x) ((x)->regs[0])
#define PT_REGS_PARM2(x) ((x)->regs[1])
#define PT_REGS_PARM3(x) ((x)->regs[2])
#define PT_REGS_PARM4(x) ((x)->regs[3])
#define PT_REGS_PARM5(x) ((x)->regs[4])
#define PT_REGS_RET(x) ((x)->regs[30])
#define PT_REGS_FP(x) ((x)->regs[29]) /* Works only with CONFIG_FRAME_POINTER */
#define PT_REGS_RC(x) ((x)->regs[0])
#define PT_REGS_SP(x) ((x)->sp)
#define PT_REGS_IP(x) ((x)->pc)
#elif defined(bpf_target_mips)
#define PT_REGS_PARM1(x) ((x)->regs[4])
#define PT_REGS_PARM2(x) ((x)->regs[5])
#define PT_REGS_PARM3(x) ((x)->regs[6])
#define PT_REGS_PARM4(x) ((x)->regs[7])
#define PT_REGS_PARM5(x) ((x)->regs[8])
#define PT_REGS_RET(x) ((x)->regs[31])
#define PT_REGS_FP(x) ((x)->regs[30]) /* Works only with CONFIG_FRAME_POINTER */
#define PT_REGS_RC(x) ((x)->regs[1])
#define PT_REGS_SP(x) ((x)->regs[29])
#define PT_REGS_IP(x) ((x)->cp0_epc)
#elif defined(bpf_target_powerpc)
#define PT_REGS_PARM1(x) ((x)->gpr[3])
#define PT_REGS_PARM2(x) ((x)->gpr[4])
#define PT_REGS_PARM3(x) ((x)->gpr[5])
#define PT_REGS_PARM4(x) ((x)->gpr[6])
#define PT_REGS_PARM5(x) ((x)->gpr[7])
#define PT_REGS_RC(x) ((x)->gpr[3])
#define PT_REGS_SP(x) ((x)->sp)
#define PT_REGS_IP(x) ((x)->nip)
#elif defined(bpf_target_sparc)
#define PT_REGS_PARM1(x) ((x)->u_regs[UREG_I0])
#define PT_REGS_PARM2(x) ((x)->u_regs[UREG_I1])
#define PT_REGS_PARM3(x) ((x)->u_regs[UREG_I2])
#define PT_REGS_PARM4(x) ((x)->u_regs[UREG_I3])
#define PT_REGS_PARM5(x) ((x)->u_regs[UREG_I4])
#define PT_REGS_RET(x) ((x)->u_regs[UREG_I7])
#define PT_REGS_RC(x) ((x)->u_regs[UREG_I0])
#define PT_REGS_SP(x) ((x)->u_regs[UREG_FP])
/* Should this also be a bpf_target check for the sparc case? */
#if defined(__arch64__)
#define PT_REGS_IP(x) ((x)->tpc)
#else
#define PT_REGS_IP(x) ((x)->pc)
#endif
#endif
#ifdef bpf_target_powerpc
#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = (ctx)->link; })
#define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP
#elif bpf_target_sparc
#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ (ip) = PT_REGS_RET(ctx); })
#define BPF_KRETPROBE_READ_RET_IP BPF_KPROBE_READ_RET_IP
#else
#define BPF_KPROBE_READ_RET_IP(ip, ctx) ({ \
bpf_probe_read(&(ip), sizeof(ip), (void *)PT_REGS_RET(ctx)); })
#define BPF_KRETPROBE_READ_RET_IP(ip, ctx) ({ \
bpf_probe_read(&(ip), sizeof(ip), \
(void *)(PT_REGS_FP(ctx) + sizeof(ip))); })
#endif
#endif
+80
View File
@@ -0,0 +1,80 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __BPF_RAND__
#define __BPF_RAND__
#include <stdint.h>
#include <stdlib.h>
#include <time.h>
static inline uint64_t bpf_rand_mask(uint64_t mask)
{
return (((uint64_t)(uint32_t)rand()) |
((uint64_t)(uint32_t)rand() << 32)) & mask;
}
#define bpf_rand_ux(x, m) \
static inline uint64_t bpf_rand_u##x(int shift) \
{ \
return bpf_rand_mask((m)) << shift; \
}
bpf_rand_ux( 8, 0xffULL)
bpf_rand_ux(16, 0xffffULL)
bpf_rand_ux(24, 0xffffffULL)
bpf_rand_ux(32, 0xffffffffULL)
bpf_rand_ux(40, 0xffffffffffULL)
bpf_rand_ux(48, 0xffffffffffffULL)
bpf_rand_ux(56, 0xffffffffffffffULL)
bpf_rand_ux(64, 0xffffffffffffffffULL)
static inline void bpf_semi_rand_init(void)
{
srand(time(NULL));
}
static inline uint64_t bpf_semi_rand_get(void)
{
switch (rand() % 39) {
case 0: return 0x000000ff00000000ULL | bpf_rand_u8(0);
case 1: return 0xffffffff00000000ULL | bpf_rand_u16(0);
case 2: return 0x00000000ffff0000ULL | bpf_rand_u16(0);
case 3: return 0x8000000000000000ULL | bpf_rand_u32(0);
case 4: return 0x00000000f0000000ULL | bpf_rand_u32(0);
case 5: return 0x0000000100000000ULL | bpf_rand_u24(0);
case 6: return 0x800ff00000000000ULL | bpf_rand_u32(0);
case 7: return 0x7fffffff00000000ULL | bpf_rand_u32(0);
case 8: return 0xffffffffffffff00ULL ^ bpf_rand_u32(24);
case 9: return 0xffffffffffffff00ULL | bpf_rand_u8(0);
case 10: return 0x0000000010000000ULL | bpf_rand_u32(0);
case 11: return 0xf000000000000000ULL | bpf_rand_u8(0);
case 12: return 0x0000f00000000000ULL | bpf_rand_u8(8);
case 13: return 0x000000000f000000ULL | bpf_rand_u8(16);
case 14: return 0x0000000000000f00ULL | bpf_rand_u8(32);
case 15: return 0x00fff00000000f00ULL | bpf_rand_u8(48);
case 16: return 0x00007fffffffffffULL ^ bpf_rand_u32(1);
case 17: return 0xffff800000000000ULL | bpf_rand_u8(4);
case 18: return 0xffff800000000000ULL | bpf_rand_u8(20);
case 19: return (0xffffffc000000000ULL + 0x80000ULL) | bpf_rand_u32(0);
case 20: return (0xffffffc000000000ULL - 0x04000000ULL) | bpf_rand_u32(0);
case 21: return 0x0000000000000000ULL | bpf_rand_u8(55) | bpf_rand_u32(20);
case 22: return 0xffffffffffffffffULL ^ bpf_rand_u8(3) ^ bpf_rand_u32(40);
case 23: return 0x0000000000000000ULL | bpf_rand_u8(bpf_rand_u8(0) % 64);
case 24: return 0x0000000000000000ULL | bpf_rand_u16(bpf_rand_u8(0) % 64);
case 25: return 0xffffffffffffffffULL ^ bpf_rand_u8(bpf_rand_u8(0) % 64);
case 26: return 0xffffffffffffffffULL ^ bpf_rand_u40(bpf_rand_u8(0) % 64);
case 27: return 0x0000800000000000ULL;
case 28: return 0x8000000000000000ULL;
case 29: return 0x0000000000000000ULL;
case 30: return 0xffffffffffffffffULL;
case 31: return bpf_rand_u16(bpf_rand_u8(0) % 64);
case 32: return bpf_rand_u24(bpf_rand_u8(0) % 64);
case 33: return bpf_rand_u32(bpf_rand_u8(0) % 64);
case 34: return bpf_rand_u40(bpf_rand_u8(0) % 64);
case 35: return bpf_rand_u48(bpf_rand_u8(0) % 64);
case 36: return bpf_rand_u56(bpf_rand_u8(0) % 64);
case 37: return bpf_rand_u64(bpf_rand_u8(0) % 64);
default: return bpf_rand_u64(0);
}
}
#endif /* __BPF_RAND__ */
+28
View File
@@ -0,0 +1,28 @@
#include <sys/resource.h>
#include <stdio.h>
static __attribute__((constructor)) void bpf_rlimit_ctor(void)
{
struct rlimit rlim_old, rlim_new = {
.rlim_cur = RLIM_INFINITY,
.rlim_max = RLIM_INFINITY,
};
getrlimit(RLIMIT_MEMLOCK, &rlim_old);
/* For the sake of running the test cases, we temporarily
* set rlimit to infinity in order for kernel to focus on
* errors from actual test cases and not getting noise
* from hitting memlock limits. The limit is on per-process
* basis and not a global one, hence destructor not really
* needed here.
*/
if (setrlimit(RLIMIT_MEMLOCK, &rlim_new) < 0) {
perror("Unable to lift memlock rlimit");
/* Trying out lower limit, but expect potential test
* case failures from this!
*/
rlim_new.rlim_cur = rlim_old.rlim_cur + (1UL << 20);
rlim_new.rlim_max = rlim_old.rlim_max + (1UL << 20);
setrlimit(RLIMIT_MEMLOCK, &rlim_new);
}
}
+61
View File
@@ -0,0 +1,61 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __BPF_UTIL__
#define __BPF_UTIL__
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
static inline unsigned int bpf_num_possible_cpus(void)
{
static const char *fcpu = "/sys/devices/system/cpu/possible";
unsigned int start, end, possible_cpus = 0;
char buff[128];
FILE *fp;
int len, n, i, j = 0;
fp = fopen(fcpu, "r");
if (!fp) {
printf("Failed to open %s: '%s'!\n", fcpu, strerror(errno));
exit(1);
}
if (!fgets(buff, sizeof(buff), fp)) {
printf("Failed to read %s!\n", fcpu);
exit(1);
}
len = strlen(buff);
for (i = 0; i <= len; i++) {
if (buff[i] == ',' || buff[i] == '\0') {
buff[i] = '\0';
n = sscanf(&buff[j], "%u-%u", &start, &end);
if (n <= 0) {
printf("Failed to retrieve # possible CPUs!\n");
exit(1);
} else if (n == 1) {
end = start;
}
possible_cpus += end - start + 1;
j = i + 1;
}
}
fclose(fp);
return possible_cpus;
}
#define __bpf_percpu_val_align __attribute__((__aligned__(8)))
#define BPF_DECLARE_PERCPU(type, name) \
struct { type v; /* padding */ } __bpf_percpu_val_align \
name[bpf_num_possible_cpus()]
#define bpf_percpu(name, cpu) name[(cpu)].v
#ifndef ARRAY_SIZE
# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
#endif
#endif /* __BPF_UTIL__ */
@@ -0,0 +1,235 @@
// SPDX-License-Identifier: GPL-2.0
#define _GNU_SOURCE
#include <sched.h>
#include <sys/mount.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <linux/limits.h>
#include <stdio.h>
#include <stdlib.h>
#include <linux/sched.h>
#include <fcntl.h>
#include <unistd.h>
#include <ftw.h>
#include "cgroup_helpers.h"
/*
* To avoid relying on the system setup, when setup_cgroup_env is called
* we create a new mount namespace, and cgroup namespace. The cgroup2
* root is mounted at CGROUP_MOUNT_PATH
*
* Unfortunately, most people don't have cgroupv2 enabled at this point in time.
* It's easier to create our own mount namespace and manage it ourselves.
*
* We assume /mnt exists.
*/
#define WALK_FD_LIMIT 16
#define CGROUP_MOUNT_PATH "/mnt"
#define CGROUP_WORK_DIR "/cgroup-test-work-dir"
#define format_cgroup_path(buf, path) \
snprintf(buf, sizeof(buf), "%s%s%s", CGROUP_MOUNT_PATH, \
CGROUP_WORK_DIR, path)
/**
* setup_cgroup_environment() - Setup the cgroup environment
*
* After calling this function, cleanup_cgroup_environment should be called
* once testing is complete.
*
* This function will print an error to stderr and return 1 if it is unable
* to setup the cgroup environment. If setup is successful, 0 is returned.
*/
int setup_cgroup_environment(void)
{
char cgroup_workdir[PATH_MAX - 24];
format_cgroup_path(cgroup_workdir, "");
if (unshare(CLONE_NEWNS)) {
log_err("unshare");
return 1;
}
if (mount("none", "/", NULL, MS_REC | MS_PRIVATE, NULL)) {
log_err("mount fakeroot");
return 1;
}
if (mount("none", CGROUP_MOUNT_PATH, "cgroup2", 0, NULL) && errno != EBUSY) {
log_err("mount cgroup2");
return 1;
}
/* Cleanup existing failed runs, now that the environment is setup */
cleanup_cgroup_environment();
if (mkdir(cgroup_workdir, 0777) && errno != EEXIST) {
log_err("mkdir cgroup work dir");
return 1;
}
return 0;
}
static int nftwfunc(const char *filename, const struct stat *statptr,
int fileflags, struct FTW *pfwt)
{
if ((fileflags & FTW_D) && rmdir(filename))
log_err("Removing cgroup: %s", filename);
return 0;
}
static int join_cgroup_from_top(char *cgroup_path)
{
char cgroup_procs_path[PATH_MAX + 1];
pid_t pid = getpid();
int fd, rc = 0;
snprintf(cgroup_procs_path, sizeof(cgroup_procs_path),
"%s/cgroup.procs", cgroup_path);
fd = open(cgroup_procs_path, O_WRONLY);
if (fd < 0) {
log_err("Opening Cgroup Procs: %s", cgroup_procs_path);
return 1;
}
if (dprintf(fd, "%d\n", pid) < 0) {
log_err("Joining Cgroup");
rc = 1;
}
close(fd);
return rc;
}
/**
* join_cgroup() - Join a cgroup
* @path: The cgroup path, relative to the workdir, to join
*
* This function expects a cgroup to already be created, relative to the cgroup
* work dir, and it joins it. For example, passing "/my-cgroup" as the path
* would actually put the calling process into the cgroup
* "/cgroup-test-work-dir/my-cgroup"
*
* On success, it returns 0, otherwise on failure it returns 1.
*/
int join_cgroup(const char *path)
{
char cgroup_path[PATH_MAX + 1];
format_cgroup_path(cgroup_path, path);
return join_cgroup_from_top(cgroup_path);
}
/**
* cleanup_cgroup_environment() - Cleanup Cgroup Testing Environment
*
* This is an idempotent function to delete all temporary cgroups that
* have been created during the test, including the cgroup testing work
* directory.
*
* At call time, it moves the calling process to the root cgroup, and then
* runs the deletion process. It is idempotent, and should not fail, unless
* a process is lingering.
*
* On failure, it will print an error to stderr, and try to continue.
*/
void cleanup_cgroup_environment(void)
{
char cgroup_workdir[PATH_MAX + 1];
format_cgroup_path(cgroup_workdir, "");
join_cgroup_from_top(CGROUP_MOUNT_PATH);
nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT);
}
/**
* create_and_get_cgroup() - Create a cgroup, relative to workdir, and get the FD
* @path: The cgroup path, relative to the workdir, to join
*
* This function creates a cgroup under the top level workdir and returns the
* file descriptor. It is idempotent.
*
* On success, it returns the file descriptor. On failure it returns 0.
* If there is a failure, it prints the error to stderr.
*/
int create_and_get_cgroup(const char *path)
{
char cgroup_path[PATH_MAX + 1];
int fd;
format_cgroup_path(cgroup_path, path);
if (mkdir(cgroup_path, 0777) && errno != EEXIST) {
log_err("mkdiring cgroup %s .. %s", path, cgroup_path);
return 0;
}
fd = open(cgroup_path, O_RDONLY);
if (fd < 0) {
log_err("Opening Cgroup");
return 0;
}
return fd;
}
/**
* get_cgroup_id() - Get cgroup id for a particular cgroup path
* @path: The cgroup path, relative to the workdir, to join
*
* On success, it returns the cgroup id. On failure it returns 0,
* which is an invalid cgroup id.
* If there is a failure, it prints the error to stderr.
*/
unsigned long long get_cgroup_id(const char *path)
{
int dirfd, err, flags, mount_id, fhsize;
union {
unsigned long long cgid;
unsigned char raw_bytes[8];
} id;
char cgroup_workdir[PATH_MAX + 1];
struct file_handle *fhp, *fhp2;
unsigned long long ret = 0;
format_cgroup_path(cgroup_workdir, path);
dirfd = AT_FDCWD;
flags = 0;
fhsize = sizeof(*fhp);
fhp = calloc(1, fhsize);
if (!fhp) {
log_err("calloc");
return 0;
}
err = name_to_handle_at(dirfd, cgroup_workdir, fhp, &mount_id, flags);
if (err >= 0 || fhp->handle_bytes != 8) {
log_err("name_to_handle_at");
goto free_mem;
}
fhsize = sizeof(struct file_handle) + fhp->handle_bytes;
fhp2 = realloc(fhp, fhsize);
if (!fhp2) {
log_err("realloc");
goto free_mem;
}
err = name_to_handle_at(dirfd, cgroup_workdir, fhp2, &mount_id, flags);
fhp = fhp2;
if (err < 0) {
log_err("name_to_handle_at");
goto free_mem;
}
memcpy(id.raw_bytes, fhp->f_handle, 8);
ret = id.cgid;
free_mem:
free(fhp);
return ret;
}
@@ -0,0 +1,18 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __CGROUP_HELPERS_H
#define __CGROUP_HELPERS_H
#include <errno.h>
#include <string.h>
#define clean_errno() (errno == 0 ? "None" : strerror(errno))
#define log_err(MSG, ...) fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \
__FILE__, __LINE__, clean_errno(), ##__VA_ARGS__)
int create_and_get_cgroup(const char *path);
int join_cgroup(const char *path);
int setup_cgroup_environment(void);
void cleanup_cgroup_environment(void);
unsigned long long get_cgroup_id(const char *path);
#endif
+20
View File
@@ -0,0 +1,20 @@
CONFIG_BPF=y
CONFIG_BPF_SYSCALL=y
CONFIG_NET_CLS_BPF=m
CONFIG_BPF_EVENTS=y
CONFIG_TEST_BPF=m
CONFIG_CGROUP_BPF=y
CONFIG_NETDEVSIM=m
CONFIG_NET_CLS_ACT=y
CONFIG_NET_SCHED=y
CONFIG_NET_SCH_INGRESS=y
CONFIG_NET_IPIP=y
CONFIG_IPV6=y
CONFIG_NET_IPGRE_DEMUX=y
CONFIG_NET_IPGRE=y
CONFIG_IPV6_GRE=y
CONFIG_CRYPTO_USER_API_HASH=m
CONFIG_CRYPTO_HMAC=m
CONFIG_CRYPTO_SHA256=m
CONFIG_VXLAN=y
CONFIG_GENEVE=y
@@ -0,0 +1,45 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2018 Facebook
#include <string.h>
#include <linux/stddef.h>
#include <linux/bpf.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <sys/socket.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
#define SRC_REWRITE_IP4 0x7f000004U
#define DST_REWRITE_IP4 0x7f000001U
#define DST_REWRITE_PORT4 4444
int _version SEC("version") = 1;
SEC("cgroup/connect4")
int connect_v4_prog(struct bpf_sock_addr *ctx)
{
struct sockaddr_in sa;
/* Rewrite destination. */
ctx->user_ip4 = bpf_htonl(DST_REWRITE_IP4);
ctx->user_port = bpf_htons(DST_REWRITE_PORT4);
if (ctx->type == SOCK_DGRAM || ctx->type == SOCK_STREAM) {
///* Rewrite source. */
memset(&sa, 0, sizeof(sa));
sa.sin_family = AF_INET;
sa.sin_port = bpf_htons(0);
sa.sin_addr.s_addr = bpf_htonl(SRC_REWRITE_IP4);
if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
return 0;
}
return 1;
}
char _license[] SEC("license") = "GPL";
@@ -0,0 +1,61 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2018 Facebook
#include <string.h>
#include <linux/stddef.h>
#include <linux/bpf.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <sys/socket.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
#define SRC_REWRITE_IP6_0 0
#define SRC_REWRITE_IP6_1 0
#define SRC_REWRITE_IP6_2 0
#define SRC_REWRITE_IP6_3 6
#define DST_REWRITE_IP6_0 0
#define DST_REWRITE_IP6_1 0
#define DST_REWRITE_IP6_2 0
#define DST_REWRITE_IP6_3 1
#define DST_REWRITE_PORT6 6666
int _version SEC("version") = 1;
SEC("cgroup/connect6")
int connect_v6_prog(struct bpf_sock_addr *ctx)
{
struct sockaddr_in6 sa;
/* Rewrite destination. */
ctx->user_ip6[0] = bpf_htonl(DST_REWRITE_IP6_0);
ctx->user_ip6[1] = bpf_htonl(DST_REWRITE_IP6_1);
ctx->user_ip6[2] = bpf_htonl(DST_REWRITE_IP6_2);
ctx->user_ip6[3] = bpf_htonl(DST_REWRITE_IP6_3);
ctx->user_port = bpf_htons(DST_REWRITE_PORT6);
if (ctx->type == SOCK_DGRAM || ctx->type == SOCK_STREAM) {
/* Rewrite source. */
memset(&sa, 0, sizeof(sa));
sa.sin6_family = AF_INET6;
sa.sin6_port = bpf_htons(0);
sa.sin6_addr.s6_addr32[0] = bpf_htonl(SRC_REWRITE_IP6_0);
sa.sin6_addr.s6_addr32[1] = bpf_htonl(SRC_REWRITE_IP6_1);
sa.sin6_addr.s6_addr32[2] = bpf_htonl(SRC_REWRITE_IP6_2);
sa.sin6_addr.s6_addr32[3] = bpf_htonl(SRC_REWRITE_IP6_3);
if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
return 0;
}
return 1;
}
char _license[] SEC("license") = "GPL";
+60
View File
@@ -0,0 +1,60 @@
/* Copyright (c) 2017 Facebook
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
#include <linux/bpf.h>
#include <linux/version.h>
#include "bpf_helpers.h"
SEC("cgroup/dev")
int bpf_prog1(struct bpf_cgroup_dev_ctx *ctx)
{
short type = ctx->access_type & 0xFFFF;
#ifdef DEBUG
short access = ctx->access_type >> 16;
char fmt[] = " %d:%d \n";
switch (type) {
case BPF_DEVCG_DEV_BLOCK:
fmt[0] = 'b';
break;
case BPF_DEVCG_DEV_CHAR:
fmt[0] = 'c';
break;
default:
fmt[0] = '?';
break;
}
if (access & BPF_DEVCG_ACC_READ)
fmt[8] = 'r';
if (access & BPF_DEVCG_ACC_WRITE)
fmt[9] = 'w';
if (access & BPF_DEVCG_ACC_MKNOD)
fmt[10] = 'm';
bpf_trace_printk(fmt, sizeof(fmt), ctx->major, ctx->minor);
#endif
/* Allow access to /dev/zero and /dev/random.
* Forbid everything else.
*/
if (ctx->major != 1 || type != BPF_DEVCG_DEV_CHAR)
return 0;
switch (ctx->minor) {
case 5: /* 1:5 /dev/zero */
case 9: /* 1:9 /dev/urandom */
return 1;
}
return 0;
}
char _license[] SEC("license") = "GPL";
__u32 _version SEC("version") = LINUX_VERSION_CODE;
@@ -0,0 +1,40 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2018 Facebook
#include <linux/bpf.h>
#include "bpf_helpers.h"
struct bpf_map_def SEC("maps") cg_ids = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(__u64),
.max_entries = 1,
};
struct bpf_map_def SEC("maps") pidmap = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(__u32),
.max_entries = 1,
};
SEC("tracepoint/syscalls/sys_enter_nanosleep")
int trace(void *ctx)
{
__u32 pid = bpf_get_current_pid_tgid();
__u32 key = 0, *expected_pid;
__u64 *val;
expected_pid = bpf_map_lookup_elem(&pidmap, &key);
if (!expected_pid || *expected_pid != pid)
return 0;
val = bpf_map_lookup_elem(&cg_ids, &key);
if (val)
*val = bpf_get_current_cgroup_id();
return 0;
}
char _license[] SEC("license") = "GPL";
__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */
@@ -0,0 +1,149 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2018 Facebook
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <fcntl.h>
#include <syscall.h>
#include <unistd.h>
#include <linux/perf_event.h>
#include <sys/ioctl.h>
#include <sys/time.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <linux/bpf.h>
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
#include "cgroup_helpers.h"
#include "bpf_rlimit.h"
#define CHECK(condition, tag, format...) ({ \
int __ret = !!(condition); \
if (__ret) { \
printf("%s:FAIL:%s ", __func__, tag); \
printf(format); \
} else { \
printf("%s:PASS:%s\n", __func__, tag); \
} \
__ret; \
})
static int bpf_find_map(const char *test, struct bpf_object *obj,
const char *name)
{
struct bpf_map *map;
map = bpf_object__find_map_by_name(obj, name);
if (!map)
return -1;
return bpf_map__fd(map);
}
#define TEST_CGROUP "/test-bpf-get-cgroup-id/"
int main(int argc, char **argv)
{
const char *probe_name = "syscalls/sys_enter_nanosleep";
const char *file = "get_cgroup_id_kern.o";
int err, bytes, efd, prog_fd, pmu_fd;
int cgroup_fd, cgidmap_fd, pidmap_fd;
struct perf_event_attr attr = {};
struct bpf_object *obj;
__u64 kcgid = 0, ucgid;
__u32 key = 0, pid;
int exit_code = 1;
char buf[256];
err = setup_cgroup_environment();
if (CHECK(err, "setup_cgroup_environment", "err %d errno %d\n", err,
errno))
return 1;
cgroup_fd = create_and_get_cgroup(TEST_CGROUP);
if (CHECK(cgroup_fd < 0, "create_and_get_cgroup", "err %d errno %d\n",
cgroup_fd, errno))
goto cleanup_cgroup_env;
err = join_cgroup(TEST_CGROUP);
if (CHECK(err, "join_cgroup", "err %d errno %d\n", err, errno))
goto cleanup_cgroup_env;
err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd);
if (CHECK(err, "bpf_prog_load", "err %d errno %d\n", err, errno))
goto cleanup_cgroup_env;
cgidmap_fd = bpf_find_map(__func__, obj, "cg_ids");
if (CHECK(cgidmap_fd < 0, "bpf_find_map", "err %d errno %d\n",
cgidmap_fd, errno))
goto close_prog;
pidmap_fd = bpf_find_map(__func__, obj, "pidmap");
if (CHECK(pidmap_fd < 0, "bpf_find_map", "err %d errno %d\n",
pidmap_fd, errno))
goto close_prog;
pid = getpid();
bpf_map_update_elem(pidmap_fd, &key, &pid, 0);
snprintf(buf, sizeof(buf),
"/sys/kernel/debug/tracing/events/%s/id", probe_name);
efd = open(buf, O_RDONLY, 0);
if (CHECK(efd < 0, "open", "err %d errno %d\n", efd, errno))
goto close_prog;
bytes = read(efd, buf, sizeof(buf));
close(efd);
if (CHECK(bytes <= 0 || bytes >= sizeof(buf), "read",
"bytes %d errno %d\n", bytes, errno))
goto close_prog;
attr.config = strtol(buf, NULL, 0);
attr.type = PERF_TYPE_TRACEPOINT;
attr.sample_type = PERF_SAMPLE_RAW;
attr.sample_period = 1;
attr.wakeup_events = 1;
/* attach to this pid so the all bpf invocations will be in the
* cgroup associated with this pid.
*/
pmu_fd = syscall(__NR_perf_event_open, &attr, getpid(), -1, -1, 0);
if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", pmu_fd,
errno))
goto close_prog;
err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
if (CHECK(err, "perf_event_ioc_enable", "err %d errno %d\n", err,
errno))
goto close_pmu;
err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd);
if (CHECK(err, "perf_event_ioc_set_bpf", "err %d errno %d\n", err,
errno))
goto close_pmu;
/* trigger some syscalls */
sleep(1);
err = bpf_map_lookup_elem(cgidmap_fd, &key, &kcgid);
if (CHECK(err, "bpf_map_lookup_elem", "err %d errno %d\n", err, errno))
goto close_pmu;
ucgid = get_cgroup_id(TEST_CGROUP);
if (CHECK(kcgid != ucgid, "compare_cgroup_id",
"kern cgid %llx user cgid %llx", kcgid, ucgid))
goto close_pmu;
exit_code = 0;
printf("%s:PASS\n", argv[0]);
close_pmu:
close(pmu_fd);
close_prog:
bpf_object__close(obj);
cleanup_cgroup_env:
cleanup_cgroup_environment();
return exit_code;
}
+1
View File
@@ -0,0 +1 @@
/* dummy .h to trick /usr/include/features.h to work with 'clang -target bpf' */
@@ -0,0 +1,23 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _UAPI_LINUX_TYPES_H
#define _UAPI_LINUX_TYPES_H
#include <asm-generic/int-ll64.h>
/* copied from linux:include/uapi/linux/types.h */
#define __bitwise
typedef __u16 __bitwise __le16;
typedef __u16 __bitwise __be16;
typedef __u32 __bitwise __le32;
typedef __u32 __bitwise __be32;
typedef __u64 __bitwise __le64;
typedef __u64 __bitwise __be64;
typedef __u16 __bitwise __sum16;
typedef __u32 __bitwise __wsum;
#define __aligned_u64 __u64 __attribute__((aligned(8)))
#define __aligned_be64 __be64 __attribute__((aligned(8)))
#define __aligned_le64 __le64 __attribute__((aligned(8)))
#endif /* _UAPI_LINUX_TYPES_H */
@@ -0,0 +1,34 @@
/* SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) */
#include <linux/bpf.h>
#include "bpf_helpers.h"
struct bpf_map_def SEC("maps") htab = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(__u32),
.value_size = sizeof(long),
.max_entries = 2,
};
struct bpf_map_def SEC("maps") array = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(long),
.max_entries = 2,
};
/* Sample program which should always load for testing control paths. */
SEC(".text") int func()
{
__u64 key64 = 0;
__u32 key = 0;
long *value;
value = bpf_map_lookup_elem(&htab, &key);
if (!value)
return 1;
value = bpf_map_lookup_elem(&array, &key64);
if (!value)
return 1;
return 0;
}
@@ -0,0 +1,7 @@
/* SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) */
/* Sample program which should always load for testing control paths. */
int func()
{
return 0;
}
@@ -0,0 +1,49 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2018 Facebook
#include <linux/stddef.h>
#include <linux/bpf.h>
#include <sys/socket.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
#define SRC1_IP4 0xAC100001U /* 172.16.0.1 */
#define SRC2_IP4 0x00000000U
#define SRC_REWRITE_IP4 0x7f000004U
#define DST_IP4 0xC0A801FEU /* 192.168.1.254 */
#define DST_REWRITE_IP4 0x7f000001U
#define DST_PORT 4040
#define DST_REWRITE_PORT4 4444
int _version SEC("version") = 1;
SEC("cgroup/sendmsg4")
int sendmsg_v4_prog(struct bpf_sock_addr *ctx)
{
if (ctx->type != SOCK_DGRAM)
return 0;
/* Rewrite source. */
if (ctx->msg_src_ip4 == bpf_htonl(SRC1_IP4) ||
ctx->msg_src_ip4 == bpf_htonl(SRC2_IP4)) {
ctx->msg_src_ip4 = bpf_htonl(SRC_REWRITE_IP4);
} else {
/* Unexpected source. Reject sendmsg. */
return 0;
}
/* Rewrite destination. */
if ((ctx->user_ip4 >> 24) == (bpf_htonl(DST_IP4) >> 24) &&
ctx->user_port == bpf_htons(DST_PORT)) {
ctx->user_ip4 = bpf_htonl(DST_REWRITE_IP4);
ctx->user_port = bpf_htons(DST_REWRITE_PORT4);
} else {
/* Unexpected source. Reject sendmsg. */
return 0;
}
return 1;
}
char _license[] SEC("license") = "GPL";
@@ -0,0 +1,59 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2018 Facebook
#include <linux/stddef.h>
#include <linux/bpf.h>
#include <sys/socket.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
#define SRC_REWRITE_IP6_0 0
#define SRC_REWRITE_IP6_1 0
#define SRC_REWRITE_IP6_2 0
#define SRC_REWRITE_IP6_3 6
#define DST_REWRITE_IP6_0 0
#define DST_REWRITE_IP6_1 0
#define DST_REWRITE_IP6_2 0
#define DST_REWRITE_IP6_3 1
#define DST_REWRITE_PORT6 6666
int _version SEC("version") = 1;
SEC("cgroup/sendmsg6")
int sendmsg_v6_prog(struct bpf_sock_addr *ctx)
{
if (ctx->type != SOCK_DGRAM)
return 0;
/* Rewrite source. */
if (ctx->msg_src_ip6[3] == bpf_htonl(1) ||
ctx->msg_src_ip6[3] == bpf_htonl(0)) {
ctx->msg_src_ip6[0] = bpf_htonl(SRC_REWRITE_IP6_0);
ctx->msg_src_ip6[1] = bpf_htonl(SRC_REWRITE_IP6_1);
ctx->msg_src_ip6[2] = bpf_htonl(SRC_REWRITE_IP6_2);
ctx->msg_src_ip6[3] = bpf_htonl(SRC_REWRITE_IP6_3);
} else {
/* Unexpected source. Reject sendmsg. */
return 0;
}
/* Rewrite destination. */
if (ctx->user_ip6[0] == bpf_htonl(0xFACEB00C)) {
ctx->user_ip6[0] = bpf_htonl(DST_REWRITE_IP6_0);
ctx->user_ip6[1] = bpf_htonl(DST_REWRITE_IP6_1);
ctx->user_ip6[2] = bpf_htonl(DST_REWRITE_IP6_2);
ctx->user_ip6[3] = bpf_htonl(DST_REWRITE_IP6_3);
ctx->user_port = bpf_htons(DST_REWRITE_PORT6);
} else {
/* Unexpected destination. Reject sendmsg. */
return 0;
}
return 1;
}
char _license[] SEC("license") = "GPL";
@@ -0,0 +1,60 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2018 Facebook
#include <linux/bpf.h>
#include <sys/socket.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
struct bpf_map_def SEC("maps") socket_cookies = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(__u64),
.value_size = sizeof(__u32),
.max_entries = 1 << 8,
};
SEC("cgroup/connect6")
int set_cookie(struct bpf_sock_addr *ctx)
{
__u32 cookie_value = 0xFF;
__u64 cookie_key;
if (ctx->family != AF_INET6 || ctx->user_family != AF_INET6)
return 1;
cookie_key = bpf_get_socket_cookie(ctx);
if (bpf_map_update_elem(&socket_cookies, &cookie_key, &cookie_value, 0))
return 0;
return 1;
}
SEC("sockops")
int update_cookie(struct bpf_sock_ops *ctx)
{
__u32 new_cookie_value;
__u32 *cookie_value;
__u64 cookie_key;
if (ctx->family != AF_INET6)
return 1;
if (ctx->op != BPF_SOCK_OPS_TCP_CONNECT_CB)
return 1;
cookie_key = bpf_get_socket_cookie(ctx);
cookie_value = bpf_map_lookup_elem(&socket_cookies, &cookie_key);
if (!cookie_value)
return 1;
new_cookie_value = (ctx->local_port << 8) | *cookie_value;
bpf_map_update_elem(&socket_cookies, &cookie_key, &new_cookie_value, 0);
return 1;
}
int _version SEC("version") = 1;
char _license[] SEC("license") = "GPL";
@@ -0,0 +1,46 @@
#include <linux/bpf.h>
#include "bpf_helpers.h"
#include "bpf_util.h"
#include "bpf_endian.h"
int _version SEC("version") = 1;
#define bpf_printk(fmt, ...) \
({ \
char ____fmt[] = fmt; \
bpf_trace_printk(____fmt, sizeof(____fmt), \
##__VA_ARGS__); \
})
SEC("sk_skb1")
int bpf_prog1(struct __sk_buff *skb)
{
void *data_end = (void *)(long) skb->data_end;
void *data = (void *)(long) skb->data;
__u32 lport = skb->local_port;
__u32 rport = skb->remote_port;
__u8 *d = data;
__u32 len = (__u32) data_end - (__u32) data;
int err;
if (data + 10 > data_end) {
err = bpf_skb_pull_data(skb, 10);
if (err)
return SK_DROP;
data_end = (void *)(long)skb->data_end;
data = (void *)(long)skb->data;
if (data + 10 > data_end)
return SK_DROP;
}
/* This write/read is a bit pointless but tests the verifier and
* strparser handler for read/write pkt data and access into sk
* fields.
*/
d = data;
d[7] = 1;
return skb->len;
}
char _license[] SEC("license") = "GPL";
@@ -0,0 +1,33 @@
#include <linux/bpf.h>
#include "bpf_helpers.h"
#include "bpf_util.h"
#include "bpf_endian.h"
int _version SEC("version") = 1;
#define bpf_printk(fmt, ...) \
({ \
char ____fmt[] = fmt; \
bpf_trace_printk(____fmt, sizeof(____fmt), \
##__VA_ARGS__); \
})
SEC("sk_msg1")
int bpf_prog1(struct sk_msg_md *msg)
{
void *data_end = (void *)(long) msg->data_end;
void *data = (void *)(long) msg->data;
char *d;
if (data + 8 > data_end)
return SK_DROP;
bpf_printk("data length %i\n", (__u64)msg->data_end - (__u64)msg->data);
d = (char *)data;
bpf_printk("hello sendmsg hook %i %i\n", d[0], d[1]);
return SK_PASS;
}
char _license[] SEC("license") = "GPL";
@@ -0,0 +1,73 @@
#include <linux/bpf.h>
#include "bpf_helpers.h"
#include "bpf_util.h"
#include "bpf_endian.h"
int _version SEC("version") = 1;
#define bpf_printk(fmt, ...) \
({ \
char ____fmt[] = fmt; \
bpf_trace_printk(____fmt, sizeof(____fmt), \
##__VA_ARGS__); \
})
struct bpf_map_def SEC("maps") sock_map_rx = {
.type = BPF_MAP_TYPE_SOCKMAP,
.key_size = sizeof(int),
.value_size = sizeof(int),
.max_entries = 20,
};
struct bpf_map_def SEC("maps") sock_map_tx = {
.type = BPF_MAP_TYPE_SOCKMAP,
.key_size = sizeof(int),
.value_size = sizeof(int),
.max_entries = 20,
};
struct bpf_map_def SEC("maps") sock_map_msg = {
.type = BPF_MAP_TYPE_SOCKMAP,
.key_size = sizeof(int),
.value_size = sizeof(int),
.max_entries = 20,
};
struct bpf_map_def SEC("maps") sock_map_break = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(int),
.max_entries = 20,
};
SEC("sk_skb2")
int bpf_prog2(struct __sk_buff *skb)
{
void *data_end = (void *)(long) skb->data_end;
void *data = (void *)(long) skb->data;
__u32 lport = skb->local_port;
__u32 rport = skb->remote_port;
__u8 *d = data;
__u8 sk, map;
if (data + 8 > data_end)
return SK_DROP;
map = d[0];
sk = d[1];
d[0] = 0xd;
d[1] = 0xe;
d[2] = 0xa;
d[3] = 0xd;
d[4] = 0xb;
d[5] = 0xe;
d[6] = 0xe;
d[7] = 0xf;
if (!map)
return bpf_sk_redirect_map(skb, &sock_map_rx, sk, 0);
return bpf_sk_redirect_map(skb, &sock_map_tx, sk, 0);
}
char _license[] SEC("license") = "GPL";
+51
View File
@@ -0,0 +1,51 @@
#!/usr/bin/env python3
#
# SPDX-License-Identifier: GPL-2.0
#
import sys, os, os.path, getopt
import socket, time
import subprocess
import select
def read(sock, n):
buf = b''
while len(buf) < n:
rem = n - len(buf)
try: s = sock.recv(rem)
except (socket.error) as e: return b''
buf += s
return buf
def send(sock, s):
total = len(s)
count = 0
while count < total:
try: n = sock.send(s)
except (socket.error) as e: n = 0
if n == 0:
return count;
count += n
return count
serverPort = int(sys.argv[1])
HostName = socket.gethostname()
# create active socket
sock = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
try:
sock.connect((HostName, serverPort))
except socket.error as e:
sys.exit(1)
buf = b''
n = 0
while n < 1000:
buf += b'+'
n += 1
sock.settimeout(1);
n = send(sock, buf)
n = read(sock, 500)
sys.exit(0)
+83
View File
@@ -0,0 +1,83 @@
#!/usr/bin/env python3
#
# SPDX-License-Identifier: GPL-2.0
#
import sys, os, os.path, getopt
import socket, time
import subprocess
import select
def read(sock, n):
buf = b''
while len(buf) < n:
rem = n - len(buf)
try: s = sock.recv(rem)
except (socket.error) as e: return b''
buf += s
return buf
def send(sock, s):
total = len(s)
count = 0
while count < total:
try: n = sock.send(s)
except (socket.error) as e: n = 0
if n == 0:
return count;
count += n
return count
SERVER_PORT = 12877
MAX_PORTS = 2
serverPort = SERVER_PORT
serverSocket = None
HostName = socket.gethostname()
# create passive socket
serverSocket = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
host = socket.gethostname()
try: serverSocket.bind((host, 0))
except socket.error as msg:
print('bind fails: ' + str(msg))
sn = serverSocket.getsockname()
serverPort = sn[1]
cmdStr = ("./tcp_client.py %d &") % (serverPort)
os.system(cmdStr)
buf = b''
n = 0
while n < 500:
buf += b'.'
n += 1
serverSocket.listen(MAX_PORTS)
readList = [serverSocket]
while True:
readyRead, readyWrite, inError = \
select.select(readList, [], [], 2)
if len(readyRead) > 0:
waitCount = 0
for sock in readyRead:
if sock == serverSocket:
(clientSocket, address) = serverSocket.accept()
address = str(address[0])
readList.append(clientSocket)
else:
sock.settimeout(1);
s = read(sock, 1000)
n = send(sock, buf)
sock.close()
serverSocket.close()
sys.exit(0)
else:
print('Select timeout!')
sys.exit(1)
@@ -0,0 +1,30 @@
/* SPDX-License-Identifier: GPL-2.0
* Copyright (c) 2018 Facebook
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
#include <linux/bpf.h>
#include <linux/if_ether.h>
#include "bpf_helpers.h"
int _version SEC("version") = 1;
SEC("xdp_adjust_tail")
int _xdp_adjust_tail(struct xdp_md *xdp)
{
void *data_end = (void *)(long)xdp->data_end;
void *data = (void *)(long)xdp->data;
int offset = 0;
if (data_end - data == 54)
offset = 256;
else
offset = 20;
if (bpf_xdp_adjust_tail(xdp, 0 - offset))
return XDP_DROP;
return XDP_TX;
}
char _license[] SEC("license") = "GPL";
+719
View File
@@ -0,0 +1,719 @@
#include <asm/types.h>
#include <linux/types.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <errno.h>
#include <string.h>
#include <stddef.h>
#include <stdbool.h>
#include <linux/unistd.h>
#include <linux/filter.h>
#include <linux/bpf_perf_event.h>
#include <linux/bpf.h>
#include <bpf/bpf.h>
#include "../../../include/linux/filter.h"
#include "bpf_rlimit.h"
#include "bpf_util.h"
#define MAX_INSNS 512
#define MAX_MATCHES 16
struct bpf_reg_match {
unsigned int line;
const char *match;
};
struct bpf_align_test {
const char *descr;
struct bpf_insn insns[MAX_INSNS];
enum {
UNDEF,
ACCEPT,
REJECT
} result;
enum bpf_prog_type prog_type;
/* Matches must be in order of increasing line */
struct bpf_reg_match matches[MAX_MATCHES];
};
static struct bpf_align_test tests[] = {
/* Four tests of known constants. These aren't staggeringly
* interesting since we track exact values now.
*/
{
.descr = "mov",
.insns = {
BPF_MOV64_IMM(BPF_REG_3, 2),
BPF_MOV64_IMM(BPF_REG_3, 4),
BPF_MOV64_IMM(BPF_REG_3, 8),
BPF_MOV64_IMM(BPF_REG_3, 16),
BPF_MOV64_IMM(BPF_REG_3, 32),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
{1, "R1=ctx(id=0,off=0,imm=0)"},
{1, "R10=fp0"},
{1, "R3_w=inv2"},
{2, "R3_w=inv4"},
{3, "R3_w=inv8"},
{4, "R3_w=inv16"},
{5, "R3_w=inv32"},
},
},
{
.descr = "shift",
.insns = {
BPF_MOV64_IMM(BPF_REG_3, 1),
BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
BPF_ALU64_IMM(BPF_RSH, BPF_REG_3, 4),
BPF_MOV64_IMM(BPF_REG_4, 32),
BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
{1, "R1=ctx(id=0,off=0,imm=0)"},
{1, "R10=fp0"},
{1, "R3_w=inv1"},
{2, "R3_w=inv2"},
{3, "R3_w=inv4"},
{4, "R3_w=inv8"},
{5, "R3_w=inv16"},
{6, "R3_w=inv1"},
{7, "R4_w=inv32"},
{8, "R4_w=inv16"},
{9, "R4_w=inv8"},
{10, "R4_w=inv4"},
{11, "R4_w=inv2"},
},
},
{
.descr = "addsub",
.insns = {
BPF_MOV64_IMM(BPF_REG_3, 4),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 4),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 2),
BPF_MOV64_IMM(BPF_REG_4, 8),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 2),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
{1, "R1=ctx(id=0,off=0,imm=0)"},
{1, "R10=fp0"},
{1, "R3_w=inv4"},
{2, "R3_w=inv8"},
{3, "R3_w=inv10"},
{4, "R4_w=inv8"},
{5, "R4_w=inv12"},
{6, "R4_w=inv14"},
},
},
{
.descr = "mul",
.insns = {
BPF_MOV64_IMM(BPF_REG_3, 7),
BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, 1),
BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, 2),
BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, 4),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
{1, "R1=ctx(id=0,off=0,imm=0)"},
{1, "R10=fp0"},
{1, "R3_w=inv7"},
{2, "R3_w=inv7"},
{3, "R3_w=inv14"},
{4, "R3_w=inv56"},
},
},
/* Tests using unknown values */
#define PREP_PKT_POINTERS \
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, \
offsetof(struct __sk_buff, data)), \
BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, \
offsetof(struct __sk_buff, data_end))
#define LOAD_UNKNOWN(DST_REG) \
PREP_PKT_POINTERS, \
BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), \
BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), \
BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_0, 1), \
BPF_EXIT_INSN(), \
BPF_LDX_MEM(BPF_B, DST_REG, BPF_REG_2, 0)
{
.descr = "unknown shift",
.insns = {
LOAD_UNKNOWN(BPF_REG_3),
BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
LOAD_UNKNOWN(BPF_REG_4),
BPF_ALU64_IMM(BPF_LSH, BPF_REG_4, 5),
BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
{7, "R0=pkt(id=0,off=8,r=8,imm=0)"},
{7, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
{8, "R3_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
{9, "R3_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
{10, "R3_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
{11, "R3_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
{18, "R3=pkt_end(id=0,off=0,imm=0)"},
{18, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
{19, "R4_w=inv(id=0,umax_value=8160,var_off=(0x0; 0x1fe0))"},
{20, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
{21, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
{22, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
{23, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
},
},
{
.descr = "unknown mul",
.insns = {
LOAD_UNKNOWN(BPF_REG_3),
BPF_MOV64_REG(BPF_REG_4, BPF_REG_3),
BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 1),
BPF_MOV64_REG(BPF_REG_4, BPF_REG_3),
BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 2),
BPF_MOV64_REG(BPF_REG_4, BPF_REG_3),
BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 4),
BPF_MOV64_REG(BPF_REG_4, BPF_REG_3),
BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 8),
BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 2),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
{7, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
{8, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
{9, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
{10, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
{11, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
{12, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
{13, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
{14, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
{15, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
{16, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
},
},
{
.descr = "packet const offset",
.insns = {
PREP_PKT_POINTERS,
BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
BPF_MOV64_IMM(BPF_REG_0, 0),
/* Skip over ethernet header. */
BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14),
BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
BPF_EXIT_INSN(),
BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 0),
BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 1),
BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 2),
BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 3),
BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_5, 0),
BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_5, 2),
BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_5, 0),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
{4, "R5_w=pkt(id=0,off=0,r=0,imm=0)"},
{5, "R5_w=pkt(id=0,off=14,r=0,imm=0)"},
{6, "R4_w=pkt(id=0,off=14,r=0,imm=0)"},
{10, "R2=pkt(id=0,off=0,r=18,imm=0)"},
{10, "R5=pkt(id=0,off=14,r=18,imm=0)"},
{10, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
{14, "R4_w=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"},
{15, "R4_w=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"},
},
},
{
.descr = "packet variable offset",
.insns = {
LOAD_UNKNOWN(BPF_REG_6),
BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 2),
/* First, add a constant to the R5 packet pointer,
* then a variable with a known alignment.
*/
BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14),
BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
BPF_EXIT_INSN(),
BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_5, 0),
/* Now, test in the other direction. Adding first
* the variable offset to R5, then the constant.
*/
BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14),
BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
BPF_EXIT_INSN(),
BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_5, 0),
/* Test multiple accumulations of unknown values
* into a packet pointer.
*/
BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14),
BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 4),
BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
BPF_EXIT_INSN(),
BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_5, 0),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
/* Calculated offset in R6 has unknown value, but known
* alignment of 4.
*/
{8, "R2=pkt(id=0,off=0,r=8,imm=0)"},
{8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
/* Offset is added to packet pointer R5, resulting in
* known fixed offset, and variable offset from R6.
*/
{11, "R5_w=pkt(id=1,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
/* At the time the word size load is performed from R5,
* it's total offset is NET_IP_ALIGN + reg->off (0) +
* reg->aux_off (14) which is 16. Then the variable
* offset is considered using reg->aux_off_align which
* is 4 and meets the load's requirements.
*/
{15, "R4=pkt(id=1,off=18,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"},
{15, "R5=pkt(id=1,off=14,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"},
/* Variable offset is added to R5 packet pointer,
* resulting in auxiliary alignment of 4.
*/
{18, "R5_w=pkt(id=2,off=0,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
/* Constant offset is added to R5, resulting in
* reg->off of 14.
*/
{19, "R5_w=pkt(id=2,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
/* At the time the word size load is performed from R5,
* its total fixed offset is NET_IP_ALIGN + reg->off
* (14) which is 16. Then the variable offset is 4-byte
* aligned, so the total offset is 4-byte aligned and
* meets the load's requirements.
*/
{23, "R4=pkt(id=2,off=18,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"},
{23, "R5=pkt(id=2,off=14,r=18,umax_value=1020,var_off=(0x0; 0x3fc))"},
/* Constant offset is added to R5 packet pointer,
* resulting in reg->off value of 14.
*/
{26, "R5_w=pkt(id=0,off=14,r=8"},
/* Variable offset is added to R5, resulting in a
* variable offset of (4n).
*/
{27, "R5_w=pkt(id=3,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
/* Constant is added to R5 again, setting reg->off to 18. */
{28, "R5_w=pkt(id=3,off=18,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
/* And once more we add a variable; resulting var_off
* is still (4n), fixed offset is not changed.
* Also, we create a new reg->id.
*/
{29, "R5_w=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc))"},
/* At the time the word size load is performed from R5,
* its total fixed offset is NET_IP_ALIGN + reg->off (18)
* which is 20. Then the variable offset is (4n), so
* the total offset is 4-byte aligned and meets the
* load's requirements.
*/
{33, "R4=pkt(id=4,off=22,r=22,umax_value=2040,var_off=(0x0; 0x7fc))"},
{33, "R5=pkt(id=4,off=18,r=22,umax_value=2040,var_off=(0x0; 0x7fc))"},
},
},
{
.descr = "packet variable offset 2",
.insns = {
/* Create an unknown offset, (4n+2)-aligned */
LOAD_UNKNOWN(BPF_REG_6),
BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 2),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 14),
/* Add it to the packet pointer */
BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
/* Check bounds and perform a read */
BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
BPF_EXIT_INSN(),
BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_5, 0),
/* Make a (4n) offset from the value we just read */
BPF_ALU64_IMM(BPF_AND, BPF_REG_6, 0xff),
BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 2),
/* Add it to the packet pointer */
BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
/* Check bounds and perform a read */
BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
BPF_EXIT_INSN(),
BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_5, 0),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
/* Calculated offset in R6 has unknown value, but known
* alignment of 4.
*/
{8, "R2=pkt(id=0,off=0,r=8,imm=0)"},
{8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
/* Adding 14 makes R6 be (4n+2) */
{9, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
/* Packet pointer has (4n+2) offset */
{11, "R5_w=pkt(id=1,off=0,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
{13, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
/* At the time the word size load is performed from R5,
* its total fixed offset is NET_IP_ALIGN + reg->off (0)
* which is 2. Then the variable offset is (4n+2), so
* the total offset is 4-byte aligned and meets the
* load's requirements.
*/
{15, "R5=pkt(id=1,off=0,r=4,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
/* Newly read value in R6 was shifted left by 2, so has
* known alignment of 4.
*/
{18, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
/* Added (4n) to packet pointer's (4n+2) var_off, giving
* another (4n+2).
*/
{19, "R5_w=pkt(id=2,off=0,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"},
{21, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"},
/* At the time the word size load is performed from R5,
* its total fixed offset is NET_IP_ALIGN + reg->off (0)
* which is 2. Then the variable offset is (4n+2), so
* the total offset is 4-byte aligned and meets the
* load's requirements.
*/
{23, "R5=pkt(id=2,off=0,r=4,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"},
},
},
{
.descr = "dubious pointer arithmetic",
.insns = {
PREP_PKT_POINTERS,
BPF_MOV64_IMM(BPF_REG_0, 0),
/* (ptr - ptr) << 2 */
BPF_MOV64_REG(BPF_REG_5, BPF_REG_3),
BPF_ALU64_REG(BPF_SUB, BPF_REG_5, BPF_REG_2),
BPF_ALU64_IMM(BPF_LSH, BPF_REG_5, 2),
/* We have a (4n) value. Let's make a packet offset
* out of it. First add 14, to make it a (4n+2)
*/
BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14),
/* Then make sure it's nonnegative */
BPF_JMP_IMM(BPF_JSGE, BPF_REG_5, 0, 1),
BPF_EXIT_INSN(),
/* Add it to packet pointer */
BPF_MOV64_REG(BPF_REG_6, BPF_REG_2),
BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_5),
/* Check bounds and perform a read */
BPF_MOV64_REG(BPF_REG_4, BPF_REG_6),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
BPF_EXIT_INSN(),
BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_6, 0),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = REJECT,
.matches = {
{4, "R5_w=pkt_end(id=0,off=0,imm=0)"},
/* (ptr - ptr) << 2 == unknown, (4n) */
{6, "R5_w=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc))"},
/* (4n) + 14 == (4n+2). We blow our bounds, because
* the add could overflow.
*/
{7, "R5=inv(id=0,var_off=(0x2; 0xfffffffffffffffc))"},
/* Checked s>=0 */
{9, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
/* packet pointer + nonnegative (4n+2) */
{11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
{13, "R4=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
/* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine.
* We checked the bounds, but it might have been able
* to overflow if the packet pointer started in the
* upper half of the address space.
* So we did not get a 'range' on R6, and the access
* attempt will fail.
*/
{15, "R6=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"},
}
},
{
.descr = "variable subtraction",
.insns = {
/* Create an unknown offset, (4n+2)-aligned */
LOAD_UNKNOWN(BPF_REG_6),
BPF_MOV64_REG(BPF_REG_7, BPF_REG_6),
BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 2),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 14),
/* Create another unknown, (4n)-aligned, and subtract
* it from the first one
*/
BPF_ALU64_IMM(BPF_LSH, BPF_REG_7, 2),
BPF_ALU64_REG(BPF_SUB, BPF_REG_6, BPF_REG_7),
/* Bounds-check the result */
BPF_JMP_IMM(BPF_JSGE, BPF_REG_6, 0, 1),
BPF_EXIT_INSN(),
/* Add it to the packet pointer */
BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
/* Check bounds and perform a read */
BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
BPF_EXIT_INSN(),
BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_5, 0),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
/* Calculated offset in R6 has unknown value, but known
* alignment of 4.
*/
{7, "R2=pkt(id=0,off=0,r=8,imm=0)"},
{9, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
/* Adding 14 makes R6 be (4n+2) */
{10, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"},
/* New unknown value in R7 is (4n) */
{11, "R7_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
/* Subtracting it from R6 blows our unsigned bounds */
{12, "R6=inv(id=0,smin_value=-1006,smax_value=1034,var_off=(0x2; 0xfffffffffffffffc))"},
/* Checked s>= 0 */
{14, "R6=inv(id=0,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc))"},
/* At the time the word size load is performed from R5,
* its total fixed offset is NET_IP_ALIGN + reg->off (0)
* which is 2. Then the variable offset is (4n+2), so
* the total offset is 4-byte aligned and meets the
* load's requirements.
*/
{20, "R5=pkt(id=1,off=0,r=4,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc))"},
},
},
{
.descr = "pointer variable subtraction",
.insns = {
/* Create an unknown offset, (4n+2)-aligned and bounded
* to [14,74]
*/
LOAD_UNKNOWN(BPF_REG_6),
BPF_MOV64_REG(BPF_REG_7, BPF_REG_6),
BPF_ALU64_IMM(BPF_AND, BPF_REG_6, 0xf),
BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 2),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 14),
/* Subtract it from the packet pointer */
BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
BPF_ALU64_REG(BPF_SUB, BPF_REG_5, BPF_REG_6),
/* Create another unknown, (4n)-aligned and >= 74.
* That in fact means >= 76, since 74 % 4 == 2
*/
BPF_ALU64_IMM(BPF_LSH, BPF_REG_7, 2),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 76),
/* Add it to the packet pointer */
BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_7),
/* Check bounds and perform a read */
BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
BPF_EXIT_INSN(),
BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_5, 0),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.matches = {
/* Calculated offset in R6 has unknown value, but known
* alignment of 4.
*/
{7, "R2=pkt(id=0,off=0,r=8,imm=0)"},
{10, "R6_w=inv(id=0,umax_value=60,var_off=(0x0; 0x3c))"},
/* Adding 14 makes R6 be (4n+2) */
{11, "R6_w=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"},
/* Subtracting from packet pointer overflows ubounds */
{13, "R5_w=pkt(id=1,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c))"},
/* New unknown value in R7 is (4n), >= 76 */
{15, "R7_w=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"},
/* Adding it to packet pointer gives nice bounds again */
{16, "R5_w=pkt(id=2,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0x7fc))"},
/* At the time the word size load is performed from R5,
* its total fixed offset is NET_IP_ALIGN + reg->off (0)
* which is 2. Then the variable offset is (4n+2), so
* the total offset is 4-byte aligned and meets the
* load's requirements.
*/
{20, "R5=pkt(id=2,off=0,r=4,umin_value=2,umax_value=1082,var_off=(0x2; 0x7fc))"},
},
},
};
static int probe_filter_length(const struct bpf_insn *fp)
{
int len;
for (len = MAX_INSNS - 1; len > 0; --len)
if (fp[len].code != 0 || fp[len].imm != 0)
break;
return len + 1;
}
static char bpf_vlog[32768];
static int do_test_single(struct bpf_align_test *test)
{
struct bpf_insn *prog = test->insns;
int prog_type = test->prog_type;
char bpf_vlog_copy[32768];
const char *line_ptr;
int cur_line = -1;
int prog_len, i;
int fd_prog;
int ret;
prog_len = probe_filter_length(prog);
fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
prog, prog_len, 1, "GPL", 0,
bpf_vlog, sizeof(bpf_vlog), 2);
if (fd_prog < 0 && test->result != REJECT) {
printf("Failed to load program.\n");
printf("%s", bpf_vlog);
ret = 1;
} else if (fd_prog >= 0 && test->result == REJECT) {
printf("Unexpected success to load!\n");
printf("%s", bpf_vlog);
ret = 1;
close(fd_prog);
} else {
ret = 0;
/* We make a local copy so that we can strtok() it */
strncpy(bpf_vlog_copy, bpf_vlog, sizeof(bpf_vlog_copy));
line_ptr = strtok(bpf_vlog_copy, "\n");
for (i = 0; i < MAX_MATCHES; i++) {
struct bpf_reg_match m = test->matches[i];
if (!m.match)
break;
while (line_ptr) {
cur_line = -1;
sscanf(line_ptr, "%u: ", &cur_line);
if (cur_line == m.line)
break;
line_ptr = strtok(NULL, "\n");
}
if (!line_ptr) {
printf("Failed to find line %u for match: %s\n",
m.line, m.match);
ret = 1;
printf("%s", bpf_vlog);
break;
}
if (!strstr(line_ptr, m.match)) {
printf("Failed to find match %u: %s\n",
m.line, m.match);
ret = 1;
printf("%s", bpf_vlog);
break;
}
}
if (fd_prog >= 0)
close(fd_prog);
}
return ret;
}
static int do_test(unsigned int from, unsigned int to)
{
int all_pass = 0;
int all_fail = 0;
unsigned int i;
for (i = from; i < to; i++) {
struct bpf_align_test *test = &tests[i];
int fail;
printf("Test %3d: %s ... ",
i, test->descr);
fail = do_test_single(test);
if (fail) {
all_fail++;
printf("FAIL\n");
} else {
all_pass++;
printf("PASS\n");
}
}
printf("Results: %d pass %d fail\n",
all_pass, all_fail);
return all_fail ? EXIT_FAILURE : EXIT_SUCCESS;
}
int main(int argc, char **argv)
{
unsigned int from = 0, to = ARRAY_SIZE(tests);
if (argc == 3) {
unsigned int l = atoi(argv[argc - 2]);
unsigned int u = atoi(argv[argc - 1]);
if (l < to && u < to) {
from = l;
to = u + 1;
}
} else if (argc == 2) {
unsigned int t = atoi(argv[argc - 1]);
if (t < to) {
from = t;
to = t + 1;
}
}
return do_test(from, to);
}
File diff suppressed because it is too large. Load diff
@@ -0,0 +1,45 @@
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (c) 2018 Facebook */
#include <linux/bpf.h>
#include "bpf_helpers.h"
int _version SEC("version") = 1;
struct ipv_counts {
unsigned int v4;
unsigned int v6;
};
struct bpf_map_def SEC("maps") btf_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(struct ipv_counts),
.max_entries = 4,
};
BPF_ANNOTATE_KV_PAIR(btf_map, int, struct ipv_counts);
struct dummy_tracepoint_args {
unsigned long long pad;
struct sock *sock;
};
SEC("dummy_tracepoint")
int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
{
struct ipv_counts *counts;
int key = 0;
if (!arg->sock)
return 0;
counts = bpf_map_lookup_elem(&btf_map, &key);
if (!counts)
return 0;
counts->v6++;
return 0;
}
char _license[] SEC("license") = "GPL";
@@ -0,0 +1,43 @@
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (c) 2018 Facebook */
#include <linux/bpf.h>
#include "bpf_helpers.h"
int _version SEC("version") = 1;
struct ipv_counts {
unsigned int v4;
unsigned int v6;
};
struct bpf_map_def SEC("maps") btf_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(struct ipv_counts),
.max_entries = 4,
};
struct dummy_tracepoint_args {
unsigned long long pad;
struct sock *sock;
};
SEC("dummy_tracepoint")
int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
{
struct ipv_counts *counts;
int key = 0;
if (!arg->sock)
return 0;
counts = bpf_map_lookup_elem(&btf_map, &key);
if (!counts)
return 0;
counts->v6++;
return 0;
}
char _license[] SEC("license") = "GPL";
@@ -0,0 +1,131 @@
// SPDX-License-Identifier: GPL-2.0
#include <assert.h>
#include <bpf/bpf.h>
#include <linux/filter.h>
#include <stdio.h>
#include <stdlib.h>
#include "bpf_rlimit.h"
#include "cgroup_helpers.h"
char bpf_log_buf[BPF_LOG_BUF_SIZE];
#define TEST_CGROUP "/test-bpf-cgroup-storage-buf/"
int main(int argc, char **argv)
{
struct bpf_insn prog[] = {
BPF_LD_MAP_FD(BPF_REG_1, 0), /* map fd */
BPF_MOV64_IMM(BPF_REG_2, 0), /* flags, not used */
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
BPF_FUNC_get_local_storage),
BPF_MOV64_IMM(BPF_REG_1, 1),
BPF_STX_XADD(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x1),
BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
BPF_EXIT_INSN(),
};
size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
int error = EXIT_FAILURE;
int map_fd, prog_fd, cgroup_fd;
struct bpf_cgroup_storage_key key;
unsigned long long value;
map_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE, sizeof(key),
sizeof(value), 0, 0);
if (map_fd < 0) {
printf("Failed to create map: %s\n", strerror(errno));
goto out;
}
prog[0].imm = map_fd;
prog_fd = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB,
prog, insns_cnt, "GPL", 0,
bpf_log_buf, BPF_LOG_BUF_SIZE);
if (prog_fd < 0) {
printf("Failed to load bpf program: %s\n", bpf_log_buf);
goto out;
}
if (setup_cgroup_environment()) {
printf("Failed to setup cgroup environment\n");
goto err;
}
/* Create a cgroup, get fd, and join it */
cgroup_fd = create_and_get_cgroup(TEST_CGROUP);
if (!cgroup_fd) {
printf("Failed to create test cgroup\n");
goto err;
}
if (join_cgroup(TEST_CGROUP)) {
printf("Failed to join cgroup\n");
goto err;
}
/* Attach the bpf program */
if (bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0)) {
printf("Failed to attach bpf program\n");
goto err;
}
if (bpf_map_get_next_key(map_fd, NULL, &key)) {
printf("Failed to get the first key in cgroup storage\n");
goto err;
}
if (bpf_map_lookup_elem(map_fd, &key, &value)) {
printf("Failed to lookup cgroup storage\n");
goto err;
}
/* Every second packet should be dropped */
assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
assert(system("ping localhost -c 1 -W 1 -q > /dev/null"));
assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
/* Check the counter in the cgroup local storage */
if (bpf_map_lookup_elem(map_fd, &key, &value)) {
printf("Failed to lookup cgroup storage\n");
goto err;
}
if (value != 3) {
printf("Unexpected data in the cgroup storage: %llu\n", value);
goto err;
}
/* Bump the counter in the cgroup local storage */
value++;
if (bpf_map_update_elem(map_fd, &key, &value, 0)) {
printf("Failed to update the data in the cgroup storage\n");
goto err;
}
/* Every second packet should be dropped */
assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
assert(system("ping localhost -c 1 -W 1 -q > /dev/null"));
assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
/* Check the final value of the counter in the cgroup local storage */
if (bpf_map_lookup_elem(map_fd, &key, &value)) {
printf("Failed to lookup the cgroup storage\n");
goto err;
}
if (value != 7) {
printf("Unexpected data in the cgroup storage: %llu\n", value);
goto err;
}
error = 0;
printf("test_cgroup_storage:PASS\n");
err:
cleanup_cgroup_environment();
out:
return error;
}
@@ -0,0 +1,96 @@
/* Copyright (c) 2017 Facebook
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <assert.h>
#include <sys/time.h>
#include <linux/bpf.h>
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
#include "cgroup_helpers.h"
#include "bpf_rlimit.h"
#define DEV_CGROUP_PROG "./dev_cgroup.o"
#define TEST_CGROUP "/test-bpf-based-device-cgroup/"
int main(int argc, char **argv)
{
struct bpf_object *obj;
int error = EXIT_FAILURE;
int prog_fd, cgroup_fd;
__u32 prog_cnt;
if (bpf_prog_load(DEV_CGROUP_PROG, BPF_PROG_TYPE_CGROUP_DEVICE,
&obj, &prog_fd)) {
printf("Failed to load DEV_CGROUP program\n");
goto out;
}
if (setup_cgroup_environment()) {
printf("Failed to load DEV_CGROUP program\n");
goto err;
}
/* Create a cgroup, get fd, and join it */
cgroup_fd = create_and_get_cgroup(TEST_CGROUP);
if (!cgroup_fd) {
printf("Failed to create test cgroup\n");
goto err;
}
if (join_cgroup(TEST_CGROUP)) {
printf("Failed to join cgroup\n");
goto err;
}
/* Attach bpf program */
if (bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_DEVICE, 0)) {
printf("Failed to attach DEV_CGROUP program");
goto err;
}
if (bpf_prog_query(cgroup_fd, BPF_CGROUP_DEVICE, 0, NULL, NULL,
&prog_cnt)) {
printf("Failed to query attached programs");
goto err;
}
/* All operations with /dev/zero and and /dev/urandom are allowed,
* everything else is forbidden.
*/
assert(system("rm -f /tmp/test_dev_cgroup_null") == 0);
assert(system("mknod /tmp/test_dev_cgroup_null c 1 3"));
assert(system("rm -f /tmp/test_dev_cgroup_null") == 0);
/* /dev/zero is whitelisted */
assert(system("rm -f /tmp/test_dev_cgroup_zero") == 0);
assert(system("mknod /tmp/test_dev_cgroup_zero c 1 5") == 0);
assert(system("rm -f /tmp/test_dev_cgroup_zero") == 0);
assert(system("dd if=/dev/urandom of=/dev/zero count=64") == 0);
/* src is allowed, target is forbidden */
assert(system("dd if=/dev/urandom of=/dev/full count=64"));
/* src is forbidden, target is allowed */
assert(system("dd if=/dev/random of=/dev/zero count=64"));
error = 0;
printf("test_dev_cgroup:PASS\n");
err:
cleanup_cgroup_environment();
out:
return error;
}
@@ -0,0 +1,102 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
#include "bpf_helpers.h"
/* Permit pretty deep stack traces */
#define MAX_STACK_RAWTP 100
struct stack_trace_t {
int pid;
int kern_stack_size;
int user_stack_size;
int user_stack_buildid_size;
__u64 kern_stack[MAX_STACK_RAWTP];
__u64 user_stack[MAX_STACK_RAWTP];
struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP];
};
struct bpf_map_def SEC("maps") perfmap = {
.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(__u32),
.max_entries = 2,
};
struct bpf_map_def SEC("maps") stackdata_map = {
.type = BPF_MAP_TYPE_PERCPU_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(struct stack_trace_t),
.max_entries = 1,
};
/* Allocate per-cpu space twice the needed. For the code below
* usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK);
* if (usize < 0)
* return 0;
* ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0);
*
* If we have value_size = MAX_STACK_RAWTP * sizeof(__u64),
* verifier will complain that access "raw_data + usize"
* with size "max_len - usize" may be out of bound.
* The maximum "raw_data + usize" is "raw_data + max_len"
* and the maximum "max_len - usize" is "max_len", verifier
* concludes that the maximum buffer access range is
* "raw_data[0...max_len * 2 - 1]" and hence reject the program.
*
* Doubling the to-be-used max buffer size can fix this verifier
* issue and avoid complicated C programming massaging.
* This is an acceptable workaround since there is one entry here.
*/
struct bpf_map_def SEC("maps") rawdata_map = {
.type = BPF_MAP_TYPE_PERCPU_ARRAY,
.key_size = sizeof(__u32),
.value_size = MAX_STACK_RAWTP * sizeof(__u64) * 2,
.max_entries = 1,
};
SEC("tracepoint/raw_syscalls/sys_enter")
int bpf_prog1(void *ctx)
{
int max_len, max_buildid_len, usize, ksize, total_size;
struct stack_trace_t *data;
void *raw_data;
__u32 key = 0;
data = bpf_map_lookup_elem(&stackdata_map, &key);
if (!data)
return 0;
max_len = MAX_STACK_RAWTP * sizeof(__u64);
max_buildid_len = MAX_STACK_RAWTP * sizeof(struct bpf_stack_build_id);
data->pid = bpf_get_current_pid_tgid();
data->kern_stack_size = bpf_get_stack(ctx, data->kern_stack,
max_len, 0);
data->user_stack_size = bpf_get_stack(ctx, data->user_stack, max_len,
BPF_F_USER_STACK);
data->user_stack_buildid_size = bpf_get_stack(
ctx, data->user_stack_buildid, max_buildid_len,
BPF_F_USER_STACK | BPF_F_USER_BUILD_ID);
bpf_perf_event_output(ctx, &perfmap, 0, data, sizeof(*data));
/* write both kernel and user stacks to the same buffer */
raw_data = bpf_map_lookup_elem(&rawdata_map, &key);
if (!raw_data)
return 0;
usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK);
if (usize < 0)
return 0;
ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0);
if (ksize < 0)
return 0;
total_size = usize + ksize;
if (total_size > 0 && total_size <= max_len)
bpf_perf_event_output(ctx, &perfmap, 0, raw_data, total_size);
return 0;
}
char _license[] SEC("license") = "GPL";
__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */
@@ -0,0 +1,37 @@
/* Copyright (c) 2016 Facebook
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
#ifndef _TEST_IPTNL_COMMON_H
#define _TEST_IPTNL_COMMON_H
#include <linux/types.h>
#define MAX_IPTNL_ENTRIES 256U
struct vip {
union {
__u32 v6[4];
__u32 v4;
} daddr;
__u16 dport;
__u16 family;
__u8 protocol;
};
struct iptnl_info {
union {
__u32 v6[4];
__u32 v4;
} saddr;
union {
__u32 v6[4];
__u32 v4;
} daddr;
__u16 family;
__u8 dmac[6];
};
#endif
+61
View File
@@ -0,0 +1,61 @@
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
# Kselftest framework requirement - SKIP code is 4.
ksft_skip=4
msg="skip all tests:"
if [ "$(id -u)" != "0" ]; then
echo $msg please run this as root >&2
exit $ksft_skip
fi
SRC_TREE=../../../../
test_run()
{
sysctl -w net.core.bpf_jit_enable=$1 2>&1 > /dev/null
sysctl -w net.core.bpf_jit_harden=$2 2>&1 > /dev/null
echo "[ JIT enabled:$1 hardened:$2 ]"
dmesg -C
if [ -f ${SRC_TREE}/lib/test_bpf.ko ]; then
insmod ${SRC_TREE}/lib/test_bpf.ko 2> /dev/null
if [ $? -ne 0 ]; then
rc=1
fi
else
# Use modprobe dry run to check for missing test_bpf module
if ! /sbin/modprobe -q -n test_bpf; then
echo "test_bpf: [SKIP]"
elif /sbin/modprobe -q test_bpf; then
echo "test_bpf: ok"
else
echo "test_bpf: [FAIL]"
rc=1
fi
fi
rmmod test_bpf 2> /dev/null
dmesg | grep FAIL
}
test_save()
{
JE=`sysctl -n net.core.bpf_jit_enable`
JH=`sysctl -n net.core.bpf_jit_harden`
}
test_restore()
{
sysctl -w net.core.bpf_jit_enable=$JE 2>&1 > /dev/null
sysctl -w net.core.bpf_jit_harden=$JH 2>&1 > /dev/null
}
rc=0
test_save
test_run 0 0
test_run 1 0
test_run 1 1
test_run 1 2
test_restore
exit $rc
+473
View File
@@ -0,0 +1,473 @@
/* Copyright (c) 2017 Facebook
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
#include <stddef.h>
#include <stdbool.h>
#include <string.h>
#include <linux/pkt_cls.h>
#include <linux/bpf.h>
#include <linux/in.h>
#include <linux/if_ether.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/icmp.h>
#include <linux/icmpv6.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include "bpf_helpers.h"
#include "test_iptunnel_common.h"
#include "bpf_endian.h"
int _version SEC("version") = 1;
static inline __u32 rol32(__u32 word, unsigned int shift)
{
return (word << shift) | (word >> ((-shift) & 31));
}
/* copy paste of jhash from kernel sources to make sure llvm
* can compile it into valid sequence of bpf instructions
*/
#define __jhash_mix(a, b, c) \
{ \
a -= c; a ^= rol32(c, 4); c += b; \
b -= a; b ^= rol32(a, 6); a += c; \
c -= b; c ^= rol32(b, 8); b += a; \
a -= c; a ^= rol32(c, 16); c += b; \
b -= a; b ^= rol32(a, 19); a += c; \
c -= b; c ^= rol32(b, 4); b += a; \
}
#define __jhash_final(a, b, c) \
{ \
c ^= b; c -= rol32(b, 14); \
a ^= c; a -= rol32(c, 11); \
b ^= a; b -= rol32(a, 25); \
c ^= b; c -= rol32(b, 16); \
a ^= c; a -= rol32(c, 4); \
b ^= a; b -= rol32(a, 14); \
c ^= b; c -= rol32(b, 24); \
}
#define JHASH_INITVAL 0xdeadbeef
typedef unsigned int u32;
static inline u32 jhash(const void *key, u32 length, u32 initval)
{
u32 a, b, c;
const unsigned char *k = key;
a = b = c = JHASH_INITVAL + length + initval;
while (length > 12) {
a += *(u32 *)(k);
b += *(u32 *)(k + 4);
c += *(u32 *)(k + 8);
__jhash_mix(a, b, c);
length -= 12;
k += 12;
}
switch (length) {
case 12: c += (u32)k[11]<<24;
case 11: c += (u32)k[10]<<16;
case 10: c += (u32)k[9]<<8;
case 9: c += k[8];
case 8: b += (u32)k[7]<<24;
case 7: b += (u32)k[6]<<16;
case 6: b += (u32)k[5]<<8;
case 5: b += k[4];
case 4: a += (u32)k[3]<<24;
case 3: a += (u32)k[2]<<16;
case 2: a += (u32)k[1]<<8;
case 1: a += k[0];
__jhash_final(a, b, c);
case 0: /* Nothing left to add */
break;
}
return c;
}
static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval)
{
a += initval;
b += initval;
c += initval;
__jhash_final(a, b, c);
return c;
}
static inline u32 jhash_2words(u32 a, u32 b, u32 initval)
{
return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2));
}
#define PCKT_FRAGMENTED 65343
#define IPV4_HDR_LEN_NO_OPT 20
#define IPV4_PLUS_ICMP_HDR 28
#define IPV6_PLUS_ICMP_HDR 48
#define RING_SIZE 2
#define MAX_VIPS 12
#define MAX_REALS 5
#define CTL_MAP_SIZE 16
#define CH_RINGS_SIZE (MAX_VIPS * RING_SIZE)
#define F_IPV6 (1 << 0)
#define F_HASH_NO_SRC_PORT (1 << 0)
#define F_ICMP (1 << 0)
#define F_SYN_SET (1 << 1)
struct packet_description {
union {
__be32 src;
__be32 srcv6[4];
};
union {
__be32 dst;
__be32 dstv6[4];
};
union {
__u32 ports;
__u16 port16[2];
};
__u8 proto;
__u8 flags;
};
struct ctl_value {
union {
__u64 value;
__u32 ifindex;
__u8 mac[6];
};
};
struct vip_meta {
__u32 flags;
__u32 vip_num;
};
struct real_definition {
union {
__be32 dst;
__be32 dstv6[4];
};
__u8 flags;
};
struct vip_stats {
__u64 bytes;
__u64 pkts;
};
struct eth_hdr {
unsigned char eth_dest[ETH_ALEN];
unsigned char eth_source[ETH_ALEN];
unsigned short eth_proto;
};
struct bpf_map_def SEC("maps") vip_map = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(struct vip),
.value_size = sizeof(struct vip_meta),
.max_entries = MAX_VIPS,
};
struct bpf_map_def SEC("maps") ch_rings = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(__u32),
.max_entries = CH_RINGS_SIZE,
};
struct bpf_map_def SEC("maps") reals = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(struct real_definition),
.max_entries = MAX_REALS,
};
struct bpf_map_def SEC("maps") stats = {
.type = BPF_MAP_TYPE_PERCPU_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(struct vip_stats),
.max_entries = MAX_VIPS,
};
struct bpf_map_def SEC("maps") ctl_array = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(struct ctl_value),
.max_entries = CTL_MAP_SIZE,
};
static __always_inline __u32 get_packet_hash(struct packet_description *pckt,
bool ipv6)
{
if (ipv6)
return jhash_2words(jhash(pckt->srcv6, 16, MAX_VIPS),
pckt->ports, CH_RINGS_SIZE);
else
return jhash_2words(pckt->src, pckt->ports, CH_RINGS_SIZE);
}
static __always_inline bool get_packet_dst(struct real_definition **real,
struct packet_description *pckt,
struct vip_meta *vip_info,
bool is_ipv6)
{
__u32 hash = get_packet_hash(pckt, is_ipv6) % RING_SIZE;
__u32 key = RING_SIZE * vip_info->vip_num + hash;
__u32 *real_pos;
real_pos = bpf_map_lookup_elem(&ch_rings, &key);
if (!real_pos)
return false;
key = *real_pos;
*real = bpf_map_lookup_elem(&reals, &key);
if (!(*real))
return false;
return true;
}
static __always_inline int parse_icmpv6(void *data, void *data_end, __u64 off,
struct packet_description *pckt)
{
struct icmp6hdr *icmp_hdr;
struct ipv6hdr *ip6h;
icmp_hdr = data + off;
if (icmp_hdr + 1 > data_end)
return TC_ACT_SHOT;
if (icmp_hdr->icmp6_type != ICMPV6_PKT_TOOBIG)
return TC_ACT_OK;
off += sizeof(struct icmp6hdr);
ip6h = data + off;
if (ip6h + 1 > data_end)
return TC_ACT_SHOT;
pckt->proto = ip6h->nexthdr;
pckt->flags |= F_ICMP;
memcpy(pckt->srcv6, ip6h->daddr.s6_addr32, 16);
memcpy(pckt->dstv6, ip6h->saddr.s6_addr32, 16);
return TC_ACT_UNSPEC;
}
static __always_inline int parse_icmp(void *data, void *data_end, __u64 off,
struct packet_description *pckt)
{
struct icmphdr *icmp_hdr;
struct iphdr *iph;
icmp_hdr = data + off;
if (icmp_hdr + 1 > data_end)
return TC_ACT_SHOT;
if (icmp_hdr->type != ICMP_DEST_UNREACH ||
icmp_hdr->code != ICMP_FRAG_NEEDED)
return TC_ACT_OK;
off += sizeof(struct icmphdr);
iph = data + off;
if (iph + 1 > data_end)
return TC_ACT_SHOT;
if (iph->ihl != 5)
return TC_ACT_SHOT;
pckt->proto = iph->protocol;
pckt->flags |= F_ICMP;
pckt->src = iph->daddr;
pckt->dst = iph->saddr;
return TC_ACT_UNSPEC;
}
static __always_inline bool parse_udp(void *data, __u64 off, void *data_end,
struct packet_description *pckt)
{
struct udphdr *udp;
udp = data + off;
if (udp + 1 > data_end)
return false;
if (!(pckt->flags & F_ICMP)) {
pckt->port16[0] = udp->source;
pckt->port16[1] = udp->dest;
} else {
pckt->port16[0] = udp->dest;
pckt->port16[1] = udp->source;
}
return true;
}
static __always_inline bool parse_tcp(void *data, __u64 off, void *data_end,
struct packet_description *pckt)
{
struct tcphdr *tcp;
tcp = data + off;
if (tcp + 1 > data_end)
return false;
if (tcp->syn)
pckt->flags |= F_SYN_SET;
if (!(pckt->flags & F_ICMP)) {
pckt->port16[0] = tcp->source;
pckt->port16[1] = tcp->dest;
} else {
pckt->port16[0] = tcp->dest;
pckt->port16[1] = tcp->source;
}
return true;
}
static __always_inline int process_packet(void *data, __u64 off, void *data_end,
bool is_ipv6, struct __sk_buff *skb)
{
void *pkt_start = (void *)(long)skb->data;
struct packet_description pckt = {};
struct eth_hdr *eth = pkt_start;
struct bpf_tunnel_key tkey = {};
struct vip_stats *data_stats;
struct real_definition *dst;
struct vip_meta *vip_info;
struct ctl_value *cval;
__u32 v4_intf_pos = 1;
__u32 v6_intf_pos = 2;
struct ipv6hdr *ip6h;
struct vip vip = {};
struct iphdr *iph;
int tun_flag = 0;
__u16 pkt_bytes;
__u64 iph_len;
__u32 ifindex;
__u8 protocol;
__u32 vip_num;
int action;
tkey.tunnel_ttl = 64;
if (is_ipv6) {
ip6h = data + off;
if (ip6h + 1 > data_end)
return TC_ACT_SHOT;
iph_len = sizeof(struct ipv6hdr);
protocol = ip6h->nexthdr;
pckt.proto = protocol;
pkt_bytes = bpf_ntohs(ip6h->payload_len);
off += iph_len;
if (protocol == IPPROTO_FRAGMENT) {
return TC_ACT_SHOT;
} else if (protocol == IPPROTO_ICMPV6) {
action = parse_icmpv6(data, data_end, off, &pckt);
if (action >= 0)
return action;
off += IPV6_PLUS_ICMP_HDR;
} else {
memcpy(pckt.srcv6, ip6h->saddr.s6_addr32, 16);
memcpy(pckt.dstv6, ip6h->daddr.s6_addr32, 16);
}
} else {
iph = data + off;
if (iph + 1 > data_end)
return TC_ACT_SHOT;
if (iph->ihl != 5)
return TC_ACT_SHOT;
protocol = iph->protocol;
pckt.proto = protocol;
pkt_bytes = bpf_ntohs(iph->tot_len);
off += IPV4_HDR_LEN_NO_OPT;
if (iph->frag_off & PCKT_FRAGMENTED)
return TC_ACT_SHOT;
if (protocol == IPPROTO_ICMP) {
action = parse_icmp(data, data_end, off, &pckt);
if (action >= 0)
return action;
off += IPV4_PLUS_ICMP_HDR;
} else {
pckt.src = iph->saddr;
pckt.dst = iph->daddr;
}
}
protocol = pckt.proto;
if (protocol == IPPROTO_TCP) {
if (!parse_tcp(data, off, data_end, &pckt))
return TC_ACT_SHOT;
} else if (protocol == IPPROTO_UDP) {
if (!parse_udp(data, off, data_end, &pckt))
return TC_ACT_SHOT;
} else {
return TC_ACT_SHOT;
}
if (is_ipv6)
memcpy(vip.daddr.v6, pckt.dstv6, 16);
else
vip.daddr.v4 = pckt.dst;
vip.dport = pckt.port16[1];
vip.protocol = pckt.proto;
vip_info = bpf_map_lookup_elem(&vip_map, &vip);
if (!vip_info) {
vip.dport = 0;
vip_info = bpf_map_lookup_elem(&vip_map, &vip);
if (!vip_info)
return TC_ACT_SHOT;
pckt.port16[1] = 0;
}
if (vip_info->flags & F_HASH_NO_SRC_PORT)
pckt.port16[0] = 0;
if (!get_packet_dst(&dst, &pckt, vip_info, is_ipv6))
return TC_ACT_SHOT;
if (dst->flags & F_IPV6) {
cval = bpf_map_lookup_elem(&ctl_array, &v6_intf_pos);
if (!cval)
return TC_ACT_SHOT;
ifindex = cval->ifindex;
memcpy(tkey.remote_ipv6, dst->dstv6, 16);
tun_flag = BPF_F_TUNINFO_IPV6;
} else {
cval = bpf_map_lookup_elem(&ctl_array, &v4_intf_pos);
if (!cval)
return TC_ACT_SHOT;
ifindex = cval->ifindex;
tkey.remote_ipv4 = dst->dst;
}
vip_num = vip_info->vip_num;
data_stats = bpf_map_lookup_elem(&stats, &vip_num);
if (!data_stats)
return TC_ACT_SHOT;
data_stats->pkts++;
data_stats->bytes += pkt_bytes;
bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), tun_flag);
*(u32 *)eth->eth_dest = tkey.remote_ipv4;
return bpf_redirect(ifindex, 0);
}
SEC("l4lb-demo")
int balancer_ingress(struct __sk_buff *ctx)
{
void *data_end = (void *)(long)ctx->data_end;
void *data = (void *)(long)ctx->data;
struct eth_hdr *eth = data;
__u32 eth_proto;
__u32 nh_off;
nh_off = sizeof(struct eth_hdr);
if (data + nh_off > data_end)
return TC_ACT_SHOT;
eth_proto = eth->eth_proto;
if (eth_proto == bpf_htons(ETH_P_IP))
return process_packet(data, nh_off, data_end, false, ctx);
else if (eth_proto == bpf_htons(ETH_P_IPV6))
return process_packet(data, nh_off, data_end, true, ctx);
else
return TC_ACT_SHOT;
}
char _license[] SEC("license") = "GPL";
@@ -0,0 +1,473 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2017 Facebook
#include <stddef.h>
#include <stdbool.h>
#include <string.h>
#include <linux/pkt_cls.h>
#include <linux/bpf.h>
#include <linux/in.h>
#include <linux/if_ether.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/icmp.h>
#include <linux/icmpv6.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include "bpf_helpers.h"
#include "test_iptunnel_common.h"
#include "bpf_endian.h"
int _version SEC("version") = 1;
static __u32 rol32(__u32 word, unsigned int shift)
{
return (word << shift) | (word >> ((-shift) & 31));
}
/* copy paste of jhash from kernel sources to make sure llvm
* can compile it into valid sequence of bpf instructions
*/
#define __jhash_mix(a, b, c) \
{ \
a -= c; a ^= rol32(c, 4); c += b; \
b -= a; b ^= rol32(a, 6); a += c; \
c -= b; c ^= rol32(b, 8); b += a; \
a -= c; a ^= rol32(c, 16); c += b; \
b -= a; b ^= rol32(a, 19); a += c; \
c -= b; c ^= rol32(b, 4); b += a; \
}
#define __jhash_final(a, b, c) \
{ \
c ^= b; c -= rol32(b, 14); \
a ^= c; a -= rol32(c, 11); \
b ^= a; b -= rol32(a, 25); \
c ^= b; c -= rol32(b, 16); \
a ^= c; a -= rol32(c, 4); \
b ^= a; b -= rol32(a, 14); \
c ^= b; c -= rol32(b, 24); \
}
#define JHASH_INITVAL 0xdeadbeef
typedef unsigned int u32;
static u32 jhash(const void *key, u32 length, u32 initval)
{
u32 a, b, c;
const unsigned char *k = key;
a = b = c = JHASH_INITVAL + length + initval;
while (length > 12) {
a += *(u32 *)(k);
b += *(u32 *)(k + 4);
c += *(u32 *)(k + 8);
__jhash_mix(a, b, c);
length -= 12;
k += 12;
}
switch (length) {
case 12: c += (u32)k[11]<<24;
case 11: c += (u32)k[10]<<16;
case 10: c += (u32)k[9]<<8;
case 9: c += k[8];
case 8: b += (u32)k[7]<<24;
case 7: b += (u32)k[6]<<16;
case 6: b += (u32)k[5]<<8;
case 5: b += k[4];
case 4: a += (u32)k[3]<<24;
case 3: a += (u32)k[2]<<16;
case 2: a += (u32)k[1]<<8;
case 1: a += k[0];
__jhash_final(a, b, c);
case 0: /* Nothing left to add */
break;
}
return c;
}
static u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval)
{
a += initval;
b += initval;
c += initval;
__jhash_final(a, b, c);
return c;
}
static u32 jhash_2words(u32 a, u32 b, u32 initval)
{
return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2));
}
#define PCKT_FRAGMENTED 65343
#define IPV4_HDR_LEN_NO_OPT 20
#define IPV4_PLUS_ICMP_HDR 28
#define IPV6_PLUS_ICMP_HDR 48
#define RING_SIZE 2
#define MAX_VIPS 12
#define MAX_REALS 5
#define CTL_MAP_SIZE 16
#define CH_RINGS_SIZE (MAX_VIPS * RING_SIZE)
#define F_IPV6 (1 << 0)
#define F_HASH_NO_SRC_PORT (1 << 0)
#define F_ICMP (1 << 0)
#define F_SYN_SET (1 << 1)
struct packet_description {
union {
__be32 src;
__be32 srcv6[4];
};
union {
__be32 dst;
__be32 dstv6[4];
};
union {
__u32 ports;
__u16 port16[2];
};
__u8 proto;
__u8 flags;
};
struct ctl_value {
union {
__u64 value;
__u32 ifindex;
__u8 mac[6];
};
};
struct vip_meta {
__u32 flags;
__u32 vip_num;
};
struct real_definition {
union {
__be32 dst;
__be32 dstv6[4];
};
__u8 flags;
};
struct vip_stats {
__u64 bytes;
__u64 pkts;
};
struct eth_hdr {
unsigned char eth_dest[ETH_ALEN];
unsigned char eth_source[ETH_ALEN];
unsigned short eth_proto;
};
struct bpf_map_def SEC("maps") vip_map = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(struct vip),
.value_size = sizeof(struct vip_meta),
.max_entries = MAX_VIPS,
};
struct bpf_map_def SEC("maps") ch_rings = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(__u32),
.max_entries = CH_RINGS_SIZE,
};
struct bpf_map_def SEC("maps") reals = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(struct real_definition),
.max_entries = MAX_REALS,
};
struct bpf_map_def SEC("maps") stats = {
.type = BPF_MAP_TYPE_PERCPU_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(struct vip_stats),
.max_entries = MAX_VIPS,
};
struct bpf_map_def SEC("maps") ctl_array = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(struct ctl_value),
.max_entries = CTL_MAP_SIZE,
};
static __u32 get_packet_hash(struct packet_description *pckt,
bool ipv6)
{
if (ipv6)
return jhash_2words(jhash(pckt->srcv6, 16, MAX_VIPS),
pckt->ports, CH_RINGS_SIZE);
else
return jhash_2words(pckt->src, pckt->ports, CH_RINGS_SIZE);
}
static bool get_packet_dst(struct real_definition **real,
struct packet_description *pckt,
struct vip_meta *vip_info,
bool is_ipv6)
{
__u32 hash = get_packet_hash(pckt, is_ipv6);
__u32 key = RING_SIZE * vip_info->vip_num + hash % RING_SIZE;
__u32 *real_pos;
if (hash != 0x358459b7 /* jhash of ipv4 packet */ &&
hash != 0x2f4bc6bb /* jhash of ipv6 packet */)
return 0;
real_pos = bpf_map_lookup_elem(&ch_rings, &key);
if (!real_pos)
return false;
key = *real_pos;
*real = bpf_map_lookup_elem(&reals, &key);
if (!(*real))
return false;
return true;
}
static int parse_icmpv6(void *data, void *data_end, __u64 off,
struct packet_description *pckt)
{
struct icmp6hdr *icmp_hdr;
struct ipv6hdr *ip6h;
icmp_hdr = data + off;
if (icmp_hdr + 1 > data_end)
return TC_ACT_SHOT;
if (icmp_hdr->icmp6_type != ICMPV6_PKT_TOOBIG)
return TC_ACT_OK;
off += sizeof(struct icmp6hdr);
ip6h = data + off;
if (ip6h + 1 > data_end)
return TC_ACT_SHOT;
pckt->proto = ip6h->nexthdr;
pckt->flags |= F_ICMP;
memcpy(pckt->srcv6, ip6h->daddr.s6_addr32, 16);
memcpy(pckt->dstv6, ip6h->saddr.s6_addr32, 16);
return TC_ACT_UNSPEC;
}
static int parse_icmp(void *data, void *data_end, __u64 off,
struct packet_description *pckt)
{
struct icmphdr *icmp_hdr;
struct iphdr *iph;
icmp_hdr = data + off;
if (icmp_hdr + 1 > data_end)
return TC_ACT_SHOT;
if (icmp_hdr->type != ICMP_DEST_UNREACH ||
icmp_hdr->code != ICMP_FRAG_NEEDED)
return TC_ACT_OK;
off += sizeof(struct icmphdr);
iph = data + off;
if (iph + 1 > data_end)
return TC_ACT_SHOT;
if (iph->ihl != 5)
return TC_ACT_SHOT;
pckt->proto = iph->protocol;
pckt->flags |= F_ICMP;
pckt->src = iph->daddr;
pckt->dst = iph->saddr;
return TC_ACT_UNSPEC;
}
static bool parse_udp(void *data, __u64 off, void *data_end,
struct packet_description *pckt)
{
struct udphdr *udp;
udp = data + off;
if (udp + 1 > data_end)
return false;
if (!(pckt->flags & F_ICMP)) {
pckt->port16[0] = udp->source;
pckt->port16[1] = udp->dest;
} else {
pckt->port16[0] = udp->dest;
pckt->port16[1] = udp->source;
}
return true;
}
static bool parse_tcp(void *data, __u64 off, void *data_end,
struct packet_description *pckt)
{
struct tcphdr *tcp;
tcp = data + off;
if (tcp + 1 > data_end)
return false;
if (tcp->syn)
pckt->flags |= F_SYN_SET;
if (!(pckt->flags & F_ICMP)) {
pckt->port16[0] = tcp->source;
pckt->port16[1] = tcp->dest;
} else {
pckt->port16[0] = tcp->dest;
pckt->port16[1] = tcp->source;
}
return true;
}
static int process_packet(void *data, __u64 off, void *data_end,
bool is_ipv6, struct __sk_buff *skb)
{
void *pkt_start = (void *)(long)skb->data;
struct packet_description pckt = {};
struct eth_hdr *eth = pkt_start;
struct bpf_tunnel_key tkey = {};
struct vip_stats *data_stats;
struct real_definition *dst;
struct vip_meta *vip_info;
struct ctl_value *cval;
__u32 v4_intf_pos = 1;
__u32 v6_intf_pos = 2;
struct ipv6hdr *ip6h;
struct vip vip = {};
struct iphdr *iph;
int tun_flag = 0;
__u16 pkt_bytes;
__u64 iph_len;
__u32 ifindex;
__u8 protocol;
__u32 vip_num;
int action;
tkey.tunnel_ttl = 64;
if (is_ipv6) {
ip6h = data + off;
if (ip6h + 1 > data_end)
return TC_ACT_SHOT;
iph_len = sizeof(struct ipv6hdr);
protocol = ip6h->nexthdr;
pckt.proto = protocol;
pkt_bytes = bpf_ntohs(ip6h->payload_len);
off += iph_len;
if (protocol == IPPROTO_FRAGMENT) {
return TC_ACT_SHOT;
} else if (protocol == IPPROTO_ICMPV6) {
action = parse_icmpv6(data, data_end, off, &pckt);
if (action >= 0)
return action;
off += IPV6_PLUS_ICMP_HDR;
} else {
memcpy(pckt.srcv6, ip6h->saddr.s6_addr32, 16);
memcpy(pckt.dstv6, ip6h->daddr.s6_addr32, 16);
}
} else {
iph = data + off;
if (iph + 1 > data_end)
return TC_ACT_SHOT;
if (iph->ihl != 5)
return TC_ACT_SHOT;
protocol = iph->protocol;
pckt.proto = protocol;
pkt_bytes = bpf_ntohs(iph->tot_len);
off += IPV4_HDR_LEN_NO_OPT;
if (iph->frag_off & PCKT_FRAGMENTED)
return TC_ACT_SHOT;
if (protocol == IPPROTO_ICMP) {
action = parse_icmp(data, data_end, off, &pckt);
if (action >= 0)
return action;
off += IPV4_PLUS_ICMP_HDR;
} else {
pckt.src = iph->saddr;
pckt.dst = iph->daddr;
}
}
protocol = pckt.proto;
if (protocol == IPPROTO_TCP) {
if (!parse_tcp(data, off, data_end, &pckt))
return TC_ACT_SHOT;
} else if (protocol == IPPROTO_UDP) {
if (!parse_udp(data, off, data_end, &pckt))
return TC_ACT_SHOT;
} else {
return TC_ACT_SHOT;
}
if (is_ipv6)
memcpy(vip.daddr.v6, pckt.dstv6, 16);
else
vip.daddr.v4 = pckt.dst;
vip.dport = pckt.port16[1];
vip.protocol = pckt.proto;
vip_info = bpf_map_lookup_elem(&vip_map, &vip);
if (!vip_info) {
vip.dport = 0;
vip_info = bpf_map_lookup_elem(&vip_map, &vip);
if (!vip_info)
return TC_ACT_SHOT;
pckt.port16[1] = 0;
}
if (vip_info->flags & F_HASH_NO_SRC_PORT)
pckt.port16[0] = 0;
if (!get_packet_dst(&dst, &pckt, vip_info, is_ipv6))
return TC_ACT_SHOT;
if (dst->flags & F_IPV6) {
cval = bpf_map_lookup_elem(&ctl_array, &v6_intf_pos);
if (!cval)
return TC_ACT_SHOT;
ifindex = cval->ifindex;
memcpy(tkey.remote_ipv6, dst->dstv6, 16);
tun_flag = BPF_F_TUNINFO_IPV6;
} else {
cval = bpf_map_lookup_elem(&ctl_array, &v4_intf_pos);
if (!cval)
return TC_ACT_SHOT;
ifindex = cval->ifindex;
tkey.remote_ipv4 = dst->dst;
}
vip_num = vip_info->vip_num;
data_stats = bpf_map_lookup_elem(&stats, &vip_num);
if (!data_stats)
return TC_ACT_SHOT;
data_stats->pkts++;
data_stats->bytes += pkt_bytes;
bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), tun_flag);
*(u32 *)eth->eth_dest = tkey.remote_ipv4;
return bpf_redirect(ifindex, 0);
}
SEC("l4lb-demo")
int balancer_ingress(struct __sk_buff *ctx)
{
void *data_end = (void *)(long)ctx->data_end;
void *data = (void *)(long)ctx->data;
struct eth_hdr *eth = data;
__u32 eth_proto;
__u32 nh_off;
nh_off = sizeof(struct eth_hdr);
if (data + nh_off > data_end)
return TC_ACT_SHOT;
eth_proto = eth->eth_proto;
if (eth_proto == bpf_htons(ETH_P_IP))
return process_packet(data, nh_off, data_end, false, ctx);
else if (eth_proto == bpf_htons(ETH_P_IPV6))
return process_packet(data, nh_off, data_end, true, ctx);
else
return TC_ACT_SHOT;
}
char _license[] SEC("license") = "GPL";
+43
View File
@@ -0,0 +1,43 @@
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
export TESTNAME=test_libbpf
# Determine selftest success via shell exit code
exit_handler()
{
if [ $? -eq 0 ]; then
echo "selftests: $TESTNAME [PASS]";
else
echo "$TESTNAME: failed at file $LAST_LOADED" 1>&2
echo "selftests: $TESTNAME [FAILED]";
fi
}
libbpf_open_file()
{
LAST_LOADED=$1
if [ -n "$VERBOSE" ]; then
./test_libbpf_open $1
else
./test_libbpf_open --quiet $1
fi
}
# Exit script immediately (well catched by trap handler) if any
# program/thing exits with a non-zero status.
set -e
# (Use 'trap -l' to list meaning of numbers)
trap exit_handler 0 2 3 6 9
libbpf_open_file test_l4lb.o
# Load a program with BPF-to-BPF calls
libbpf_open_file test_l4lb_noinline.o
# Load a program compiled without the "-target bpf" flag
libbpf_open_file test_xdp.o
# Success
exit 0
@@ -0,0 +1,152 @@
/* SPDX-License-Identifier: GPL-2.0
* Copyright (c) 2018 Jesper Dangaard Brouer, Red Hat Inc.
*/
static const char *__doc__ =
"Libbpf test program for loading BPF ELF object files";
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <stdarg.h>
#include <bpf/libbpf.h>
#include <getopt.h>
#include "bpf_rlimit.h"
static const struct option long_options[] = {
{"help", no_argument, NULL, 'h' },
{"debug", no_argument, NULL, 'D' },
{"quiet", no_argument, NULL, 'q' },
{0, 0, NULL, 0 }
};
static void usage(char *argv[])
{
int i;
printf("\nDOCUMENTATION:\n%s\n\n", __doc__);
printf(" Usage: %s (options-see-below) BPF_FILE\n", argv[0]);
printf(" Listing options:\n");
for (i = 0; long_options[i].name != 0; i++) {
printf(" --%-12s", long_options[i].name);
printf(" short-option: -%c",
long_options[i].val);
printf("\n");
}
printf("\n");
}
#define DEFINE_PRINT_FN(name, enabled) \
static int libbpf_##name(const char *fmt, ...) \
{ \
va_list args; \
int ret; \
\
va_start(args, fmt); \
if (enabled) { \
fprintf(stderr, "[" #name "] "); \
ret = vfprintf(stderr, fmt, args); \
} \
va_end(args); \
return ret; \
}
DEFINE_PRINT_FN(warning, 1)
DEFINE_PRINT_FN(info, 1)
DEFINE_PRINT_FN(debug, 1)
#define EXIT_FAIL_LIBBPF EXIT_FAILURE
#define EXIT_FAIL_OPTION 2
int test_walk_progs(struct bpf_object *obj, bool verbose)
{
struct bpf_program *prog;
int cnt = 0;
bpf_object__for_each_program(prog, obj) {
cnt++;
if (verbose)
printf("Prog (count:%d) section_name: %s\n", cnt,
bpf_program__title(prog, false));
}
return 0;
}
int test_walk_maps(struct bpf_object *obj, bool verbose)
{
struct bpf_map *map;
int cnt = 0;
bpf_map__for_each(map, obj) {
cnt++;
if (verbose)
printf("Map (count:%d) name: %s\n", cnt,
bpf_map__name(map));
}
return 0;
}
int test_open_file(char *filename, bool verbose)
{
struct bpf_object *bpfobj = NULL;
long err;
if (verbose)
printf("Open BPF ELF-file with libbpf: %s\n", filename);
/* Load BPF ELF object file and check for errors */
bpfobj = bpf_object__open(filename);
err = libbpf_get_error(bpfobj);
if (err) {
char err_buf[128];
libbpf_strerror(err, err_buf, sizeof(err_buf));
if (verbose)
printf("Unable to load eBPF objects in file '%s': %s\n",
filename, err_buf);
return EXIT_FAIL_LIBBPF;
}
test_walk_progs(bpfobj, verbose);
test_walk_maps(bpfobj, verbose);
if (verbose)
printf("Close BPF ELF-file with libbpf: %s\n",
bpf_object__name(bpfobj));
bpf_object__close(bpfobj);
return 0;
}
int main(int argc, char **argv)
{
char filename[1024] = { 0 };
bool verbose = 1;
int longindex = 0;
int opt;
libbpf_set_print(libbpf_warning, libbpf_info, NULL);
/* Parse commands line args */
while ((opt = getopt_long(argc, argv, "hDq",
long_options, &longindex)) != -1) {
switch (opt) {
case 'D':
libbpf_set_print(libbpf_warning, libbpf_info,
libbpf_debug);
break;
case 'q': /* Use in scripting mode */
verbose = 0;
break;
case 'h':
default:
usage(argv);
return EXIT_FAIL_OPTION;
}
}
if (optind >= argc) {
usage(argv);
printf("ERROR: Expected BPF_FILE argument after options\n");
return EXIT_FAIL_OPTION;
}
snprintf(filename, sizeof(filename), "%s", argv[optind]);
return test_open_file(filename, verbose);
}
+37
View File
@@ -0,0 +1,37 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
# Kselftest framework requirement - SKIP code is 4.
ksft_skip=4
msg="skip all tests:"
if [ $UID != 0 ]; then
echo $msg please run this as root >&2
exit $ksft_skip
fi
GREEN='\033[0;92m'
RED='\033[0;31m'
NC='\033[0m' # No Color
modprobe rc-loopback
for i in /sys/class/rc/rc*
do
if grep -q DRV_NAME=rc-loopback $i/uevent
then
LIRCDEV=$(grep DEVNAME= $i/lirc*/uevent | sed sQDEVNAME=Q/dev/Q)
fi
done
if [ -n $LIRCDEV ];
then
TYPE=lirc_mode2
./test_lirc_mode2_user $LIRCDEV
ret=$?
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: $TYPE"${NC}
else
echo -e ${GREEN}"PASS: $TYPE"${NC}
fi
fi
@@ -0,0 +1,23 @@
// SPDX-License-Identifier: GPL-2.0
// test ir decoder
//
// Copyright (C) 2018 Sean Young <sean@mess.org>
#include <linux/bpf.h>
#include <linux/lirc.h>
#include "bpf_helpers.h"
SEC("lirc_mode2")
int bpf_decoder(unsigned int *sample)
{
if (LIRC_IS_PULSE(*sample)) {
unsigned int duration = LIRC_VALUE(*sample);
if (duration & 0x10000)
bpf_rc_keydown(sample, 0x40, duration & 0xffff, 0);
}
return 0;
}
char _license[] SEC("license") = "GPL";
@@ -0,0 +1,149 @@
// SPDX-License-Identifier: GPL-2.0
// test ir decoder
//
// Copyright (C) 2018 Sean Young <sean@mess.org>
// A lirc chardev is a device representing a consumer IR (cir) device which
// can receive infrared signals from remote control and/or transmit IR.
//
// IR is sent as a series of pulses and space somewhat like morse code. The
// BPF program can decode this into scancodes so that rc-core can translate
// this into input key codes using the rc keymap.
//
// This test works by sending IR over rc-loopback, so the IR is processed by
// BPF and then decoded into scancodes. The lirc chardev must be the one
// associated with rc-loopback, see the output of ir-keytable(1).
//
// The following CONFIG options must be enabled for the test to succeed:
// CONFIG_RC_CORE=y
// CONFIG_BPF_RAWIR_EVENT=y
// CONFIG_RC_LOOPBACK=y
// Steps:
// 1. Open the /dev/lircN device for rc-loopback (given on command line)
// 2. Attach bpf_lirc_mode2 program which decodes some IR.
// 3. Send some IR to the same IR device; since it is loopback, this will
// end up in the bpf program
// 4. bpf program should decode IR and report keycode
// 5. We can read keycode from same /dev/lirc device
#include <linux/bpf.h>
#include <linux/lirc.h>
#include <errno.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <poll.h>
#include <sys/types.h>
#include <sys/ioctl.h>
#include <sys/stat.h>
#include <fcntl.h>
#include "bpf_util.h"
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
int main(int argc, char **argv)
{
struct bpf_object *obj;
int ret, lircfd, progfd, mode;
int testir = 0x1dead;
u32 prog_ids[10], prog_flags[10], prog_cnt;
if (argc != 2) {
printf("Usage: %s /dev/lircN\n", argv[0]);
return 2;
}
ret = bpf_prog_load("test_lirc_mode2_kern.o",
BPF_PROG_TYPE_LIRC_MODE2, &obj, &progfd);
if (ret) {
printf("Failed to load bpf program\n");
return 1;
}
lircfd = open(argv[1], O_RDWR | O_NONBLOCK);
if (lircfd == -1) {
printf("failed to open lirc device %s: %m\n", argv[1]);
return 1;
}
/* Let's try detach it before it was ever attached */
ret = bpf_prog_detach2(progfd, lircfd, BPF_LIRC_MODE2);
if (ret != -1 || errno != ENOENT) {
printf("bpf_prog_detach2 not attached should fail: %m\n");
return 1;
}
mode = LIRC_MODE_SCANCODE;
if (ioctl(lircfd, LIRC_SET_REC_MODE, &mode)) {
printf("failed to set rec mode: %m\n");
return 1;
}
prog_cnt = 10;
ret = bpf_prog_query(lircfd, BPF_LIRC_MODE2, 0, prog_flags, prog_ids,
&prog_cnt);
if (ret) {
printf("Failed to query bpf programs on lirc device: %m\n");
return 1;
}
if (prog_cnt != 0) {
printf("Expected nothing to be attached\n");
return 1;
}
ret = bpf_prog_attach(progfd, lircfd, BPF_LIRC_MODE2, 0);
if (ret) {
printf("Failed to attach bpf to lirc device: %m\n");
return 1;
}
/* Write raw IR */
ret = write(lircfd, &testir, sizeof(testir));
if (ret != sizeof(testir)) {
printf("Failed to send test IR message: %m\n");
return 1;
}
struct pollfd pfd = { .fd = lircfd, .events = POLLIN };
struct lirc_scancode lsc;
poll(&pfd, 1, 100);
/* Read decoded IR */
ret = read(lircfd, &lsc, sizeof(lsc));
if (ret != sizeof(lsc)) {
printf("Failed to read decoded IR: %m\n");
return 1;
}
if (lsc.scancode != 0xdead || lsc.rc_proto != 64) {
printf("Incorrect scancode decoded\n");
return 1;
}
prog_cnt = 10;
ret = bpf_prog_query(lircfd, BPF_LIRC_MODE2, 0, prog_flags, prog_ids,
&prog_cnt);
if (ret) {
printf("Failed to query bpf programs on lirc device: %m\n");
return 1;
}
if (prog_cnt != 1) {
printf("Expected one program to be attached\n");
return 1;
}
/* Let's try detaching it now it is actually attached */
ret = bpf_prog_detach2(progfd, lircfd, BPF_LIRC_MODE2);
if (ret) {
printf("bpf_prog_detach2: returned %m\n");
return 1;
}
return 0;
}
+804
View File
@@ -0,0 +1,804 @@
// SPDX-License-Identifier: GPL-2.0
/*
* Randomized tests for eBPF longest-prefix-match maps
*
* This program runs randomized tests against the lpm-bpf-map. It implements a
* "Trivial Longest Prefix Match" (tlpm) based on simple, linear, singly linked
* lists. The implementation should be pretty straightforward.
*
* Based on tlpm, this inserts randomized data into bpf-lpm-maps and verifies
* the trie-based bpf-map implementation behaves the same way as tlpm.
*/
#include <assert.h>
#include <errno.h>
#include <inttypes.h>
#include <linux/bpf.h>
#include <pthread.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <time.h>
#include <unistd.h>
#include <arpa/inet.h>
#include <sys/time.h>
#include <bpf/bpf.h>
#include "bpf_util.h"
#include "bpf_rlimit.h"
struct tlpm_node {
struct tlpm_node *next;
size_t n_bits;
uint8_t key[];
};
static struct tlpm_node *tlpm_match(struct tlpm_node *list,
const uint8_t *key,
size_t n_bits);
static struct tlpm_node *tlpm_add(struct tlpm_node *list,
const uint8_t *key,
size_t n_bits)
{
struct tlpm_node *node;
size_t n;
n = (n_bits + 7) / 8;
/* 'overwrite' an equivalent entry if one already exists */
node = tlpm_match(list, key, n_bits);
if (node && node->n_bits == n_bits) {
memcpy(node->key, key, n);
return list;
}
/* add new entry with @key/@n_bits to @list and return new head */
node = malloc(sizeof(*node) + n);
assert(node);
node->next = list;
node->n_bits = n_bits;
memcpy(node->key, key, n);
return node;
}
static void tlpm_clear(struct tlpm_node *list)
{
struct tlpm_node *node;
/* free all entries in @list */
while ((node = list)) {
list = list->next;
free(node);
}
}
static struct tlpm_node *tlpm_match(struct tlpm_node *list,
const uint8_t *key,
size_t n_bits)
{
struct tlpm_node *best = NULL;
size_t i;
/* Perform longest prefix-match on @key/@n_bits. That is, iterate all
* entries and match each prefix against @key. Remember the "best"
* entry we find (i.e., the longest prefix that matches) and return it
* to the caller when done.
*/
for ( ; list; list = list->next) {
for (i = 0; i < n_bits && i < list->n_bits; ++i) {
if ((key[i / 8] & (1 << (7 - i % 8))) !=
(list->key[i / 8] & (1 << (7 - i % 8))))
break;
}
if (i >= list->n_bits) {
if (!best || i > best->n_bits)
best = list;
}
}
return best;
}
static struct tlpm_node *tlpm_delete(struct tlpm_node *list,
const uint8_t *key,
size_t n_bits)
{
struct tlpm_node *best = tlpm_match(list, key, n_bits);
struct tlpm_node *node;
if (!best || best->n_bits != n_bits)
return list;
if (best == list) {
node = best->next;
free(best);
return node;
}
for (node = list; node; node = node->next) {
if (node->next == best) {
node->next = best->next;
free(best);
return list;
}
}
/* should never get here */
assert(0);
return list;
}
static void test_lpm_basic(void)
{
struct tlpm_node *list = NULL, *t1, *t2;
/* very basic, static tests to verify tlpm works as expected */
assert(!tlpm_match(list, (uint8_t[]){ 0xff }, 8));
t1 = list = tlpm_add(list, (uint8_t[]){ 0xff }, 8);
assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff }, 8));
assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 16));
assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0x00 }, 16));
assert(!tlpm_match(list, (uint8_t[]){ 0x7f }, 8));
assert(!tlpm_match(list, (uint8_t[]){ 0xfe }, 8));
assert(!tlpm_match(list, (uint8_t[]){ 0xff }, 7));
t2 = list = tlpm_add(list, (uint8_t[]){ 0xff, 0xff }, 16);
assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff }, 8));
assert(t2 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 16));
assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 15));
assert(!tlpm_match(list, (uint8_t[]){ 0x7f, 0xff }, 16));
list = tlpm_delete(list, (uint8_t[]){ 0xff, 0xff }, 16);
assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff }, 8));
assert(t1 == tlpm_match(list, (uint8_t[]){ 0xff, 0xff }, 16));
list = tlpm_delete(list, (uint8_t[]){ 0xff }, 8);
assert(!tlpm_match(list, (uint8_t[]){ 0xff }, 8));
tlpm_clear(list);
}
static void test_lpm_order(void)
{
struct tlpm_node *t1, *t2, *l1 = NULL, *l2 = NULL;
size_t i, j;
/* Verify the tlpm implementation works correctly regardless of the
* order of entries. Insert a random set of entries into @l1, and copy
* the same data in reverse order into @l2. Then verify a lookup of
* random keys will yield the same result in both sets.
*/
for (i = 0; i < (1 << 12); ++i)
l1 = tlpm_add(l1, (uint8_t[]){
rand() % 0xff,
rand() % 0xff,
}, rand() % 16 + 1);
for (t1 = l1; t1; t1 = t1->next)
l2 = tlpm_add(l2, t1->key, t1->n_bits);
for (i = 0; i < (1 << 8); ++i) {
uint8_t key[] = { rand() % 0xff, rand() % 0xff };
t1 = tlpm_match(l1, key, 16);
t2 = tlpm_match(l2, key, 16);
assert(!t1 == !t2);
if (t1) {
assert(t1->n_bits == t2->n_bits);
for (j = 0; j < t1->n_bits; ++j)
assert((t1->key[j / 8] & (1 << (7 - j % 8))) ==
(t2->key[j / 8] & (1 << (7 - j % 8))));
}
}
tlpm_clear(l1);
tlpm_clear(l2);
}
static void test_lpm_map(int keysize)
{
size_t i, j, n_matches, n_matches_after_delete, n_nodes, n_lookups;
struct tlpm_node *t, *list = NULL;
struct bpf_lpm_trie_key *key;
uint8_t *data, *value;
int r, map;
/* Compare behavior of tlpm vs. bpf-lpm. Create a randomized set of
* prefixes and insert it into both tlpm and bpf-lpm. Then run some
* randomized lookups and verify both maps return the same result.
*/
n_matches = 0;
n_matches_after_delete = 0;
n_nodes = 1 << 8;
n_lookups = 1 << 16;
data = alloca(keysize);
memset(data, 0, keysize);
value = alloca(keysize + 1);
memset(value, 0, keysize + 1);
key = alloca(sizeof(*key) + keysize);
memset(key, 0, sizeof(*key) + keysize);
map = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE,
sizeof(*key) + keysize,
keysize + 1,
4096,
BPF_F_NO_PREALLOC);
assert(map >= 0);
for (i = 0; i < n_nodes; ++i) {
for (j = 0; j < keysize; ++j)
value[j] = rand() & 0xff;
value[keysize] = rand() % (8 * keysize + 1);
list = tlpm_add(list, value, value[keysize]);
key->prefixlen = value[keysize];
memcpy(key->data, value, keysize);
r = bpf_map_update_elem(map, key, value, 0);
assert(!r);
}
for (i = 0; i < n_lookups; ++i) {
for (j = 0; j < keysize; ++j)
data[j] = rand() & 0xff;
t = tlpm_match(list, data, 8 * keysize);
key->prefixlen = 8 * keysize;
memcpy(key->data, data, keysize);
r = bpf_map_lookup_elem(map, key, value);
assert(!r || errno == ENOENT);
assert(!t == !!r);
if (t) {
++n_matches;
assert(t->n_bits == value[keysize]);
for (j = 0; j < t->n_bits; ++j)
assert((t->key[j / 8] & (1 << (7 - j % 8))) ==
(value[j / 8] & (1 << (7 - j % 8))));
}
}
/* Remove the first half of the elements in the tlpm and the
* corresponding nodes from the bpf-lpm. Then run the same
* large number of random lookups in both and make sure they match.
* Note: we need to count the number of nodes actually inserted
* since there may have been duplicates.
*/
for (i = 0, t = list; t; i++, t = t->next)
;
for (j = 0; j < i / 2; ++j) {
key->prefixlen = list->n_bits;
memcpy(key->data, list->key, keysize);
r = bpf_map_delete_elem(map, key);
assert(!r);
list = tlpm_delete(list, list->key, list->n_bits);
assert(list);
}
for (i = 0; i < n_lookups; ++i) {
for (j = 0; j < keysize; ++j)
data[j] = rand() & 0xff;
t = tlpm_match(list, data, 8 * keysize);
key->prefixlen = 8 * keysize;
memcpy(key->data, data, keysize);
r = bpf_map_lookup_elem(map, key, value);
assert(!r || errno == ENOENT);
assert(!t == !!r);
if (t) {
++n_matches_after_delete;
assert(t->n_bits == value[keysize]);
for (j = 0; j < t->n_bits; ++j)
assert((t->key[j / 8] & (1 << (7 - j % 8))) ==
(value[j / 8] & (1 << (7 - j % 8))));
}
}
close(map);
tlpm_clear(list);
/* With 255 random nodes in the map, we are pretty likely to match
* something on every lookup. For statistics, use this:
*
* printf(" nodes: %zu\n"
* " lookups: %zu\n"
* " matches: %zu\n"
* "matches(delete): %zu\n",
* n_nodes, n_lookups, n_matches, n_matches_after_delete);
*/
}
/* Test the implementation with some 'real world' examples */
static void test_lpm_ipaddr(void)
{
struct bpf_lpm_trie_key *key_ipv4;
struct bpf_lpm_trie_key *key_ipv6;
size_t key_size_ipv4;
size_t key_size_ipv6;
int map_fd_ipv4;
int map_fd_ipv6;
__u64 value;
key_size_ipv4 = sizeof(*key_ipv4) + sizeof(__u32);
key_size_ipv6 = sizeof(*key_ipv6) + sizeof(__u32) * 4;
key_ipv4 = alloca(key_size_ipv4);
key_ipv6 = alloca(key_size_ipv6);
map_fd_ipv4 = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE,
key_size_ipv4, sizeof(value),
100, BPF_F_NO_PREALLOC);
assert(map_fd_ipv4 >= 0);
map_fd_ipv6 = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE,
key_size_ipv6, sizeof(value),
100, BPF_F_NO_PREALLOC);
assert(map_fd_ipv6 >= 0);
/* Fill data some IPv4 and IPv6 address ranges */
value = 1;
key_ipv4->prefixlen = 16;
inet_pton(AF_INET, "192.168.0.0", key_ipv4->data);
assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0);
value = 2;
key_ipv4->prefixlen = 24;
inet_pton(AF_INET, "192.168.0.0", key_ipv4->data);
assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0);
value = 3;
key_ipv4->prefixlen = 24;
inet_pton(AF_INET, "192.168.128.0", key_ipv4->data);
assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0);
value = 5;
key_ipv4->prefixlen = 24;
inet_pton(AF_INET, "192.168.1.0", key_ipv4->data);
assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0);
value = 4;
key_ipv4->prefixlen = 23;
inet_pton(AF_INET, "192.168.0.0", key_ipv4->data);
assert(bpf_map_update_elem(map_fd_ipv4, key_ipv4, &value, 0) == 0);
value = 0xdeadbeef;
key_ipv6->prefixlen = 64;
inet_pton(AF_INET6, "2a00:1450:4001:814::200e", key_ipv6->data);
assert(bpf_map_update_elem(map_fd_ipv6, key_ipv6, &value, 0) == 0);
/* Set tprefixlen to maximum for lookups */
key_ipv4->prefixlen = 32;
key_ipv6->prefixlen = 128;
/* Test some lookups that should come back with a value */
inet_pton(AF_INET, "192.168.128.23", key_ipv4->data);
assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == 0);
assert(value == 3);
inet_pton(AF_INET, "192.168.0.1", key_ipv4->data);
assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == 0);
assert(value == 2);
inet_pton(AF_INET6, "2a00:1450:4001:814::", key_ipv6->data);
assert(bpf_map_lookup_elem(map_fd_ipv6, key_ipv6, &value) == 0);
assert(value == 0xdeadbeef);
inet_pton(AF_INET6, "2a00:1450:4001:814::1", key_ipv6->data);
assert(bpf_map_lookup_elem(map_fd_ipv6, key_ipv6, &value) == 0);
assert(value == 0xdeadbeef);
/* Test some lookups that should not match any entry */
inet_pton(AF_INET, "10.0.0.1", key_ipv4->data);
assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == -1 &&
errno == ENOENT);
inet_pton(AF_INET, "11.11.11.11", key_ipv4->data);
assert(bpf_map_lookup_elem(map_fd_ipv4, key_ipv4, &value) == -1 &&
errno == ENOENT);
inet_pton(AF_INET6, "2a00:ffff::", key_ipv6->data);
assert(bpf_map_lookup_elem(map_fd_ipv6, key_ipv6, &value) == -1 &&
errno == ENOENT);
close(map_fd_ipv4);
close(map_fd_ipv6);
}
static void test_lpm_delete(void)
{
struct bpf_lpm_trie_key *key;
size_t key_size;
int map_fd;
__u64 value;
key_size = sizeof(*key) + sizeof(__u32);
key = alloca(key_size);
map_fd = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE,
key_size, sizeof(value),
100, BPF_F_NO_PREALLOC);
assert(map_fd >= 0);
/* Add nodes:
* 192.168.0.0/16 (1)
* 192.168.0.0/24 (2)
* 192.168.128.0/24 (3)
* 192.168.1.0/24 (4)
*
* (1)
* / \
* (IM) (3)
* / \
* (2) (4)
*/
value = 1;
key->prefixlen = 16;
inet_pton(AF_INET, "192.168.0.0", key->data);
assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0);
value = 2;
key->prefixlen = 24;
inet_pton(AF_INET, "192.168.0.0", key->data);
assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0);
value = 3;
key->prefixlen = 24;
inet_pton(AF_INET, "192.168.128.0", key->data);
assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0);
value = 4;
key->prefixlen = 24;
inet_pton(AF_INET, "192.168.1.0", key->data);
assert(bpf_map_update_elem(map_fd, key, &value, 0) == 0);
/* remove non-existent node */
key->prefixlen = 32;
inet_pton(AF_INET, "10.0.0.1", key->data);
assert(bpf_map_lookup_elem(map_fd, key, &value) == -1 &&
errno == ENOENT);
key->prefixlen = 30; // unused prefix so far
inet_pton(AF_INET, "192.255.0.0", key->data);
assert(bpf_map_delete_elem(map_fd, key) == -1 &&
errno == ENOENT);
key->prefixlen = 16; // same prefix as the root node
inet_pton(AF_INET, "192.255.0.0", key->data);
assert(bpf_map_delete_elem(map_fd, key) == -1 &&
errno == ENOENT);
/* assert initial lookup */
key->prefixlen = 32;
inet_pton(AF_INET, "192.168.0.1", key->data);
assert(bpf_map_lookup_elem(map_fd, key, &value) == 0);
assert(value == 2);
/* remove leaf node */
key->prefixlen = 24;
inet_pton(AF_INET, "192.168.0.0", key->data);
assert(bpf_map_delete_elem(map_fd, key) == 0);
key->prefixlen = 32;
inet_pton(AF_INET, "192.168.0.1", key->data);
assert(bpf_map_lookup_elem(map_fd, key, &value) == 0);
assert(value == 1);
/* remove leaf (and intermediary) node */
key->prefixlen = 24;
inet_pton(AF_INET, "192.168.1.0", key->data);
assert(bpf_map_delete_elem(map_fd, key) == 0);
key->prefixlen = 32;
inet_pton(AF_INET, "192.168.1.1", key->data);
assert(bpf_map_lookup_elem(map_fd, key, &value) == 0);
assert(value == 1);
/* remove root node */
key->prefixlen = 16;
inet_pton(AF_INET, "192.168.0.0", key->data);
assert(bpf_map_delete_elem(map_fd, key) == 0);
key->prefixlen = 32;
inet_pton(AF_INET, "192.168.128.1", key->data);
assert(bpf_map_lookup_elem(map_fd, key, &value) == 0);
assert(value == 3);
/* remove last node */
key->prefixlen = 24;
inet_pton(AF_INET, "192.168.128.0", key->data);
assert(bpf_map_delete_elem(map_fd, key) == 0);
key->prefixlen = 32;
inet_pton(AF_INET, "192.168.128.1", key->data);
assert(bpf_map_lookup_elem(map_fd, key, &value) == -1 &&
errno == ENOENT);
close(map_fd);
}
static void test_lpm_get_next_key(void)
{
struct bpf_lpm_trie_key *key_p, *next_key_p;
size_t key_size;
__u32 value = 0;
int map_fd;
key_size = sizeof(*key_p) + sizeof(__u32);
key_p = alloca(key_size);
next_key_p = alloca(key_size);
map_fd = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE, key_size, sizeof(value),
100, BPF_F_NO_PREALLOC);
assert(map_fd >= 0);
/* empty tree. get_next_key should return ENOENT */
assert(bpf_map_get_next_key(map_fd, NULL, key_p) == -1 &&
errno == ENOENT);
/* get and verify the first key, get the second one should fail. */
key_p->prefixlen = 16;
inet_pton(AF_INET, "192.168.0.0", key_p->data);
assert(bpf_map_update_elem(map_fd, key_p, &value, 0) == 0);
memset(key_p, 0, key_size);
assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0);
assert(key_p->prefixlen == 16 && key_p->data[0] == 192 &&
key_p->data[1] == 168);
assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == -1 &&
errno == ENOENT);
/* no exact matching key should get the first one in post order. */
key_p->prefixlen = 8;
assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0);
assert(key_p->prefixlen == 16 && key_p->data[0] == 192 &&
key_p->data[1] == 168);
/* add one more element (total two) */
key_p->prefixlen = 24;
inet_pton(AF_INET, "192.168.128.0", key_p->data);
assert(bpf_map_update_elem(map_fd, key_p, &value, 0) == 0);
memset(key_p, 0, key_size);
assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0);
assert(key_p->prefixlen == 24 && key_p->data[0] == 192 &&
key_p->data[1] == 168 && key_p->data[2] == 128);
memset(next_key_p, 0, key_size);
assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
assert(next_key_p->prefixlen == 16 && next_key_p->data[0] == 192 &&
next_key_p->data[1] == 168);
memcpy(key_p, next_key_p, key_size);
assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == -1 &&
errno == ENOENT);
/* Add one more element (total three) */
key_p->prefixlen = 24;
inet_pton(AF_INET, "192.168.0.0", key_p->data);
assert(bpf_map_update_elem(map_fd, key_p, &value, 0) == 0);
memset(key_p, 0, key_size);
assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0);
assert(key_p->prefixlen == 24 && key_p->data[0] == 192 &&
key_p->data[1] == 168 && key_p->data[2] == 0);
memset(next_key_p, 0, key_size);
assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 &&
next_key_p->data[1] == 168 && next_key_p->data[2] == 128);
memcpy(key_p, next_key_p, key_size);
assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
assert(next_key_p->prefixlen == 16 && next_key_p->data[0] == 192 &&
next_key_p->data[1] == 168);
memcpy(key_p, next_key_p, key_size);
assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == -1 &&
errno == ENOENT);
/* Add one more element (total four) */
key_p->prefixlen = 24;
inet_pton(AF_INET, "192.168.1.0", key_p->data);
assert(bpf_map_update_elem(map_fd, key_p, &value, 0) == 0);
memset(key_p, 0, key_size);
assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0);
assert(key_p->prefixlen == 24 && key_p->data[0] == 192 &&
key_p->data[1] == 168 && key_p->data[2] == 0);
memset(next_key_p, 0, key_size);
assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 &&
next_key_p->data[1] == 168 && next_key_p->data[2] == 1);
memcpy(key_p, next_key_p, key_size);
assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 &&
next_key_p->data[1] == 168 && next_key_p->data[2] == 128);
memcpy(key_p, next_key_p, key_size);
assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
assert(next_key_p->prefixlen == 16 && next_key_p->data[0] == 192 &&
next_key_p->data[1] == 168);
memcpy(key_p, next_key_p, key_size);
assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == -1 &&
errno == ENOENT);
/* Add one more element (total five) */
key_p->prefixlen = 28;
inet_pton(AF_INET, "192.168.1.128", key_p->data);
assert(bpf_map_update_elem(map_fd, key_p, &value, 0) == 0);
memset(key_p, 0, key_size);
assert(bpf_map_get_next_key(map_fd, NULL, key_p) == 0);
assert(key_p->prefixlen == 24 && key_p->data[0] == 192 &&
key_p->data[1] == 168 && key_p->data[2] == 0);
memset(next_key_p, 0, key_size);
assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
assert(next_key_p->prefixlen == 28 && next_key_p->data[0] == 192 &&
next_key_p->data[1] == 168 && next_key_p->data[2] == 1 &&
next_key_p->data[3] == 128);
memcpy(key_p, next_key_p, key_size);
assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 &&
next_key_p->data[1] == 168 && next_key_p->data[2] == 1);
memcpy(key_p, next_key_p, key_size);
assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 &&
next_key_p->data[1] == 168 && next_key_p->data[2] == 128);
memcpy(key_p, next_key_p, key_size);
assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
assert(next_key_p->prefixlen == 16 && next_key_p->data[0] == 192 &&
next_key_p->data[1] == 168);
memcpy(key_p, next_key_p, key_size);
assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == -1 &&
errno == ENOENT);
/* no exact matching key should return the first one in post order */
key_p->prefixlen = 22;
inet_pton(AF_INET, "192.168.1.0", key_p->data);
assert(bpf_map_get_next_key(map_fd, key_p, next_key_p) == 0);
assert(next_key_p->prefixlen == 24 && next_key_p->data[0] == 192 &&
next_key_p->data[1] == 168 && next_key_p->data[2] == 0);
close(map_fd);
}
#define MAX_TEST_KEYS 4
struct lpm_mt_test_info {
int cmd; /* 0: update, 1: delete, 2: lookup, 3: get_next_key */
int iter;
int map_fd;
struct {
__u32 prefixlen;
__u32 data;
} key[MAX_TEST_KEYS];
};
static void *lpm_test_command(void *arg)
{
int i, j, ret, iter, key_size;
struct lpm_mt_test_info *info = arg;
struct bpf_lpm_trie_key *key_p;
key_size = sizeof(struct bpf_lpm_trie_key) + sizeof(__u32);
key_p = alloca(key_size);
for (iter = 0; iter < info->iter; iter++)
for (i = 0; i < MAX_TEST_KEYS; i++) {
/* first half of iterations in forward order,
* and second half in backward order.
*/
j = (iter < (info->iter / 2)) ? i : MAX_TEST_KEYS - i - 1;
key_p->prefixlen = info->key[j].prefixlen;
memcpy(key_p->data, &info->key[j].data, sizeof(__u32));
if (info->cmd == 0) {
__u32 value = j;
/* update must succeed */
assert(bpf_map_update_elem(info->map_fd, key_p, &value, 0) == 0);
} else if (info->cmd == 1) {
ret = bpf_map_delete_elem(info->map_fd, key_p);
assert(ret == 0 || errno == ENOENT);
} else if (info->cmd == 2) {
__u32 value;
ret = bpf_map_lookup_elem(info->map_fd, key_p, &value);
assert(ret == 0 || errno == ENOENT);
} else {
struct bpf_lpm_trie_key *next_key_p = alloca(key_size);
ret = bpf_map_get_next_key(info->map_fd, key_p, next_key_p);
assert(ret == 0 || errno == ENOENT || errno == ENOMEM);
}
}
// Pass successful exit info back to the main thread
pthread_exit((void *)info);
}
static void setup_lpm_mt_test_info(struct lpm_mt_test_info *info, int map_fd)
{
info->iter = 2000;
info->map_fd = map_fd;
info->key[0].prefixlen = 16;
inet_pton(AF_INET, "192.168.0.0", &info->key[0].data);
info->key[1].prefixlen = 24;
inet_pton(AF_INET, "192.168.0.0", &info->key[1].data);
info->key[2].prefixlen = 24;
inet_pton(AF_INET, "192.168.128.0", &info->key[2].data);
info->key[3].prefixlen = 24;
inet_pton(AF_INET, "192.168.1.0", &info->key[3].data);
}
static void test_lpm_multi_thread(void)
{
struct lpm_mt_test_info info[4];
size_t key_size, value_size;
pthread_t thread_id[4];
int i, map_fd;
void *ret;
/* create a trie */
value_size = sizeof(__u32);
key_size = sizeof(struct bpf_lpm_trie_key) + value_size;
map_fd = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE, key_size, value_size,
100, BPF_F_NO_PREALLOC);
/* create 4 threads to test update, delete, lookup and get_next_key */
setup_lpm_mt_test_info(&info[0], map_fd);
for (i = 0; i < 4; i++) {
if (i != 0)
memcpy(&info[i], &info[0], sizeof(info[i]));
info[i].cmd = i;
assert(pthread_create(&thread_id[i], NULL, &lpm_test_command, &info[i]) == 0);
}
for (i = 0; i < 4; i++)
assert(pthread_join(thread_id[i], &ret) == 0 && ret == (void *)&info[i]);
close(map_fd);
}
int main(void)
{
int i;
/* we want predictable, pseudo random tests */
srand(0xf00ba1);
test_lpm_basic();
test_lpm_order();
/* Test with 8, 16, 24, 32, ... 128 bit prefix length */
for (i = 1; i <= 16; ++i)
test_lpm_map(i);
test_lpm_ipaddr();
test_lpm_delete();
test_lpm_get_next_key();
test_lpm_multi_thread();
printf("test_lpm: OK\n");
return 0;
}
+646
View File
@@ -0,0 +1,646 @@
/*
* Copyright (c) 2016 Facebook
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
#define _GNU_SOURCE
#include <stdio.h>
#include <unistd.h>
#include <errno.h>
#include <string.h>
#include <assert.h>
#include <sched.h>
#include <stdlib.h>
#include <time.h>
#include <sys/wait.h>
#include <bpf/bpf.h>
#include "bpf_util.h"
#include "bpf_rlimit.h"
#define LOCAL_FREE_TARGET (128)
#define PERCPU_FREE_TARGET (4)
static int nr_cpus;
static int create_map(int map_type, int map_flags, unsigned int size)
{
int map_fd;
map_fd = bpf_create_map(map_type, sizeof(unsigned long long),
sizeof(unsigned long long), size, map_flags);
if (map_fd == -1)
perror("bpf_create_map");
return map_fd;
}
static int map_subset(int map0, int map1)
{
unsigned long long next_key = 0;
unsigned long long value0[nr_cpus], value1[nr_cpus];
int ret;
while (!bpf_map_get_next_key(map1, &next_key, &next_key)) {
assert(!bpf_map_lookup_elem(map1, &next_key, value1));
ret = bpf_map_lookup_elem(map0, &next_key, value0);
if (ret) {
printf("key:%llu not found from map. %s(%d)\n",
next_key, strerror(errno), errno);
return 0;
}
if (value0[0] != value1[0]) {
printf("key:%llu value0:%llu != value1:%llu\n",
next_key, value0[0], value1[0]);
return 0;
}
}
return 1;
}
static int map_equal(int lru_map, int expected)
{
return map_subset(lru_map, expected) && map_subset(expected, lru_map);
}
static int sched_next_online(int pid, int *next_to_try)
{
cpu_set_t cpuset;
int next = *next_to_try;
int ret = -1;
while (next < nr_cpus) {
CPU_ZERO(&cpuset);
CPU_SET(next++, &cpuset);
if (!sched_setaffinity(pid, sizeof(cpuset), &cpuset)) {
ret = 0;
break;
}
}
*next_to_try = next;
return ret;
}
/* Size of the LRU amp is 2
* Add key=1 (+1 key)
* Add key=2 (+1 key)
* Lookup Key=1
* Add Key=3
* => Key=2 will be removed by LRU
* Iterate map. Only found key=1 and key=3
*/
static void test_lru_sanity0(int map_type, int map_flags)
{
unsigned long long key, value[nr_cpus];
int lru_map_fd, expected_map_fd;
int next_cpu = 0;
printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
map_flags);
assert(sched_next_online(0, &next_cpu) != -1);
if (map_flags & BPF_F_NO_COMMON_LRU)
lru_map_fd = create_map(map_type, map_flags, 2 * nr_cpus);
else
lru_map_fd = create_map(map_type, map_flags, 2);
assert(lru_map_fd != -1);
expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, 2);
assert(expected_map_fd != -1);
value[0] = 1234;
/* insert key=1 element */
key = 1;
assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST));
assert(!bpf_map_update_elem(expected_map_fd, &key, value,
BPF_NOEXIST));
/* BPF_NOEXIST means: add new element if it doesn't exist */
assert(bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST) == -1
/* key=1 already exists */
&& errno == EEXIST);
assert(bpf_map_update_elem(lru_map_fd, &key, value, -1) == -1 &&
errno == EINVAL);
/* insert key=2 element */
/* check that key=2 is not found */
key = 2;
assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1 &&
errno == ENOENT);
/* BPF_EXIST means: update existing element */
assert(bpf_map_update_elem(lru_map_fd, &key, value, BPF_EXIST) == -1 &&
/* key=2 is not there */
errno == ENOENT);
assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST));
/* insert key=3 element */
/* check that key=3 is not found */
key = 3;
assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1 &&
errno == ENOENT);
/* check that key=1 can be found and mark the ref bit to
* stop LRU from removing key=1
*/
key = 1;
assert(!bpf_map_lookup_elem(lru_map_fd, &key, value));
assert(value[0] == 1234);
key = 3;
assert(!bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST));
assert(!bpf_map_update_elem(expected_map_fd, &key, value,
BPF_NOEXIST));
/* key=2 has been removed from the LRU */
key = 2;
assert(bpf_map_lookup_elem(lru_map_fd, &key, value) == -1);
assert(map_equal(lru_map_fd, expected_map_fd));
close(expected_map_fd);
close(lru_map_fd);
printf("Pass\n");
}
/* Size of the LRU map is 1.5*tgt_free
* Insert 1 to tgt_free (+tgt_free keys)
* Lookup 1 to tgt_free/2
* Insert 1+tgt_free to 2*tgt_free (+tgt_free keys)
* => 1+tgt_free/2 to LOCALFREE_TARGET will be removed by LRU
*/
static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
{
unsigned long long key, end_key, value[nr_cpus];
int lru_map_fd, expected_map_fd;
unsigned int batch_size;
unsigned int map_size;
int next_cpu = 0;
if (map_flags & BPF_F_NO_COMMON_LRU)
/* This test is only applicable to common LRU list */
return;
printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
map_flags);
assert(sched_next_online(0, &next_cpu) != -1);
batch_size = tgt_free / 2;
assert(batch_size * 2 == tgt_free);
map_size = tgt_free + batch_size;
lru_map_fd = create_map(map_type, map_flags, map_size);
assert(lru_map_fd != -1);
expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size);
assert(expected_map_fd != -1);
value[0] = 1234;
/* Insert 1 to tgt_free (+tgt_free keys) */
end_key = 1 + tgt_free;
for (key = 1; key < end_key; key++)
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
/* Lookup 1 to tgt_free/2 */
end_key = 1 + batch_size;
for (key = 1; key < end_key; key++) {
assert(!bpf_map_lookup_elem(lru_map_fd, &key, value));
assert(!bpf_map_update_elem(expected_map_fd, &key, value,
BPF_NOEXIST));
}
/* Insert 1+tgt_free to 2*tgt_free
* => 1+tgt_free/2 to LOCALFREE_TARGET will be
* removed by LRU
*/
key = 1 + tgt_free;
end_key = key + tgt_free;
for (; key < end_key; key++) {
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
assert(!bpf_map_update_elem(expected_map_fd, &key, value,
BPF_NOEXIST));
}
assert(map_equal(lru_map_fd, expected_map_fd));
close(expected_map_fd);
close(lru_map_fd);
printf("Pass\n");
}
/* Size of the LRU map 1.5 * tgt_free
* Insert 1 to tgt_free (+tgt_free keys)
* Update 1 to tgt_free/2
* => The original 1 to tgt_free/2 will be removed due to
* the LRU shrink process
* Re-insert 1 to tgt_free/2 again and do a lookup immeidately
* Insert 1+tgt_free to tgt_free*3/2
* Insert 1+tgt_free*3/2 to tgt_free*5/2
* => Key 1+tgt_free to tgt_free*3/2
* will be removed from LRU because it has never
* been lookup and ref bit is not set
*/
static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
{
unsigned long long key, value[nr_cpus];
unsigned long long end_key;
int lru_map_fd, expected_map_fd;
unsigned int batch_size;
unsigned int map_size;
int next_cpu = 0;
if (map_flags & BPF_F_NO_COMMON_LRU)
/* This test is only applicable to common LRU list */
return;
printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
map_flags);
assert(sched_next_online(0, &next_cpu) != -1);
batch_size = tgt_free / 2;
assert(batch_size * 2 == tgt_free);
map_size = tgt_free + batch_size;
lru_map_fd = create_map(map_type, map_flags, map_size);
assert(lru_map_fd != -1);
expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size);
assert(expected_map_fd != -1);
value[0] = 1234;
/* Insert 1 to tgt_free (+tgt_free keys) */
end_key = 1 + tgt_free;
for (key = 1; key < end_key; key++)
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
/* Any bpf_map_update_elem will require to acquire a new node
* from LRU first.
*
* The local list is running out of free nodes.
* It gets from the global LRU list which tries to
* shrink the inactive list to get tgt_free
* number of free nodes.
*
* Hence, the oldest key 1 to tgt_free/2
* are removed from the LRU list.
*/
key = 1;
if (map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
assert(!bpf_map_delete_elem(lru_map_fd, &key));
} else {
assert(bpf_map_update_elem(lru_map_fd, &key, value,
BPF_EXIST));
}
/* Re-insert 1 to tgt_free/2 again and do a lookup
* immeidately.
*/
end_key = 1 + batch_size;
value[0] = 4321;
for (key = 1; key < end_key; key++) {
assert(bpf_map_lookup_elem(lru_map_fd, &key, value));
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
assert(!bpf_map_lookup_elem(lru_map_fd, &key, value));
assert(value[0] == 4321);
assert(!bpf_map_update_elem(expected_map_fd, &key, value,
BPF_NOEXIST));
}
value[0] = 1234;
/* Insert 1+tgt_free to tgt_free*3/2 */
end_key = 1 + tgt_free + batch_size;
for (key = 1 + tgt_free; key < end_key; key++)
/* These newly added but not referenced keys will be
* gone during the next LRU shrink.
*/
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
/* Insert 1+tgt_free*3/2 to tgt_free*5/2 */
end_key = key + tgt_free;
for (; key < end_key; key++) {
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
assert(!bpf_map_update_elem(expected_map_fd, &key, value,
BPF_NOEXIST));
}
assert(map_equal(lru_map_fd, expected_map_fd));
close(expected_map_fd);
close(lru_map_fd);
printf("Pass\n");
}
/* Size of the LRU map is 2*tgt_free
* It is to test the active/inactive list rotation
* Insert 1 to 2*tgt_free (+2*tgt_free keys)
* Lookup key 1 to tgt_free*3/2
* Add 1+2*tgt_free to tgt_free*5/2 (+tgt_free/2 keys)
* => key 1+tgt_free*3/2 to 2*tgt_free are removed from LRU
*/
static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
{
unsigned long long key, end_key, value[nr_cpus];
int lru_map_fd, expected_map_fd;
unsigned int batch_size;
unsigned int map_size;
int next_cpu = 0;
if (map_flags & BPF_F_NO_COMMON_LRU)
/* This test is only applicable to common LRU list */
return;
printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
map_flags);
assert(sched_next_online(0, &next_cpu) != -1);
batch_size = tgt_free / 2;
assert(batch_size * 2 == tgt_free);
map_size = tgt_free * 2;
lru_map_fd = create_map(map_type, map_flags, map_size);
assert(lru_map_fd != -1);
expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size);
assert(expected_map_fd != -1);
value[0] = 1234;
/* Insert 1 to 2*tgt_free (+2*tgt_free keys) */
end_key = 1 + (2 * tgt_free);
for (key = 1; key < end_key; key++)
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
/* Lookup key 1 to tgt_free*3/2 */
end_key = tgt_free + batch_size;
for (key = 1; key < end_key; key++) {
assert(!bpf_map_lookup_elem(lru_map_fd, &key, value));
assert(!bpf_map_update_elem(expected_map_fd, &key, value,
BPF_NOEXIST));
}
/* Add 1+2*tgt_free to tgt_free*5/2
* (+tgt_free/2 keys)
*/
key = 2 * tgt_free + 1;
end_key = key + batch_size;
for (; key < end_key; key++) {
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
assert(!bpf_map_update_elem(expected_map_fd, &key, value,
BPF_NOEXIST));
}
assert(map_equal(lru_map_fd, expected_map_fd));
close(expected_map_fd);
close(lru_map_fd);
printf("Pass\n");
}
/* Test deletion */
static void test_lru_sanity4(int map_type, int map_flags, unsigned int tgt_free)
{
int lru_map_fd, expected_map_fd;
unsigned long long key, value[nr_cpus];
unsigned long long end_key;
int next_cpu = 0;
printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
map_flags);
assert(sched_next_online(0, &next_cpu) != -1);
if (map_flags & BPF_F_NO_COMMON_LRU)
lru_map_fd = create_map(map_type, map_flags,
3 * tgt_free * nr_cpus);
else
lru_map_fd = create_map(map_type, map_flags, 3 * tgt_free);
assert(lru_map_fd != -1);
expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0,
3 * tgt_free);
assert(expected_map_fd != -1);
value[0] = 1234;
for (key = 1; key <= 2 * tgt_free; key++)
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
key = 1;
assert(bpf_map_update_elem(lru_map_fd, &key, value, BPF_NOEXIST));
for (key = 1; key <= tgt_free; key++) {
assert(!bpf_map_lookup_elem(lru_map_fd, &key, value));
assert(!bpf_map_update_elem(expected_map_fd, &key, value,
BPF_NOEXIST));
}
for (; key <= 2 * tgt_free; key++) {
assert(!bpf_map_delete_elem(lru_map_fd, &key));
assert(bpf_map_delete_elem(lru_map_fd, &key));
}
end_key = key + 2 * tgt_free;
for (; key < end_key; key++) {
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
assert(!bpf_map_update_elem(expected_map_fd, &key, value,
BPF_NOEXIST));
}
assert(map_equal(lru_map_fd, expected_map_fd));
close(expected_map_fd);
close(lru_map_fd);
printf("Pass\n");
}
static void do_test_lru_sanity5(unsigned long long last_key, int map_fd)
{
unsigned long long key, value[nr_cpus];
/* Ensure the last key inserted by previous CPU can be found */
assert(!bpf_map_lookup_elem(map_fd, &last_key, value));
value[0] = 1234;
key = last_key + 1;
assert(!bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST));
assert(!bpf_map_lookup_elem(map_fd, &key, value));
/* Cannot find the last key because it was removed by LRU */
assert(bpf_map_lookup_elem(map_fd, &last_key, value));
}
/* Test map with only one element */
static void test_lru_sanity5(int map_type, int map_flags)
{
unsigned long long key, value[nr_cpus];
int next_cpu = 0;
int map_fd;
if (map_flags & BPF_F_NO_COMMON_LRU)
return;
printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
map_flags);
map_fd = create_map(map_type, map_flags, 1);
assert(map_fd != -1);
value[0] = 1234;
key = 0;
assert(!bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST));
while (sched_next_online(0, &next_cpu) != -1) {
pid_t pid;
pid = fork();
if (pid == 0) {
do_test_lru_sanity5(key, map_fd);
exit(0);
} else if (pid == -1) {
printf("couldn't spawn process to test key:%llu\n",
key);
exit(1);
} else {
int status;
assert(waitpid(pid, &status, 0) == pid);
assert(status == 0);
key++;
}
}
close(map_fd);
/* At least one key should be tested */
assert(key > 0);
printf("Pass\n");
}
/* Test list rotation for BPF_F_NO_COMMON_LRU map */
static void test_lru_sanity6(int map_type, int map_flags, int tgt_free)
{
int lru_map_fd, expected_map_fd;
unsigned long long key, value[nr_cpus];
unsigned int map_size = tgt_free * 2;
int next_cpu = 0;
if (!(map_flags & BPF_F_NO_COMMON_LRU))
return;
printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
map_flags);
assert(sched_next_online(0, &next_cpu) != -1);
expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0, map_size);
assert(expected_map_fd != -1);
lru_map_fd = create_map(map_type, map_flags, map_size * nr_cpus);
assert(lru_map_fd != -1);
value[0] = 1234;
for (key = 1; key <= tgt_free; key++) {
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
assert(!bpf_map_update_elem(expected_map_fd, &key, value,
BPF_NOEXIST));
}
for (; key <= tgt_free * 2; key++) {
unsigned long long stable_key;
/* Make ref bit sticky for key: [1, tgt_free] */
for (stable_key = 1; stable_key <= tgt_free; stable_key++) {
/* Mark the ref bit */
assert(!bpf_map_lookup_elem(lru_map_fd, &stable_key,
value));
}
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
}
for (; key <= tgt_free * 3; key++) {
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
assert(!bpf_map_update_elem(expected_map_fd, &key, value,
BPF_NOEXIST));
}
assert(map_equal(lru_map_fd, expected_map_fd));
close(expected_map_fd);
close(lru_map_fd);
printf("Pass\n");
}
int main(int argc, char **argv)
{
int map_types[] = {BPF_MAP_TYPE_LRU_HASH,
BPF_MAP_TYPE_LRU_PERCPU_HASH};
int map_flags[] = {0, BPF_F_NO_COMMON_LRU};
int t, f;
setbuf(stdout, NULL);
nr_cpus = bpf_num_possible_cpus();
assert(nr_cpus != -1);
printf("nr_cpus:%d\n\n", nr_cpus);
for (f = 0; f < sizeof(map_flags) / sizeof(*map_flags); f++) {
unsigned int tgt_free = (map_flags[f] & BPF_F_NO_COMMON_LRU) ?
PERCPU_FREE_TARGET : LOCAL_FREE_TARGET;
for (t = 0; t < sizeof(map_types) / sizeof(*map_types); t++) {
test_lru_sanity0(map_types[t], map_flags[f]);
test_lru_sanity1(map_types[t], map_flags[f], tgt_free);
test_lru_sanity2(map_types[t], map_flags[f], tgt_free);
test_lru_sanity3(map_types[t], map_flags[f], tgt_free);
test_lru_sanity4(map_types[t], map_flags[f], tgt_free);
test_lru_sanity5(map_types[t], map_flags[f]);
test_lru_sanity6(map_types[t], map_flags[f], tgt_free);
printf("\n");
}
}
return 0;
}
@@ -0,0 +1,437 @@
#include <stddef.h>
#include <inttypes.h>
#include <errno.h>
#include <linux/seg6_local.h>
#include <linux/bpf.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
#define bpf_printk(fmt, ...) \
({ \
char ____fmt[] = fmt; \
bpf_trace_printk(____fmt, sizeof(____fmt), \
##__VA_ARGS__); \
})
/* Packet parsing state machine helpers. */
#define cursor_advance(_cursor, _len) \
({ void *_tmp = _cursor; _cursor += _len; _tmp; })
#define SR6_FLAG_ALERT (1 << 4)
#define htonll(x) ((bpf_htonl(1)) == 1 ? (x) : ((uint64_t)bpf_htonl((x) & \
0xFFFFFFFF) << 32) | bpf_htonl((x) >> 32))
#define ntohll(x) ((bpf_ntohl(1)) == 1 ? (x) : ((uint64_t)bpf_ntohl((x) & \
0xFFFFFFFF) << 32) | bpf_ntohl((x) >> 32))
#define BPF_PACKET_HEADER __attribute__((packed))
struct ip6_t {
unsigned int ver:4;
unsigned int priority:8;
unsigned int flow_label:20;
unsigned short payload_len;
unsigned char next_header;
unsigned char hop_limit;
unsigned long long src_hi;
unsigned long long src_lo;
unsigned long long dst_hi;
unsigned long long dst_lo;
} BPF_PACKET_HEADER;
struct ip6_addr_t {
unsigned long long hi;
unsigned long long lo;
} BPF_PACKET_HEADER;
struct ip6_srh_t {
unsigned char nexthdr;
unsigned char hdrlen;
unsigned char type;
unsigned char segments_left;
unsigned char first_segment;
unsigned char flags;
unsigned short tag;
struct ip6_addr_t segments[0];
} BPF_PACKET_HEADER;
struct sr6_tlv_t {
unsigned char type;
unsigned char len;
unsigned char value[0];
} BPF_PACKET_HEADER;
static __always_inline struct ip6_srh_t *get_srh(struct __sk_buff *skb)
{
void *cursor, *data_end;
struct ip6_srh_t *srh;
struct ip6_t *ip;
uint8_t *ipver;
data_end = (void *)(long)skb->data_end;
cursor = (void *)(long)skb->data;
ipver = (uint8_t *)cursor;
if ((void *)ipver + sizeof(*ipver) > data_end)
return NULL;
if ((*ipver >> 4) != 6)
return NULL;
ip = cursor_advance(cursor, sizeof(*ip));
if ((void *)ip + sizeof(*ip) > data_end)
return NULL;
if (ip->next_header != 43)
return NULL;
srh = cursor_advance(cursor, sizeof(*srh));
if ((void *)srh + sizeof(*srh) > data_end)
return NULL;
if (srh->type != 4)
return NULL;
return srh;
}
static __always_inline
int update_tlv_pad(struct __sk_buff *skb, uint32_t new_pad,
uint32_t old_pad, uint32_t pad_off)
{
int err;
if (new_pad != old_pad) {
err = bpf_lwt_seg6_adjust_srh(skb, pad_off,
(int) new_pad - (int) old_pad);
if (err)
return err;
}
if (new_pad > 0) {
char pad_tlv_buf[16] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0};
struct sr6_tlv_t *pad_tlv = (struct sr6_tlv_t *) pad_tlv_buf;
pad_tlv->type = SR6_TLV_PADDING;
pad_tlv->len = new_pad - 2;
err = bpf_lwt_seg6_store_bytes(skb, pad_off,
(void *)pad_tlv_buf, new_pad);
if (err)
return err;
}
return 0;
}
static __always_inline
int is_valid_tlv_boundary(struct __sk_buff *skb, struct ip6_srh_t *srh,
uint32_t *tlv_off, uint32_t *pad_size,
uint32_t *pad_off)
{
uint32_t srh_off, cur_off;
int offset_valid = 0;
int err;
srh_off = (char *)srh - (char *)(long)skb->data;
// cur_off = end of segments, start of possible TLVs
cur_off = srh_off + sizeof(*srh) +
sizeof(struct ip6_addr_t) * (srh->first_segment + 1);
*pad_off = 0;
// we can only go as far as ~10 TLVs due to the BPF max stack size
#pragma clang loop unroll(full)
for (int i = 0; i < 10; i++) {
struct sr6_tlv_t tlv;
if (cur_off == *tlv_off)
offset_valid = 1;
if (cur_off >= srh_off + ((srh->hdrlen + 1) << 3))
break;
err = bpf_skb_load_bytes(skb, cur_off, &tlv, sizeof(tlv));
if (err)
return err;
if (tlv.type == SR6_TLV_PADDING) {
*pad_size = tlv.len + sizeof(tlv);
*pad_off = cur_off;
if (*tlv_off == srh_off) {
*tlv_off = cur_off;
offset_valid = 1;
}
break;
} else if (tlv.type == SR6_TLV_HMAC) {
break;
}
cur_off += sizeof(tlv) + tlv.len;
} // we reached the padding or HMAC TLVs, or the end of the SRH
if (*pad_off == 0)
*pad_off = cur_off;
if (*tlv_off == -1)
*tlv_off = cur_off;
else if (!offset_valid)
return -EINVAL;
return 0;
}
static __always_inline
int add_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh, uint32_t tlv_off,
struct sr6_tlv_t *itlv, uint8_t tlv_size)
{
uint32_t srh_off = (char *)srh - (char *)(long)skb->data;
uint8_t len_remaining, new_pad;
uint32_t pad_off = 0;
uint32_t pad_size = 0;
uint32_t partial_srh_len;
int err;
if (tlv_off != -1)
tlv_off += srh_off;
if (itlv->type == SR6_TLV_PADDING || itlv->type == SR6_TLV_HMAC)
return -EINVAL;
err = is_valid_tlv_boundary(skb, srh, &tlv_off, &pad_size, &pad_off);
if (err)
return err;
err = bpf_lwt_seg6_adjust_srh(skb, tlv_off, sizeof(*itlv) + itlv->len);
if (err)
return err;
err = bpf_lwt_seg6_store_bytes(skb, tlv_off, (void *)itlv, tlv_size);
if (err)
return err;
// the following can't be moved inside update_tlv_pad because the
// bpf verifier has some issues with it
pad_off += sizeof(*itlv) + itlv->len;
partial_srh_len = pad_off - srh_off;
len_remaining = partial_srh_len % 8;
new_pad = 8 - len_remaining;
if (new_pad == 1) // cannot pad for 1 byte only
new_pad = 9;
else if (new_pad == 8)
new_pad = 0;
return update_tlv_pad(skb, new_pad, pad_size, pad_off);
}
static __always_inline
int delete_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh,
uint32_t tlv_off)
{
uint32_t srh_off = (char *)srh - (char *)(long)skb->data;
uint8_t len_remaining, new_pad;
uint32_t partial_srh_len;
uint32_t pad_off = 0;
uint32_t pad_size = 0;
struct sr6_tlv_t tlv;
int err;
tlv_off += srh_off;
err = is_valid_tlv_boundary(skb, srh, &tlv_off, &pad_size, &pad_off);
if (err)
return err;
err = bpf_skb_load_bytes(skb, tlv_off, &tlv, sizeof(tlv));
if (err)
return err;
err = bpf_lwt_seg6_adjust_srh(skb, tlv_off, -(sizeof(tlv) + tlv.len));
if (err)
return err;
pad_off -= sizeof(tlv) + tlv.len;
partial_srh_len = pad_off - srh_off;
len_remaining = partial_srh_len % 8;
new_pad = 8 - len_remaining;
if (new_pad == 1) // cannot pad for 1 byte only
new_pad = 9;
else if (new_pad == 8)
new_pad = 0;
return update_tlv_pad(skb, new_pad, pad_size, pad_off);
}
static __always_inline
int has_egr_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh)
{
int tlv_offset = sizeof(struct ip6_t) + sizeof(struct ip6_srh_t) +
((srh->first_segment + 1) << 4);
struct sr6_tlv_t tlv;
if (bpf_skb_load_bytes(skb, tlv_offset, &tlv, sizeof(struct sr6_tlv_t)))
return 0;
if (tlv.type == SR6_TLV_EGRESS && tlv.len == 18) {
struct ip6_addr_t egr_addr;
if (bpf_skb_load_bytes(skb, tlv_offset + 4, &egr_addr, 16))
return 0;
// check if egress TLV value is correct
if (ntohll(egr_addr.hi) == 0xfd00000000000000 &&
ntohll(egr_addr.lo) == 0x4)
return 1;
}
return 0;
}
// This function will push a SRH with segments fd00::1, fd00::2, fd00::3,
// fd00::4
SEC("encap_srh")
int __encap_srh(struct __sk_buff *skb)
{
unsigned long long hi = 0xfd00000000000000;
struct ip6_addr_t *seg;
struct ip6_srh_t *srh;
char srh_buf[72]; // room for 4 segments
int err;
srh = (struct ip6_srh_t *)srh_buf;
srh->nexthdr = 0;
srh->hdrlen = 8;
srh->type = 4;
srh->segments_left = 3;
srh->first_segment = 3;
srh->flags = 0;
srh->tag = 0;
seg = (struct ip6_addr_t *)((char *)srh + sizeof(*srh));
#pragma clang loop unroll(full)
for (unsigned long long lo = 0; lo < 4; lo++) {
seg->lo = htonll(4 - lo);
seg->hi = htonll(hi);
seg = (struct ip6_addr_t *)((char *)seg + sizeof(*seg));
}
err = bpf_lwt_push_encap(skb, 0, (void *)srh, sizeof(srh_buf));
if (err)
return BPF_DROP;
return BPF_REDIRECT;
}
// Add an Egress TLV fc00::4, add the flag A,
// and apply End.X action to fc42::1
SEC("add_egr_x")
int __add_egr_x(struct __sk_buff *skb)
{
unsigned long long hi = 0xfc42000000000000;
unsigned long long lo = 0x1;
struct ip6_srh_t *srh = get_srh(skb);
uint8_t new_flags = SR6_FLAG_ALERT;
struct ip6_addr_t addr;
int err, offset;
if (srh == NULL)
return BPF_DROP;
uint8_t tlv[20] = {2, 18, 0, 0, 0xfd, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x4};
err = add_tlv(skb, srh, (srh->hdrlen+1) << 3,
(struct sr6_tlv_t *)&tlv, 20);
if (err)
return BPF_DROP;
offset = sizeof(struct ip6_t) + offsetof(struct ip6_srh_t, flags);
err = bpf_lwt_seg6_store_bytes(skb, offset,
(void *)&new_flags, sizeof(new_flags));
if (err)
return BPF_DROP;
addr.lo = htonll(lo);
addr.hi = htonll(hi);
err = bpf_lwt_seg6_action(skb, SEG6_LOCAL_ACTION_END_X,
(void *)&addr, sizeof(addr));
if (err)
return BPF_DROP;
return BPF_REDIRECT;
}
// Pop the Egress TLV, reset the flags, change the tag 2442 and finally do a
// simple End action
SEC("pop_egr")
int __pop_egr(struct __sk_buff *skb)
{
struct ip6_srh_t *srh = get_srh(skb);
uint16_t new_tag = bpf_htons(2442);
uint8_t new_flags = 0;
int err, offset;
if (srh == NULL)
return BPF_DROP;
if (srh->flags != SR6_FLAG_ALERT)
return BPF_DROP;
if (srh->hdrlen != 11) // 4 segments + Egress TLV + Padding TLV
return BPF_DROP;
if (!has_egr_tlv(skb, srh))
return BPF_DROP;
err = delete_tlv(skb, srh, 8 + (srh->first_segment + 1) * 16);
if (err)
return BPF_DROP;
offset = sizeof(struct ip6_t) + offsetof(struct ip6_srh_t, flags);
if (bpf_lwt_seg6_store_bytes(skb, offset, (void *)&new_flags,
sizeof(new_flags)))
return BPF_DROP;
offset = sizeof(struct ip6_t) + offsetof(struct ip6_srh_t, tag);
if (bpf_lwt_seg6_store_bytes(skb, offset, (void *)&new_tag,
sizeof(new_tag)))
return BPF_DROP;
return BPF_OK;
}
// Inspect if the Egress TLV and flag have been removed, if the tag is correct,
// then apply a End.T action to reach the last segment
SEC("inspect_t")
int __inspect_t(struct __sk_buff *skb)
{
struct ip6_srh_t *srh = get_srh(skb);
int table = 117;
int err;
if (srh == NULL)
return BPF_DROP;
if (srh->flags != 0)
return BPF_DROP;
if (srh->tag != bpf_htons(2442))
return BPF_DROP;
if (srh->hdrlen != 8) // 4 segments
return BPF_DROP;
err = bpf_lwt_seg6_action(skb, SEG6_LOCAL_ACTION_END_T,
(void *)&table, sizeof(table));
if (err)
return BPF_DROP;
return BPF_REDIRECT;
}
char __license[] SEC("license") = "GPL";
+149
View File
@@ -0,0 +1,149 @@
#!/bin/bash
# Connects 6 network namespaces through veths.
# Each NS may have different IPv6 global scope addresses :
# NS1 ---- NS2 ---- NS3 ---- NS4 ---- NS5 ---- NS6
# fb00::1 fd00::1 fd00::2 fd00::3 fb00::6
# fc42::1 fd00::4
#
# All IPv6 packets going to fb00::/16 through NS2 will be encapsulated in a
# IPv6 header with a Segment Routing Header, with segments :
# fd00::1 -> fd00::2 -> fd00::3 -> fd00::4
#
# 3 fd00::/16 IPv6 addresses are binded to seg6local End.BPF actions :
# - fd00::1 : add a TLV, change the flags and apply a End.X action to fc42::1
# - fd00::2 : remove the TLV, change the flags, add a tag
# - fd00::3 : apply an End.T action to fd00::4, through routing table 117
#
# fd00::4 is a simple Segment Routing node decapsulating the inner IPv6 packet.
# Each End.BPF action will validate the operations applied on the SRH by the
# previous BPF program in the chain, otherwise the packet is dropped.
#
# An UDP datagram is sent from fb00::1 to fb00::6. The test succeeds if this
# datagram can be read on NS6 when binding to fb00::6.
# Kselftest framework requirement - SKIP code is 4.
ksft_skip=4
msg="skip all tests:"
if [ $UID != 0 ]; then
echo $msg please run this as root >&2
exit $ksft_skip
fi
TMP_FILE="/tmp/selftest_lwt_seg6local.txt"
cleanup()
{
if [ "$?" = "0" ]; then
echo "selftests: test_lwt_seg6local [PASS]";
else
echo "selftests: test_lwt_seg6local [FAILED]";
fi
set +e
ip netns del ns1 2> /dev/null
ip netns del ns2 2> /dev/null
ip netns del ns3 2> /dev/null
ip netns del ns4 2> /dev/null
ip netns del ns5 2> /dev/null
ip netns del ns6 2> /dev/null
rm -f $TMP_FILE
}
set -e
ip netns add ns1
ip netns add ns2
ip netns add ns3
ip netns add ns4
ip netns add ns5
ip netns add ns6
trap cleanup 0 2 3 6 9
ip link add veth1 type veth peer name veth2
ip link add veth3 type veth peer name veth4
ip link add veth5 type veth peer name veth6
ip link add veth7 type veth peer name veth8
ip link add veth9 type veth peer name veth10
ip link set veth1 netns ns1
ip link set veth2 netns ns2
ip link set veth3 netns ns2
ip link set veth4 netns ns3
ip link set veth5 netns ns3
ip link set veth6 netns ns4
ip link set veth7 netns ns4
ip link set veth8 netns ns5
ip link set veth9 netns ns5
ip link set veth10 netns ns6
ip netns exec ns1 ip link set dev veth1 up
ip netns exec ns2 ip link set dev veth2 up
ip netns exec ns2 ip link set dev veth3 up
ip netns exec ns3 ip link set dev veth4 up
ip netns exec ns3 ip link set dev veth5 up
ip netns exec ns4 ip link set dev veth6 up
ip netns exec ns4 ip link set dev veth7 up
ip netns exec ns5 ip link set dev veth8 up
ip netns exec ns5 ip link set dev veth9 up
ip netns exec ns6 ip link set dev veth10 up
ip netns exec ns6 ip link set dev lo up
# All link scope addresses and routes required between veths
ip netns exec ns1 ip -6 addr add fb00::12/16 dev veth1 scope link
ip netns exec ns1 ip -6 route add fb00::21 dev veth1 scope link
ip netns exec ns2 ip -6 addr add fb00::21/16 dev veth2 scope link
ip netns exec ns2 ip -6 addr add fb00::34/16 dev veth3 scope link
ip netns exec ns2 ip -6 route add fb00::43 dev veth3 scope link
ip netns exec ns3 ip -6 route add fb00::65 dev veth5 scope link
ip netns exec ns3 ip -6 addr add fb00::43/16 dev veth4 scope link
ip netns exec ns3 ip -6 addr add fb00::56/16 dev veth5 scope link
ip netns exec ns4 ip -6 addr add fb00::65/16 dev veth6 scope link
ip netns exec ns4 ip -6 addr add fb00::78/16 dev veth7 scope link
ip netns exec ns4 ip -6 route add fb00::87 dev veth7 scope link
ip netns exec ns5 ip -6 addr add fb00::87/16 dev veth8 scope link
ip netns exec ns5 ip -6 addr add fb00::910/16 dev veth9 scope link
ip netns exec ns5 ip -6 route add fb00::109 dev veth9 scope link
ip netns exec ns5 ip -6 route add fb00::109 table 117 dev veth9 scope link
ip netns exec ns6 ip -6 addr add fb00::109/16 dev veth10 scope link
ip netns exec ns1 ip -6 addr add fb00::1/16 dev lo
ip netns exec ns1 ip -6 route add fb00::6 dev veth1 via fb00::21
ip netns exec ns2 ip -6 route add fb00::6 encap bpf in obj test_lwt_seg6local.o sec encap_srh dev veth2
ip netns exec ns2 ip -6 route add fd00::1 dev veth3 via fb00::43 scope link
ip netns exec ns3 ip -6 route add fc42::1 dev veth5 via fb00::65
ip netns exec ns3 ip -6 route add fd00::1 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec add_egr_x dev veth4
ip netns exec ns4 ip -6 route add fd00::2 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec pop_egr dev veth6
ip netns exec ns4 ip -6 addr add fc42::1 dev lo
ip netns exec ns4 ip -6 route add fd00::3 dev veth7 via fb00::87
ip netns exec ns5 ip -6 route add fd00::4 table 117 dev veth9 via fb00::109
ip netns exec ns5 ip -6 route add fd00::3 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec inspect_t dev veth8
ip netns exec ns6 ip -6 addr add fb00::6/16 dev lo
ip netns exec ns6 ip -6 addr add fd00::4/16 dev lo
ip netns exec ns1 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
ip netns exec ns2 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
ip netns exec ns3 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
ip netns exec ns4 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
ip netns exec ns5 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
ip netns exec ns6 sysctl net.ipv6.conf.all.seg6_enabled=1 > /dev/null
ip netns exec ns6 sysctl net.ipv6.conf.lo.seg6_enabled=1 > /dev/null
ip netns exec ns6 sysctl net.ipv6.conf.veth10.seg6_enabled=1 > /dev/null
ip netns exec ns6 nc -l -6 -u -d 7330 > $TMP_FILE &
ip netns exec ns1 bash -c "echo 'foobar' | nc -w0 -6 -u -p 2121 -s fb00::1 fb00::6 7330"
sleep 5 # wait enough time to ensure the UDP datagram arrived to the last segment
kill -INT $!
if [[ $(< $TMP_FILE) != "foobar" ]]; then
exit 1
fi
exit 0
File diff suppressed because it is too large. Load diff
+35
View File
@@ -0,0 +1,35 @@
/* Copyright (c) 2017 Facebook
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
#include <stddef.h>
#include <linux/bpf.h>
#include <linux/pkt_cls.h>
#include "bpf_helpers.h"
/* It is a dumb bpf program such that it must have no
* issue to be loaded since testing the verifier is
* not the focus here.
*/
int _version SEC("version") = 1;
struct bpf_map_def SEC("maps") test_map_id = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(__u64),
.max_entries = 1,
};
SEC("test_obj_id_dummy")
int test_obj_id(struct __sk_buff *skb)
{
__u32 key = 0;
__u64 *value;
value = bpf_map_lookup_elem(&test_map_id, &key);
return TC_ACT_OK;
}
File diff suppressed because it is too large. Load diff
@@ -0,0 +1,65 @@
/* Copyright (c) 2017 Facebook
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
#include <stddef.h>
#include <string.h>
#include <linux/bpf.h>
#include <linux/if_ether.h>
#include <linux/if_packet.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/in.h>
#include <linux/tcp.h>
#include <linux/pkt_cls.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
#define barrier() __asm__ __volatile__("": : :"memory")
int _version SEC("version") = 1;
SEC("test1")
int process(struct __sk_buff *skb)
{
void *data_end = (void *)(long)skb->data_end;
void *data = (void *)(long)skb->data;
struct ethhdr *eth = (struct ethhdr *)(data);
struct tcphdr *tcp = NULL;
__u8 proto = 255;
__u64 ihl_len;
if (eth + 1 > data_end)
return TC_ACT_SHOT;
if (eth->h_proto == bpf_htons(ETH_P_IP)) {
struct iphdr *iph = (struct iphdr *)(eth + 1);
if (iph + 1 > data_end)
return TC_ACT_SHOT;
ihl_len = iph->ihl * 4;
proto = iph->protocol;
tcp = (struct tcphdr *)((void *)(iph) + ihl_len);
} else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) {
struct ipv6hdr *ip6h = (struct ipv6hdr *)(eth + 1);
if (ip6h + 1 > data_end)
return TC_ACT_SHOT;
ihl_len = sizeof(*ip6h);
proto = ip6h->nexthdr;
tcp = (struct tcphdr *)((void *)(ip6h) + ihl_len);
}
if (tcp) {
if (((void *)(tcp) + 20) > data_end || proto != 6)
return TC_ACT_SHOT;
barrier(); /* to force ordering of checks */
if (((void *)(tcp) + 18) > data_end)
return TC_ACT_SHOT;
if (tcp->urg_ptr == 123)
return TC_ACT_OK;
}
return TC_ACT_UNSPEC;
}
@@ -0,0 +1,46 @@
/* Copyright (c) 2017 Facebook
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
#include <stddef.h>
#include <string.h>
#include <linux/bpf.h>
#include <linux/pkt_cls.h>
#include "bpf_helpers.h"
int _version SEC("version") = 1;
#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
#define TEST_FIELD(TYPE, FIELD, MASK) \
{ \
TYPE tmp = *(volatile TYPE *)&skb->FIELD; \
if (tmp != ((*(volatile __u32 *)&skb->FIELD) & MASK)) \
return TC_ACT_SHOT; \
}
#else
#define TEST_FIELD_OFFSET(a, b) ((sizeof(a) - sizeof(b)) / sizeof(b))
#define TEST_FIELD(TYPE, FIELD, MASK) \
{ \
TYPE tmp = *((volatile TYPE *)&skb->FIELD + \
TEST_FIELD_OFFSET(skb->FIELD, TYPE)); \
if (tmp != ((*(volatile __u32 *)&skb->FIELD) & MASK)) \
return TC_ACT_SHOT; \
}
#endif
SEC("test1")
int process(struct __sk_buff *skb)
{
TEST_FIELD(__u8, len, 0xFF);
TEST_FIELD(__u16, len, 0xFFFF);
TEST_FIELD(__u32, len, 0xFFFFFFFF);
TEST_FIELD(__u16, protocol, 0xFFFF);
TEST_FIELD(__u32, protocol, 0xFFFFFFFF);
TEST_FIELD(__u8, hash, 0xFF);
TEST_FIELD(__u16, hash, 0xFFFF);
TEST_FIELD(__u32, hash, 0xFFFFFFFF);
return TC_ACT_OK;
}
File diff suppressed because it is too large. Load diff
@@ -0,0 +1,700 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2018 Facebook */
#include <stdlib.h>
#include <unistd.h>
#include <stdbool.h>
#include <string.h>
#include <errno.h>
#include <assert.h>
#include <fcntl.h>
#include <linux/bpf.h>
#include <linux/err.h>
#include <linux/types.h>
#include <linux/if_ether.h>
#include <sys/types.h>
#include <sys/epoll.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
#include "bpf_rlimit.h"
#include "bpf_util.h"
#include "test_select_reuseport_common.h"
#define MIN_TCPHDR_LEN 20
#define UDPHDR_LEN 8
#define TCP_SYNCOOKIE_SYSCTL "/proc/sys/net/ipv4/tcp_syncookies"
#define TCP_FO_SYSCTL "/proc/sys/net/ipv4/tcp_fastopen"
#define REUSEPORT_ARRAY_SIZE 32
static int result_map, tmp_index_ovr_map, linum_map, data_check_map;
static __u32 expected_results[NR_RESULTS];
static int sk_fds[REUSEPORT_ARRAY_SIZE];
static int reuseport_array, outer_map;
static int select_by_skb_data_prog;
static int saved_tcp_syncookie;
static struct bpf_object *obj;
static int saved_tcp_fo;
static __u32 index_zero;
static int epfd;
static union sa46 {
struct sockaddr_in6 v6;
struct sockaddr_in v4;
sa_family_t family;
} srv_sa;
#define CHECK(condition, tag, format...) ({ \
int __ret = !!(condition); \
if (__ret) { \
printf("%s(%d):FAIL:%s ", __func__, __LINE__, tag); \
printf(format); \
exit(-1); \
} \
})
static void create_maps(void)
{
struct bpf_create_map_attr attr = {};
/* Creating reuseport_array */
attr.name = "reuseport_array";
attr.map_type = BPF_MAP_TYPE_REUSEPORT_SOCKARRAY;
attr.key_size = sizeof(__u32);
attr.value_size = sizeof(__u32);
attr.max_entries = REUSEPORT_ARRAY_SIZE;
reuseport_array = bpf_create_map_xattr(&attr);
CHECK(reuseport_array == -1, "creating reuseport_array",
"reuseport_array:%d errno:%d\n", reuseport_array, errno);
/* Creating outer_map */
attr.name = "outer_map";
attr.map_type = BPF_MAP_TYPE_ARRAY_OF_MAPS;
attr.key_size = sizeof(__u32);
attr.value_size = sizeof(__u32);
attr.max_entries = 1;
attr.inner_map_fd = reuseport_array;
outer_map = bpf_create_map_xattr(&attr);
CHECK(outer_map == -1, "creating outer_map",
"outer_map:%d errno:%d\n", outer_map, errno);
}
static void prepare_bpf_obj(void)
{
struct bpf_program *prog;
struct bpf_map *map;
int err;
struct bpf_object_open_attr attr = {
.file = "test_select_reuseport_kern.o",
.prog_type = BPF_PROG_TYPE_SK_REUSEPORT,
};
obj = bpf_object__open_xattr(&attr);
CHECK(IS_ERR_OR_NULL(obj), "open test_select_reuseport_kern.o",
"obj:%p PTR_ERR(obj):%ld\n", obj, PTR_ERR(obj));
prog = bpf_program__next(NULL, obj);
CHECK(!prog, "get first bpf_program", "!prog\n");
bpf_program__set_type(prog, attr.prog_type);
map = bpf_object__find_map_by_name(obj, "outer_map");
CHECK(!map, "find outer_map", "!map\n");
err = bpf_map__reuse_fd(map, outer_map);
CHECK(err, "reuse outer_map", "err:%d\n", err);
err = bpf_object__load(obj);
CHECK(err, "load bpf_object", "err:%d\n", err);
select_by_skb_data_prog = bpf_program__fd(prog);
CHECK(select_by_skb_data_prog == -1, "get prog fd",
"select_by_skb_data_prog:%d\n", select_by_skb_data_prog);
map = bpf_object__find_map_by_name(obj, "result_map");
CHECK(!map, "find result_map", "!map\n");
result_map = bpf_map__fd(map);
CHECK(result_map == -1, "get result_map fd",
"result_map:%d\n", result_map);
map = bpf_object__find_map_by_name(obj, "tmp_index_ovr_map");
CHECK(!map, "find tmp_index_ovr_map", "!map\n");
tmp_index_ovr_map = bpf_map__fd(map);
CHECK(tmp_index_ovr_map == -1, "get tmp_index_ovr_map fd",
"tmp_index_ovr_map:%d\n", tmp_index_ovr_map);
map = bpf_object__find_map_by_name(obj, "linum_map");
CHECK(!map, "find linum_map", "!map\n");
linum_map = bpf_map__fd(map);
CHECK(linum_map == -1, "get linum_map fd",
"linum_map:%d\n", linum_map);
map = bpf_object__find_map_by_name(obj, "data_check_map");
CHECK(!map, "find data_check_map", "!map\n");
data_check_map = bpf_map__fd(map);
CHECK(data_check_map == -1, "get data_check_map fd",
"data_check_map:%d\n", data_check_map);
}
static void sa46_init_loopback(union sa46 *sa, sa_family_t family)
{
memset(sa, 0, sizeof(*sa));
sa->family = family;
if (sa->family == AF_INET6)
sa->v6.sin6_addr = in6addr_loopback;
else
sa->v4.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
}
static void sa46_init_inany(union sa46 *sa, sa_family_t family)
{
memset(sa, 0, sizeof(*sa));
sa->family = family;
if (sa->family == AF_INET6)
sa->v6.sin6_addr = in6addr_any;
else
sa->v4.sin_addr.s_addr = INADDR_ANY;
}
static int read_int_sysctl(const char *sysctl)
{
char buf[16];
int fd, ret;
fd = open(sysctl, 0);
CHECK(fd == -1, "open(sysctl)", "sysctl:%s fd:%d errno:%d\n",
sysctl, fd, errno);
ret = read(fd, buf, sizeof(buf));
CHECK(ret <= 0, "read(sysctl)", "sysctl:%s ret:%d errno:%d\n",
sysctl, ret, errno);
close(fd);
return atoi(buf);
}
static void write_int_sysctl(const char *sysctl, int v)
{
int fd, ret, size;
char buf[16];
fd = open(sysctl, O_RDWR);
CHECK(fd == -1, "open(sysctl)", "sysctl:%s fd:%d errno:%d\n",
sysctl, fd, errno);
size = snprintf(buf, sizeof(buf), "%d", v);
ret = write(fd, buf, size);
CHECK(ret != size, "write(sysctl)",
"sysctl:%s ret:%d size:%d errno:%d\n", sysctl, ret, size, errno);
close(fd);
}
static void restore_sysctls(void)
{
write_int_sysctl(TCP_FO_SYSCTL, saved_tcp_fo);
write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, saved_tcp_syncookie);
}
static void enable_fastopen(void)
{
int fo;
fo = read_int_sysctl(TCP_FO_SYSCTL);
write_int_sysctl(TCP_FO_SYSCTL, fo | 7);
}
static void enable_syncookie(void)
{
write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, 2);
}
static void disable_syncookie(void)
{
write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, 0);
}
static __u32 get_linum(void)
{
__u32 linum;
int err;
err = bpf_map_lookup_elem(linum_map, &index_zero, &linum);
CHECK(err == -1, "lookup_elem(linum_map)", "err:%d errno:%d\n",
err, errno);
return linum;
}
static void check_data(int type, sa_family_t family, const struct cmd *cmd,
int cli_fd)
{
struct data_check expected = {}, result;
union sa46 cli_sa;
socklen_t addrlen;
int err;
addrlen = sizeof(cli_sa);
err = getsockname(cli_fd, (struct sockaddr *)&cli_sa,
&addrlen);
CHECK(err == -1, "getsockname(cli_fd)", "err:%d errno:%d\n",
err, errno);
err = bpf_map_lookup_elem(data_check_map, &index_zero, &result);
CHECK(err == -1, "lookup_elem(data_check_map)", "err:%d errno:%d\n",
err, errno);
if (type == SOCK_STREAM) {
expected.len = MIN_TCPHDR_LEN;
expected.ip_protocol = IPPROTO_TCP;
} else {
expected.len = UDPHDR_LEN;
expected.ip_protocol = IPPROTO_UDP;
}
if (family == AF_INET6) {
expected.eth_protocol = htons(ETH_P_IPV6);
expected.bind_inany = !srv_sa.v6.sin6_addr.s6_addr32[3] &&
!srv_sa.v6.sin6_addr.s6_addr32[2] &&
!srv_sa.v6.sin6_addr.s6_addr32[1] &&
!srv_sa.v6.sin6_addr.s6_addr32[0];
memcpy(&expected.skb_addrs[0], cli_sa.v6.sin6_addr.s6_addr32,
sizeof(cli_sa.v6.sin6_addr));
memcpy(&expected.skb_addrs[4], &in6addr_loopback,
sizeof(in6addr_loopback));
expected.skb_ports[0] = cli_sa.v6.sin6_port;
expected.skb_ports[1] = srv_sa.v6.sin6_port;
} else {
expected.eth_protocol = htons(ETH_P_IP);
expected.bind_inany = !srv_sa.v4.sin_addr.s_addr;
expected.skb_addrs[0] = cli_sa.v4.sin_addr.s_addr;
expected.skb_addrs[1] = htonl(INADDR_LOOPBACK);
expected.skb_ports[0] = cli_sa.v4.sin_port;
expected.skb_ports[1] = srv_sa.v4.sin_port;
}
if (memcmp(&result, &expected, offsetof(struct data_check,
equal_check_end))) {
printf("unexpected data_check\n");
printf(" result: (0x%x, %u, %u)\n",
result.eth_protocol, result.ip_protocol,
result.bind_inany);
printf("expected: (0x%x, %u, %u)\n",
expected.eth_protocol, expected.ip_protocol,
expected.bind_inany);
CHECK(1, "data_check result != expected",
"bpf_prog_linum:%u\n", get_linum());
}
CHECK(!result.hash, "data_check result.hash empty",
"result.hash:%u", result.hash);
expected.len += cmd ? sizeof(*cmd) : 0;
if (type == SOCK_STREAM)
CHECK(expected.len > result.len, "expected.len > result.len",
"expected.len:%u result.len:%u bpf_prog_linum:%u\n",
expected.len, result.len, get_linum());
else
CHECK(expected.len != result.len, "expected.len != result.len",
"expected.len:%u result.len:%u bpf_prog_linum:%u\n",
expected.len, result.len, get_linum());
}
static void check_results(void)
{
__u32 results[NR_RESULTS];
__u32 i, broken = 0;
int err;
for (i = 0; i < NR_RESULTS; i++) {
err = bpf_map_lookup_elem(result_map, &i, &results[i]);
CHECK(err == -1, "lookup_elem(result_map)",
"i:%u err:%d errno:%d\n", i, err, errno);
}
for (i = 0; i < NR_RESULTS; i++) {
if (results[i] != expected_results[i]) {
broken = i;
break;
}
}
if (i == NR_RESULTS)
return;
printf("unexpected result\n");
printf(" result: [");
printf("%u", results[0]);
for (i = 1; i < NR_RESULTS; i++)
printf(", %u", results[i]);
printf("]\n");
printf("expected: [");
printf("%u", expected_results[0]);
for (i = 1; i < NR_RESULTS; i++)
printf(", %u", expected_results[i]);
printf("]\n");
CHECK(expected_results[broken] != results[broken],
"unexpected result",
"expected_results[%u] != results[%u] bpf_prog_linum:%u\n",
broken, broken, get_linum());
}
static int send_data(int type, sa_family_t family, void *data, size_t len,
enum result expected)
{
union sa46 cli_sa;
int fd, err;
fd = socket(family, type, 0);
CHECK(fd == -1, "socket()", "fd:%d errno:%d\n", fd, errno);
sa46_init_loopback(&cli_sa, family);
err = bind(fd, (struct sockaddr *)&cli_sa, sizeof(cli_sa));
CHECK(fd == -1, "bind(cli_sa)", "err:%d errno:%d\n", err, errno);
err = sendto(fd, data, len, MSG_FASTOPEN, (struct sockaddr *)&srv_sa,
sizeof(srv_sa));
CHECK(err != len && expected >= PASS,
"sendto()", "family:%u err:%d errno:%d expected:%d\n",
family, err, errno, expected);
return fd;
}
static void do_test(int type, sa_family_t family, struct cmd *cmd,
enum result expected)
{
int nev, srv_fd, cli_fd;
struct epoll_event ev;
struct cmd rcv_cmd;
ssize_t nread;
cli_fd = send_data(type, family, cmd, cmd ? sizeof(*cmd) : 0,
expected);
nev = epoll_wait(epfd, &ev, 1, expected >= PASS ? 5 : 0);
CHECK((nev <= 0 && expected >= PASS) ||
(nev > 0 && expected < PASS),
"nev <> expected",
"nev:%d expected:%d type:%d family:%d data:(%d, %d)\n",
nev, expected, type, family,
cmd ? cmd->reuseport_index : -1,
cmd ? cmd->pass_on_failure : -1);
check_results();
check_data(type, family, cmd, cli_fd);
if (expected < PASS)
return;
CHECK(expected != PASS_ERR_SK_SELECT_REUSEPORT &&
cmd->reuseport_index != ev.data.u32,
"check cmd->reuseport_index",
"cmd:(%u, %u) ev.data.u32:%u\n",
cmd->pass_on_failure, cmd->reuseport_index, ev.data.u32);
srv_fd = sk_fds[ev.data.u32];
if (type == SOCK_STREAM) {
int new_fd = accept(srv_fd, NULL, 0);
CHECK(new_fd == -1, "accept(srv_fd)",
"ev.data.u32:%u new_fd:%d errno:%d\n",
ev.data.u32, new_fd, errno);
nread = recv(new_fd, &rcv_cmd, sizeof(rcv_cmd), MSG_DONTWAIT);
CHECK(nread != sizeof(rcv_cmd),
"recv(new_fd)",
"ev.data.u32:%u nread:%zd sizeof(rcv_cmd):%zu errno:%d\n",
ev.data.u32, nread, sizeof(rcv_cmd), errno);
close(new_fd);
} else {
nread = recv(srv_fd, &rcv_cmd, sizeof(rcv_cmd), MSG_DONTWAIT);
CHECK(nread != sizeof(rcv_cmd),
"recv(sk_fds)",
"ev.data.u32:%u nread:%zd sizeof(rcv_cmd):%zu errno:%d\n",
ev.data.u32, nread, sizeof(rcv_cmd), errno);
}
close(cli_fd);
}
static void test_err_inner_map(int type, sa_family_t family)
{
struct cmd cmd = {
.reuseport_index = 0,
.pass_on_failure = 0,
};
printf("%s: ", __func__);
expected_results[DROP_ERR_INNER_MAP]++;
do_test(type, family, &cmd, DROP_ERR_INNER_MAP);
printf("OK\n");
}
static void test_err_skb_data(int type, sa_family_t family)
{
printf("%s: ", __func__);
expected_results[DROP_ERR_SKB_DATA]++;
do_test(type, family, NULL, DROP_ERR_SKB_DATA);
printf("OK\n");
}
static void test_err_sk_select_port(int type, sa_family_t family)
{
struct cmd cmd = {
.reuseport_index = REUSEPORT_ARRAY_SIZE,
.pass_on_failure = 0,
};
printf("%s: ", __func__);
expected_results[DROP_ERR_SK_SELECT_REUSEPORT]++;
do_test(type, family, &cmd, DROP_ERR_SK_SELECT_REUSEPORT);
printf("OK\n");
}
static void test_pass(int type, sa_family_t family)
{
struct cmd cmd;
int i;
printf("%s: ", __func__);
cmd.pass_on_failure = 0;
for (i = 0; i < REUSEPORT_ARRAY_SIZE; i++) {
expected_results[PASS]++;
cmd.reuseport_index = i;
do_test(type, family, &cmd, PASS);
}
printf("OK\n");
}
static void test_syncookie(int type, sa_family_t family)
{
int err, tmp_index = 1;
struct cmd cmd = {
.reuseport_index = 0,
.pass_on_failure = 0,
};
if (type != SOCK_STREAM)
return;
printf("%s: ", __func__);
/*
* +1 for TCP-SYN and
* +1 for the TCP-ACK (ack the syncookie)
*/
expected_results[PASS] += 2;
enable_syncookie();
/*
* Simulate TCP-SYN and TCP-ACK are handled by two different sk:
* TCP-SYN: select sk_fds[tmp_index = 1] tmp_index is from the
* tmp_index_ovr_map
* TCP-ACK: select sk_fds[reuseport_index = 0] reuseport_index
* is from the cmd.reuseport_index
*/
err = bpf_map_update_elem(tmp_index_ovr_map, &index_zero,
&tmp_index, BPF_ANY);
CHECK(err == -1, "update_elem(tmp_index_ovr_map, 0, 1)",
"err:%d errno:%d\n", err, errno);
do_test(type, family, &cmd, PASS);
err = bpf_map_lookup_elem(tmp_index_ovr_map, &index_zero,
&tmp_index);
CHECK(err == -1 || tmp_index != -1,
"lookup_elem(tmp_index_ovr_map)",
"err:%d errno:%d tmp_index:%d\n",
err, errno, tmp_index);
disable_syncookie();
printf("OK\n");
}
static void test_pass_on_err(int type, sa_family_t family)
{
struct cmd cmd = {
.reuseport_index = REUSEPORT_ARRAY_SIZE,
.pass_on_failure = 1,
};
printf("%s: ", __func__);
expected_results[PASS_ERR_SK_SELECT_REUSEPORT] += 1;
do_test(type, family, &cmd, PASS_ERR_SK_SELECT_REUSEPORT);
printf("OK\n");
}
static void prepare_sk_fds(int type, sa_family_t family, bool inany)
{
const int first = REUSEPORT_ARRAY_SIZE - 1;
int i, err, optval = 1;
struct epoll_event ev;
socklen_t addrlen;
if (inany)
sa46_init_inany(&srv_sa, family);
else
sa46_init_loopback(&srv_sa, family);
addrlen = sizeof(srv_sa);
/*
* The sk_fds[] is filled from the back such that the order
* is exactly opposite to the (struct sock_reuseport *)reuse->socks[].
*/
for (i = first; i >= 0; i--) {
sk_fds[i] = socket(family, type, 0);
CHECK(sk_fds[i] == -1, "socket()", "sk_fds[%d]:%d errno:%d\n",
i, sk_fds[i], errno);
err = setsockopt(sk_fds[i], SOL_SOCKET, SO_REUSEPORT,
&optval, sizeof(optval));
CHECK(err == -1, "setsockopt(SO_REUSEPORT)",
"sk_fds[%d] err:%d errno:%d\n",
i, err, errno);
if (i == first) {
err = setsockopt(sk_fds[i], SOL_SOCKET,
SO_ATTACH_REUSEPORT_EBPF,
&select_by_skb_data_prog,
sizeof(select_by_skb_data_prog));
CHECK(err == -1, "setsockopt(SO_ATTACH_REUEPORT_EBPF)",
"err:%d errno:%d\n", err, errno);
}
err = bind(sk_fds[i], (struct sockaddr *)&srv_sa, addrlen);
CHECK(err == -1, "bind()", "sk_fds[%d] err:%d errno:%d\n",
i, err, errno);
if (type == SOCK_STREAM) {
err = listen(sk_fds[i], 10);
CHECK(err == -1, "listen()",
"sk_fds[%d] err:%d errno:%d\n",
i, err, errno);
}
err = bpf_map_update_elem(reuseport_array, &i, &sk_fds[i],
BPF_NOEXIST);
CHECK(err == -1, "update_elem(reuseport_array)",
"sk_fds[%d] err:%d errno:%d\n", i, err, errno);
if (i == first) {
socklen_t addrlen = sizeof(srv_sa);
err = getsockname(sk_fds[i], (struct sockaddr *)&srv_sa,
&addrlen);
CHECK(err == -1, "getsockname()",
"sk_fds[%d] err:%d errno:%d\n", i, err, errno);
}
}
epfd = epoll_create(1);
CHECK(epfd == -1, "epoll_create(1)",
"epfd:%d errno:%d\n", epfd, errno);
ev.events = EPOLLIN;
for (i = 0; i < REUSEPORT_ARRAY_SIZE; i++) {
ev.data.u32 = i;
err = epoll_ctl(epfd, EPOLL_CTL_ADD, sk_fds[i], &ev);
CHECK(err, "epoll_ctl(EPOLL_CTL_ADD)", "sk_fds[%d]\n", i);
}
}
static void setup_per_test(int type, unsigned short family, bool inany)
{
int ovr = -1, err;
prepare_sk_fds(type, family, inany);
err = bpf_map_update_elem(tmp_index_ovr_map, &index_zero, &ovr,
BPF_ANY);
CHECK(err == -1, "update_elem(tmp_index_ovr_map, 0, -1)",
"err:%d errno:%d\n", err, errno);
}
static void cleanup_per_test(void)
{
int i, err, zero = 0;
memset(expected_results, 0, sizeof(expected_results));
for (i = 0; i < NR_RESULTS; i++) {
err = bpf_map_update_elem(result_map, &i, &zero, BPF_ANY);
CHECK(err, "reset elem in result_map",
"i:%u err:%d errno:%d\n", i, err, errno);
}
err = bpf_map_update_elem(linum_map, &zero, &zero, BPF_ANY);
CHECK(err, "reset line number in linum_map", "err:%d errno:%d\n",
err, errno);
for (i = 0; i < REUSEPORT_ARRAY_SIZE; i++)
close(sk_fds[i]);
close(epfd);
err = bpf_map_delete_elem(outer_map, &index_zero);
CHECK(err == -1, "delete_elem(outer_map)",
"err:%d errno:%d\n", err, errno);
}
static void cleanup(void)
{
close(outer_map);
close(reuseport_array);
bpf_object__close(obj);
}
static void test_all(void)
{
/* Extra SOCK_STREAM to test bind_inany==true */
const int types[] = { SOCK_STREAM, SOCK_DGRAM, SOCK_STREAM };
const char * const type_strings[] = { "TCP", "UDP", "TCP" };
const char * const family_strings[] = { "IPv6", "IPv4" };
const unsigned short families[] = { AF_INET6, AF_INET };
const bool bind_inany[] = { false, false, true };
int t, f, err;
for (f = 0; f < ARRAY_SIZE(families); f++) {
unsigned short family = families[f];
for (t = 0; t < ARRAY_SIZE(types); t++) {
bool inany = bind_inany[t];
int type = types[t];
printf("######## %s/%s %s ########\n",
family_strings[f], type_strings[t],
inany ? " INANY " : "LOOPBACK");
setup_per_test(type, family, inany);
test_err_inner_map(type, family);
/* Install reuseport_array to the outer_map */
err = bpf_map_update_elem(outer_map, &index_zero,
&reuseport_array, BPF_ANY);
CHECK(err == -1, "update_elem(outer_map)",
"err:%d errno:%d\n", err, errno);
test_err_skb_data(type, family);
test_err_sk_select_port(type, family);
test_pass(type, family);
test_syncookie(type, family);
test_pass_on_err(type, family);
cleanup_per_test();
printf("\n");
}
}
}
int main(int argc, const char **argv)
{
create_maps();
prepare_bpf_obj();
saved_tcp_fo = read_int_sysctl(TCP_FO_SYSCTL);
saved_tcp_syncookie = read_int_sysctl(TCP_SYNCOOKIE_SYSCTL);
enable_fastopen();
disable_syncookie();
atexit(restore_sysctls);
test_all();
cleanup();
return 0;
}
@@ -0,0 +1,36 @@
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (c) 2018 Facebook */
#ifndef __TEST_SELECT_REUSEPORT_COMMON_H
#define __TEST_SELECT_REUSEPORT_COMMON_H
#include <linux/types.h>
enum result {
DROP_ERR_INNER_MAP,
DROP_ERR_SKB_DATA,
DROP_ERR_SK_SELECT_REUSEPORT,
DROP_MISC,
PASS,
PASS_ERR_SK_SELECT_REUSEPORT,
NR_RESULTS,
};
struct cmd {
__u32 reuseport_index;
__u32 pass_on_failure;
};
struct data_check {
__u32 ip_protocol;
__u32 skb_addrs[8];
__u16 skb_ports[2];
__u16 eth_protocol;
__u8 bind_inany;
__u8 equal_check_end[0];
__u32 len;
__u32 hash;
};
#endif
@@ -0,0 +1,180 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2018 Facebook */
#include <stdlib.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/bpf.h>
#include <linux/types.h>
#include <linux/if_ether.h>
#include "bpf_endian.h"
#include "bpf_helpers.h"
#include "test_select_reuseport_common.h"
int _version SEC("version") = 1;
#ifndef offsetof
#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER)
#endif
struct bpf_map_def SEC("maps") outer_map = {
.type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
.key_size = sizeof(__u32),
.value_size = sizeof(__u32),
.max_entries = 1,
};
struct bpf_map_def SEC("maps") result_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(__u32),
.max_entries = NR_RESULTS,
};
struct bpf_map_def SEC("maps") tmp_index_ovr_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(int),
.max_entries = 1,
};
struct bpf_map_def SEC("maps") linum_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(__u32),
.max_entries = 1,
};
struct bpf_map_def SEC("maps") data_check_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(struct data_check),
.max_entries = 1,
};
#define GOTO_DONE(_result) ({ \
result = (_result); \
linum = __LINE__; \
goto done; \
})
SEC("select_by_skb_data")
int _select_by_skb_data(struct sk_reuseport_md *reuse_md)
{
__u32 linum, index = 0, flags = 0, index_zero = 0;
__u32 *result_cnt, *linum_value;
struct data_check data_check = {};
struct cmd *cmd, cmd_copy;
void *data, *data_end;
void *reuseport_array;
enum result result;
int *index_ovr;
int err;
data = reuse_md->data;
data_end = reuse_md->data_end;
data_check.len = reuse_md->len;
data_check.eth_protocol = reuse_md->eth_protocol;
data_check.ip_protocol = reuse_md->ip_protocol;
data_check.hash = reuse_md->hash;
data_check.bind_inany = reuse_md->bind_inany;
if (data_check.eth_protocol == bpf_htons(ETH_P_IP)) {
if (bpf_skb_load_bytes_relative(reuse_md,
offsetof(struct iphdr, saddr),
data_check.skb_addrs, 8,
BPF_HDR_START_NET))
GOTO_DONE(DROP_MISC);
} else {
if (bpf_skb_load_bytes_relative(reuse_md,
offsetof(struct ipv6hdr, saddr),
data_check.skb_addrs, 32,
BPF_HDR_START_NET))
GOTO_DONE(DROP_MISC);
}
/*
* The ip_protocol could be a compile time decision
* if the bpf_prog.o is dedicated to either TCP or
* UDP.
*
* Otherwise, reuse_md->ip_protocol or
* the protocol field in the iphdr can be used.
*/
if (data_check.ip_protocol == IPPROTO_TCP) {
struct tcphdr *th = data;
if (th + 1 > data_end)
GOTO_DONE(DROP_MISC);
data_check.skb_ports[0] = th->source;
data_check.skb_ports[1] = th->dest;
if ((th->doff << 2) + sizeof(*cmd) > data_check.len)
GOTO_DONE(DROP_ERR_SKB_DATA);
if (bpf_skb_load_bytes(reuse_md, th->doff << 2, &cmd_copy,
sizeof(cmd_copy)))
GOTO_DONE(DROP_MISC);
cmd = &cmd_copy;
} else if (data_check.ip_protocol == IPPROTO_UDP) {
struct udphdr *uh = data;
if (uh + 1 > data_end)
GOTO_DONE(DROP_MISC);
data_check.skb_ports[0] = uh->source;
data_check.skb_ports[1] = uh->dest;
if (sizeof(struct udphdr) + sizeof(*cmd) > data_check.len)
GOTO_DONE(DROP_ERR_SKB_DATA);
if (data + sizeof(struct udphdr) + sizeof(*cmd) > data_end) {
if (bpf_skb_load_bytes(reuse_md, sizeof(struct udphdr),
&cmd_copy, sizeof(cmd_copy)))
GOTO_DONE(DROP_MISC);
cmd = &cmd_copy;
} else {
cmd = data + sizeof(struct udphdr);
}
} else {
GOTO_DONE(DROP_MISC);
}
reuseport_array = bpf_map_lookup_elem(&outer_map, &index_zero);
if (!reuseport_array)
GOTO_DONE(DROP_ERR_INNER_MAP);
index = cmd->reuseport_index;
index_ovr = bpf_map_lookup_elem(&tmp_index_ovr_map, &index_zero);
if (!index_ovr)
GOTO_DONE(DROP_MISC);
if (*index_ovr != -1) {
index = *index_ovr;
*index_ovr = -1;
}
err = bpf_sk_select_reuseport(reuse_md, reuseport_array, &index,
flags);
if (!err)
GOTO_DONE(PASS);
if (cmd->pass_on_failure)
GOTO_DONE(PASS_ERR_SK_SELECT_REUSEPORT);
else
GOTO_DONE(DROP_ERR_SK_SELECT_REUSEPORT);
done:
result_cnt = bpf_map_lookup_elem(&result_map, &result);
if (!result_cnt)
return SK_DROP;
bpf_map_update_elem(&linum_map, &index_zero, &linum, BPF_ANY);
bpf_map_update_elem(&data_check_map, &index_zero, &data_check, BPF_ANY);
(*result_cnt)++;
return result < PASS ? SK_DROP : SK_PASS;
}
char _license[] SEC("license") = "GPL";
+62
View File
@@ -0,0 +1,62 @@
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
# Copyright (c) 2018 Facebook
set -eu
wait_for_ip()
{
local _i
echo -n "Wait for testing link-local IP to become available "
for _i in $(seq ${MAX_PING_TRIES}); do
echo -n "."
if ping -6 -q -c 1 -W 1 ff02::1%${TEST_IF} >/dev/null 2>&1; then
echo " OK"
return
fi
sleep 1
done
echo 1>&2 "ERROR: Timeout waiting for test IP to become available."
exit 1
}
setup()
{
# Create testing interfaces not to interfere with current environment.
ip link add dev ${TEST_IF} type veth peer name ${TEST_IF_PEER}
ip link set ${TEST_IF} up
ip link set ${TEST_IF_PEER} up
wait_for_ip
tc qdisc add dev ${TEST_IF} clsact
tc filter add dev ${TEST_IF} egress bpf obj ${BPF_PROG_OBJ} \
sec ${BPF_PROG_SECTION} da
BPF_PROG_ID=$(tc filter show dev ${TEST_IF} egress | \
awk '/ id / {sub(/.* id /, "", $0); print($1)}')
}
cleanup()
{
ip link del ${TEST_IF} 2>/dev/null || :
ip link del ${TEST_IF_PEER} 2>/dev/null || :
}
main()
{
trap cleanup EXIT 2 3 6 15
setup
${PROG} ${TEST_IF} ${BPF_PROG_ID}
}
DIR=$(dirname $0)
TEST_IF="test_cgid_1"
TEST_IF_PEER="test_cgid_2"
MAX_PING_TRIES=5
BPF_PROG_OBJ="${DIR}/test_skb_cgroup_id_kern.o"
BPF_PROG_SECTION="cgroup_id_logger"
BPF_PROG_ID=0
PROG="${DIR}/test_skb_cgroup_id_user"
main
@@ -0,0 +1,47 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2018 Facebook
#include <linux/bpf.h>
#include <linux/pkt_cls.h>
#include <string.h>
#include "bpf_helpers.h"
#define NUM_CGROUP_LEVELS 4
struct bpf_map_def SEC("maps") cgroup_ids = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(__u64),
.max_entries = NUM_CGROUP_LEVELS,
};
static __always_inline void log_nth_level(struct __sk_buff *skb, __u32 level)
{
__u64 id;
/* [1] &level passed to external function that may change it, it's
* incompatible with loop unroll.
*/
id = bpf_skb_ancestor_cgroup_id(skb, level);
bpf_map_update_elem(&cgroup_ids, &level, &id, 0);
}
SEC("cgroup_id_logger")
int log_cgroup_id(struct __sk_buff *skb)
{
/* Loop unroll can't be used here due to [1]. Unrolling manually.
* Number of calls should be in sync with NUM_CGROUP_LEVELS.
*/
log_nth_level(skb, 0);
log_nth_level(skb, 1);
log_nth_level(skb, 2);
log_nth_level(skb, 3);
return TC_ACT_OK;
}
int _version SEC("version") = 1;
char _license[] SEC("license") = "GPL";
@@ -0,0 +1,187 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2018 Facebook
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <arpa/inet.h>
#include <net/if.h>
#include <netinet/in.h>
#include <sys/socket.h>
#include <sys/types.h>
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
#include "bpf_rlimit.h"
#include "cgroup_helpers.h"
#define CGROUP_PATH "/skb_cgroup_test"
#define NUM_CGROUP_LEVELS 4
/* RFC 4291, Section 2.7.1 */
#define LINKLOCAL_MULTICAST "ff02::1"
static int mk_dst_addr(const char *ip, const char *iface,
struct sockaddr_in6 *dst)
{
memset(dst, 0, sizeof(*dst));
dst->sin6_family = AF_INET6;
dst->sin6_port = htons(1025);
if (inet_pton(AF_INET6, ip, &dst->sin6_addr) != 1) {
log_err("Invalid IPv6: %s", ip);
return -1;
}
dst->sin6_scope_id = if_nametoindex(iface);
if (!dst->sin6_scope_id) {
log_err("Failed to get index of iface: %s", iface);
return -1;
}
return 0;
}
static int send_packet(const char *iface)
{
struct sockaddr_in6 dst;
char msg[] = "msg";
int err = 0;
int fd = -1;
if (mk_dst_addr(LINKLOCAL_MULTICAST, iface, &dst))
goto err;
fd = socket(AF_INET6, SOCK_DGRAM, 0);
if (fd == -1) {
log_err("Failed to create UDP socket");
goto err;
}
if (sendto(fd, &msg, sizeof(msg), 0, (const struct sockaddr *)&dst,
sizeof(dst)) == -1) {
log_err("Failed to send datagram");
goto err;
}
goto out;
err:
err = -1;
out:
if (fd >= 0)
close(fd);
return err;
}
int get_map_fd_by_prog_id(int prog_id)
{
struct bpf_prog_info info = {};
__u32 info_len = sizeof(info);
__u32 map_ids[1];
int prog_fd = -1;
int map_fd = -1;
prog_fd = bpf_prog_get_fd_by_id(prog_id);
if (prog_fd < 0) {
log_err("Failed to get fd by prog id %d", prog_id);
goto err;
}
info.nr_map_ids = 1;
info.map_ids = (__u64) (unsigned long) map_ids;
if (bpf_obj_get_info_by_fd(prog_fd, &info, &info_len)) {
log_err("Failed to get info by prog fd %d", prog_fd);
goto err;
}
if (!info.nr_map_ids) {
log_err("No maps found for prog fd %d", prog_fd);
goto err;
}
map_fd = bpf_map_get_fd_by_id(map_ids[0]);
if (map_fd < 0)
log_err("Failed to get fd by map id %d", map_ids[0]);
err:
if (prog_fd >= 0)
close(prog_fd);
return map_fd;
}
int check_ancestor_cgroup_ids(int prog_id)
{
__u64 actual_ids[NUM_CGROUP_LEVELS], expected_ids[NUM_CGROUP_LEVELS];
__u32 level;
int err = 0;
int map_fd;
expected_ids[0] = 0x100000001; /* root cgroup */
expected_ids[1] = get_cgroup_id("");
expected_ids[2] = get_cgroup_id(CGROUP_PATH);
expected_ids[3] = 0; /* non-existent cgroup */
map_fd = get_map_fd_by_prog_id(prog_id);
if (map_fd < 0)
goto err;
for (level = 0; level < NUM_CGROUP_LEVELS; ++level) {
if (bpf_map_lookup_elem(map_fd, &level, &actual_ids[level])) {
log_err("Failed to lookup key %d", level);
goto err;
}
if (actual_ids[level] != expected_ids[level]) {
log_err("%llx (actual) != %llx (expected), level: %u\n",
actual_ids[level], expected_ids[level], level);
goto err;
}
}
goto out;
err:
err = -1;
out:
if (map_fd >= 0)
close(map_fd);
return err;
}
int main(int argc, char **argv)
{
int cgfd = -1;
int err = 0;
if (argc < 3) {
fprintf(stderr, "Usage: %s iface prog_id\n", argv[0]);
exit(EXIT_FAILURE);
}
if (setup_cgroup_environment())
goto err;
cgfd = create_and_get_cgroup(CGROUP_PATH);
if (!cgfd)
goto err;
if (join_cgroup(CGROUP_PATH))
goto err;
if (send_packet(argv[1]))
goto err;
if (check_ancestor_cgroup_ids(atoi(argv[2])))
goto err;
goto out;
err:
err = -1;
out:
close(cgfd);
cleanup_cgroup_environment();
printf("[%s]\n", err ? "FAIL" : "PASS");
return err;
}
+480
View File
@@ -0,0 +1,480 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2018 Facebook
#include <stdio.h>
#include <unistd.h>
#include <arpa/inet.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <linux/filter.h>
#include <bpf/bpf.h>
#include "cgroup_helpers.h"
#include "bpf_endian.h"
#include "bpf_rlimit.h"
#include "bpf_util.h"
#define CG_PATH "/foo"
#define MAX_INSNS 512
char bpf_log_buf[BPF_LOG_BUF_SIZE];
struct sock_test {
const char *descr;
/* BPF prog properties */
struct bpf_insn insns[MAX_INSNS];
enum bpf_attach_type expected_attach_type;
enum bpf_attach_type attach_type;
/* Socket properties */
int domain;
int type;
/* Endpoint to bind() to */
const char *ip;
unsigned short port;
/* Expected test result */
enum {
LOAD_REJECT,
ATTACH_REJECT,
BIND_REJECT,
SUCCESS,
} result;
};
static struct sock_test tests[] = {
{
"bind4 load with invalid access: src_ip6",
.insns = {
BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock, src_ip6[0])),
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET4_POST_BIND,
BPF_CGROUP_INET4_POST_BIND,
0,
0,
NULL,
0,
LOAD_REJECT,
},
{
"bind4 load with invalid access: mark",
.insns = {
BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock, mark)),
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET4_POST_BIND,
BPF_CGROUP_INET4_POST_BIND,
0,
0,
NULL,
0,
LOAD_REJECT,
},
{
"bind6 load with invalid access: src_ip4",
.insns = {
BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock, src_ip4)),
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET6_POST_BIND,
BPF_CGROUP_INET6_POST_BIND,
0,
0,
NULL,
0,
LOAD_REJECT,
},
{
"sock_create load with invalid access: src_port",
.insns = {
BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock, src_port)),
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET_SOCK_CREATE,
BPF_CGROUP_INET_SOCK_CREATE,
0,
0,
NULL,
0,
LOAD_REJECT,
},
{
"sock_create load w/o expected_attach_type (compat mode)",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
0,
BPF_CGROUP_INET_SOCK_CREATE,
AF_INET,
SOCK_STREAM,
"127.0.0.1",
8097,
SUCCESS,
},
{
"sock_create load w/ expected_attach_type",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET_SOCK_CREATE,
BPF_CGROUP_INET_SOCK_CREATE,
AF_INET,
SOCK_STREAM,
"127.0.0.1",
8097,
SUCCESS,
},
{
"attach type mismatch bind4 vs bind6",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET4_POST_BIND,
BPF_CGROUP_INET6_POST_BIND,
0,
0,
NULL,
0,
ATTACH_REJECT,
},
{
"attach type mismatch bind6 vs bind4",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET6_POST_BIND,
BPF_CGROUP_INET4_POST_BIND,
0,
0,
NULL,
0,
ATTACH_REJECT,
},
{
"attach type mismatch default vs bind4",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
0,
BPF_CGROUP_INET4_POST_BIND,
0,
0,
NULL,
0,
ATTACH_REJECT,
},
{
"attach type mismatch bind6 vs sock_create",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET6_POST_BIND,
BPF_CGROUP_INET_SOCK_CREATE,
0,
0,
NULL,
0,
ATTACH_REJECT,
},
{
"bind4 reject all",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET4_POST_BIND,
BPF_CGROUP_INET4_POST_BIND,
AF_INET,
SOCK_STREAM,
"0.0.0.0",
0,
BIND_REJECT,
},
{
"bind6 reject all",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET6_POST_BIND,
BPF_CGROUP_INET6_POST_BIND,
AF_INET6,
SOCK_STREAM,
"::",
0,
BIND_REJECT,
},
{
"bind6 deny specific IP & port",
.insns = {
BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
/* if (ip == expected && port == expected) */
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock, src_ip6[3])),
BPF_JMP_IMM(BPF_JNE, BPF_REG_7,
__bpf_constant_ntohl(0x00000001), 4),
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock, src_port)),
BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x2001, 2),
/* return DENY; */
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_JMP_A(1),
/* else return ALLOW; */
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET6_POST_BIND,
BPF_CGROUP_INET6_POST_BIND,
AF_INET6,
SOCK_STREAM,
"::1",
8193,
BIND_REJECT,
},
{
"bind4 allow specific IP & port",
.insns = {
BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
/* if (ip == expected && port == expected) */
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock, src_ip4)),
BPF_JMP_IMM(BPF_JNE, BPF_REG_7,
__bpf_constant_ntohl(0x7F000001), 4),
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock, src_port)),
BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x1002, 2),
/* return ALLOW; */
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_JMP_A(1),
/* else return DENY; */
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET4_POST_BIND,
BPF_CGROUP_INET4_POST_BIND,
AF_INET,
SOCK_STREAM,
"127.0.0.1",
4098,
SUCCESS,
},
{
"bind4 allow all",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET4_POST_BIND,
BPF_CGROUP_INET4_POST_BIND,
AF_INET,
SOCK_STREAM,
"0.0.0.0",
0,
SUCCESS,
},
{
"bind6 allow all",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
BPF_CGROUP_INET6_POST_BIND,
BPF_CGROUP_INET6_POST_BIND,
AF_INET6,
SOCK_STREAM,
"::",
0,
SUCCESS,
},
};
static size_t probe_prog_length(const struct bpf_insn *fp)
{
size_t len;
for (len = MAX_INSNS - 1; len > 0; --len)
if (fp[len].code != 0 || fp[len].imm != 0)
break;
return len + 1;
}
static int load_sock_prog(const struct bpf_insn *prog,
enum bpf_attach_type attach_type)
{
struct bpf_load_program_attr attr;
memset(&attr, 0, sizeof(struct bpf_load_program_attr));
attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK;
attr.expected_attach_type = attach_type;
attr.insns = prog;
attr.insns_cnt = probe_prog_length(attr.insns);
attr.license = "GPL";
return bpf_load_program_xattr(&attr, bpf_log_buf, BPF_LOG_BUF_SIZE);
}
static int attach_sock_prog(int cgfd, int progfd,
enum bpf_attach_type attach_type)
{
return bpf_prog_attach(progfd, cgfd, attach_type, BPF_F_ALLOW_OVERRIDE);
}
static int bind_sock(int domain, int type, const char *ip, unsigned short port)
{
struct sockaddr_storage addr;
struct sockaddr_in6 *addr6;
struct sockaddr_in *addr4;
int sockfd = -1;
socklen_t len;
int err = 0;
sockfd = socket(domain, type, 0);
if (sockfd < 0)
goto err;
memset(&addr, 0, sizeof(addr));
if (domain == AF_INET) {
len = sizeof(struct sockaddr_in);
addr4 = (struct sockaddr_in *)&addr;
addr4->sin_family = domain;
addr4->sin_port = htons(port);
if (inet_pton(domain, ip, (void *)&addr4->sin_addr) != 1)
goto err;
} else if (domain == AF_INET6) {
len = sizeof(struct sockaddr_in6);
addr6 = (struct sockaddr_in6 *)&addr;
addr6->sin6_family = domain;
addr6->sin6_port = htons(port);
if (inet_pton(domain, ip, (void *)&addr6->sin6_addr) != 1)
goto err;
} else {
goto err;
}
if (bind(sockfd, (const struct sockaddr *)&addr, len) == -1)
goto err;
goto out;
err:
err = -1;
out:
close(sockfd);
return err;
}
static int run_test_case(int cgfd, const struct sock_test *test)
{
int progfd = -1;
int err = 0;
printf("Test case: %s .. ", test->descr);
progfd = load_sock_prog(test->insns, test->expected_attach_type);
if (progfd < 0) {
if (test->result == LOAD_REJECT)
goto out;
else
goto err;
}
if (attach_sock_prog(cgfd, progfd, test->attach_type) == -1) {
if (test->result == ATTACH_REJECT)
goto out;
else
goto err;
}
if (bind_sock(test->domain, test->type, test->ip, test->port) == -1) {
/* sys_bind() may fail for different reasons, errno has to be
* checked to confirm that BPF program rejected it.
*/
if (test->result == BIND_REJECT && errno == EPERM)
goto out;
else
goto err;
}
if (test->result != SUCCESS)
goto err;
goto out;
err:
err = -1;
out:
/* Detaching w/o checking return code: best effort attempt. */
if (progfd != -1)
bpf_prog_detach(cgfd, test->attach_type);
close(progfd);
printf("[%s]\n", err ? "FAIL" : "PASS");
return err;
}
static int run_tests(int cgfd)
{
int passes = 0;
int fails = 0;
int i;
for (i = 0; i < ARRAY_SIZE(tests); ++i) {
if (run_test_case(cgfd, &tests[i]))
++fails;
else
++passes;
}
printf("Summary: %d PASSED, %d FAILED\n", passes, fails);
return fails ? -1 : 0;
}
int main(int argc, char **argv)
{
int cgfd = -1;
int err = 0;
if (setup_cgroup_environment())
goto err;
cgfd = create_and_get_cgroup(CG_PATH);
if (!cgfd)
goto err;
if (join_cgroup(CG_PATH))
goto err;
if (run_tests(cgfd))
goto err;
goto out;
err:
err = -1;
out:
close(cgfd);
cleanup_cgroup_environment();
return err;
}
File diff suppressed because it is too large. Load diff
+57
View File
@@ -0,0 +1,57 @@
#!/bin/sh
set -eu
ping_once()
{
ping -${1} -q -c 1 -W 1 ${2%%/*} >/dev/null 2>&1
}
wait_for_ip()
{
local _i
echo -n "Wait for testing IPv4/IPv6 to become available "
for _i in $(seq ${MAX_PING_TRIES}); do
echo -n "."
if ping_once 4 ${TEST_IPv4} && ping_once 6 ${TEST_IPv6}; then
echo " OK"
return
fi
done
echo 1>&2 "ERROR: Timeout waiting for test IP to become available."
exit 1
}
setup()
{
# Create testing interfaces not to interfere with current environment.
ip link add dev ${TEST_IF} type veth peer name ${TEST_IF_PEER}
ip link set ${TEST_IF} up
ip link set ${TEST_IF_PEER} up
ip -4 addr add ${TEST_IPv4} dev ${TEST_IF}
ip -6 addr add ${TEST_IPv6} dev ${TEST_IF}
wait_for_ip
}
cleanup()
{
ip link del ${TEST_IF} 2>/dev/null || :
ip link del ${TEST_IF_PEER} 2>/dev/null || :
}
main()
{
trap cleanup EXIT 2 3 6 15
setup
./test_sock_addr setup_done
}
BASENAME=$(basename $0 .sh)
TEST_IF="${BASENAME}1"
TEST_IF_PEER="${BASENAME}2"
TEST_IPv4="127.0.0.4/8"
TEST_IPv6="::6/128"
MAX_PING_TRIES=5
main
@@ -0,0 +1,225 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2018 Facebook
#include <string.h>
#include <unistd.h>
#include <arpa/inet.h>
#include <netinet/in.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
#include "bpf_rlimit.h"
#include "cgroup_helpers.h"
#define CG_PATH "/foo"
#define SOCKET_COOKIE_PROG "./socket_cookie_prog.o"
static int start_server(void)
{
struct sockaddr_in6 addr;
int fd;
fd = socket(AF_INET6, SOCK_STREAM, 0);
if (fd == -1) {
log_err("Failed to create server socket");
goto out;
}
memset(&addr, 0, sizeof(addr));
addr.sin6_family = AF_INET6;
addr.sin6_addr = in6addr_loopback;
addr.sin6_port = 0;
if (bind(fd, (const struct sockaddr *)&addr, sizeof(addr)) == -1) {
log_err("Failed to bind server socket");
goto close_out;
}
if (listen(fd, 128) == -1) {
log_err("Failed to listen on server socket");
goto close_out;
}
goto out;
close_out:
close(fd);
fd = -1;
out:
return fd;
}
static int connect_to_server(int server_fd)
{
struct sockaddr_storage addr;
socklen_t len = sizeof(addr);
int fd;
fd = socket(AF_INET6, SOCK_STREAM, 0);
if (fd == -1) {
log_err("Failed to create client socket");
goto out;
}
if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) {
log_err("Failed to get server addr");
goto close_out;
}
if (connect(fd, (const struct sockaddr *)&addr, len) == -1) {
log_err("Fail to connect to server");
goto close_out;
}
goto out;
close_out:
close(fd);
fd = -1;
out:
return fd;
}
static int validate_map(struct bpf_map *map, int client_fd)
{
__u32 cookie_expected_value;
struct sockaddr_in6 addr;
socklen_t len = sizeof(addr);
__u32 cookie_value;
__u64 cookie_key;
int err = 0;
int map_fd;
if (!map) {
log_err("Map not found in BPF object");
goto err;
}
map_fd = bpf_map__fd(map);
err = bpf_map_get_next_key(map_fd, NULL, &cookie_key);
if (err) {
log_err("Can't get cookie key from map");
goto out;
}
err = bpf_map_lookup_elem(map_fd, &cookie_key, &cookie_value);
if (err) {
log_err("Can't get cookie value from map");
goto out;
}
err = getsockname(client_fd, (struct sockaddr *)&addr, &len);
if (err) {
log_err("Can't get client local addr");
goto out;
}
cookie_expected_value = (ntohs(addr.sin6_port) << 8) | 0xFF;
if (cookie_value != cookie_expected_value) {
log_err("Unexpected value in map: %x != %x", cookie_value,
cookie_expected_value);
goto err;
}
goto out;
err:
err = -1;
out:
return err;
}
static int run_test(int cgfd)
{
enum bpf_attach_type attach_type;
struct bpf_prog_load_attr attr;
struct bpf_program *prog;
struct bpf_object *pobj;
const char *prog_name;
int server_fd = -1;
int client_fd = -1;
int prog_fd = -1;
int err = 0;
memset(&attr, 0, sizeof(attr));
attr.file = SOCKET_COOKIE_PROG;
attr.prog_type = BPF_PROG_TYPE_UNSPEC;
err = bpf_prog_load_xattr(&attr, &pobj, &prog_fd);
if (err) {
log_err("Failed to load %s", attr.file);
goto out;
}
bpf_object__for_each_program(prog, pobj) {
prog_name = bpf_program__title(prog, /*needs_copy*/ false);
if (strcmp(prog_name, "cgroup/connect6") == 0) {
attach_type = BPF_CGROUP_INET6_CONNECT;
} else if (strcmp(prog_name, "sockops") == 0) {
attach_type = BPF_CGROUP_SOCK_OPS;
} else {
log_err("Unexpected prog: %s", prog_name);
goto err;
}
err = bpf_prog_attach(bpf_program__fd(prog), cgfd, attach_type,
BPF_F_ALLOW_OVERRIDE);
if (err) {
log_err("Failed to attach prog %s", prog_name);
goto out;
}
}
server_fd = start_server();
if (server_fd == -1)
goto err;
client_fd = connect_to_server(server_fd);
if (client_fd == -1)
goto err;
if (validate_map(bpf_map__next(NULL, pobj), client_fd))
goto err;
goto out;
err:
err = -1;
out:
close(client_fd);
close(server_fd);
bpf_object__close(pobj);
printf("%s\n", err ? "FAILED" : "PASSED");
return err;
}
int main(int argc, char **argv)
{
int cgfd = -1;
int err = 0;
if (setup_cgroup_environment())
goto err;
cgfd = create_and_get_cgroup(CG_PATH);
if (!cgfd)
goto err;
if (join_cgroup(CG_PATH))
goto err;
if (run_test(cgfd))
goto err;
goto out;
err:
err = -1;
out:
close(cgfd);
cleanup_cgroup_environment();
return err;
}
@@ -0,0 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2018 Covalent IO, Inc. http://covalent.io
#undef SOCKMAP
#define TEST_MAP_TYPE BPF_MAP_TYPE_SOCKHASH
#include "./test_sockmap_kern.h"
File diff suppressed because it is too large. Load diff
@@ -0,0 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2018 Covalent IO, Inc. http://covalent.io
#define SOCKMAP
#define TEST_MAP_TYPE BPF_MAP_TYPE_SOCKMAP
#include "./test_sockmap_kern.h"
@@ -0,0 +1,363 @@
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright (c) 2017-2018 Covalent IO, Inc. http://covalent.io */
#include <stddef.h>
#include <string.h>
#include <linux/bpf.h>
#include <linux/if_ether.h>
#include <linux/if_packet.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/in.h>
#include <linux/udp.h>
#include <linux/tcp.h>
#include <linux/pkt_cls.h>
#include <sys/socket.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
/* Sockmap sample program connects a client and a backend together
* using cgroups.
*
* client:X <---> frontend:80 client:X <---> backend:80
*
* For simplicity we hard code values here and bind 1:1. The hard
* coded values are part of the setup in sockmap.sh script that
* is associated with this BPF program.
*
* The bpf_printk is verbose and prints information as connections
* are established and verdicts are decided.
*/
#define bpf_printk(fmt, ...) \
({ \
char ____fmt[] = fmt; \
bpf_trace_printk(____fmt, sizeof(____fmt), \
##__VA_ARGS__); \
})
struct bpf_map_def SEC("maps") sock_map = {
.type = TEST_MAP_TYPE,
.key_size = sizeof(int),
.value_size = sizeof(int),
.max_entries = 20,
};
struct bpf_map_def SEC("maps") sock_map_txmsg = {
.type = TEST_MAP_TYPE,
.key_size = sizeof(int),
.value_size = sizeof(int),
.max_entries = 20,
};
struct bpf_map_def SEC("maps") sock_map_redir = {
.type = TEST_MAP_TYPE,
.key_size = sizeof(int),
.value_size = sizeof(int),
.max_entries = 20,
};
struct bpf_map_def SEC("maps") sock_apply_bytes = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(int),
.max_entries = 1
};
struct bpf_map_def SEC("maps") sock_cork_bytes = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(int),
.max_entries = 1
};
struct bpf_map_def SEC("maps") sock_pull_bytes = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(int),
.max_entries = 2
};
struct bpf_map_def SEC("maps") sock_redir_flags = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(int),
.max_entries = 1
};
struct bpf_map_def SEC("maps") sock_skb_opts = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(int),
.max_entries = 1
};
SEC("sk_skb1")
int bpf_prog1(struct __sk_buff *skb)
{
return skb->len;
}
SEC("sk_skb2")
int bpf_prog2(struct __sk_buff *skb)
{
__u32 lport = skb->local_port;
__u32 rport = skb->remote_port;
int len, *f, ret, zero = 0;
__u64 flags = 0;
if (lport == 10000)
ret = 10;
else
ret = 1;
len = (__u32)skb->data_end - (__u32)skb->data;
f = bpf_map_lookup_elem(&sock_skb_opts, &zero);
if (f && *f) {
ret = 3;
flags = *f;
}
bpf_printk("sk_skb2: redirect(%iB) flags=%i\n",
len, flags);
#ifdef SOCKMAP
return bpf_sk_redirect_map(skb, &sock_map, ret, flags);
#else
return bpf_sk_redirect_hash(skb, &sock_map, &ret, flags);
#endif
}
SEC("sockops")
int bpf_sockmap(struct bpf_sock_ops *skops)
{
__u32 lport, rport;
int op, err = 0, index, key, ret;
op = (int) skops->op;
switch (op) {
case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
lport = skops->local_port;
rport = skops->remote_port;
if (lport == 10000) {
ret = 1;
#ifdef SOCKMAP
err = bpf_sock_map_update(skops, &sock_map, &ret,
BPF_NOEXIST);
#else
err = bpf_sock_hash_update(skops, &sock_map, &ret,
BPF_NOEXIST);
#endif
bpf_printk("passive(%i -> %i) map ctx update err: %d\n",
lport, bpf_ntohl(rport), err);
}
break;
case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
lport = skops->local_port;
rport = skops->remote_port;
if (bpf_ntohl(rport) == 10001) {
ret = 10;
#ifdef SOCKMAP
err = bpf_sock_map_update(skops, &sock_map, &ret,
BPF_NOEXIST);
#else
err = bpf_sock_hash_update(skops, &sock_map, &ret,
BPF_NOEXIST);
#endif
bpf_printk("active(%i -> %i) map ctx update err: %d\n",
lport, bpf_ntohl(rport), err);
}
break;
default:
break;
}
return 0;
}
SEC("sk_msg1")
int bpf_prog4(struct sk_msg_md *msg)
{
int *bytes, zero = 0, one = 1;
int *start, *end;
bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
if (bytes)
bpf_msg_apply_bytes(msg, *bytes);
bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
if (bytes)
bpf_msg_cork_bytes(msg, *bytes);
start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
if (start && end)
bpf_msg_pull_data(msg, *start, *end, 0);
return SK_PASS;
}
SEC("sk_msg2")
int bpf_prog5(struct sk_msg_md *msg)
{
int err1 = -1, err2 = -1, zero = 0, one = 1;
int *bytes, *start, *end, len1, len2;
bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
if (bytes)
err1 = bpf_msg_apply_bytes(msg, *bytes);
bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
if (bytes)
err2 = bpf_msg_cork_bytes(msg, *bytes);
len1 = (__u64)msg->data_end - (__u64)msg->data;
start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
if (start && end) {
int err;
bpf_printk("sk_msg2: pull(%i:%i)\n",
start ? *start : 0, end ? *end : 0);
err = bpf_msg_pull_data(msg, *start, *end, 0);
if (err)
bpf_printk("sk_msg2: pull_data err %i\n",
err);
len2 = (__u64)msg->data_end - (__u64)msg->data;
bpf_printk("sk_msg2: length update %i->%i\n",
len1, len2);
}
bpf_printk("sk_msg2: data length %i err1 %i err2 %i\n",
len1, err1, err2);
return SK_PASS;
}
SEC("sk_msg3")
int bpf_prog6(struct sk_msg_md *msg)
{
int *bytes, zero = 0, one = 1, key = 0;
int *start, *end, *f;
__u64 flags = 0;
bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
if (bytes)
bpf_msg_apply_bytes(msg, *bytes);
bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
if (bytes)
bpf_msg_cork_bytes(msg, *bytes);
start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
if (start && end)
bpf_msg_pull_data(msg, *start, *end, 0);
f = bpf_map_lookup_elem(&sock_redir_flags, &zero);
if (f && *f) {
key = 2;
flags = *f;
}
#ifdef SOCKMAP
return bpf_msg_redirect_map(msg, &sock_map_redir, key, flags);
#else
return bpf_msg_redirect_hash(msg, &sock_map_redir, &key, flags);
#endif
}
SEC("sk_msg4")
int bpf_prog7(struct sk_msg_md *msg)
{
int err1 = 0, err2 = 0, zero = 0, one = 1, key = 0;
int *f, *bytes, *start, *end, len1, len2;
__u64 flags = 0;
int err;
bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
if (bytes)
err1 = bpf_msg_apply_bytes(msg, *bytes);
bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
if (bytes)
err2 = bpf_msg_cork_bytes(msg, *bytes);
len1 = (__u64)msg->data_end - (__u64)msg->data;
start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
if (start && end) {
bpf_printk("sk_msg2: pull(%i:%i)\n",
start ? *start : 0, end ? *end : 0);
err = bpf_msg_pull_data(msg, *start, *end, 0);
if (err)
bpf_printk("sk_msg2: pull_data err %i\n",
err);
len2 = (__u64)msg->data_end - (__u64)msg->data;
bpf_printk("sk_msg2: length update %i->%i\n",
len1, len2);
}
f = bpf_map_lookup_elem(&sock_redir_flags, &zero);
if (f && *f) {
key = 2;
flags = *f;
}
bpf_printk("sk_msg3: redirect(%iB) flags=%i err=%i\n",
len1, flags, err1 ? err1 : err2);
#ifdef SOCKMAP
err = bpf_msg_redirect_map(msg, &sock_map_redir, key, flags);
#else
err = bpf_msg_redirect_hash(msg, &sock_map_redir, &key, flags);
#endif
bpf_printk("sk_msg3: err %i\n", err);
return err;
}
SEC("sk_msg5")
int bpf_prog8(struct sk_msg_md *msg)
{
void *data_end = (void *)(long) msg->data_end;
void *data = (void *)(long) msg->data;
int ret = 0, *bytes, zero = 0;
bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
if (bytes) {
ret = bpf_msg_apply_bytes(msg, *bytes);
if (ret)
return SK_DROP;
} else {
return SK_DROP;
}
return SK_PASS;
}
SEC("sk_msg6")
int bpf_prog9(struct sk_msg_md *msg)
{
void *data_end = (void *)(long) msg->data_end;
void *data = (void *)(long) msg->data;
int ret = 0, *bytes, zero = 0;
bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
if (bytes) {
if (((__u64)data_end - (__u64)data) >= *bytes)
return SK_PASS;
ret = bpf_msg_cork_bytes(msg, *bytes);
if (ret)
return SK_DROP;
}
return SK_PASS;
}
SEC("sk_msg7")
int bpf_prog10(struct sk_msg_md *msg)
{
int *bytes, zero = 0, one = 1;
int *start, *end;
bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
if (bytes)
bpf_msg_apply_bytes(msg, *bytes);
bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
if (bytes)
bpf_msg_cork_bytes(msg, *bytes);
start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
if (start && end)
bpf_msg_pull_data(msg, *start, *end, 0);
return SK_DROP;
}
int _version SEC("version") = 1;
char _license[] SEC("license") = "GPL";
@@ -0,0 +1,76 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2018 Facebook
#include <linux/bpf.h>
#include "bpf_helpers.h"
#ifndef PERF_MAX_STACK_DEPTH
#define PERF_MAX_STACK_DEPTH 127
#endif
struct bpf_map_def SEC("maps") control_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(__u32),
.max_entries = 1,
};
struct bpf_map_def SEC("maps") stackid_hmap = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(__u32),
.value_size = sizeof(__u32),
.max_entries = 16384,
};
struct bpf_map_def SEC("maps") stackmap = {
.type = BPF_MAP_TYPE_STACK_TRACE,
.key_size = sizeof(__u32),
.value_size = sizeof(struct bpf_stack_build_id)
* PERF_MAX_STACK_DEPTH,
.max_entries = 128,
.map_flags = BPF_F_STACK_BUILD_ID,
};
struct bpf_map_def SEC("maps") stack_amap = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(struct bpf_stack_build_id)
* PERF_MAX_STACK_DEPTH,
.max_entries = 128,
};
/* taken from /sys/kernel/debug/tracing/events/random/urandom_read/format */
struct random_urandom_args {
unsigned long long pad;
int got_bits;
int pool_left;
int input_left;
};
SEC("tracepoint/random/urandom_read")
int oncpu(struct random_urandom_args *args)
{
__u32 max_len = sizeof(struct bpf_stack_build_id)
* PERF_MAX_STACK_DEPTH;
__u32 key = 0, val = 0, *value_p;
void *stack_p;
value_p = bpf_map_lookup_elem(&control_map, &key);
if (value_p && *value_p)
return 0; /* skip if non-zero *value_p */
/* The size of stackmap and stackid_hmap should be the same */
key = bpf_get_stackid(args, &stackmap, BPF_F_USER_STACK);
if ((int)key >= 0) {
bpf_map_update_elem(&stackid_hmap, &key, &val, 0);
stack_p = bpf_map_lookup_elem(&stack_amap, &key);
if (stack_p)
bpf_get_stack(args, stack_p, max_len,
BPF_F_USER_STACK | BPF_F_USER_BUILD_ID);
}
return 0;
}
char _license[] SEC("license") = "GPL";
__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */
@@ -0,0 +1,75 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2018 Facebook
#include <linux/bpf.h>
#include "bpf_helpers.h"
#ifndef PERF_MAX_STACK_DEPTH
#define PERF_MAX_STACK_DEPTH 127
#endif
struct bpf_map_def SEC("maps") control_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(__u32),
.max_entries = 1,
};
struct bpf_map_def SEC("maps") stackid_hmap = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(__u32),
.value_size = sizeof(__u32),
.max_entries = 16384,
};
struct bpf_map_def SEC("maps") stackmap = {
.type = BPF_MAP_TYPE_STACK_TRACE,
.key_size = sizeof(__u32),
.value_size = sizeof(__u64) * PERF_MAX_STACK_DEPTH,
.max_entries = 16384,
};
struct bpf_map_def SEC("maps") stack_amap = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(__u64) * PERF_MAX_STACK_DEPTH,
.max_entries = 16384,
};
/* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
struct sched_switch_args {
unsigned long long pad;
char prev_comm[16];
int prev_pid;
int prev_prio;
long long prev_state;
char next_comm[16];
int next_pid;
int next_prio;
};
SEC("tracepoint/sched/sched_switch")
int oncpu(struct sched_switch_args *ctx)
{
__u32 max_len = PERF_MAX_STACK_DEPTH * sizeof(__u64);
__u32 key = 0, val = 0, *value_p;
void *stack_p;
value_p = bpf_map_lookup_elem(&control_map, &key);
if (value_p && *value_p)
return 0; /* skip if non-zero *value_p */
/* The size of stackmap and stackid_hmap should be the same */
key = bpf_get_stackid(ctx, &stackmap, 0);
if ((int)key >= 0) {
bpf_map_update_elem(&stackid_hmap, &key, &val, 0);
stack_p = bpf_map_lookup_elem(&stack_amap, &key);
if (stack_p)
bpf_get_stack(ctx, stack_p, max_len, 0);
}
return 0;
}
char _license[] SEC("license") = "GPL";
__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */
+202
View File
@@ -0,0 +1,202 @@
// SPDX-License-Identifier: GPL-2.0
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <ctype.h>
#include <time.h>
#include <errno.h>
#include <unistd.h>
#include <string.h>
#include <sched.h>
#include <limits.h>
#include <assert.h>
#include <sys/socket.h>
#include <linux/filter.h>
#include <linux/bpf.h>
#include <linux/if_alg.h>
#include <bpf/bpf.h>
#include "../../../include/linux/filter.h"
#include "bpf_rlimit.h"
static struct bpf_insn prog[BPF_MAXINSNS];
static void bpf_gen_imm_prog(unsigned int insns, int fd_map)
{
int i;
srand(time(NULL));
for (i = 0; i < insns; i++)
prog[i] = BPF_ALU64_IMM(BPF_MOV, i % BPF_REG_10, rand());
prog[i - 1] = BPF_EXIT_INSN();
}
static void bpf_gen_map_prog(unsigned int insns, int fd_map)
{
int i, j = 0;
for (i = 0; i + 1 < insns; i += 2) {
struct bpf_insn tmp[] = {
BPF_LD_MAP_FD(j++ % BPF_REG_10, fd_map)
};
memcpy(&prog[i], tmp, sizeof(tmp));
}
if (insns % 2 == 0)
prog[insns - 2] = BPF_ALU64_IMM(BPF_MOV, i % BPF_REG_10, 42);
prog[insns - 1] = BPF_EXIT_INSN();
}
static int bpf_try_load_prog(int insns, int fd_map,
void (*bpf_filler)(unsigned int insns,
int fd_map))
{
int fd_prog;
bpf_filler(insns, fd_map);
fd_prog = bpf_load_program(BPF_PROG_TYPE_SCHED_CLS, prog, insns, "", 0,
NULL, 0);
assert(fd_prog > 0);
if (fd_map > 0)
bpf_filler(insns, 0);
return fd_prog;
}
static int __hex2bin(char ch)
{
if ((ch >= '0') && (ch <= '9'))
return ch - '0';
ch = tolower(ch);
if ((ch >= 'a') && (ch <= 'f'))
return ch - 'a' + 10;
return -1;
}
static int hex2bin(uint8_t *dst, const char *src, size_t count)
{
while (count--) {
int hi = __hex2bin(*src++);
int lo = __hex2bin(*src++);
if ((hi < 0) || (lo < 0))
return -1;
*dst++ = (hi << 4) | lo;
}
return 0;
}
static void tag_from_fdinfo(int fd_prog, uint8_t *tag, uint32_t len)
{
const int prefix_len = sizeof("prog_tag:\t") - 1;
char buff[256];
int ret = -1;
FILE *fp;
snprintf(buff, sizeof(buff), "/proc/%d/fdinfo/%d", getpid(),
fd_prog);
fp = fopen(buff, "r");
assert(fp);
while (fgets(buff, sizeof(buff), fp)) {
if (strncmp(buff, "prog_tag:\t", prefix_len))
continue;
ret = hex2bin(tag, buff + prefix_len, len);
break;
}
fclose(fp);
assert(!ret);
}
static void tag_from_alg(int insns, uint8_t *tag, uint32_t len)
{
static const struct sockaddr_alg alg = {
.salg_family = AF_ALG,
.salg_type = "hash",
.salg_name = "sha1",
};
int fd_base, fd_alg, ret;
ssize_t size;
fd_base = socket(AF_ALG, SOCK_SEQPACKET, 0);
assert(fd_base > 0);
ret = bind(fd_base, (struct sockaddr *)&alg, sizeof(alg));
assert(!ret);
fd_alg = accept(fd_base, NULL, 0);
assert(fd_alg > 0);
insns *= sizeof(struct bpf_insn);
size = write(fd_alg, prog, insns);
assert(size == insns);
size = read(fd_alg, tag, len);
assert(size == len);
close(fd_alg);
close(fd_base);
}
static void tag_dump(const char *prefix, uint8_t *tag, uint32_t len)
{
int i;
printf("%s", prefix);
for (i = 0; i < len; i++)
printf("%02x", tag[i]);
printf("\n");
}
static void tag_exit_report(int insns, int fd_map, uint8_t *ftag,
uint8_t *atag, uint32_t len)
{
printf("Program tag mismatch for %d insns%s!\n", insns,
fd_map < 0 ? "" : " with map");
tag_dump(" fdinfo result: ", ftag, len);
tag_dump(" af_alg result: ", atag, len);
exit(1);
}
static void do_test(uint32_t *tests, int start_insns, int fd_map,
void (*bpf_filler)(unsigned int insns, int fd))
{
int i, fd_prog;
for (i = start_insns; i <= BPF_MAXINSNS; i++) {
uint8_t ftag[8], atag[sizeof(ftag)];
fd_prog = bpf_try_load_prog(i, fd_map, bpf_filler);
tag_from_fdinfo(fd_prog, ftag, sizeof(ftag));
tag_from_alg(i, atag, sizeof(atag));
if (memcmp(ftag, atag, sizeof(ftag)))
tag_exit_report(i, fd_map, ftag, atag, sizeof(ftag));
close(fd_prog);
sched_yield();
(*tests)++;
}
}
int main(void)
{
uint32_t tests = 0;
int i, fd_map;
fd_map = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(int),
sizeof(int), 1, BPF_F_NO_PREALLOC);
assert(fd_map > 0);
for (i = 0; i < 5; i++) {
do_test(&tests, 2, -1, bpf_gen_imm_prog);
do_test(&tests, 3, fd_map, bpf_gen_map_prog);
}
printf("test_tag: OK (%u tests)\n", tests);
close(fd_map);
return 0;
}
@@ -0,0 +1,258 @@
/* Copyright (c) 2017 Facebook
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
/* This program shows clang/llvm is able to generate code pattern
* like:
* _tcp_send_active_reset:
* 0: bf 16 00 00 00 00 00 00 r6 = r1
* ......
* 335: b7 01 00 00 0f 00 00 00 r1 = 15
* 336: 05 00 48 00 00 00 00 00 goto 72
*
* LBB0_3:
* 337: b7 01 00 00 01 00 00 00 r1 = 1
* 338: 63 1a d0 ff 00 00 00 00 *(u32 *)(r10 - 48) = r1
* 408: b7 01 00 00 03 00 00 00 r1 = 3
*
* LBB0_4:
* 409: 71 a2 fe ff 00 00 00 00 r2 = *(u8 *)(r10 - 2)
* 410: bf a7 00 00 00 00 00 00 r7 = r10
* 411: 07 07 00 00 b8 ff ff ff r7 += -72
* 412: bf 73 00 00 00 00 00 00 r3 = r7
* 413: 0f 13 00 00 00 00 00 00 r3 += r1
* 414: 73 23 2d 00 00 00 00 00 *(u8 *)(r3 + 45) = r2
*
* From the above code snippet, the code generated by the compiler
* is reasonable. The "r1" is assigned to different values in basic
* blocks "_tcp_send_active_reset" and "LBB0_3", and used in "LBB0_4".
* The verifier should be able to handle such code patterns.
*/
#include <string.h>
#include <linux/bpf.h>
#include <linux/ipv6.h>
#include <linux/version.h>
#include <sys/socket.h>
#include "bpf_helpers.h"
#define _(P) ({typeof(P) val = 0; bpf_probe_read(&val, sizeof(val), &P); val;})
#define TCP_ESTATS_MAGIC 0xBAADBEEF
/* This test case needs "sock" and "pt_regs" data structure.
* Recursively, "sock" needs "sock_common" and "inet_sock".
* However, this is a unit test case only for
* verifier purpose without bpf program execution.
* We can safely mock much simpler data structures, basically
* only taking the necessary fields from kernel headers.
*/
typedef __u32 __bitwise __portpair;
typedef __u64 __bitwise __addrpair;
struct sock_common {
unsigned short skc_family;
union {
__addrpair skc_addrpair;
struct {
__be32 skc_daddr;
__be32 skc_rcv_saddr;
};
};
union {
__portpair skc_portpair;
struct {
__be16 skc_dport;
__u16 skc_num;
};
};
struct in6_addr skc_v6_daddr;
struct in6_addr skc_v6_rcv_saddr;
};
struct sock {
struct sock_common __sk_common;
#define sk_family __sk_common.skc_family
#define sk_v6_daddr __sk_common.skc_v6_daddr
#define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr
};
struct inet_sock {
struct sock sk;
#define inet_daddr sk.__sk_common.skc_daddr
#define inet_dport sk.__sk_common.skc_dport
__be32 inet_saddr;
__be16 inet_sport;
};
struct pt_regs {
long di;
};
static inline struct inet_sock *inet_sk(const struct sock *sk)
{
return (struct inet_sock *)sk;
}
/* Define various data structures for state recording.
* Some fields are not used due to test simplification.
*/
enum tcp_estats_addrtype {
TCP_ESTATS_ADDRTYPE_IPV4 = 1,
TCP_ESTATS_ADDRTYPE_IPV6 = 2
};
enum tcp_estats_event_type {
TCP_ESTATS_ESTABLISH,
TCP_ESTATS_PERIODIC,
TCP_ESTATS_TIMEOUT,
TCP_ESTATS_RETRANSMIT_TIMEOUT,
TCP_ESTATS_RETRANSMIT_OTHER,
TCP_ESTATS_SYN_RETRANSMIT,
TCP_ESTATS_SYNACK_RETRANSMIT,
TCP_ESTATS_TERM,
TCP_ESTATS_TX_RESET,
TCP_ESTATS_RX_RESET,
TCP_ESTATS_WRITE_TIMEOUT,
TCP_ESTATS_CONN_TIMEOUT,
TCP_ESTATS_ACK_LATENCY,
TCP_ESTATS_NEVENTS,
};
struct tcp_estats_event {
int pid;
int cpu;
unsigned long ts;
unsigned int magic;
enum tcp_estats_event_type event_type;
};
/* The below data structure is packed in order for
* llvm compiler to generate expected code.
*/
struct tcp_estats_conn_id {
unsigned int localaddressType;
struct {
unsigned char data[16];
} localaddress;
struct {
unsigned char data[16];
} remaddress;
unsigned short localport;
unsigned short remport;
} __attribute__((__packed__));
struct tcp_estats_basic_event {
struct tcp_estats_event event;
struct tcp_estats_conn_id conn_id;
};
struct bpf_map_def SEC("maps") ev_record_map = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(__u32),
.value_size = sizeof(struct tcp_estats_basic_event),
.max_entries = 1024,
};
struct dummy_tracepoint_args {
unsigned long long pad;
struct sock *sock;
};
static __always_inline void tcp_estats_ev_init(struct tcp_estats_event *event,
enum tcp_estats_event_type type)
{
event->magic = TCP_ESTATS_MAGIC;
event->ts = bpf_ktime_get_ns();
event->event_type = type;
}
static __always_inline void unaligned_u32_set(unsigned char *to, __u8 *from)
{
to[0] = _(from[0]);
to[1] = _(from[1]);
to[2] = _(from[2]);
to[3] = _(from[3]);
}
static __always_inline void conn_id_ipv4_init(struct tcp_estats_conn_id *conn_id,
__be32 *saddr, __be32 *daddr)
{
conn_id->localaddressType = TCP_ESTATS_ADDRTYPE_IPV4;
unaligned_u32_set(conn_id->localaddress.data, (__u8 *)saddr);
unaligned_u32_set(conn_id->remaddress.data, (__u8 *)daddr);
}
static __always_inline void conn_id_ipv6_init(struct tcp_estats_conn_id *conn_id,
__be32 *saddr, __be32 *daddr)
{
conn_id->localaddressType = TCP_ESTATS_ADDRTYPE_IPV6;
unaligned_u32_set(conn_id->localaddress.data, (__u8 *)saddr);
unaligned_u32_set(conn_id->localaddress.data + sizeof(__u32),
(__u8 *)(saddr + 1));
unaligned_u32_set(conn_id->localaddress.data + sizeof(__u32) * 2,
(__u8 *)(saddr + 2));
unaligned_u32_set(conn_id->localaddress.data + sizeof(__u32) * 3,
(__u8 *)(saddr + 3));
unaligned_u32_set(conn_id->remaddress.data,
(__u8 *)(daddr));
unaligned_u32_set(conn_id->remaddress.data + sizeof(__u32),
(__u8 *)(daddr + 1));
unaligned_u32_set(conn_id->remaddress.data + sizeof(__u32) * 2,
(__u8 *)(daddr + 2));
unaligned_u32_set(conn_id->remaddress.data + sizeof(__u32) * 3,
(__u8 *)(daddr + 3));
}
static __always_inline void tcp_estats_conn_id_init(struct tcp_estats_conn_id *conn_id,
struct sock *sk)
{
conn_id->localport = _(inet_sk(sk)->inet_sport);
conn_id->remport = _(inet_sk(sk)->inet_dport);
if (_(sk->sk_family) == AF_INET6)
conn_id_ipv6_init(conn_id,
sk->sk_v6_rcv_saddr.s6_addr32,
sk->sk_v6_daddr.s6_addr32);
else
conn_id_ipv4_init(conn_id,
&inet_sk(sk)->inet_saddr,
&inet_sk(sk)->inet_daddr);
}
static __always_inline void tcp_estats_init(struct sock *sk,
struct tcp_estats_event *event,
struct tcp_estats_conn_id *conn_id,
enum tcp_estats_event_type type)
{
tcp_estats_ev_init(event, type);
tcp_estats_conn_id_init(conn_id, sk);
}
static __always_inline void send_basic_event(struct sock *sk,
enum tcp_estats_event_type type)
{
struct tcp_estats_basic_event ev;
__u32 key = bpf_get_prandom_u32();
memset(&ev, 0, sizeof(ev));
tcp_estats_init(sk, &ev.event, &ev.conn_id, type);
bpf_map_update_elem(&ev_record_map, &key, &ev, BPF_ANY);
}
SEC("dummy_tracepoint")
int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
{
if (!arg->sock)
return 0;
send_basic_event(arg->sock, TCP_ESTATS_TX_RESET);
return 0;
}
char _license[] SEC("license") = "GPL";
__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */
+17
View File
@@ -0,0 +1,17 @@
// SPDX-License-Identifier: GPL-2.0
#ifndef _TEST_TCPBPF_H
#define _TEST_TCPBPF_H
struct tcpbpf_globals {
__u32 event_map;
__u32 total_retrans;
__u32 data_segs_in;
__u32 data_segs_out;
__u32 bad_cb_test_rv;
__u32 good_cb_test_rv;
__u64 bytes_received;
__u64 bytes_acked;
__u32 num_listen;
};
#endif
@@ -0,0 +1,121 @@
// SPDX-License-Identifier: GPL-2.0
#include <stddef.h>
#include <string.h>
#include <linux/bpf.h>
#include <linux/if_ether.h>
#include <linux/if_packet.h>
#include <linux/ip.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/tcp.h>
#include <netinet/in.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
#include "test_tcpbpf.h"
struct bpf_map_def SEC("maps") global_map = {
.type = BPF_MAP_TYPE_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(struct tcpbpf_globals),
.max_entries = 2,
};
static inline void update_event_map(int event)
{
__u32 key = 0;
struct tcpbpf_globals g, *gp;
gp = bpf_map_lookup_elem(&global_map, &key);
if (gp == NULL) {
struct tcpbpf_globals g = {0};
g.event_map |= (1 << event);
bpf_map_update_elem(&global_map, &key, &g,
BPF_ANY);
} else {
g = *gp;
g.event_map |= (1 << event);
bpf_map_update_elem(&global_map, &key, &g,
BPF_ANY);
}
}
int _version SEC("version") = 1;
SEC("sockops")
int bpf_testcb(struct bpf_sock_ops *skops)
{
int rv = -1;
int bad_call_rv = 0;
int good_call_rv = 0;
int op;
int v = 0;
op = (int) skops->op;
update_event_map(op);
switch (op) {
case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
/* Test failure to set largest cb flag (assumes not defined) */
bad_call_rv = bpf_sock_ops_cb_flags_set(skops, 0x80);
/* Set callback */
good_call_rv = bpf_sock_ops_cb_flags_set(skops,
BPF_SOCK_OPS_STATE_CB_FLAG);
/* Update results */
{
__u32 key = 0;
struct tcpbpf_globals g, *gp;
gp = bpf_map_lookup_elem(&global_map, &key);
if (!gp)
break;
g = *gp;
g.bad_cb_test_rv = bad_call_rv;
g.good_cb_test_rv = good_call_rv;
bpf_map_update_elem(&global_map, &key, &g,
BPF_ANY);
}
break;
case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
skops->sk_txhash = 0x12345f;
v = 0xff;
rv = bpf_setsockopt(skops, SOL_IPV6, IPV6_TCLASS, &v,
sizeof(v));
break;
case BPF_SOCK_OPS_RTO_CB:
break;
case BPF_SOCK_OPS_RETRANS_CB:
break;
case BPF_SOCK_OPS_STATE_CB:
if (skops->args[1] == BPF_TCP_CLOSE) {
__u32 key = 0;
struct tcpbpf_globals g, *gp;
gp = bpf_map_lookup_elem(&global_map, &key);
if (!gp)
break;
g = *gp;
if (skops->args[0] == BPF_TCP_LISTEN) {
g.num_listen++;
} else {
g.total_retrans = skops->total_retrans;
g.data_segs_in = skops->data_segs_in;
g.data_segs_out = skops->data_segs_out;
g.bytes_received = skops->bytes_received;
g.bytes_acked = skops->bytes_acked;
}
bpf_map_update_elem(&global_map, &key, &g,
BPF_ANY);
}
break;
case BPF_SOCK_OPS_TCP_LISTEN_CB:
bpf_sock_ops_cb_flags_set(skops, BPF_SOCK_OPS_STATE_CB_FLAG);
break;
default:
rv = -1;
}
skops->reply = rv;
return 1;
}
char _license[] SEC("license") = "GPL";
@@ -0,0 +1,131 @@
// SPDX-License-Identifier: GPL-2.0
#include <inttypes.h>
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <errno.h>
#include <string.h>
#include <linux/bpf.h>
#include <sys/types.h>
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
#include "bpf_rlimit.h"
#include "bpf_util.h"
#include "cgroup_helpers.h"
#include "test_tcpbpf.h"
#define EXPECT_EQ(expected, actual, fmt) \
do { \
if ((expected) != (actual)) { \
printf(" Value of: " #actual "\n" \
" Actual: %" fmt "\n" \
" Expected: %" fmt "\n", \
(actual), (expected)); \
goto err; \
} \
} while (0)
int verify_result(const struct tcpbpf_globals *result)
{
__u32 expected_events;
expected_events = ((1 << BPF_SOCK_OPS_TIMEOUT_INIT) |
(1 << BPF_SOCK_OPS_RWND_INIT) |
(1 << BPF_SOCK_OPS_TCP_CONNECT_CB) |
(1 << BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB) |
(1 << BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB) |
(1 << BPF_SOCK_OPS_NEEDS_ECN) |
(1 << BPF_SOCK_OPS_STATE_CB) |
(1 << BPF_SOCK_OPS_TCP_LISTEN_CB));
EXPECT_EQ(expected_events, result->event_map, "#" PRIx32);
EXPECT_EQ(501ULL, result->bytes_received, "llu");
EXPECT_EQ(1002ULL, result->bytes_acked, "llu");
EXPECT_EQ(1, result->data_segs_in, PRIu32);
EXPECT_EQ(1, result->data_segs_out, PRIu32);
EXPECT_EQ(0x80, result->bad_cb_test_rv, PRIu32);
EXPECT_EQ(0, result->good_cb_test_rv, PRIu32);
EXPECT_EQ(1, result->num_listen, PRIu32);
return 0;
err:
return -1;
}
static int bpf_find_map(const char *test, struct bpf_object *obj,
const char *name)
{
struct bpf_map *map;
map = bpf_object__find_map_by_name(obj, name);
if (!map) {
printf("%s:FAIL:map '%s' not found\n", test, name);
return -1;
}
return bpf_map__fd(map);
}
int main(int argc, char **argv)
{
const char *file = "test_tcpbpf_kern.o";
struct tcpbpf_globals g = {0};
const char *cg_path = "/foo";
int error = EXIT_FAILURE;
struct bpf_object *obj;
int prog_fd, map_fd;
int cg_fd = -1;
__u32 key = 0;
int rv;
if (setup_cgroup_environment())
goto err;
cg_fd = create_and_get_cgroup(cg_path);
if (!cg_fd)
goto err;
if (join_cgroup(cg_path))
goto err;
if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) {
printf("FAILED: load_bpf_file failed for: %s\n", file);
goto err;
}
rv = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_SOCK_OPS, 0);
if (rv) {
printf("FAILED: bpf_prog_attach: %d (%s)\n",
error, strerror(errno));
goto err;
}
if (system("./tcp_server.py")) {
printf("FAILED: TCP server\n");
goto err;
}
map_fd = bpf_find_map(__func__, obj, "global_map");
if (map_fd < 0)
goto err;
rv = bpf_map_lookup_elem(map_fd, &key, &g);
if (rv != 0) {
printf("FAILED: bpf_map_lookup_elem returns %d\n", rv);
goto err;
}
if (verify_result(&g)) {
printf("FAILED: Wrong stats\n");
goto err;
}
printf("PASSED!\n");
error = 0;
err:
bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS);
close(cg_fd);
cleanup_cgroup_environment();
return error;
}
@@ -0,0 +1,26 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2017 Facebook
#include <linux/bpf.h>
#include "bpf_helpers.h"
/* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
struct sched_switch_args {
unsigned long long pad;
char prev_comm[16];
int prev_pid;
int prev_prio;
long long prev_state;
char next_comm[16];
int next_pid;
int next_prio;
};
SEC("tracepoint/sched/sched_switch")
int oncpu(struct sched_switch_args *ctx)
{
return 0;
}
char _license[] SEC("license") = "GPL";
__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */
+731
View File
@@ -0,0 +1,731 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
# End-to-end eBPF tunnel test suite
# The script tests BPF network tunnel implementation.
#
# Topology:
# ---------
# root namespace | at_ns0 namespace
# |
# ----------- | -----------
# | tnl dev | | | tnl dev | (overlay network)
# ----------- | -----------
# metadata-mode | native-mode
# with bpf |
# |
# ---------- | ----------
# | veth1 | --------- | veth0 | (underlay network)
# ---------- peer ----------
#
#
# Device Configuration
# --------------------
# Root namespace with metadata-mode tunnel + BPF
# Device names and addresses:
# veth1 IP: 172.16.1.200, IPv6: 00::22 (underlay)
# tunnel dev <type>11, ex: gre11, IPv4: 10.1.1.200 (overlay)
#
# Namespace at_ns0 with native tunnel
# Device names and addresses:
# veth0 IPv4: 172.16.1.100, IPv6: 00::11 (underlay)
# tunnel dev <type>00, ex: gre00, IPv4: 10.1.1.100 (overlay)
#
#
# End-to-end ping packet flow
# ---------------------------
# Most of the tests start by namespace creation, device configuration,
# then ping the underlay and overlay network. When doing 'ping 10.1.1.100'
# from root namespace, the following operations happen:
# 1) Route lookup shows 10.1.1.100/24 belongs to tnl dev, fwd to tnl dev.
# 2) Tnl device's egress BPF program is triggered and set the tunnel metadata,
# with remote_ip=172.16.1.200 and others.
# 3) Outer tunnel header is prepended and route the packet to veth1's egress
# 4) veth0's ingress queue receive the tunneled packet at namespace at_ns0
# 5) Tunnel protocol handler, ex: vxlan_rcv, decap the packet
# 6) Forward the packet to the overlay tnl dev
PING_ARG="-c 3 -w 10 -q"
ret=0
GREEN='\033[0;92m'
RED='\033[0;31m'
NC='\033[0m' # No Color
config_device()
{
ip netns add at_ns0
ip link add veth0 type veth peer name veth1
ip link set veth0 netns at_ns0
ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0
ip netns exec at_ns0 ip link set dev veth0 up
ip link set dev veth1 up mtu 1500
ip addr add dev veth1 172.16.1.200/24
}
add_gre_tunnel()
{
# at_ns0 namespace
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE seq key 2 \
local 172.16.1.100 remote 172.16.1.200
ip netns exec at_ns0 ip link set dev $DEV_NS up
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
# root namespace
ip link add dev $DEV type $TYPE key 2 external
ip link set dev $DEV up
ip addr add dev $DEV 10.1.1.200/24
}
add_ip6gretap_tunnel()
{
# assign ipv6 address
ip netns exec at_ns0 ip addr add ::11/96 dev veth0
ip netns exec at_ns0 ip link set dev veth0 up
ip addr add dev veth1 ::22/96
ip link set dev veth1 up
# at_ns0 namespace
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE seq flowlabel 0xbcdef key 2 \
local ::11 remote ::22
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
ip netns exec at_ns0 ip addr add dev $DEV_NS fc80::100/96
ip netns exec at_ns0 ip link set dev $DEV_NS up
# root namespace
ip link add dev $DEV type $TYPE external
ip addr add dev $DEV 10.1.1.200/24
ip addr add dev $DEV fc80::200/24
ip link set dev $DEV up
}
add_erspan_tunnel()
{
# at_ns0 namespace
if [ "$1" == "v1" ]; then
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE seq key 2 \
local 172.16.1.100 remote 172.16.1.200 \
erspan_ver 1 erspan 123
else
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE seq key 2 \
local 172.16.1.100 remote 172.16.1.200 \
erspan_ver 2 erspan_dir egress erspan_hwid 3
fi
ip netns exec at_ns0 ip link set dev $DEV_NS up
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
# root namespace
ip link add dev $DEV type $TYPE external
ip link set dev $DEV up
ip addr add dev $DEV 10.1.1.200/24
}
add_ip6erspan_tunnel()
{
# assign ipv6 address
ip netns exec at_ns0 ip addr add ::11/96 dev veth0
ip netns exec at_ns0 ip link set dev veth0 up
ip addr add dev veth1 ::22/96
ip link set dev veth1 up
# at_ns0 namespace
if [ "$1" == "v1" ]; then
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE seq key 2 \
local ::11 remote ::22 \
erspan_ver 1 erspan 123
else
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE seq key 2 \
local ::11 remote ::22 \
erspan_ver 2 erspan_dir egress erspan_hwid 7
fi
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
ip netns exec at_ns0 ip link set dev $DEV_NS up
# root namespace
ip link add dev $DEV type $TYPE external
ip addr add dev $DEV 10.1.1.200/24
ip link set dev $DEV up
}
add_vxlan_tunnel()
{
# Set static ARP entry here because iptables set-mark works
# on L3 packet, as a result not applying to ARP packets,
# causing errors at get_tunnel_{key/opt}.
# at_ns0 namespace
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE \
id 2 dstport 4789 gbp remote 172.16.1.200
ip netns exec at_ns0 \
ip link set dev $DEV_NS address 52:54:00:d9:01:00 up
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
ip netns exec at_ns0 arp -s 10.1.1.200 52:54:00:d9:02:00
ip netns exec at_ns0 iptables -A OUTPUT -j MARK --set-mark 0x800FF
# root namespace
ip link add dev $DEV type $TYPE external gbp dstport 4789
ip link set dev $DEV address 52:54:00:d9:02:00 up
ip addr add dev $DEV 10.1.1.200/24
arp -s 10.1.1.100 52:54:00:d9:01:00
}
add_ip6vxlan_tunnel()
{
#ip netns exec at_ns0 ip -4 addr del 172.16.1.100 dev veth0
ip netns exec at_ns0 ip -6 addr add ::11/96 dev veth0
ip netns exec at_ns0 ip link set dev veth0 up
#ip -4 addr del 172.16.1.200 dev veth1
ip -6 addr add dev veth1 ::22/96
ip link set dev veth1 up
# at_ns0 namespace
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE id 22 dstport 4789 \
local ::11 remote ::22
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
ip netns exec at_ns0 ip link set dev $DEV_NS up
# root namespace
ip link add dev $DEV type $TYPE external dstport 4789
ip addr add dev $DEV 10.1.1.200/24
ip link set dev $DEV up
}
add_geneve_tunnel()
{
# at_ns0 namespace
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE \
id 2 dstport 6081 remote 172.16.1.200
ip netns exec at_ns0 ip link set dev $DEV_NS up
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
# root namespace
ip link add dev $DEV type $TYPE dstport 6081 external
ip link set dev $DEV up
ip addr add dev $DEV 10.1.1.200/24
}
add_ip6geneve_tunnel()
{
ip netns exec at_ns0 ip addr add ::11/96 dev veth0
ip netns exec at_ns0 ip link set dev veth0 up
ip addr add dev veth1 ::22/96
ip link set dev veth1 up
# at_ns0 namespace
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE id 22 \
remote ::22 # geneve has no local option
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
ip netns exec at_ns0 ip link set dev $DEV_NS up
# root namespace
ip link add dev $DEV type $TYPE external
ip addr add dev $DEV 10.1.1.200/24
ip link set dev $DEV up
}
add_ipip_tunnel()
{
# at_ns0 namespace
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE \
local 172.16.1.100 remote 172.16.1.200
ip netns exec at_ns0 ip link set dev $DEV_NS up
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
# root namespace
ip link add dev $DEV type $TYPE external
ip link set dev $DEV up
ip addr add dev $DEV 10.1.1.200/24
}
add_ipip6tnl_tunnel()
{
ip netns exec at_ns0 ip addr add ::11/96 dev veth0
ip netns exec at_ns0 ip link set dev veth0 up
ip addr add dev veth1 ::22/96
ip link set dev veth1 up
# at_ns0 namespace
ip netns exec at_ns0 \
ip link add dev $DEV_NS type $TYPE \
local ::11 remote ::22
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
ip netns exec at_ns0 ip link set dev $DEV_NS up
# root namespace
ip link add dev $DEV type $TYPE external
ip addr add dev $DEV 10.1.1.200/24
ip link set dev $DEV up
}
test_gre()
{
TYPE=gretap
DEV_NS=gretap00
DEV=gretap11
ret=0
check $TYPE
config_device
add_gre_tunnel
attach_bpf $DEV gre_set_tunnel gre_get_tunnel
ping $PING_ARG 10.1.1.100
check_err $?
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: $TYPE"${NC}
return 1
fi
echo -e ${GREEN}"PASS: $TYPE"${NC}
}
test_ip6gre()
{
TYPE=ip6gre
DEV_NS=ip6gre00
DEV=ip6gre11
ret=0
check $TYPE
config_device
# reuse the ip6gretap function
add_ip6gretap_tunnel
attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel
# underlay
ping6 $PING_ARG ::11
# overlay: ipv4 over ipv6
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
ping $PING_ARG 10.1.1.100
check_err $?
# overlay: ipv6 over ipv6
ip netns exec at_ns0 ping6 $PING_ARG fc80::200
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: $TYPE"${NC}
return 1
fi
echo -e ${GREEN}"PASS: $TYPE"${NC}
}
test_ip6gretap()
{
TYPE=ip6gretap
DEV_NS=ip6gretap00
DEV=ip6gretap11
ret=0
check $TYPE
config_device
add_ip6gretap_tunnel
attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel
# underlay
ping6 $PING_ARG ::11
# overlay: ipv4 over ipv6
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
ping $PING_ARG 10.1.1.100
check_err $?
# overlay: ipv6 over ipv6
ip netns exec at_ns0 ping6 $PING_ARG fc80::200
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: $TYPE"${NC}
return 1
fi
echo -e ${GREEN}"PASS: $TYPE"${NC}
}
test_erspan()
{
TYPE=erspan
DEV_NS=erspan00
DEV=erspan11
ret=0
check $TYPE
config_device
add_erspan_tunnel $1
attach_bpf $DEV erspan_set_tunnel erspan_get_tunnel
ping $PING_ARG 10.1.1.100
check_err $?
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: $TYPE"${NC}
return 1
fi
echo -e ${GREEN}"PASS: $TYPE"${NC}
}
test_ip6erspan()
{
TYPE=ip6erspan
DEV_NS=ip6erspan00
DEV=ip6erspan11
ret=0
check $TYPE
config_device
add_ip6erspan_tunnel $1
attach_bpf $DEV ip4ip6erspan_set_tunnel ip4ip6erspan_get_tunnel
ping6 $PING_ARG ::11
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: $TYPE"${NC}
return 1
fi
echo -e ${GREEN}"PASS: $TYPE"${NC}
}
test_vxlan()
{
TYPE=vxlan
DEV_NS=vxlan00
DEV=vxlan11
ret=0
check $TYPE
config_device
add_vxlan_tunnel
attach_bpf $DEV vxlan_set_tunnel vxlan_get_tunnel
ping $PING_ARG 10.1.1.100
check_err $?
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: $TYPE"${NC}
return 1
fi
echo -e ${GREEN}"PASS: $TYPE"${NC}
}
test_ip6vxlan()
{
TYPE=vxlan
DEV_NS=ip6vxlan00
DEV=ip6vxlan11
ret=0
check $TYPE
config_device
add_ip6vxlan_tunnel
ip link set dev veth1 mtu 1500
attach_bpf $DEV ip6vxlan_set_tunnel ip6vxlan_get_tunnel
# underlay
ping6 $PING_ARG ::11
# ip4 over ip6
ping $PING_ARG 10.1.1.100
check_err $?
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: ip6$TYPE"${NC}
return 1
fi
echo -e ${GREEN}"PASS: ip6$TYPE"${NC}
}
test_geneve()
{
TYPE=geneve
DEV_NS=geneve00
DEV=geneve11
ret=0
check $TYPE
config_device
add_geneve_tunnel
attach_bpf $DEV geneve_set_tunnel geneve_get_tunnel
ping $PING_ARG 10.1.1.100
check_err $?
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: $TYPE"${NC}
return 1
fi
echo -e ${GREEN}"PASS: $TYPE"${NC}
}
test_ip6geneve()
{
TYPE=geneve
DEV_NS=ip6geneve00
DEV=ip6geneve11
ret=0
check $TYPE
config_device
add_ip6geneve_tunnel
attach_bpf $DEV ip6geneve_set_tunnel ip6geneve_get_tunnel
ping $PING_ARG 10.1.1.100
check_err $?
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: ip6$TYPE"${NC}
return 1
fi
echo -e ${GREEN}"PASS: ip6$TYPE"${NC}
}
test_ipip()
{
TYPE=ipip
DEV_NS=ipip00
DEV=ipip11
ret=0
check $TYPE
config_device
add_ipip_tunnel
ip link set dev veth1 mtu 1500
attach_bpf $DEV ipip_set_tunnel ipip_get_tunnel
ping $PING_ARG 10.1.1.100
check_err $?
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: $TYPE"${NC}
return 1
fi
echo -e ${GREEN}"PASS: $TYPE"${NC}
}
test_ipip6()
{
TYPE=ip6tnl
DEV_NS=ipip6tnl00
DEV=ipip6tnl11
ret=0
check $TYPE
config_device
add_ipip6tnl_tunnel
ip link set dev veth1 mtu 1500
attach_bpf $DEV ipip6_set_tunnel ipip6_get_tunnel
# underlay
ping6 $PING_ARG ::11
# ip4 over ip6
ping $PING_ARG 10.1.1.100
check_err $?
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: $TYPE"${NC}
return 1
fi
echo -e ${GREEN}"PASS: $TYPE"${NC}
}
setup_xfrm_tunnel()
{
auth=0x$(printf '1%.0s' {1..40})
enc=0x$(printf '2%.0s' {1..32})
spi_in_to_out=0x1
spi_out_to_in=0x2
# at_ns0 namespace
# at_ns0 -> root
ip netns exec at_ns0 \
ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \
spi $spi_in_to_out reqid 1 mode tunnel \
auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
ip netns exec at_ns0 \
ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir out \
tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \
mode tunnel
# root -> at_ns0
ip netns exec at_ns0 \
ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \
spi $spi_out_to_in reqid 2 mode tunnel \
auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
ip netns exec at_ns0 \
ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir in \
tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \
mode tunnel
# address & route
ip netns exec at_ns0 \
ip addr add dev veth0 10.1.1.100/32
ip netns exec at_ns0 \
ip route add 10.1.1.200 dev veth0 via 172.16.1.200 \
src 10.1.1.100
# root namespace
# at_ns0 -> root
ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \
spi $spi_in_to_out reqid 1 mode tunnel \
auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir in \
tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \
mode tunnel
# root -> at_ns0
ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \
spi $spi_out_to_in reqid 2 mode tunnel \
auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir out \
tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \
mode tunnel
# address & route
ip addr add dev veth1 10.1.1.200/32
ip route add 10.1.1.100 dev veth1 via 172.16.1.100 src 10.1.1.200
}
test_xfrm_tunnel()
{
config_device
> /sys/kernel/debug/tracing/trace
setup_xfrm_tunnel
tc qdisc add dev veth1 clsact
tc filter add dev veth1 proto ip ingress bpf da obj test_tunnel_kern.o \
sec xfrm_get_state
ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
sleep 1
grep "reqid 1" /sys/kernel/debug/tracing/trace
check_err $?
grep "spi 0x1" /sys/kernel/debug/tracing/trace
check_err $?
grep "remote ip 0xac100164" /sys/kernel/debug/tracing/trace
check_err $?
cleanup
if [ $ret -ne 0 ]; then
echo -e ${RED}"FAIL: xfrm tunnel"${NC}
return 1
fi
echo -e ${GREEN}"PASS: xfrm tunnel"${NC}
}
attach_bpf()
{
DEV=$1
SET=$2
GET=$3
tc qdisc add dev $DEV clsact
tc filter add dev $DEV egress bpf da obj test_tunnel_kern.o sec $SET
tc filter add dev $DEV ingress bpf da obj test_tunnel_kern.o sec $GET
}
cleanup()
{
ip netns delete at_ns0 2> /dev/null
ip link del veth1 2> /dev/null
ip link del ipip11 2> /dev/null
ip link del ipip6tnl11 2> /dev/null
ip link del gretap11 2> /dev/null
ip link del ip6gre11 2> /dev/null
ip link del ip6gretap11 2> /dev/null
ip link del vxlan11 2> /dev/null
ip link del ip6vxlan11 2> /dev/null
ip link del geneve11 2> /dev/null
ip link del ip6geneve11 2> /dev/null
ip link del erspan11 2> /dev/null
ip link del ip6erspan11 2> /dev/null
ip xfrm policy delete dir out src 10.1.1.200/32 dst 10.1.1.100/32 2> /dev/null
ip xfrm policy delete dir in src 10.1.1.100/32 dst 10.1.1.200/32 2> /dev/null
ip xfrm state delete src 172.16.1.100 dst 172.16.1.200 proto esp spi 0x1 2> /dev/null
ip xfrm state delete src 172.16.1.200 dst 172.16.1.100 proto esp spi 0x2 2> /dev/null
}
cleanup_exit()
{
echo "CATCH SIGKILL or SIGINT, cleanup and exit"
cleanup
exit 0
}
check()
{
ip link help 2>&1 | grep -q "\s$1\s"
if [ $? -ne 0 ];then
echo "SKIP $1: iproute2 not support"
cleanup
return 1
fi
}
enable_debug()
{
echo 'file ip_gre.c +p' > /sys/kernel/debug/dynamic_debug/control
echo 'file ip6_gre.c +p' > /sys/kernel/debug/dynamic_debug/control
echo 'file vxlan.c +p' > /sys/kernel/debug/dynamic_debug/control
echo 'file geneve.c +p' > /sys/kernel/debug/dynamic_debug/control
echo 'file ipip.c +p' > /sys/kernel/debug/dynamic_debug/control
}
check_err()
{
if [ $ret -eq 0 ]; then
ret=$1
fi
}
bpf_tunnel_test()
{
echo "Testing GRE tunnel..."
test_gre
echo "Testing IP6GRE tunnel..."
test_ip6gre
echo "Testing IP6GRETAP tunnel..."
test_ip6gretap
echo "Testing ERSPAN tunnel..."
test_erspan v2
echo "Testing IP6ERSPAN tunnel..."
test_ip6erspan v2
echo "Testing VXLAN tunnel..."
test_vxlan
echo "Testing IP6VXLAN tunnel..."
test_ip6vxlan
echo "Testing GENEVE tunnel..."
test_geneve
echo "Testing IP6GENEVE tunnel..."
test_ip6geneve
echo "Testing IPIP tunnel..."
test_ipip
echo "Testing IPIP6 tunnel..."
test_ipip6
echo "Testing IPSec tunnel..."
test_xfrm_tunnel
}
trap cleanup 0 3 6
trap cleanup_exit 2 9
cleanup
bpf_tunnel_test
exit 0
@@ -0,0 +1,713 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2016 VMware
* Copyright (c) 2016 Facebook
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
#include <stddef.h>
#include <string.h>
#include <arpa/inet.h>
#include <linux/bpf.h>
#include <linux/if_ether.h>
#include <linux/if_packet.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/types.h>
#include <linux/tcp.h>
#include <linux/socket.h>
#include <linux/pkt_cls.h>
#include <linux/erspan.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
#define ERROR(ret) do {\
char fmt[] = "ERROR line:%d ret:%d\n";\
bpf_trace_printk(fmt, sizeof(fmt), __LINE__, ret); \
} while (0)
int _version SEC("version") = 1;
struct geneve_opt {
__be16 opt_class;
__u8 type;
__u8 length:5;
__u8 r3:1;
__u8 r2:1;
__u8 r1:1;
__u8 opt_data[8]; /* hard-coded to 8 byte */
};
struct vxlan_metadata {
__u32 gbp;
};
SEC("gre_set_tunnel")
int _gre_set_tunnel(struct __sk_buff *skb)
{
int ret;
struct bpf_tunnel_key key;
__builtin_memset(&key, 0x0, sizeof(key));
key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
key.tunnel_id = 2;
key.tunnel_tos = 0;
key.tunnel_ttl = 64;
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_ZERO_CSUM_TX | BPF_F_SEQ_NUMBER);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
SEC("gre_get_tunnel")
int _gre_get_tunnel(struct __sk_buff *skb)
{
int ret;
struct bpf_tunnel_key key;
char fmt[] = "key %d remote ip 0x%x\n";
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
bpf_trace_printk(fmt, sizeof(fmt), key.tunnel_id, key.remote_ipv4);
return TC_ACT_OK;
}
SEC("ip6gretap_set_tunnel")
int _ip6gretap_set_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key;
int ret;
__builtin_memset(&key, 0x0, sizeof(key));
key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
key.tunnel_id = 2;
key.tunnel_tos = 0;
key.tunnel_ttl = 64;
key.tunnel_label = 0xabcde;
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX |
BPF_F_SEQ_NUMBER);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
SEC("ip6gretap_get_tunnel")
int _ip6gretap_get_tunnel(struct __sk_buff *skb)
{
char fmt[] = "key %d remote ip6 ::%x label %x\n";
struct bpf_tunnel_key key;
int ret;
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
bpf_trace_printk(fmt, sizeof(fmt),
key.tunnel_id, key.remote_ipv6[3], key.tunnel_label);
return TC_ACT_OK;
}
SEC("erspan_set_tunnel")
int _erspan_set_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key;
struct erspan_metadata md;
int ret;
__builtin_memset(&key, 0x0, sizeof(key));
key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
key.tunnel_id = 2;
key.tunnel_tos = 0;
key.tunnel_ttl = 64;
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_ZERO_CSUM_TX);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
__builtin_memset(&md, 0, sizeof(md));
#ifdef ERSPAN_V1
md.version = 1;
md.u.index = bpf_htonl(123);
#else
__u8 direction = 1;
__u8 hwid = 7;
md.version = 2;
md.u.md2.dir = direction;
md.u.md2.hwid = hwid & 0xf;
md.u.md2.hwid_upper = (hwid >> 4) & 0x3;
#endif
ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md));
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
SEC("erspan_get_tunnel")
int _erspan_get_tunnel(struct __sk_buff *skb)
{
char fmt[] = "key %d remote ip 0x%x erspan version %d\n";
struct bpf_tunnel_key key;
struct erspan_metadata md;
__u32 index;
int ret;
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md));
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
bpf_trace_printk(fmt, sizeof(fmt),
key.tunnel_id, key.remote_ipv4, md.version);
#ifdef ERSPAN_V1
char fmt2[] = "\tindex %x\n";
index = bpf_ntohl(md.u.index);
bpf_trace_printk(fmt2, sizeof(fmt2), index);
#else
char fmt2[] = "\tdirection %d hwid %x timestamp %u\n";
bpf_trace_printk(fmt2, sizeof(fmt2),
md.u.md2.dir,
(md.u.md2.hwid_upper << 4) + md.u.md2.hwid,
bpf_ntohl(md.u.md2.timestamp));
#endif
return TC_ACT_OK;
}
SEC("ip4ip6erspan_set_tunnel")
int _ip4ip6erspan_set_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key;
struct erspan_metadata md;
int ret;
__builtin_memset(&key, 0x0, sizeof(key));
key.remote_ipv6[3] = bpf_htonl(0x11);
key.tunnel_id = 2;
key.tunnel_tos = 0;
key.tunnel_ttl = 64;
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
__builtin_memset(&md, 0, sizeof(md));
#ifdef ERSPAN_V1
md.u.index = bpf_htonl(123);
md.version = 1;
#else
__u8 direction = 0;
__u8 hwid = 17;
md.version = 2;
md.u.md2.dir = direction;
md.u.md2.hwid = hwid & 0xf;
md.u.md2.hwid_upper = (hwid >> 4) & 0x3;
#endif
ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md));
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
SEC("ip4ip6erspan_get_tunnel")
int _ip4ip6erspan_get_tunnel(struct __sk_buff *skb)
{
char fmt[] = "ip6erspan get key %d remote ip6 ::%x erspan version %d\n";
struct bpf_tunnel_key key;
struct erspan_metadata md;
__u32 index;
int ret;
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md));
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
bpf_trace_printk(fmt, sizeof(fmt),
key.tunnel_id, key.remote_ipv4, md.version);
#ifdef ERSPAN_V1
char fmt2[] = "\tindex %x\n";
index = bpf_ntohl(md.u.index);
bpf_trace_printk(fmt2, sizeof(fmt2), index);
#else
char fmt2[] = "\tdirection %d hwid %x timestamp %u\n";
bpf_trace_printk(fmt2, sizeof(fmt2),
md.u.md2.dir,
(md.u.md2.hwid_upper << 4) + md.u.md2.hwid,
bpf_ntohl(md.u.md2.timestamp));
#endif
return TC_ACT_OK;
}
SEC("vxlan_set_tunnel")
int _vxlan_set_tunnel(struct __sk_buff *skb)
{
int ret;
struct bpf_tunnel_key key;
struct vxlan_metadata md;
__builtin_memset(&key, 0x0, sizeof(key));
key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
key.tunnel_id = 2;
key.tunnel_tos = 0;
key.tunnel_ttl = 64;
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_ZERO_CSUM_TX);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
md.gbp = 0x800FF; /* Set VXLAN Group Policy extension */
ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md));
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
SEC("vxlan_get_tunnel")
int _vxlan_get_tunnel(struct __sk_buff *skb)
{
int ret;
struct bpf_tunnel_key key;
struct vxlan_metadata md;
char fmt[] = "key %d remote ip 0x%x vxlan gbp 0x%x\n";
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md));
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
bpf_trace_printk(fmt, sizeof(fmt),
key.tunnel_id, key.remote_ipv4, md.gbp);
return TC_ACT_OK;
}
SEC("ip6vxlan_set_tunnel")
int _ip6vxlan_set_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key;
int ret;
__builtin_memset(&key, 0x0, sizeof(key));
key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
key.tunnel_id = 22;
key.tunnel_tos = 0;
key.tunnel_ttl = 64;
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
SEC("ip6vxlan_get_tunnel")
int _ip6vxlan_get_tunnel(struct __sk_buff *skb)
{
char fmt[] = "key %d remote ip6 ::%x label %x\n";
struct bpf_tunnel_key key;
int ret;
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
bpf_trace_printk(fmt, sizeof(fmt),
key.tunnel_id, key.remote_ipv6[3], key.tunnel_label);
return TC_ACT_OK;
}
SEC("geneve_set_tunnel")
int _geneve_set_tunnel(struct __sk_buff *skb)
{
int ret, ret2;
struct bpf_tunnel_key key;
struct geneve_opt gopt;
__builtin_memset(&key, 0x0, sizeof(key));
key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
key.tunnel_id = 2;
key.tunnel_tos = 0;
key.tunnel_ttl = 64;
__builtin_memset(&gopt, 0x0, sizeof(gopt));
gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */
gopt.type = 0x08;
gopt.r1 = 0;
gopt.r2 = 0;
gopt.r3 = 0;
gopt.length = 2; /* 4-byte multiple */
*(int *) &gopt.opt_data = bpf_htonl(0xdeadbeef);
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_ZERO_CSUM_TX);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
ret = bpf_skb_set_tunnel_opt(skb, &gopt, sizeof(gopt));
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
SEC("geneve_get_tunnel")
int _geneve_get_tunnel(struct __sk_buff *skb)
{
int ret;
struct bpf_tunnel_key key;
struct geneve_opt gopt;
char fmt[] = "key %d remote ip 0x%x geneve class 0x%x\n";
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt));
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
bpf_trace_printk(fmt, sizeof(fmt),
key.tunnel_id, key.remote_ipv4, gopt.opt_class);
return TC_ACT_OK;
}
SEC("ip6geneve_set_tunnel")
int _ip6geneve_set_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key;
struct geneve_opt gopt;
int ret;
__builtin_memset(&key, 0x0, sizeof(key));
key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
key.tunnel_id = 22;
key.tunnel_tos = 0;
key.tunnel_ttl = 64;
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
__builtin_memset(&gopt, 0x0, sizeof(gopt));
gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */
gopt.type = 0x08;
gopt.r1 = 0;
gopt.r2 = 0;
gopt.r3 = 0;
gopt.length = 2; /* 4-byte multiple */
*(int *) &gopt.opt_data = bpf_htonl(0xfeedbeef);
ret = bpf_skb_set_tunnel_opt(skb, &gopt, sizeof(gopt));
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
SEC("ip6geneve_get_tunnel")
int _ip6geneve_get_tunnel(struct __sk_buff *skb)
{
char fmt[] = "key %d remote ip 0x%x geneve class 0x%x\n";
struct bpf_tunnel_key key;
struct geneve_opt gopt;
int ret;
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt));
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
bpf_trace_printk(fmt, sizeof(fmt),
key.tunnel_id, key.remote_ipv4, gopt.opt_class);
return TC_ACT_OK;
}
SEC("ipip_set_tunnel")
int _ipip_set_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key = {};
void *data = (void *)(long)skb->data;
struct iphdr *iph = data;
struct tcphdr *tcp = data + sizeof(*iph);
void *data_end = (void *)(long)skb->data_end;
int ret;
/* single length check */
if (data + sizeof(*iph) + sizeof(*tcp) > data_end) {
ERROR(1);
return TC_ACT_SHOT;
}
key.tunnel_ttl = 64;
if (iph->protocol == IPPROTO_ICMP) {
key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
} else {
if (iph->protocol != IPPROTO_TCP || iph->ihl != 5)
return TC_ACT_SHOT;
if (tcp->dest == bpf_htons(5200))
key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
else if (tcp->dest == bpf_htons(5201))
key.remote_ipv4 = 0xac100165; /* 172.16.1.101 */
else
return TC_ACT_SHOT;
}
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
SEC("ipip_get_tunnel")
int _ipip_get_tunnel(struct __sk_buff *skb)
{
int ret;
struct bpf_tunnel_key key;
char fmt[] = "remote ip 0x%x\n";
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
bpf_trace_printk(fmt, sizeof(fmt), key.remote_ipv4);
return TC_ACT_OK;
}
SEC("ipip6_set_tunnel")
int _ipip6_set_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key = {};
void *data = (void *)(long)skb->data;
struct iphdr *iph = data;
struct tcphdr *tcp = data + sizeof(*iph);
void *data_end = (void *)(long)skb->data_end;
int ret;
/* single length check */
if (data + sizeof(*iph) + sizeof(*tcp) > data_end) {
ERROR(1);
return TC_ACT_SHOT;
}
__builtin_memset(&key, 0x0, sizeof(key));
key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
key.tunnel_ttl = 64;
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
SEC("ipip6_get_tunnel")
int _ipip6_get_tunnel(struct __sk_buff *skb)
{
int ret;
struct bpf_tunnel_key key;
char fmt[] = "remote ip6 %x::%x\n";
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
bpf_trace_printk(fmt, sizeof(fmt), bpf_htonl(key.remote_ipv6[0]),
bpf_htonl(key.remote_ipv6[3]));
return TC_ACT_OK;
}
SEC("ip6ip6_set_tunnel")
int _ip6ip6_set_tunnel(struct __sk_buff *skb)
{
struct bpf_tunnel_key key = {};
void *data = (void *)(long)skb->data;
struct ipv6hdr *iph = data;
struct tcphdr *tcp = data + sizeof(*iph);
void *data_end = (void *)(long)skb->data_end;
int ret;
/* single length check */
if (data + sizeof(*iph) + sizeof(*tcp) > data_end) {
ERROR(1);
return TC_ACT_SHOT;
}
key.remote_ipv6[0] = bpf_htonl(0x2401db00);
key.tunnel_ttl = 64;
if (iph->nexthdr == 58 /* NEXTHDR_ICMP */) {
key.remote_ipv6[3] = bpf_htonl(1);
} else {
if (iph->nexthdr != 6 /* NEXTHDR_TCP */) {
ERROR(iph->nexthdr);
return TC_ACT_SHOT;
}
if (tcp->dest == bpf_htons(5200)) {
key.remote_ipv6[3] = bpf_htonl(1);
} else if (tcp->dest == bpf_htons(5201)) {
key.remote_ipv6[3] = bpf_htonl(2);
} else {
ERROR(tcp->dest);
return TC_ACT_SHOT;
}
}
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
return TC_ACT_OK;
}
SEC("ip6ip6_get_tunnel")
int _ip6ip6_get_tunnel(struct __sk_buff *skb)
{
int ret;
struct bpf_tunnel_key key;
char fmt[] = "remote ip6 %x::%x\n";
ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
if (ret < 0) {
ERROR(ret);
return TC_ACT_SHOT;
}
bpf_trace_printk(fmt, sizeof(fmt), bpf_htonl(key.remote_ipv6[0]),
bpf_htonl(key.remote_ipv6[3]));
return TC_ACT_OK;
}
SEC("xfrm_get_state")
int _xfrm_get_state(struct __sk_buff *skb)
{
struct bpf_xfrm_state x;
char fmt[] = "reqid %d spi 0x%x remote ip 0x%x\n";
int ret;
ret = bpf_skb_get_xfrm_state(skb, 0, &x, sizeof(x), 0);
if (ret < 0)
return TC_ACT_OK;
bpf_trace_printk(fmt, sizeof(fmt), x.reqid, bpf_ntohl(x.spi),
bpf_ntohl(x.remote_ipv4));
return TC_ACT_OK;
}
char _license[] SEC("license") = "GPL";
File diff suppressed because it is too large. Load diff
@@ -0,0 +1,174 @@
#include <errno.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <unistd.h>
#include <sys/time.h>
#include <linux/bpf.h>
#include <linux/filter.h>
#include <linux/unistd.h>
#include <bpf/bpf.h>
#include "bpf_rlimit.h"
#define LOG_SIZE (1 << 20)
#define err(str...) printf("ERROR: " str)
static const struct bpf_insn code_sample[] = {
/* We need a few instructions to pass the min log length */
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
BPF_FUNC_map_lookup_elem),
BPF_EXIT_INSN(),
};
static inline __u64 ptr_to_u64(const void *ptr)
{
return (__u64) (unsigned long) ptr;
}
static int load(char *log, size_t log_len, int log_level)
{
union bpf_attr attr;
bzero(&attr, sizeof(attr));
attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
attr.insn_cnt = (__u32)(sizeof(code_sample) / sizeof(struct bpf_insn));
attr.insns = ptr_to_u64(code_sample);
attr.license = ptr_to_u64("GPL");
attr.log_buf = ptr_to_u64(log);
attr.log_size = log_len;
attr.log_level = log_level;
return syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
}
static void check_ret(int ret, int exp_errno)
{
if (ret > 0) {
close(ret);
err("broken sample loaded successfully!?\n");
exit(1);
}
if (!ret || errno != exp_errno) {
err("Program load returned: ret:%d/errno:%d, expected ret:%d/errno:%d\n",
ret, errno, -1, exp_errno);
exit(1);
}
}
static void check_ones(const char *buf, size_t len, const char *msg)
{
while (len--)
if (buf[len] != 1) {
err("%s", msg);
exit(1);
}
}
static void test_log_good(char *log, size_t buf_len, size_t log_len,
size_t exp_len, int exp_errno, const char *full_log)
{
size_t len;
int ret;
memset(log, 1, buf_len);
ret = load(log, log_len, 1);
check_ret(ret, exp_errno);
len = strnlen(log, buf_len);
if (len == buf_len) {
err("verifier did not NULL terminate the log\n");
exit(1);
}
if (exp_len && len != exp_len) {
err("incorrect log length expected:%zd have:%zd\n",
exp_len, len);
exit(1);
}
if (strchr(log, 1)) {
err("verifier leaked a byte through\n");
exit(1);
}
check_ones(log + len + 1, buf_len - len - 1,
"verifier wrote bytes past NULL termination\n");
if (memcmp(full_log, log, LOG_SIZE)) {
err("log did not match expected output\n");
exit(1);
}
}
static void test_log_bad(char *log, size_t log_len, int log_level)
{
int ret;
ret = load(log, log_len, log_level);
check_ret(ret, EINVAL);
if (log)
check_ones(log, LOG_SIZE,
"verifier touched log with bad parameters\n");
}
int main(int argc, char **argv)
{
char full_log[LOG_SIZE];
char log[LOG_SIZE];
size_t want_len;
int i;
memset(log, 1, LOG_SIZE);
/* Test incorrect attr */
printf("Test log_level 0...\n");
test_log_bad(log, LOG_SIZE, 0);
printf("Test log_size < 128...\n");
test_log_bad(log, 15, 1);
printf("Test log_buff = NULL...\n");
test_log_bad(NULL, LOG_SIZE, 1);
/* Test with log big enough */
printf("Test oversized buffer...\n");
test_log_good(full_log, LOG_SIZE, LOG_SIZE, 0, EACCES, full_log);
want_len = strlen(full_log);
printf("Test exact buffer...\n");
test_log_good(log, LOG_SIZE, want_len + 2, want_len, EACCES, full_log);
printf("Test undersized buffers...\n");
for (i = 0; i < 64; i++) {
full_log[want_len - i + 1] = 1;
full_log[want_len - i] = 0;
test_log_good(log, LOG_SIZE, want_len + 1 - i, want_len - i,
ENOSPC, full_log);
}
printf("test_verifier_log: OK\n");
return 0;
}
+235
View File
@@ -0,0 +1,235 @@
/* Copyright (c) 2016,2017 Facebook
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*/
#include <stddef.h>
#include <string.h>
#include <linux/bpf.h>
#include <linux/if_ether.h>
#include <linux/if_packet.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/in.h>
#include <linux/udp.h>
#include <linux/tcp.h>
#include <linux/pkt_cls.h>
#include <sys/socket.h>
#include "bpf_helpers.h"
#include "bpf_endian.h"
#include "test_iptunnel_common.h"
int _version SEC("version") = 1;
struct bpf_map_def SEC("maps") rxcnt = {
.type = BPF_MAP_TYPE_PERCPU_ARRAY,
.key_size = sizeof(__u32),
.value_size = sizeof(__u64),
.max_entries = 256,
};
struct bpf_map_def SEC("maps") vip2tnl = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(struct vip),
.value_size = sizeof(struct iptnl_info),
.max_entries = MAX_IPTNL_ENTRIES,
};
static __always_inline void count_tx(__u32 protocol)
{
__u64 *rxcnt_count;
rxcnt_count = bpf_map_lookup_elem(&rxcnt, &protocol);
if (rxcnt_count)
*rxcnt_count += 1;
}
static __always_inline int get_dport(void *trans_data, void *data_end,
__u8 protocol)
{
struct tcphdr *th;
struct udphdr *uh;
switch (protocol) {
case IPPROTO_TCP:
th = (struct tcphdr *)trans_data;
if (th + 1 > data_end)
return -1;
return th->dest;
case IPPROTO_UDP:
uh = (struct udphdr *)trans_data;
if (uh + 1 > data_end)
return -1;
return uh->dest;
default:
return 0;
}
}
static __always_inline void set_ethhdr(struct ethhdr *new_eth,
const struct ethhdr *old_eth,
const struct iptnl_info *tnl,
__be16 h_proto)
{
memcpy(new_eth->h_source, old_eth->h_dest, sizeof(new_eth->h_source));
memcpy(new_eth->h_dest, tnl->dmac, sizeof(new_eth->h_dest));
new_eth->h_proto = h_proto;
}
static __always_inline int handle_ipv4(struct xdp_md *xdp)
{
void *data_end = (void *)(long)xdp->data_end;
void *data = (void *)(long)xdp->data;
struct iptnl_info *tnl;
struct ethhdr *new_eth;
struct ethhdr *old_eth;
struct iphdr *iph = data + sizeof(struct ethhdr);
__u16 *next_iph;
__u16 payload_len;
struct vip vip = {};
int dport;
__u32 csum = 0;
int i;
if (iph + 1 > data_end)
return XDP_DROP;
dport = get_dport(iph + 1, data_end, iph->protocol);
if (dport == -1)
return XDP_DROP;
vip.protocol = iph->protocol;
vip.family = AF_INET;
vip.daddr.v4 = iph->daddr;
vip.dport = dport;
payload_len = bpf_ntohs(iph->tot_len);
tnl = bpf_map_lookup_elem(&vip2tnl, &vip);
/* It only does v4-in-v4 */
if (!tnl || tnl->family != AF_INET)
return XDP_PASS;
if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct iphdr)))
return XDP_DROP;
data = (void *)(long)xdp->data;
data_end = (void *)(long)xdp->data_end;
new_eth = data;
iph = data + sizeof(*new_eth);
old_eth = data + sizeof(*iph);
if (new_eth + 1 > data_end ||
old_eth + 1 > data_end ||
iph + 1 > data_end)
return XDP_DROP;
set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IP));
iph->version = 4;
iph->ihl = sizeof(*iph) >> 2;
iph->frag_off = 0;
iph->protocol = IPPROTO_IPIP;
iph->check = 0;
iph->tos = 0;
iph->tot_len = bpf_htons(payload_len + sizeof(*iph));
iph->daddr = tnl->daddr.v4;
iph->saddr = tnl->saddr.v4;
iph->ttl = 8;
next_iph = (__u16 *)iph;
#pragma clang loop unroll(full)
for (i = 0; i < sizeof(*iph) >> 1; i++)
csum += *next_iph++;
iph->check = ~((csum & 0xffff) + (csum >> 16));
count_tx(vip.protocol);
return XDP_TX;
}
static __always_inline int handle_ipv6(struct xdp_md *xdp)
{
void *data_end = (void *)(long)xdp->data_end;
void *data = (void *)(long)xdp->data;
struct iptnl_info *tnl;
struct ethhdr *new_eth;
struct ethhdr *old_eth;
struct ipv6hdr *ip6h = data + sizeof(struct ethhdr);
__u16 payload_len;
struct vip vip = {};
int dport;
if (ip6h + 1 > data_end)
return XDP_DROP;
dport = get_dport(ip6h + 1, data_end, ip6h->nexthdr);
if (dport == -1)
return XDP_DROP;
vip.protocol = ip6h->nexthdr;
vip.family = AF_INET6;
memcpy(vip.daddr.v6, ip6h->daddr.s6_addr32, sizeof(vip.daddr));
vip.dport = dport;
payload_len = ip6h->payload_len;
tnl = bpf_map_lookup_elem(&vip2tnl, &vip);
/* It only does v6-in-v6 */
if (!tnl || tnl->family != AF_INET6)
return XDP_PASS;
if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(struct ipv6hdr)))
return XDP_DROP;
data = (void *)(long)xdp->data;
data_end = (void *)(long)xdp->data_end;
new_eth = data;
ip6h = data + sizeof(*new_eth);
old_eth = data + sizeof(*ip6h);
if (new_eth + 1 > data_end || old_eth + 1 > data_end ||
ip6h + 1 > data_end)
return XDP_DROP;
set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IPV6));
ip6h->version = 6;
ip6h->priority = 0;
memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl));
ip6h->payload_len = bpf_htons(bpf_ntohs(payload_len) + sizeof(*ip6h));
ip6h->nexthdr = IPPROTO_IPV6;
ip6h->hop_limit = 8;
memcpy(ip6h->saddr.s6_addr32, tnl->saddr.v6, sizeof(tnl->saddr.v6));
memcpy(ip6h->daddr.s6_addr32, tnl->daddr.v6, sizeof(tnl->daddr.v6));
count_tx(vip.protocol);
return XDP_TX;
}
SEC("xdp_tx_iptunnel")
int _xdp_tx_iptunnel(struct xdp_md *xdp)
{
void *data_end = (void *)(long)xdp->data_end;
void *data = (void *)(long)xdp->data;
struct ethhdr *eth = data;
__u16 h_proto;
if (eth + 1 > data_end)
return XDP_DROP;
h_proto = eth->h_proto;
if (h_proto == bpf_htons(ETH_P_IP))
return handle_ipv4(xdp);
else if (h_proto == bpf_htons(ETH_P_IPV6))
return handle_ipv6(xdp);
else
return XDP_DROP;
}
char _license[] SEC("license") = "GPL";
@@ -0,0 +1,53 @@
#include <linux/bpf.h>
#include <linux/if_ether.h>
#include <linux/pkt_cls.h>
#include "bpf_helpers.h"
#define __round_mask(x, y) ((__typeof__(x))((y) - 1))
#define round_up(x, y) ((((x) - 1) | __round_mask(x, y)) + 1)
#define ctx_ptr(ctx, mem) (void *)(unsigned long)ctx->mem
SEC("t")
int ing_cls(struct __sk_buff *ctx)
{
__u8 *data, *data_meta, *data_end;
__u32 diff = 0;
data_meta = ctx_ptr(ctx, data_meta);
data_end = ctx_ptr(ctx, data_end);
data = ctx_ptr(ctx, data);
if (data + ETH_ALEN > data_end ||
data_meta + round_up(ETH_ALEN, 4) > data)
return TC_ACT_SHOT;
diff |= ((__u32 *)data_meta)[0] ^ ((__u32 *)data)[0];
diff |= ((__u16 *)data_meta)[2] ^ ((__u16 *)data)[2];
return diff ? TC_ACT_SHOT : TC_ACT_OK;
}
SEC("x")
int ing_xdp(struct xdp_md *ctx)
{
__u8 *data, *data_meta, *data_end;
int ret;
ret = bpf_xdp_adjust_meta(ctx, -round_up(ETH_ALEN, 4));
if (ret < 0)
return XDP_DROP;
data_meta = ctx_ptr(ctx, data_meta);
data_end = ctx_ptr(ctx, data_end);
data = ctx_ptr(ctx, data);
if (data + ETH_ALEN > data_end ||
data_meta + round_up(ETH_ALEN, 4) > data)
return XDP_DROP;
__builtin_memcpy(data_meta, data, ETH_ALEN);
return XDP_PASS;
}
char _license[] SEC("license") = "GPL";
+52
View File
@@ -0,0 +1,52 @@
#!/bin/sh
cleanup()
{
if [ "$?" = "0" ]; then
echo "selftests: test_xdp_meta [PASS]";
else
echo "selftests: test_xdp_meta [FAILED]";
fi
set +e
ip link del veth1 2> /dev/null
ip netns del ns1 2> /dev/null
ip netns del ns2 2> /dev/null
}
ip link set dev lo xdp off 2>/dev/null > /dev/null
if [ $? -ne 0 ];then
echo "selftests: [SKIP] Could not run test without the ip xdp support"
exit 0
fi
set -e
ip netns add ns1
ip netns add ns2
trap cleanup 0 2 3 6 9
ip link add veth1 type veth peer name veth2
ip link set veth1 netns ns1
ip link set veth2 netns ns2
ip netns exec ns1 ip addr add 10.1.1.11/24 dev veth1
ip netns exec ns2 ip addr add 10.1.1.22/24 dev veth2
ip netns exec ns1 tc qdisc add dev veth1 clsact
ip netns exec ns2 tc qdisc add dev veth2 clsact
ip netns exec ns1 tc filter add dev veth1 ingress bpf da obj test_xdp_meta.o sec t
ip netns exec ns2 tc filter add dev veth2 ingress bpf da obj test_xdp_meta.o sec t
ip netns exec ns1 ip link set dev veth1 xdp obj test_xdp_meta.o sec x
ip netns exec ns2 ip link set dev veth2 xdp obj test_xdp_meta.o sec x
ip netns exec ns1 ip link set dev veth1 up
ip netns exec ns2 ip link set dev veth2 up
ip netns exec ns1 ping -c 1 10.1.1.22
ip netns exec ns2 ping -c 1 10.1.1.11
exit 0
Loaded 100 of 80519 files, more files were not shown because too many files have changed in this diff. Show more