Resguardo inicial

linux-7.2.3/samples/Kconfig

@@ -0,0 +1,335 @@
+# SPDX-License-Identifier: GPL-2.0-only
+menuconfig SAMPLES
+	bool "Sample kernel code"
+	help
+	  You can build and test sample kernel code here.
+
+if SAMPLES
+
+config SAMPLE_AUXDISPLAY
+	bool "auxdisplay sample"
+	depends on CC_CAN_LINK
+
+config SAMPLE_TRACE_EVENTS
+	tristate "Build trace_events examples -- loadable modules only"
+	depends on EVENT_TRACING && m
+	help
+	  This builds the trace event example module.
+
+config SAMPLE_TRACE_CUSTOM_EVENTS
+	tristate "Build custom trace event example -- loadable modules only"
+	depends on EVENT_TRACING && m
+	help
+	  This builds the custom trace event example module.
+
+config SAMPLE_TRACE_PRINTK
+	tristate "Build trace_printk module - tests various trace_printk formats"
+	depends on EVENT_TRACING && m
+	help
+	  This builds a module that calls trace_printk() and can be used to
+	  test various trace_printk() calls from a module.
+
+config SAMPLE_FTRACE_DIRECT
+	tristate "Build register_ftrace_direct() example"
+	depends on DYNAMIC_FTRACE_WITH_DIRECT_CALLS && m
+	depends on HAVE_SAMPLE_FTRACE_DIRECT
+	help
+	  This builds an ftrace direct function example
+	  that hooks to wake_up_process and prints the parameters.
+
+config SAMPLE_FTRACE_DIRECT_MULTI
+	tristate "Build register_ftrace_direct() on multiple ips example"
+	depends on DYNAMIC_FTRACE_WITH_DIRECT_CALLS && m
+	depends on HAVE_SAMPLE_FTRACE_DIRECT_MULTI
+	help
+	  This builds an ftrace direct function example
+	  that hooks to wake_up_process and schedule, and prints
+	  the function addresses.
+
+config SAMPLE_FTRACE_OPS
+	tristate "Build custom ftrace ops example"
+	depends on FUNCTION_TRACER
+	help
+	  This builds an ftrace ops example that hooks two functions and
+	  measures the time taken to invoke one function a number of times.
+
+config SAMPLE_TRACE_ARRAY
+	tristate "Build sample module for kernel access to Ftrace instances"
+	depends on EVENT_TRACING && m
+	help
+	  This builds a module that demonstrates the use of various APIs to
+	  access Ftrace instances from within the kernel.
+
+config SAMPLE_KOBJECT
+	tristate "Build kobject examples"
+	help
+	  This config option will allow you to build a number of
+	  different kobject sample modules showing how to use kobjects,
+	  ksets, and ktypes properly.
+
+	  If in doubt, say "N" here.
+
+config SAMPLE_KPROBES
+	tristate "Build kprobes examples -- loadable modules only"
+	depends on KPROBES && m
+	help
+	  This build several kprobes example modules.
+
+config SAMPLE_KRETPROBES
+	tristate "Build kretprobes example -- loadable modules only"
+	default m
+	depends on SAMPLE_KPROBES && KRETPROBES
+
+config SAMPLE_HW_BREAKPOINT
+	tristate "Build kernel hardware breakpoint examples -- loadable module only"
+	depends on HAVE_HW_BREAKPOINT && m
+	help
+	  This builds kernel hardware breakpoint example modules.
+
+config SAMPLE_FPROBE
+	tristate "Build fprobe examples -- loadable modules only"
+	depends on FPROBE && m
+	help
+	  This builds a fprobe example module. This module has an option 'symbol'.
+	  You can specify a probed symbol or symbols separated with ','.
+
+config SAMPLE_KFIFO
+	tristate "Build kfifo examples -- loadable modules only"
+	depends on m
+	help
+	  This config option will allow you to build a number of
+	  different kfifo sample modules showing how to use the
+	  generic kfifo API.
+
+	  If in doubt, say "N" here.
+
+config SAMPLE_KDB
+	tristate "Build kdb command example -- loadable modules only"
+	depends on KGDB_KDB && m
+	help
+	  Build an example of how to dynamically add the hello
+	  command to the kdb shell.
+
+config SAMPLE_QMI_CLIENT
+	tristate "Build qmi client sample -- loadable modules only"
+	depends on m
+	depends on ARCH_QCOM
+	depends on NET
+	select QCOM_QMI_HELPERS
+	help
+	  Build an QMI client sample driver, which demonstrates how to
+	  communicate with a remote QRTR service, using QMI encoded messages.
+
+config SAMPLE_RPMSG_CLIENT
+	tristate "Build rpmsg client sample -- loadable modules only"
+	depends on RPMSG && m
+	help
+	  Build an rpmsg client sample driver, which demonstrates how
+	  to communicate with an AMP-configured remote processor over
+	  the rpmsg bus.
+
+config SAMPLE_LIVEPATCH
+	tristate "Build live patching samples -- loadable modules only"
+	depends on LIVEPATCH && m
+	help
+	  Build sample live patch demonstrations.
+
+config SAMPLE_CONFIGFS
+	tristate "Build configfs patching sample -- loadable modules only"
+	depends on CONFIGFS_FS && m
+	help
+	  Builds a sample configfs interface.
+
+config SAMPLE_CONNECTOR
+	tristate "Build connector sample -- loadable modules only"
+	depends on CONNECTOR && HEADERS_INSTALL && m
+	help
+	  When enabled, this builds both a sample kernel module for
+	  the connector interface and a user space tool to communicate
+	  with it.
+	  See also Documentation/driver-api/connector.rst
+
+config SAMPLE_FANOTIFY_ERROR
+	bool "Build fanotify error monitoring sample"
+	depends on FANOTIFY && CC_CAN_LINK && HEADERS_INSTALL
+	help
+	  When enabled, this builds an example code that uses the
+	  FAN_FS_ERROR fanotify mechanism to monitor filesystem
+	  errors.
+	  See also Documentation/admin-guide/filesystem-monitoring.rst.
+
+config SAMPLE_HIDRAW
+	bool "hidraw sample"
+	depends on CC_CAN_LINK && HEADERS_INSTALL
+
+config SAMPLE_LANDLOCK
+	bool "Landlock example"
+	depends on CC_CAN_LINK && HEADERS_INSTALL
+	help
+	  Build a simple Landlock sandbox manager able to start a process
+	  restricted by a user-defined filesystem access control policy.
+
+config SAMPLE_PIDFD
+	bool "pidfd sample"
+	depends on CC_CAN_LINK && HEADERS_INSTALL
+
+config SAMPLE_SECCOMP
+	bool "Build seccomp sample code"
+	depends on SECCOMP_FILTER && CC_CAN_LINK && HEADERS_INSTALL
+	help
+	  Build samples of seccomp filters using various methods of
+	  BPF filter construction.
+
+config SAMPLE_TIMER
+	bool "Timer sample"
+	depends on CC_CAN_LINK && HEADERS_INSTALL
+
+config SAMPLE_TSM_MR
+	tristate "TSM measurement sample"
+	select CRYPTO_LIB_SHA256
+	select CRYPTO_LIB_SHA512
+	select TSM_MEASUREMENTS
+	select VIRT_DRIVERS
+	help
+	  Build a sample module that emulates MRs (Measurement Registers) and
+	  exposes them to user mode applications through the TSM sysfs
+	  interface (/sys/class/misc/tsm_mr_sample/emulated_mr/).
+
+	  The module name will be tsm-mr-sample when built as a module.
+
+config SAMPLE_UHID
+	bool "UHID sample"
+	depends on CC_CAN_LINK && HEADERS_INSTALL
+	help
+	  Build UHID sample program.
+
+config SAMPLE_VFIO_MDEV_MTTY
+	tristate "Build VFIO mtty example mediated device sample code"
+	depends on VFIO
+	select VFIO_MDEV
+	help
+	  Build a virtual tty sample driver for use as a VFIO
+	  mediated device
+
+config SAMPLE_VFIO_MDEV_MDPY
+	tristate "Build VFIO mdpy example mediated device sample code"
+	depends on VFIO
+	select VFIO_MDEV
+	help
+	  Build a virtual display sample driver for use as a VFIO
+	  mediated device.  It is a simple framebuffer and supports
+	  the region display interface (VFIO_GFX_PLANE_TYPE_REGION).
+
+config SAMPLE_VFIO_MDEV_MDPY_FB
+	tristate "Build VFIO mdpy example guest fbdev driver"
+	depends on FB
+	select FB_IOMEM_HELPERS
+	help
+	  Guest fbdev driver for the virtual display sample driver.
+
+config SAMPLE_VFIO_MDEV_MBOCHS
+	tristate "Build VFIO mbochs example mediated device sample code"
+	depends on VFIO
+	select VFIO_MDEV
+	select DMA_SHARED_BUFFER
+	help
+	  Build a virtual display sample driver for use as a VFIO
+	  mediated device.  It supports the region display interface
+	  (VFIO_GFX_PLANE_TYPE_DMABUF).
+	  Emulate enough of qemu stdvga to make bochs-drm.ko happy.
+	  That is basically the vram memory bar and the bochs dispi
+	  interface vbe registers in the mmio register bar.
+	  Specifically it does *not* include any legacy vga stuff.
+	  Device looks a lot like "qemu -device secondary-vga".
+
+config SAMPLE_ANDROID_BINDERFS
+	bool "Build Android binderfs example"
+	depends on CC_CAN_LINK && HEADERS_INSTALL
+	help
+	  Builds a sample program to illustrate the use of the Android binderfs
+	  filesystem.
+
+config SAMPLE_VFS
+	bool "Build example programs that use new VFS system calls"
+	depends on CC_CAN_LINK && HEADERS_INSTALL
+	help
+	  Build example userspace programs that use new VFS system calls such
+	  as mount API and statx().  Note that this is restricted to the x86
+	  arch whilst it accesses system calls that aren't yet in all arches.
+
+config SAMPLE_INTEL_MEI
+	bool "Build example program working with intel mei driver"
+	depends on INTEL_MEI
+	depends on CC_CAN_LINK && HEADERS_INSTALL
+	help
+	  Build a sample program to work with mei device.
+
+config SAMPLE_TPS6594_PFSM
+	bool "Build example program working with TPS6594 PFSM driver"
+	depends on HEADERS_INSTALL
+	depends on CC_CAN_LINK
+	help
+	  Build a sample program to work with PFSM devices.
+
+config SAMPLE_WATCHDOG
+	bool "watchdog sample"
+	depends on CC_CAN_LINK
+
+config SAMPLE_WATCH_QUEUE
+	bool "Build example watch_queue notification API consumer"
+	depends on CC_CAN_LINK && HEADERS_INSTALL
+	help
+	  Build example userspace program to use the new mount_notify(),
+	  sb_notify() syscalls and the KEYCTL_WATCH_KEY keyctl() function.
+
+config SAMPLE_CORESIGHT_SYSCFG
+	tristate "Build example loadable module for CoreSight config"
+	depends on CORESIGHT && m
+	help
+	  Build an example loadable module that adds new CoreSight features
+	  and configuration using the CoreSight system configuration API.
+	  This demonstrates how a user may create their own CoreSight
+	  configurations and easily load them into the system at runtime.
+
+config SAMPLE_KMEMLEAK
+	tristate "Simple test for the kernel memory leak detector"
+	depends on DEBUG_KMEMLEAK && m
+	help
+	  Build a sample program which have explicitly leaks memory to test
+	  kmemleak.
+
+config SAMPLE_CGROUP
+	bool "Build cgroup sample code"
+	depends on CGROUPS && CC_CAN_LINK && HEADERS_INSTALL
+	help
+	  Build samples that demonstrate the usage of the cgroup API.
+
+config SAMPLE_CHECK_EXEC
+	bool "Exec secure bits examples"
+	depends on CC_CAN_LINK && HEADERS_INSTALL
+	help
+	  Build a tool to easily configure SECBIT_EXEC_RESTRICT_FILE and
+	  SECBIT_EXEC_DENY_INTERACTIVE, and a simple script interpreter to
+	  demonstrate how they should be used with execveat(2) +
+	  AT_EXECVE_CHECK.
+
+config SAMPLE_HUNG_TASK
+	tristate "Hung task detector test code"
+	depends on DETECT_HUNG_TASK && DEBUG_FS
+	help
+	  Build a module that provides debugfs files (e.g., mutex, semaphore,
+	  rw_semaphore_read, rw_semaphore_write) under <debugfs>/hung_task.
+	  Reading these files with multiple processes triggers hung task
+	  detection by holding locks for a long time (256 seconds).
+
+source "samples/rust/Kconfig"
+
+source "samples/damon/Kconfig"
+
+endif # SAMPLES
+
+config HAVE_SAMPLE_FTRACE_DIRECT
+	bool
+
+config HAVE_SAMPLE_FTRACE_DIRECT_MULTI
+	bool

linux-7.2.3/samples/Makefile

@@ -0,0 +1,47 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for Linux samples code
+
+subdir-$(CONFIG_SAMPLE_AUXDISPLAY)	+= auxdisplay
+subdir-$(CONFIG_SAMPLE_ANDROID_BINDERFS) += binderfs
+subdir-$(CONFIG_SAMPLE_CHECK_EXEC)	+= check-exec
+subdir-$(CONFIG_SAMPLE_CGROUP) += cgroup
+obj-$(CONFIG_SAMPLE_CONFIGFS)		+= configfs/
+obj-$(CONFIG_SAMPLE_CONNECTOR)		+= connector/
+obj-$(CONFIG_SAMPLE_FANOTIFY_ERROR)	+= fanotify/
+subdir-$(CONFIG_SAMPLE_HIDRAW)		+= hidraw
+obj-$(CONFIG_SAMPLE_HW_BREAKPOINT)	+= hw_breakpoint/
+obj-$(CONFIG_SAMPLE_KDB)		+= kdb/
+obj-$(CONFIG_SAMPLE_KFIFO)		+= kfifo/
+obj-$(CONFIG_SAMPLE_KOBJECT)		+= kobject/
+obj-$(CONFIG_SAMPLE_KPROBES)		+= kprobes/
+subdir-$(CONFIG_SAMPLE_LANDLOCK)	+= landlock
+obj-$(CONFIG_SAMPLE_LIVEPATCH)		+= livepatch/
+subdir-$(CONFIG_SAMPLE_PIDFD)		+= pidfd
+obj-$(CONFIG_SAMPLE_QMI_CLIENT)		+= qmi/
+obj-$(CONFIG_SAMPLE_RPMSG_CLIENT)	+= rpmsg/
+subdir-$(CONFIG_SAMPLE_SECCOMP)		+= seccomp
+subdir-$(CONFIG_SAMPLE_TIMER)		+= timers
+obj-$(CONFIG_SAMPLE_TRACE_EVENTS)	+= trace_events/
+obj-$(CONFIG_SAMPLE_TRACE_CUSTOM_EVENTS) += trace_events/
+obj-$(CONFIG_SAMPLE_TRACE_PRINTK)	+= trace_printk/
+obj-$(CONFIG_SAMPLE_FTRACE_DIRECT)	+= ftrace/
+obj-$(CONFIG_SAMPLE_FTRACE_DIRECT_MULTI) += ftrace/
+obj-$(CONFIG_SAMPLE_FTRACE_OPS)		+= ftrace/
+obj-$(CONFIG_SAMPLE_TRACE_ARRAY)	+= ftrace/
+subdir-$(CONFIG_SAMPLE_UHID)		+= uhid
+obj-$(CONFIG_VIDEO_PCI_SKELETON)	+= v4l/
+obj-y					+= vfio-mdev/
+subdir-$(CONFIG_SAMPLE_VFS)		+= vfs
+obj-$(CONFIG_SAMPLE_INTEL_MEI)		+= mei/
+obj-$(CONFIG_SAMPLE_TPS6594_PFSM)	+= pfsm/
+subdir-$(CONFIG_SAMPLE_WATCHDOG)	+= watchdog
+subdir-$(CONFIG_SAMPLE_WATCH_QUEUE)	+= watch_queue
+obj-$(CONFIG_SAMPLE_KMEMLEAK)		+= kmemleak/
+obj-$(CONFIG_SAMPLE_CORESIGHT_SYSCFG)	+= coresight/
+obj-$(CONFIG_SAMPLE_FPROBE)		+= fprobe/
+obj-$(CONFIG_SAMPLES_RUST)		+= rust/
+obj-$(CONFIG_SAMPLE_DAMON_WSSE)		+= damon/
+obj-$(CONFIG_SAMPLE_DAMON_PRCL)		+= damon/
+obj-$(CONFIG_SAMPLE_DAMON_MTIER)	+= damon/
+obj-$(CONFIG_SAMPLE_HUNG_TASK)		+= hung_task/
+obj-$(CONFIG_SAMPLE_TSM_MR)		+= tsm-mr/

linux-7.2.3/samples/acrn/Makefile

@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0
+
+.PHONY: vm-sample
+
+vm-sample: vm-sample.o payload.o
+	$(CC) $^ -o $@
+
+payload.o: payload.ld guest16.o
+	$(LD) -T $< -o $@
+
+clean:
+	rm *.o vm-sample

linux-7.2.3/samples/acrn/guest.ld

@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+OUTPUT_FORMAT(binary)
+SECTIONS
+{
+        .start : { *(.start) }
+        .text : { *(.text*) }
+        .rodata : { *(.rodata) }
+        .data : { *(.data) }
+}

linux-7.2.3/samples/acrn/payload.ld

@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+SECTIONS
+{
+        .payload16 0 : {
+                guest16 = .;
+                guest16.o(.text)
+                guest16_end = .;
+        }
+}

linux-7.2.3/samples/acrn/vm-sample.c

@@ -0,0 +1,132 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A sample program to run a User VM on the ACRN hypervisor
+ *
+ * This sample runs in a Service VM, which is a privileged VM of ACRN.
+ * CONFIG_ACRN_HSM needs to be enabled in the Service VM.
+ *
+ * Guest VM code in guest16.s will be executed after the VM launched.
+ *
+ * Copyright (C) 2020 Intel Corporation. All rights reserved.
+ */
+#include <stdio.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <signal.h>
+#include <sys/ioctl.h>
+#include <linux/acrn.h>
+
+#define GUEST_MEMORY_SIZE	(1024*1024)
+void *guest_memory;
+
+extern const unsigned char guest16[], guest16_end[];
+static char io_request_page[4096] __attribute__((aligned(4096)));
+static struct acrn_io_request *io_req_buf = (struct acrn_io_request *)io_request_page;
+
+__u16 vcpu_num;
+__u16 vmid;
+
+int hsm_fd;
+int is_running = 1;
+
+void vm_exit(int sig)
+{
+	sig = sig;
+
+	is_running = 0;
+	ioctl(hsm_fd, ACRN_IOCTL_PAUSE_VM, vmid);
+	ioctl(hsm_fd, ACRN_IOCTL_DESTROY_IOREQ_CLIENT, 0);
+}
+
+int main(int argc, char **argv)
+{
+	int vcpu_id, ret;
+	struct acrn_vm_creation create_vm = {0};
+	struct acrn_vm_memmap ram_map = {0};
+	struct acrn_vcpu_regs regs;
+	struct acrn_io_request *io_req;
+	struct acrn_ioreq_notify __attribute__((aligned(8))) notify;
+
+	argc = argc;
+	argv = argv;
+
+	ret = posix_memalign(&guest_memory, 4096, GUEST_MEMORY_SIZE);
+	if (ret < 0) {
+		printf("Not enough memory!\n");
+		return -1;
+	}
+	hsm_fd = open("/dev/acrn_hsm", O_RDWR|O_CLOEXEC);
+
+	create_vm.ioreq_buf = (__u64)io_req_buf;
+	ret = ioctl(hsm_fd, ACRN_IOCTL_CREATE_VM, &create_vm);
+	printf("Created VM! [%d]\n", ret);
+	vcpu_num = create_vm.vcpu_num;
+	vmid = create_vm.vmid;
+
+	/* setup guest memory */
+	ram_map.type = ACRN_MEMMAP_RAM;
+	ram_map.vma_base = (__u64)guest_memory;
+	ram_map.len = GUEST_MEMORY_SIZE;
+	ram_map.user_vm_pa = 0;
+	ram_map.attr = ACRN_MEM_ACCESS_RWX;
+	ret = ioctl(hsm_fd, ACRN_IOCTL_SET_MEMSEG, &ram_map);
+	printf("Set up VM memory! [%d]\n", ret);
+
+	memcpy(guest_memory, guest16, guest16_end-guest16);
+
+	/* setup vcpu registers */
+	memset(&regs, 0, sizeof(regs));
+	regs.vcpu_id = 0;
+	regs.vcpu_regs.rip = 0;
+
+	/* CR0_ET | CR0_NE */
+	regs.vcpu_regs.cr0 = 0x30U;
+	regs.vcpu_regs.cs_ar = 0x009FU;
+	regs.vcpu_regs.cs_sel = 0xF000U;
+	regs.vcpu_regs.cs_limit = 0xFFFFU;
+	regs.vcpu_regs.cs_base = 0 & 0xFFFF0000UL;
+	regs.vcpu_regs.rip = 0 & 0xFFFFUL;
+
+	ret = ioctl(hsm_fd, ACRN_IOCTL_SET_VCPU_REGS, &regs);
+	printf("Set up VM BSP registers! [%d]\n", ret);
+
+	/* create an ioreq client for this VM */
+	ret = ioctl(hsm_fd, ACRN_IOCTL_CREATE_IOREQ_CLIENT, 0);
+	printf("Created IO request client! [%d]\n", ret);
+
+	/* run vm */
+	ret = ioctl(hsm_fd, ACRN_IOCTL_START_VM, vmid);
+	printf("Start VM! [%d]\n", ret);
+
+	signal(SIGINT, vm_exit);
+	while (is_running) {
+		ret = ioctl(hsm_fd, ACRN_IOCTL_ATTACH_IOREQ_CLIENT, 0);
+
+		for (vcpu_id = 0; vcpu_id < vcpu_num; vcpu_id++) {
+			io_req = &io_req_buf[vcpu_id];
+			if ((__sync_add_and_fetch(&io_req->processed, 0) == ACRN_IOREQ_STATE_PROCESSING)
+					&& (!io_req->kernel_handled))
+				if (io_req->type == ACRN_IOREQ_TYPE_PORTIO) {
+					int bytes, port, in;
+
+					port = io_req->reqs.pio_request.address;
+					bytes = io_req->reqs.pio_request.size;
+					in = (io_req->reqs.pio_request.direction == ACRN_IOREQ_DIR_READ);
+					printf("Guest VM %s PIO[%x] with size[%x]\n", in ? "read" : "write", port, bytes);
+
+					notify.vmid = vmid;
+					notify.vcpu = vcpu_id;
+					ioctl(hsm_fd, ACRN_IOCTL_NOTIFY_REQUEST_FINISH, &notify);
+				}
+		}
+	}
+
+	ret = ioctl(hsm_fd, ACRN_IOCTL_DESTROY_VM, NULL);
+	printf("Destroy VM! [%d]\n", ret);
+	close(hsm_fd);
+	free(guest_memory);
+	return 0;
+}

linux-7.2.3/samples/auxdisplay/.gitignore

@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+/cfag12864b-example

linux-7.2.3/samples/auxdisplay/Makefile

@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0
+userprogs-always-y += cfag12864b-example

linux-7.2.3/samples/auxdisplay/cfag12864b-example.c

@@ -0,0 +1,267 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *    Filename: cfag12864b-example.c
+ *     Version: 0.1.0
+ * Description: cfag12864b LCD userspace example program
+ *
+ *      Author: Copyright (C) Miguel Ojeda <ojeda@kernel.org>
+ *        Date: 2006-10-31
+ */
+
+/*
+ * ------------------------
+ * start of cfag12864b code
+ * ------------------------
+ */
+
+#include <string.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+
+#define CFAG12864B_WIDTH		(128)
+#define CFAG12864B_HEIGHT		(64)
+#define CFAG12864B_SIZE			(128 * 64 / 8)
+#define CFAG12864B_BPB			(8)
+#define CFAG12864B_ADDRESS(x, y)	((y) * CFAG12864B_WIDTH / \
+					CFAG12864B_BPB + (x) / CFAG12864B_BPB)
+#define CFAG12864B_BIT(n)		(((unsigned char) 1) << (n))
+
+#undef CFAG12864B_DOCHECK
+#ifdef CFAG12864B_DOCHECK
+	#define CFAG12864B_CHECK(x, y)		((x) < CFAG12864B_WIDTH && \
+						(y) < CFAG12864B_HEIGHT)
+#else
+	#define CFAG12864B_CHECK(x, y)		(1)
+#endif
+
+int cfag12864b_fd;
+unsigned char * cfag12864b_mem;
+unsigned char cfag12864b_buffer[CFAG12864B_SIZE];
+
+/*
+ * init a cfag12864b framebuffer device
+ *
+ * No error:       return = 0
+ * Unable to open: return = -1
+ * Unable to mmap: return = -2
+ */
+static int cfag12864b_init(char *path)
+{
+	cfag12864b_fd = open(path, O_RDWR);
+	if (cfag12864b_fd == -1)
+		return -1;
+
+	cfag12864b_mem = mmap(0, CFAG12864B_SIZE, PROT_READ | PROT_WRITE,
+		MAP_SHARED, cfag12864b_fd, 0);
+	if (cfag12864b_mem == MAP_FAILED) {
+		close(cfag12864b_fd);
+		return -2;
+	}
+
+	return 0;
+}
+
+/*
+ * exit a cfag12864b framebuffer device
+ */
+static void cfag12864b_exit(void)
+{
+	munmap(cfag12864b_mem, CFAG12864B_SIZE);
+	close(cfag12864b_fd);
+}
+
+/*
+ * set (x, y) pixel
+ */
+static void cfag12864b_set(unsigned char x, unsigned char y)
+{
+	if (CFAG12864B_CHECK(x, y))
+		cfag12864b_buffer[CFAG12864B_ADDRESS(x, y)] |=
+			CFAG12864B_BIT(x % CFAG12864B_BPB);
+}
+
+/*
+ * unset (x, y) pixel
+ */
+static void cfag12864b_unset(unsigned char x, unsigned char y)
+{
+	if (CFAG12864B_CHECK(x, y))
+		cfag12864b_buffer[CFAG12864B_ADDRESS(x, y)] &=
+			~CFAG12864B_BIT(x % CFAG12864B_BPB);
+}
+
+/*
+ * is set (x, y) pixel?
+ *
+ * Pixel off: return = 0
+ * Pixel on:  return = 1
+ */
+static unsigned char cfag12864b_isset(unsigned char x, unsigned char y)
+{
+	if (CFAG12864B_CHECK(x, y))
+		if (cfag12864b_buffer[CFAG12864B_ADDRESS(x, y)] &
+			CFAG12864B_BIT(x % CFAG12864B_BPB))
+			return 1;
+
+	return 0;
+}
+
+/*
+ * not (x, y) pixel
+ */
+static void cfag12864b_not(unsigned char x, unsigned char y)
+{
+	if (cfag12864b_isset(x, y))
+		cfag12864b_unset(x, y);
+	else
+		cfag12864b_set(x, y);
+}
+
+/*
+ * fill (set all pixels)
+ */
+static void cfag12864b_fill(void)
+{
+	unsigned short i;
+
+	for (i = 0; i < CFAG12864B_SIZE; i++)
+		cfag12864b_buffer[i] = 0xFF;
+}
+
+/*
+ * clear (unset all pixels)
+ */
+static void cfag12864b_clear(void)
+{
+	unsigned short i;
+
+	for (i = 0; i < CFAG12864B_SIZE; i++)
+		cfag12864b_buffer[i] = 0;
+}
+
+/*
+ * format a [128*64] matrix
+ *
+ * Pixel off: src[i] = 0
+ * Pixel on:  src[i] > 0
+ */
+static void cfag12864b_format(unsigned char * matrix)
+{
+	unsigned char i, j, n;
+
+	for (i = 0; i < CFAG12864B_HEIGHT; i++)
+	for (j = 0; j < CFAG12864B_WIDTH / CFAG12864B_BPB; j++) {
+		cfag12864b_buffer[i * CFAG12864B_WIDTH / CFAG12864B_BPB +
+			j] = 0;
+		for (n = 0; n < CFAG12864B_BPB; n++)
+			if (matrix[i * CFAG12864B_WIDTH +
+				j * CFAG12864B_BPB + n])
+				cfag12864b_buffer[i * CFAG12864B_WIDTH /
+					CFAG12864B_BPB + j] |=
+					CFAG12864B_BIT(n);
+	}
+}
+
+/*
+ * blit buffer to lcd
+ */
+static void cfag12864b_blit(void)
+{
+	memcpy(cfag12864b_mem, cfag12864b_buffer, CFAG12864B_SIZE);
+}
+
+/*
+ * ----------------------
+ * end of cfag12864b code
+ * ----------------------
+ */
+
+#include <stdio.h>
+
+#define EXAMPLES	6
+
+static void example(unsigned char n)
+{
+	unsigned short i, j;
+	unsigned char matrix[CFAG12864B_WIDTH * CFAG12864B_HEIGHT];
+
+	if (n > EXAMPLES)
+		return;
+
+	printf("Example %i/%i - ", n, EXAMPLES);
+
+	switch (n) {
+	case 1:
+		printf("Draw points setting bits");
+		cfag12864b_clear();
+		for (i = 0; i < CFAG12864B_WIDTH; i += 2)
+			for (j = 0; j < CFAG12864B_HEIGHT; j += 2)
+				cfag12864b_set(i, j);
+		break;
+
+	case 2:
+		printf("Clear the LCD");
+		cfag12864b_clear();
+		break;
+
+	case 3:
+		printf("Draw rows formatting a [128*64] matrix");
+		memset(matrix, 0, CFAG12864B_WIDTH * CFAG12864B_HEIGHT);
+		for (i = 0; i < CFAG12864B_WIDTH; i++)
+			for (j = 0; j < CFAG12864B_HEIGHT; j += 2)
+				matrix[j * CFAG12864B_WIDTH + i] = 1;
+		cfag12864b_format(matrix);
+		break;
+
+	case 4:
+		printf("Fill the lcd");
+		cfag12864b_fill();
+		break;
+
+	case 5:
+		printf("Draw columns unsetting bits");
+		for (i = 0; i < CFAG12864B_WIDTH; i += 2)
+			for (j = 0; j < CFAG12864B_HEIGHT; j++)
+				cfag12864b_unset(i, j);
+		break;
+
+	case 6:
+		printf("Do negative not-ing all bits");
+		for (i = 0; i < CFAG12864B_WIDTH; i++)
+			for (j = 0; j < CFAG12864B_HEIGHT; j ++)
+				cfag12864b_not(i, j);
+		break;
+	}
+
+	puts(" - [Press Enter]");
+}
+
+int main(int argc, char *argv[])
+{
+	unsigned char n;
+
+	if (argc != 2) {
+		printf(
+			"Syntax:  %s fbdev\n"
+			"Usually: /dev/fb0, /dev/fb1...\n", argv[0]);
+		return -1;
+	}
+
+	if (cfag12864b_init(argv[1])) {
+		printf("Can't init %s fbdev\n", argv[1]);
+		return -2;
+	}
+
+	for (n = 1; n <= EXAMPLES; n++) {
+		example(n);
+		cfag12864b_blit();
+		while (getchar() != '\n');
+	}
+
+	cfag12864b_exit();
+
+	return 0;
+}

linux-7.2.3/samples/binderfs/.gitignore

@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0
+/binderfs_example

linux-7.2.3/samples/binderfs/Makefile

@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+userprogs-always-y += binderfs_example
+
+userccflags += -I usr/include

linux-7.2.3/samples/binderfs/binderfs_example.c

@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include <linux/android/binder.h>
+#include <linux/android/binderfs.h>
+
+int main(int argc, char *argv[])
+{
+	int fd, ret, saved_errno;
+	struct binderfs_device device = { 0 };
+
+	ret = unshare(CLONE_NEWNS);
+	if (ret < 0) {
+		fprintf(stderr, "%s - Failed to unshare mount namespace\n",
+			strerror(errno));
+		exit(EXIT_FAILURE);
+	}
+
+	ret = mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0);
+	if (ret < 0) {
+		fprintf(stderr, "%s - Failed to mount / as private\n",
+			strerror(errno));
+		exit(EXIT_FAILURE);
+	}
+
+	ret = mkdir("/dev/binderfs", 0755);
+	if (ret < 0 && errno != EEXIST) {
+		fprintf(stderr, "%s - Failed to create binderfs mountpoint\n",
+			strerror(errno));
+		exit(EXIT_FAILURE);
+	}
+
+	ret = mount(NULL, "/dev/binderfs", "binder", 0, 0);
+	if (ret < 0) {
+		fprintf(stderr, "%s - Failed to mount binderfs\n",
+			strerror(errno));
+		exit(EXIT_FAILURE);
+	}
+
+	memcpy(device.name, "my-binder", strlen("my-binder"));
+
+	fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC);
+	if (fd < 0) {
+		fprintf(stderr, "%s - Failed to open binder-control device\n",
+			strerror(errno));
+		exit(EXIT_FAILURE);
+	}
+
+	ret = ioctl(fd, BINDER_CTL_ADD, &device);
+	saved_errno = errno;
+	close(fd);
+	errno = saved_errno;
+	if (ret < 0) {
+		fprintf(stderr, "%s - Failed to allocate new binder device\n",
+			strerror(errno));
+		exit(EXIT_FAILURE);
+	}
+
+	printf("Allocated new binder device with major %d, minor %d, and name %s\n",
+	       device.major, device.minor, device.name);
+
+	ret = unlink("/dev/binderfs/my-binder");
+	if (ret < 0) {
+		fprintf(stderr, "%s - Failed to delete binder device\n",
+			strerror(errno));
+		exit(EXIT_FAILURE);
+	}
+
+	/* Cleanup happens when the mount namespace dies. */
+	exit(EXIT_SUCCESS);
+}

linux-7.2.3/samples/bpf/.gitignore

@@ -0,0 +1,51 @@
+# SPDX-License-Identifier: GPL-2.0-only
+cpustat
+fds_example
+hbm
+ibumad
+lathist
+lwt_len_hist
+map_perf_test
+offwaketime
+per_socket_stats_example
+sampleip
+sock_example
+sockex1
+sockex2
+sockex3
+spintest
+syscall_nrs.h
+syscall_tp
+task_fd_query
+tc_l2_redirect
+test_cgrp2_array_pin
+test_cgrp2_attach
+test_cgrp2_attach2
+test_cgrp2_sock
+test_cgrp2_sock2
+test_current_task_under_cgroup
+test_lru_dist
+test_map_in_map
+test_overhead
+test_probe_write_user
+trace_event
+trace_output
+tracex1
+tracex2
+tracex3
+tracex4
+tracex5
+tracex6
+tracex7
+xdp_adjust_tail
+xdp_fwd
+xdp_router_ipv4
+xdp_tx_iptunnel
+testfile.img
+hbm_out.log
+iperf.*
+*.out
+*.skel.h
+/vmlinux.h
+/bpftool/
+/libbpf/

linux-7.2.3/samples/bpf/Makefile

@@ -0,0 +1,392 @@
+# SPDX-License-Identifier: GPL-2.0
+
+BPF_SAMPLES_PATH ?= $(abspath $(src))
+TOOLS_PATH := $(BPF_SAMPLES_PATH)/../../tools
+
+pound := \#
+
+# List of programs to build
+tprogs-y := test_lru_dist
+tprogs-y += sock_example
+tprogs-y += fds_example
+tprogs-y += sockex1
+tprogs-y += sockex2
+tprogs-y += sockex3
+tprogs-y += tracex1
+tprogs-y += tracex3
+tprogs-y += tracex4
+tprogs-y += tracex5
+tprogs-y += tracex6
+tprogs-y += trace_output
+tprogs-y += lathist
+tprogs-y += offwaketime
+tprogs-y += spintest
+tprogs-y += map_perf_test
+tprogs-y += xdp_router_ipv4
+tprogs-y += trace_event
+tprogs-y += sampleip
+tprogs-y += tc_l2_redirect
+tprogs-y += lwt_len_hist
+tprogs-y += xdp_tx_iptunnel
+tprogs-y += test_map_in_map
+tprogs-y += per_socket_stats_example
+tprogs-y += syscall_tp
+tprogs-y += cpustat
+tprogs-y += xdp_adjust_tail
+tprogs-y += xdp_fwd
+tprogs-y += task_fd_query
+tprogs-y += ibumad
+tprogs-y += hbm
+
+# Libbpf dependencies
+LIBBPF_SRC = $(TOOLS_PATH)/lib/bpf
+LIBBPF_OUTPUT = $(abspath $(BPF_SAMPLES_PATH))/libbpf
+LIBBPF_DESTDIR = $(LIBBPF_OUTPUT)
+LIBBPF_INCLUDE = $(LIBBPF_DESTDIR)/include
+LIBBPF = $(LIBBPF_OUTPUT)/libbpf.a
+
+CGROUP_HELPERS := ../../tools/testing/selftests/bpf/cgroup_helpers.o
+TRACE_HELPERS := ../../tools/testing/selftests/bpf/trace_helpers.o
+XDP_SAMPLE := xdp_sample_user.o
+
+fds_example-objs := fds_example.o
+sockex1-objs := sockex1_user.o
+sockex2-objs := sockex2_user.o
+sockex3-objs := sockex3_user.o
+tracex1-objs := tracex1_user.o $(TRACE_HELPERS)
+tracex3-objs := tracex3_user.o
+tracex4-objs := tracex4_user.o
+tracex5-objs := tracex5_user.o $(TRACE_HELPERS)
+tracex6-objs := tracex6_user.o
+trace_output-objs := trace_output_user.o
+lathist-objs := lathist_user.o
+offwaketime-objs := offwaketime_user.o $(TRACE_HELPERS)
+spintest-objs := spintest_user.o $(TRACE_HELPERS)
+map_perf_test-objs := map_perf_test_user.o
+test_overhead-objs := test_overhead_user.o
+trace_event-objs := trace_event_user.o $(TRACE_HELPERS)
+sampleip-objs := sampleip_user.o $(TRACE_HELPERS)
+tc_l2_redirect-objs := tc_l2_redirect_user.o
+lwt_len_hist-objs := lwt_len_hist_user.o
+xdp_tx_iptunnel-objs := xdp_tx_iptunnel_user.o
+test_map_in_map-objs := test_map_in_map_user.o
+per_socket_stats_example-objs := cookie_uid_helper_example.o
+syscall_tp-objs := syscall_tp_user.o
+cpustat-objs := cpustat_user.o
+xdp_adjust_tail-objs := xdp_adjust_tail_user.o
+xdp_fwd-objs := xdp_fwd_user.o
+task_fd_query-objs := task_fd_query_user.o $(TRACE_HELPERS)
+ibumad-objs := ibumad_user.o
+hbm-objs := hbm.o $(CGROUP_HELPERS)
+
+xdp_router_ipv4-objs := xdp_router_ipv4_user.o $(XDP_SAMPLE)
+
+# Tell kbuild to always build the programs
+always-y := $(tprogs-y)
+always-y += sockex1_kern.o
+always-y += sockex2_kern.o
+always-y += sockex3_kern.o
+always-y += tracex1.bpf.o
+always-y += tracex3.bpf.o
+always-y += tracex4.bpf.o
+always-y += tracex5.bpf.o
+always-y += tracex6.bpf.o
+always-y += trace_output.bpf.o
+always-y += tcbpf1_kern.o
+always-y += tc_l2_redirect_kern.o
+always-y += lathist_kern.o
+always-y += offwaketime.bpf.o
+always-y += spintest.bpf.o
+always-y += map_perf_test.bpf.o
+always-y += parse_varlen.o parse_simple.o parse_ldabs.o
+always-y += trace_event_kern.o
+always-y += sampleip_kern.o
+always-y += lwt_len_hist.bpf.o
+always-y += xdp_tx_iptunnel_kern.o
+always-y += test_map_in_map.bpf.o
+always-y += tcp_synrto_kern.o
+always-y += tcp_rwnd_kern.o
+always-y += tcp_bufs_kern.o
+always-y += tcp_cong_kern.o
+always-y += tcp_iw_kern.o
+always-y += tcp_clamp_kern.o
+always-y += tcp_basertt_kern.o
+always-y += tcp_tos_reflect_kern.o
+always-y += tcp_dumpstats_kern.o
+always-y += xdp2skb_meta_kern.o
+always-y += syscall_tp_kern.o
+always-y += cpustat_kern.o
+always-y += xdp_adjust_tail_kern.o
+always-y += xdp_fwd_kern.o
+always-y += task_fd_query_kern.o
+always-y += ibumad_kern.o
+always-y += hbm_out_kern.o
+always-y += hbm_edt_kern.o
+
+COMMON_CFLAGS = $(TPROGS_USER_CFLAGS)
+TPROGS_LDFLAGS = $(TPROGS_USER_LDFLAGS)
+
+ifeq ($(ARCH), arm)
+# Strip all except -D__LINUX_ARM_ARCH__ option needed to handle linux
+# headers when arm instruction set identification is requested.
+ARM_ARCH_SELECTOR := $(filter -D__LINUX_ARM_ARCH__%, $(KBUILD_CFLAGS))
+BPF_EXTRA_CFLAGS := $(ARM_ARCH_SELECTOR)
+TPROGS_CFLAGS += $(ARM_ARCH_SELECTOR)
+endif
+
+ifeq ($(ARCH), mips)
+TPROGS_CFLAGS += -D__SANE_USERSPACE_TYPES__
+ifdef CONFIG_MACH_LOONGSON64
+BPF_EXTRA_CFLAGS += -I$(srctree)/arch/mips/include/asm/mach-loongson64
+BPF_EXTRA_CFLAGS += -I$(srctree)/arch/mips/include/asm/mach-generic
+endif
+endif
+
+ifeq ($(ARCH), x86)
+BPF_EXTRA_CFLAGS += -fcf-protection
+endif
+
+COMMON_CFLAGS += -Wall -O2
+COMMON_CFLAGS += -Wmissing-prototypes
+COMMON_CFLAGS += -Wstrict-prototypes
+COMMON_CFLAGS += $(call try-run,\
+	printf "int main() { return 0; }" |\
+	$(CC) -Werror -fsanitize=bounds -x c - -o "$$TMP",-fsanitize=bounds,)
+
+TPROGS_CFLAGS += $(COMMON_CFLAGS)
+TPROGS_CFLAGS += -I$(objtree)/usr/include
+TPROGS_CFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
+TPROGS_CFLAGS += -I$(LIBBPF_INCLUDE)
+TPROGS_CFLAGS += -I$(srctree)/tools/include
+TPROGS_CFLAGS += -I$(srctree)/tools/perf
+TPROGS_CFLAGS += -I$(srctree)/tools/lib
+TPROGS_CFLAGS += -DHAVE_ATTR_TEST=0
+
+ifdef SYSROOT
+COMMON_CFLAGS += --sysroot=$(SYSROOT)
+TPROGS_LDFLAGS := -L$(SYSROOT)/usr/lib
+endif
+
+TPROGS_LDLIBS			+= $(LIBBPF) -lelf -lz
+TPROGLDLIBS_xdp_router_ipv4	+= -lm -pthread
+TPROGLDLIBS_tracex4		+= -lrt
+TPROGLDLIBS_trace_output	+= -lrt
+TPROGLDLIBS_map_perf_test	+= -lrt
+
+# Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
+# make M=samples/bpf LLC=~/git/llvm-project/llvm/build/bin/llc CLANG=~/git/llvm-project/llvm/build/bin/clang
+LLC ?= llc
+CLANG ?= clang
+OPT ?= opt
+LLVM_DIS ?= llvm-dis
+LLVM_OBJCOPY ?= llvm-objcopy
+LLVM_READELF ?= llvm-readelf
+BTF_PAHOLE ?= pahole
+
+# Detect that we're cross compiling and use the cross compiler
+ifdef CROSS_COMPILE
+CLANG_ARCH_ARGS = --target=$(notdir $(CROSS_COMPILE:%-=%))
+endif
+
+# Don't evaluate probes and warnings if we need to run make recursively
+ifneq ($(src),)
+HDR_PROBE := $(shell printf "$(pound)include <linux/types.h>\n struct list_head { int a; }; int main() { return 0; }" | \
+	$(CC) $(TPROGS_CFLAGS) $(TPROGS_LDFLAGS) -x c - \
+	-o /dev/null 2>/dev/null && echo okay)
+
+ifeq ($(HDR_PROBE),)
+$(warning WARNING: Detected possible issues with include path.)
+$(warning WARNING: Please install kernel headers locally (make headers_install).)
+endif
+
+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')
+BTF_LLVM_PROBE := $(shell echo "int main() { return 0; }" | \
+			  $(CLANG) --target=bpf -O2 -g -c -x c - -o ./llvm_btf_verify.o; \
+			  $(LLVM_READELF) -S ./llvm_btf_verify.o | grep BTF; \
+			  /bin/rm -f ./llvm_btf_verify.o)
+
+BPF_EXTRA_CFLAGS += -fno-stack-protector
+ifneq ($(BTF_LLVM_PROBE),)
+	BPF_EXTRA_CFLAGS += -g
+else
+ifneq ($(and $(BTF_LLC_PROBE),$(BTF_PAHOLE_PROBE),$(BTF_OBJCOPY_PROBE)),)
+	BPF_EXTRA_CFLAGS += -g
+	LLC_FLAGS += -mattr=dwarfris
+	DWARF2BTF = y
+endif
+endif
+endif
+
+# Trick to allow make to be run from this directory
+all:
+	$(MAKE) -C ../../ M=$(CURDIR) BPF_SAMPLES_PATH=$(CURDIR)
+
+clean:
+	$(MAKE) -C ../../ M=$(CURDIR) clean
+	@find $(CURDIR) -type f -name '*~' -delete
+	@$(RM) -r $(CURDIR)/libbpf $(CURDIR)/bpftool
+
+$(LIBBPF): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OUTPUT)
+# Fix up variables inherited from Kbuild that tools/ build system won't like
+	$(MAKE) -C $(LIBBPF_SRC) RM='rm -rf' EXTRA_CFLAGS="$(COMMON_CFLAGS)" \
+		LDFLAGS="$(TPROGS_LDFLAGS)" srctree=$(BPF_SAMPLES_PATH)/../../ \
+		O= OUTPUT=$(LIBBPF_OUTPUT)/ DESTDIR=$(LIBBPF_DESTDIR) prefix= \
+		$@ install_headers
+
+BPFTOOLDIR := $(TOOLS_PATH)/bpf/bpftool
+BPFTOOL_OUTPUT := $(abspath $(BPF_SAMPLES_PATH))/bpftool
+DEFAULT_BPFTOOL := $(BPFTOOL_OUTPUT)/bootstrap/bpftool
+BPFTOOL ?= $(DEFAULT_BPFTOOL)
+$(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) | $(BPFTOOL_OUTPUT)
+	$(MAKE) -C $(BPFTOOLDIR) srctree=$(BPF_SAMPLES_PATH)/../../ 		\
+		OUTPUT=$(BPFTOOL_OUTPUT)/ bootstrap
+
+$(LIBBPF_OUTPUT) $(BPFTOOL_OUTPUT):
+	$(call msg,MKDIR,$@)
+	$(Q)mkdir -p $@
+
+$(obj)/syscall_nrs.h:	$(obj)/syscall_nrs.s FORCE
+	$(call filechk,offsets,__SYSCALL_NRS_H__)
+
+targets += syscall_nrs.s
+clean-files += syscall_nrs.h
+
+FORCE:
+
+
+# Verify LLVM compiler tools are available and bpf target is supported by llc
+.PHONY: verify_cmds verify_target_bpf $(CLANG) $(LLC)
+
+verify_cmds: $(CLANG) $(LLC)
+	@for TOOL in $^ ; do \
+		if ! (which -- "$${TOOL}" > /dev/null 2>&1); then \
+			echo "*** ERROR: Cannot find LLVM tool $${TOOL}" ;\
+			exit 1; \
+		else true; fi; \
+	done
+
+verify_target_bpf: verify_cmds
+	@if ! (${LLC} -march=bpf -mattr=help > /dev/null 2>&1); then \
+		echo "*** ERROR: LLVM (${LLC}) does not support 'bpf' target" ;\
+		echo "   NOTICE: LLVM version >= 3.7.1 required" ;\
+		exit 2; \
+	else true; fi
+
+$(BPF_SAMPLES_PATH)/*.c: verify_target_bpf $(LIBBPF)
+$(src)/*.c: verify_target_bpf $(LIBBPF)
+
+libbpf_hdrs: $(LIBBPF)
+$(obj)/$(TRACE_HELPERS) $(obj)/$(CGROUP_HELPERS) $(obj)/$(XDP_SAMPLE): | libbpf_hdrs
+
+.PHONY: libbpf_hdrs
+
+$(obj)/xdp_router_ipv4_user.o: $(obj)/xdp_router_ipv4.skel.h
+
+$(obj)/tracex5.bpf.o: $(obj)/syscall_nrs.h
+$(obj)/hbm_out_kern.o: $(src)/hbm.h $(src)/hbm_kern.h
+$(obj)/hbm.o: $(src)/hbm.h
+$(obj)/hbm_edt_kern.o: $(src)/hbm.h $(src)/hbm_kern.h
+
+# Override includes for xdp_sample_user.o because $(srctree)/usr/include in
+# TPROGS_CFLAGS causes conflicts
+XDP_SAMPLE_CFLAGS += -Wall -O2 \
+		     -I$(src)/../../tools/include \
+		     -I$(src)/../../tools/include/uapi \
+		     -I$(LIBBPF_INCLUDE) \
+		     -I$(src)/../../tools/testing/selftests/bpf
+
+$(obj)/$(XDP_SAMPLE): TPROGS_CFLAGS = $(XDP_SAMPLE_CFLAGS) $(TPROGS_USER_CFLAGS)
+$(obj)/$(XDP_SAMPLE): $(src)/xdp_sample_user.h $(src)/xdp_sample_shared.h
+# Override includes for trace_helpers.o because __must_check won't be defined
+# in our include path.
+$(obj)/$(TRACE_HELPERS): TPROGS_CFLAGS := $(TPROGS_CFLAGS) -D__must_check=
+
+-include $(BPF_SAMPLES_PATH)/Makefile.target
+
+VMLINUX_BTF_PATHS ?= $(abspath $(if $(O),$(O)/vmlinux))				\
+		     $(abspath $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux))	\
+		     $(abspath $(objtree)/vmlinux)
+VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
+
+$(obj)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL)
+ifeq ($(VMLINUX_H),)
+ifeq ($(VMLINUX_BTF),)
+	$(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)",\
+		build the kernel or set VMLINUX_BTF like "VMLINUX_BTF=/sys/kernel/btf/vmlinux" or VMLINUX_H variable)
+endif
+	$(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@
+else
+	$(Q)cp "$(VMLINUX_H)" $@
+endif
+
+clean-files += vmlinux.h
+
+# Get Clang's default includes on this system, as opposed to those seen by
+# '--target=bpf'. This fixes "missing" files on some architectures/distros,
+# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
+#
+# Use '-idirafter': Don't interfere with include mechanics except where the
+# build would have failed anyways.
+define get_sys_includes
+$(shell $(1) -v -E - </dev/null 2>&1 \
+        | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \
+$(shell $(1) -dM -E - </dev/null | grep '#define __riscv_xlen ' | sed 's/#define /-D/' | sed 's/ /=/')
+endef
+
+CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG))
+
+$(obj)/xdp_router_ipv4.bpf.o: $(obj)/xdp_sample.bpf.o
+
+$(obj)/%.bpf.o: $(src)/%.bpf.c $(obj)/vmlinux.h $(src)/xdp_sample.bpf.h $(src)/xdp_sample_shared.h
+	@echo "  CLANG-BPF " $@
+	$(Q)$(CLANG) -g -O2 --target=bpf -D__TARGET_ARCH_$(SRCARCH) \
+		-Wno-compare-distinct-pointer-types -I$(srctree)/include \
+		-I$(srctree)/samples/bpf -I$(srctree)/tools/include \
+		-I$(LIBBPF_INCLUDE) $(CLANG_SYS_INCLUDES) \
+		-c $(filter %.bpf.c,$^) -o $@
+
+LINKED_SKELS := xdp_router_ipv4.skel.h
+clean-files += $(LINKED_SKELS)
+
+xdp_router_ipv4.skel.h-deps := xdp_router_ipv4.bpf.o xdp_sample.bpf.o
+
+LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.bpf.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps)))
+
+BPF_SRCS_LINKED := $(notdir $(wildcard $(src)/*.bpf.c))
+BPF_OBJS_LINKED := $(patsubst %.bpf.c,$(obj)/%.bpf.o, $(BPF_SRCS_LINKED))
+BPF_SKELS_LINKED := $(addprefix $(obj)/,$(LINKED_SKELS))
+
+$(BPF_SKELS_LINKED): $(BPF_OBJS_LINKED) $(BPFTOOL)
+	@echo "  BPF GEN-OBJ " $(@:.skel.h=)
+	$(Q)$(BPFTOOL) gen object $(@:.skel.h=.lbpf.o) $(addprefix $(obj)/,$($(@F)-deps))
+	@echo "  BPF GEN-SKEL" $(@:.skel.h=)
+	$(Q)$(BPFTOOL) gen skeleton $(@:.skel.h=.lbpf.o) name $(notdir $(@:.skel.h=)) > $@
+
+# asm/sysreg.h - inline assembly used by it is incompatible with llvm.
+# But, there is no easy way to fix it, so just exclude it since it is
+# useless for BPF samples.
+# below we use long chain of commands, clang | opt | llvm-dis | llc,
+# to generate final object file. 'clang' compiles the source into IR
+# with native target, e.g., x64, arm64, etc. 'opt' does bpf CORE IR builtin
+# processing (llvm12) and IR optimizations. 'llvm-dis' converts
+# 'opt' output to IR, and finally 'llc' generates bpf byte code.
+$(obj)/%.o: $(src)/%.c
+	@echo "  CLANG-bpf " $@
+	$(Q)$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(BPF_EXTRA_CFLAGS) \
+		-I$(obj) -I$(srctree)/tools/testing/selftests/bpf/ \
+		-I$(LIBBPF_INCLUDE) $(CLANG_SYS_INCLUDES) \
+		-D__KERNEL__ -D__BPF_TRACING__ -Wno-unused-value -Wno-pointer-sign \
+		-D__TARGET_ARCH_$(SRCARCH) -Wno-compare-distinct-pointer-types \
+		-Wno-gnu-variable-sized-type-not-at-end \
+		-Wno-address-of-packed-member -Wno-tautological-compare \
+		-Wno-unknown-warning-option $(CLANG_ARCH_ARGS) \
+		-fno-asynchronous-unwind-tables \
+		-I$(srctree)/samples/bpf/ -include asm_goto_workaround.h \
+		-O2 -emit-llvm -Xclang -disable-llvm-passes -c $< -o - | \
+		$(OPT) -O2 -mtriple=bpf-pc-linux | $(LLVM_DIS) | \
+		$(LLC) -march=bpf $(LLC_FLAGS) -filetype=obj -o $@
+ifeq ($(DWARF2BTF),y)
+	$(BTF_PAHOLE) -J $@
+endif

linux-7.2.3/samples/bpf/Makefile.target

@@ -0,0 +1,75 @@
+# SPDX-License-Identifier: GPL-2.0
+# ==========================================================================
+# Building binaries on the host system
+# Binaries are not used during the compilation of the kernel, and intended
+# to be build for target board, target board can be host of course. Added to
+# build binaries to run not on host system.
+#
+# Sample syntax
+# tprogs-y := xsk_example
+# Will compile xsk_example.c and create an executable named xsk_example
+#
+# tprogs-y    := xdpsock
+# xdpsock-objs := xdpsock_1.o xdpsock_2.o
+# Will compile xdpsock_1.c and xdpsock_2.c, and then link the executable
+# xdpsock, based on xdpsock_1.o and xdpsock_2.o
+#
+# Derived from scripts/Makefile.host
+#
+__tprogs := $(sort $(tprogs-y))
+
+# C code
+# Executables compiled from a single .c file
+tprog-csingle	:= $(foreach m,$(__tprogs), \
+			$(if $($(m)-objs),,$(m)))
+
+# C executables linked based on several .o files
+tprog-cmulti	:= $(foreach m,$(__tprogs),\
+			$(if $($(m)-objs),$(m)))
+
+# Object (.o) files compiled from .c files
+tprog-cobjs	:= $(sort $(foreach m,$(__tprogs),$($(m)-objs)))
+
+tprog-csingle	:= $(addprefix $(obj)/,$(tprog-csingle))
+tprog-cmulti	:= $(addprefix $(obj)/,$(tprog-cmulti))
+tprog-cobjs	:= $(addprefix $(obj)/,$(tprog-cobjs))
+
+#####
+# Handle options to gcc. Support building with separate output directory
+
+_tprogc_flags   = $(TPROGS_CFLAGS) \
+                 $(TPROGCFLAGS_$(basetarget).o)
+
+# $(objtree)/$(obj) for including generated headers from checkin source files
+ifeq ($(KBUILD_EXTMOD),)
+ifdef building_out_of_srctree
+_tprogc_flags   += -I $(objtree)/$(obj)
+endif
+endif
+
+tprogc_flags    = -Wp,-MD,$(depfile) $(_tprogc_flags)
+
+# Create executable from a single .c file
+# tprog-csingle -> Executable
+quiet_cmd_tprog-csingle 	= CC  $@
+      cmd_tprog-csingle	= $(CC) $(tprogc_flags) $(TPROGS_LDFLAGS) -o $@ $< \
+		$(TPROGS_LDLIBS) $(TPROGLDLIBS_$(@F))
+$(tprog-csingle): $(obj)/%: $(src)/%.c FORCE
+	$(call if_changed_dep,tprog-csingle)
+
+# Link an executable based on list of .o files, all plain c
+# tprog-cmulti -> executable
+quiet_cmd_tprog-cmulti	= LD  $@
+      cmd_tprog-cmulti	= $(CC) $(tprogc_flags) $(TPROGS_LDFLAGS) -o $@ \
+			  $(addprefix $(obj)/,$($(@F)-objs)) \
+			  $(TPROGS_LDLIBS) $(TPROGLDLIBS_$(@F))
+$(tprog-cmulti): $(tprog-cobjs) FORCE
+	$(call if_changed,tprog-cmulti)
+$(call multi_depend, $(tprog-cmulti), , -objs)
+
+# Create .o file from a single .c file
+# tprog-cobjs -> .o
+quiet_cmd_tprog-cobjs	= CC  $@
+      cmd_tprog-cobjs	= $(CC) $(tprogc_flags) -c -o $@ $<
+$(tprog-cobjs): $(obj)/%.o: $(src)/%.c FORCE
+	$(call if_changed_dep,tprog-cobjs)

linux-7.2.3/samples/bpf/README.rst

@@ -0,0 +1,121 @@
+eBPF sample programs
+====================
+
+This directory contains a test stubs, verifier test-suite and examples
+for using eBPF. The examples use libbpf from tools/lib/bpf.
+
+Note that the XDP-specific samples have been removed from this directory and
+moved to the xdp-tools repository: https://github.com/xdp-project/xdp-tools
+See the commit messages removing each tool from this directory for how to
+convert specific command invocations between the old samples and the utilities
+in xdp-tools.
+
+Build dependencies
+==================
+
+Compiling requires having installed:
+ * clang
+ * llvm
+ * pahole
+
+Consult :ref:`Documentation/process/changes.rst <changes>` for the minimum
+version numbers required and how to update them. Note that LLVM's tool
+'llc' must support target 'bpf', list version and supported targets with
+command: ``llc --version``
+
+Clean and configuration
+-----------------------
+
+It can be needed to clean tools, samples or kernel before trying new arch or
+after some changes (on demand)::
+
+ make -C tools clean
+ make -C samples/bpf clean
+ make clean
+
+Configure kernel, defconfig for instance
+(see "tools/testing/selftests/bpf/config" for a reference config)::
+
+ make defconfig
+
+Kernel headers
+--------------
+
+There are usually dependencies to header files of the current kernel.
+To avoid installing devel kernel headers system wide, as a normal
+user, simply call::
+
+ make headers_install
+
+This will create a local "usr/include" directory in the git/build top
+level directory, that the make system will automatically pick up first.
+
+Compiling
+=========
+
+For building the BPF samples, issue the below command from the kernel
+top level directory::
+
+ make M=samples/bpf
+
+It is also possible to call make from this directory.  This will just
+hide the invocation of make as above.
+
+Manually compiling LLVM with 'bpf' support
+------------------------------------------
+
+Since version 3.7.0, LLVM adds a proper LLVM backend target for the
+BPF bytecode architecture.
+
+By default llvm will build all non-experimental backends including bpf.
+To generate a smaller llc binary one can use::
+
+ -DLLVM_TARGETS_TO_BUILD="BPF"
+
+We recommend that developers who want the fastest incremental builds
+use the Ninja build system, you can find it in your system's package
+manager, usually the package is ninja or ninja-build.
+
+Quick sniplet for manually compiling LLVM and clang
+(build dependencies are ninja, cmake and gcc-c++)::
+
+ $ git clone https://github.com/llvm/llvm-project.git
+ $ mkdir -p llvm-project/llvm/build
+ $ cd llvm-project/llvm/build
+ $ cmake .. -G "Ninja" -DLLVM_TARGETS_TO_BUILD="BPF;X86" \
+            -DLLVM_ENABLE_PROJECTS="clang"    \
+            -DCMAKE_BUILD_TYPE=Release        \
+            -DLLVM_BUILD_RUNTIME=OFF
+ $ ninja
+
+It is also possible to point make to the newly compiled 'llc' or
+'clang' command via redefining LLC or CLANG on the make command line::
+
+ make M=samples/bpf LLC=~/git/llvm-project/llvm/build/bin/llc CLANG=~/git/llvm-project/llvm/build/bin/clang
+
+Cross compiling samples
+-----------------------
+In order to cross-compile, say for arm64 targets, export CROSS_COMPILE and ARCH
+environment variables before calling make. But do this before clean,
+configuration and header install steps described above. This will direct make to
+build samples for the cross target::
+
+ export ARCH=arm64
+ export CROSS_COMPILE="aarch64-linux-gnu-"
+
+Headers can be also installed on RFS of target board if need to keep them in
+sync (not necessarily and it creates a local "usr/include" directory also)::
+
+ make INSTALL_HDR_PATH=~/some_sysroot/usr headers_install
+
+Pointing LLC and CLANG is not necessarily if it's installed on HOST and have
+in its targets appropriate arm64 arch (usually it has several arches).
+Build samples::
+
+ make M=samples/bpf
+
+Or build samples with SYSROOT if some header or library is absent in toolchain,
+say libelf, providing address to file system containing headers and libs,
+can be RFS of target board::
+
+ make M=samples/bpf SYSROOT=~/some_sysroot

linux-7.2.3/samples/bpf/asm_goto_workaround.h

@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019 Facebook */
+#ifndef __ASM_GOTO_WORKAROUND_H
+#define __ASM_GOTO_WORKAROUND_H
+
+/*
+ * This will bring in asm_goto_output and asm_inline macro definitions
+ * if enabled by compiler and config options.
+ */
+#include <linux/types.h>
+
+#ifdef asm_goto_output
+#undef asm_goto_output
+#define asm_goto_output(x...) asm volatile("invalid use of asm_goto_output")
+#endif
+
+/*
+ * asm_inline is defined as asm __inline in "include/linux/compiler_types.h"
+ * if supported by the kernel's CC (i.e CONFIG_CC_HAS_ASM_INLINE) which is not
+ * supported by CLANG.
+ */
+#ifdef asm_inline
+#undef asm_inline
+#define asm_inline asm
+#endif
+
+#define volatile(x...) volatile("")
+#endif

linux-7.2.3/samples/bpf/bpf_insn.h

@@ -0,0 +1,233 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/* eBPF instruction mini library */
+#ifndef __BPF_INSN_H
+#define __BPF_INSN_H
+
+struct bpf_insn;
+
+/* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */
+
+#define BPF_ALU64_REG(OP, DST, SRC)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU64 | BPF_OP(OP) | BPF_X,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = 0,					\
+		.imm   = 0 })
+
+#define BPF_ALU32_REG(OP, DST, SRC)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU | BPF_OP(OP) | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = 0,					\
+		.imm   = 0 })
+
+/* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */
+
+#define BPF_ALU64_IMM(OP, DST, IMM)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU64 | BPF_OP(OP) | BPF_K,	\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
+#define BPF_ALU32_IMM(OP, DST, IMM)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU | BPF_OP(OP) | BPF_K,		\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
+/* Short form of mov, dst_reg = src_reg */
+
+#define BPF_MOV64_REG(DST, SRC)					\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU64 | BPF_MOV | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = 0,					\
+		.imm   = 0 })
+
+#define BPF_MOV32_REG(DST, SRC)					\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU | BPF_MOV | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = 0,					\
+		.imm   = 0 })
+
+/* Short form of mov, dst_reg = imm32 */
+
+#define BPF_MOV64_IMM(DST, IMM)					\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU64 | BPF_MOV | BPF_K,		\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
+#define BPF_MOV32_IMM(DST, IMM)					\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU | BPF_MOV | BPF_K,		\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
+/* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */
+#define BPF_LD_IMM64(DST, IMM)					\
+	BPF_LD_IMM64_RAW(DST, 0, IMM)
+
+#define BPF_LD_IMM64_RAW(DST, SRC, IMM)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_LD | BPF_DW | BPF_IMM,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = 0,					\
+		.imm   = (__u32) (IMM) }),			\
+	((struct bpf_insn) {					\
+		.code  = 0, /* zero is reserved opcode */	\
+		.dst_reg = 0,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = ((__u64) (IMM)) >> 32 })
+
+#ifndef BPF_PSEUDO_MAP_FD
+# define BPF_PSEUDO_MAP_FD	1
+#endif
+
+/* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */
+#define BPF_LD_MAP_FD(DST, MAP_FD)				\
+	BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD)
+
+
+/* Direct packet access, R0 = *(uint *) (skb->data + imm32) */
+
+#define BPF_LD_ABS(SIZE, IMM)					\
+	((struct bpf_insn) {					\
+		.code  = BPF_LD | BPF_SIZE(SIZE) | BPF_ABS,	\
+		.dst_reg = 0,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
+/* Memory load, dst_reg = *(uint *) (src_reg + off16) */
+
+#define BPF_LDX_MEM(SIZE, DST, SRC, OFF)			\
+	((struct bpf_insn) {					\
+		.code  = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
+/* Memory store, *(uint *) (dst_reg + off16) = src_reg */
+
+#define BPF_STX_MEM(SIZE, DST, SRC, OFF)			\
+	((struct bpf_insn) {					\
+		.code  = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
+/*
+ * Atomic operations:
+ *
+ *   BPF_ADD                  *(uint *) (dst_reg + off16) += src_reg
+ *   BPF_AND                  *(uint *) (dst_reg + off16) &= src_reg
+ *   BPF_OR                   *(uint *) (dst_reg + off16) |= src_reg
+ *   BPF_XOR                  *(uint *) (dst_reg + off16) ^= src_reg
+ *   BPF_ADD | BPF_FETCH      src_reg = atomic_fetch_add(dst_reg + off16, src_reg);
+ *   BPF_AND | BPF_FETCH      src_reg = atomic_fetch_and(dst_reg + off16, src_reg);
+ *   BPF_OR | BPF_FETCH       src_reg = atomic_fetch_or(dst_reg + off16, src_reg);
+ *   BPF_XOR | BPF_FETCH      src_reg = atomic_fetch_xor(dst_reg + off16, src_reg);
+ *   BPF_XCHG                 src_reg = atomic_xchg(dst_reg + off16, src_reg)
+ *   BPF_CMPXCHG              r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg)
+ */
+
+#define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF)			\
+	((struct bpf_insn) {					\
+		.code  = BPF_STX | BPF_SIZE(SIZE) | BPF_ATOMIC,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = OP })
+
+/* Legacy alias */
+#define BPF_STX_XADD(SIZE, DST, SRC, OFF) BPF_ATOMIC_OP(SIZE, BPF_ADD, DST, SRC, OFF)
+
+/* Memory store, *(uint *) (dst_reg + off16) = imm32 */
+
+#define BPF_ST_MEM(SIZE, DST, OFF, IMM)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ST | BPF_SIZE(SIZE) | BPF_MEM,	\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = OFF,					\
+		.imm   = IMM })
+
+/* Conditional jumps against registers, if (dst_reg 'op' src_reg) goto pc + off16 */
+
+#define BPF_JMP_REG(OP, DST, SRC, OFF)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_JMP | BPF_OP(OP) | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
+/* Like BPF_JMP_REG, but with 32-bit wide operands for comparison. */
+
+#define BPF_JMP32_REG(OP, DST, SRC, OFF)			\
+	((struct bpf_insn) {					\
+		.code  = BPF_JMP32 | BPF_OP(OP) | BPF_X,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
+/* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */
+
+#define BPF_JMP_IMM(OP, DST, IMM, OFF)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_JMP | BPF_OP(OP) | BPF_K,		\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = OFF,					\
+		.imm   = IMM })
+
+/* Like BPF_JMP_IMM, but with 32-bit wide operands for comparison. */
+
+#define BPF_JMP32_IMM(OP, DST, IMM, OFF)			\
+	((struct bpf_insn) {					\
+		.code  = BPF_JMP32 | BPF_OP(OP) | BPF_K,	\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = OFF,					\
+		.imm   = IMM })
+
+/* Raw code statement block */
+
+#define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM)			\
+	((struct bpf_insn) {					\
+		.code  = CODE,					\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = IMM })
+
+/* Program exit */
+
+#define BPF_EXIT_INSN()						\
+	((struct bpf_insn) {					\
+		.code  = BPF_JMP | BPF_EXIT,			\
+		.dst_reg = 0,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = 0 })
+
+#endif

linux-7.2.3/samples/bpf/cookie_uid_helper_example.c

@@ -0,0 +1,332 @@
+/* This test is a demo of using get_socket_uid and get_socket_cookie
+ * helper function to do per socket based network traffic monitoring.
+ * It requires iptables version higher then 1.6.1. to load pinned eBPF
+ * program into the xt_bpf match.
+ *
+ * TEST:
+ * ./run_cookie_uid_helper_example.sh -option
+ * option:
+ *	-t: do traffic monitoring test, the program will continuously
+ * print out network traffic happens after program started A sample
+ * output is shown below:
+ *
+ * cookie: 877, uid: 0x3e8, Pakcet Count: 20, Bytes Count: 11058
+ * cookie: 132, uid: 0x0, Pakcet Count: 2, Bytes Count: 286
+ * cookie: 812, uid: 0x3e8, Pakcet Count: 3, Bytes Count: 1726
+ * cookie: 802, uid: 0x3e8, Pakcet Count: 2, Bytes Count: 104
+ * cookie: 877, uid: 0x3e8, Pakcet Count: 20, Bytes Count: 11058
+ * cookie: 831, uid: 0x3e8, Pakcet Count: 2, Bytes Count: 104
+ * cookie: 0, uid: 0x0, Pakcet Count: 6, Bytes Count: 712
+ * cookie: 880, uid: 0xfffe, Pakcet Count: 1, Bytes Count: 70
+ *
+ *	-s: do getsockopt SO_COOKIE test, the program will set up a pair of
+ * UDP sockets and send packets between them. And read out the traffic data
+ * directly from the ebpf map based on the socket cookie.
+ *
+ * Clean up: if using shell script, the script file will delete the iptables
+ * rule and unmount the bpf program when exit. Else the iptables rule need
+ * to be deleted by hand, see run_cookie_uid_helper_example.sh for detail.
+ */
+
+#define _GNU_SOURCE
+
+#define offsetof(type, member)	__builtin_offsetof(type, member)
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <limits.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <net/if.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include <bpf/bpf.h>
+#include "bpf_insn.h"
+
+#define PORT 8888
+
+struct stats {
+	uint32_t uid;
+	uint64_t packets;
+	uint64_t bytes;
+};
+
+static int map_fd, prog_fd;
+
+static bool test_finish;
+
+static void maps_create(void)
+{
+	map_fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(uint32_t),
+				sizeof(struct stats), 100, NULL);
+	if (map_fd < 0)
+		error(1, errno, "map create failed!\n");
+}
+
+static void prog_load(void)
+{
+	static char log_buf[1 << 16];
+
+	struct bpf_insn prog[] = {
+		/*
+		 * Save sk_buff for future usage. value stored in R6 to R10 will
+		 * not be reset after a bpf helper function call.
+		 */
+		BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+		/*
+		 * pc1: BPF_FUNC_get_socket_cookie takes one parameter,
+		 * R1: sk_buff
+		 */
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				BPF_FUNC_get_socket_cookie),
+		/* pc2-4: save &socketCookie to r7 for future usage*/
+		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+		BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
+		/*
+		 * pc5-8: set up the registers for BPF_FUNC_map_lookup_elem,
+		 * it takes two parameters (R1: map_fd,  R2: &socket_cookie)
+		 */
+		BPF_LD_MAP_FD(BPF_REG_1, map_fd),
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				BPF_FUNC_map_lookup_elem),
+		/*
+		 * pc9. if r0 != 0x0, go to pc+14, since we have the cookie
+		 * stored already
+		 * Otherwise do pc10-22 to setup a new data entry.
+		 */
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 14),
+		BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				BPF_FUNC_get_socket_uid),
+		/*
+		 * Place a struct stats in the R10 stack and sequentially
+		 * place the member value into the memory. Packets value
+		 * is set by directly place a IMM value 1 into the stack.
+		 */
+		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0,
+			    -32 + (__s16)offsetof(struct stats, uid)),
+		BPF_ST_MEM(BPF_DW, BPF_REG_10,
+			   -32 + (__s16)offsetof(struct stats, packets), 1),
+		/*
+		 * __sk_buff is a special struct used for eBPF program to
+		 * directly access some sk_buff field.
+		 */
+		BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+				offsetof(struct __sk_buff, len)),
+		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1,
+			    -32 + (__s16)offsetof(struct stats, bytes)),
+		/*
+		 * add new map entry using BPF_FUNC_map_update_elem, it takes
+		 * 4 parameters (R1: map_fd, R2: &socket_cookie, R3: &stats,
+		 * R4: flags)
+		 */
+		BPF_LD_MAP_FD(BPF_REG_1, map_fd),
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+		BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -32),
+		BPF_MOV64_IMM(BPF_REG_4, 0),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				BPF_FUNC_map_update_elem),
+		BPF_JMP_IMM(BPF_JA, 0, 0, 5),
+		/*
+		 * pc24-30 update the packet info to a exist data entry, it can
+		 * be done by directly write to pointers instead of using
+		 * BPF_FUNC_map_update_elem helper function
+		 */
+		BPF_MOV64_REG(BPF_REG_9, BPF_REG_0),
+		BPF_MOV64_IMM(BPF_REG_1, 1),
+		BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_9, BPF_REG_1,
+			      offsetof(struct stats, packets)),
+		BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+				offsetof(struct __sk_buff, len)),
+		BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_9, BPF_REG_1,
+			      offsetof(struct stats, bytes)),
+		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6,
+				offsetof(struct __sk_buff, len)),
+		BPF_EXIT_INSN(),
+	};
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		.log_buf = log_buf,
+		.log_size = sizeof(log_buf),
+	);
+
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL",
+				prog, ARRAY_SIZE(prog), &opts);
+	if (prog_fd < 0)
+		error(1, errno, "failed to load prog\n%s\n", log_buf);
+}
+
+static void prog_attach_iptables(char *file)
+{
+	int ret;
+	char rules[256];
+
+	if (bpf_obj_pin(prog_fd, file))
+		error(1, errno, "bpf_obj_pin");
+	if (strlen(file) > 50) {
+		printf("file path too long: %s\n", file);
+		exit(1);
+	}
+	ret = snprintf(rules, sizeof(rules),
+		       "iptables -A OUTPUT -m bpf --object-pinned %s -j ACCEPT",
+		       file);
+	if (ret < 0 || ret >= sizeof(rules)) {
+		printf("error constructing iptables command\n");
+		exit(1);
+	}
+	ret = system(rules);
+	if (ret < 0) {
+		printf("iptables rule update failed: %d/n", WEXITSTATUS(ret));
+		exit(1);
+	}
+}
+
+static void print_table(void)
+{
+	struct stats curEntry;
+	uint32_t curN = UINT32_MAX;
+	uint32_t nextN;
+	int res;
+
+	while (bpf_map_get_next_key(map_fd, &curN, &nextN) > -1) {
+		curN = nextN;
+		res = bpf_map_lookup_elem(map_fd, &curN, &curEntry);
+		if (res < 0) {
+			error(1, errno, "fail to get entry value of Key: %u\n",
+				curN);
+		} else {
+			printf("cookie: %u, uid: 0x%x, Packet Count: %lu,"
+				" Bytes Count: %lu\n", curN, curEntry.uid,
+				curEntry.packets, curEntry.bytes);
+		}
+	}
+}
+
+static void udp_client(void)
+{
+	struct sockaddr_in si_other = {0};
+	struct sockaddr_in si_me = {0};
+	struct stats dataEntry;
+	int s_rcv, s_send, i, recv_len;
+	char message = 'a';
+	char buf;
+	uint64_t cookie;
+	int res;
+	socklen_t cookie_len = sizeof(cookie);
+	socklen_t slen = sizeof(si_other);
+
+	s_rcv = socket(PF_INET, SOCK_DGRAM, 0);
+	if (s_rcv < 0)
+		error(1, errno, "rcv socket creat failed!\n");
+	si_other.sin_family = AF_INET;
+	si_other.sin_port = htons(PORT);
+	if (inet_aton("127.0.0.1", &si_other.sin_addr) == 0)
+		error(1, errno, "inet_aton\n");
+	if (bind(s_rcv, (struct sockaddr *)&si_other, sizeof(si_other)) == -1)
+		error(1, errno, "bind\n");
+	s_send = socket(PF_INET, SOCK_DGRAM, 0);
+	if (s_send < 0)
+		error(1, errno, "send socket creat failed!\n");
+	res = getsockopt(s_send, SOL_SOCKET, SO_COOKIE, &cookie, &cookie_len);
+	if (res < 0)
+		printf("get cookie failed: %s\n", strerror(errno));
+	res = bpf_map_lookup_elem(map_fd, &cookie, &dataEntry);
+	if (res != -1)
+		error(1, errno, "socket stat found while flow not active\n");
+	for (i = 0; i < 10; i++) {
+		res = sendto(s_send, &message, sizeof(message), 0,
+			     (struct sockaddr *)&si_other, slen);
+		if (res == -1)
+			error(1, errno, "send\n");
+		if (res != sizeof(message))
+			error(1, 0, "%uB != %luB\n", res, sizeof(message));
+		recv_len = recvfrom(s_rcv, &buf, sizeof(buf), 0,
+			     (struct sockaddr *)&si_me, &slen);
+		if (recv_len < 0)
+			error(1, errno, "receive\n");
+		res = memcmp(&(si_other.sin_addr), &(si_me.sin_addr),
+			   sizeof(si_me.sin_addr));
+		if (res != 0)
+			error(1, EFAULT, "sender addr error: %d\n", res);
+		printf("Message received: %c\n", buf);
+		res = bpf_map_lookup_elem(map_fd, &cookie, &dataEntry);
+		if (res < 0)
+			error(1, errno, "lookup sk stat failed, cookie: %lu\n",
+			      cookie);
+		printf("cookie: %lu, uid: 0x%x, Packet Count: %lu,"
+			" Bytes Count: %lu\n\n", cookie, dataEntry.uid,
+			dataEntry.packets, dataEntry.bytes);
+	}
+	close(s_send);
+	close(s_rcv);
+}
+
+static int usage(void)
+{
+	printf("Usage: ./run_cookie_uid_helper_example.sh"
+		" bpfObjName -option\n"
+		"	-t	traffic monitor test\n"
+		"	-s	getsockopt cookie test\n");
+	return 1;
+}
+
+static void finish(int ret)
+{
+	test_finish = true;
+}
+
+int main(int argc, char *argv[])
+{
+	int opt;
+	bool cfg_test_traffic = false;
+	bool cfg_test_cookie = false;
+
+	if (argc != 3)
+		return usage();
+	while ((opt = getopt(argc, argv, "ts")) != -1) {
+		switch (opt) {
+		case 't':
+			cfg_test_traffic = true;
+			break;
+		case 's':
+			cfg_test_cookie = true;
+			break;
+
+		default:
+			printf("unknown option %c\n", opt);
+			usage();
+			return -1;
+		}
+	}
+	maps_create();
+	prog_load();
+	prog_attach_iptables(argv[2]);
+	if (cfg_test_traffic) {
+		if (signal(SIGINT, finish) == SIG_ERR)
+			error(1, errno, "register SIGINT handler failed");
+		if (signal(SIGTERM, finish) == SIG_ERR)
+			error(1, errno, "register SIGTERM handler failed");
+		while (!test_finish) {
+			print_table();
+			printf("\n");
+			sleep(1);
+		}
+	} else if (cfg_test_cookie) {
+		udp_client();
+	}
+	close(prog_fd);
+	close(map_fd);
+	return 0;
+}

linux-7.2.3/samples/bpf/cpustat_kern.c

@@ -0,0 +1,280 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/version.h>
+#include <linux/ptrace.h>
+#include <uapi/linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+/*
+ * The CPU number, cstate number and pstate number are based
+ * on 96boards Hikey with octa CA53 CPUs.
+ *
+ * Every CPU have three idle states for cstate:
+ *   WFI, CPU_OFF, CLUSTER_OFF
+ *
+ * Every CPU have 5 operating points:
+ *   208MHz, 432MHz, 729MHz, 960MHz, 1200MHz
+ *
+ * This code is based on these assumption and other platforms
+ * need to adjust these definitions.
+ */
+#define MAX_CPU			8
+#define MAX_PSTATE_ENTRIES	5
+#define MAX_CSTATE_ENTRIES	3
+
+static int cpu_opps[] = { 208000, 432000, 729000, 960000, 1200000 };
+
+/*
+ * my_map structure is used to record cstate and pstate index and
+ * timestamp (Idx, Ts), when new event incoming we need to update
+ * combination for new state index and timestamp (Idx`, Ts`).
+ *
+ * Based on (Idx, Ts) and (Idx`, Ts`) we can calculate the time
+ * interval for the previous state: Duration(Idx) = Ts` - Ts.
+ *
+ * Every CPU has one below array for recording state index and
+ * timestamp, and record for cstate and pstate saperately:
+ *
+ * +--------------------------+
+ * | cstate timestamp         |
+ * +--------------------------+
+ * | cstate index             |
+ * +--------------------------+
+ * | pstate timestamp         |
+ * +--------------------------+
+ * | pstate index             |
+ * +--------------------------+
+ */
+#define MAP_OFF_CSTATE_TIME	0
+#define MAP_OFF_CSTATE_IDX	1
+#define MAP_OFF_PSTATE_TIME	2
+#define MAP_OFF_PSTATE_IDX	3
+#define MAP_OFF_NUM		4
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, u32);
+	__type(value, u64);
+	__uint(max_entries, MAX_CPU * MAP_OFF_NUM);
+} my_map SEC(".maps");
+
+/* cstate_duration records duration time for every idle state per CPU */
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, u32);
+	__type(value, u64);
+	__uint(max_entries, MAX_CPU * MAX_CSTATE_ENTRIES);
+} cstate_duration SEC(".maps");
+
+/* pstate_duration records duration time for every operating point per CPU */
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, u32);
+	__type(value, u64);
+	__uint(max_entries, MAX_CPU * MAX_PSTATE_ENTRIES);
+} pstate_duration SEC(".maps");
+
+/*
+ * The trace events for cpu_idle and cpu_frequency are taken from:
+ * /sys/kernel/tracing/events/power/cpu_idle/format
+ * /sys/kernel/tracing/events/power/cpu_frequency/format
+ *
+ * These two events have same format, so define one common structure.
+ */
+struct cpu_args {
+	u64 pad;
+	u32 state;
+	u32 cpu_id;
+};
+
+/* calculate pstate index, returns MAX_PSTATE_ENTRIES for failure */
+static u32 find_cpu_pstate_idx(u32 frequency)
+{
+	u32 i;
+
+	for (i = 0; i < sizeof(cpu_opps) / sizeof(u32); i++) {
+		if (frequency == cpu_opps[i])
+			return i;
+	}
+
+	return i;
+}
+
+SEC("tracepoint/power/cpu_idle")
+int bpf_prog1(struct cpu_args *ctx)
+{
+	u64 *cts, *pts, *cstate, *pstate, prev_state, cur_ts, delta;
+	u32 key, cpu, pstate_idx;
+	u64 *val;
+
+	if (ctx->cpu_id > MAX_CPU)
+		return 0;
+
+	cpu = ctx->cpu_id;
+
+	key = cpu * MAP_OFF_NUM + MAP_OFF_CSTATE_TIME;
+	cts = bpf_map_lookup_elem(&my_map, &key);
+	if (!cts)
+		return 0;
+
+	key = cpu * MAP_OFF_NUM + MAP_OFF_CSTATE_IDX;
+	cstate = bpf_map_lookup_elem(&my_map, &key);
+	if (!cstate)
+		return 0;
+
+	key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_TIME;
+	pts = bpf_map_lookup_elem(&my_map, &key);
+	if (!pts)
+		return 0;
+
+	key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_IDX;
+	pstate = bpf_map_lookup_elem(&my_map, &key);
+	if (!pstate)
+		return 0;
+
+	prev_state = *cstate;
+	*cstate = ctx->state;
+
+	if (!*cts) {
+		*cts = bpf_ktime_get_ns();
+		return 0;
+	}
+
+	cur_ts = bpf_ktime_get_ns();
+	delta = cur_ts - *cts;
+	*cts = cur_ts;
+
+	/*
+	 * When state doesn't equal to (u32)-1, the cpu will enter
+	 * one idle state; for this case we need to record interval
+	 * for the pstate.
+	 *
+	 *                 OPP2
+	 *            +---------------------+
+	 *     OPP1   |                     |
+	 *   ---------+                     |
+	 *                                  |  Idle state
+	 *                                  +---------------
+	 *
+	 *            |<- pstate duration ->|
+	 *            ^                     ^
+	 *           pts                  cur_ts
+	 */
+	if (ctx->state != (u32)-1) {
+
+		/* record pstate after have first cpu_frequency event */
+		if (!*pts)
+			return 0;
+
+		delta = cur_ts - *pts;
+
+		pstate_idx = find_cpu_pstate_idx(*pstate);
+		if (pstate_idx >= MAX_PSTATE_ENTRIES)
+			return 0;
+
+		key = cpu * MAX_PSTATE_ENTRIES + pstate_idx;
+		val = bpf_map_lookup_elem(&pstate_duration, &key);
+		if (val)
+			__sync_fetch_and_add((long *)val, delta);
+
+	/*
+	 * When state equal to (u32)-1, the cpu just exits from one
+	 * specific idle state; for this case we need to record
+	 * interval for the pstate.
+	 *
+	 *       OPP2
+	 *   -----------+
+	 *              |                          OPP1
+	 *              |                     +-----------
+	 *              |     Idle state      |
+	 *              +---------------------+
+	 *
+	 *              |<- cstate duration ->|
+	 *              ^                     ^
+	 *             cts                  cur_ts
+	 */
+	} else {
+
+		key = cpu * MAX_CSTATE_ENTRIES + prev_state;
+		val = bpf_map_lookup_elem(&cstate_duration, &key);
+		if (val)
+			__sync_fetch_and_add((long *)val, delta);
+	}
+
+	/* Update timestamp for pstate as new start time */
+	if (*pts)
+		*pts = cur_ts;
+
+	return 0;
+}
+
+SEC("tracepoint/power/cpu_frequency")
+int bpf_prog2(struct cpu_args *ctx)
+{
+	u64 *pts, *cstate, *pstate, cur_ts, delta;
+	u32 key, cpu, pstate_idx;
+	u64 *val;
+
+	cpu = ctx->cpu_id;
+
+	key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_TIME;
+	pts = bpf_map_lookup_elem(&my_map, &key);
+	if (!pts)
+		return 0;
+
+	key = cpu * MAP_OFF_NUM + MAP_OFF_PSTATE_IDX;
+	pstate = bpf_map_lookup_elem(&my_map, &key);
+	if (!pstate)
+		return 0;
+
+	key = cpu * MAP_OFF_NUM + MAP_OFF_CSTATE_IDX;
+	cstate = bpf_map_lookup_elem(&my_map, &key);
+	if (!cstate)
+		return 0;
+
+	*pstate = ctx->state;
+
+	if (!*pts) {
+		*pts = bpf_ktime_get_ns();
+		return 0;
+	}
+
+	cur_ts = bpf_ktime_get_ns();
+	delta = cur_ts - *pts;
+	*pts = cur_ts;
+
+	/* When CPU is in idle, bail out to skip pstate statistics */
+	if (*cstate != (u32)(-1))
+		return 0;
+
+	/*
+	 * The cpu changes to another different OPP (in below diagram
+	 * change frequency from OPP3 to OPP1), need recording interval
+	 * for previous frequency OPP3 and update timestamp as start
+	 * time for new frequency OPP1.
+	 *
+	 *                 OPP3
+	 *            +---------------------+
+	 *     OPP2   |                     |
+	 *   ---------+                     |
+	 *                                  |    OPP1
+	 *                                  +---------------
+	 *
+	 *            |<- pstate duration ->|
+	 *            ^                     ^
+	 *           pts                  cur_ts
+	 */
+	pstate_idx = find_cpu_pstate_idx(*pstate);
+	if (pstate_idx >= MAX_PSTATE_ENTRIES)
+		return 0;
+
+	key = cpu * MAX_PSTATE_ENTRIES + pstate_idx;
+	val = bpf_map_lookup_elem(&pstate_duration, &key);
+	if (val)
+		__sync_fetch_and_add((long *)val, delta);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;

linux-7.2.3/samples/bpf/cpustat_user.c

@@ -0,0 +1,251 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <sched.h>
+#include <string.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <locale.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/wait.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+static int cstate_map_fd, pstate_map_fd;
+
+#define MAX_CPU			8
+#define MAX_PSTATE_ENTRIES	5
+#define MAX_CSTATE_ENTRIES	3
+#define MAX_STARS		40
+
+#define CPUFREQ_MAX_SYSFS_PATH	"/sys/devices/system/cpu/cpu0/cpufreq/scaling_max_freq"
+#define CPUFREQ_LOWEST_FREQ	"208000"
+#define CPUFREQ_HIGHEST_FREQ	"12000000"
+
+struct cpu_stat_data {
+	unsigned long cstate[MAX_CSTATE_ENTRIES];
+	unsigned long pstate[MAX_PSTATE_ENTRIES];
+};
+
+static struct cpu_stat_data stat_data[MAX_CPU];
+
+static void cpu_stat_print(void)
+{
+	int i, j;
+	char state_str[sizeof("cstate-9")];
+	struct cpu_stat_data *data;
+
+	/* Clear screen */
+	printf("\033[2J");
+
+	/* Header */
+	printf("\nCPU states statistics:\n");
+	printf("%-10s ", "state(ms)");
+
+	for (i = 0; i < MAX_CSTATE_ENTRIES; i++) {
+		sprintf(state_str, "cstate-%d", i);
+		printf("%-11s ", state_str);
+	}
+
+	for (i = 0; i < MAX_PSTATE_ENTRIES; i++) {
+		sprintf(state_str, "pstate-%d", i);
+		printf("%-11s ", state_str);
+	}
+
+	printf("\n");
+
+	for (j = 0; j < MAX_CPU; j++) {
+		data = &stat_data[j];
+
+		printf("CPU-%-6d ", j);
+		for (i = 0; i < MAX_CSTATE_ENTRIES; i++)
+			printf("%-11lu ", data->cstate[i] / 1000000);
+
+		for (i = 0; i < MAX_PSTATE_ENTRIES; i++)
+			printf("%-11lu ", data->pstate[i] / 1000000);
+
+		printf("\n");
+	}
+}
+
+static void cpu_stat_update(int cstate_fd, int pstate_fd)
+{
+	unsigned long key, value;
+	int c, i;
+
+	for (c = 0; c < MAX_CPU; c++) {
+		for (i = 0; i < MAX_CSTATE_ENTRIES; i++) {
+			key = c * MAX_CSTATE_ENTRIES + i;
+			bpf_map_lookup_elem(cstate_fd, &key, &value);
+			stat_data[c].cstate[i] = value;
+		}
+
+		for (i = 0; i < MAX_PSTATE_ENTRIES; i++) {
+			key = c * MAX_PSTATE_ENTRIES + i;
+			bpf_map_lookup_elem(pstate_fd, &key, &value);
+			stat_data[c].pstate[i] = value;
+		}
+	}
+}
+
+/*
+ * This function is copied from 'idlestat' tool function
+ * idlestat_wake_all() in idlestate.c.
+ *
+ * It sets the self running task affinity to cpus one by one so can wake up
+ * the specific CPU to handle scheduling; this results in all cpus can be
+ * waken up once and produce ftrace event 'trace_cpu_idle'.
+ */
+static int cpu_stat_inject_cpu_idle_event(void)
+{
+	int rcpu, i, ret;
+	cpu_set_t cpumask;
+	cpu_set_t original_cpumask;
+
+	ret = sysconf(_SC_NPROCESSORS_CONF);
+	if (ret < 0)
+		return -1;
+
+	rcpu = sched_getcpu();
+	if (rcpu < 0)
+		return -1;
+
+	/* Keep track of the CPUs we will run on */
+	sched_getaffinity(0, sizeof(original_cpumask), &original_cpumask);
+
+	for (i = 0; i < ret; i++) {
+
+		/* Pointless to wake up ourself */
+		if (i == rcpu)
+			continue;
+
+		/* Pointless to wake CPUs we will not run on */
+		if (!CPU_ISSET(i, &original_cpumask))
+			continue;
+
+		CPU_ZERO(&cpumask);
+		CPU_SET(i, &cpumask);
+
+		sched_setaffinity(0, sizeof(cpumask), &cpumask);
+	}
+
+	/* Enable all the CPUs of the original mask */
+	sched_setaffinity(0, sizeof(original_cpumask), &original_cpumask);
+	return 0;
+}
+
+/*
+ * It's possible to have no any frequency change for long time and cannot
+ * get ftrace event 'trace_cpu_frequency' for long period, this introduces
+ * big deviation for pstate statistics.
+ *
+ * To solve this issue, below code forces to set 'scaling_max_freq' to 208MHz
+ * for triggering ftrace event 'trace_cpu_frequency' and then recovery back to
+ * the maximum frequency value 1.2GHz.
+ */
+static int cpu_stat_inject_cpu_frequency_event(void)
+{
+	int len, fd;
+
+	fd = open(CPUFREQ_MAX_SYSFS_PATH, O_WRONLY);
+	if (fd < 0) {
+		printf("failed to open scaling_max_freq, errno=%d\n", errno);
+		return fd;
+	}
+
+	len = write(fd, CPUFREQ_LOWEST_FREQ, strlen(CPUFREQ_LOWEST_FREQ));
+	if (len < 0) {
+		printf("failed to open scaling_max_freq, errno=%d\n", errno);
+		goto err;
+	}
+
+	len = write(fd, CPUFREQ_HIGHEST_FREQ, strlen(CPUFREQ_HIGHEST_FREQ));
+	if (len < 0) {
+		printf("failed to open scaling_max_freq, errno=%d\n", errno);
+		goto err;
+	}
+
+err:
+	close(fd);
+	return len;
+}
+
+static void int_exit(int sig)
+{
+	cpu_stat_inject_cpu_idle_event();
+	cpu_stat_inject_cpu_frequency_event();
+	cpu_stat_update(cstate_map_fd, pstate_map_fd);
+	cpu_stat_print();
+	exit(0);
+}
+
+int main(int argc, char **argv)
+{
+	struct bpf_link *link = NULL;
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	char filename[256];
+	int ret;
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+	obj = bpf_object__open_file(filename, NULL);
+	if (libbpf_get_error(obj)) {
+		fprintf(stderr, "ERROR: opening BPF object file failed\n");
+		return 0;
+	}
+
+	prog = bpf_object__find_program_by_name(obj, "bpf_prog1");
+	if (!prog) {
+		printf("finding a prog in obj file failed\n");
+		goto cleanup;
+	}
+
+	/* load BPF program */
+	if (bpf_object__load(obj)) {
+		fprintf(stderr, "ERROR: loading BPF object file failed\n");
+		goto cleanup;
+	}
+
+	cstate_map_fd = bpf_object__find_map_fd_by_name(obj, "cstate_duration");
+	pstate_map_fd = bpf_object__find_map_fd_by_name(obj, "pstate_duration");
+	if (cstate_map_fd < 0 || pstate_map_fd < 0) {
+		fprintf(stderr, "ERROR: finding a map in obj file failed\n");
+		goto cleanup;
+	}
+
+	link = bpf_program__attach(prog);
+	if (libbpf_get_error(link)) {
+		fprintf(stderr, "ERROR: bpf_program__attach failed\n");
+		link = NULL;
+		goto cleanup;
+	}
+
+	ret = cpu_stat_inject_cpu_idle_event();
+	if (ret < 0)
+		return 1;
+
+	ret = cpu_stat_inject_cpu_frequency_event();
+	if (ret < 0)
+		return 1;
+
+	signal(SIGINT, int_exit);
+	signal(SIGTERM, int_exit);
+
+	while (1) {
+		cpu_stat_update(cstate_map_fd, pstate_map_fd);
+		cpu_stat_print();
+		sleep(5);
+	}
+
+cleanup:
+	bpf_link__destroy(link);
+	bpf_object__close(obj);
+	return 0;
+}

linux-7.2.3/samples/bpf/do_hbm_test.sh

@@ -0,0 +1,438 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2019 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.
+
+Usage() {
+  echo "Script for testing HBM (Host Bandwidth Manager) framework."
+  echo "It creates a cgroup to use for testing and load a BPF program to limit"
+  echo "egress or ingress bandwidth. It then uses iperf3 or netperf to create"
+  echo "loads. The output is the goodput in Mbps (unless -D was used)."
+  echo ""
+  echo "USAGE: $name [out] [-b=<prog>|--bpf=<prog>] [-c=<cc>|--cc=<cc>]"
+  echo "             [-D] [-d=<delay>|--delay=<delay>] [--debug] [-E] [--edt]"
+  echo "             [-f=<#flows>|--flows=<#flows>] [-h] [-i=<id>|--id=<id >]"
+  echo "             [-l] [-N] [--no_cn] [-p=<port>|--port=<port>] [-P]"
+  echo "             [-q=<qdisc>] [-R] [-s=<server>|--server=<server]"
+  echo "             [-S|--stats] -t=<time>|--time=<time>] [-w] [cubic|dctcp]"
+  echo "  Where:"
+  echo "    out               egress (default)"
+  echo "    -b or --bpf       BPF program filename to load and attach."
+  echo "                      Default is hbm_out_kern.o for egress,"
+  echo "    -c or -cc         TCP congestion control (cubic or dctcp)"
+  echo "    --debug           print BPF trace buffer"
+  echo "    -d or --delay     add a delay in ms using netem"
+  echo "    -D                In addition to the goodput in Mbps, it also outputs"
+  echo "                      other detailed information. This information is"
+  echo "                      test dependent (i.e. iperf3 or netperf)."
+  echo "    -E                enable ECN (not required for dctcp)"
+  echo "    --edt             use fq's Earliest Departure Time (requires fq)"
+  echo "    -f or --flows     number of concurrent flows (default=1)"
+  echo "    -i or --id        cgroup id (an integer, default is 1)"
+  echo "    -N                use netperf instead of iperf3"
+  echo "    --no_cn           Do not return CN notifications"
+  echo "    -l                do not limit flows using loopback"
+  echo "    -h                Help"
+  echo "    -p or --port      iperf3 port (default is 5201)"
+  echo "    -P                use an iperf3 instance for each flow"
+  echo "    -q                use the specified qdisc"
+  echo "    -r or --rate      rate in Mbps (default 1s 1Gbps)"
+  echo "    -R                Use TCP_RR for netperf. 1st flow has req"
+  echo "                      size of 10KB, rest of 1MB. Reply in all"
+  echo "                      cases is 1 byte."
+  echo "                      More detailed output for each flow can be found"
+  echo "                      in the files netperf.<cg>.<flow>, where <cg> is the"
+  echo "                      cgroup id as specified with the -i flag, and <flow>"
+  echo "                      is the flow id starting at 1 and increasing by 1 for"
+  echo "                      flow (as specified by -f)."
+  echo "    -s or --server    hostname of netperf server. Used to create netperf"
+  echo "                      test traffic between to hosts (default is within host)"
+  echo "                      netserver must be running on the host."
+  echo "    -S or --stats     whether to update hbm stats (default is yes)."
+  echo "    -t or --time      duration of iperf3 in seconds (default=5)"
+  echo "    -w                Work conserving flag. cgroup can increase its"
+  echo "                      bandwidth beyond the rate limit specified"
+  echo "                      while there is available bandwidth. Current"
+  echo "                      implementation assumes there is only one NIC"
+  echo "                      (eth0), but can be extended to support multiple"
+  echo "                       NICs."
+  echo "    cubic or dctcp    specify which TCP CC to use"
+  echo " "
+  exit
+}
+
+#set -x
+
+debug_flag=0
+args="$@"
+name="$0"
+netem=0
+cc=x
+dir="-o"
+dir_name="out"
+dur=5
+flows=1
+id=1
+prog=""
+port=5201
+rate=1000
+multi_iperf=0
+flow_cnt=1
+use_netperf=0
+rr=0
+ecn=0
+details=0
+server=""
+qdisc=""
+flags=""
+do_stats=0
+
+BPFFS=/sys/fs/bpf
+function config_bpffs () {
+	if mount | grep $BPFFS > /dev/null; then
+		echo "bpffs already mounted"
+	else
+		echo "bpffs not mounted. Mounting..."
+		mount -t bpf none $BPFFS
+	fi
+}
+
+function start_hbm () {
+  rm -f hbm.out
+  echo "./hbm $dir -n $id -r $rate -t $dur $flags $dbg $prog" > hbm.out
+  echo " " >> hbm.out
+  ./hbm $dir -n $id -r $rate -t $dur $flags $dbg $prog >> hbm.out 2>&1  &
+  echo $!
+}
+
+processArgs () {
+  for i in $args ; do
+    case $i in
+    # Support for upcoming ingress rate limiting
+    #in)         # support for upcoming ingress rate limiting
+    #  dir="-i"
+    #  dir_name="in"
+    #  ;;
+    out)
+      dir="-o"
+      dir_name="out"
+      ;;
+    -b=*|--bpf=*)
+      prog="${i#*=}"
+      ;;
+    -c=*|--cc=*)
+      cc="${i#*=}"
+      ;;
+    --no_cn)
+      flags="$flags --no_cn"
+      ;;
+    --debug)
+      flags="$flags -d"
+      debug_flag=1
+      ;;
+    -d=*|--delay=*)
+      netem="${i#*=}"
+      ;;
+    -D)
+      details=1
+      ;;
+    -E)
+      ecn=1
+      ;;
+    --edt)
+      flags="$flags --edt"
+      qdisc="fq"
+     ;;
+    -f=*|--flows=*)
+      flows="${i#*=}"
+      ;;
+    -i=*|--id=*)
+      id="${i#*=}"
+      ;;
+    -l)
+      flags="$flags -l"
+      ;;
+    -N)
+      use_netperf=1
+      ;;
+    -p=*|--port=*)
+      port="${i#*=}"
+      ;;
+    -P)
+      multi_iperf=1
+      ;;
+    -q=*)
+      qdisc="${i#*=}"
+      ;;
+    -r=*|--rate=*)
+      rate="${i#*=}"
+      ;;
+    -R)
+      rr=1
+      ;;
+    -s=*|--server=*)
+      server="${i#*=}"
+      ;;
+    -S|--stats)
+      flags="$flags -s"
+      do_stats=1
+      ;;
+    -t=*|--time=*)
+      dur="${i#*=}"
+      ;;
+    -w)
+      flags="$flags -w"
+      ;;
+    cubic)
+      cc=cubic
+      ;;
+    dctcp)
+      cc=dctcp
+      ;;
+    *)
+      echo "Unknown arg:$i"
+      Usage
+      ;;
+    esac
+  done
+}
+
+processArgs
+config_bpffs
+
+if [ $debug_flag -eq 1 ] ; then
+  rm -f hbm_out.log
+fi
+
+hbm_pid=$(start_hbm)
+usleep 100000
+
+host=`hostname`
+cg_base_dir=/sys/fs/cgroup/unified
+cg_dir="$cg_base_dir/cgroup-test-work-dir/hbm$id"
+
+echo $$ >> $cg_dir/cgroup.procs
+
+ulimit -l unlimited
+
+rm -f ss.out
+rm -f hbm.[0-9]*.$dir_name
+if [ $ecn -ne 0 ] ; then
+  sysctl -w -q -n net.ipv4.tcp_ecn=1
+fi
+
+if [ $use_netperf -eq 0 ] ; then
+  cur_cc=`sysctl -n net.ipv4.tcp_congestion_control`
+  if [ "$cc" != "x" ] ; then
+    sysctl -w -q -n net.ipv4.tcp_congestion_control=$cc
+  fi
+fi
+
+if [ "$netem" -ne "0" ] ; then
+  if [ "$qdisc" != "" ] ; then
+    echo "WARNING: Ignoring -q options because -d option used"
+  fi
+  tc qdisc del dev lo root > /dev/null 2>&1
+  tc qdisc add dev lo root netem delay $netem\ms > /dev/null 2>&1
+elif [ "$qdisc" != "" ] ; then
+  tc qdisc del dev eth0 root > /dev/null 2>&1
+  tc qdisc add dev eth0 root $qdisc > /dev/null 2>&1
+fi
+
+n=0
+m=$[$dur * 5]
+hn="::1"
+if [ $use_netperf -ne 0 ] ; then
+  if [ "$server" != "" ] ; then
+    hn=$server
+  fi
+fi
+
+( ping6 -i 0.2 -c $m $hn > ping.out 2>&1 ) &
+
+if [ $use_netperf -ne 0 ] ; then
+  begNetserverPid=`ps ax | grep netserver | grep --invert-match "grep" | \
+                   awk '{ print $1 }'`
+  if [ "$begNetserverPid" == "" ] ; then
+    if [ "$server" == "" ] ; then
+      ( ./netserver > /dev/null 2>&1) &
+      usleep 100000
+    fi
+  fi
+  flow_cnt=1
+  if [ "$server" == "" ] ; then
+    np_server=$host
+  else
+    np_server=$server
+  fi
+  if [ "$cc" == "x" ] ; then
+    np_cc=""
+  else
+    np_cc="-K $cc,$cc"
+  fi
+  replySize=1
+  while [ $flow_cnt -le $flows ] ; do
+    if [ $rr -ne 0 ] ; then
+      reqSize=1M
+      if [ $flow_cnt -eq 1 ] ; then
+        reqSize=10K
+      fi
+      if [ "$dir" == "-i" ] ; then
+        replySize=$reqSize
+        reqSize=1
+      fi
+      ( ./netperf -H $np_server -l $dur -f m -j -t TCP_RR  -- -r $reqSize,$replySize $np_cc -k P50_lATENCY,P90_LATENCY,LOCAL_TRANSPORT_RETRANS,REMOTE_TRANSPORT_RETRANS,LOCAL_SEND_THROUGHPUT,LOCAL_RECV_THROUGHPUT,REQUEST_SIZE,RESPONSE_SIZE > netperf.$id.$flow_cnt ) &
+    else
+      if [ "$dir" == "-i" ] ; then
+        ( ./netperf -H $np_server -l $dur -f m -j -t TCP_RR -- -r 1,10M $np_cc -k P50_LATENCY,P90_LATENCY,LOCAL_TRANSPORT_RETRANS,LOCAL_SEND_THROUGHPUT,REMOTE_TRANSPORT_RETRANS,REMOTE_SEND_THROUGHPUT,REQUEST_SIZE,RESPONSE_SIZE > netperf.$id.$flow_cnt ) &
+      else
+        ( ./netperf -H $np_server -l $dur -f m -j -t TCP_STREAM -- $np_cc -k P50_lATENCY,P90_LATENCY,LOCAL_TRANSPORT_RETRANS,LOCAL_SEND_THROUGHPUT,REQUEST_SIZE,RESPONSE_SIZE > netperf.$id.$flow_cnt ) &
+      fi
+    fi
+    flow_cnt=$[flow_cnt+1]
+  done
+
+# sleep for duration of test (plus some buffer)
+  n=$[dur+2]
+  sleep $n
+
+# force graceful termination of netperf
+  pids=`pgrep netperf`
+  for p in $pids ; do
+    kill -SIGALRM $p
+  done
+
+  flow_cnt=1
+  rate=0
+  if [ $details -ne 0 ] ; then
+    echo ""
+    echo "Details for HBM in cgroup $id"
+    if [ $do_stats -eq 1 ] ; then
+      if [ -e hbm.$id.$dir_name ] ; then
+        cat hbm.$id.$dir_name
+      fi
+    fi
+  fi
+  while [ $flow_cnt -le $flows ] ; do
+    if [ "$dir" == "-i" ] ; then
+      r=`cat netperf.$id.$flow_cnt | grep -o "REMOTE_SEND_THROUGHPUT=[0-9]*" | grep -o "[0-9]*"`
+    else
+      r=`cat netperf.$id.$flow_cnt | grep -o "LOCAL_SEND_THROUGHPUT=[0-9]*" | grep -o "[0-9]*"`
+    fi
+    echo "rate for flow $flow_cnt: $r"
+    rate=$[rate+r]
+    if [ $details -ne 0 ] ; then
+      echo "-----"
+      echo "Details for cgroup $id, flow $flow_cnt"
+      cat netperf.$id.$flow_cnt
+    fi
+    flow_cnt=$[flow_cnt+1]
+  done
+  if [ $details -ne 0 ] ; then
+    echo ""
+    delay=`grep "avg" ping.out | grep -o "= [0-9.]*/[0-9.]*" | grep -o "[0-9.]*$"`
+    echo "PING AVG DELAY:$delay"
+    echo "AGGREGATE_GOODPUT:$rate"
+  else
+    echo $rate
+  fi
+elif [ $multi_iperf -eq 0 ] ; then
+  (iperf3 -s -p $port -1 > /dev/null 2>&1) &
+  usleep 100000
+  iperf3 -c $host -p $port -i 0 -P $flows -f m -t $dur > iperf.$id
+  rates=`grep receiver iperf.$id | grep -o "[0-9.]* Mbits" | grep -o "^[0-9]*"`
+  rate=`echo $rates | grep -o "[0-9]*$"`
+
+  if [ $details -ne 0 ] ; then
+    echo ""
+    echo "Details for HBM in cgroup $id"
+    if [ $do_stats -eq 1 ] ; then
+      if [ -e hbm.$id.$dir_name ] ; then
+        cat hbm.$id.$dir_name
+      fi
+    fi
+    delay=`grep "avg" ping.out | grep -o "= [0-9.]*/[0-9.]*" | grep -o "[0-9.]*$"`
+    echo "PING AVG DELAY:$delay"
+    echo "AGGREGATE_GOODPUT:$rate"
+  else
+    echo $rate
+  fi
+else
+  flow_cnt=1
+  while [ $flow_cnt -le $flows ] ; do
+    (iperf3 -s -p $port -1 > /dev/null 2>&1) &
+    ( iperf3 -c $host -p $port -i 0 -P 1 -f m -t $dur | grep receiver | grep -o "[0-9.]* Mbits" | grep -o "^[0-9]*" | grep -o "[0-9]*$" > iperf3.$id.$flow_cnt ) &
+    port=$[port+1]
+    flow_cnt=$[flow_cnt+1]
+  done
+  n=$[dur+1]
+  sleep $n
+  flow_cnt=1
+  rate=0
+  if [ $details -ne 0 ] ; then
+    echo ""
+    echo "Details for HBM in cgroup $id"
+    if [ $do_stats -eq 1 ] ; then
+      if [ -e hbm.$id.$dir_name ] ; then
+        cat hbm.$id.$dir_name
+      fi
+    fi
+  fi
+
+  while [ $flow_cnt -le $flows ] ; do
+    r=`cat iperf3.$id.$flow_cnt`
+#    echo "rate for flow $flow_cnt: $r"
+  if [ $details -ne 0 ] ; then
+    echo "Rate for cgroup $id, flow $flow_cnt LOCAL_SEND_THROUGHPUT=$r"
+  fi
+    rate=$[rate+r]
+    flow_cnt=$[flow_cnt+1]
+  done
+  if [ $details -ne 0 ] ; then
+    delay=`grep "avg" ping.out | grep -o "= [0-9.]*/[0-9.]*" | grep -o "[0-9.]*$"`
+    echo "PING AVG DELAY:$delay"
+    echo "AGGREGATE_GOODPUT:$rate"
+  else
+    echo $rate
+  fi
+fi
+
+if [ $use_netperf -eq 0 ] ; then
+  sysctl -w -q -n net.ipv4.tcp_congestion_control=$cur_cc
+fi
+if [ $ecn -ne 0 ] ; then
+  sysctl -w -q -n net.ipv4.tcp_ecn=0
+fi
+if [ "$netem" -ne "0" ] ; then
+  tc qdisc del dev lo root > /dev/null 2>&1
+fi
+if [ "$qdisc" != "" ] ; then
+  tc qdisc del dev eth0 root > /dev/null 2>&1
+fi
+sleep 2
+
+hbmPid=`ps ax | grep "hbm " | grep --invert-match "grep" | awk '{ print $1 }'`
+if [ "$hbmPid" == "$hbm_pid" ] ; then
+  kill $hbm_pid
+fi
+
+sleep 1
+
+# Detach any pinned BPF programs that may have lingered
+rm -rf $BPFFS/hbm*
+
+if [ $use_netperf -ne 0 ] ; then
+  if [ "$server" == "" ] ; then
+    if [ "$begNetserverPid" == "" ] ; then
+      netserverPid=`ps ax | grep netserver | grep --invert-match "grep" | awk '{ print $1 }'`
+      if [ "$netserverPid" != "" ] ; then
+        kill $netserverPid
+      fi
+    fi
+  fi
+fi
+exit

linux-7.2.3/samples/bpf/fds_example.c

@@ -0,0 +1,195 @@
+#include <linux/unistd.h>
+#include <linux/bpf.h>
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <unistd.h>
+#include <string.h>
+#include <assert.h>
+#include <errno.h>
+
+#include <sys/types.h>
+#include <sys/socket.h>
+
+#include <bpf/bpf.h>
+
+#include <bpf/libbpf.h>
+#include "bpf_insn.h"
+#include "sock_example.h"
+#include "bpf_util.h"
+
+#define BPF_F_PIN	(1 << 0)
+#define BPF_F_GET	(1 << 1)
+#define BPF_F_PIN_GET	(BPF_F_PIN | BPF_F_GET)
+
+#define BPF_F_KEY	(1 << 2)
+#define BPF_F_VAL	(1 << 3)
+#define BPF_F_KEY_VAL	(BPF_F_KEY | BPF_F_VAL)
+
+#define BPF_M_UNSPEC	0
+#define BPF_M_MAP	1
+#define BPF_M_PROG	2
+
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
+static void usage(void)
+{
+	printf("Usage: fds_example [...]\n");
+	printf("       -F <file>   File to pin/get object\n");
+	printf("       -P          |- pin object\n");
+	printf("       -G          `- get object\n");
+	printf("       -m          eBPF map mode\n");
+	printf("       -k <key>    |- map key\n");
+	printf("       -v <value>  `- map value\n");
+	printf("       -p          eBPF prog mode\n");
+	printf("       -o <object> `- object file\n");
+	printf("       -h          Display this help.\n");
+}
+
+static int bpf_prog_create(const char *object)
+{
+	static struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+	};
+	size_t insns_cnt = ARRAY_SIZE(insns);
+	struct bpf_object *obj;
+	int err;
+
+	if (object) {
+		obj = bpf_object__open_file(object, NULL);
+		assert(!libbpf_get_error(obj));
+		err = bpf_object__load(obj);
+		assert(!err);
+		return bpf_program__fd(bpf_object__next_program(obj, NULL));
+	} else {
+		LIBBPF_OPTS(bpf_prog_load_opts, opts,
+			.log_buf = bpf_log_buf,
+			.log_size = BPF_LOG_BUF_SIZE,
+		);
+
+		return bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL",
+				     insns, insns_cnt, &opts);
+	}
+}
+
+static int bpf_do_map(const char *file, uint32_t flags, uint32_t key,
+		      uint32_t value)
+{
+	int fd, ret;
+
+	if (flags & BPF_F_PIN) {
+		fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(uint32_t),
+				    sizeof(uint32_t), 1024, NULL);
+		printf("bpf: map fd:%d (%s)\n", fd, strerror(errno));
+		assert(fd > 0);
+
+		ret = bpf_obj_pin(fd, file);
+		printf("bpf: pin ret:(%d,%s)\n", ret, strerror(errno));
+		assert(ret == 0);
+	} else {
+		fd = bpf_obj_get(file);
+		printf("bpf: get fd:%d (%s)\n", fd, strerror(errno));
+		assert(fd > 0);
+	}
+
+	if ((flags & BPF_F_KEY_VAL) == BPF_F_KEY_VAL) {
+		ret = bpf_map_update_elem(fd, &key, &value, 0);
+		printf("bpf: fd:%d u->(%u:%u) ret:(%d,%s)\n", fd, key, value,
+		       ret, strerror(errno));
+		assert(ret == 0);
+	} else if (flags & BPF_F_KEY) {
+		ret = bpf_map_lookup_elem(fd, &key, &value);
+		printf("bpf: fd:%d l->(%u):%u ret:(%d,%s)\n", fd, key, value,
+		       ret, strerror(errno));
+		assert(ret == 0);
+	}
+
+	return 0;
+}
+
+static int bpf_do_prog(const char *file, uint32_t flags, const char *object)
+{
+	int fd, sock, ret;
+
+	if (flags & BPF_F_PIN) {
+		fd = bpf_prog_create(object);
+		printf("bpf: prog fd:%d (%s)\n", fd, strerror(errno));
+		assert(fd > 0);
+
+		ret = bpf_obj_pin(fd, file);
+		printf("bpf: pin ret:(%d,%s)\n", ret, strerror(errno));
+		assert(ret == 0);
+	} else {
+		fd = bpf_obj_get(file);
+		printf("bpf: get fd:%d (%s)\n", fd, strerror(errno));
+		assert(fd > 0);
+	}
+
+	sock = open_raw_sock("lo");
+	assert(sock > 0);
+
+	ret = setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &fd, sizeof(fd));
+	printf("bpf: sock:%d <- fd:%d attached ret:(%d,%s)\n", sock, fd,
+	       ret, strerror(errno));
+	assert(ret == 0);
+
+	return 0;
+}
+
+int main(int argc, char **argv)
+{
+	const char *file = NULL, *object = NULL;
+	uint32_t key = 0, value = 0, flags = 0;
+	int opt, mode = BPF_M_UNSPEC;
+
+	while ((opt = getopt(argc, argv, "F:PGmk:v:po:")) != -1) {
+		switch (opt) {
+		/* General args */
+		case 'F':
+			file = optarg;
+			break;
+		case 'P':
+			flags |= BPF_F_PIN;
+			break;
+		case 'G':
+			flags |= BPF_F_GET;
+			break;
+		/* Map-related args */
+		case 'm':
+			mode = BPF_M_MAP;
+			break;
+		case 'k':
+			key = strtoul(optarg, NULL, 0);
+			flags |= BPF_F_KEY;
+			break;
+		case 'v':
+			value = strtoul(optarg, NULL, 0);
+			flags |= BPF_F_VAL;
+			break;
+		/* Prog-related args */
+		case 'p':
+			mode = BPF_M_PROG;
+			break;
+		case 'o':
+			object = optarg;
+			break;
+		default:
+			goto out;
+		}
+	}
+
+	if (!(flags & BPF_F_PIN_GET) || !file)
+		goto out;
+
+	switch (mode) {
+	case BPF_M_MAP:
+		return bpf_do_map(file, flags, key, value);
+	case BPF_M_PROG:
+		return bpf_do_prog(file, flags, object);
+	}
+out:
+	usage();
+	return -1;
+}

linux-7.2.3/samples/bpf/gnu/stubs.h

@@ -0,0 +1 @@
+/* dummy .h to trick /usr/include/features.h to work with 'clang --target=bpf' */

linux-7.2.3/samples/bpf/hash_func01.h

@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: LGPL-2.1
+ *
+ * Based on Paul Hsieh's (LGPG 2.1) hash function
+ * From: http://www.azillionmonkeys.com/qed/hash.html
+ */
+
+#define get16bits(d) (*((const __u16 *) (d)))
+
+static __always_inline
+__u32 SuperFastHash (const char *data, int len, __u32 initval) {
+	__u32 hash = initval;
+	__u32 tmp;
+	int rem;
+
+	if (len <= 0 || data == NULL) return 0;
+
+	rem = len & 3;
+	len >>= 2;
+
+	/* Main loop */
+#pragma clang loop unroll(full)
+	for (;len > 0; len--) {
+		hash  += get16bits (data);
+		tmp    = (get16bits (data+2) << 11) ^ hash;
+		hash   = (hash << 16) ^ tmp;
+		data  += 2*sizeof (__u16);
+		hash  += hash >> 11;
+	}
+
+	/* Handle end cases */
+	switch (rem) {
+        case 3: hash += get16bits (data);
+                hash ^= hash << 16;
+                hash ^= ((signed char)data[sizeof (__u16)]) << 18;
+                hash += hash >> 11;
+                break;
+        case 2: hash += get16bits (data);
+                hash ^= hash << 11;
+                hash += hash >> 17;
+                break;
+        case 1: hash += (signed char)*data;
+                hash ^= hash << 10;
+                hash += hash >> 1;
+	}
+
+	/* Force "avalanching" of final 127 bits */
+	hash ^= hash << 3;
+	hash += hash >> 5;
+	hash ^= hash << 4;
+	hash += hash >> 17;
+	hash ^= hash << 25;
+	hash += hash >> 6;
+
+	return hash;
+}

linux-7.2.3/samples/bpf/hbm.c

@@ -0,0 +1,515 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 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.
+ *
+ * Example program for Host Bandwidth Management
+ *
+ * This program loads a cgroup skb BPF program to enforce cgroup output
+ * (egress) or input (ingress) bandwidth limits.
+ *
+ * USAGE: hbm [-d] [-l] [-n <id>] [-r <rate>] [-s] [-t <secs>] [-w] [-h] [prog]
+ *   Where:
+ *    -d	Print BPF trace debug buffer
+ *    -l	Also limit flows doing loopback
+ *    -n <#>	To create cgroup \"/hbm#\" and attach prog
+ *		Default is /hbm1
+ *    --no_cn   Do not return cn notifications
+ *    -r <rate>	Rate limit in Mbps
+ *    -s	Get HBM stats (marked, dropped, etc.)
+ *    -t <time>	Exit after specified seconds (default is 0)
+ *    -w	Work conserving flag. cgroup can increase its bandwidth
+ *		beyond the rate limit specified while there is available
+ *		bandwidth. Current implementation assumes there is only
+ *		NIC (eth0), but can be extended to support multiple NICs.
+ *		Currently only supported for egress.
+ *    -h	Print this info
+ *    prog	BPF program file name. Name defaults to hbm_out_kern.o
+ */
+
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <assert.h>
+#include <sys/time.h>
+#include <unistd.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/unistd.h>
+#include <linux/compiler.h>
+
+#include <linux/bpf.h>
+#include <bpf/bpf.h>
+#include <getopt.h>
+
+#include "cgroup_helpers.h"
+#include "hbm.h"
+#include "bpf_util.h"
+#include <bpf/libbpf.h>
+
+bool outFlag = true;
+int minRate = 1000;		/* cgroup rate limit in Mbps */
+int rate = 1000;		/* can grow if rate conserving is enabled */
+int dur = 1;
+bool stats_flag;
+bool loopback_flag;
+bool debugFlag;
+bool work_conserving_flag;
+bool no_cn_flag;
+bool edt_flag;
+
+static void Usage(void);
+static void read_trace_pipe2(void);
+static void do_error(char *msg, bool errno_flag);
+
+#define TRACEFS "/sys/kernel/tracing/"
+
+static struct bpf_program *bpf_prog;
+static struct bpf_object *obj;
+static int queue_stats_fd;
+
+static void read_trace_pipe2(void)
+{
+	int trace_fd;
+	FILE *outf;
+	char *outFname = "hbm_out.log";
+
+	trace_fd = open(TRACEFS "trace_pipe", O_RDONLY, 0);
+	if (trace_fd < 0) {
+		printf("Error opening trace_pipe\n");
+		return;
+	}
+
+//	Future support of ingress
+//	if (!outFlag)
+//		outFname = "hbm_in.log";
+	outf = fopen(outFname, "w");
+
+	if (outf == NULL)
+		printf("Error creating %s\n", outFname);
+
+	while (1) {
+		static char buf[4097];
+		ssize_t sz;
+
+		sz = read(trace_fd, buf, sizeof(buf) - 1);
+		if (sz > 0) {
+			buf[sz] = 0;
+			puts(buf);
+			if (outf != NULL) {
+				fprintf(outf, "%s\n", buf);
+				fflush(outf);
+			}
+		}
+	}
+}
+
+static void do_error(char *msg, bool errno_flag)
+{
+	if (errno_flag)
+		printf("ERROR: %s, errno: %d\n", msg, errno);
+	else
+		printf("ERROR: %s\n", msg);
+	exit(1);
+}
+
+static int prog_load(char *prog)
+{
+	struct bpf_program *pos;
+	const char *sec_name;
+
+	obj = bpf_object__open_file(prog, NULL);
+	if (libbpf_get_error(obj)) {
+		printf("ERROR: opening BPF object file failed\n");
+		return 1;
+	}
+
+	/* load BPF program */
+	if (bpf_object__load(obj)) {
+		printf("ERROR: loading BPF object file failed\n");
+		goto err;
+	}
+
+	bpf_object__for_each_program(pos, obj) {
+		sec_name = bpf_program__section_name(pos);
+		if (sec_name && !strcmp(sec_name, "cgroup_skb/egress")) {
+			bpf_prog = pos;
+			break;
+		}
+	}
+	if (!bpf_prog) {
+		printf("ERROR: finding a prog in obj file failed\n");
+		goto err;
+	}
+
+	queue_stats_fd = bpf_object__find_map_fd_by_name(obj, "queue_stats");
+	if (queue_stats_fd < 0) {
+		printf("ERROR: finding a map in obj file failed\n");
+		goto err;
+	}
+
+	return 0;
+
+err:
+	bpf_object__close(obj);
+	return 1;
+}
+
+static int run_bpf_prog(char *prog, int cg_id)
+{
+	struct hbm_queue_stats qstats = {0};
+	char cg_dir[100], cg_pin_path[100];
+	struct bpf_link *link = NULL;
+	int key = 0;
+	int cg1 = 0;
+	int rc = 0;
+
+	sprintf(cg_dir, "/hbm%d", cg_id);
+	rc = prog_load(prog);
+	if (rc != 0)
+		return rc;
+
+	if (setup_cgroup_environment()) {
+		printf("ERROR: setting cgroup environment\n");
+		goto err;
+	}
+	cg1 = create_and_get_cgroup(cg_dir);
+	if (!cg1) {
+		printf("ERROR: create_and_get_cgroup\n");
+		goto err;
+	}
+	if (join_cgroup(cg_dir)) {
+		printf("ERROR: join_cgroup\n");
+		goto err;
+	}
+
+	qstats.rate = rate;
+	qstats.stats = stats_flag ? 1 : 0;
+	qstats.loopback = loopback_flag ? 1 : 0;
+	qstats.no_cn = no_cn_flag ? 1 : 0;
+	if (bpf_map_update_elem(queue_stats_fd, &key, &qstats, BPF_ANY)) {
+		printf("ERROR: Could not update map element\n");
+		goto err;
+	}
+
+	if (!outFlag)
+		bpf_program__set_expected_attach_type(bpf_prog, BPF_CGROUP_INET_INGRESS);
+
+	link = bpf_program__attach_cgroup(bpf_prog, cg1);
+	if (libbpf_get_error(link)) {
+		fprintf(stderr, "ERROR: bpf_program__attach_cgroup failed\n");
+		goto err;
+	}
+
+	sprintf(cg_pin_path, "/sys/fs/bpf/hbm%d", cg_id);
+	rc = bpf_link__pin(link, cg_pin_path);
+	if (rc < 0) {
+		printf("ERROR: bpf_link__pin failed: %d\n", rc);
+		goto err;
+	}
+
+	if (work_conserving_flag) {
+		struct timeval t0, t_last, t_new;
+		FILE *fin;
+		unsigned long long last_eth_tx_bytes, new_eth_tx_bytes;
+		signed long long last_cg_tx_bytes, new_cg_tx_bytes;
+		signed long long delta_time, delta_bytes, delta_rate;
+		int delta_ms;
+#define DELTA_RATE_CHECK 10000		/* in us */
+#define RATE_THRESHOLD 9500000000	/* 9.5 Gbps */
+
+		bpf_map_lookup_elem(queue_stats_fd, &key, &qstats);
+		if (gettimeofday(&t0, NULL) < 0)
+			do_error("gettimeofday failed", true);
+		t_last = t0;
+		fin = fopen("/sys/class/net/eth0/statistics/tx_bytes", "r");
+		if (fscanf(fin, "%llu", &last_eth_tx_bytes) != 1)
+			do_error("fscanf fails", false);
+		fclose(fin);
+		last_cg_tx_bytes = qstats.bytes_total;
+		while (true) {
+			usleep(DELTA_RATE_CHECK);
+			if (gettimeofday(&t_new, NULL) < 0)
+				do_error("gettimeofday failed", true);
+			delta_ms = (t_new.tv_sec - t0.tv_sec) * 1000 +
+				(t_new.tv_usec - t0.tv_usec)/1000;
+			if (delta_ms > dur * 1000)
+				break;
+			delta_time = (t_new.tv_sec - t_last.tv_sec) * 1000000 +
+				(t_new.tv_usec - t_last.tv_usec);
+			if (delta_time == 0)
+				continue;
+			t_last = t_new;
+			fin = fopen("/sys/class/net/eth0/statistics/tx_bytes",
+				    "r");
+			if (fscanf(fin, "%llu", &new_eth_tx_bytes) != 1)
+				do_error("fscanf fails", false);
+			fclose(fin);
+			printf("  new_eth_tx_bytes:%llu\n",
+			       new_eth_tx_bytes);
+			bpf_map_lookup_elem(queue_stats_fd, &key, &qstats);
+			new_cg_tx_bytes = qstats.bytes_total;
+			delta_bytes = new_eth_tx_bytes - last_eth_tx_bytes;
+			last_eth_tx_bytes = new_eth_tx_bytes;
+			delta_rate = (delta_bytes * 8000000) / delta_time;
+			printf("%5d - eth_rate:%.1fGbps cg_rate:%.3fGbps",
+			       delta_ms, delta_rate/1000000000.0,
+			       rate/1000.0);
+			if (delta_rate < RATE_THRESHOLD) {
+				/* can increase cgroup rate limit, but first
+				 * check if we are using the current limit.
+				 * Currently increasing by 6.25%, unknown
+				 * if that is the optimal rate.
+				 */
+				int rate_diff100;
+
+				delta_bytes = new_cg_tx_bytes -
+					last_cg_tx_bytes;
+				last_cg_tx_bytes = new_cg_tx_bytes;
+				delta_rate = (delta_bytes * 8000000) /
+					delta_time;
+				printf(" rate:%.3fGbps",
+				       delta_rate/1000000000.0);
+				rate_diff100 = (((long long)rate)*1000000 -
+						     delta_rate) * 100 /
+					(((long long) rate) * 1000000);
+				printf("  rdiff:%d", rate_diff100);
+				if (rate_diff100  <= 3) {
+					rate += (rate >> 4);
+					if (rate > RATE_THRESHOLD / 1000000)
+						rate = RATE_THRESHOLD / 1000000;
+					qstats.rate = rate;
+					printf(" INC\n");
+				} else {
+					printf("\n");
+				}
+			} else {
+				/* Need to decrease cgroup rate limit.
+				 * Currently decreasing by 12.5%, unknown
+				 * if that is optimal
+				 */
+				printf(" DEC\n");
+				rate -= (rate >> 3);
+				if (rate < minRate)
+					rate = minRate;
+				qstats.rate = rate;
+			}
+			if (bpf_map_update_elem(queue_stats_fd, &key, &qstats, BPF_ANY))
+				do_error("update map element fails", false);
+		}
+	} else {
+		sleep(dur);
+	}
+	// Get stats!
+	if (stats_flag && bpf_map_lookup_elem(queue_stats_fd, &key, &qstats)) {
+		char fname[100];
+		FILE *fout;
+
+		if (!outFlag)
+			sprintf(fname, "hbm.%d.in", cg_id);
+		else
+			sprintf(fname, "hbm.%d.out", cg_id);
+		fout = fopen(fname, "w");
+		fprintf(fout, "id:%d\n", cg_id);
+		fprintf(fout, "ERROR: Could not lookup queue_stats\n");
+		fclose(fout);
+	} else if (stats_flag && qstats.lastPacketTime >
+		   qstats.firstPacketTime) {
+		long long delta_us = (qstats.lastPacketTime -
+				      qstats.firstPacketTime)/1000;
+		unsigned int rate_mbps = ((qstats.bytes_total -
+					   qstats.bytes_dropped) * 8 /
+					  delta_us);
+		double percent_pkts, percent_bytes;
+		char fname[100];
+		FILE *fout;
+		int k;
+		static const char *returnValNames[] = {
+			"DROP_PKT",
+			"ALLOW_PKT",
+			"DROP_PKT_CWR",
+			"ALLOW_PKT_CWR"
+		};
+#define RET_VAL_COUNT 4
+
+// Future support of ingress
+//		if (!outFlag)
+//			sprintf(fname, "hbm.%d.in", cg_id);
+//		else
+		sprintf(fname, "hbm.%d.out", cg_id);
+		fout = fopen(fname, "w");
+		fprintf(fout, "id:%d\n", cg_id);
+		fprintf(fout, "rate_mbps:%d\n", rate_mbps);
+		fprintf(fout, "duration:%.1f secs\n",
+			(qstats.lastPacketTime - qstats.firstPacketTime) /
+			1000000000.0);
+		fprintf(fout, "packets:%d\n", (int)qstats.pkts_total);
+		fprintf(fout, "bytes_MB:%d\n", (int)(qstats.bytes_total /
+						     1000000));
+		fprintf(fout, "pkts_dropped:%d\n", (int)qstats.pkts_dropped);
+		fprintf(fout, "bytes_dropped_MB:%d\n",
+			(int)(qstats.bytes_dropped /
+						       1000000));
+		// Marked Pkts and Bytes
+		percent_pkts = (qstats.pkts_marked * 100.0) /
+			(qstats.pkts_total + 1);
+		percent_bytes = (qstats.bytes_marked * 100.0) /
+			(qstats.bytes_total + 1);
+		fprintf(fout, "pkts_marked_percent:%6.2f\n", percent_pkts);
+		fprintf(fout, "bytes_marked_percent:%6.2f\n", percent_bytes);
+
+		// Dropped Pkts and Bytes
+		percent_pkts = (qstats.pkts_dropped * 100.0) /
+			(qstats.pkts_total + 1);
+		percent_bytes = (qstats.bytes_dropped * 100.0) /
+			(qstats.bytes_total + 1);
+		fprintf(fout, "pkts_dropped_percent:%6.2f\n", percent_pkts);
+		fprintf(fout, "bytes_dropped_percent:%6.2f\n", percent_bytes);
+
+		// ECN CE markings
+		percent_pkts = (qstats.pkts_ecn_ce * 100.0) /
+			(qstats.pkts_total + 1);
+		fprintf(fout, "pkts_ecn_ce:%6.2f (%d)\n", percent_pkts,
+			(int)qstats.pkts_ecn_ce);
+
+		// Average cwnd
+		fprintf(fout, "avg cwnd:%d\n",
+			(int)(qstats.sum_cwnd / (qstats.sum_cwnd_cnt + 1)));
+		// Average rtt
+		fprintf(fout, "avg rtt:%d\n",
+			(int)(qstats.sum_rtt / (qstats.pkts_total + 1)));
+		// Average credit
+		if (edt_flag)
+			fprintf(fout, "avg credit_ms:%.03f\n",
+				(qstats.sum_credit /
+				 (qstats.pkts_total + 1.0)) / 1000000.0);
+		else
+			fprintf(fout, "avg credit:%d\n",
+				(int)(qstats.sum_credit /
+				      (1500 * ((int)qstats.pkts_total ) + 1)));
+
+		// Return values stats
+		for (k = 0; k < RET_VAL_COUNT; k++) {
+			percent_pkts = (qstats.returnValCount[k] * 100.0) /
+				(qstats.pkts_total + 1);
+			fprintf(fout, "%s:%6.2f (%d)\n", returnValNames[k],
+				percent_pkts, (int)qstats.returnValCount[k]);
+		}
+		fclose(fout);
+	}
+
+	if (debugFlag)
+		read_trace_pipe2();
+	goto cleanup;
+
+err:
+	rc = 1;
+
+cleanup:
+	bpf_link__destroy(link);
+	bpf_object__close(obj);
+
+	if (cg1 != -1)
+		close(cg1);
+
+	if (rc != 0)
+		cleanup_cgroup_environment();
+	return rc;
+}
+
+static void Usage(void)
+{
+	printf("This program loads a cgroup skb BPF program to enforce\n"
+	       "cgroup output (egress) bandwidth limits.\n\n"
+	       "USAGE: hbm [-o] [-d]  [-l] [-n <id>] [--no_cn] [-r <rate>]\n"
+	       "           [-s] [-t <secs>] [-w] [-h] [prog]\n"
+	       "  Where:\n"
+	       "    -o         indicates egress direction (default)\n"
+	       "    -d         print BPF trace debug buffer\n"
+	       "    --edt      use fq's Earliest Departure Time\n"
+	       "    -l         also limit flows using loopback\n"
+	       "    -n <#>     to create cgroup \"/hbm#\" and attach prog\n"
+	       "               Default is /hbm1\n"
+	       "    --no_cn    disable CN notifications\n"
+	       "    -r <rate>  Rate in Mbps\n"
+	       "    -s         Update HBM stats\n"
+	       "    -t <time>  Exit after specified seconds (default is 0)\n"
+	       "    -w	       Work conserving flag. cgroup can increase\n"
+	       "               bandwidth beyond the rate limit specified\n"
+	       "               while there is available bandwidth. Current\n"
+	       "               implementation assumes there is only eth0\n"
+	       "               but can be extended to support multiple NICs\n"
+	       "    -h         print this info\n"
+	       "    prog       BPF program file name. Name defaults to\n"
+	       "                 hbm_out_kern.o\n");
+}
+
+int main(int argc, char **argv)
+{
+	char *prog = "hbm_out_kern.o";
+	int  k;
+	int cg_id = 1;
+	char *optstring = "iodln:r:st:wh";
+	struct option loptions[] = {
+		{"no_cn", 0, NULL, 1},
+		{"edt", 0, NULL, 2},
+		{NULL, 0, NULL, 0}
+	};
+
+	while ((k = getopt_long(argc, argv, optstring, loptions, NULL)) != -1) {
+		switch (k) {
+		case 1:
+			no_cn_flag = true;
+			break;
+		case 2:
+			prog = "hbm_edt_kern.o";
+			edt_flag = true;
+			break;
+		case'o':
+			break;
+		case 'd':
+			debugFlag = true;
+			break;
+		case 'l':
+			loopback_flag = true;
+			break;
+		case 'n':
+			cg_id = atoi(optarg);
+			break;
+		case 'r':
+			minRate = atoi(optarg) * 1.024;
+			rate = minRate;
+			break;
+		case 's':
+			stats_flag = true;
+			break;
+		case 't':
+			dur = atoi(optarg);
+			break;
+		case 'w':
+			work_conserving_flag = true;
+			break;
+		case '?':
+			if (optopt == 'n' || optopt == 'r' || optopt == 't')
+				fprintf(stderr,
+					"Option -%c requires an argument.\n\n",
+					optopt);
+		case 'h':
+		default:
+			Usage();
+			return 0;
+		}
+	}
+
+	if (optind < argc)
+		prog = argv[optind];
+	printf("HBM prog: %s\n", prog != NULL ? prog : "NULL");
+
+	/* Use libbpf 1.0 API mode */
+	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
+
+	return run_bpf_prog(prog, cg_id);
+}

linux-7.2.3/samples/bpf/hbm.h

@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright (c) 2019 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 file for Host Bandwidth Management (HBM) programs
+ */
+struct hbm_vqueue {
+	struct bpf_spin_lock lock;
+	/* 4 byte hole */
+	unsigned long long lasttime;	/* In ns */
+	int credit;			/* In bytes */
+	unsigned int rate;		/* In bytes per NS << 20 */
+};
+
+struct hbm_queue_stats {
+	unsigned long rate;		/* in Mbps*/
+	unsigned long stats:1,		/* get HBM stats (marked, dropped,..) */
+		loopback:1,		/* also limit flows using loopback */
+		no_cn:1;		/* do not use cn flags */
+	unsigned long long pkts_marked;
+	unsigned long long bytes_marked;
+	unsigned long long pkts_dropped;
+	unsigned long long bytes_dropped;
+	unsigned long long pkts_total;
+	unsigned long long bytes_total;
+	unsigned long long firstPacketTime;
+	unsigned long long lastPacketTime;
+	unsigned long long pkts_ecn_ce;
+	unsigned long long returnValCount[4];
+	unsigned long long sum_cwnd;
+	unsigned long long sum_rtt;
+	unsigned long long sum_cwnd_cnt;
+	long long sum_credit;
+};

linux-7.2.3/samples/bpf/hbm_edt_kern.c

@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 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.
+ *
+ * Sample Host Bandwidth Manager (HBM) BPF program.
+ *
+ * A cgroup skb BPF egress program to limit cgroup output bandwidth.
+ * It uses a modified virtual token bucket queue to limit average
+ * egress bandwidth. The implementation uses credits instead of tokens.
+ * Negative credits imply that queueing would have happened (this is
+ * a virtual queue, so no queueing is done by it. However, queueing may
+ * occur at the actual qdisc (which is not used for rate limiting).
+ *
+ * This implementation uses 3 thresholds, one to start marking packets and
+ * the other two to drop packets:
+ *                                  CREDIT
+ *        - <--------------------------|------------------------> +
+ *              |    |          |      0
+ *              |  Large pkt    |
+ *              |  drop thresh  |
+ *   Small pkt drop             Mark threshold
+ *       thresh
+ *
+ * The effect of marking depends on the type of packet:
+ * a) If the packet is ECN enabled and it is a TCP packet, then the packet
+ *    is ECN marked.
+ * b) If the packet is a TCP packet, then we probabilistically call tcp_cwr
+ *    to reduce the congestion window. The current implementation uses a linear
+ *    distribution (0% probability at marking threshold, 100% probability
+ *    at drop threshold).
+ * c) If the packet is not a TCP packet, then it is dropped.
+ *
+ * If the credit is below the drop threshold, the packet is dropped. If it
+ * is a TCP packet, then it also calls tcp_cwr since packets dropped by
+ * a cgroup skb BPF program do not automatically trigger a call to
+ * tcp_cwr in the current kernel code.
+ *
+ * This BPF program actually uses 2 drop thresholds, one threshold
+ * for larger packets (>= 120 bytes) and another for smaller packets. This
+ * protects smaller packets such as SYNs, ACKs, etc.
+ *
+ * The default bandwidth limit is set at 1Gbps but this can be changed by
+ * a user program through a shared BPF map. In addition, by default this BPF
+ * program does not limit connections using loopback. This behavior can be
+ * overwritten by the user program. There is also an option to calculate
+ * some statistics, such as percent of packets marked or dropped, which
+ * a user program, such as hbm, can access.
+ */
+
+#include "hbm_kern.h"
+
+SEC("cgroup_skb/egress")
+int _hbm_out_cg(struct __sk_buff *skb)
+{
+	long long delta = 0, delta_send;
+	unsigned long long curtime, sendtime;
+	struct hbm_queue_stats *qsp = NULL;
+	unsigned int queue_index = 0;
+	bool congestion_flag = false;
+	bool ecn_ce_flag = false;
+	struct hbm_pkt_info pkti = {};
+	struct hbm_vqueue *qdp;
+	bool drop_flag = false;
+	bool cwr_flag = false;
+	int len = skb->len;
+	int rv = ALLOW_PKT;
+
+	qsp = bpf_map_lookup_elem(&queue_stats, &queue_index);
+
+	// Check if we should ignore loopback traffic
+	if (qsp != NULL && !qsp->loopback && (skb->ifindex == 1))
+		return ALLOW_PKT;
+
+	hbm_get_pkt_info(skb, &pkti);
+
+	// We may want to account for the length of headers in len
+	// calculation, like ETH header + overhead, specially if it
+	// is a gso packet. But I am not doing it right now.
+
+	qdp = bpf_get_local_storage(&queue_state, 0);
+	if (!qdp)
+		return ALLOW_PKT;
+	if (qdp->lasttime == 0)
+		hbm_init_edt_vqueue(qdp, 1024);
+
+	curtime = bpf_ktime_get_ns();
+
+	// Begin critical section
+	bpf_spin_lock(&qdp->lock);
+	delta = qdp->lasttime - curtime;
+	// bound bursts to 100us
+	if (delta < -BURST_SIZE_NS) {
+		// negative delta is a credit that allows bursts
+		qdp->lasttime = curtime - BURST_SIZE_NS;
+		delta = -BURST_SIZE_NS;
+	}
+	sendtime = qdp->lasttime;
+	delta_send = BYTES_TO_NS(len, qdp->rate);
+	__sync_add_and_fetch(&(qdp->lasttime), delta_send);
+	bpf_spin_unlock(&qdp->lock);
+	// End critical section
+
+	// Set EDT of packet
+	skb->tstamp = sendtime;
+
+	// Check if we should update rate
+	if (qsp != NULL && (qsp->rate * 128) != qdp->rate)
+		qdp->rate = qsp->rate * 128;
+
+	// Set flags (drop, congestion, cwr)
+	// last packet will be sent in the future, bound latency
+	if (delta > DROP_THRESH_NS || (delta > LARGE_PKT_DROP_THRESH_NS &&
+				       len > LARGE_PKT_THRESH)) {
+		drop_flag = true;
+		if (pkti.is_tcp && pkti.ecn == 0)
+			cwr_flag = true;
+	} else if (delta > MARK_THRESH_NS) {
+		if (pkti.is_tcp)
+			congestion_flag = true;
+		else
+			drop_flag = true;
+	}
+
+	if (congestion_flag) {
+		if (bpf_skb_ecn_set_ce(skb)) {
+			ecn_ce_flag = true;
+		} else {
+			if (pkti.is_tcp) {
+				unsigned int rand = bpf_get_prandom_u32();
+
+				if (delta >= MARK_THRESH_NS +
+				    (rand % MARK_REGION_SIZE_NS)) {
+					// Do congestion control
+					cwr_flag = true;
+				}
+			} else if (len > LARGE_PKT_THRESH) {
+				// Problem if too many small packets?
+				drop_flag = true;
+				congestion_flag = false;
+			}
+		}
+	}
+
+	if (pkti.is_tcp && drop_flag && pkti.packets_out <= 1) {
+		drop_flag = false;
+		cwr_flag = true;
+		congestion_flag = false;
+	}
+
+	if (qsp != NULL && qsp->no_cn)
+			cwr_flag = false;
+
+	hbm_update_stats(qsp, len, curtime, congestion_flag, drop_flag,
+			 cwr_flag, ecn_ce_flag, &pkti, (int) delta);
+
+	if (drop_flag) {
+		__sync_add_and_fetch(&(qdp->lasttime), -delta_send);
+		rv = DROP_PKT;
+	}
+
+	if (cwr_flag)
+		rv |= CWR;
+	return rv;
+}
+char _license[] SEC("license") = "GPL";

linux-7.2.3/samples/bpf/hbm_kern.h

@@ -0,0 +1,215 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright (c) 2019 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 file for sample Host Bandwidth Manager (HBM) BPF programs
+ */
+#define KBUILD_MODNAME "foo"
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <uapi/linux/ipv6.h>
+#include <uapi/linux/in.h>
+#include <uapi/linux/tcp.h>
+#include <uapi/linux/filter.h>
+#include <uapi/linux/pkt_cls.h>
+#include <net/ipv6.h>
+#include <net/inet_ecn.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
+#include "hbm.h"
+
+#define DROP_PKT	0
+#define ALLOW_PKT	1
+#define TCP_ECN_OK	1
+#define CWR		2
+
+#ifndef HBM_DEBUG  // Define HBM_DEBUG to enable debugging
+#undef bpf_printk
+#define bpf_printk(fmt, ...)
+#endif
+
+#define INITIAL_CREDIT_PACKETS	100
+#define MAX_BYTES_PER_PACKET	1500
+#define MARK_THRESH		(40 * MAX_BYTES_PER_PACKET)
+#define DROP_THRESH		(80 * 5 * MAX_BYTES_PER_PACKET)
+#define LARGE_PKT_DROP_THRESH	(DROP_THRESH - (15 * MAX_BYTES_PER_PACKET))
+#define MARK_REGION_SIZE	(LARGE_PKT_DROP_THRESH - MARK_THRESH)
+#define LARGE_PKT_THRESH	120
+#define MAX_CREDIT		(100 * MAX_BYTES_PER_PACKET)
+#define INIT_CREDIT		(INITIAL_CREDIT_PACKETS * MAX_BYTES_PER_PACKET)
+
+// Time base accounting for fq's EDT
+#define BURST_SIZE_NS		100000 // 100us
+#define MARK_THRESH_NS		50000 // 50us
+#define DROP_THRESH_NS		500000 // 500us
+// Reserve 20us of queuing for small packets (less than 120 bytes)
+#define LARGE_PKT_DROP_THRESH_NS (DROP_THRESH_NS - 20000)
+#define MARK_REGION_SIZE_NS	(LARGE_PKT_DROP_THRESH_NS - MARK_THRESH_NS)
+
+// rate in bytes per ns << 20
+#define CREDIT_PER_NS(delta, rate) ((((u64)(delta)) * (rate)) >> 20)
+#define BYTES_PER_NS(delta, rate) ((((u64)(delta)) * (rate)) >> 20)
+#define BYTES_TO_NS(bytes, rate) div64_u64(((u64)(bytes)) << 20, (u64)(rate))
+
+struct {
+	__uint(type, BPF_MAP_TYPE_CGROUP_STORAGE);
+	__type(key, struct bpf_cgroup_storage_key);
+	__type(value, struct hbm_vqueue);
+} queue_state SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, u32);
+	__type(value, struct hbm_queue_stats);
+} queue_stats SEC(".maps");
+
+struct hbm_pkt_info {
+	int	cwnd;
+	int	rtt;
+	int	packets_out;
+	bool	is_ip;
+	bool	is_tcp;
+	short	ecn;
+};
+
+static int get_tcp_info(struct __sk_buff *skb, struct hbm_pkt_info *pkti)
+{
+	struct bpf_sock *sk;
+	struct bpf_tcp_sock *tp;
+
+	sk = skb->sk;
+	if (sk) {
+		sk = bpf_sk_fullsock(sk);
+		if (sk) {
+			if (sk->protocol == IPPROTO_TCP) {
+				tp = bpf_tcp_sock(sk);
+				if (tp) {
+					pkti->cwnd = tp->snd_cwnd;
+					pkti->rtt = tp->srtt_us >> 3;
+					pkti->packets_out = tp->packets_out;
+					return 0;
+				}
+			}
+		}
+	}
+	pkti->cwnd = 0;
+	pkti->rtt = 0;
+	pkti->packets_out = 0;
+	return 1;
+}
+
+static void hbm_get_pkt_info(struct __sk_buff *skb,
+			     struct hbm_pkt_info *pkti)
+{
+	struct iphdr iph;
+	struct ipv6hdr *ip6h;
+
+	pkti->cwnd = 0;
+	pkti->rtt = 0;
+	bpf_skb_load_bytes(skb, 0, &iph, 12);
+	if (iph.version == 6) {
+		ip6h = (struct ipv6hdr *)&iph;
+		pkti->is_ip = true;
+		pkti->is_tcp = (ip6h->nexthdr == 6);
+		pkti->ecn = (ip6h->flow_lbl[0] >> 4) & INET_ECN_MASK;
+	} else if (iph.version == 4) {
+		pkti->is_ip = true;
+		pkti->is_tcp = (iph.protocol == 6);
+		pkti->ecn = iph.tos & INET_ECN_MASK;
+	} else {
+		pkti->is_ip = false;
+		pkti->is_tcp = false;
+		pkti->ecn = 0;
+	}
+	if (pkti->is_tcp)
+		get_tcp_info(skb, pkti);
+}
+
+static __always_inline void hbm_init_vqueue(struct hbm_vqueue *qdp, int rate)
+{
+	bpf_printk("Initializing queue_state, rate:%d\n", rate * 128);
+	qdp->lasttime = bpf_ktime_get_ns();
+	qdp->credit = INIT_CREDIT;
+	qdp->rate = rate * 128;
+}
+
+static __always_inline void hbm_init_edt_vqueue(struct hbm_vqueue *qdp,
+						int rate)
+{
+	unsigned long long curtime;
+
+	curtime = bpf_ktime_get_ns();
+	bpf_printk("Initializing queue_state, rate:%d\n", rate * 128);
+	qdp->lasttime = curtime - BURST_SIZE_NS;	// support initial burst
+	qdp->credit = 0;				// not used
+	qdp->rate = rate * 128;
+}
+
+static __always_inline void hbm_update_stats(struct hbm_queue_stats *qsp,
+					     int len,
+					     unsigned long long curtime,
+					     bool congestion_flag,
+					     bool drop_flag,
+					     bool cwr_flag,
+					     bool ecn_ce_flag,
+					     struct hbm_pkt_info *pkti,
+					     int credit)
+{
+	int rv = ALLOW_PKT;
+
+	if (qsp != NULL) {
+		// Following is needed for work conserving
+		__sync_add_and_fetch(&(qsp->bytes_total), len);
+		if (qsp->stats) {
+			// Optionally update statistics
+			if (qsp->firstPacketTime == 0)
+				qsp->firstPacketTime = curtime;
+			qsp->lastPacketTime = curtime;
+			__sync_add_and_fetch(&(qsp->pkts_total), 1);
+			if (congestion_flag) {
+				__sync_add_and_fetch(&(qsp->pkts_marked), 1);
+				__sync_add_and_fetch(&(qsp->bytes_marked), len);
+			}
+			if (drop_flag) {
+				__sync_add_and_fetch(&(qsp->pkts_dropped), 1);
+				__sync_add_and_fetch(&(qsp->bytes_dropped),
+						     len);
+			}
+			if (ecn_ce_flag)
+				__sync_add_and_fetch(&(qsp->pkts_ecn_ce), 1);
+			if (pkti->cwnd) {
+				__sync_add_and_fetch(&(qsp->sum_cwnd),
+						     pkti->cwnd);
+				__sync_add_and_fetch(&(qsp->sum_cwnd_cnt), 1);
+			}
+			if (pkti->rtt)
+				__sync_add_and_fetch(&(qsp->sum_rtt),
+						     pkti->rtt);
+			__sync_add_and_fetch(&(qsp->sum_credit), credit);
+
+			if (drop_flag)
+				rv = DROP_PKT;
+			if (cwr_flag)
+				rv |= 2;
+			if (rv == DROP_PKT)
+				__sync_add_and_fetch(&(qsp->returnValCount[0]),
+						     1);
+			else if (rv == ALLOW_PKT)
+				__sync_add_and_fetch(&(qsp->returnValCount[1]),
+						     1);
+			else if (rv == 2)
+				__sync_add_and_fetch(&(qsp->returnValCount[2]),
+						     1);
+			else if (rv == 3)
+				__sync_add_and_fetch(&(qsp->returnValCount[3]),
+						     1);
+		}
+	}
+}

linux-7.2.3/samples/bpf/hbm_out_kern.c

@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 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.
+ *
+ * Sample Host Bandwidth Manager (HBM) BPF program.
+ *
+ * A cgroup skb BPF egress program to limit cgroup output bandwidth.
+ * It uses a modified virtual token bucket queue to limit average
+ * egress bandwidth. The implementation uses credits instead of tokens.
+ * Negative credits imply that queueing would have happened (this is
+ * a virtual queue, so no queueing is done by it. However, queueing may
+ * occur at the actual qdisc (which is not used for rate limiting).
+ *
+ * This implementation uses 3 thresholds, one to start marking packets and
+ * the other two to drop packets:
+ *                                  CREDIT
+ *        - <--------------------------|------------------------> +
+ *              |    |          |      0
+ *              |  Large pkt    |
+ *              |  drop thresh  |
+ *   Small pkt drop             Mark threshold
+ *       thresh
+ *
+ * The effect of marking depends on the type of packet:
+ * a) If the packet is ECN enabled and it is a TCP packet, then the packet
+ *    is ECN marked.
+ * b) If the packet is a TCP packet, then we probabilistically call tcp_cwr
+ *    to reduce the congestion window. The current implementation uses a linear
+ *    distribution (0% probability at marking threshold, 100% probability
+ *    at drop threshold).
+ * c) If the packet is not a TCP packet, then it is dropped.
+ *
+ * If the credit is below the drop threshold, the packet is dropped. If it
+ * is a TCP packet, then it also calls tcp_cwr since packets dropped by
+ * by a cgroup skb BPF program do not automatically trigger a call to
+ * tcp_cwr in the current kernel code.
+ *
+ * This BPF program actually uses 2 drop thresholds, one threshold
+ * for larger packets (>= 120 bytes) and another for smaller packets. This
+ * protects smaller packets such as SYNs, ACKs, etc.
+ *
+ * The default bandwidth limit is set at 1Gbps but this can be changed by
+ * a user program through a shared BPF map. In addition, by default this BPF
+ * program does not limit connections using loopback. This behavior can be
+ * overwritten by the user program. There is also an option to calculate
+ * some statistics, such as percent of packets marked or dropped, which
+ * the user program can access.
+ *
+ * A latter patch provides such a program (hbm.c)
+ */
+
+#include "hbm_kern.h"
+
+SEC("cgroup_skb/egress")
+int _hbm_out_cg(struct __sk_buff *skb)
+{
+	struct hbm_pkt_info pkti;
+	int len = skb->len;
+	unsigned int queue_index = 0;
+	unsigned long long curtime;
+	int credit;
+	signed long long delta = 0, new_credit;
+	int max_credit = MAX_CREDIT;
+	bool congestion_flag = false;
+	bool drop_flag = false;
+	bool cwr_flag = false;
+	bool ecn_ce_flag = false;
+	struct hbm_vqueue *qdp;
+	struct hbm_queue_stats *qsp = NULL;
+	int rv = ALLOW_PKT;
+
+	qsp = bpf_map_lookup_elem(&queue_stats, &queue_index);
+	if (qsp != NULL && !qsp->loopback && (skb->ifindex == 1))
+		return ALLOW_PKT;
+
+	hbm_get_pkt_info(skb, &pkti);
+
+	// We may want to account for the length of headers in len
+	// calculation, like ETH header + overhead, specially if it
+	// is a gso packet. But I am not doing it right now.
+
+	qdp = bpf_get_local_storage(&queue_state, 0);
+	if (!qdp)
+		return ALLOW_PKT;
+	else if (qdp->lasttime == 0)
+		hbm_init_vqueue(qdp, 1024);
+
+	curtime = bpf_ktime_get_ns();
+
+	// Begin critical section
+	bpf_spin_lock(&qdp->lock);
+	credit = qdp->credit;
+	delta = curtime - qdp->lasttime;
+	/* delta < 0 implies that another process with a curtime greater
+	 * than ours beat us to the critical section and already added
+	 * the new credit, so we should not add it ourselves
+	 */
+	if (delta > 0) {
+		qdp->lasttime = curtime;
+		new_credit = credit + CREDIT_PER_NS(delta, qdp->rate);
+		if (new_credit > MAX_CREDIT)
+			credit = MAX_CREDIT;
+		else
+			credit = new_credit;
+	}
+	credit -= len;
+	qdp->credit = credit;
+	bpf_spin_unlock(&qdp->lock);
+	// End critical section
+
+	// Check if we should update rate
+	if (qsp != NULL && (qsp->rate * 128) != qdp->rate) {
+		qdp->rate = qsp->rate * 128;
+		bpf_printk("Updating rate: %d (1sec:%llu bits)\n",
+			   (int)qdp->rate,
+			   CREDIT_PER_NS(1000000000, qdp->rate) * 8);
+	}
+
+	// Set flags (drop, congestion, cwr)
+	// Dropping => we are congested, so ignore congestion flag
+	if (credit < -DROP_THRESH ||
+	    (len > LARGE_PKT_THRESH && credit < -LARGE_PKT_DROP_THRESH)) {
+		// Very congested, set drop packet
+		drop_flag = true;
+		if (pkti.ecn)
+			congestion_flag = true;
+		else if (pkti.is_tcp)
+			cwr_flag = true;
+	} else if (credit < 0) {
+		// Congested, set congestion flag
+		if (pkti.ecn || pkti.is_tcp) {
+			if (credit < -MARK_THRESH)
+				congestion_flag = true;
+			else
+				congestion_flag = false;
+		} else {
+			congestion_flag = true;
+		}
+	}
+
+	if (congestion_flag) {
+		if (bpf_skb_ecn_set_ce(skb)) {
+			ecn_ce_flag = true;
+		} else {
+			if (pkti.is_tcp) {
+				unsigned int rand = bpf_get_prandom_u32();
+
+				if (-credit >= MARK_THRESH +
+				    (rand % MARK_REGION_SIZE)) {
+					// Do congestion control
+					cwr_flag = true;
+				}
+			} else if (len > LARGE_PKT_THRESH) {
+				// Problem if too many small packets?
+				drop_flag = true;
+			}
+		}
+	}
+
+	if (qsp != NULL)
+		if (qsp->no_cn)
+			cwr_flag = false;
+
+	hbm_update_stats(qsp, len, curtime, congestion_flag, drop_flag,
+			 cwr_flag, ecn_ce_flag, &pkti, credit);
+
+	if (drop_flag) {
+		__sync_add_and_fetch(&(qdp->credit), len);
+		rv = DROP_PKT;
+	}
+
+	if (cwr_flag)
+		rv |= 2;
+	return rv;
+}
+char _license[] SEC("license") = "GPL";

linux-7.2.3/samples/bpf/ibumad_kern.c

@@ -0,0 +1,138 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+
+/*
+ * ibumad BPF sample kernel side
+ *
+ * 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.
+ *
+ * Copyright(c) 2018 Ira Weiny, Intel Corporation
+ */
+
+#define KBUILD_MODNAME "ibumad_count_pkts_by_class"
+#include <uapi/linux/bpf.h>
+
+#include <bpf/bpf_helpers.h>
+
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, u32); /* class; u32 required */
+	__type(value, u64); /* count of mads read */
+	__uint(max_entries, 256); /* Room for all Classes */
+} read_count SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, u32); /* class; u32 required */
+	__type(value, u64); /* count of mads written */
+	__uint(max_entries, 256); /* Room for all Classes */
+} write_count SEC(".maps");
+
+#undef DEBUG
+#ifndef DEBUG
+#undef bpf_printk
+#define bpf_printk(fmt, ...)
+#endif
+
+/* Taken from the current format defined in
+ * include/trace/events/ib_umad.h
+ * and
+ * /sys/kernel/tracing/events/ib_umad/ib_umad_read/format
+ * /sys/kernel/tracing/events/ib_umad/ib_umad_write/format
+ */
+struct ib_umad_rw_args {
+	u64 pad;
+	u8 port_num;
+	u8 sl;
+	u8 path_bits;
+	u8 grh_present;
+	u32 id;
+	u32 status;
+	u32 timeout_ms;
+	u32 retires;
+	u32 length;
+	u32 qpn;
+	u32 qkey;
+	u8 gid_index;
+	u8 hop_limit;
+	u16 lid;
+	u16 attr_id;
+	u16 pkey_index;
+	u8 base_version;
+	u8 mgmt_class;
+	u8 class_version;
+	u8 method;
+	u32 flow_label;
+	u16 mad_status;
+	u16 class_specific;
+	u32 attr_mod;
+	u64 tid;
+	u8 gid[16];
+	u32 dev_index;
+	u8 traffic_class;
+};
+
+SEC("tracepoint/ib_umad/ib_umad_read_recv")
+int on_ib_umad_read_recv(struct ib_umad_rw_args *ctx)
+{
+	u64 zero = 0, *val;
+	u8 class = ctx->mgmt_class;
+
+	bpf_printk("ib_umad read recv : class 0x%x\n", class);
+
+	val = bpf_map_lookup_elem(&read_count, &class);
+	if (!val) {
+		bpf_map_update_elem(&read_count, &class, &zero, BPF_NOEXIST);
+		val = bpf_map_lookup_elem(&read_count, &class);
+		if (!val)
+			return 0;
+	}
+
+	(*val) += 1;
+
+	return 0;
+}
+SEC("tracepoint/ib_umad/ib_umad_read_send")
+int on_ib_umad_read_send(struct ib_umad_rw_args *ctx)
+{
+	u64 zero = 0, *val;
+	u8 class = ctx->mgmt_class;
+
+	bpf_printk("ib_umad read send : class 0x%x\n", class);
+
+	val = bpf_map_lookup_elem(&read_count, &class);
+	if (!val) {
+		bpf_map_update_elem(&read_count, &class, &zero, BPF_NOEXIST);
+		val = bpf_map_lookup_elem(&read_count, &class);
+		if (!val)
+			return 0;
+	}
+
+	(*val) += 1;
+
+	return 0;
+}
+SEC("tracepoint/ib_umad/ib_umad_write")
+int on_ib_umad_write(struct ib_umad_rw_args *ctx)
+{
+	u64 zero = 0, *val;
+	u8 class = ctx->mgmt_class;
+
+	bpf_printk("ib_umad write : class 0x%x\n", class);
+
+	val = bpf_map_lookup_elem(&write_count, &class);
+	if (!val) {
+		bpf_map_update_elem(&write_count, &class, &zero, BPF_NOEXIST);
+		val = bpf_map_lookup_elem(&write_count, &class);
+		if (!val)
+			return 0;
+	}
+
+	(*val) += 1;
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";

linux-7.2.3/samples/bpf/ibumad_user.c

@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+
+/*
+ * ibumad BPF sample user side
+ *
+ * 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.
+ *
+ * Copyright(c) 2018 Ira Weiny, Intel Corporation
+ */
+
+#include <linux/bpf.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <limits.h>
+
+#include <getopt.h>
+#include <net/if.h>
+
+#include <bpf/bpf.h>
+#include "bpf_util.h"
+#include <bpf/libbpf.h>
+
+static struct bpf_link *tp_links[3];
+static struct bpf_object *obj;
+static int map_fd[2];
+static int tp_cnt;
+
+static void dump_counts(int fd)
+{
+	__u32 key;
+	__u64 value;
+
+	for (key = 0; key < 256; key++) {
+		if (bpf_map_lookup_elem(fd, &key, &value)) {
+			printf("failed to read key %u\n", key);
+			continue;
+		}
+		if (value)
+			printf("0x%02x : %llu\n", key, value);
+	}
+}
+
+static void dump_all_counts(void)
+{
+	printf("Read 'Class : count'\n");
+	dump_counts(map_fd[0]);
+	printf("Write 'Class : count'\n");
+	dump_counts(map_fd[1]);
+}
+
+static void dump_exit(int sig)
+{
+	dump_all_counts();
+	/* Detach tracepoints */
+	while (tp_cnt)
+		bpf_link__destroy(tp_links[--tp_cnt]);
+
+	bpf_object__close(obj);
+	exit(0);
+}
+
+static const struct option long_options[] = {
+	{"help",      no_argument,       NULL, 'h'},
+	{"delay",     required_argument, NULL, 'd'},
+};
+
+static void usage(char *cmd)
+{
+	printf("eBPF test program to count packets from various IP addresses\n"
+		"Usage: %s <options>\n"
+		"       --help,   -h  this menu\n"
+		"       --delay,  -d  <delay>  wait <delay> sec between prints [1 - 1000000]\n"
+		, cmd
+		);
+}
+
+int main(int argc, char **argv)
+{
+	struct bpf_program *prog;
+	unsigned long delay = 5;
+	char filename[256];
+	int longindex = 0;
+	int opt, err = -1;
+
+	while ((opt = getopt_long(argc, argv, "hd:rSw",
+				  long_options, &longindex)) != -1) {
+		switch (opt) {
+		case 'd':
+			delay = strtoul(optarg, NULL, 0);
+			if (delay == ULONG_MAX || delay < 0 ||
+			    delay > 1000000) {
+				fprintf(stderr, "ERROR: invalid delay : %s\n",
+					optarg);
+				usage(argv[0]);
+				return 1;
+			}
+			break;
+		default:
+		case 'h':
+			usage(argv[0]);
+			return 1;
+		}
+	}
+
+	/* Do one final dump when exiting */
+	signal(SIGINT, dump_exit);
+	signal(SIGTERM, dump_exit);
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+	obj = bpf_object__open_file(filename, NULL);
+	if (libbpf_get_error(obj)) {
+		fprintf(stderr, "ERROR: opening BPF object file failed\n");
+		return err;
+	}
+
+	/* load BPF program */
+	if (bpf_object__load(obj)) {
+		fprintf(stderr, "ERROR: loading BPF object file failed\n");
+		goto cleanup;
+	}
+
+	map_fd[0] = bpf_object__find_map_fd_by_name(obj, "read_count");
+	map_fd[1] = bpf_object__find_map_fd_by_name(obj, "write_count");
+	if (map_fd[0] < 0 || map_fd[1] < 0) {
+		fprintf(stderr, "ERROR: finding a map in obj file failed\n");
+		goto cleanup;
+	}
+
+	bpf_object__for_each_program(prog, obj) {
+		tp_links[tp_cnt] = bpf_program__attach(prog);
+		if (libbpf_get_error(tp_links[tp_cnt])) {
+			fprintf(stderr, "ERROR: bpf_program__attach failed\n");
+			tp_links[tp_cnt] = NULL;
+			goto cleanup;
+		}
+		tp_cnt++;
+	}
+
+	while (1) {
+		sleep(delay);
+		dump_all_counts();
+	}
+	err = 0;
+
+cleanup:
+	/* Detach tracepoints */
+	while (tp_cnt)
+		bpf_link__destroy(tp_links[--tp_cnt]);
+
+	bpf_object__close(obj);
+	return err;
+}

linux-7.2.3/samples/bpf/lathist_kern.c

@@ -0,0 +1,99 @@
+/* Copyright (c) 2013-2015 PLUMgrid, http://plumgrid.com
+ * Copyright (c) 2015 BMW Car IT GmbH
+ *
+ * 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/version.h>
+#include <linux/ptrace.h>
+#include <uapi/linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+#define MAX_ENTRIES	20
+#define MAX_CPU		4
+
+/* We need to stick to static allocated memory (an array instead of
+ * hash table) because managing dynamic memory from the
+ * trace_preempt_[on|off] tracepoints hooks is not supported.
+ */
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, u64);
+	__uint(max_entries, MAX_CPU);
+} my_map SEC(".maps");
+
+SEC("kprobe/trace_preempt_off")
+int bpf_prog1(struct pt_regs *ctx)
+{
+	int cpu = bpf_get_smp_processor_id();
+	u64 *ts = bpf_map_lookup_elem(&my_map, &cpu);
+
+	if (ts)
+		*ts = bpf_ktime_get_ns();
+
+	return 0;
+}
+
+static unsigned int log2(unsigned int v)
+{
+	unsigned int r;
+	unsigned int shift;
+
+	r = (v > 0xFFFF) << 4; v >>= r;
+	shift = (v > 0xFF) << 3; v >>= shift; r |= shift;
+	shift = (v > 0xF) << 2; v >>= shift; r |= shift;
+	shift = (v > 0x3) << 1; v >>= shift; r |= shift;
+	r |= (v >> 1);
+
+	return r;
+}
+
+static unsigned int log2l(unsigned long v)
+{
+	unsigned int hi = v >> 32;
+
+	if (hi)
+		return log2(hi) + 32;
+	else
+		return log2(v);
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, long);
+	__uint(max_entries, MAX_CPU * MAX_ENTRIES);
+} my_lat SEC(".maps");
+
+SEC("kprobe/trace_preempt_on")
+int bpf_prog2(struct pt_regs *ctx)
+{
+	u64 *ts, cur_ts, delta;
+	int key, cpu;
+	long *val;
+
+	cpu = bpf_get_smp_processor_id();
+	ts = bpf_map_lookup_elem(&my_map, &cpu);
+	if (!ts)
+		return 0;
+
+	cur_ts = bpf_ktime_get_ns();
+	delta = log2l(cur_ts - *ts);
+
+	if (delta > MAX_ENTRIES - 1)
+		delta = MAX_ENTRIES - 1;
+
+	key = cpu * MAX_ENTRIES + delta;
+	val = bpf_map_lookup_elem(&my_lat, &key);
+	if (val)
+		__sync_fetch_and_add((long *)val, 1);
+
+	return 0;
+
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;

linux-7.2.3/samples/bpf/lathist_user.c

@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2013-2015 PLUMgrid, http://plumgrid.com
+ * Copyright (c) 2015 BMW Car IT GmbH
+ */
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <bpf/libbpf.h>
+#include <bpf/bpf.h>
+
+#define MAX_ENTRIES	20
+#define MAX_CPU		4
+#define MAX_STARS	40
+
+struct cpu_hist {
+	long data[MAX_ENTRIES];
+	long max;
+};
+
+static struct cpu_hist cpu_hist[MAX_CPU];
+
+static void stars(char *str, long val, long max, int width)
+{
+	int i;
+
+	for (i = 0; i < (width * val / max) - 1 && i < width - 1; i++)
+		str[i] = '*';
+	if (val > max)
+		str[i - 1] = '+';
+	str[i] = '\0';
+}
+
+static void print_hist(void)
+{
+	char starstr[MAX_STARS];
+	struct cpu_hist *hist;
+	int i, j;
+
+	/* clear screen */
+	printf("\033[2J");
+
+	for (j = 0; j < MAX_CPU; j++) {
+		hist = &cpu_hist[j];
+
+		/* ignore CPUs without data (maybe offline?) */
+		if (hist->max == 0)
+			continue;
+
+		printf("CPU %d\n", j);
+		printf("      latency        : count     distribution\n");
+		for (i = 1; i <= MAX_ENTRIES; i++) {
+			stars(starstr, hist->data[i - 1], hist->max, MAX_STARS);
+			printf("%8ld -> %-8ld : %-8ld |%-*s|\n",
+				(1l << i) >> 1, (1l << i) - 1,
+				hist->data[i - 1], MAX_STARS, starstr);
+		}
+	}
+}
+
+static void get_data(int fd)
+{
+	long key, value;
+	int c, i;
+
+	for (i = 0; i < MAX_CPU; i++)
+		cpu_hist[i].max = 0;
+
+	for (c = 0; c < MAX_CPU; c++) {
+		for (i = 0; i < MAX_ENTRIES; i++) {
+			key = c * MAX_ENTRIES + i;
+			bpf_map_lookup_elem(fd, &key, &value);
+
+			cpu_hist[c].data[i] = value;
+			if (value > cpu_hist[c].max)
+				cpu_hist[c].max = value;
+		}
+	}
+}
+
+int main(int argc, char **argv)
+{
+	struct bpf_link *links[2];
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	char filename[256];
+	int map_fd, i = 0;
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+	obj = bpf_object__open_file(filename, NULL);
+	if (libbpf_get_error(obj)) {
+		fprintf(stderr, "ERROR: opening BPF object file failed\n");
+		return 0;
+	}
+
+	/* load BPF program */
+	if (bpf_object__load(obj)) {
+		fprintf(stderr, "ERROR: loading BPF object file failed\n");
+		goto cleanup;
+	}
+
+	map_fd = bpf_object__find_map_fd_by_name(obj, "my_lat");
+	if (map_fd < 0) {
+		fprintf(stderr, "ERROR: finding a map in obj file failed\n");
+		goto cleanup;
+	}
+
+	bpf_object__for_each_program(prog, obj) {
+		links[i] = bpf_program__attach(prog);
+		if (libbpf_get_error(links[i])) {
+			fprintf(stderr, "ERROR: bpf_program__attach failed\n");
+			links[i] = NULL;
+			goto cleanup;
+		}
+		i++;
+	}
+
+	while (1) {
+		get_data(map_fd);
+		print_hist();
+		sleep(5);
+	}
+
+cleanup:
+	for (i--; i >= 0; i--)
+		bpf_link__destroy(links[i]);
+
+	bpf_object__close(obj);
+	return 0;
+}

linux-7.2.3/samples/bpf/lwt_len_hist.bpf.c

@@ -0,0 +1,62 @@
+/* Copyright (c) 2016 Thomas Graf <tgraf@tgraf.ch>
+ *
+ * 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 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 "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_HASH);
+	__type(key, u64);
+	__type(value, u64);
+	__uint(pinning, LIBBPF_PIN_BY_NAME);
+	__uint(max_entries, 1024);
+} lwt_len_hist_map SEC(".maps");
+
+static unsigned int log2(unsigned int v)
+{
+	unsigned int r;
+	unsigned int shift;
+
+	r = (v > 0xFFFF) << 4; v >>= r;
+	shift = (v > 0xFF) << 3; v >>= shift; r |= shift;
+	shift = (v > 0xF) << 2; v >>= shift; r |= shift;
+	shift = (v > 0x3) << 1; v >>= shift; r |= shift;
+	r |= (v >> 1);
+	return r;
+}
+
+static unsigned int log2l(unsigned long v)
+{
+	unsigned int hi = v >> 32;
+	if (hi)
+		return log2(hi) + 32;
+	else
+		return log2(v);
+}
+
+SEC("len_hist")
+int do_len_hist(struct __sk_buff *skb)
+{
+	__u64 *value, key, init_val = 1;
+
+	key = log2l(skb->len);
+
+	value = bpf_map_lookup_elem(&lwt_len_hist_map, &key);
+	if (value)
+		__sync_fetch_and_add(value, 1);
+	else
+		bpf_map_update_elem(&lwt_len_hist_map, &key, &init_val, BPF_ANY);
+
+	return BPF_OK;
+}
+
+char _license[] SEC("license") = "GPL";

linux-7.2.3/samples/bpf/lwt_len_hist.sh

@@ -0,0 +1,40 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+NS1=lwt_ns1
+VETH0=tst_lwt1a
+VETH1=tst_lwt1b
+BPF_PROG=lwt_len_hist.bpf.o
+TRACE_ROOT=/sys/kernel/tracing
+
+function cleanup {
+	# To reset saved histogram, remove pinned map
+	rm /sys/fs/bpf/tc/globals/lwt_len_hist_map
+	ip route del 192.168.253.2/32 dev $VETH0 2> /dev/null
+	ip link del $VETH0 2> /dev/null
+	ip link del $VETH1 2> /dev/null
+	ip netns exec $NS1 killall netserver
+	ip netns delete $NS1 2> /dev/null
+}
+
+cleanup
+
+ip netns add $NS1
+ip link add $VETH0 type veth peer name $VETH1
+ip link set dev $VETH0 up
+ip addr add 192.168.253.1/24 dev $VETH0
+ip link set $VETH1 netns $NS1
+ip netns exec $NS1 ip link set dev $VETH1 up
+ip netns exec $NS1 ip addr add 192.168.253.2/24 dev $VETH1
+ip netns exec $NS1 netserver
+
+echo 1 > ${TRACE_ROOT}/tracing_on
+cp /dev/null ${TRACE_ROOT}/trace
+ip route add 192.168.253.2/32 encap bpf out obj $BPF_PROG section len_hist dev $VETH0
+netperf -H 192.168.253.2 -t TCP_STREAM
+cat ${TRACE_ROOT}/trace | grep -v '^#'
+./lwt_len_hist
+cleanup
+echo 0 > ${TRACE_ROOT}/tracing_on
+
+exit 0

linux-7.2.3/samples/bpf/lwt_len_hist_user.c

@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/unistd.h>
+#include <linux/bpf.h>
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <string.h>
+#include <errno.h>
+#include <arpa/inet.h>
+
+#include <bpf/bpf.h>
+#include "bpf_util.h"
+
+#define MAX_INDEX 64
+#define MAX_STARS 38
+
+static void stars(char *str, long val, long max, int width)
+{
+	int i;
+
+	for (i = 0; i < (width * val / max) - 1 && i < width - 1; i++)
+		str[i] = '*';
+	if (val > max)
+		str[i - 1] = '+';
+	str[i] = '\0';
+}
+
+int main(int argc, char **argv)
+{
+	unsigned int nr_cpus = bpf_num_possible_cpus();
+	const char *map_filename = "/sys/fs/bpf/tc/globals/lwt_len_hist_map";
+	uint64_t values[nr_cpus], sum, max_value = 0, data[MAX_INDEX] = {};
+	uint64_t key = 0, next_key, max_key = 0;
+	char starstr[MAX_STARS];
+	int i, map_fd;
+
+	map_fd = bpf_obj_get(map_filename);
+	if (map_fd < 0) {
+		fprintf(stderr, "bpf_obj_get(%s): %s(%d)\n",
+			map_filename, strerror(errno), errno);
+		return -1;
+	}
+
+	while (bpf_map_get_next_key(map_fd, &key, &next_key) == 0) {
+		if (next_key >= MAX_INDEX) {
+			fprintf(stderr, "Key %lu out of bounds\n", next_key);
+			continue;
+		}
+
+		bpf_map_lookup_elem(map_fd, &next_key, values);
+
+		sum = 0;
+		for (i = 0; i < nr_cpus; i++)
+			sum += values[i];
+
+		data[next_key] = sum;
+		if (sum && next_key > max_key)
+			max_key = next_key;
+
+		if (sum > max_value)
+			max_value = sum;
+
+		key = next_key;
+	}
+
+	for (i = 1; i <= max_key + 1; i++) {
+		stars(starstr, data[i - 1], max_value, MAX_STARS);
+		printf("%8ld -> %-8ld : %-8ld |%-*s|\n",
+		       (1l << i) >> 1, (1l << i) - 1, data[i - 1],
+		       MAX_STARS, starstr);
+	}
+
+	close(map_fd);
+
+	return 0;
+}

linux-7.2.3/samples/bpf/map_perf_test.bpf.c

@@ -0,0 +1,297 @@
+/* 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 "vmlinux.h"
+#include <errno.h>
+#include <linux/version.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+#define MAX_ENTRIES 1000
+#define MAX_NR_CPUS 1024
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, MAX_ENTRIES);
+} hash_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_LRU_HASH);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, 10000);
+} lru_hash_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_LRU_HASH);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, 10000);
+	__uint(map_flags, BPF_F_NO_COMMON_LRU);
+} nocommon_lru_hash_map SEC(".maps");
+
+struct inner_lru {
+	__uint(type, BPF_MAP_TYPE_LRU_HASH);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, MAX_ENTRIES);
+	__uint(map_flags, BPF_F_NUMA_NODE);
+	__uint(numa_node, 0);
+} inner_lru_hash_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__uint(max_entries, MAX_NR_CPUS);
+	__uint(key_size, sizeof(u32));
+	__array(values, struct inner_lru); /* use inner_lru as inner map */
+} array_of_lru_hashs SEC(".maps") = {
+	/* statically initialize the first element */
+	.values = { &inner_lru_hash_map },
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_HASH);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(long));
+	__uint(max_entries, MAX_ENTRIES);
+} percpu_hash_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, MAX_ENTRIES);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+} hash_map_alloc SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_HASH);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(long));
+	__uint(max_entries, MAX_ENTRIES);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+} percpu_hash_map_alloc SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_LPM_TRIE);
+	__uint(key_size, 8);
+	__uint(value_size, sizeof(long));
+	__uint(max_entries, 10000);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+} lpm_trie_map_alloc SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, MAX_ENTRIES);
+} array_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_LRU_HASH);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, MAX_ENTRIES);
+} lru_hash_lookup_map SEC(".maps");
+
+SEC("ksyscall/getuid")
+int BPF_KSYSCALL(stress_hmap)
+{
+	u32 key = bpf_get_current_pid_tgid();
+	long init_val = 1;
+	long *value;
+	int i;
+
+	for (i = 0; i < 10; i++) {
+		bpf_map_update_elem(&hash_map, &key, &init_val, BPF_ANY);
+		value = bpf_map_lookup_elem(&hash_map, &key);
+		if (value)
+			bpf_map_delete_elem(&hash_map, &key);
+	}
+
+	return 0;
+}
+
+SEC("ksyscall/geteuid")
+int BPF_KSYSCALL(stress_percpu_hmap)
+{
+	u32 key = bpf_get_current_pid_tgid();
+	long init_val = 1;
+	long *value;
+	int i;
+
+	for (i = 0; i < 10; i++) {
+		bpf_map_update_elem(&percpu_hash_map, &key, &init_val, BPF_ANY);
+		value = bpf_map_lookup_elem(&percpu_hash_map, &key);
+		if (value)
+			bpf_map_delete_elem(&percpu_hash_map, &key);
+	}
+	return 0;
+}
+
+SEC("ksyscall/getgid")
+int BPF_KSYSCALL(stress_hmap_alloc)
+{
+	u32 key = bpf_get_current_pid_tgid();
+	long init_val = 1;
+	long *value;
+	int i;
+
+	for (i = 0; i < 10; i++) {
+		bpf_map_update_elem(&hash_map_alloc, &key, &init_val, BPF_ANY);
+		value = bpf_map_lookup_elem(&hash_map_alloc, &key);
+		if (value)
+			bpf_map_delete_elem(&hash_map_alloc, &key);
+	}
+	return 0;
+}
+
+SEC("ksyscall/getegid")
+int BPF_KSYSCALL(stress_percpu_hmap_alloc)
+{
+	u32 key = bpf_get_current_pid_tgid();
+	long init_val = 1;
+	long *value;
+	int i;
+
+	for (i = 0; i < 10; i++) {
+		bpf_map_update_elem(&percpu_hash_map_alloc, &key, &init_val, BPF_ANY);
+		value = bpf_map_lookup_elem(&percpu_hash_map_alloc, &key);
+		if (value)
+			bpf_map_delete_elem(&percpu_hash_map_alloc, &key);
+	}
+	return 0;
+}
+SEC("ksyscall/connect")
+int BPF_KSYSCALL(stress_lru_hmap_alloc, int fd, struct sockaddr_in *uservaddr,
+		 int addrlen)
+{
+	char fmt[] = "Failed at stress_lru_hmap_alloc. ret:%dn";
+	union {
+		u16 dst6[8];
+		struct {
+			u16 magic0;
+			u16 magic1;
+			u16 tcase;
+			u16 unused16;
+			u32 unused32;
+			u32 key;
+		};
+	} test_params;
+	struct sockaddr_in6 *in6 = (struct sockaddr_in6 *)uservaddr;
+	u16 test_case;
+	long val = 1;
+	u32 key = 0;
+	int ret;
+
+	if (addrlen != sizeof(*in6))
+		return 0;
+
+	ret = bpf_probe_read_user(test_params.dst6, sizeof(test_params.dst6),
+				  &in6->sin6_addr);
+	if (ret)
+		goto done;
+
+	if (test_params.magic0 != 0xdead ||
+	    test_params.magic1 != 0xbeef)
+		return 0;
+
+	test_case = test_params.tcase;
+	if (test_case != 3)
+		key = bpf_get_prandom_u32();
+
+	if (test_case == 0) {
+		ret = bpf_map_update_elem(&lru_hash_map, &key, &val, BPF_ANY);
+	} else if (test_case == 1) {
+		ret = bpf_map_update_elem(&nocommon_lru_hash_map, &key, &val,
+					  BPF_ANY);
+	} else if (test_case == 2) {
+		void *nolocal_lru_map;
+		int cpu = bpf_get_smp_processor_id();
+
+		nolocal_lru_map = bpf_map_lookup_elem(&array_of_lru_hashs,
+						      &cpu);
+		if (!nolocal_lru_map) {
+			ret = -ENOENT;
+			goto done;
+		}
+
+		ret = bpf_map_update_elem(nolocal_lru_map, &key, &val,
+					  BPF_ANY);
+	} else if (test_case == 3) {
+		u32 i;
+
+		key = test_params.key;
+
+#pragma clang loop unroll(full)
+		for (i = 0; i < 32; i++) {
+			bpf_map_lookup_elem(&lru_hash_lookup_map, &key);
+			key++;
+		}
+	} else {
+		ret = -EINVAL;
+	}
+
+done:
+	if (ret)
+		bpf_trace_printk(fmt, sizeof(fmt), ret);
+
+	return 0;
+}
+
+SEC("ksyscall/gettid")
+int BPF_KSYSCALL(stress_lpm_trie_map_alloc)
+{
+	union {
+		u32 b32[2];
+		u8 b8[8];
+	} key;
+	unsigned int i;
+
+	key.b32[0] = 32;
+	key.b8[4] = 192;
+	key.b8[5] = 168;
+	key.b8[6] = 0;
+	key.b8[7] = 1;
+
+#pragma clang loop unroll(full)
+	for (i = 0; i < 32; ++i)
+		bpf_map_lookup_elem(&lpm_trie_map_alloc, &key);
+
+	return 0;
+}
+
+SEC("ksyscall/getpgid")
+int BPF_KSYSCALL(stress_hash_map_lookup)
+{
+	u32 key = 1, i;
+	long *value;
+
+#pragma clang loop unroll(full)
+	for (i = 0; i < 64; ++i)
+		value = bpf_map_lookup_elem(&hash_map, &key);
+
+	return 0;
+}
+
+SEC("ksyscall/getppid")
+int BPF_KSYSCALL(stress_array_map_lookup)
+{
+	u32 key = 1, i;
+	long *value;
+
+#pragma clang loop unroll(full)
+	for (i = 0; i < 64; ++i)
+		value = bpf_map_lookup_elem(&array_map, &key);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;

linux-7.2.3/samples/bpf/map_perf_test_user.c

@@ -0,0 +1,503 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2016 Facebook
+ */
+#define _GNU_SOURCE
+#include <sched.h>
+#include <stdio.h>
+#include <sys/types.h>
+#include <asm/unistd.h>
+#include <unistd.h>
+#include <assert.h>
+#include <sys/wait.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <string.h>
+#include <time.h>
+#include <arpa/inet.h>
+#include <errno.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#define TEST_BIT(t) (1U << (t))
+#define MAX_NR_CPUS 1024
+
+static __u64 time_get_ns(void)
+{
+	struct timespec ts;
+
+	clock_gettime(CLOCK_MONOTONIC, &ts);
+	return ts.tv_sec * 1000000000ull + ts.tv_nsec;
+}
+
+enum test_type {
+	HASH_PREALLOC,
+	PERCPU_HASH_PREALLOC,
+	HASH_KMALLOC,
+	PERCPU_HASH_KMALLOC,
+	LRU_HASH_PREALLOC,
+	NOCOMMON_LRU_HASH_PREALLOC,
+	LPM_KMALLOC,
+	HASH_LOOKUP,
+	ARRAY_LOOKUP,
+	INNER_LRU_HASH_PREALLOC,
+	LRU_HASH_LOOKUP,
+	NR_TESTS,
+};
+
+const char *test_map_names[NR_TESTS] = {
+	[HASH_PREALLOC] = "hash_map",
+	[PERCPU_HASH_PREALLOC] = "percpu_hash_map",
+	[HASH_KMALLOC] = "hash_map_alloc",
+	[PERCPU_HASH_KMALLOC] = "percpu_hash_map_alloc",
+	[LRU_HASH_PREALLOC] = "lru_hash_map",
+	[NOCOMMON_LRU_HASH_PREALLOC] = "nocommon_lru_hash_map",
+	[LPM_KMALLOC] = "lpm_trie_map_alloc",
+	[HASH_LOOKUP] = "hash_map",
+	[ARRAY_LOOKUP] = "array_map",
+	[INNER_LRU_HASH_PREALLOC] = "inner_lru_hash_map",
+	[LRU_HASH_LOOKUP] = "lru_hash_lookup_map",
+};
+
+enum map_idx {
+	array_of_lru_hashs_idx,
+	hash_map_alloc_idx,
+	lru_hash_lookup_idx,
+	NR_IDXES,
+};
+
+static int map_fd[NR_IDXES];
+
+static int test_flags = ~0;
+static uint32_t num_map_entries;
+static uint32_t inner_lru_hash_size;
+static int lru_hash_lookup_test_entries = 32;
+static uint32_t max_cnt = 10000;
+
+static int check_test_flags(enum test_type t)
+{
+	return test_flags & TEST_BIT(t);
+}
+
+static void test_hash_prealloc(int cpu)
+{
+	__u64 start_time;
+	int i;
+
+	start_time = time_get_ns();
+	for (i = 0; i < max_cnt; i++)
+		syscall(__NR_getuid);
+	printf("%d:hash_map_perf pre-alloc %lld events per sec\n",
+	       cpu, max_cnt * 1000000000ll / (time_get_ns() - start_time));
+}
+
+static int pre_test_lru_hash_lookup(int tasks)
+{
+	int fd = map_fd[lru_hash_lookup_idx];
+	uint32_t key;
+	long val = 1;
+	int ret;
+
+	if (num_map_entries > lru_hash_lookup_test_entries)
+		lru_hash_lookup_test_entries = num_map_entries;
+
+	/* Populate the lru_hash_map for LRU_HASH_LOOKUP perf test.
+	 *
+	 * It is fine that the user requests for a map with
+	 * num_map_entries < 32 and some of the later lru hash lookup
+	 * may return not found.  For LRU map, we are not interested
+	 * in such small map performance.
+	 */
+	for (key = 0; key < lru_hash_lookup_test_entries; key++) {
+		ret = bpf_map_update_elem(fd, &key, &val, BPF_NOEXIST);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void do_test_lru(enum test_type test, int cpu)
+{
+	static int inner_lru_map_fds[MAX_NR_CPUS];
+
+	struct sockaddr_in6 in6 = { .sin6_family = AF_INET6 };
+	const char *test_name;
+	__u64 start_time;
+	int i, ret;
+
+	if (test == INNER_LRU_HASH_PREALLOC && cpu) {
+		/* If CPU is not 0, create inner_lru hash map and insert the fd
+		 * value into the array_of_lru_hash map. In case of CPU 0,
+		 * 'inner_lru_hash_map' was statically inserted on the map init
+		 */
+		int outer_fd = map_fd[array_of_lru_hashs_idx];
+		unsigned int mycpu, mynode;
+		LIBBPF_OPTS(bpf_map_create_opts, opts,
+			.map_flags = BPF_F_NUMA_NODE,
+		);
+
+		assert(cpu < MAX_NR_CPUS);
+
+		ret = syscall(__NR_getcpu, &mycpu, &mynode, NULL);
+		assert(!ret);
+
+		opts.numa_node = mynode;
+		inner_lru_map_fds[cpu] =
+			bpf_map_create(BPF_MAP_TYPE_LRU_HASH,
+				       test_map_names[INNER_LRU_HASH_PREALLOC],
+				       sizeof(uint32_t),
+				       sizeof(long),
+				       inner_lru_hash_size, &opts);
+		if (inner_lru_map_fds[cpu] == -1) {
+			printf("cannot create BPF_MAP_TYPE_LRU_HASH %s(%d)\n",
+			       strerror(errno), errno);
+			exit(1);
+		}
+
+		ret = bpf_map_update_elem(outer_fd, &cpu,
+					  &inner_lru_map_fds[cpu],
+					  BPF_ANY);
+		if (ret) {
+			printf("cannot update ARRAY_OF_LRU_HASHS with key:%u. %s(%d)\n",
+			       cpu, strerror(errno), errno);
+			exit(1);
+		}
+	}
+
+	in6.sin6_addr.s6_addr16[0] = 0xdead;
+	in6.sin6_addr.s6_addr16[1] = 0xbeef;
+
+	if (test == LRU_HASH_PREALLOC) {
+		test_name = "lru_hash_map_perf";
+		in6.sin6_addr.s6_addr16[2] = 0;
+	} else if (test == NOCOMMON_LRU_HASH_PREALLOC) {
+		test_name = "nocommon_lru_hash_map_perf";
+		in6.sin6_addr.s6_addr16[2] = 1;
+	} else if (test == INNER_LRU_HASH_PREALLOC) {
+		test_name = "inner_lru_hash_map_perf";
+		in6.sin6_addr.s6_addr16[2] = 2;
+	} else if (test == LRU_HASH_LOOKUP) {
+		test_name = "lru_hash_lookup_perf";
+		in6.sin6_addr.s6_addr16[2] = 3;
+		in6.sin6_addr.s6_addr32[3] = 0;
+	} else {
+		assert(0);
+	}
+
+	start_time = time_get_ns();
+	for (i = 0; i < max_cnt; i++) {
+		ret = connect(-1, (const struct sockaddr *)&in6, sizeof(in6));
+		assert(ret == -1 && errno == EBADF);
+		if (in6.sin6_addr.s6_addr32[3] <
+		    lru_hash_lookup_test_entries - 32)
+			in6.sin6_addr.s6_addr32[3] += 32;
+		else
+			in6.sin6_addr.s6_addr32[3] = 0;
+	}
+	printf("%d:%s pre-alloc %lld events per sec\n",
+	       cpu, test_name,
+	       max_cnt * 1000000000ll / (time_get_ns() - start_time));
+}
+
+static void test_lru_hash_prealloc(int cpu)
+{
+	do_test_lru(LRU_HASH_PREALLOC, cpu);
+}
+
+static void test_nocommon_lru_hash_prealloc(int cpu)
+{
+	do_test_lru(NOCOMMON_LRU_HASH_PREALLOC, cpu);
+}
+
+static void test_inner_lru_hash_prealloc(int cpu)
+{
+	do_test_lru(INNER_LRU_HASH_PREALLOC, cpu);
+}
+
+static void test_lru_hash_lookup(int cpu)
+{
+	do_test_lru(LRU_HASH_LOOKUP, cpu);
+}
+
+static void test_percpu_hash_prealloc(int cpu)
+{
+	__u64 start_time;
+	int i;
+
+	start_time = time_get_ns();
+	for (i = 0; i < max_cnt; i++)
+		syscall(__NR_geteuid);
+	printf("%d:percpu_hash_map_perf pre-alloc %lld events per sec\n",
+	       cpu, max_cnt * 1000000000ll / (time_get_ns() - start_time));
+}
+
+static void test_hash_kmalloc(int cpu)
+{
+	__u64 start_time;
+	int i;
+
+	start_time = time_get_ns();
+	for (i = 0; i < max_cnt; i++)
+		syscall(__NR_getgid);
+	printf("%d:hash_map_perf kmalloc %lld events per sec\n",
+	       cpu, max_cnt * 1000000000ll / (time_get_ns() - start_time));
+}
+
+static void test_percpu_hash_kmalloc(int cpu)
+{
+	__u64 start_time;
+	int i;
+
+	start_time = time_get_ns();
+	for (i = 0; i < max_cnt; i++)
+		syscall(__NR_getegid);
+	printf("%d:percpu_hash_map_perf kmalloc %lld events per sec\n",
+	       cpu, max_cnt * 1000000000ll / (time_get_ns() - start_time));
+}
+
+static void test_lpm_kmalloc(int cpu)
+{
+	__u64 start_time;
+	int i;
+
+	start_time = time_get_ns();
+	for (i = 0; i < max_cnt; i++)
+		syscall(__NR_gettid);
+	printf("%d:lpm_perf kmalloc %lld events per sec\n",
+	       cpu, max_cnt * 1000000000ll / (time_get_ns() - start_time));
+}
+
+static void test_hash_lookup(int cpu)
+{
+	__u64 start_time;
+	int i;
+
+	start_time = time_get_ns();
+	for (i = 0; i < max_cnt; i++)
+		syscall(__NR_getpgid, 0);
+	printf("%d:hash_lookup %lld lookups per sec\n",
+	       cpu, max_cnt * 1000000000ll * 64 / (time_get_ns() - start_time));
+}
+
+static void test_array_lookup(int cpu)
+{
+	__u64 start_time;
+	int i;
+
+	start_time = time_get_ns();
+	for (i = 0; i < max_cnt; i++)
+		syscall(__NR_getppid, 0);
+	printf("%d:array_lookup %lld lookups per sec\n",
+	       cpu, max_cnt * 1000000000ll * 64 / (time_get_ns() - start_time));
+}
+
+typedef int (*pre_test_func)(int tasks);
+const pre_test_func pre_test_funcs[] = {
+	[LRU_HASH_LOOKUP] = pre_test_lru_hash_lookup,
+};
+
+typedef void (*test_func)(int cpu);
+const test_func test_funcs[] = {
+	[HASH_PREALLOC] = test_hash_prealloc,
+	[PERCPU_HASH_PREALLOC] = test_percpu_hash_prealloc,
+	[HASH_KMALLOC] = test_hash_kmalloc,
+	[PERCPU_HASH_KMALLOC] = test_percpu_hash_kmalloc,
+	[LRU_HASH_PREALLOC] = test_lru_hash_prealloc,
+	[NOCOMMON_LRU_HASH_PREALLOC] = test_nocommon_lru_hash_prealloc,
+	[LPM_KMALLOC] = test_lpm_kmalloc,
+	[HASH_LOOKUP] = test_hash_lookup,
+	[ARRAY_LOOKUP] = test_array_lookup,
+	[INNER_LRU_HASH_PREALLOC] = test_inner_lru_hash_prealloc,
+	[LRU_HASH_LOOKUP] = test_lru_hash_lookup,
+};
+
+static int pre_test(int tasks)
+{
+	int i;
+
+	for (i = 0; i < NR_TESTS; i++) {
+		if (pre_test_funcs[i] && check_test_flags(i)) {
+			int ret = pre_test_funcs[i](tasks);
+
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+static void loop(int cpu)
+{
+	cpu_set_t cpuset;
+	int i;
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(cpu, &cpuset);
+	sched_setaffinity(0, sizeof(cpuset), &cpuset);
+
+	for (i = 0; i < NR_TESTS; i++) {
+		if (check_test_flags(i))
+			test_funcs[i](cpu);
+	}
+}
+
+static void run_perf_test(int tasks)
+{
+	pid_t pid[tasks];
+	int i;
+
+	assert(!pre_test(tasks));
+
+	for (i = 0; i < tasks; i++) {
+		pid[i] = fork();
+		if (pid[i] == 0) {
+			loop(i);
+			exit(0);
+		} else if (pid[i] == -1) {
+			printf("couldn't spawn #%d process\n", i);
+			exit(1);
+		}
+	}
+	for (i = 0; i < tasks; i++) {
+		int status;
+
+		assert(waitpid(pid[i], &status, 0) == pid[i]);
+		assert(status == 0);
+	}
+}
+
+static void fill_lpm_trie(void)
+{
+	struct bpf_lpm_trie_key_u8 *key;
+	unsigned long value = 0;
+	unsigned int i;
+	int r;
+
+	key = alloca(sizeof(*key) + 4);
+	key->prefixlen = 32;
+
+	for (i = 0; i < 512; ++i) {
+		key->prefixlen = rand() % 33;
+		key->data[0] = rand() & 0xff;
+		key->data[1] = rand() & 0xff;
+		key->data[2] = rand() & 0xff;
+		key->data[3] = rand() & 0xff;
+		r = bpf_map_update_elem(map_fd[hash_map_alloc_idx],
+					key, &value, 0);
+		assert(!r);
+	}
+
+	key->prefixlen = 32;
+	key->data[0] = 192;
+	key->data[1] = 168;
+	key->data[2] = 0;
+	key->data[3] = 1;
+	value = 128;
+
+	r = bpf_map_update_elem(map_fd[hash_map_alloc_idx], key, &value, 0);
+	assert(!r);
+}
+
+static void fixup_map(struct bpf_object *obj)
+{
+	struct bpf_map *map;
+	int i;
+
+	bpf_object__for_each_map(map, obj) {
+		const char *name = bpf_map__name(map);
+
+		/* Only change the max_entries for the enabled test(s) */
+		for (i = 0; i < NR_TESTS; i++) {
+			if (!strcmp(test_map_names[i], name) &&
+			    (check_test_flags(i))) {
+				bpf_map__set_max_entries(map, num_map_entries);
+				continue;
+			}
+		}
+	}
+
+	inner_lru_hash_size = num_map_entries;
+}
+
+int main(int argc, char **argv)
+{
+	int nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
+	struct bpf_link *links[8];
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	struct bpf_map *map;
+	char filename[256];
+	int i = 0;
+
+	if (argc > 1)
+		test_flags = atoi(argv[1]) ? : test_flags;
+
+	if (argc > 2)
+		nr_cpus = atoi(argv[2]) ? : nr_cpus;
+
+	if (argc > 3)
+		num_map_entries = atoi(argv[3]);
+
+	if (argc > 4)
+		max_cnt = atoi(argv[4]);
+
+	snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
+	obj = bpf_object__open_file(filename, NULL);
+	if (libbpf_get_error(obj)) {
+		fprintf(stderr, "ERROR: opening BPF object file failed\n");
+		return 0;
+	}
+
+	map = bpf_object__find_map_by_name(obj, "inner_lru_hash_map");
+	if (libbpf_get_error(map)) {
+		fprintf(stderr, "ERROR: finding a map in obj file failed\n");
+		goto cleanup;
+	}
+
+	inner_lru_hash_size = bpf_map__max_entries(map);
+	if (!inner_lru_hash_size) {
+		fprintf(stderr, "ERROR: failed to get map attribute\n");
+		goto cleanup;
+	}
+
+	/* resize BPF map prior to loading */
+	if (num_map_entries > 0)
+		fixup_map(obj);
+
+	/* load BPF program */
+	if (bpf_object__load(obj)) {
+		fprintf(stderr, "ERROR: loading BPF object file failed\n");
+		goto cleanup;
+	}
+
+	map_fd[0] = bpf_object__find_map_fd_by_name(obj, "array_of_lru_hashs");
+	map_fd[1] = bpf_object__find_map_fd_by_name(obj, "hash_map_alloc");
+	map_fd[2] = bpf_object__find_map_fd_by_name(obj, "lru_hash_lookup_map");
+	if (map_fd[0] < 0 || map_fd[1] < 0 || map_fd[2] < 0) {
+		fprintf(stderr, "ERROR: finding a map in obj file failed\n");
+		goto cleanup;
+	}
+
+	bpf_object__for_each_program(prog, obj) {
+		links[i] = bpf_program__attach(prog);
+		if (libbpf_get_error(links[i])) {
+			fprintf(stderr, "ERROR: bpf_program__attach failed\n");
+			links[i] = NULL;
+			goto cleanup;
+		}
+		i++;
+	}
+
+	fill_lpm_trie();
+
+	run_perf_test(nr_cpus);
+
+cleanup:
+	for (i--; i >= 0; i--)
+		bpf_link__destroy(links[i]);
+
+	bpf_object__close(obj);
+	return 0;
+}

linux-7.2.3/samples/bpf/net_shared.h

@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef _NET_SHARED_H
+#define _NET_SHARED_H
+
+#define AF_INET		2
+#define AF_INET6	10
+
+#define ETH_ALEN 6
+#define ETH_P_802_3_MIN 0x0600
+#define ETH_P_8021Q 0x8100
+#define ETH_P_8021AD 0x88A8
+#define ETH_P_IP 0x0800
+#define ETH_P_IPV6 0x86DD
+#define ETH_P_ARP 0x0806
+#define IPPROTO_ICMPV6 58
+
+#define TC_ACT_OK		0
+#define TC_ACT_SHOT		2
+
+#define IFNAMSIZ 16
+
+#if defined(__BYTE_ORDER__) && defined(__ORDER_LITTLE_ENDIAN__) && \
+	__BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+#define bpf_ntohs(x)		__builtin_bswap16(x)
+#define bpf_htons(x)		__builtin_bswap16(x)
+#elif defined(__BYTE_ORDER__) && defined(__ORDER_BIG_ENDIAN__) && \
+	__BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+#define bpf_ntohs(x)		(x)
+#define bpf_htons(x)		(x)
+#else
+# error "Endianness detection needs to be set up for your compiler?!"
+#endif
+
+#endif

linux-7.2.3/samples/bpf/offwaketime.bpf.c

@@ -0,0 +1,141 @@
+/* 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 "vmlinux.h"
+#include <linux/version.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+#ifndef PERF_MAX_STACK_DEPTH
+#define PERF_MAX_STACK_DEPTH         127
+#endif
+
+#define MINBLOCK_US	1
+#define MAX_ENTRIES	10000
+
+struct key_t {
+	char waker[TASK_COMM_LEN];
+	char target[TASK_COMM_LEN];
+	u32 wret;
+	u32 tret;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, struct key_t);
+	__type(value, u64);
+	__uint(max_entries, MAX_ENTRIES);
+} counts SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, u32);
+	__type(value, u64);
+	__uint(max_entries, MAX_ENTRIES);
+} start SEC(".maps");
+
+struct wokeby_t {
+	char name[TASK_COMM_LEN];
+	u32 ret;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, u32);
+	__type(value, struct wokeby_t);
+	__uint(max_entries, MAX_ENTRIES);
+} wokeby SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_STACK_TRACE);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, PERF_MAX_STACK_DEPTH * sizeof(u64));
+	__uint(max_entries, MAX_ENTRIES);
+} stackmap SEC(".maps");
+
+#define STACKID_FLAGS (0 | BPF_F_FAST_STACK_CMP)
+
+SEC("kprobe/try_to_wake_up")
+int waker(struct pt_regs *ctx)
+{
+	struct task_struct *p = (void *)PT_REGS_PARM1_CORE(ctx);
+	u32 pid = BPF_CORE_READ(p, pid);
+	struct wokeby_t woke;
+
+	bpf_get_current_comm(&woke.name, sizeof(woke.name));
+	woke.ret = bpf_get_stackid(ctx, &stackmap, STACKID_FLAGS);
+
+	bpf_map_update_elem(&wokeby, &pid, &woke, BPF_ANY);
+	return 0;
+}
+
+static inline int update_counts(void *ctx, u32 pid, u64 delta)
+{
+	struct wokeby_t *woke;
+	u64 zero = 0, *val;
+	struct key_t key;
+
+	__builtin_memset(&key.waker, 0, sizeof(key.waker));
+	bpf_get_current_comm(&key.target, sizeof(key.target));
+	key.tret = bpf_get_stackid(ctx, &stackmap, STACKID_FLAGS);
+	key.wret = 0;
+
+	woke = bpf_map_lookup_elem(&wokeby, &pid);
+	if (woke) {
+		key.wret = woke->ret;
+		__builtin_memcpy(&key.waker, woke->name, sizeof(key.waker));
+		bpf_map_delete_elem(&wokeby, &pid);
+	}
+
+	val = bpf_map_lookup_elem(&counts, &key);
+	if (!val) {
+		bpf_map_update_elem(&counts, &key, &zero, BPF_NOEXIST);
+		val = bpf_map_lookup_elem(&counts, &key);
+		if (!val)
+			return 0;
+	}
+	(*val) += delta;
+	return 0;
+}
+
+#if 1
+/* taken from /sys/kernel/tracing/events/sched/sched_switch/format */
+SEC("tracepoint/sched/sched_switch")
+int oncpu(struct trace_event_raw_sched_switch *ctx)
+{
+	/* record previous thread sleep time */
+	u32 pid = ctx->prev_pid;
+#else
+SEC("kprobe.multi/finish_task_switch*")
+int oncpu(struct pt_regs *ctx)
+{
+	struct task_struct *p = (void *)PT_REGS_PARM1_CORE(ctx);
+	/* record previous thread sleep time */
+	u32 pid = BPF_CORE_READ(p, pid);
+#endif
+	u64 delta, ts, *tsp;
+
+	ts = bpf_ktime_get_ns();
+	bpf_map_update_elem(&start, &pid, &ts, BPF_ANY);
+
+	/* calculate current thread's delta time */
+	pid = bpf_get_current_pid_tgid();
+	tsp = bpf_map_lookup_elem(&start, &pid);
+	if (!tsp)
+		/* missed start or filtered */
+		return 0;
+
+	delta = bpf_ktime_get_ns() - *tsp;
+	bpf_map_delete_elem(&start, &pid);
+	delta = delta / 1000;
+	if (delta < MINBLOCK_US)
+		return 0;
+
+	return update_counts(ctx, pid, delta);
+}
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;

linux-7.2.3/samples/bpf/offwaketime_user.c

@@ -0,0 +1,153 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2016 Facebook
+ */
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <linux/perf_event.h>
+#include <errno.h>
+#include <stdbool.h>
+#include <bpf/libbpf.h>
+#include <bpf/bpf.h>
+#include "trace_helpers.h"
+
+#define PRINT_RAW_ADDR 0
+
+/* counts, stackmap */
+static int map_fd[2];
+
+static void print_ksym(__u64 addr)
+{
+	struct ksym *sym;
+
+	if (!addr)
+		return;
+	sym = ksym_search(addr);
+	if (!sym) {
+		printf("ksym not found. Is kallsyms loaded?\n");
+		return;
+	}
+
+	if (PRINT_RAW_ADDR)
+		printf("%s/%llx;", sym->name, addr);
+	else
+		printf("%s;", sym->name);
+}
+
+#define TASK_COMM_LEN 16
+
+struct key_t {
+	char waker[TASK_COMM_LEN];
+	char target[TASK_COMM_LEN];
+	__u32 wret;
+	__u32 tret;
+};
+
+static void print_stack(struct key_t *key, __u64 count)
+{
+	__u64 ip[PERF_MAX_STACK_DEPTH] = {};
+	static bool warned;
+	int i;
+
+	printf("%s;", key->target);
+	if (bpf_map_lookup_elem(map_fd[1], &key->tret, ip) != 0) {
+		printf("---;");
+	} else {
+		for (i = PERF_MAX_STACK_DEPTH - 1; i >= 0; i--)
+			print_ksym(ip[i]);
+	}
+	printf("-;");
+	if (bpf_map_lookup_elem(map_fd[1], &key->wret, ip) != 0) {
+		printf("---;");
+	} else {
+		for (i = 0; i < PERF_MAX_STACK_DEPTH; i++)
+			print_ksym(ip[i]);
+	}
+	printf(";%s %lld\n", key->waker, count);
+
+	if ((key->tret == -EEXIST || key->wret == -EEXIST) && !warned) {
+		printf("stackmap collisions seen. Consider increasing size\n");
+		warned = true;
+	} else if (((int)(key->tret) < 0 || (int)(key->wret) < 0)) {
+		printf("err stackid %d %d\n", key->tret, key->wret);
+	}
+}
+
+static void print_stacks(int fd)
+{
+	struct key_t key = {}, next_key;
+	__u64 value;
+
+	while (bpf_map_get_next_key(fd, &key, &next_key) == 0) {
+		bpf_map_lookup_elem(fd, &next_key, &value);
+		print_stack(&next_key, value);
+		key = next_key;
+	}
+}
+
+static void int_exit(int sig)
+{
+	print_stacks(map_fd[0]);
+	exit(0);
+}
+
+int main(int argc, char **argv)
+{
+	struct bpf_object *obj = NULL;
+	struct bpf_link *links[2];
+	struct bpf_program *prog;
+	int delay = 1, i = 0;
+	char filename[256];
+
+	if (load_kallsyms()) {
+		printf("failed to process /proc/kallsyms\n");
+		return 2;
+	}
+
+	snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
+	obj = bpf_object__open_file(filename, NULL);
+	if (libbpf_get_error(obj)) {
+		fprintf(stderr, "ERROR: opening BPF object file failed\n");
+		obj = NULL;
+		goto cleanup;
+	}
+
+	/* load BPF program */
+	if (bpf_object__load(obj)) {
+		fprintf(stderr, "ERROR: loading BPF object file failed\n");
+		goto cleanup;
+	}
+
+	map_fd[0] = bpf_object__find_map_fd_by_name(obj, "counts");
+	map_fd[1] = bpf_object__find_map_fd_by_name(obj, "stackmap");
+	if (map_fd[0] < 0 || map_fd[1] < 0) {
+		fprintf(stderr, "ERROR: finding a map in obj file failed\n");
+		goto cleanup;
+	}
+
+	signal(SIGINT, int_exit);
+	signal(SIGTERM, int_exit);
+
+	bpf_object__for_each_program(prog, obj) {
+		links[i] = bpf_program__attach(prog);
+		if (libbpf_get_error(links[i])) {
+			fprintf(stderr, "ERROR: bpf_program__attach failed\n");
+			links[i] = NULL;
+			goto cleanup;
+		}
+		i++;
+	}
+
+	if (argc > 1)
+		delay = atoi(argv[1]);
+	sleep(delay);
+	print_stacks(map_fd[0]);
+
+cleanup:
+	for (i--; i >= 0; i--)
+		bpf_link__destroy(links[i]);
+
+	bpf_object__close(obj);
+	return 0;
+}

linux-7.2.3/samples/bpf/parse_ldabs.c

@@ -0,0 +1,43 @@
+/* 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 KBUILD_MODNAME "foo"
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/in.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <uapi/linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_legacy.h"
+
+#define DEFAULT_PKTGEN_UDP_PORT	9
+#define IP_MF			0x2000
+#define IP_OFFSET		0x1FFF
+
+static inline int ip_is_fragment(struct __sk_buff *ctx, __u64 nhoff)
+{
+	return load_half(ctx, nhoff + offsetof(struct iphdr, frag_off))
+		& (IP_MF | IP_OFFSET);
+}
+
+SEC("ldabs")
+int handle_ingress(struct __sk_buff *skb)
+{
+	__u64 troff = ETH_HLEN + sizeof(struct iphdr);
+
+	if (load_half(skb, offsetof(struct ethhdr, h_proto)) != ETH_P_IP)
+		return 0;
+	if (load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol)) != IPPROTO_UDP ||
+	    load_byte(skb, ETH_HLEN) != 0x45)
+		return 0;
+	if (ip_is_fragment(skb, ETH_HLEN))
+		return 0;
+	if (load_half(skb, troff + offsetof(struct udphdr, dest)) == DEFAULT_PKTGEN_UDP_PORT)
+		return TC_ACT_SHOT;
+	return 0;
+}
+char _license[] SEC("license") = "GPL";

linux-7.2.3/samples/bpf/parse_simple.c

@@ -0,0 +1,49 @@
+/* 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 KBUILD_MODNAME "foo"
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/in.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <uapi/linux/bpf.h>
+#include <net/ip.h>
+#include <bpf/bpf_helpers.h>
+
+#define DEFAULT_PKTGEN_UDP_PORT 9
+
+/* copy of 'struct ethhdr' without __packed */
+struct eth_hdr {
+	unsigned char   h_dest[ETH_ALEN];
+	unsigned char   h_source[ETH_ALEN];
+	unsigned short  h_proto;
+};
+
+SEC("simple")
+int handle_ingress(struct __sk_buff *skb)
+{
+	void *data = (void *)(long)skb->data;
+	struct eth_hdr *eth = data;
+	struct iphdr *iph = data + sizeof(*eth);
+	struct udphdr *udp = data + sizeof(*eth) + sizeof(*iph);
+	void *data_end = (void *)(long)skb->data_end;
+
+	/* single length check */
+	if (data + sizeof(*eth) + sizeof(*iph) + sizeof(*udp) > data_end)
+		return 0;
+
+	if (eth->h_proto != htons(ETH_P_IP))
+		return 0;
+	if (iph->protocol != IPPROTO_UDP || iph->ihl != 5)
+		return 0;
+	if (ip_is_fragment(iph))
+		return 0;
+	if (udp->dest == htons(DEFAULT_PKTGEN_UDP_PORT))
+		return TC_ACT_SHOT;
+	return 0;
+}
+char _license[] SEC("license") = "GPL";

linux-7.2.3/samples/bpf/parse_varlen.c

@@ -0,0 +1,150 @@
+/* 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 KBUILD_MODNAME "foo"
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/in.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <uapi/linux/bpf.h>
+#include <net/ip.h>
+#include <bpf/bpf_helpers.h>
+
+#define DEFAULT_PKTGEN_UDP_PORT 9
+#define DEBUG 0
+
+static int tcp(void *data, uint64_t tp_off, void *data_end)
+{
+	struct tcphdr *tcp = data + tp_off;
+
+	if (tcp + 1 > data_end)
+		return 0;
+	if (tcp->dest == htons(80) || tcp->source == htons(80))
+		return TC_ACT_SHOT;
+	return 0;
+}
+
+static int udp(void *data, uint64_t tp_off, void *data_end)
+{
+	struct udphdr *udp = data + tp_off;
+
+	if (udp + 1 > data_end)
+		return 0;
+	if (udp->dest == htons(DEFAULT_PKTGEN_UDP_PORT) ||
+	    udp->source == htons(DEFAULT_PKTGEN_UDP_PORT)) {
+		if (DEBUG) {
+			char fmt[] = "udp port 9 indeed\n";
+
+			bpf_trace_printk(fmt, sizeof(fmt));
+		}
+		return TC_ACT_SHOT;
+	}
+	return 0;
+}
+
+static int parse_ipv4(void *data, uint64_t nh_off, void *data_end)
+{
+	struct iphdr *iph;
+	uint64_t ihl_len;
+
+	iph = data + nh_off;
+	if (iph + 1 > data_end)
+		return 0;
+
+	if (ip_is_fragment(iph))
+		return 0;
+	ihl_len = iph->ihl * 4;
+
+	if (iph->protocol == IPPROTO_IPIP) {
+		iph = data + nh_off + ihl_len;
+		if (iph + 1 > data_end)
+			return 0;
+		ihl_len += iph->ihl * 4;
+	}
+
+	if (iph->protocol == IPPROTO_TCP)
+		return tcp(data, nh_off + ihl_len, data_end);
+	else if (iph->protocol == IPPROTO_UDP)
+		return udp(data, nh_off + ihl_len, data_end);
+	return 0;
+}
+
+static int parse_ipv6(void *data, uint64_t nh_off, void *data_end)
+{
+	struct ipv6hdr *ip6h;
+	struct iphdr *iph;
+	uint64_t ihl_len = sizeof(struct ipv6hdr);
+	uint64_t nexthdr;
+
+	ip6h = data + nh_off;
+	if (ip6h + 1 > data_end)
+		return 0;
+
+	nexthdr = ip6h->nexthdr;
+
+	if (nexthdr == IPPROTO_IPIP) {
+		iph = data + nh_off + ihl_len;
+		if (iph + 1 > data_end)
+			return 0;
+		ihl_len += iph->ihl * 4;
+		nexthdr = iph->protocol;
+	} else if (nexthdr == IPPROTO_IPV6) {
+		ip6h = data + nh_off + ihl_len;
+		if (ip6h + 1 > data_end)
+			return 0;
+		ihl_len += sizeof(struct ipv6hdr);
+		nexthdr = ip6h->nexthdr;
+	}
+
+	if (nexthdr == IPPROTO_TCP)
+		return tcp(data, nh_off + ihl_len, data_end);
+	else if (nexthdr == IPPROTO_UDP)
+		return udp(data, nh_off + ihl_len, data_end);
+	return 0;
+}
+
+SEC("varlen")
+int handle_ingress(struct __sk_buff *skb)
+{
+	void *data = (void *)(long)skb->data;
+	struct ethhdr *eth = data;
+	void *data_end = (void *)(long)skb->data_end;
+	uint64_t h_proto, nh_off;
+
+	nh_off = sizeof(*eth);
+	if (data + nh_off > data_end)
+		return 0;
+
+	h_proto = eth->h_proto;
+
+	if (h_proto == ETH_P_8021Q || h_proto == ETH_P_8021AD) {
+		struct vlan_hdr *vhdr;
+
+		vhdr = data + nh_off;
+		nh_off += sizeof(struct vlan_hdr);
+		if (data + nh_off > data_end)
+			return 0;
+		h_proto = vhdr->h_vlan_encapsulated_proto;
+	}
+	if (h_proto == ETH_P_8021Q || h_proto == ETH_P_8021AD) {
+		struct vlan_hdr *vhdr;
+
+		vhdr = data + nh_off;
+		nh_off += sizeof(struct vlan_hdr);
+		if (data + nh_off > data_end)
+			return 0;
+		h_proto = vhdr->h_vlan_encapsulated_proto;
+	}
+	if (h_proto == htons(ETH_P_IP))
+		return parse_ipv4(data, nh_off, data_end);
+	else if (h_proto == htons(ETH_P_IPV6))
+		return parse_ipv6(data, nh_off, data_end);
+	return 0;
+}
+char _license[] SEC("license") = "GPL";

linux-7.2.3/samples/bpf/run_cookie_uid_helper_example.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+local_dir="$(pwd)"
+root_dir=$local_dir/../..
+mnt_dir=$(mktemp -d --tmp)
+
+on_exit() {
+	iptables -D OUTPUT -m bpf --object-pinned ${mnt_dir}/bpf_prog -j ACCEPT
+	umount ${mnt_dir}
+	rm -r ${mnt_dir}
+}
+
+trap on_exit EXIT
+mount -t bpf bpf ${mnt_dir}
+./per_socket_stats_example ${mnt_dir}/bpf_prog $1

linux-7.2.3/samples/bpf/sampleip_kern.c

@@ -0,0 +1,38 @@
+/* Copyright 2016 Netflix, Inc.
+ *
+ * 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/ptrace.h>
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/bpf_perf_event.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#define MAX_IPS		8192
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, u64);
+	__type(value, u32);
+	__uint(max_entries, MAX_IPS);
+} ip_map SEC(".maps");
+
+SEC("perf_event")
+int do_sample(struct bpf_perf_event_data *ctx)
+{
+	u64 ip;
+	u32 *value, init_val = 1;
+
+	ip = PT_REGS_IP(&ctx->regs);
+	value = bpf_map_lookup_elem(&ip_map, &ip);
+	if (value)
+		*value += 1;
+	else
+		/* E2BIG not tested for this example only */
+		bpf_map_update_elem(&ip_map, &ip, &init_val, BPF_NOEXIST);
+
+	return 0;
+}
+char _license[] SEC("license") = "GPL";

linux-7.2.3/samples/bpf/sampleip_user.c

@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * sampleip: sample instruction pointer and frequency count in a BPF map.
+ *
+ * Copyright 2016 Netflix, Inc.
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <errno.h>
+#include <signal.h>
+#include <string.h>
+#include <linux/perf_event.h>
+#include <linux/ptrace.h>
+#include <linux/bpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "perf-sys.h"
+#include "trace_helpers.h"
+
+#define DEFAULT_FREQ	99
+#define DEFAULT_SECS	5
+#define MAX_IPS		8192
+
+static int map_fd;
+static int nr_cpus;
+static long _text_addr;
+
+static void usage(void)
+{
+	printf("USAGE: sampleip [-F freq] [duration]\n");
+	printf("       -F freq    # sample frequency (Hertz), default 99\n");
+	printf("       duration   # sampling duration (seconds), default 5\n");
+}
+
+static int sampling_start(int freq, struct bpf_program *prog,
+			  struct bpf_link *links[])
+{
+	int i, pmu_fd;
+
+	struct perf_event_attr pe_sample_attr = {
+		.type = PERF_TYPE_SOFTWARE,
+		.freq = 1,
+		.sample_period = freq,
+		.config = PERF_COUNT_SW_CPU_CLOCK,
+		.inherit = 1,
+	};
+
+	for (i = 0; i < nr_cpus; i++) {
+		pmu_fd = sys_perf_event_open(&pe_sample_attr, -1 /* pid */, i,
+					    -1 /* group_fd */, 0 /* flags */);
+		if (pmu_fd < 0) {
+			fprintf(stderr, "ERROR: Initializing perf sampling\n");
+			return 1;
+		}
+		links[i] = bpf_program__attach_perf_event(prog, pmu_fd);
+		if (libbpf_get_error(links[i])) {
+			fprintf(stderr, "ERROR: Attach perf event\n");
+			links[i] = NULL;
+			close(pmu_fd);
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+static void sampling_end(struct bpf_link *links[])
+{
+	int i;
+
+	for (i = 0; i < nr_cpus; i++)
+		bpf_link__destroy(links[i]);
+}
+
+struct ipcount {
+	__u64 ip;
+	__u32 count;
+};
+
+/* used for sorting */
+struct ipcount counts[MAX_IPS];
+
+static int count_cmp(const void *p1, const void *p2)
+{
+	return ((struct ipcount *)p1)->count - ((struct ipcount *)p2)->count;
+}
+
+static void print_ip_map(int fd)
+{
+	struct ksym *sym;
+	__u64 key, next_key;
+	__u32 value;
+	int i, max;
+
+	printf("%-19s %-32s %s\n", "ADDR", "KSYM", "COUNT");
+
+	/* fetch IPs and counts */
+	key = 0, i = 0;
+	while (bpf_map_get_next_key(fd, &key, &next_key) == 0) {
+		bpf_map_lookup_elem(fd, &next_key, &value);
+		counts[i].ip = next_key;
+		counts[i++].count = value;
+		key = next_key;
+	}
+	max = i;
+
+	/* sort and print */
+	qsort(counts, max, sizeof(struct ipcount), count_cmp);
+	for (i = 0; i < max; i++) {
+		if (counts[i].ip > _text_addr) {
+			sym = ksym_search(counts[i].ip);
+			if (!sym) {
+				printf("ksym not found. Is kallsyms loaded?\n");
+				continue;
+			}
+
+			printf("0x%-17llx %-32s %u\n", counts[i].ip, sym->name,
+			       counts[i].count);
+		} else {
+			printf("0x%-17llx %-32s %u\n", counts[i].ip, "(user)",
+			       counts[i].count);
+		}
+	}
+
+	if (max == MAX_IPS) {
+		printf("WARNING: IP hash was full (max %d entries); ", max);
+		printf("may have dropped samples\n");
+	}
+}
+
+static void int_exit(int sig)
+{
+	printf("\n");
+	print_ip_map(map_fd);
+	exit(0);
+}
+
+int main(int argc, char **argv)
+{
+	int opt, freq = DEFAULT_FREQ, secs = DEFAULT_SECS, error = 1;
+	struct bpf_object *obj = NULL;
+	struct bpf_program *prog;
+	struct bpf_link **links;
+	char filename[256];
+
+	/* process arguments */
+	while ((opt = getopt(argc, argv, "F:h")) != -1) {
+		switch (opt) {
+		case 'F':
+			freq = atoi(optarg);
+			break;
+		case 'h':
+		default:
+			usage();
+			return 0;
+		}
+	}
+	if (argc - optind == 1)
+		secs = atoi(argv[optind]);
+	if (freq == 0 || secs == 0) {
+		usage();
+		return 1;
+	}
+
+	/* initialize kernel symbol translation */
+	if (load_kallsyms()) {
+		fprintf(stderr, "ERROR: loading /proc/kallsyms\n");
+		return 2;
+	}
+
+	/* used to determine whether the address is kernel space */
+	_text_addr = ksym_get_addr("_text");
+	if (!_text_addr) {
+		fprintf(stderr, "ERROR: no '_text' in /proc/kallsyms\n");
+		return 3;
+	}
+
+	/* create perf FDs for each CPU */
+	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
+	links = calloc(nr_cpus, sizeof(struct bpf_link *));
+	if (!links) {
+		fprintf(stderr, "ERROR: malloc of links\n");
+		goto cleanup;
+	}
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+	obj = bpf_object__open_file(filename, NULL);
+	if (libbpf_get_error(obj)) {
+		fprintf(stderr, "ERROR: opening BPF object file failed\n");
+		obj = NULL;
+		goto cleanup;
+	}
+
+	prog = bpf_object__find_program_by_name(obj, "do_sample");
+	if (!prog) {
+		fprintf(stderr, "ERROR: finding a prog in obj file failed\n");
+		goto cleanup;
+	}
+
+	/* load BPF program */
+	if (bpf_object__load(obj)) {
+		fprintf(stderr, "ERROR: loading BPF object file failed\n");
+		goto cleanup;
+	}
+
+	map_fd = bpf_object__find_map_fd_by_name(obj, "ip_map");
+	if (map_fd < 0) {
+		fprintf(stderr, "ERROR: finding a map in obj file failed\n");
+		goto cleanup;
+	}
+
+	signal(SIGINT, int_exit);
+	signal(SIGTERM, int_exit);
+
+	/* do sampling */
+	printf("Sampling at %d Hertz for %d seconds. Ctrl-C also ends.\n",
+	       freq, secs);
+	if (sampling_start(freq, prog, links) != 0)
+		goto cleanup;
+
+	sleep(secs);
+	error = 0;
+
+cleanup:
+	sampling_end(links);
+	/* output sample counts */
+	if (!error)
+		print_ip_map(map_fd);
+
+	free(links);
+	bpf_object__close(obj);
+	return error;
+}

linux-7.2.3/samples/bpf/sock_example.c

@@ -0,0 +1,111 @@
+/* eBPF example program:
+ * - creates arraymap in kernel with key 4 bytes and value 8 bytes
+ *
+ * - loads eBPF program:
+ *   r0 = skb->data[ETH_HLEN + offsetof(struct iphdr, protocol)];
+ *   *(u32*)(fp - 4) = r0;
+ *   // assuming packet is IPv4, lookup ip->proto in a map
+ *   value = bpf_map_lookup_elem(map_fd, fp - 4);
+ *   if (value)
+ *        (*(u64*)value) += 1;
+ *
+ * - attaches this program to loopback interface "lo" raw socket
+ *
+ * - every second user space reads map[tcp], map[udp], map[icmp] to see
+ *   how many packets of given protocol were seen on "lo"
+ */
+#include <stdio.h>
+#include <unistd.h>
+#include <assert.h>
+#include <linux/bpf.h>
+#include <string.h>
+#include <stdlib.h>
+#include <errno.h>
+#include <sys/socket.h>
+#include <arpa/inet.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <stddef.h>
+#include <bpf/bpf.h>
+#include "bpf_insn.h"
+#include "sock_example.h"
+#include "bpf_util.h"
+
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
+static int test_sock(void)
+{
+	int sock = -1, map_fd, prog_fd, i, key;
+	long long value = 0, tcp_cnt, udp_cnt, icmp_cnt;
+
+	map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(key), sizeof(value),
+				256, NULL);
+	if (map_fd < 0) {
+		printf("failed to create map '%s'\n", strerror(errno));
+		goto cleanup;
+	}
+
+	struct bpf_insn prog[] = {
+		BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+		BPF_LD_ABS(BPF_B, ETH_HLEN + offsetof(struct iphdr, protocol) /* R0 = ip->proto */),
+		BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */
+		BPF_LD_MAP_FD(BPF_REG_1, map_fd),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+		BPF_MOV64_IMM(BPF_REG_1, 1), /* r1 = 1 */
+		BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_0, BPF_REG_1, 0),
+		BPF_MOV64_IMM(BPF_REG_0, 0), /* r0 = 0 */
+		BPF_EXIT_INSN(),
+	};
+	size_t insns_cnt = ARRAY_SIZE(prog);
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		.log_buf = bpf_log_buf,
+		.log_size = BPF_LOG_BUF_SIZE,
+	);
+
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL",
+				prog, insns_cnt, &opts);
+	if (prog_fd < 0) {
+		printf("failed to load prog '%s'\n", strerror(errno));
+		goto cleanup;
+	}
+
+	sock = open_raw_sock("lo");
+
+	if (setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &prog_fd,
+		       sizeof(prog_fd)) < 0) {
+		printf("setsockopt %s\n", strerror(errno));
+		goto cleanup;
+	}
+
+	for (i = 0; i < 10; i++) {
+		key = IPPROTO_TCP;
+		assert(bpf_map_lookup_elem(map_fd, &key, &tcp_cnt) == 0);
+
+		key = IPPROTO_UDP;
+		assert(bpf_map_lookup_elem(map_fd, &key, &udp_cnt) == 0);
+
+		key = IPPROTO_ICMP;
+		assert(bpf_map_lookup_elem(map_fd, &key, &icmp_cnt) == 0);
+
+		printf("TCP %lld UDP %lld ICMP %lld packets\n",
+		       tcp_cnt, udp_cnt, icmp_cnt);
+		sleep(1);
+	}
+
+cleanup:
+	/* maps, programs, raw sockets will auto cleanup on process exit */
+	return 0;
+}
+
+int main(void)
+{
+	FILE *f;
+
+	f = popen("ping -4 -c5 localhost", "r");
+	(void)f;
+
+	return test_sock();
+}

linux-7.2.3/samples/bpf/sock_example.h

@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <stdlib.h>
+#include <stdio.h>
+#include <linux/unistd.h>
+#include <unistd.h>
+#include <string.h>
+#include <errno.h>
+#include <linux/if_ether.h>
+#include <net/if.h>
+#include <linux/if_packet.h>
+#include <arpa/inet.h>
+
+static inline int open_raw_sock(const char *name)
+{
+	struct sockaddr_ll sll;
+	int sock;
+
+	sock = socket(PF_PACKET, SOCK_RAW | SOCK_NONBLOCK | SOCK_CLOEXEC, htons(ETH_P_ALL));
+	if (sock < 0) {
+		printf("cannot create raw socket\n");
+		return -1;
+	}
+
+	memset(&sll, 0, sizeof(sll));
+	sll.sll_family = AF_PACKET;
+	sll.sll_ifindex = if_nametoindex(name);
+	sll.sll_protocol = htons(ETH_P_ALL);
+	if (bind(sock, (struct sockaddr *)&sll, sizeof(sll)) < 0) {
+		printf("bind to %s: %s\n", name, strerror(errno));
+		close(sock);
+		return -1;
+	}
+
+	return sock;
+}

linux-7.2.3/samples/bpf/sockex1_kern.c

@@ -0,0 +1,30 @@
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_legacy.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, u32);
+	__type(value, long);
+	__uint(max_entries, 256);
+} my_map SEC(".maps");
+
+SEC("socket1")
+int bpf_prog1(struct __sk_buff *skb)
+{
+	int index = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol));
+	long *value;
+
+	if (skb->pkt_type != PACKET_OUTGOING)
+		return 0;
+
+	value = bpf_map_lookup_elem(&my_map, &index);
+	if (value)
+		__sync_fetch_and_add(value, skb->len);
+
+	return 0;
+}
+char _license[] SEC("license") = "GPL";

linux-7.2.3/samples/bpf/sockex1_user.c

@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <assert.h>
+#include <linux/bpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "sock_example.h"
+#include <unistd.h>
+#include <arpa/inet.h>
+
+int main(int ac, char **argv)
+{
+	struct bpf_object *obj;
+	struct bpf_program *prog;
+	int map_fd, prog_fd;
+	char filename[256];
+	int i, sock, err;
+	FILE *f;
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	obj = bpf_object__open_file(filename, NULL);
+	if (libbpf_get_error(obj))
+		return 1;
+
+	prog = bpf_object__next_program(obj, NULL);
+	bpf_program__set_type(prog, BPF_PROG_TYPE_SOCKET_FILTER);
+
+	err = bpf_object__load(obj);
+	if (err)
+		return 1;
+
+	prog_fd = bpf_program__fd(prog);
+	map_fd = bpf_object__find_map_fd_by_name(obj, "my_map");
+
+	sock = open_raw_sock("lo");
+
+	assert(setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &prog_fd,
+			  sizeof(prog_fd)) == 0);
+
+	f = popen("ping -4 -c5 localhost", "r");
+	(void) f;
+
+	for (i = 0; i < 5; i++) {
+		long long tcp_cnt, udp_cnt, icmp_cnt;
+		int key;
+
+		key = IPPROTO_TCP;
+		assert(bpf_map_lookup_elem(map_fd, &key, &tcp_cnt) == 0);
+
+		key = IPPROTO_UDP;
+		assert(bpf_map_lookup_elem(map_fd, &key, &udp_cnt) == 0);
+
+		key = IPPROTO_ICMP;
+		assert(bpf_map_lookup_elem(map_fd, &key, &icmp_cnt) == 0);
+
+		printf("TCP %lld UDP %lld ICMP %lld bytes\n",
+		       tcp_cnt, udp_cnt, icmp_cnt);
+		sleep(1);
+	}
+
+	return 0;
+}

linux-7.2.3/samples/bpf/sockex2_kern.c

@@ -0,0 +1,222 @@
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/in.h>
+#include <uapi/linux/if.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/ip.h>
+#include <uapi/linux/ipv6.h>
+#include <uapi/linux/if_tunnel.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_legacy.h"
+#define IP_MF		0x2000
+#define IP_OFFSET	0x1FFF
+
+struct vlan_hdr {
+	__be16 h_vlan_TCI;
+	__be16 h_vlan_encapsulated_proto;
+};
+
+struct flow_key_record {
+	__be32 src;
+	__be32 dst;
+	union {
+		__be32 ports;
+		__be16 port16[2];
+	};
+	__u16 thoff;
+	__u8 ip_proto;
+};
+
+static inline int proto_ports_offset(__u64 proto)
+{
+	switch (proto) {
+	case IPPROTO_TCP:
+	case IPPROTO_UDP:
+	case IPPROTO_ESP:
+	case IPPROTO_SCTP:
+	case IPPROTO_UDPLITE:
+		return 0;
+	case IPPROTO_AH:
+		return 4;
+	default:
+		return 0;
+	}
+}
+
+static inline int ip_is_fragment(struct __sk_buff *ctx, __u64 nhoff)
+{
+	return load_half(ctx, nhoff + offsetof(struct iphdr, frag_off))
+		& (IP_MF | IP_OFFSET);
+}
+
+static inline __u32 ipv6_addr_hash(struct __sk_buff *ctx, __u64 off)
+{
+	__u64 w0 = load_word(ctx, off);
+	__u64 w1 = load_word(ctx, off + 4);
+	__u64 w2 = load_word(ctx, off + 8);
+	__u64 w3 = load_word(ctx, off + 12);
+
+	return (__u32)(w0 ^ w1 ^ w2 ^ w3);
+}
+
+static inline __u64 parse_ip(struct __sk_buff *skb, __u64 nhoff, __u64 *ip_proto,
+			     struct flow_key_record *flow)
+{
+	__u64 verlen;
+
+	if (unlikely(ip_is_fragment(skb, nhoff)))
+		*ip_proto = 0;
+	else
+		*ip_proto = load_byte(skb, nhoff + offsetof(struct iphdr, protocol));
+
+	if (*ip_proto != IPPROTO_GRE) {
+		flow->src = load_word(skb, nhoff + offsetof(struct iphdr, saddr));
+		flow->dst = load_word(skb, nhoff + offsetof(struct iphdr, daddr));
+	}
+
+	verlen = load_byte(skb, nhoff + 0/*offsetof(struct iphdr, ihl)*/);
+	if (likely(verlen == 0x45))
+		nhoff += 20;
+	else
+		nhoff += (verlen & 0xF) << 2;
+
+	return nhoff;
+}
+
+static inline __u64 parse_ipv6(struct __sk_buff *skb, __u64 nhoff, __u64 *ip_proto,
+			       struct flow_key_record *flow)
+{
+	*ip_proto = load_byte(skb,
+			      nhoff + offsetof(struct ipv6hdr, nexthdr));
+	flow->src = ipv6_addr_hash(skb,
+				   nhoff + offsetof(struct ipv6hdr, saddr));
+	flow->dst = ipv6_addr_hash(skb,
+				   nhoff + offsetof(struct ipv6hdr, daddr));
+	nhoff += sizeof(struct ipv6hdr);
+
+	return nhoff;
+}
+
+static inline bool flow_dissector(struct __sk_buff *skb,
+				  struct flow_key_record *flow)
+{
+	__u64 nhoff = ETH_HLEN;
+	__u64 ip_proto;
+	__u64 proto = load_half(skb, 12);
+	int poff;
+
+	if (proto == ETH_P_8021AD) {
+		proto = load_half(skb, nhoff + offsetof(struct vlan_hdr,
+							h_vlan_encapsulated_proto));
+		nhoff += sizeof(struct vlan_hdr);
+	}
+
+	if (proto == ETH_P_8021Q) {
+		proto = load_half(skb, nhoff + offsetof(struct vlan_hdr,
+							h_vlan_encapsulated_proto));
+		nhoff += sizeof(struct vlan_hdr);
+	}
+
+	if (likely(proto == ETH_P_IP))
+		nhoff = parse_ip(skb, nhoff, &ip_proto, flow);
+	else if (proto == ETH_P_IPV6)
+		nhoff = parse_ipv6(skb, nhoff, &ip_proto, flow);
+	else
+		return false;
+
+	switch (ip_proto) {
+	case IPPROTO_GRE: {
+		struct gre_hdr {
+			__be16 flags;
+			__be16 proto;
+		};
+
+		__u64 gre_flags = load_half(skb,
+					    nhoff + offsetof(struct gre_hdr, flags));
+		__u64 gre_proto = load_half(skb,
+					    nhoff + offsetof(struct gre_hdr, proto));
+
+		if (gre_flags & (GRE_VERSION|GRE_ROUTING))
+			break;
+
+		proto = gre_proto;
+		nhoff += 4;
+		if (gre_flags & GRE_CSUM)
+			nhoff += 4;
+		if (gre_flags & GRE_KEY)
+			nhoff += 4;
+		if (gre_flags & GRE_SEQ)
+			nhoff += 4;
+
+		if (proto == ETH_P_8021Q) {
+			proto = load_half(skb,
+					  nhoff + offsetof(struct vlan_hdr,
+							   h_vlan_encapsulated_proto));
+			nhoff += sizeof(struct vlan_hdr);
+		}
+
+		if (proto == ETH_P_IP)
+			nhoff = parse_ip(skb, nhoff, &ip_proto, flow);
+		else if (proto == ETH_P_IPV6)
+			nhoff = parse_ipv6(skb, nhoff, &ip_proto, flow);
+		else
+			return false;
+		break;
+	}
+	case IPPROTO_IPIP:
+		nhoff = parse_ip(skb, nhoff, &ip_proto, flow);
+		break;
+	case IPPROTO_IPV6:
+		nhoff = parse_ipv6(skb, nhoff, &ip_proto, flow);
+		break;
+	default:
+		break;
+	}
+
+	flow->ip_proto = ip_proto;
+	poff = proto_ports_offset(ip_proto);
+	if (poff >= 0) {
+		nhoff += poff;
+		flow->ports = load_word(skb, nhoff);
+	}
+
+	flow->thoff = (__u16) nhoff;
+
+	return true;
+}
+
+struct pair {
+	long packets;
+	long bytes;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, __be32);
+	__type(value, struct pair);
+	__uint(max_entries, 1024);
+} hash_map SEC(".maps");
+
+SEC("socket2")
+int bpf_prog2(struct __sk_buff *skb)
+{
+	struct flow_key_record flow = {};
+	struct pair *value;
+	u32 key;
+
+	if (!flow_dissector(skb, &flow))
+		return 0;
+
+	key = flow.dst;
+	value = bpf_map_lookup_elem(&hash_map, &key);
+	if (value) {
+		__sync_fetch_and_add(&value->packets, 1);
+		__sync_fetch_and_add(&value->bytes, skb->len);
+	} else {
+		struct pair val = {1, skb->len};
+
+		bpf_map_update_elem(&hash_map, &key, &val, BPF_ANY);
+	}
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";

linux-7.2.3/samples/bpf/sockex2_user.c

@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <assert.h>
+#include <linux/bpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "sock_example.h"
+#include <unistd.h>
+#include <arpa/inet.h>
+
+struct pair {
+	__u64 packets;
+	__u64 bytes;
+};
+
+int main(int ac, char **argv)
+{
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	int map_fd, prog_fd;
+	char filename[256];
+	int i, sock, err;
+	FILE *f;
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+	obj = bpf_object__open_file(filename, NULL);
+	if (libbpf_get_error(obj))
+		return 1;
+
+	prog = bpf_object__next_program(obj, NULL);
+	bpf_program__set_type(prog, BPF_PROG_TYPE_SOCKET_FILTER);
+
+	err = bpf_object__load(obj);
+	if (err)
+		return 1;
+
+	prog_fd = bpf_program__fd(prog);
+	map_fd = bpf_object__find_map_fd_by_name(obj, "hash_map");
+
+	sock = open_raw_sock("lo");
+
+	assert(setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &prog_fd,
+			  sizeof(prog_fd)) == 0);
+
+	f = popen("ping -4 -c5 localhost", "r");
+	(void) f;
+
+	for (i = 0; i < 5; i++) {
+		int key = 0, next_key;
+		struct pair value;
+
+		while (bpf_map_get_next_key(map_fd, &key, &next_key) == 0) {
+			bpf_map_lookup_elem(map_fd, &next_key, &value);
+			printf("ip %s bytes %lld packets %lld\n",
+			       inet_ntoa((struct in_addr){htonl(next_key)}),
+			       value.bytes, value.packets);
+			key = next_key;
+		}
+		sleep(1);
+	}
+	return 0;
+}

linux-7.2.3/samples/bpf/sockex3_kern.c

@@ -0,0 +1,304 @@
+/* Copyright (c) 2015 PLUMgrid, http://plumgrid.com
+ *
+ * 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 <uapi/linux/bpf.h>
+#include <uapi/linux/in.h>
+#include <uapi/linux/if.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/ip.h>
+#include <uapi/linux/ipv6.h>
+#include <uapi/linux/if_tunnel.h>
+#include <uapi/linux/mpls.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_legacy.h"
+#define IP_MF		0x2000
+#define IP_OFFSET	0x1FFF
+
+#define PARSE_VLAN 1
+#define PARSE_MPLS 2
+#define PARSE_IP 3
+#define PARSE_IPV6 4
+
+struct vlan_hdr {
+	__be16 h_vlan_TCI;
+	__be16 h_vlan_encapsulated_proto;
+};
+
+struct flow_key_record {
+	__be32 src;
+	__be32 dst;
+	union {
+		__be32 ports;
+		__be16 port16[2];
+	};
+	__u32 ip_proto;
+};
+
+static inline void parse_eth_proto(struct __sk_buff *skb, u32 proto);
+
+static inline int ip_is_fragment(struct __sk_buff *ctx, __u64 nhoff)
+{
+	return load_half(ctx, nhoff + offsetof(struct iphdr, frag_off))
+		& (IP_MF | IP_OFFSET);
+}
+
+static inline __u32 ipv6_addr_hash(struct __sk_buff *ctx, __u64 off)
+{
+	__u64 w0 = load_word(ctx, off);
+	__u64 w1 = load_word(ctx, off + 4);
+	__u64 w2 = load_word(ctx, off + 8);
+	__u64 w3 = load_word(ctx, off + 12);
+
+	return (__u32)(w0 ^ w1 ^ w2 ^ w3);
+}
+
+struct globals {
+	struct flow_key_record flow;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, __u32);
+	__type(value, struct globals);
+	__uint(max_entries, 32);
+} percpu_map SEC(".maps");
+
+/* user poor man's per_cpu until native support is ready */
+static struct globals *this_cpu_globals(void)
+{
+	u32 key = bpf_get_smp_processor_id();
+
+	return bpf_map_lookup_elem(&percpu_map, &key);
+}
+
+/* some simple stats for user space consumption */
+struct pair {
+	__u64 packets;
+	__u64 bytes;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, struct flow_key_record);
+	__type(value, struct pair);
+	__uint(max_entries, 1024);
+} hash_map SEC(".maps");
+
+static void update_stats(struct __sk_buff *skb, struct globals *g)
+{
+	struct flow_key_record key = g->flow;
+	struct pair *value;
+
+	value = bpf_map_lookup_elem(&hash_map, &key);
+	if (value) {
+		__sync_fetch_and_add(&value->packets, 1);
+		__sync_fetch_and_add(&value->bytes, skb->len);
+	} else {
+		struct pair val = {1, skb->len};
+
+		bpf_map_update_elem(&hash_map, &key, &val, BPF_ANY);
+	}
+}
+
+static __always_inline void parse_ip_proto(struct __sk_buff *skb,
+					   struct globals *g, __u32 ip_proto)
+{
+	__u32 nhoff = skb->cb[0];
+	int poff;
+
+	switch (ip_proto) {
+	case IPPROTO_GRE: {
+		struct gre_hdr {
+			__be16 flags;
+			__be16 proto;
+		};
+
+		__u32 gre_flags = load_half(skb,
+					    nhoff + offsetof(struct gre_hdr, flags));
+		__u32 gre_proto = load_half(skb,
+					    nhoff + offsetof(struct gre_hdr, proto));
+
+		if (gre_flags & (GRE_VERSION|GRE_ROUTING))
+			break;
+
+		nhoff += 4;
+		if (gre_flags & GRE_CSUM)
+			nhoff += 4;
+		if (gre_flags & GRE_KEY)
+			nhoff += 4;
+		if (gre_flags & GRE_SEQ)
+			nhoff += 4;
+
+		skb->cb[0] = nhoff;
+		parse_eth_proto(skb, gre_proto);
+		break;
+	}
+	case IPPROTO_IPIP:
+		parse_eth_proto(skb, ETH_P_IP);
+		break;
+	case IPPROTO_IPV6:
+		parse_eth_proto(skb, ETH_P_IPV6);
+		break;
+	case IPPROTO_TCP:
+	case IPPROTO_UDP:
+		g->flow.ports = load_word(skb, nhoff);
+	case IPPROTO_ICMP:
+		g->flow.ip_proto = ip_proto;
+		update_stats(skb, g);
+		break;
+	default:
+		break;
+	}
+}
+
+SEC("socket")
+int bpf_func_ip(struct __sk_buff *skb)
+{
+	struct globals *g = this_cpu_globals();
+	__u32 nhoff, verlen, ip_proto;
+
+	if (!g)
+		return 0;
+
+	nhoff = skb->cb[0];
+
+	if (unlikely(ip_is_fragment(skb, nhoff)))
+		return 0;
+
+	ip_proto = load_byte(skb, nhoff + offsetof(struct iphdr, protocol));
+
+	if (ip_proto != IPPROTO_GRE) {
+		g->flow.src = load_word(skb, nhoff + offsetof(struct iphdr, saddr));
+		g->flow.dst = load_word(skb, nhoff + offsetof(struct iphdr, daddr));
+	}
+
+	verlen = load_byte(skb, nhoff + 0/*offsetof(struct iphdr, ihl)*/);
+	nhoff += (verlen & 0xF) << 2;
+
+	skb->cb[0] = nhoff;
+	parse_ip_proto(skb, g, ip_proto);
+	return 0;
+}
+
+SEC("socket")
+int bpf_func_ipv6(struct __sk_buff *skb)
+{
+	struct globals *g = this_cpu_globals();
+	__u32 nhoff, ip_proto;
+
+	if (!g)
+		return 0;
+
+	nhoff = skb->cb[0];
+
+	ip_proto = load_byte(skb,
+			     nhoff + offsetof(struct ipv6hdr, nexthdr));
+	g->flow.src = ipv6_addr_hash(skb,
+				     nhoff + offsetof(struct ipv6hdr, saddr));
+	g->flow.dst = ipv6_addr_hash(skb,
+				     nhoff + offsetof(struct ipv6hdr, daddr));
+	nhoff += sizeof(struct ipv6hdr);
+
+	skb->cb[0] = nhoff;
+	parse_ip_proto(skb, g, ip_proto);
+	return 0;
+}
+
+SEC("socket")
+int bpf_func_vlan(struct __sk_buff *skb)
+{
+	__u32 nhoff, proto;
+
+	nhoff = skb->cb[0];
+
+	proto = load_half(skb, nhoff + offsetof(struct vlan_hdr,
+						h_vlan_encapsulated_proto));
+	nhoff += sizeof(struct vlan_hdr);
+	skb->cb[0] = nhoff;
+
+	parse_eth_proto(skb, proto);
+
+	return 0;
+}
+
+SEC("socket")
+int bpf_func_mpls(struct __sk_buff *skb)
+{
+	__u32 nhoff, label;
+
+	nhoff = skb->cb[0];
+
+	label = load_word(skb, nhoff);
+	nhoff += sizeof(struct mpls_label);
+	skb->cb[0] = nhoff;
+
+	if (label & MPLS_LS_S_MASK) {
+		__u8 verlen = load_byte(skb, nhoff);
+		if ((verlen & 0xF0) == 4)
+			parse_eth_proto(skb, ETH_P_IP);
+		else
+			parse_eth_proto(skb, ETH_P_IPV6);
+	} else {
+		parse_eth_proto(skb, ETH_P_MPLS_UC);
+	}
+
+	return 0;
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(key_size, sizeof(u32));
+	__uint(max_entries, 8);
+	__array(values, u32 (void *));
+} prog_array_init SEC(".maps") = {
+	.values = {
+		[PARSE_VLAN] = (void *)&bpf_func_vlan,
+		[PARSE_IP]   = (void *)&bpf_func_ip,
+		[PARSE_IPV6] = (void *)&bpf_func_ipv6,
+		[PARSE_MPLS] = (void *)&bpf_func_mpls,
+	},
+};
+
+/* Protocol dispatch routine. It tail-calls next BPF program depending
+ * on eth proto. Note, we could have used ...
+ *
+ *   bpf_tail_call(skb, &prog_array_init, proto);
+ *
+ * ... but it would need large prog_array and cannot be optimised given
+ * the map key is not static.
+ */
+static inline void parse_eth_proto(struct __sk_buff *skb, u32 proto)
+{
+	switch (proto) {
+	case ETH_P_8021Q:
+	case ETH_P_8021AD:
+		bpf_tail_call(skb, &prog_array_init, PARSE_VLAN);
+		break;
+	case ETH_P_MPLS_UC:
+	case ETH_P_MPLS_MC:
+		bpf_tail_call(skb, &prog_array_init, PARSE_MPLS);
+		break;
+	case ETH_P_IP:
+		bpf_tail_call(skb, &prog_array_init, PARSE_IP);
+		break;
+	case ETH_P_IPV6:
+		bpf_tail_call(skb, &prog_array_init, PARSE_IPV6);
+		break;
+	}
+}
+
+SEC("socket")
+int main_prog(struct __sk_buff *skb)
+{
+	__u32 nhoff = ETH_HLEN;
+	__u32 proto = load_half(skb, 12);
+
+	skb->cb[0] = nhoff;
+	parse_eth_proto(skb, proto);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";

linux-7.2.3/samples/bpf/sockex3_user.c

@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <assert.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "sock_example.h"
+#include <unistd.h>
+#include <arpa/inet.h>
+
+struct flow_key_record {
+	__be32 src;
+	__be32 dst;
+	union {
+		__be32 ports;
+		__be16 port16[2];
+	};
+	__u32 ip_proto;
+};
+
+struct pair {
+	__u64 packets;
+	__u64 bytes;
+};
+
+int main(int argc, char **argv)
+{
+	int i, sock, fd, main_prog_fd, hash_map_fd;
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	char filename[256];
+	FILE *f;
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	obj = bpf_object__open_file(filename, NULL);
+	if (libbpf_get_error(obj)) {
+		fprintf(stderr, "ERROR: opening BPF object file failed\n");
+		return 0;
+	}
+
+	/* load BPF program */
+	if (bpf_object__load(obj)) {
+		fprintf(stderr, "ERROR: loading BPF object file failed\n");
+		goto cleanup;
+	}
+
+	hash_map_fd = bpf_object__find_map_fd_by_name(obj, "hash_map");
+	if (hash_map_fd < 0) {
+		fprintf(stderr, "ERROR: finding a map in obj file failed\n");
+		goto cleanup;
+	}
+
+	/* find BPF main program */
+	main_prog_fd = 0;
+	bpf_object__for_each_program(prog, obj) {
+		fd = bpf_program__fd(prog);
+
+		if (!strcmp(bpf_program__name(prog), "main_prog"))
+			main_prog_fd = fd;
+	}
+
+	if (main_prog_fd == 0) {
+		fprintf(stderr, "ERROR: can't find main_prog\n");
+		goto cleanup;
+	}
+
+	sock = open_raw_sock("lo");
+
+	/* attach BPF program to socket */
+	assert(setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &main_prog_fd,
+			  sizeof(__u32)) == 0);
+
+	if (argc > 1)
+		f = popen("ping -4 -c5 localhost", "r");
+	else
+		f = popen("netperf -l 4 localhost", "r");
+	(void) f;
+
+	for (i = 0; i < 5; i++) {
+		struct flow_key_record key = {}, next_key;
+		struct pair value;
+
+		sleep(1);
+		printf("IP     src.port -> dst.port               bytes      packets\n");
+		while (bpf_map_get_next_key(hash_map_fd, &key, &next_key) == 0) {
+			bpf_map_lookup_elem(hash_map_fd, &next_key, &value);
+			printf("%s.%05d -> %s.%05d %12lld %12lld\n",
+			       inet_ntoa((struct in_addr){htonl(next_key.src)}),
+			       next_key.port16[0],
+			       inet_ntoa((struct in_addr){htonl(next_key.dst)}),
+			       next_key.port16[1],
+			       value.bytes, value.packets);
+			key = next_key;
+		}
+	}
+
+cleanup:
+	bpf_object__close(obj);
+	return 0;
+}

linux-7.2.3/samples/bpf/spintest.bpf.c

@@ -0,0 +1,60 @@
+/* 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 "vmlinux.h"
+#include <linux/version.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#ifndef PERF_MAX_STACK_DEPTH
+#define PERF_MAX_STACK_DEPTH         127
+#endif
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, long);
+	__type(value, long);
+	__uint(max_entries, 1024);
+} my_map SEC(".maps");
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_HASH);
+	__uint(key_size, sizeof(long));
+	__uint(value_size, sizeof(long));
+	__uint(max_entries, 1024);
+} my_map2 SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_STACK_TRACE);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, PERF_MAX_STACK_DEPTH * sizeof(u64));
+	__uint(max_entries, 10000);
+} stackmap SEC(".maps");
+
+#define PROG(foo) \
+int foo(struct pt_regs *ctx) \
+{ \
+	long v = PT_REGS_IP(ctx), *val; \
+\
+	val = bpf_map_lookup_elem(&my_map, &v); \
+	bpf_map_update_elem(&my_map, &v, &v, BPF_ANY); \
+	bpf_map_update_elem(&my_map2, &v, &v, BPF_ANY); \
+	bpf_map_delete_elem(&my_map2, &v); \
+	bpf_get_stackid(ctx, &stackmap, BPF_F_REUSE_STACKID); \
+	return 0; \
+}
+
+/* add kprobes to all possible *spin* functions */
+SEC("kprobe.multi/spin_*lock*")PROG(spin_lock)
+SEC("kprobe.multi/*_spin_on_owner")PROG(spin_on_owner)
+SEC("kprobe.multi/_raw_spin_*lock*")PROG(raw_spin_lock)
+
+/* and to inner bpf helpers */
+SEC("kprobe/htab_map_update_elem")PROG(p15)
+SEC("kprobe/__htab_percpu_map_update_elem")PROG(p16)
+SEC("kprobe/htab_map_alloc")PROG(p17)
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;

linux-7.2.3/samples/bpf/spintest_user.c

@@ -0,0 +1,84 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <unistd.h>
+#include <string.h>
+#include <assert.h>
+#include <bpf/libbpf.h>
+#include <bpf/bpf.h>
+#include "trace_helpers.h"
+
+int main(int ac, char **argv)
+{
+	struct bpf_object *obj = NULL;
+	struct bpf_link *links[20];
+	long key, next_key, value;
+	struct bpf_program *prog;
+	int map_fd, i, j = 0;
+	char filename[256];
+	struct ksym *sym;
+
+	if (load_kallsyms()) {
+		printf("failed to process /proc/kallsyms\n");
+		return 2;
+	}
+
+	snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
+	obj = bpf_object__open_file(filename, NULL);
+	if (libbpf_get_error(obj)) {
+		fprintf(stderr, "ERROR: opening BPF object file failed\n");
+		obj = NULL;
+		goto cleanup;
+	}
+
+	/* load BPF program */
+	if (bpf_object__load(obj)) {
+		fprintf(stderr, "ERROR: loading BPF object file failed\n");
+		goto cleanup;
+	}
+
+	map_fd = bpf_object__find_map_fd_by_name(obj, "my_map");
+	if (map_fd < 0) {
+		fprintf(stderr, "ERROR: finding a map in obj file failed\n");
+		goto cleanup;
+	}
+
+	bpf_object__for_each_program(prog, obj) {
+		links[j] = bpf_program__attach(prog);
+		if (libbpf_get_error(links[j])) {
+			fprintf(stderr, "bpf_program__attach failed\n");
+			links[j] = NULL;
+			goto cleanup;
+		}
+		j++;
+	}
+
+	for (i = 0; i < 5; i++) {
+		key = 0;
+		printf("kprobing funcs:");
+		while (bpf_map_get_next_key(map_fd, &key, &next_key) == 0) {
+			bpf_map_lookup_elem(map_fd, &next_key, &value);
+			assert(next_key == value);
+			sym = ksym_search(value);
+			key = next_key;
+			if (!sym) {
+				printf("ksym not found. Is kallsyms loaded?\n");
+				continue;
+			}
+
+			printf(" %s", sym->name);
+		}
+		if (key)
+			printf("\n");
+		key = 0;
+		while (bpf_map_get_next_key(map_fd, &key, &next_key) == 0)
+			bpf_map_delete_elem(map_fd, &next_key);
+		sleep(1);
+	}
+
+cleanup:
+	for (j--; j >= 0; j--)
+		bpf_link__destroy(links[j]);
+
+	bpf_object__close(obj);
+	return 0;
+}

linux-7.2.3/samples/bpf/syscall_nrs.c

@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <uapi/linux/unistd.h>
+#include <linux/kbuild.h>
+
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wmissing-prototypes"
+
+#define SYSNR(_NR) DEFINE(SYS ## _NR, _NR)
+
+void syscall_defines(void)
+{
+	COMMENT("Linux system call numbers.");
+	SYSNR(__NR_write);
+	SYSNR(__NR_read);
+#ifdef __NR_mmap2
+	SYSNR(__NR_mmap2);
+#endif
+#ifdef __NR_mmap
+	SYSNR(__NR_mmap);
+#endif
+
+}
+
+#pragma GCC diagnostic pop

linux-7.2.3/samples/bpf/syscall_tp_kern.c

@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2017 Facebook
+ */
+#include <uapi/linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+#if !defined(__aarch64__)
+struct syscalls_enter_open_args {
+	unsigned long long unused;
+	long syscall_nr;
+	long filename_ptr;
+	long flags;
+	long mode;
+};
+#endif
+
+struct syscalls_exit_open_args {
+	unsigned long long unused;
+	long syscall_nr;
+	long ret;
+};
+
+struct syscalls_enter_open_at_args {
+	unsigned long long unused;
+	long syscall_nr;
+	long long dfd;
+	long filename_ptr;
+	long flags;
+	long mode;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, u32);
+	__type(value, u32);
+	__uint(max_entries, 1);
+} enter_open_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, u32);
+	__type(value, u32);
+	__uint(max_entries, 1);
+} exit_open_map SEC(".maps");
+
+static __always_inline void count(void *map)
+{
+	u32 key = 0;
+	u32 *value, init_val = 1;
+
+	value = bpf_map_lookup_elem(map, &key);
+	if (value)
+		*value += 1;
+	else
+		bpf_map_update_elem(map, &key, &init_val, BPF_NOEXIST);
+}
+
+#if !defined(__aarch64__)
+SEC("tracepoint/syscalls/sys_enter_open")
+int trace_enter_open(struct syscalls_enter_open_args *ctx)
+{
+	count(&enter_open_map);
+	return 0;
+}
+#endif
+
+SEC("tracepoint/syscalls/sys_enter_openat")
+int trace_enter_open_at(struct syscalls_enter_open_at_args *ctx)
+{
+	count(&enter_open_map);
+	return 0;
+}
+
+SEC("tracepoint/syscalls/sys_enter_openat2")
+int trace_enter_open_at2(struct syscalls_enter_open_at_args *ctx)
+{
+	count(&enter_open_map);
+	return 0;
+}
+
+#if !defined(__aarch64__)
+SEC("tracepoint/syscalls/sys_exit_open")
+int trace_enter_exit(struct syscalls_exit_open_args *ctx)
+{
+	count(&exit_open_map);
+	return 0;
+}
+#endif
+
+SEC("tracepoint/syscalls/sys_exit_openat")
+int trace_enter_exit_at(struct syscalls_exit_open_args *ctx)
+{
+	count(&exit_open_map);
+	return 0;
+}
+
+SEC("tracepoint/syscalls/sys_exit_openat2")
+int trace_enter_exit_at2(struct syscalls_exit_open_args *ctx)
+{
+	count(&exit_open_map);
+	return 0;
+}

linux-7.2.3/samples/bpf/syscall_tp_user.c

@@ -0,0 +1,155 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2017 Facebook
+ */
+#include <stdio.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/perf_event.h>
+#include <errno.h>
+#include <bpf/libbpf.h>
+#include <bpf/bpf.h>
+
+/* This program verifies bpf attachment to tracepoint sys_enter_* and sys_exit_*.
+ * This requires kernel CONFIG_FTRACE_SYSCALLS to be set.
+ */
+
+static void usage(const char *cmd)
+{
+	printf("USAGE: %s [-i nr_tests] [-h]\n", cmd);
+	printf("       -i nr_tests      # rounds of test to run\n");
+	printf("       -h               # help\n");
+}
+
+static void verify_map(int map_id)
+{
+	__u32 key = 0;
+	__u32 val;
+
+	if (bpf_map_lookup_elem(map_id, &key, &val) != 0) {
+		fprintf(stderr, "map_lookup failed: %s\n", strerror(errno));
+		return;
+	}
+	if (val == 0) {
+		fprintf(stderr, "failed: map #%d returns value 0\n", map_id);
+		return;
+	}
+
+	printf("verify map:%d val: %d\n", map_id, val);
+
+	val = 0;
+	if (bpf_map_update_elem(map_id, &key, &val, BPF_ANY) != 0) {
+		fprintf(stderr, "map_update failed: %s\n", strerror(errno));
+		return;
+	}
+}
+
+static int test(char *filename, int nr_tests)
+{
+	int map0_fds[nr_tests], map1_fds[nr_tests], fd, i, j = 0;
+	struct bpf_link **links = NULL;
+	struct bpf_object *objs[nr_tests];
+	struct bpf_program *prog;
+
+	for (i = 0; i < nr_tests; i++) {
+		objs[i] = bpf_object__open_file(filename, NULL);
+		if (libbpf_get_error(objs[i])) {
+			fprintf(stderr, "opening BPF object file failed\n");
+			objs[i] = NULL;
+			goto cleanup;
+		}
+
+		/* One-time initialization */
+		if (!links) {
+			int nr_progs = 0;
+
+			bpf_object__for_each_program(prog, objs[i])
+				nr_progs += 1;
+
+			links = calloc(nr_progs * nr_tests, sizeof(struct bpf_link *));
+
+			if (!links)
+				goto cleanup;
+		}
+
+		/* load BPF program */
+		if (bpf_object__load(objs[i])) {
+			fprintf(stderr, "loading BPF object file failed\n");
+			goto cleanup;
+		}
+
+		map0_fds[i] = bpf_object__find_map_fd_by_name(objs[i],
+							      "enter_open_map");
+		map1_fds[i] = bpf_object__find_map_fd_by_name(objs[i],
+							      "exit_open_map");
+		if (map0_fds[i] < 0 || map1_fds[i] < 0) {
+			fprintf(stderr, "finding a map in obj file failed\n");
+			goto cleanup;
+		}
+
+		bpf_object__for_each_program(prog, objs[i]) {
+			links[j] = bpf_program__attach(prog);
+			if (libbpf_get_error(links[j])) {
+				fprintf(stderr, "bpf_program__attach failed\n");
+				links[j] = NULL;
+				goto cleanup;
+			}
+			j++;
+		}
+		printf("prog #%d: map ids %d %d\n", i, map0_fds[i], map1_fds[i]);
+	}
+
+	/* current load_bpf_file has perf_event_open default pid = -1
+	 * and cpu = 0, which permits attached bpf execution on
+	 * all cpus for all pid's. bpf program execution ignores
+	 * cpu affinity.
+	 */
+	/* trigger some "open" operations */
+	fd = open(filename, O_RDONLY);
+	if (fd < 0) {
+		fprintf(stderr, "open failed: %s\n", strerror(errno));
+		return 1;
+	}
+	close(fd);
+
+	/* verify the map */
+	for (i = 0; i < nr_tests; i++) {
+		verify_map(map0_fds[i]);
+		verify_map(map1_fds[i]);
+	}
+
+cleanup:
+	if (links) {
+		for (j--; j >= 0; j--)
+			bpf_link__destroy(links[j]);
+
+		free(links);
+	}
+
+	for (i--; i >= 0; i--)
+		bpf_object__close(objs[i]);
+	return 0;
+}
+
+int main(int argc, char **argv)
+{
+	int opt, nr_tests = 1;
+	char filename[256];
+
+	while ((opt = getopt(argc, argv, "i:h")) != -1) {
+		switch (opt) {
+		case 'i':
+			nr_tests = atoi(optarg);
+			break;
+		case 'h':
+		default:
+			usage(argv[0]);
+			return 0;
+		}
+	}
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	return test(filename, nr_tests);
+}

linux-7.2.3/samples/bpf/task_fd_query_kern.c

@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/version.h>
+#include <linux/ptrace.h>
+#include <uapi/linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+SEC("kprobe/blk_mq_start_request")
+int bpf_prog1(struct pt_regs *ctx)
+{
+	return 0;
+}
+
+SEC("kretprobe/__blk_account_io_done")
+int bpf_prog2(struct pt_regs *ctx)
+{
+	return 0;
+}
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;

linux-7.2.3/samples/bpf/task_fd_query_user.c

@@ -0,0 +1,423 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <unistd.h>
+#include <stdbool.h>
+#include <string.h>
+#include <stdint.h>
+#include <fcntl.h>
+#include <linux/bpf.h>
+#include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <linux/perf_event.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "bpf_util.h"
+#include "perf-sys.h"
+#include "trace_helpers.h"
+
+static struct bpf_program *progs[2];
+static struct bpf_link *links[2];
+
+#define CHECK_PERROR_RET(condition) ({			\
+	int __ret = !!(condition);			\
+	if (__ret) {					\
+		printf("FAIL: %s:\n", __func__);	\
+		perror("    ");			\
+		return -1;				\
+	}						\
+})
+
+#define CHECK_AND_RET(condition) ({			\
+	int __ret = !!(condition);			\
+	if (__ret)					\
+		return -1;				\
+})
+
+static __u64 ptr_to_u64(void *ptr)
+{
+	return (__u64) (unsigned long) ptr;
+}
+
+#define PMU_TYPE_FILE "/sys/bus/event_source/devices/%s/type"
+static int bpf_find_probe_type(const char *event_type)
+{
+	char buf[256];
+	int fd, ret;
+
+	ret = snprintf(buf, sizeof(buf), PMU_TYPE_FILE, event_type);
+	CHECK_PERROR_RET(ret < 0 || ret >= sizeof(buf));
+
+	fd = open(buf, O_RDONLY);
+	CHECK_PERROR_RET(fd < 0);
+
+	ret = read(fd, buf, sizeof(buf));
+	close(fd);
+	CHECK_PERROR_RET(ret < 0 || ret >= sizeof(buf));
+
+	errno = 0;
+	ret = (int)strtol(buf, NULL, 10);
+	CHECK_PERROR_RET(errno);
+	return ret;
+}
+
+#define PMU_RETPROBE_FILE "/sys/bus/event_source/devices/%s/format/retprobe"
+static int bpf_get_retprobe_bit(const char *event_type)
+{
+	char buf[256];
+	int fd, ret;
+
+	ret = snprintf(buf, sizeof(buf), PMU_RETPROBE_FILE, event_type);
+	CHECK_PERROR_RET(ret < 0 || ret >= sizeof(buf));
+
+	fd = open(buf, O_RDONLY);
+	CHECK_PERROR_RET(fd < 0);
+
+	ret = read(fd, buf, sizeof(buf));
+	close(fd);
+	CHECK_PERROR_RET(ret < 0 || ret >= sizeof(buf));
+	CHECK_PERROR_RET(strlen(buf) < strlen("config:"));
+
+	errno = 0;
+	ret = (int)strtol(buf + strlen("config:"), NULL, 10);
+	CHECK_PERROR_RET(errno);
+	return ret;
+}
+
+static int test_debug_fs_kprobe(int link_idx, const char *fn_name,
+				__u32 expected_fd_type)
+{
+	__u64 probe_offset, probe_addr;
+	__u32 len, prog_id, fd_type;
+	int err, event_fd;
+	char buf[256];
+
+	len = sizeof(buf);
+	event_fd = bpf_link__fd(links[link_idx]);
+	err = bpf_task_fd_query(getpid(), event_fd, 0, buf, &len,
+				&prog_id, &fd_type, &probe_offset,
+				&probe_addr);
+	if (err < 0) {
+		printf("FAIL: %s, for event_fd idx %d, fn_name %s\n",
+		       __func__, link_idx, fn_name);
+		perror("    :");
+		return -1;
+	}
+	if (strcmp(buf, fn_name) != 0 ||
+	    fd_type != expected_fd_type ||
+	    probe_offset != 0x0 || probe_addr != 0x0) {
+		printf("FAIL: bpf_trace_event_query(event_fd[%d]):\n",
+		       link_idx);
+		printf("buf: %s, fd_type: %u, probe_offset: 0x%llx,"
+		       " probe_addr: 0x%llx\n",
+		       buf, fd_type, probe_offset, probe_addr);
+		return -1;
+	}
+	return 0;
+}
+
+static int test_nondebug_fs_kuprobe_common(const char *event_type,
+	const char *name, __u64 offset, __u64 addr, bool is_return,
+	char *buf, __u32 *buf_len, __u32 *prog_id, __u32 *fd_type,
+	__u64 *probe_offset, __u64 *probe_addr)
+{
+	int is_return_bit = bpf_get_retprobe_bit(event_type);
+	int type = bpf_find_probe_type(event_type);
+	struct perf_event_attr attr = {};
+	struct bpf_link *link;
+	int fd, err = -1;
+
+	if (type < 0 || is_return_bit < 0) {
+		printf("FAIL: %s incorrect type (%d) or is_return_bit (%d)\n",
+			__func__, type, is_return_bit);
+		return err;
+	}
+
+	attr.sample_period = 1;
+	attr.wakeup_events = 1;
+	if (is_return)
+		attr.config |= 1 << is_return_bit;
+
+	if (name) {
+		attr.config1 = ptr_to_u64((void *)name);
+		attr.config2 = offset;
+	} else {
+		attr.config1 = 0;
+		attr.config2 = addr;
+	}
+	attr.size = sizeof(attr);
+	attr.type = type;
+
+	fd = sys_perf_event_open(&attr, -1, 0, -1, 0);
+	link = bpf_program__attach_perf_event(progs[0], fd);
+	if (libbpf_get_error(link)) {
+		printf("ERROR: bpf_program__attach_perf_event failed\n");
+		link = NULL;
+		close(fd);
+		goto cleanup;
+	}
+
+	CHECK_PERROR_RET(bpf_task_fd_query(getpid(), fd, 0, buf, buf_len,
+			 prog_id, fd_type, probe_offset, probe_addr) < 0);
+	err = 0;
+
+cleanup:
+	bpf_link__destroy(link);
+	return err;
+}
+
+static int test_nondebug_fs_probe(const char *event_type, const char *name,
+				  __u64 offset, __u64 addr, bool is_return,
+				  __u32 expected_fd_type,
+				  __u32 expected_ret_fd_type,
+				  char *buf, __u32 buf_len)
+{
+	__u64 probe_offset, probe_addr;
+	__u32 prog_id, fd_type;
+	int err;
+
+	err = test_nondebug_fs_kuprobe_common(event_type, name,
+					      offset, addr, is_return,
+					      buf, &buf_len, &prog_id,
+					      &fd_type, &probe_offset,
+					      &probe_addr);
+	if (err < 0) {
+		printf("FAIL: %s, "
+		       "for name %s, offset 0x%llx, addr 0x%llx, is_return %d\n",
+		       __func__, name ? name : "", offset, addr, is_return);
+		perror("    :");
+		return -1;
+	}
+	if ((is_return && fd_type != expected_ret_fd_type) ||
+	    (!is_return && fd_type != expected_fd_type)) {
+		printf("FAIL: %s, incorrect fd_type %u\n",
+		       __func__, fd_type);
+		return -1;
+	}
+	if (name) {
+		if (strcmp(name, buf) != 0) {
+			printf("FAIL: %s, incorrect buf %s\n", __func__, buf);
+			return -1;
+		}
+		if (probe_offset != offset) {
+			printf("FAIL: %s, incorrect probe_offset 0x%llx\n",
+			       __func__, probe_offset);
+			return -1;
+		}
+	} else {
+		if (buf_len != 0) {
+			printf("FAIL: %s, incorrect buf %p\n",
+			       __func__, buf);
+			return -1;
+		}
+
+		if (probe_addr != addr) {
+			printf("FAIL: %s, incorrect probe_addr 0x%llx\n",
+			       __func__, probe_addr);
+			return -1;
+		}
+	}
+	return 0;
+}
+
+static int test_debug_fs_uprobe(char *binary_path, long offset, bool is_return)
+{
+	char buf[256], event_alias[sizeof("test_1234567890")];
+	const char *event_type = "uprobe";
+	struct perf_event_attr attr = {};
+	__u64 probe_offset, probe_addr;
+	__u32 len, prog_id, fd_type;
+	int err = -1, res, kfd, efd;
+	struct bpf_link *link;
+	ssize_t bytes;
+
+	snprintf(buf, sizeof(buf), "/sys/kernel/tracing/%s_events",
+		 event_type);
+	kfd = open(buf, O_WRONLY | O_TRUNC, 0);
+	CHECK_PERROR_RET(kfd < 0);
+
+	res = snprintf(event_alias, sizeof(event_alias), "test_%d", getpid());
+	CHECK_PERROR_RET(res < 0 || res >= sizeof(event_alias));
+
+	res = snprintf(buf, sizeof(buf), "%c:%ss/%s %s:0x%lx",
+		       is_return ? 'r' : 'p', event_type, event_alias,
+		       binary_path, offset);
+	CHECK_PERROR_RET(res < 0 || res >= sizeof(buf));
+	CHECK_PERROR_RET(write(kfd, buf, strlen(buf)) < 0);
+
+	close(kfd);
+	kfd = -1;
+
+	snprintf(buf, sizeof(buf), "/sys/kernel/tracing/events/%ss/%s/id",
+		 event_type, event_alias);
+	efd = open(buf, O_RDONLY, 0);
+	CHECK_PERROR_RET(efd < 0);
+
+	bytes = read(efd, buf, sizeof(buf));
+	CHECK_PERROR_RET(bytes <= 0 || bytes >= sizeof(buf));
+	close(efd);
+	buf[bytes] = '\0';
+
+	attr.config = strtol(buf, NULL, 0);
+	attr.type = PERF_TYPE_TRACEPOINT;
+	attr.sample_period = 1;
+	attr.wakeup_events = 1;
+
+	kfd = sys_perf_event_open(&attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC);
+	link = bpf_program__attach_perf_event(progs[0], kfd);
+	if (libbpf_get_error(link)) {
+		printf("ERROR: bpf_program__attach_perf_event failed\n");
+		link = NULL;
+		close(kfd);
+		goto cleanup;
+	}
+
+	len = sizeof(buf);
+	err = bpf_task_fd_query(getpid(), kfd, 0, buf, &len,
+				&prog_id, &fd_type, &probe_offset,
+				&probe_addr);
+	if (err < 0) {
+		printf("FAIL: %s, binary_path %s\n", __func__, binary_path);
+		perror("    :");
+		return -1;
+	}
+	if ((is_return && fd_type != BPF_FD_TYPE_URETPROBE) ||
+	    (!is_return && fd_type != BPF_FD_TYPE_UPROBE)) {
+		printf("FAIL: %s, incorrect fd_type %u\n", __func__,
+		       fd_type);
+		return -1;
+	}
+	if (strcmp(binary_path, buf) != 0) {
+		printf("FAIL: %s, incorrect buf %s\n", __func__, buf);
+		return -1;
+	}
+	if (probe_offset != offset) {
+		printf("FAIL: %s, incorrect probe_offset 0x%llx\n", __func__,
+		       probe_offset);
+		return -1;
+	}
+	err = 0;
+
+cleanup:
+	bpf_link__destroy(link);
+	return err;
+}
+
+int main(int argc, char **argv)
+{
+	extern char __executable_start;
+	char filename[256], buf[256];
+	__u64 uprobe_file_offset;
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	int i = 0, err = -1;
+
+	if (load_kallsyms()) {
+		printf("failed to process /proc/kallsyms\n");
+		return err;
+	}
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+	obj = bpf_object__open_file(filename, NULL);
+	if (libbpf_get_error(obj)) {
+		fprintf(stderr, "ERROR: opening BPF object file failed\n");
+		return err;
+	}
+
+	/* load BPF program */
+	if (bpf_object__load(obj)) {
+		fprintf(stderr, "ERROR: loading BPF object file failed\n");
+		goto cleanup;
+	}
+
+	bpf_object__for_each_program(prog, obj) {
+		progs[i] = prog;
+		links[i] = bpf_program__attach(progs[i]);
+		if (libbpf_get_error(links[i])) {
+			fprintf(stderr, "ERROR: bpf_program__attach failed\n");
+			links[i] = NULL;
+			goto cleanup;
+		}
+		i++;
+	}
+
+	/* test two functions in the corresponding *_kern.c file */
+	CHECK_AND_RET(test_debug_fs_kprobe(0, "blk_mq_start_request",
+					   BPF_FD_TYPE_KPROBE));
+	CHECK_AND_RET(test_debug_fs_kprobe(1, "__blk_account_io_done",
+					   BPF_FD_TYPE_KRETPROBE));
+
+	/* test nondebug fs kprobe */
+	CHECK_AND_RET(test_nondebug_fs_probe("kprobe", "bpf_check", 0x0, 0x0,
+					     false, BPF_FD_TYPE_KPROBE,
+					     BPF_FD_TYPE_KRETPROBE,
+					     buf, sizeof(buf)));
+#ifdef __x86_64__
+	/* set a kprobe on "bpf_check + 0x5", which is x64 specific */
+	CHECK_AND_RET(test_nondebug_fs_probe("kprobe", "bpf_check", 0x5, 0x0,
+					     false, BPF_FD_TYPE_KPROBE,
+					     BPF_FD_TYPE_KRETPROBE,
+					     buf, sizeof(buf)));
+#endif
+	CHECK_AND_RET(test_nondebug_fs_probe("kprobe", "bpf_check", 0x0, 0x0,
+					     true, BPF_FD_TYPE_KPROBE,
+					     BPF_FD_TYPE_KRETPROBE,
+					     buf, sizeof(buf)));
+	CHECK_AND_RET(test_nondebug_fs_probe("kprobe", NULL, 0x0,
+					     ksym_get_addr("bpf_check"), false,
+					     BPF_FD_TYPE_KPROBE,
+					     BPF_FD_TYPE_KRETPROBE,
+					     buf, sizeof(buf)));
+	CHECK_AND_RET(test_nondebug_fs_probe("kprobe", NULL, 0x0,
+					     ksym_get_addr("bpf_check"), false,
+					     BPF_FD_TYPE_KPROBE,
+					     BPF_FD_TYPE_KRETPROBE,
+					     NULL, 0));
+	CHECK_AND_RET(test_nondebug_fs_probe("kprobe", NULL, 0x0,
+					     ksym_get_addr("bpf_check"), true,
+					     BPF_FD_TYPE_KPROBE,
+					     BPF_FD_TYPE_KRETPROBE,
+					     buf, sizeof(buf)));
+	CHECK_AND_RET(test_nondebug_fs_probe("kprobe", NULL, 0x0,
+					     ksym_get_addr("bpf_check"), true,
+					     BPF_FD_TYPE_KPROBE,
+					     BPF_FD_TYPE_KRETPROBE,
+					     0, 0));
+
+	/* test nondebug fs uprobe */
+	/* the calculation of uprobe file offset is based on gcc 7.3.1 on x64
+	 * and the default linker script, which defines __executable_start as
+	 * the start of the .text section. The calculation could be different
+	 * on different systems with different compilers. The right way is
+	 * to parse the ELF file. We took a shortcut here.
+	 */
+	uprobe_file_offset = (unsigned long)main - (unsigned long)&__executable_start;
+	CHECK_AND_RET(test_nondebug_fs_probe("uprobe", (char *)argv[0],
+					     uprobe_file_offset, 0x0, false,
+					     BPF_FD_TYPE_UPROBE,
+					     BPF_FD_TYPE_URETPROBE,
+					     buf, sizeof(buf)));
+	CHECK_AND_RET(test_nondebug_fs_probe("uprobe", (char *)argv[0],
+					     uprobe_file_offset, 0x0, true,
+					     BPF_FD_TYPE_UPROBE,
+					     BPF_FD_TYPE_URETPROBE,
+					     buf, sizeof(buf)));
+
+	/* test debug fs uprobe */
+	CHECK_AND_RET(test_debug_fs_uprobe((char *)argv[0], uprobe_file_offset,
+					   false));
+	CHECK_AND_RET(test_debug_fs_uprobe((char *)argv[0], uprobe_file_offset,
+					   true));
+	err = 0;
+
+cleanup:
+	for (i--; i >= 0; i--)
+		bpf_link__destroy(links[i]);
+
+	bpf_object__close(obj);
+	return err;
+}

linux-7.2.3/samples/bpf/tc_l2_redirect.sh

@@ -0,0 +1,177 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+[[ -z $TC ]] && TC='tc'
+[[ -z $IP ]] && IP='ip'
+
+REDIRECT_USER='./tc_l2_redirect'
+REDIRECT_BPF='./tc_l2_redirect_kern.o'
+
+RP_FILTER=$(< /proc/sys/net/ipv4/conf/all/rp_filter)
+IPV6_DISABLED=$(< /proc/sys/net/ipv6/conf/all/disable_ipv6)
+IPV6_FORWARDING=$(< /proc/sys/net/ipv6/conf/all/forwarding)
+
+function config_common {
+	local tun_type=$1
+
+	$IP netns add ns1
+	$IP netns add ns2
+	$IP link add ve1 type veth peer name vens1
+	$IP link add ve2 type veth peer name vens2
+	$IP link set dev ve1 up
+	$IP link set dev ve2 up
+	$IP link set dev ve1 mtu 1500
+	$IP link set dev ve2 mtu 1500
+	$IP link set dev vens1 netns ns1
+	$IP link set dev vens2 netns ns2
+
+	$IP -n ns1 link set dev lo up
+	$IP -n ns1 link set dev vens1 up
+	$IP -n ns1 addr add 10.1.1.101/24 dev vens1
+	$IP -n ns1 addr add 2401:db01::65/64 dev vens1 nodad
+	$IP -n ns1 route add default via 10.1.1.1 dev vens1
+	$IP -n ns1 route add default via 2401:db01::1 dev vens1
+
+	$IP -n ns2 link set dev lo up
+	$IP -n ns2 link set dev vens2 up
+	$IP -n ns2 addr add 10.2.1.102/24 dev vens2
+	$IP -n ns2 addr add 2401:db02::66/64 dev vens2 nodad
+	$IP -n ns2 addr add 10.10.1.102 dev lo
+	$IP -n ns2 addr add 2401:face::66/64 dev lo nodad
+	$IP -n ns2 link add ipt2 type ipip local 10.2.1.102 remote 10.2.1.1
+	$IP -n ns2 link add ip6t2 type ip6tnl mode any local 2401:db02::66 remote 2401:db02::1
+	$IP -n ns2 link set dev ipt2 up
+	$IP -n ns2 link set dev ip6t2 up
+	$IP netns exec ns2 $TC qdisc add dev vens2 clsact
+	$IP netns exec ns2 $TC filter add dev vens2 ingress bpf da obj $REDIRECT_BPF sec drop_non_tun_vip
+	if [[ $tun_type == "ipip" ]]; then
+		$IP -n ns2 route add 10.1.1.0/24 dev ipt2
+		$IP netns exec ns2 sysctl -q -w net.ipv4.conf.all.rp_filter=0
+		$IP netns exec ns2 sysctl -q -w net.ipv4.conf.ipt2.rp_filter=0
+	else
+		$IP -n ns2 route add 10.1.1.0/24 dev ip6t2
+		$IP -n ns2 route add 2401:db01::/64 dev ip6t2
+		$IP netns exec ns2 sysctl -q -w net.ipv4.conf.all.rp_filter=0
+		$IP netns exec ns2 sysctl -q -w net.ipv4.conf.ip6t2.rp_filter=0
+	fi
+
+	$IP addr add 10.1.1.1/24 dev ve1
+	$IP addr add 2401:db01::1/64 dev ve1 nodad
+	$IP addr add 10.2.1.1/24 dev ve2
+	$IP addr add 2401:db02::1/64 dev ve2 nodad
+
+	$TC qdisc add dev ve2 clsact
+	$TC filter add dev ve2 ingress bpf da obj $REDIRECT_BPF sec l2_to_iptun_ingress_forward
+
+	sysctl -q -w net.ipv4.conf.all.rp_filter=0
+	sysctl -q -w net.ipv6.conf.all.forwarding=1
+	sysctl -q -w net.ipv6.conf.all.disable_ipv6=0
+}
+
+function cleanup {
+	set +e
+	[[ -z $DEBUG ]] || set +x
+	$IP netns delete ns1 >& /dev/null
+	$IP netns delete ns2 >& /dev/null
+	$IP link del ve1 >& /dev/null
+	$IP link del ve2 >& /dev/null
+	$IP link del ipt >& /dev/null
+	$IP link del ip6t >& /dev/null
+	sysctl -q -w net.ipv4.conf.all.rp_filter=$RP_FILTER
+	sysctl -q -w net.ipv6.conf.all.forwarding=$IPV6_FORWARDING
+	sysctl -q -w net.ipv6.conf.all.disable_ipv6=$IPV6_DISABLED
+	rm -f /sys/fs/bpf/tc/globals/tun_iface
+	[[ -z $DEBUG ]] || set -x
+	set -e
+}
+
+function l2_to_ipip {
+	echo -n "l2_to_ipip $1: "
+
+	local dir=$1
+
+	config_common ipip
+
+	$IP link add ipt type ipip external
+	$IP link set dev ipt up
+	sysctl -q -w net.ipv4.conf.ipt.rp_filter=0
+	sysctl -q -w net.ipv4.conf.ipt.forwarding=1
+
+	if [[ $dir == "egress" ]]; then
+		$IP route add 10.10.1.0/24 via 10.2.1.102 dev ve2
+		$TC filter add dev ve2 egress bpf da obj $REDIRECT_BPF sec l2_to_iptun_ingress_redirect
+		sysctl -q -w net.ipv4.conf.ve1.forwarding=1
+	else
+		$TC qdisc add dev ve1 clsact
+		$TC filter add dev ve1 ingress bpf da obj $REDIRECT_BPF sec l2_to_iptun_ingress_redirect
+	fi
+
+	$REDIRECT_USER -U /sys/fs/bpf/tc/globals/tun_iface -i $(< /sys/class/net/ipt/ifindex)
+
+	$IP netns exec ns1 ping -c1 10.10.1.102 >& /dev/null
+
+	if [[ $dir == "egress" ]]; then
+		# test direct egress to ve2 (i.e. not forwarding from
+		# ve1 to ve2).
+		ping -c1 10.10.1.102 >& /dev/null
+	fi
+
+	cleanup
+
+	echo "OK"
+}
+
+function l2_to_ip6tnl {
+	echo -n "l2_to_ip6tnl $1: "
+
+	local dir=$1
+
+	config_common ip6tnl
+
+	$IP link add ip6t type ip6tnl mode any external
+	$IP link set dev ip6t up
+	sysctl -q -w net.ipv4.conf.ip6t.rp_filter=0
+	sysctl -q -w net.ipv4.conf.ip6t.forwarding=1
+
+	if [[ $dir == "egress" ]]; then
+		$IP route add 10.10.1.0/24 via 10.2.1.102 dev ve2
+		$IP route add 2401:face::/64 via 2401:db02::66 dev ve2
+		$TC filter add dev ve2 egress bpf da obj $REDIRECT_BPF sec l2_to_ip6tun_ingress_redirect
+		sysctl -q -w net.ipv4.conf.ve1.forwarding=1
+	else
+		$TC qdisc add dev ve1 clsact
+		$TC filter add dev ve1 ingress bpf da obj $REDIRECT_BPF sec l2_to_ip6tun_ingress_redirect
+	fi
+
+	$REDIRECT_USER -U /sys/fs/bpf/tc/globals/tun_iface -i $(< /sys/class/net/ip6t/ifindex)
+
+	$IP netns exec ns1 ping -c1 10.10.1.102 >& /dev/null
+	$IP netns exec ns1 ping -6 -c1 2401:face::66 >& /dev/null
+
+	if [[ $dir == "egress" ]]; then
+		# test direct egress to ve2 (i.e. not forwarding from
+		# ve1 to ve2).
+		ping -c1 10.10.1.102 >& /dev/null
+		ping -6 -c1 2401:face::66 >& /dev/null
+	fi
+
+	cleanup
+
+	echo "OK"
+}
+
+cleanup
+test_names="l2_to_ipip l2_to_ip6tnl"
+test_dirs="ingress egress"
+if [[ $# -ge 2 ]]; then
+	test_names=$1
+	test_dirs=$2
+elif [[ $# -ge 1 ]]; then
+	test_names=$1
+fi
+
+for t in $test_names; do
+	for d in $test_dirs; do
+		$t $d
+	done
+done

linux-7.2.3/samples/bpf/tc_l2_redirect_kern.c

@@ -0,0 +1,231 @@
+/* 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 KBUILD_MODNAME "foo"
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <uapi/linux/ipv6.h>
+#include <uapi/linux/in.h>
+#include <uapi/linux/tcp.h>
+#include <uapi/linux/filter.h>
+#include <uapi/linux/pkt_cls.h>
+#include <net/ipv6.h>
+#include <bpf/bpf_helpers.h>
+
+#define _htonl __builtin_bswap32
+
+#define PIN_GLOBAL_NS		2
+struct bpf_elf_map {
+	__u32 type;
+	__u32 size_key;
+	__u32 size_value;
+	__u32 max_elem;
+	__u32 flags;
+	__u32 id;
+	__u32 pinning;
+};
+
+/* copy of 'struct ethhdr' without __packed */
+struct eth_hdr {
+	unsigned char   h_dest[ETH_ALEN];
+	unsigned char   h_source[ETH_ALEN];
+	unsigned short  h_proto;
+};
+
+struct bpf_elf_map SEC("maps") tun_iface = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.size_key = sizeof(int),
+	.size_value = sizeof(int),
+	.pinning = PIN_GLOBAL_NS,
+	.max_elem = 1,
+};
+
+static __always_inline bool is_vip_addr(__be16 eth_proto, __be32 daddr)
+{
+	if (eth_proto == htons(ETH_P_IP))
+		return (_htonl(0xffffff00) & daddr) == _htonl(0x0a0a0100);
+	else if (eth_proto == htons(ETH_P_IPV6))
+		return (daddr == _htonl(0x2401face));
+
+	return false;
+}
+
+SEC("l2_to_iptun_ingress_forward")
+int _l2_to_iptun_ingress_forward(struct __sk_buff *skb)
+{
+	void *data = (void *)(long)skb->data;
+	struct eth_hdr *eth = data;
+	void *data_end = (void *)(long)skb->data_end;
+	int key = 0, *ifindex;
+
+	if (data + sizeof(*eth) > data_end)
+		return TC_ACT_OK;
+
+	ifindex = bpf_map_lookup_elem(&tun_iface, &key);
+	if (!ifindex)
+		return TC_ACT_OK;
+
+	if (eth->h_proto == htons(ETH_P_IP)) {
+		char fmt4[] = "ingress forward to ifindex:%d daddr4:%x\n";
+		struct iphdr *iph = data + sizeof(*eth);
+
+		if (data + sizeof(*eth) + sizeof(*iph) > data_end)
+			return TC_ACT_OK;
+
+		if (iph->protocol != IPPROTO_IPIP)
+			return TC_ACT_OK;
+
+		bpf_trace_printk(fmt4, sizeof(fmt4), *ifindex,
+				 _htonl(iph->daddr));
+		return bpf_redirect(*ifindex, BPF_F_INGRESS);
+	} else if (eth->h_proto == htons(ETH_P_IPV6)) {
+		char fmt6[] = "ingress forward to ifindex:%d daddr6:%x::%x\n";
+		struct ipv6hdr *ip6h = data + sizeof(*eth);
+
+		if (data + sizeof(*eth) + sizeof(*ip6h) > data_end)
+			return TC_ACT_OK;
+
+		if (ip6h->nexthdr != IPPROTO_IPIP &&
+		    ip6h->nexthdr != IPPROTO_IPV6)
+			return TC_ACT_OK;
+
+		bpf_trace_printk(fmt6, sizeof(fmt6), *ifindex,
+				 _htonl(ip6h->daddr.s6_addr32[0]),
+				 _htonl(ip6h->daddr.s6_addr32[3]));
+		return bpf_redirect(*ifindex, BPF_F_INGRESS);
+	}
+
+	return TC_ACT_OK;
+}
+
+SEC("l2_to_iptun_ingress_redirect")
+int _l2_to_iptun_ingress_redirect(struct __sk_buff *skb)
+{
+	struct bpf_tunnel_key tkey = {};
+	void *data = (void *)(long)skb->data;
+	struct eth_hdr *eth = data;
+	void *data_end = (void *)(long)skb->data_end;
+	int key = 0, *ifindex;
+
+	if (data + sizeof(*eth) > data_end)
+		return TC_ACT_OK;
+
+	ifindex = bpf_map_lookup_elem(&tun_iface, &key);
+	if (!ifindex)
+		return TC_ACT_OK;
+
+	if (eth->h_proto == htons(ETH_P_IP)) {
+		char fmt4[] = "e/ingress redirect daddr4:%x to ifindex:%d\n";
+		struct iphdr *iph = data + sizeof(*eth);
+		__be32 daddr = iph->daddr;
+
+		if (data + sizeof(*eth) + sizeof(*iph) > data_end)
+			return TC_ACT_OK;
+
+		if (!is_vip_addr(eth->h_proto, daddr))
+			return TC_ACT_OK;
+
+		bpf_trace_printk(fmt4, sizeof(fmt4), _htonl(daddr), *ifindex);
+	} else {
+		return TC_ACT_OK;
+	}
+
+	tkey.tunnel_id = 10000;
+	tkey.tunnel_ttl = 64;
+	tkey.remote_ipv4 = 0x0a020166; /* 10.2.1.102 */
+	bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), 0);
+	return bpf_redirect(*ifindex, 0);
+}
+
+SEC("l2_to_ip6tun_ingress_redirect")
+int _l2_to_ip6tun_ingress_redirect(struct __sk_buff *skb)
+{
+	struct bpf_tunnel_key tkey = {};
+	void *data = (void *)(long)skb->data;
+	struct eth_hdr *eth = data;
+	void *data_end = (void *)(long)skb->data_end;
+	int key = 0, *ifindex;
+
+	if (data + sizeof(*eth) > data_end)
+		return TC_ACT_OK;
+
+	ifindex = bpf_map_lookup_elem(&tun_iface, &key);
+	if (!ifindex)
+		return TC_ACT_OK;
+
+	if (eth->h_proto == htons(ETH_P_IP)) {
+		char fmt4[] = "e/ingress redirect daddr4:%x to ifindex:%d\n";
+		struct iphdr *iph = data + sizeof(*eth);
+
+		if (data + sizeof(*eth) + sizeof(*iph) > data_end)
+			return TC_ACT_OK;
+
+		if (!is_vip_addr(eth->h_proto, iph->daddr))
+			return TC_ACT_OK;
+
+		bpf_trace_printk(fmt4, sizeof(fmt4), _htonl(iph->daddr),
+				 *ifindex);
+	} else if (eth->h_proto == htons(ETH_P_IPV6)) {
+		char fmt6[] = "e/ingress redirect daddr6:%x to ifindex:%d\n";
+		struct ipv6hdr *ip6h = data + sizeof(*eth);
+
+		if (data + sizeof(*eth) + sizeof(*ip6h) > data_end)
+			return TC_ACT_OK;
+
+		if (!is_vip_addr(eth->h_proto, ip6h->daddr.s6_addr32[0]))
+			return TC_ACT_OK;
+
+		bpf_trace_printk(fmt6, sizeof(fmt6),
+				 _htonl(ip6h->daddr.s6_addr32[0]), *ifindex);
+	} else {
+		return TC_ACT_OK;
+	}
+
+	tkey.tunnel_id = 10000;
+	tkey.tunnel_ttl = 64;
+	/* 2401:db02:0:0:0:0:0:66 */
+	tkey.remote_ipv6[0] = _htonl(0x2401db02);
+	tkey.remote_ipv6[1] = 0;
+	tkey.remote_ipv6[2] = 0;
+	tkey.remote_ipv6[3] = _htonl(0x00000066);
+	bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), BPF_F_TUNINFO_IPV6);
+	return bpf_redirect(*ifindex, 0);
+}
+
+SEC("drop_non_tun_vip")
+int _drop_non_tun_vip(struct __sk_buff *skb)
+{
+	void *data = (void *)(long)skb->data;
+	struct eth_hdr *eth = data;
+	void *data_end = (void *)(long)skb->data_end;
+
+	if (data + sizeof(*eth) > data_end)
+		return TC_ACT_OK;
+
+	if (eth->h_proto == htons(ETH_P_IP)) {
+		struct iphdr *iph = data + sizeof(*eth);
+
+		if (data + sizeof(*eth) + sizeof(*iph) > data_end)
+			return TC_ACT_OK;
+
+		if (is_vip_addr(eth->h_proto, iph->daddr))
+			return TC_ACT_SHOT;
+	} else if (eth->h_proto == htons(ETH_P_IPV6)) {
+		struct ipv6hdr *ip6h = data + sizeof(*eth);
+
+		if (data + sizeof(*eth) + sizeof(*ip6h) > data_end)
+			return TC_ACT_OK;
+
+		if (is_vip_addr(eth->h_proto, ip6h->daddr.s6_addr32[0]))
+			return TC_ACT_SHOT;
+	}
+
+	return TC_ACT_OK;
+}
+
+char _license[] SEC("license") = "GPL";

linux-7.2.3/samples/bpf/tc_l2_redirect_user.c

@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2016 Facebook
+ */
+#include <linux/unistd.h>
+#include <linux/bpf.h>
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <string.h>
+#include <errno.h>
+
+#include <bpf/bpf.h>
+
+static void usage(void)
+{
+	printf("Usage: tc_l2_ipip_redirect [...]\n");
+	printf("       -U <file>   Update an already pinned BPF array\n");
+	printf("       -i <ifindex> Interface index\n");
+	printf("       -h          Display this help\n");
+}
+
+int main(int argc, char **argv)
+{
+	const char *pinned_file = NULL;
+	int ifindex = -1;
+	int array_key = 0;
+	int array_fd = -1;
+	int ret = -1;
+	int opt;
+
+	while ((opt = getopt(argc, argv, "F:U:i:")) != -1) {
+		switch (opt) {
+		/* General args */
+		case 'U':
+			pinned_file = optarg;
+			break;
+		case 'i':
+			ifindex = atoi(optarg);
+			break;
+		default:
+			usage();
+			goto out;
+		}
+	}
+
+	if (ifindex < 0 || !pinned_file) {
+		usage();
+		goto out;
+	}
+
+	array_fd = bpf_obj_get(pinned_file);
+	if (array_fd < 0) {
+		fprintf(stderr, "bpf_obj_get(%s): %s(%d)\n",
+			pinned_file, strerror(errno), errno);
+		goto out;
+	}
+
+	/* bpf_tunnel_key.remote_ipv4 expects host byte orders */
+	ret = bpf_map_update_elem(array_fd, &array_key, &ifindex, 0);
+	if (ret) {
+		perror("bpf_map_update_elem");
+		goto out;
+	}
+
+out:
+	if (array_fd != -1)
+		close(array_fd);
+	return ret;
+}

linux-7.2.3/samples/bpf/tcbpf1_kern.c

@@ -0,0 +1,91 @@
+#define KBUILD_MODNAME "foo"
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <uapi/linux/in.h>
+#include <uapi/linux/tcp.h>
+#include <uapi/linux/filter.h>
+#include <uapi/linux/pkt_cls.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_legacy.h"
+
+/* compiler workaround */
+#define _htonl __builtin_bswap32
+
+static inline void set_dst_mac(struct __sk_buff *skb, char *mac)
+{
+	bpf_skb_store_bytes(skb, 0, mac, ETH_ALEN, 1);
+}
+
+#define IP_CSUM_OFF (ETH_HLEN + offsetof(struct iphdr, check))
+#define TOS_OFF (ETH_HLEN + offsetof(struct iphdr, tos))
+
+static inline void set_ip_tos(struct __sk_buff *skb, __u8 new_tos)
+{
+	__u8 old_tos = load_byte(skb, TOS_OFF);
+
+	bpf_l3_csum_replace(skb, IP_CSUM_OFF, htons(old_tos), htons(new_tos), 2);
+	bpf_skb_store_bytes(skb, TOS_OFF, &new_tos, sizeof(new_tos), 0);
+}
+
+#define TCP_CSUM_OFF (ETH_HLEN + sizeof(struct iphdr) + offsetof(struct tcphdr, check))
+#define IP_SRC_OFF (ETH_HLEN + offsetof(struct iphdr, saddr))
+
+#define IS_PSEUDO 0x10
+
+static inline void set_tcp_ip_src(struct __sk_buff *skb, __u32 new_ip)
+{
+	__u32 old_ip = _htonl(load_word(skb, IP_SRC_OFF));
+
+	bpf_l4_csum_replace(skb, TCP_CSUM_OFF, old_ip, new_ip, IS_PSEUDO | sizeof(new_ip));
+	bpf_l3_csum_replace(skb, IP_CSUM_OFF, old_ip, new_ip, sizeof(new_ip));
+	bpf_skb_store_bytes(skb, IP_SRC_OFF, &new_ip, sizeof(new_ip), 0);
+}
+
+#define TCP_DPORT_OFF (ETH_HLEN + sizeof(struct iphdr) + offsetof(struct tcphdr, dest))
+static inline void set_tcp_dest_port(struct __sk_buff *skb, __u16 new_port)
+{
+	__u16 old_port = htons(load_half(skb, TCP_DPORT_OFF));
+
+	bpf_l4_csum_replace(skb, TCP_CSUM_OFF, old_port, new_port, sizeof(new_port));
+	bpf_skb_store_bytes(skb, TCP_DPORT_OFF, &new_port, sizeof(new_port), 0);
+}
+
+SEC("classifier")
+int bpf_prog1(struct __sk_buff *skb)
+{
+	__u8 proto = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol));
+	long *value;
+
+	if (proto == IPPROTO_TCP) {
+		set_ip_tos(skb, 8);
+		set_tcp_ip_src(skb, 0xA010101);
+		set_tcp_dest_port(skb, 5001);
+	}
+
+	return 0;
+}
+SEC("redirect_xmit")
+int _redirect_xmit(struct __sk_buff *skb)
+{
+	return bpf_redirect(skb->ifindex + 1, 0);
+}
+SEC("redirect_recv")
+int _redirect_recv(struct __sk_buff *skb)
+{
+	return bpf_redirect(skb->ifindex + 1, 1);
+}
+SEC("clone_redirect_xmit")
+int _clone_redirect_xmit(struct __sk_buff *skb)
+{
+	bpf_clone_redirect(skb, skb->ifindex + 1, 0);
+	return TC_ACT_SHOT;
+}
+SEC("clone_redirect_recv")
+int _clone_redirect_recv(struct __sk_buff *skb)
+{
+	bpf_clone_redirect(skb, skb->ifindex + 1, 1);
+	return TC_ACT_SHOT;
+}
+char _license[] SEC("license") = "GPL";

linux-7.2.3/samples/bpf/tcp_basertt_kern.c

@@ -0,0 +1,71 @@
+/* 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.
+ *
+ * BPF program to set base_rtt to 80us when host is running TCP-NV and
+ * both hosts are in the same datacenter (as determined by IPv6 prefix).
+ *
+ * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program.
+ */
+
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/tcp.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <linux/socket.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define DEBUG 1
+
+SEC("sockops")
+int bpf_basertt(struct bpf_sock_ops *skops)
+{
+	char cong[20];
+	char nv[] = "nv";
+	int rv = 0, n;
+	int op;
+
+	op = (int) skops->op;
+
+#ifdef DEBUG
+	bpf_printk("BPF command: %d\n", op);
+#endif
+
+	/* Check if both hosts are in the same datacenter. For this
+	 * example they are if the 1st 5.5 bytes in the IPv6 address
+	 * are the same.
+	 */
+	if (skops->family == AF_INET6 &&
+	    skops->local_ip6[0] == skops->remote_ip6[0] &&
+	    (bpf_ntohl(skops->local_ip6[1]) & 0xfff00000) ==
+	    (bpf_ntohl(skops->remote_ip6[1]) & 0xfff00000)) {
+		switch (op) {
+		case BPF_SOCK_OPS_BASE_RTT:
+			n = bpf_getsockopt(skops, SOL_TCP, TCP_CONGESTION,
+					   cong, sizeof(cong));
+			if (!n && !__builtin_memcmp(cong, nv, sizeof(nv))) {
+				/* Set base_rtt to 80us */
+				rv = 80;
+			} else if (n) {
+				rv = n;
+			} else {
+				rv = -1;
+			}
+			break;
+		default:
+			rv = -1;
+		}
+	} else {
+		rv = -1;
+	}
+#ifdef DEBUG
+	bpf_printk("Returning %d\n", rv);
+#endif
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";

linux-7.2.3/samples/bpf/tcp_bpf.readme

@@ -0,0 +1,28 @@
+This file describes how to run the tcp_*_kern.o tcp_bpf (or socket_ops)
+programs. These programs attach to a cgroupv2. The following commands create
+a cgroupv2 and attach a bash shell to the group.
+
+  mkdir -p /tmp/cgroupv2
+  mount -t cgroup2 none /tmp/cgroupv2
+  mkdir -p /tmp/cgroupv2/foo
+  bash
+  echo $$ >> /tmp/cgroupv2/foo/cgroup.procs
+
+Anything that runs under this shell belongs to the foo cgroupv2. To load
+(attach) one of the tcp_*_kern.o programs:
+
+  bpftool prog load tcp_basertt_kern.o /sys/fs/bpf/tcp_prog
+  bpftool cgroup attach /tmp/cgroupv2/foo sock_ops pinned /sys/fs/bpf/tcp_prog
+  bpftool prog tracelog
+
+"bpftool prog tracelog" will continue to run printing the BPF log buffer.
+The tcp_*_kern.o programs use special print functions to print logging
+information (if enabled by the ifdef).
+
+If using netperf/netserver to create traffic, you need to run them under the
+cgroupv2 to which the BPF programs are attached (i.e. under bash shell
+attached to the cgroupv2).
+
+To remove (unattach) a socket_ops BPF program from a cgroupv2:
+
+  bpftool cgroup detach /tmp/cgroupv2/foo sock_ops pinned /sys/fs/bpf/tcp_prog

linux-7.2.3/samples/bpf/tcp_bufs_kern.c

@@ -0,0 +1,81 @@
+/* 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.
+ *
+ * BPF program to set initial receive window to 40 packets and send
+ * and receive buffers to 1.5MB. This would usually be done after
+ * doing appropriate checks that indicate the hosts are far enough
+ * away (i.e. large RTT).
+ *
+ * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program.
+ */
+
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <linux/socket.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define DEBUG 1
+
+SEC("sockops")
+int bpf_bufs(struct bpf_sock_ops *skops)
+{
+	int bufsize = 1500000;
+	int rwnd_init = 40;
+	int rv = 0;
+	int op;
+
+	/* For testing purposes, only execute rest of BPF program
+	 * if neither port numberis 55601
+	 */
+	if (bpf_ntohl(skops->remote_port) != 55601 &&
+	    skops->local_port != 55601) {
+		skops->reply = -1;
+		return 1;
+	}
+
+	op = (int) skops->op;
+
+#ifdef DEBUG
+	bpf_printk("Returning %d\n", rv);
+#endif
+
+	/* Usually there would be a check to insure the hosts are far
+	 * from each other so it makes sense to increase buffer sizes
+	 */
+	switch (op) {
+	case BPF_SOCK_OPS_RWND_INIT:
+		rv = rwnd_init;
+		break;
+	case BPF_SOCK_OPS_TCP_CONNECT_CB:
+		/* Set sndbuf and rcvbuf of active connections */
+		rv = bpf_setsockopt(skops, SOL_SOCKET, SO_SNDBUF, &bufsize,
+				    sizeof(bufsize));
+		rv += bpf_setsockopt(skops, SOL_SOCKET, SO_RCVBUF,
+				     &bufsize, sizeof(bufsize));
+		break;
+	case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+		/* Nothing to do */
+		break;
+	case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+		/* Set sndbuf and rcvbuf of passive connections */
+		rv = bpf_setsockopt(skops, SOL_SOCKET, SO_SNDBUF, &bufsize,
+				    sizeof(bufsize));
+		rv += bpf_setsockopt(skops, SOL_SOCKET, SO_RCVBUF,
+				     &bufsize, sizeof(bufsize));
+		break;
+	default:
+		rv = -1;
+	}
+#ifdef DEBUG
+	bpf_printk("Returning %d\n", rv);
+#endif
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";

linux-7.2.3/samples/bpf/tcp_clamp_kern.c

@@ -0,0 +1,97 @@
+/* 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.
+ *
+ * Sample BPF program to set send and receive buffers to 150KB, sndcwnd clamp
+ * to 100 packets and SYN and SYN_ACK RTOs to 10ms when both hosts are within
+ * the same datacenter. For his example, we assume they are within the same
+ * datacenter when the first 5.5 bytes of their IPv6 addresses are the same.
+ *
+ * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program.
+ */
+
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <linux/socket.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define DEBUG 1
+
+SEC("sockops")
+int bpf_clamp(struct bpf_sock_ops *skops)
+{
+	int bufsize = 150000;
+	int to_init = 10;
+	int clamp = 100;
+	int rv = 0;
+	int op;
+
+	/* For testing purposes, only execute rest of BPF program
+	 * if neither port numberis 55601
+	 */
+	if (bpf_ntohl(skops->remote_port) != 55601 && skops->local_port != 55601) {
+		skops->reply = -1;
+		return 0;
+	}
+
+	op = (int) skops->op;
+
+#ifdef DEBUG
+	bpf_printk("BPF command: %d\n", op);
+#endif
+
+	/* Check that both hosts are within same datacenter. For this example
+	 * it is the case when the first 5.5 bytes of their IPv6 addresses are
+	 * the same.
+	 */
+	if (skops->family == AF_INET6 &&
+	    skops->local_ip6[0] == skops->remote_ip6[0] &&
+	    (bpf_ntohl(skops->local_ip6[1]) & 0xfff00000) ==
+	    (bpf_ntohl(skops->remote_ip6[1]) & 0xfff00000)) {
+		switch (op) {
+		case BPF_SOCK_OPS_TIMEOUT_INIT:
+			rv = to_init;
+			break;
+		case BPF_SOCK_OPS_TCP_CONNECT_CB:
+			/* Set sndbuf and rcvbuf of active connections */
+			rv = bpf_setsockopt(skops, SOL_SOCKET, SO_SNDBUF,
+					    &bufsize, sizeof(bufsize));
+			rv += bpf_setsockopt(skops, SOL_SOCKET,
+					     SO_RCVBUF, &bufsize,
+					     sizeof(bufsize));
+			break;
+		case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+			rv = bpf_setsockopt(skops, SOL_TCP,
+					    TCP_BPF_SNDCWND_CLAMP,
+					    &clamp, sizeof(clamp));
+			break;
+		case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+			/* Set sndbuf and rcvbuf of passive connections */
+			rv = bpf_setsockopt(skops, SOL_TCP,
+					    TCP_BPF_SNDCWND_CLAMP,
+					    &clamp, sizeof(clamp));
+			rv += bpf_setsockopt(skops, SOL_SOCKET,
+					     SO_SNDBUF, &bufsize,
+					     sizeof(bufsize));
+			rv += bpf_setsockopt(skops, SOL_SOCKET,
+					     SO_RCVBUF, &bufsize,
+					     sizeof(bufsize));
+			break;
+		default:
+			rv = -1;
+		}
+	} else {
+		rv = -1;
+	}
+#ifdef DEBUG
+	bpf_printk("Returning %d\n", rv);
+#endif
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";

linux-7.2.3/samples/bpf/tcp_cong_kern.c

@@ -0,0 +1,78 @@
+/* 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.
+ *
+ * BPF program to set congestion control to dctcp when both hosts are
+ * in the same datacenter (as determined by IPv6 prefix).
+ *
+ * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program.
+ */
+
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/tcp.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <linux/socket.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define DEBUG 1
+
+SEC("sockops")
+int bpf_cong(struct bpf_sock_ops *skops)
+{
+	char cong[] = "dctcp";
+	int rv = 0;
+	int op;
+
+	/* For testing purposes, only execute rest of BPF program
+	 * if neither port numberis 55601
+	 */
+	if (bpf_ntohl(skops->remote_port) != 55601 &&
+	    skops->local_port != 55601) {
+		skops->reply = -1;
+		return 1;
+	}
+
+	op = (int) skops->op;
+
+#ifdef DEBUG
+	bpf_printk("BPF command: %d\n", op);
+#endif
+
+	/* Check if both hosts are in the same datacenter. For this
+	 * example they are if the 1st 5.5 bytes in the IPv6 address
+	 * are the same.
+	 */
+	if (skops->family == AF_INET6 &&
+	    skops->local_ip6[0] == skops->remote_ip6[0] &&
+	    (bpf_ntohl(skops->local_ip6[1]) & 0xfff00000) ==
+	    (bpf_ntohl(skops->remote_ip6[1]) & 0xfff00000)) {
+		switch (op) {
+		case BPF_SOCK_OPS_NEEDS_ECN:
+			rv = 1;
+			break;
+		case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+			rv = bpf_setsockopt(skops, SOL_TCP, TCP_CONGESTION,
+					    cong, sizeof(cong));
+			break;
+		case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+			rv = bpf_setsockopt(skops, SOL_TCP, TCP_CONGESTION,
+					    cong, sizeof(cong));
+			break;
+		default:
+			rv = -1;
+		}
+	} else {
+		rv = -1;
+	}
+#ifdef DEBUG
+	bpf_printk("Returning %d\n", rv);
+#endif
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";

linux-7.2.3/samples/bpf/tcp_dumpstats_kern.c

@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Refer to samples/bpf/tcp_bpf.readme for the instructions on
+ * how to run this sample program.
+ */
+#include <linux/bpf.h>
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define INTERVAL			1000000000ULL
+
+int _version SEC("version") = 1;
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__u32 type;
+	__u32 map_flags;
+	int *key;
+	__u64 *value;
+} bpf_next_dump SEC(".maps") = {
+	.type = BPF_MAP_TYPE_SK_STORAGE,
+	.map_flags = BPF_F_NO_PREALLOC,
+};
+
+SEC("sockops")
+int _sockops(struct bpf_sock_ops *ctx)
+{
+	struct bpf_tcp_sock *tcp_sk;
+	struct bpf_sock *sk;
+	__u64 *next_dump;
+	__u64 now;
+
+	switch (ctx->op) {
+	case BPF_SOCK_OPS_TCP_CONNECT_CB:
+		bpf_sock_ops_cb_flags_set(ctx, BPF_SOCK_OPS_RTT_CB_FLAG);
+		return 1;
+	case BPF_SOCK_OPS_RTT_CB:
+		break;
+	default:
+		return 1;
+	}
+
+	sk = ctx->sk;
+	if (!sk)
+		return 1;
+
+	next_dump = bpf_sk_storage_get(&bpf_next_dump, sk, 0,
+				       BPF_SK_STORAGE_GET_F_CREATE);
+	if (!next_dump)
+		return 1;
+
+	now = bpf_ktime_get_ns();
+	if (now < *next_dump)
+		return 1;
+
+	tcp_sk = bpf_tcp_sock(sk);
+	if (!tcp_sk)
+		return 1;
+
+	*next_dump = now + INTERVAL;
+
+	bpf_printk("dsack_dups=%u delivered=%u\n",
+		   tcp_sk->dsack_dups, tcp_sk->delivered);
+	bpf_printk("delivered_ce=%u icsk_retransmits=%u\n",
+		   tcp_sk->delivered_ce, tcp_sk->icsk_retransmits);
+
+	return 1;
+}

linux-7.2.3/samples/bpf/tcp_iw_kern.c

@@ -0,0 +1,83 @@
+/* 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.
+ *
+ * BPF program to set initial congestion window and initial receive
+ * window to 40 packets and send and receive buffers to 1.5MB. This
+ * would usually be done after doing appropriate checks that indicate
+ * the hosts are far enough away (i.e. large RTT).
+ *
+ * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program.
+ */
+
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <linux/socket.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define DEBUG 1
+
+SEC("sockops")
+int bpf_iw(struct bpf_sock_ops *skops)
+{
+	int bufsize = 1500000;
+	int rwnd_init = 40;
+	int iw = 40;
+	int rv = 0;
+	int op;
+
+	/* For testing purposes, only execute rest of BPF program
+	 * if neither port numberis 55601
+	 */
+	if (bpf_ntohl(skops->remote_port) != 55601 &&
+	    skops->local_port != 55601) {
+		skops->reply = -1;
+		return 1;
+	}
+
+	op = (int) skops->op;
+
+#ifdef DEBUG
+	bpf_printk("BPF command: %d\n", op);
+#endif
+
+	/* Usually there would be a check to insure the hosts are far
+	 * from each other so it makes sense to increase buffer sizes
+	 */
+	switch (op) {
+	case BPF_SOCK_OPS_RWND_INIT:
+		rv = rwnd_init;
+		break;
+	case BPF_SOCK_OPS_TCP_CONNECT_CB:
+		/* Set sndbuf and rcvbuf of active connections */
+		rv = bpf_setsockopt(skops, SOL_SOCKET, SO_SNDBUF, &bufsize,
+				    sizeof(bufsize));
+		rv += bpf_setsockopt(skops, SOL_SOCKET, SO_RCVBUF,
+				     &bufsize, sizeof(bufsize));
+		break;
+	case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+		rv = bpf_setsockopt(skops, SOL_TCP, TCP_BPF_IW, &iw,
+				    sizeof(iw));
+		break;
+	case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+		/* Set sndbuf and rcvbuf of passive connections */
+		rv = bpf_setsockopt(skops, SOL_SOCKET, SO_SNDBUF, &bufsize,
+				    sizeof(bufsize));
+		rv +=  bpf_setsockopt(skops, SOL_SOCKET, SO_RCVBUF,
+				      &bufsize, sizeof(bufsize));
+		break;
+	default:
+		rv = -1;
+	}
+#ifdef DEBUG
+	bpf_printk("Returning %d\n", rv);
+#endif
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";

linux-7.2.3/samples/bpf/tcp_rwnd_kern.c

@@ -0,0 +1,64 @@
+/* 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.
+ *
+ * BPF program to set initial receive window to 40 packets when using IPv6
+ * and the first 5.5 bytes of the IPv6 addresses are not the same (in this
+ * example that means both hosts are not the same datacenter).
+ *
+ * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program.
+ */
+
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <linux/socket.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define DEBUG 1
+
+SEC("sockops")
+int bpf_rwnd(struct bpf_sock_ops *skops)
+{
+	int rv = -1;
+	int op;
+
+	/* For testing purposes, only execute rest of BPF program
+	 * if neither port numberis 55601
+	 */
+	if (bpf_ntohl(skops->remote_port) !=
+	    55601 && skops->local_port != 55601) {
+		skops->reply = -1;
+		return 1;
+	}
+
+	op = (int) skops->op;
+
+#ifdef DEBUG
+	bpf_printk("BPF command: %d\n", op);
+#endif
+
+	/* Check for RWND_INIT operation and IPv6 addresses */
+	if (op == BPF_SOCK_OPS_RWND_INIT &&
+		skops->family == AF_INET6) {
+
+		/* If the first 5.5 bytes of the IPv6 address are not the same
+		 * then both hosts are not in the same datacenter
+		 * so use a larger initial advertized window (40 packets)
+		 */
+		if (skops->local_ip6[0] != skops->remote_ip6[0] ||
+		    (bpf_ntohl(skops->local_ip6[1]) & 0xfffff000) !=
+		    (bpf_ntohl(skops->remote_ip6[1]) & 0xfffff000))
+			rv = 40;
+	}
+#ifdef DEBUG
+	bpf_printk("Returning %d\n", rv);
+#endif
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";

linux-7.2.3/samples/bpf/tcp_synrto_kern.c

@@ -0,0 +1,64 @@
+/* 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.
+ *
+ * BPF program to set SYN and SYN-ACK RTOs to 10ms when using IPv6 addresses
+ * and the first 5.5 bytes of the IPv6 addresses are the same (in this example
+ * that means both hosts are in the same datacenter).
+ *
+ * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program.
+ */
+
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <linux/socket.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define DEBUG 1
+
+SEC("sockops")
+int bpf_synrto(struct bpf_sock_ops *skops)
+{
+	int rv = -1;
+	int op;
+
+	/* For testing purposes, only execute rest of BPF program
+	 * if neither port numberis 55601
+	 */
+	if (bpf_ntohl(skops->remote_port) != 55601 &&
+	    skops->local_port != 55601) {
+		skops->reply = -1;
+		return 1;
+	}
+
+	op = (int) skops->op;
+
+#ifdef DEBUG
+	bpf_printk("BPF command: %d\n", op);
+#endif
+
+	/* Check for TIMEOUT_INIT operation and IPv6 addresses */
+	if (op == BPF_SOCK_OPS_TIMEOUT_INIT &&
+		skops->family == AF_INET6) {
+
+		/* If the first 5.5 bytes of the IPv6 address are the same
+		 * then both hosts are in the same datacenter
+		 * so use an RTO of 10ms
+		 */
+		if (skops->local_ip6[0] == skops->remote_ip6[0] &&
+		    (bpf_ntohl(skops->local_ip6[1]) & 0xfff00000) ==
+		    (bpf_ntohl(skops->remote_ip6[1]) & 0xfff00000))
+			rv = 10;
+	}
+#ifdef DEBUG
+	bpf_printk("Returning %d\n", rv);
+#endif
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";

linux-7.2.3/samples/bpf/tcp_tos_reflect_kern.c

@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018 Facebook
+ *
+ * BPF program to automatically reflect TOS option from received syn packet
+ *
+ * Use "bpftool cgroup attach $cg sock_ops $prog" to load this BPF program.
+ */
+
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/tcp.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <uapi/linux/ipv6.h>
+#include <uapi/linux/in.h>
+#include <linux/socket.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define DEBUG 1
+
+SEC("sockops")
+int bpf_basertt(struct bpf_sock_ops *skops)
+{
+	char header[sizeof(struct ipv6hdr)];
+	struct ipv6hdr *hdr6;
+	struct iphdr *hdr;
+	int hdr_size = 0;
+	int save_syn = 1;
+	int tos = 0;
+	int rv = 0;
+	int op;
+
+	op = (int) skops->op;
+
+#ifdef DEBUG
+	bpf_printk("BPF command: %d\n", op);
+#endif
+	switch (op) {
+	case BPF_SOCK_OPS_TCP_LISTEN_CB:
+		rv = bpf_setsockopt(skops, SOL_TCP, TCP_SAVE_SYN,
+				   &save_syn, sizeof(save_syn));
+		break;
+	case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+		if (skops->family == AF_INET)
+			hdr_size = sizeof(struct iphdr);
+		else
+			hdr_size = sizeof(struct ipv6hdr);
+		rv = bpf_getsockopt(skops, SOL_TCP, TCP_SAVED_SYN,
+				    header, hdr_size);
+		if (!rv) {
+			if (skops->family == AF_INET) {
+				hdr = (struct iphdr *) header;
+				tos = hdr->tos;
+				if (tos != 0)
+					bpf_setsockopt(skops, SOL_IP, IP_TOS,
+						       &tos, sizeof(tos));
+			} else {
+				hdr6 = (struct ipv6hdr *) header;
+				tos = ((hdr6->priority) << 4 |
+				       (hdr6->flow_lbl[0]) >>  4);
+				if (tos)
+					bpf_setsockopt(skops, SOL_IPV6,
+						       IPV6_TCLASS,
+						       &tos, sizeof(tos));
+			}
+			rv = 0;
+		}
+		break;
+	default:
+		rv = -1;
+	}
+#ifdef DEBUG
+	bpf_printk("Returning %d\n", rv);
+#endif
+	skops->reply = rv;
+	return 1;
+}
+char _license[] SEC("license") = "GPL";

linux-7.2.3/samples/bpf/test_cls_bpf.sh

@@ -0,0 +1,38 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+function pktgen {
+    ../pktgen/pktgen_bench_xmit_mode_netif_receive.sh -i $IFC -s 64 \
+        -m 90:e2:ba:ff:ff:ff -d 192.168.0.1 -t 4
+    local dropped=`tc -s qdisc show dev $IFC | tail -3 | awk '/drop/{print $7}'`
+    if [ "$dropped" == "0," ]; then
+        echo "FAIL"
+    else
+        echo "Successfully filtered " $dropped " packets"
+    fi
+}
+
+function test {
+    echo -n "Loading bpf program '$2'... "
+    tc qdisc add dev $IFC clsact
+    tc filter add dev $IFC ingress bpf da obj $1 sec $2
+    local status=$?
+    if [ $status -ne 0 ]; then
+        echo "FAIL"
+    else
+        echo "ok"
+	pktgen
+    fi
+    tc qdisc del dev $IFC clsact
+}
+
+IFC=test_veth
+
+ip link add name $IFC type veth peer name pair_$IFC
+ip link set $IFC up
+ip link set pair_$IFC up
+
+test ./parse_simple.o simple
+test ./parse_varlen.o varlen
+test ./parse_ldabs.o ldabs
+ip link del dev $IFC

linux-7.2.3/samples/bpf/test_lru_dist.c

@@ -0,0 +1,534 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2016 Facebook
+ */
+#define _GNU_SOURCE
+#include <linux/types.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <linux/bpf.h>
+#include <errno.h>
+#include <string.h>
+#include <assert.h>
+#include <sched.h>
+#include <sys/wait.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <stdlib.h>
+#include <time.h>
+
+#include <bpf/bpf.h>
+#include "bpf_util.h"
+
+#define min(a, b) ((a) < (b) ? (a) : (b))
+#ifndef offsetof
+# define offsetof(TYPE, MEMBER)	((size_t)&((TYPE *)0)->MEMBER)
+#endif
+#define container_of(ptr, type, member) ({			\
+	const typeof( ((type *)0)->member ) *__mptr = (ptr);	\
+	(type *)( (char *)__mptr - offsetof(type,member) );})
+
+static int nr_cpus;
+static unsigned long long *dist_keys;
+static unsigned int dist_key_counts;
+
+struct list_head {
+	struct list_head *next, *prev;
+};
+
+static inline void INIT_LIST_HEAD(struct list_head *list)
+{
+	list->next = list;
+	list->prev = list;
+}
+
+static inline void __list_add(struct list_head *new,
+			      struct list_head *prev,
+			      struct list_head *next)
+{
+	next->prev = new;
+	new->next = next;
+	new->prev = prev;
+	prev->next = new;
+}
+
+static inline void list_add(struct list_head *new, struct list_head *head)
+{
+	__list_add(new, head, head->next);
+}
+
+static inline void __list_del(struct list_head *prev, struct list_head *next)
+{
+	next->prev = prev;
+	prev->next = next;
+}
+
+static inline void __list_del_entry(struct list_head *entry)
+{
+	__list_del(entry->prev, entry->next);
+}
+
+static inline void list_move(struct list_head *list, struct list_head *head)
+{
+	__list_del_entry(list);
+	list_add(list, head);
+}
+
+#define list_entry(ptr, type, member) \
+	container_of(ptr, type, member)
+
+#define list_last_entry(ptr, type, member) \
+	list_entry((ptr)->prev, type, member)
+
+struct pfect_lru_node {
+	struct list_head list;
+	unsigned long long key;
+};
+
+struct pfect_lru {
+	struct list_head list;
+	struct pfect_lru_node *free_nodes;
+	unsigned int cur_size;
+	unsigned int lru_size;
+	unsigned int nr_unique;
+	unsigned int nr_misses;
+	unsigned int total;
+	int map_fd;
+};
+
+static void pfect_lru_init(struct pfect_lru *lru, unsigned int lru_size,
+			   unsigned int nr_possible_elems)
+{
+	lru->map_fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL,
+				     sizeof(unsigned long long),
+				     sizeof(struct pfect_lru_node *),
+				     nr_possible_elems, NULL);
+	assert(lru->map_fd != -1);
+
+	lru->free_nodes = malloc(lru_size * sizeof(struct pfect_lru_node));
+	assert(lru->free_nodes);
+
+	INIT_LIST_HEAD(&lru->list);
+	lru->cur_size = 0;
+	lru->lru_size = lru_size;
+	lru->nr_unique = lru->nr_misses = lru->total = 0;
+}
+
+static void pfect_lru_destroy(struct pfect_lru *lru)
+{
+	close(lru->map_fd);
+	free(lru->free_nodes);
+}
+
+static int pfect_lru_lookup_or_insert(struct pfect_lru *lru,
+				      unsigned long long key)
+{
+	struct pfect_lru_node *node = NULL;
+	int seen = 0;
+
+	lru->total++;
+	if (!bpf_map_lookup_elem(lru->map_fd, &key, &node)) {
+		if (node) {
+			list_move(&node->list, &lru->list);
+			return 1;
+		}
+		seen = 1;
+	}
+
+	if (lru->cur_size < lru->lru_size) {
+		node =  &lru->free_nodes[lru->cur_size++];
+		INIT_LIST_HEAD(&node->list);
+	} else {
+		struct pfect_lru_node *null_node = NULL;
+
+		node = list_last_entry(&lru->list,
+				       struct pfect_lru_node,
+				       list);
+		bpf_map_update_elem(lru->map_fd, &node->key, &null_node, BPF_EXIST);
+	}
+
+	node->key = key;
+	list_move(&node->list, &lru->list);
+
+	lru->nr_misses++;
+	if (seen) {
+		assert(!bpf_map_update_elem(lru->map_fd, &key, &node, BPF_EXIST));
+	} else {
+		lru->nr_unique++;
+		assert(!bpf_map_update_elem(lru->map_fd, &key, &node, BPF_NOEXIST));
+	}
+
+	return seen;
+}
+
+static unsigned int read_keys(const char *dist_file,
+			      unsigned long long **keys)
+{
+	struct stat fst;
+	unsigned long long *retkeys;
+	unsigned int counts = 0;
+	int dist_fd;
+	char *b, *l;
+	int i;
+
+	dist_fd = open(dist_file, 0);
+	assert(dist_fd != -1);
+
+	assert(fstat(dist_fd, &fst) == 0);
+	b = malloc(fst.st_size);
+	assert(b);
+
+	assert(read(dist_fd, b, fst.st_size) == fst.st_size);
+	close(dist_fd);
+	for (i = 0; i < fst.st_size; i++) {
+		if (b[i] == '\n')
+			counts++;
+	}
+	counts++; /* in case the last line has no \n */
+
+	retkeys = malloc(counts * sizeof(unsigned long long));
+	assert(retkeys);
+
+	counts = 0;
+	for (l = strtok(b, "\n"); l; l = strtok(NULL, "\n"))
+		retkeys[counts++] = strtoull(l, NULL, 10);
+	free(b);
+
+	*keys = retkeys;
+
+	return counts;
+}
+
+static int create_map(int map_type, int map_flags, unsigned int size)
+{
+	LIBBPF_OPTS(bpf_map_create_opts, opts,
+		.map_flags = map_flags,
+	);
+	int map_fd;
+
+	map_fd = bpf_map_create(map_type, NULL, sizeof(unsigned long long),
+				sizeof(unsigned long long), size, &opts);
+
+	if (map_fd == -1)
+		perror("bpf_create_map");
+
+	return map_fd;
+}
+
+static int sched_next_online(int pid, int next_to_try)
+{
+	cpu_set_t cpuset;
+
+	if (next_to_try == nr_cpus)
+		return -1;
+
+	while (next_to_try < nr_cpus) {
+		CPU_ZERO(&cpuset);
+		CPU_SET(next_to_try++, &cpuset);
+		if (!sched_setaffinity(pid, sizeof(cpuset), &cpuset))
+			break;
+	}
+
+	return next_to_try;
+}
+
+static void run_parallel(unsigned int tasks, void (*fn)(int i, void *data),
+			 void *data)
+{
+	int next_sched_cpu = 0;
+	pid_t pid[tasks];
+	int i;
+
+	for (i = 0; i < tasks; i++) {
+		pid[i] = fork();
+		if (pid[i] == 0) {
+			next_sched_cpu = sched_next_online(0, next_sched_cpu);
+			fn(i, data);
+			exit(0);
+		} else if (pid[i] == -1) {
+			printf("couldn't spawn #%d process\n", i);
+			exit(1);
+		}
+		/* It is mostly redundant and just allow the parent
+		 * process to update next_shced_cpu for the next child
+		 * process
+		 */
+		next_sched_cpu = sched_next_online(pid[i], next_sched_cpu);
+	}
+	for (i = 0; i < tasks; i++) {
+		int status;
+
+		assert(waitpid(pid[i], &status, 0) == pid[i]);
+		assert(status == 0);
+	}
+}
+
+static void do_test_lru_dist(int task, void *data)
+{
+	unsigned int nr_misses = 0;
+	struct pfect_lru pfect_lru;
+	unsigned long long key, value = 1234;
+	unsigned int i;
+
+	unsigned int lru_map_fd = ((unsigned int *)data)[0];
+	unsigned int lru_size = ((unsigned int *)data)[1];
+	unsigned long long key_offset = task * dist_key_counts;
+
+	pfect_lru_init(&pfect_lru, lru_size, dist_key_counts);
+
+	for (i = 0; i < dist_key_counts; i++) {
+		key = dist_keys[i] + key_offset;
+
+		pfect_lru_lookup_or_insert(&pfect_lru, key);
+
+		if (!bpf_map_lookup_elem(lru_map_fd, &key, &value))
+			continue;
+
+		if (bpf_map_update_elem(lru_map_fd, &key, &value, BPF_NOEXIST)) {
+			printf("bpf_map_update_elem(lru_map_fd, %llu): errno:%d\n",
+			       key, errno);
+			assert(0);
+		}
+
+		nr_misses++;
+	}
+
+	printf("    task:%d BPF LRU: nr_unique:%u(/%u) nr_misses:%u(/%u)\n",
+	       task, pfect_lru.nr_unique, dist_key_counts, nr_misses,
+	       dist_key_counts);
+	printf("    task:%d Perfect LRU: nr_unique:%u(/%u) nr_misses:%u(/%u)\n",
+	       task, pfect_lru.nr_unique, pfect_lru.total,
+	       pfect_lru.nr_misses, pfect_lru.total);
+
+	pfect_lru_destroy(&pfect_lru);
+	close(lru_map_fd);
+}
+
+static void test_parallel_lru_dist(int map_type, int map_flags,
+				   int nr_tasks, unsigned int lru_size)
+{
+	int child_data[2];
+	int lru_map_fd;
+
+	printf("%s (map_type:%d map_flags:0x%X):\n", __func__, map_type,
+	       map_flags);
+
+	if (map_flags & BPF_F_NO_COMMON_LRU)
+		lru_map_fd = create_map(map_type, map_flags,
+					nr_cpus * lru_size);
+	else
+		lru_map_fd = create_map(map_type, map_flags,
+					nr_tasks * lru_size);
+	assert(lru_map_fd != -1);
+
+	child_data[0] = lru_map_fd;
+	child_data[1] = lru_size;
+
+	run_parallel(nr_tasks, do_test_lru_dist, child_data);
+
+	close(lru_map_fd);
+}
+
+static void test_lru_loss0(int map_type, int map_flags)
+{
+	unsigned long long key, value[nr_cpus];
+	unsigned int old_unused_losses = 0;
+	unsigned int new_unused_losses = 0;
+	unsigned int used_losses = 0;
+	int map_fd;
+
+	printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
+	       map_flags);
+
+	assert(sched_next_online(0, 0) != -1);
+
+	if (map_flags & BPF_F_NO_COMMON_LRU)
+		map_fd = create_map(map_type, map_flags, 900 * nr_cpus);
+	else
+		map_fd = create_map(map_type, map_flags, 900);
+
+	assert(map_fd != -1);
+
+	value[0] = 1234;
+
+	for (key = 1; key <= 1000; key++) {
+		int start_key, end_key;
+
+		assert(bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST) == 0);
+
+		start_key = 101;
+		end_key = min(key, 900);
+
+		while (start_key <= end_key) {
+			bpf_map_lookup_elem(map_fd, &start_key, value);
+			start_key++;
+		}
+	}
+
+	for (key = 1; key <= 1000; key++) {
+		if (bpf_map_lookup_elem(map_fd, &key, value)) {
+			if (key <= 100)
+				old_unused_losses++;
+			else if (key <= 900)
+				used_losses++;
+			else
+				new_unused_losses++;
+		}
+	}
+
+	close(map_fd);
+
+	printf("older-elem-losses:%d(/100) active-elem-losses:%d(/800) "
+	       "newer-elem-losses:%d(/100)\n",
+	       old_unused_losses, used_losses, new_unused_losses);
+}
+
+static void test_lru_loss1(int map_type, int map_flags)
+{
+	unsigned long long key, value[nr_cpus];
+	int map_fd;
+	unsigned int nr_losses = 0;
+
+	printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
+	       map_flags);
+
+	assert(sched_next_online(0, 0) != -1);
+
+	if (map_flags & BPF_F_NO_COMMON_LRU)
+		map_fd = create_map(map_type, map_flags, 1000 * nr_cpus);
+	else
+		map_fd = create_map(map_type, map_flags, 1000);
+
+	assert(map_fd != -1);
+
+	value[0] = 1234;
+
+	for (key = 1; key <= 1000; key++)
+		assert(!bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST));
+
+	for (key = 1; key <= 1000; key++) {
+		if (bpf_map_lookup_elem(map_fd, &key, value))
+			nr_losses++;
+	}
+
+	close(map_fd);
+
+	printf("nr_losses:%d(/1000)\n", nr_losses);
+}
+
+static void do_test_parallel_lru_loss(int task, void *data)
+{
+	const unsigned int nr_stable_elems = 1000;
+	const unsigned int nr_repeats = 100000;
+
+	int map_fd = *(int *)data;
+	unsigned long long stable_base;
+	unsigned long long key, value[nr_cpus];
+	unsigned long long next_ins_key;
+	unsigned int nr_losses = 0;
+	unsigned int i;
+
+	stable_base = task * nr_repeats * 2 + 1;
+	next_ins_key = stable_base;
+	value[0] = 1234;
+	for (i = 0; i < nr_stable_elems; i++) {
+		assert(bpf_map_update_elem(map_fd, &next_ins_key, value,
+				       BPF_NOEXIST) == 0);
+		next_ins_key++;
+	}
+
+	for (i = 0; i < nr_repeats; i++) {
+		int rn;
+
+		rn = rand();
+
+		if (rn % 10) {
+			key = rn % nr_stable_elems + stable_base;
+			bpf_map_lookup_elem(map_fd, &key, value);
+		} else {
+			bpf_map_update_elem(map_fd, &next_ins_key, value,
+					BPF_NOEXIST);
+			next_ins_key++;
+		}
+	}
+
+	key = stable_base;
+	for (i = 0; i < nr_stable_elems; i++) {
+		if (bpf_map_lookup_elem(map_fd, &key, value))
+			nr_losses++;
+		key++;
+	}
+
+	printf("    task:%d nr_losses:%u\n", task, nr_losses);
+}
+
+static void test_parallel_lru_loss(int map_type, int map_flags, int nr_tasks)
+{
+	int map_fd;
+
+	printf("%s (map_type:%d map_flags:0x%X):\n", __func__, map_type,
+	       map_flags);
+
+	/* Give 20% more than the active working set */
+	if (map_flags & BPF_F_NO_COMMON_LRU)
+		map_fd = create_map(map_type, map_flags,
+				    nr_cpus * (1000 + 200));
+	else
+		map_fd = create_map(map_type, map_flags,
+				    nr_tasks * (1000 + 200));
+
+	assert(map_fd != -1);
+
+	run_parallel(nr_tasks, do_test_parallel_lru_loss, &map_fd);
+
+	close(map_fd);
+}
+
+int main(int argc, char **argv)
+{
+	int map_flags[] = {0, BPF_F_NO_COMMON_LRU};
+	const char *dist_file;
+	int nr_tasks = 1;
+	int lru_size;
+	int f;
+
+	if (argc < 4) {
+		printf("Usage: %s <dist-file> <lru-size> <nr-tasks>\n",
+		       argv[0]);
+		return -1;
+	}
+
+	dist_file = argv[1];
+	lru_size = atoi(argv[2]);
+	nr_tasks = atoi(argv[3]);
+
+	setbuf(stdout, NULL);
+
+	srand(time(NULL));
+
+	nr_cpus = bpf_num_possible_cpus();
+	assert(nr_cpus != -1);
+	printf("nr_cpus:%d\n\n", nr_cpus);
+
+	nr_tasks = min(nr_tasks, nr_cpus);
+
+	dist_key_counts = read_keys(dist_file, &dist_keys);
+	if (!dist_key_counts) {
+		printf("%s has no key\n", dist_file);
+		return -1;
+	}
+
+	for (f = 0; f < ARRAY_SIZE(map_flags); f++) {
+		test_lru_loss0(BPF_MAP_TYPE_LRU_HASH, map_flags[f]);
+		test_lru_loss1(BPF_MAP_TYPE_LRU_HASH, map_flags[f]);
+		test_parallel_lru_loss(BPF_MAP_TYPE_LRU_HASH, map_flags[f],
+				       nr_tasks);
+		test_parallel_lru_dist(BPF_MAP_TYPE_LRU_HASH, map_flags[f],
+				       nr_tasks, lru_size);
+		printf("\n");
+	}
+
+	free(dist_keys);
+
+	return 0;
+}

linux-7.2.3/samples/bpf/test_lwt_bpf.c

@@ -0,0 +1,245 @@
+/* Copyright (c) 2016 Thomas Graf <tgraf@tgraf.ch>
+ *
+ * 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 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 "vmlinux.h"
+#include "net_shared.h"
+#include <bpf/bpf_helpers.h>
+#include <string.h>
+
+# define printk(fmt, ...)						\
+		({							\
+			char ____fmt[] = fmt;				\
+			bpf_trace_printk(____fmt, sizeof(____fmt),	\
+				     ##__VA_ARGS__);			\
+		})
+
+#define CB_MAGIC 1234
+
+/* Test: Pass all packets through */
+SEC("nop")
+int do_nop(struct __sk_buff *skb)
+{
+	return BPF_OK;
+}
+
+/* Test: Verify context information can be accessed */
+SEC("test_ctx")
+int do_test_ctx(struct __sk_buff *skb)
+{
+	skb->cb[0] = CB_MAGIC;
+	printk("len %d hash %d protocol %d", skb->len, skb->hash,
+	       skb->protocol);
+	printk("cb %d ingress_ifindex %d ifindex %d", skb->cb[0],
+	       skb->ingress_ifindex, skb->ifindex);
+
+	return BPF_OK;
+}
+
+/* Test: Ensure skb->cb[] buffer is cleared */
+SEC("test_cb")
+int do_test_cb(struct __sk_buff *skb)
+{
+	printk("cb0: %x cb1: %x cb2: %x", skb->cb[0], skb->cb[1],
+	       skb->cb[2]);
+	printk("cb3: %x cb4: %x", skb->cb[3], skb->cb[4]);
+
+	return BPF_OK;
+}
+
+/* Test: Verify skb data can be read */
+SEC("test_data")
+int do_test_data(struct __sk_buff *skb)
+{
+	void *data = (void *)(long)skb->data;
+	void *data_end = (void *)(long)skb->data_end;
+	struct iphdr *iph = data;
+
+	if (data + sizeof(*iph) > data_end) {
+		printk("packet truncated");
+		return BPF_DROP;
+	}
+
+	printk("src: %x dst: %x", iph->saddr, iph->daddr);
+
+	return BPF_OK;
+}
+
+#define IP_CSUM_OFF offsetof(struct iphdr, check)
+#define IP_DST_OFF offsetof(struct iphdr, daddr)
+#define IP_SRC_OFF offsetof(struct iphdr, saddr)
+#define IP_PROTO_OFF offsetof(struct iphdr, protocol)
+#define TCP_CSUM_OFF offsetof(struct tcphdr, check)
+#define UDP_CSUM_OFF offsetof(struct udphdr, check)
+#define IS_PSEUDO 0x10
+
+static inline int rewrite(struct __sk_buff *skb, uint32_t old_ip,
+			  uint32_t new_ip, int rw_daddr)
+{
+	int ret, off = 0, flags = IS_PSEUDO;
+	uint8_t proto;
+
+	ret = bpf_skb_load_bytes(skb, IP_PROTO_OFF, &proto, 1);
+	if (ret < 0) {
+		printk("bpf_l4_csum_replace failed: %d", ret);
+		return BPF_DROP;
+	}
+
+	switch (proto) {
+	case IPPROTO_TCP:
+		off = TCP_CSUM_OFF;
+		break;
+
+	case IPPROTO_UDP:
+		off = UDP_CSUM_OFF;
+		flags |= BPF_F_MARK_MANGLED_0;
+		break;
+
+	case IPPROTO_ICMPV6:
+		off = offsetof(struct icmp6hdr, icmp6_cksum);
+		break;
+	}
+
+	if (off) {
+		ret = bpf_l4_csum_replace(skb, off, old_ip, new_ip,
+					  flags | sizeof(new_ip));
+		if (ret < 0) {
+			printk("bpf_l4_csum_replace failed: %d");
+			return BPF_DROP;
+		}
+	}
+
+	ret = bpf_l3_csum_replace(skb, IP_CSUM_OFF, old_ip, new_ip, sizeof(new_ip));
+	if (ret < 0) {
+		printk("bpf_l3_csum_replace failed: %d", ret);
+		return BPF_DROP;
+	}
+
+	if (rw_daddr)
+		ret = bpf_skb_store_bytes(skb, IP_DST_OFF, &new_ip, sizeof(new_ip), 0);
+	else
+		ret = bpf_skb_store_bytes(skb, IP_SRC_OFF, &new_ip, sizeof(new_ip), 0);
+
+	if (ret < 0) {
+		printk("bpf_skb_store_bytes() failed: %d", ret);
+		return BPF_DROP;
+	}
+
+	return BPF_OK;
+}
+
+/* Test: Verify skb data can be modified */
+SEC("test_rewrite")
+int do_test_rewrite(struct __sk_buff *skb)
+{
+	uint32_t old_ip, new_ip = 0x3fea8c0;
+	int ret;
+
+	ret = bpf_skb_load_bytes(skb, IP_DST_OFF, &old_ip, 4);
+	if (ret < 0) {
+		printk("bpf_skb_load_bytes failed: %d", ret);
+		return BPF_DROP;
+	}
+
+	if (old_ip == 0x2fea8c0) {
+		printk("out: rewriting from %x to %x", old_ip, new_ip);
+		return rewrite(skb, old_ip, new_ip, 1);
+	}
+
+	return BPF_OK;
+}
+
+static inline int __do_push_ll_and_redirect(struct __sk_buff *skb)
+{
+	uint64_t smac = SRC_MAC, dmac = DST_MAC;
+	int ret, ifindex = DST_IFINDEX;
+	struct ethhdr ehdr;
+
+	ret = bpf_skb_change_head(skb, 14, 0);
+	if (ret < 0) {
+		printk("skb_change_head() failed: %d", ret);
+	}
+
+	ehdr.h_proto = bpf_htons(ETH_P_IP);
+	memcpy(&ehdr.h_source, &smac, 6);
+	memcpy(&ehdr.h_dest, &dmac, 6);
+
+	ret = bpf_skb_store_bytes(skb, 0, &ehdr, sizeof(ehdr), 0);
+	if (ret < 0) {
+		printk("skb_store_bytes() failed: %d", ret);
+		return BPF_DROP;
+	}
+
+	return bpf_redirect(ifindex, 0);
+}
+
+SEC("push_ll_and_redirect_silent")
+int do_push_ll_and_redirect_silent(struct __sk_buff *skb)
+{
+	return __do_push_ll_and_redirect(skb);
+}
+
+SEC("push_ll_and_redirect")
+int do_push_ll_and_redirect(struct __sk_buff *skb)
+{
+	int ret, ifindex = DST_IFINDEX;
+
+	ret = __do_push_ll_and_redirect(skb);
+	if (ret >= 0)
+		printk("redirected to %d", ifindex);
+
+	return ret;
+}
+
+static inline void __fill_garbage(struct __sk_buff *skb)
+{
+	uint64_t f = 0xFFFFFFFFFFFFFFFF;
+
+	bpf_skb_store_bytes(skb, 0, &f, sizeof(f), 0);
+	bpf_skb_store_bytes(skb, 8, &f, sizeof(f), 0);
+	bpf_skb_store_bytes(skb, 16, &f, sizeof(f), 0);
+	bpf_skb_store_bytes(skb, 24, &f, sizeof(f), 0);
+	bpf_skb_store_bytes(skb, 32, &f, sizeof(f), 0);
+	bpf_skb_store_bytes(skb, 40, &f, sizeof(f), 0);
+	bpf_skb_store_bytes(skb, 48, &f, sizeof(f), 0);
+	bpf_skb_store_bytes(skb, 56, &f, sizeof(f), 0);
+	bpf_skb_store_bytes(skb, 64, &f, sizeof(f), 0);
+	bpf_skb_store_bytes(skb, 72, &f, sizeof(f), 0);
+	bpf_skb_store_bytes(skb, 80, &f, sizeof(f), 0);
+	bpf_skb_store_bytes(skb, 88, &f, sizeof(f), 0);
+}
+
+SEC("fill_garbage")
+int do_fill_garbage(struct __sk_buff *skb)
+{
+	__fill_garbage(skb);
+	printk("Set initial 96 bytes of header to FF");
+	return BPF_OK;
+}
+
+SEC("fill_garbage_and_redirect")
+int do_fill_garbage_and_redirect(struct __sk_buff *skb)
+{
+	int ifindex = DST_IFINDEX;
+	__fill_garbage(skb);
+	printk("redirected to %d", ifindex);
+	return bpf_redirect(ifindex, 0);
+}
+
+/* Drop all packets */
+SEC("drop_all")
+int do_drop_all(struct __sk_buff *skb)
+{
+	printk("dropping with: %d", BPF_DROP);
+	return BPF_DROP;
+}
+
+char _license[] SEC("license") = "GPL";

linux-7.2.3/samples/bpf/test_lwt_bpf.sh

@@ -0,0 +1,405 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Uncomment to see generated bytecode
+#VERBOSE=verbose
+
+NS1=lwt_ns1
+NS2=lwt_ns2
+VETH0=tst_lwt1a
+VETH1=tst_lwt1b
+VETH2=tst_lwt2a
+VETH3=tst_lwt2b
+IPVETH0="192.168.254.1"
+IPVETH1="192.168.254.2"
+IPVETH1b="192.168.254.3"
+
+IPVETH2="192.168.111.1"
+IPVETH3="192.168.111.2"
+
+IP_LOCAL="192.168.99.1"
+
+PROG_SRC="test_lwt_bpf.c"
+BPF_PROG="test_lwt_bpf.o"
+TRACE_ROOT=/sys/kernel/tracing
+CONTEXT_INFO=$(cat ${TRACE_ROOT}/trace_options | grep context)
+
+function lookup_mac()
+{
+	set +x
+	if [ ! -z "$2" ]; then
+		MAC=$(ip netns exec $2 ip link show $1 | grep ether | awk '{print $2}')
+	else
+		MAC=$(ip link show $1 | grep ether | awk '{print $2}')
+	fi
+	MAC="${MAC//:/}"
+	echo "0x${MAC:10:2}${MAC:8:2}${MAC:6:2}${MAC:4:2}${MAC:2:2}${MAC:0:2}"
+	set -x
+}
+
+function cleanup {
+	set +ex
+	rm $BPF_PROG 2> /dev/null
+	ip link del $VETH0 2> /dev/null
+	ip link del $VETH1 2> /dev/null
+	ip link del $VETH2 2> /dev/null
+	ip link del $VETH3 2> /dev/null
+	ip netns exec $NS1 killall netserver
+	ip netns delete $NS1 2> /dev/null
+	ip netns delete $NS2 2> /dev/null
+	set -ex
+}
+
+function setup_one_veth {
+	ip netns add $1
+	ip link add $2 type veth peer name $3
+	ip link set dev $2 up
+	ip addr add $4/24 dev $2
+	ip link set $3 netns $1
+	ip netns exec $1 ip link set dev $3 up
+	ip netns exec $1 ip addr add $5/24 dev $3
+
+	if [ "$6" ]; then
+		ip netns exec $1 ip addr add $6/32 dev $3
+	fi
+}
+
+function get_trace {
+	set +x
+	cat ${TRACE_ROOT}/trace | grep -v '^#'
+	set -x
+}
+
+function cleanup_routes {
+	ip route del ${IPVETH1}/32 dev $VETH0 2> /dev/null || true
+	ip route del table local local ${IP_LOCAL}/32 dev lo 2> /dev/null || true
+}
+
+function install_test {
+	cleanup_routes
+	cp /dev/null ${TRACE_ROOT}/trace
+
+	OPTS="encap bpf headroom 14 $1 obj $BPF_PROG section $2 $VERBOSE"
+
+	if [ "$1" == "in" ];  then
+		ip route add table local local ${IP_LOCAL}/32 $OPTS dev lo
+	else
+		ip route add ${IPVETH1}/32 $OPTS dev $VETH0
+	fi
+}
+
+function remove_prog {
+	if [ "$1" == "in" ];  then
+		ip route del table local local ${IP_LOCAL}/32 dev lo
+	else
+		ip route del ${IPVETH1}/32 dev $VETH0
+	fi
+}
+
+function filter_trace {
+	# Add newline to allow starting EXPECT= variables on newline
+	NL=$'\n'
+	echo "${NL}$*" | sed -e 's/bpf_trace_printk: //g'
+}
+
+function expect_fail {
+	set +x
+	echo "FAIL:"
+	echo "Expected: $1"
+	echo "Got: $2"
+	set -x
+	exit 1
+}
+
+function match_trace {
+	set +x
+	RET=0
+	TRACE=$1
+	EXPECT=$2
+	GOT="$(filter_trace "$TRACE")"
+
+	[ "$GOT" != "$EXPECT" ] && {
+		expect_fail "$EXPECT" "$GOT"
+		RET=1
+	}
+	set -x
+	return $RET
+}
+
+function test_start {
+	set +x
+	echo "----------------------------------------------------------------"
+	echo "Starting test: $*"
+	echo "----------------------------------------------------------------"
+	set -x
+}
+
+function failure {
+	get_trace
+	echo "FAIL: $*"
+	exit 1
+}
+
+function test_ctx_xmit {
+	test_start "test_ctx on lwt xmit"
+	install_test xmit test_ctx
+	ping -c 3 $IPVETH1 || {
+		failure "test_ctx xmit: packets are dropped"
+	}
+	match_trace "$(get_trace)" "
+len 84 hash 0 protocol 8
+cb 1234 ingress_ifindex 0 ifindex $DST_IFINDEX
+len 84 hash 0 protocol 8
+cb 1234 ingress_ifindex 0 ifindex $DST_IFINDEX
+len 84 hash 0 protocol 8
+cb 1234 ingress_ifindex 0 ifindex $DST_IFINDEX" || exit 1
+	remove_prog xmit
+}
+
+function test_ctx_out {
+	test_start "test_ctx on lwt out"
+	install_test out test_ctx
+	ping -c 3 $IPVETH1 || {
+		failure "test_ctx out: packets are dropped"
+	}
+	match_trace "$(get_trace)" "
+len 84 hash 0 protocol 8
+cb 1234 ingress_ifindex 0 ifindex 0
+len 84 hash 0 protocol 8
+cb 1234 ingress_ifindex 0 ifindex 0
+len 84 hash 0 protocol 8
+cb 1234 ingress_ifindex 0 ifindex 0" || exit 1
+	remove_prog out
+}
+
+function test_ctx_in {
+	test_start "test_ctx on lwt in"
+	install_test in test_ctx
+	ping -c 3 $IP_LOCAL || {
+		failure "test_ctx out: packets are dropped"
+	}
+	# We will both request & reply packets as the packets will
+	# be from $IP_LOCAL => $IP_LOCAL
+	match_trace "$(get_trace)" "
+len 84 hash 0 protocol 8
+cb 1234 ingress_ifindex 1 ifindex 1
+len 84 hash 0 protocol 8
+cb 1234 ingress_ifindex 1 ifindex 1
+len 84 hash 0 protocol 8
+cb 1234 ingress_ifindex 1 ifindex 1
+len 84 hash 0 protocol 8
+cb 1234 ingress_ifindex 1 ifindex 1
+len 84 hash 0 protocol 8
+cb 1234 ingress_ifindex 1 ifindex 1
+len 84 hash 0 protocol 8
+cb 1234 ingress_ifindex 1 ifindex 1" || exit 1
+	remove_prog in
+}
+
+function test_data {
+	test_start "test_data on lwt $1"
+	install_test $1 test_data
+	ping -c 3 $IPVETH1 || {
+		failure "test_data ${1}: packets are dropped"
+	}
+	match_trace "$(get_trace)" "
+src: 1fea8c0 dst: 2fea8c0
+src: 1fea8c0 dst: 2fea8c0
+src: 1fea8c0 dst: 2fea8c0" || exit 1
+	remove_prog $1
+}
+
+function test_data_in {
+	test_start "test_data on lwt in"
+	install_test in test_data
+	ping -c 3 $IP_LOCAL || {
+		failure "test_data in: packets are dropped"
+	}
+	# We will both request & reply packets as the packets will
+	# be from $IP_LOCAL => $IP_LOCAL
+	match_trace "$(get_trace)" "
+src: 163a8c0 dst: 163a8c0
+src: 163a8c0 dst: 163a8c0
+src: 163a8c0 dst: 163a8c0
+src: 163a8c0 dst: 163a8c0
+src: 163a8c0 dst: 163a8c0
+src: 163a8c0 dst: 163a8c0" || exit 1
+	remove_prog in
+}
+
+function test_cb {
+	test_start "test_cb on lwt $1"
+	install_test $1 test_cb
+	ping -c 3 $IPVETH1 || {
+		failure "test_cb ${1}: packets are dropped"
+	}
+	match_trace "$(get_trace)" "
+cb0: 0 cb1: 0 cb2: 0
+cb3: 0 cb4: 0
+cb0: 0 cb1: 0 cb2: 0
+cb3: 0 cb4: 0
+cb0: 0 cb1: 0 cb2: 0
+cb3: 0 cb4: 0" || exit 1
+	remove_prog $1
+}
+
+function test_cb_in {
+	test_start "test_cb on lwt in"
+	install_test in test_cb
+	ping -c 3 $IP_LOCAL || {
+		failure "test_cb in: packets are dropped"
+	}
+	# We will both request & reply packets as the packets will
+	# be from $IP_LOCAL => $IP_LOCAL
+	match_trace "$(get_trace)" "
+cb0: 0 cb1: 0 cb2: 0
+cb3: 0 cb4: 0
+cb0: 0 cb1: 0 cb2: 0
+cb3: 0 cb4: 0
+cb0: 0 cb1: 0 cb2: 0
+cb3: 0 cb4: 0
+cb0: 0 cb1: 0 cb2: 0
+cb3: 0 cb4: 0
+cb0: 0 cb1: 0 cb2: 0
+cb3: 0 cb4: 0
+cb0: 0 cb1: 0 cb2: 0
+cb3: 0 cb4: 0" || exit 1
+	remove_prog in
+}
+
+function test_drop_all {
+	test_start "test_drop_all on lwt $1"
+	install_test $1 drop_all
+	ping -c 3 $IPVETH1 && {
+		failure "test_drop_all ${1}: Unexpected success of ping"
+	}
+	match_trace "$(get_trace)" "
+dropping with: 2
+dropping with: 2
+dropping with: 2" || exit 1
+	remove_prog $1
+}
+
+function test_drop_all_in {
+	test_start "test_drop_all on lwt in"
+	install_test in drop_all
+	ping -c 3 $IP_LOCAL && {
+		failure "test_drop_all in: Unexpected success of ping"
+	}
+	match_trace "$(get_trace)" "
+dropping with: 2
+dropping with: 2
+dropping with: 2" || exit 1
+	remove_prog in
+}
+
+function test_push_ll_and_redirect {
+	test_start "test_push_ll_and_redirect on lwt xmit"
+	install_test xmit push_ll_and_redirect
+	ping -c 3 $IPVETH1 || {
+		failure "Redirected packets appear to be dropped"
+	}
+	match_trace "$(get_trace)" "
+redirected to $DST_IFINDEX
+redirected to $DST_IFINDEX
+redirected to $DST_IFINDEX" || exit 1
+	remove_prog xmit
+}
+
+function test_no_l2_and_redirect {
+	test_start "test_no_l2_and_redirect on lwt xmit"
+	install_test xmit fill_garbage_and_redirect
+	ping -c 3 $IPVETH1 && {
+		failure "Unexpected success despite lack of L2 header"
+	}
+	match_trace "$(get_trace)" "
+redirected to $DST_IFINDEX
+redirected to $DST_IFINDEX
+redirected to $DST_IFINDEX" || exit 1
+	remove_prog xmit
+}
+
+function test_rewrite {
+	test_start "test_rewrite on lwt xmit"
+	install_test xmit test_rewrite
+	ping -c 3 $IPVETH1 || {
+		failure "Rewritten packets appear to be dropped"
+	}
+	match_trace "$(get_trace)" "
+out: rewriting from 2fea8c0 to 3fea8c0
+out: rewriting from 2fea8c0 to 3fea8c0
+out: rewriting from 2fea8c0 to 3fea8c0" || exit 1
+	remove_prog out
+}
+
+function test_fill_garbage {
+	test_start "test_fill_garbage on lwt xmit"
+	install_test xmit fill_garbage
+	ping -c 3 $IPVETH1 && {
+		failure "test_drop_all ${1}: Unexpected success of ping"
+	}
+	match_trace "$(get_trace)" "
+Set initial 96 bytes of header to FF
+Set initial 96 bytes of header to FF
+Set initial 96 bytes of header to FF" || exit 1
+	remove_prog xmit
+}
+
+function test_netperf_nop {
+	test_start "test_netperf_nop on lwt xmit"
+	install_test xmit nop
+	netperf -H $IPVETH1 -t TCP_STREAM || {
+		failure "packets appear to be dropped"
+	}
+	match_trace "$(get_trace)" ""|| exit 1
+	remove_prog xmit
+}
+
+function test_netperf_redirect {
+	test_start "test_netperf_redirect on lwt xmit"
+	install_test xmit push_ll_and_redirect_silent
+	netperf -H $IPVETH1 -t TCP_STREAM || {
+		failure "Rewritten packets appear to be dropped"
+	}
+	match_trace "$(get_trace)" ""|| exit 1
+	remove_prog xmit
+}
+
+cleanup
+setup_one_veth $NS1 $VETH0 $VETH1 $IPVETH0 $IPVETH1 $IPVETH1b
+setup_one_veth $NS2 $VETH2 $VETH3 $IPVETH2 $IPVETH3
+ip netns exec $NS1 netserver
+echo 1 > ${TRACE_ROOT}/tracing_on
+echo nocontext-info > ${TRACE_ROOT}/trace_options
+
+DST_MAC=$(lookup_mac $VETH1 $NS1)
+SRC_MAC=$(lookup_mac $VETH0)
+DST_IFINDEX=$(cat /sys/class/net/$VETH0/ifindex)
+
+CLANG_OPTS="-O2 --target=bpf -I ../include/"
+CLANG_OPTS+=" -DSRC_MAC=$SRC_MAC -DDST_MAC=$DST_MAC -DDST_IFINDEX=$DST_IFINDEX"
+clang $CLANG_OPTS -c $PROG_SRC -o $BPF_PROG
+
+test_ctx_xmit
+test_ctx_out
+test_ctx_in
+test_data "xmit"
+test_data "out"
+test_data_in
+test_cb "xmit"
+test_cb "out"
+test_cb_in
+test_drop_all "xmit"
+test_drop_all "out"
+test_drop_all_in
+test_rewrite
+test_push_ll_and_redirect
+test_no_l2_and_redirect
+test_fill_garbage
+test_netperf_nop
+test_netperf_redirect
+
+cleanup
+echo 0 > ${TRACE_ROOT}/tracing_on
+echo $CONTEXT_INFO > ${TRACE_ROOT}/trace_options
+exit 0

linux-7.2.3/samples/bpf/test_map_in_map.bpf.c

@@ -0,0 +1,172 @@
+/*
+ * 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.
+ */
+#define KBUILD_MODNAME "foo"
+#include "vmlinux.h"
+#include <linux/version.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+#define MAX_NR_PORTS 65536
+
+#define EINVAL 22
+#define ENOENT 2
+
+/* map #0 */
+struct inner_a {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, u32);
+	__type(value, int);
+	__uint(max_entries, MAX_NR_PORTS);
+} port_a SEC(".maps");
+
+/* map #1 */
+struct inner_h {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, u32);
+	__type(value, int);
+	__uint(max_entries, 1);
+} port_h SEC(".maps");
+
+/* map #2 */
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, u32);
+	__type(value, int);
+	__uint(max_entries, 1);
+} reg_result_h SEC(".maps");
+
+/* map #3 */
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, u32);
+	__type(value, int);
+	__uint(max_entries, 1);
+} inline_result_h SEC(".maps");
+
+/* map #4 */ /* Test case #0 */
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__uint(max_entries, MAX_NR_PORTS);
+	__uint(key_size, sizeof(u32));
+	__array(values, struct inner_a); /* use inner_a as inner map */
+} a_of_port_a SEC(".maps");
+
+/* map #5 */ /* Test case #1 */
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(u32));
+	__array(values, struct inner_a); /* use inner_a as inner map */
+} h_of_port_a SEC(".maps");
+
+/* map #6 */ /* Test case #2 */
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(u32));
+	__array(values, struct inner_h); /* use inner_h as inner map */
+} h_of_port_h SEC(".maps");
+
+static __always_inline int do_reg_lookup(void *inner_map, u32 port)
+{
+	int *result;
+
+	result = bpf_map_lookup_elem(inner_map, &port);
+	return result ? *result : -ENOENT;
+}
+
+static __always_inline int do_inline_array_lookup(void *inner_map, u32 port)
+{
+	int *result;
+
+	if (inner_map != &port_a)
+		return -EINVAL;
+
+	result = bpf_map_lookup_elem(&port_a, &port);
+	return result ? *result : -ENOENT;
+}
+
+static __always_inline int do_inline_hash_lookup(void *inner_map, u32 port)
+{
+	int *result;
+
+	if (inner_map != &port_h)
+		return -EINVAL;
+
+	result = bpf_map_lookup_elem(&port_h, &port);
+	return result ? *result : -ENOENT;
+}
+
+SEC("ksyscall/connect")
+int BPF_KSYSCALL(trace_sys_connect, unsigned int fd, struct sockaddr_in6 *in6, int addrlen)
+{
+	u16 test_case, port, dst6[8];
+	int ret, inline_ret, ret_key = 0;
+	u32 port_key;
+	void *outer_map, *inner_map;
+	bool inline_hash = false;
+
+	if (addrlen != sizeof(*in6))
+		return 0;
+
+	ret = bpf_probe_read_user(dst6, sizeof(dst6), &in6->sin6_addr);
+	if (ret) {
+		inline_ret = ret;
+		goto done;
+	}
+
+	if (dst6[0] != 0xdead || dst6[1] != 0xbeef)
+		return 0;
+
+	test_case = dst6[7];
+
+	ret = bpf_probe_read_user(&port, sizeof(port), &in6->sin6_port);
+	if (ret) {
+		inline_ret = ret;
+		goto done;
+	}
+
+	port_key = port;
+
+	ret = -ENOENT;
+	if (test_case == 0) {
+		outer_map = &a_of_port_a;
+	} else if (test_case == 1) {
+		outer_map = &h_of_port_a;
+	} else if (test_case == 2) {
+		outer_map = &h_of_port_h;
+	} else {
+		ret = __LINE__;
+		inline_ret = ret;
+		goto done;
+	}
+
+	inner_map = bpf_map_lookup_elem(outer_map, &port_key);
+	if (!inner_map) {
+		ret = __LINE__;
+		inline_ret = ret;
+		goto done;
+	}
+
+	ret = do_reg_lookup(inner_map, port_key);
+
+	if (test_case == 0 || test_case == 1)
+		inline_ret = do_inline_array_lookup(inner_map, port_key);
+	else
+		inline_ret = do_inline_hash_lookup(inner_map, port_key);
+
+done:
+	bpf_map_update_elem(&reg_result_h, &ret_key, &ret, BPF_ANY);
+	bpf_map_update_elem(&inline_result_h, &ret_key, &inline_ret, BPF_ANY);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;

linux-7.2.3/samples/bpf/test_map_in_map_user.c

@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2017 Facebook
+ */
+#include <sys/socket.h>
+#include <arpa/inet.h>
+#include <stdint.h>
+#include <assert.h>
+#include <errno.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "bpf_util.h"
+
+static int map_fd[7];
+
+#define PORT_A		(map_fd[0])
+#define PORT_H		(map_fd[1])
+#define REG_RESULT_H	(map_fd[2])
+#define INLINE_RESULT_H	(map_fd[3])
+#define A_OF_PORT_A	(map_fd[4]) /* Test case #0 */
+#define H_OF_PORT_A	(map_fd[5]) /* Test case #1 */
+#define H_OF_PORT_H	(map_fd[6]) /* Test case #2 */
+
+static const char * const test_names[] = {
+	"Array of Array",
+	"Hash of Array",
+	"Hash of Hash",
+};
+
+#define NR_TESTS ARRAY_SIZE(test_names)
+
+static void check_map_id(int inner_map_fd, int map_in_map_fd, uint32_t key)
+{
+	struct bpf_map_info info = {};
+	uint32_t info_len = sizeof(info);
+	int ret, id;
+
+	ret = bpf_map_get_info_by_fd(inner_map_fd, &info, &info_len);
+	assert(!ret);
+
+	ret = bpf_map_lookup_elem(map_in_map_fd, &key, &id);
+	assert(!ret);
+	assert(id == info.id);
+}
+
+static void populate_map(uint32_t port_key, int magic_result)
+{
+	int ret;
+
+	ret = bpf_map_update_elem(PORT_A, &port_key, &magic_result, BPF_ANY);
+	assert(!ret);
+
+	ret = bpf_map_update_elem(PORT_H, &port_key, &magic_result,
+				  BPF_NOEXIST);
+	assert(!ret);
+
+	ret = bpf_map_update_elem(A_OF_PORT_A, &port_key, &PORT_A, BPF_ANY);
+	assert(!ret);
+	check_map_id(PORT_A, A_OF_PORT_A, port_key);
+
+	ret = bpf_map_update_elem(H_OF_PORT_A, &port_key, &PORT_A, BPF_NOEXIST);
+	assert(!ret);
+	check_map_id(PORT_A, H_OF_PORT_A, port_key);
+
+	ret = bpf_map_update_elem(H_OF_PORT_H, &port_key, &PORT_H, BPF_NOEXIST);
+	assert(!ret);
+	check_map_id(PORT_H, H_OF_PORT_H, port_key);
+}
+
+static void test_map_in_map(void)
+{
+	struct sockaddr_in6 in6 = { .sin6_family = AF_INET6 };
+	uint32_t result_key = 0, port_key;
+	int result, inline_result;
+	int magic_result = 0xfaceb00c;
+	int ret;
+	int i;
+
+	port_key = rand() & 0x00FF;
+	populate_map(port_key, magic_result);
+
+	in6.sin6_addr.s6_addr16[0] = 0xdead;
+	in6.sin6_addr.s6_addr16[1] = 0xbeef;
+	in6.sin6_port = port_key;
+
+	for (i = 0; i < NR_TESTS; i++) {
+		printf("%s: ", test_names[i]);
+
+		in6.sin6_addr.s6_addr16[7] = i;
+		ret = connect(-1, (struct sockaddr *)&in6, sizeof(in6));
+		assert(ret == -1 && errno == EBADF);
+
+		ret = bpf_map_lookup_elem(REG_RESULT_H, &result_key, &result);
+		assert(!ret);
+
+		ret = bpf_map_lookup_elem(INLINE_RESULT_H, &result_key,
+					  &inline_result);
+		assert(!ret);
+
+		if (result != magic_result || inline_result != magic_result) {
+			printf("Error. result:%d inline_result:%d\n",
+			       result, inline_result);
+			exit(1);
+		}
+
+		bpf_map_delete_elem(REG_RESULT_H, &result_key);
+		bpf_map_delete_elem(INLINE_RESULT_H, &result_key);
+
+		printf("Pass\n");
+	}
+}
+
+int main(int argc, char **argv)
+{
+	struct bpf_link *link = NULL;
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	char filename[256];
+
+	snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
+	obj = bpf_object__open_file(filename, NULL);
+	if (libbpf_get_error(obj)) {
+		fprintf(stderr, "ERROR: opening BPF object file failed\n");
+		return 0;
+	}
+
+	prog = bpf_object__find_program_by_name(obj, "trace_sys_connect");
+	if (!prog) {
+		printf("finding a prog in obj file failed\n");
+		goto cleanup;
+	}
+
+	/* load BPF program */
+	if (bpf_object__load(obj)) {
+		fprintf(stderr, "ERROR: loading BPF object file failed\n");
+		goto cleanup;
+	}
+
+	map_fd[0] = bpf_object__find_map_fd_by_name(obj, "port_a");
+	map_fd[1] = bpf_object__find_map_fd_by_name(obj, "port_h");
+	map_fd[2] = bpf_object__find_map_fd_by_name(obj, "reg_result_h");
+	map_fd[3] = bpf_object__find_map_fd_by_name(obj, "inline_result_h");
+	map_fd[4] = bpf_object__find_map_fd_by_name(obj, "a_of_port_a");
+	map_fd[5] = bpf_object__find_map_fd_by_name(obj, "h_of_port_a");
+	map_fd[6] = bpf_object__find_map_fd_by_name(obj, "h_of_port_h");
+	if (map_fd[0] < 0 || map_fd[1] < 0 || map_fd[2] < 0 ||
+	    map_fd[3] < 0 || map_fd[4] < 0 || map_fd[5] < 0 || map_fd[6] < 0) {
+		fprintf(stderr, "ERROR: finding a map in obj file failed\n");
+		goto cleanup;
+	}
+
+	link = bpf_program__attach(prog);
+	if (libbpf_get_error(link)) {
+		fprintf(stderr, "ERROR: bpf_program__attach failed\n");
+		link = NULL;
+		goto cleanup;
+	}
+
+	test_map_in_map();
+
+cleanup:
+	bpf_link__destroy(link);
+	bpf_object__close(obj);
+	return 0;
+}

linux-7.2.3/samples/bpf/trace_event_kern.c

@@ -0,0 +1,79 @@
+/* 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 <linux/ptrace.h>
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/bpf_perf_event.h>
+#include <uapi/linux/perf_event.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+struct key_t {
+	char comm[TASK_COMM_LEN];
+	u32 kernstack;
+	u32 userstack;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, struct key_t);
+	__type(value, u64);
+	__uint(max_entries, 10000);
+} counts SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_STACK_TRACE);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, PERF_MAX_STACK_DEPTH * sizeof(u64));
+	__uint(max_entries, 10000);
+} stackmap SEC(".maps");
+
+#define KERN_STACKID_FLAGS (0 | BPF_F_FAST_STACK_CMP)
+#define USER_STACKID_FLAGS (0 | BPF_F_FAST_STACK_CMP | BPF_F_USER_STACK)
+
+SEC("perf_event")
+int bpf_prog1(struct bpf_perf_event_data *ctx)
+{
+	char time_fmt1[] = "Time Enabled: %llu, Time Running: %llu";
+	char time_fmt2[] = "Get Time Failed, ErrCode: %d";
+	char addr_fmt[] = "Address recorded on event: %llx";
+	char fmt[] = "CPU-%d period %lld ip %llx";
+	u32 cpu = bpf_get_smp_processor_id();
+	struct bpf_perf_event_value value_buf;
+	struct key_t key;
+	u64 *val, one = 1;
+	int ret;
+
+	if (ctx->sample_period < 10000)
+		/* ignore warmup */
+		return 0;
+	bpf_get_current_comm(&key.comm, sizeof(key.comm));
+	key.kernstack = bpf_get_stackid(ctx, &stackmap, KERN_STACKID_FLAGS);
+	key.userstack = bpf_get_stackid(ctx, &stackmap, USER_STACKID_FLAGS);
+	if ((int)key.kernstack < 0 && (int)key.userstack < 0) {
+		bpf_trace_printk(fmt, sizeof(fmt), cpu, ctx->sample_period,
+				 PT_REGS_IP(&ctx->regs));
+		return 0;
+	}
+
+	ret = bpf_perf_prog_read_value(ctx, (void *)&value_buf, sizeof(struct bpf_perf_event_value));
+	if (!ret)
+	  bpf_trace_printk(time_fmt1, sizeof(time_fmt1), value_buf.enabled, value_buf.running);
+	else
+	  bpf_trace_printk(time_fmt2, sizeof(time_fmt2), ret);
+
+	if (ctx->addr != 0)
+	  bpf_trace_printk(addr_fmt, sizeof(addr_fmt), ctx->addr);
+
+	val = bpf_map_lookup_elem(&counts, &key);
+	if (val)
+		(*val)++;
+	else
+		bpf_map_update_elem(&counts, &key, &one, BPF_NOEXIST);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";

linux-7.2.3/samples/bpf/trace_event_user.c

@@ -0,0 +1,352 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2016 Facebook
+ */
+#include <stdio.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <linux/perf_event.h>
+#include <linux/bpf.h>
+#include <signal.h>
+#include <errno.h>
+#include <sys/resource.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "perf-sys.h"
+#include "trace_helpers.h"
+
+#define SAMPLE_FREQ 50
+
+static int pid;
+/* counts, stackmap */
+static int map_fd[2];
+struct bpf_program *prog;
+static bool sys_read_seen, sys_write_seen;
+
+static void print_ksym(__u64 addr)
+{
+	struct ksym *sym;
+
+	if (!addr)
+		return;
+	sym = ksym_search(addr);
+	if (!sym) {
+		printf("ksym not found. Is kallsyms loaded?\n");
+		return;
+	}
+
+	printf("%s;", sym->name);
+	if (!strstr(sym->name, "sys_read"))
+		sys_read_seen = true;
+	else if (!strstr(sym->name, "sys_write"))
+		sys_write_seen = true;
+}
+
+static void print_addr(__u64 addr)
+{
+	if (!addr)
+		return;
+	printf("%llx;", addr);
+}
+
+#define TASK_COMM_LEN 16
+
+struct key_t {
+	char comm[TASK_COMM_LEN];
+	__u32 kernstack;
+	__u32 userstack;
+};
+
+static void print_stack(struct key_t *key, __u64 count)
+{
+	__u64 ip[PERF_MAX_STACK_DEPTH] = {};
+	static bool warned;
+	int i;
+
+	printf("%3lld %s;", count, key->comm);
+	if (bpf_map_lookup_elem(map_fd[1], &key->kernstack, ip) != 0) {
+		printf("---;");
+	} else {
+		for (i = PERF_MAX_STACK_DEPTH - 1; i >= 0; i--)
+			print_ksym(ip[i]);
+	}
+	printf("-;");
+	if (bpf_map_lookup_elem(map_fd[1], &key->userstack, ip) != 0) {
+		printf("---;");
+	} else {
+		for (i = PERF_MAX_STACK_DEPTH - 1; i >= 0; i--)
+			print_addr(ip[i]);
+	}
+	if (count < 6)
+		printf("\r");
+	else
+		printf("\n");
+
+	if (key->kernstack == -EEXIST && !warned) {
+		printf("stackmap collisions seen. Consider increasing size\n");
+		warned = true;
+	} else if ((int)key->kernstack < 0 && (int)key->userstack < 0) {
+		printf("err stackid %d %d\n", key->kernstack, key->userstack);
+	}
+}
+
+static void err_exit(int err)
+{
+	kill(pid, SIGKILL);
+	exit(err);
+}
+
+static void print_stacks(void)
+{
+	struct key_t key = {}, next_key;
+	__u64 value;
+	__u32 stackid = 0, next_id;
+	int error = 1, fd = map_fd[0], stack_map = map_fd[1];
+
+	sys_read_seen = sys_write_seen = false;
+	while (bpf_map_get_next_key(fd, &key, &next_key) == 0) {
+		bpf_map_lookup_elem(fd, &next_key, &value);
+		print_stack(&next_key, value);
+		bpf_map_delete_elem(fd, &next_key);
+		key = next_key;
+	}
+	printf("\n");
+	if (!sys_read_seen || !sys_write_seen) {
+		printf("BUG kernel stack doesn't contain sys_read() and sys_write()\n");
+		err_exit(error);
+	}
+
+	/* clear stack map */
+	while (bpf_map_get_next_key(stack_map, &stackid, &next_id) == 0) {
+		bpf_map_delete_elem(stack_map, &next_id);
+		stackid = next_id;
+	}
+}
+
+static inline int generate_load(void)
+{
+	if (system("dd if=/dev/zero of=/dev/null count=5000k status=none") < 0) {
+		printf("failed to generate some load with dd: %s\n", strerror(errno));
+		return -1;
+	}
+
+	return 0;
+}
+
+static void test_perf_event_all_cpu(struct perf_event_attr *attr)
+{
+	int nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
+	struct bpf_link **links = calloc(nr_cpus, sizeof(struct bpf_link *));
+	int i, pmu_fd, error = 1;
+
+	if (!links) {
+		printf("malloc of links failed\n");
+		goto err;
+	}
+
+	/* system wide perf event, no need to inherit */
+	attr->inherit = 0;
+
+	/* open perf_event on all cpus */
+	for (i = 0; i < nr_cpus; i++) {
+		pmu_fd = sys_perf_event_open(attr, -1, i, -1, 0);
+		if (pmu_fd < 0) {
+			printf("sys_perf_event_open failed\n");
+			goto all_cpu_err;
+		}
+		links[i] = bpf_program__attach_perf_event(prog, pmu_fd);
+		if (libbpf_get_error(links[i])) {
+			printf("bpf_program__attach_perf_event failed\n");
+			links[i] = NULL;
+			close(pmu_fd);
+			goto all_cpu_err;
+		}
+	}
+
+	if (generate_load() < 0)
+		goto all_cpu_err;
+
+	print_stacks();
+	error = 0;
+all_cpu_err:
+	for (i--; i >= 0; i--)
+		bpf_link__destroy(links[i]);
+err:
+	free(links);
+	if (error)
+		err_exit(error);
+}
+
+static void test_perf_event_task(struct perf_event_attr *attr)
+{
+	struct bpf_link *link = NULL;
+	int pmu_fd, error = 1;
+
+	/* per task perf event, enable inherit so the "dd ..." command can be traced properly.
+	 * Enabling inherit will cause bpf_perf_prog_read_time helper failure.
+	 */
+	attr->inherit = 1;
+
+	/* open task bound event */
+	pmu_fd = sys_perf_event_open(attr, 0, -1, -1, 0);
+	if (pmu_fd < 0) {
+		printf("sys_perf_event_open failed\n");
+		goto err;
+	}
+	link = bpf_program__attach_perf_event(prog, pmu_fd);
+	if (libbpf_get_error(link)) {
+		printf("bpf_program__attach_perf_event failed\n");
+		link = NULL;
+		close(pmu_fd);
+		goto err;
+	}
+
+	if (generate_load() < 0)
+		goto err;
+
+	print_stacks();
+	error = 0;
+err:
+	bpf_link__destroy(link);
+	if (error)
+		err_exit(error);
+}
+
+static void test_bpf_perf_event(void)
+{
+	struct perf_event_attr attr_type_hw = {
+		.sample_freq = SAMPLE_FREQ,
+		.freq = 1,
+		.type = PERF_TYPE_HARDWARE,
+		.config = PERF_COUNT_HW_CPU_CYCLES,
+	};
+	struct perf_event_attr attr_type_sw = {
+		.sample_freq = SAMPLE_FREQ,
+		.freq = 1,
+		.type = PERF_TYPE_SOFTWARE,
+		.config = PERF_COUNT_SW_CPU_CLOCK,
+	};
+	struct perf_event_attr attr_hw_cache_l1d = {
+		.sample_freq = SAMPLE_FREQ,
+		.freq = 1,
+		.type = PERF_TYPE_HW_CACHE,
+		.config =
+			PERF_COUNT_HW_CACHE_L1D |
+			(PERF_COUNT_HW_CACHE_OP_READ << 8) |
+			(PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16),
+	};
+	struct perf_event_attr attr_hw_cache_branch_miss = {
+		.sample_freq = SAMPLE_FREQ,
+		.freq = 1,
+		.type = PERF_TYPE_HW_CACHE,
+		.config =
+			PERF_COUNT_HW_CACHE_BPU |
+			(PERF_COUNT_HW_CACHE_OP_READ << 8) |
+			(PERF_COUNT_HW_CACHE_RESULT_MISS << 16),
+	};
+	struct perf_event_attr attr_type_raw = {
+		.sample_freq = SAMPLE_FREQ,
+		.freq = 1,
+		.type = PERF_TYPE_RAW,
+		/* Intel Instruction Retired */
+		.config = 0xc0,
+	};
+	struct perf_event_attr attr_type_raw_lock_load = {
+		.sample_freq = SAMPLE_FREQ,
+		.freq = 1,
+		.type = PERF_TYPE_RAW,
+		/* Intel MEM_UOPS_RETIRED.LOCK_LOADS */
+		.config = 0x21d0,
+		/* Request to record lock address from PEBS */
+		.sample_type = PERF_SAMPLE_ADDR,
+		/* Record address value requires precise event */
+		.precise_ip = 2,
+	};
+
+	printf("Test HW_CPU_CYCLES\n");
+	test_perf_event_all_cpu(&attr_type_hw);
+	test_perf_event_task(&attr_type_hw);
+
+	printf("Test SW_CPU_CLOCK\n");
+	test_perf_event_all_cpu(&attr_type_sw);
+	test_perf_event_task(&attr_type_sw);
+
+	printf("Test HW_CACHE_L1D\n");
+	test_perf_event_all_cpu(&attr_hw_cache_l1d);
+	test_perf_event_task(&attr_hw_cache_l1d);
+
+	printf("Test HW_CACHE_BPU\n");
+	test_perf_event_all_cpu(&attr_hw_cache_branch_miss);
+	test_perf_event_task(&attr_hw_cache_branch_miss);
+
+	printf("Test Instruction Retired\n");
+	test_perf_event_all_cpu(&attr_type_raw);
+	test_perf_event_task(&attr_type_raw);
+
+	printf("Test Lock Load\n");
+	test_perf_event_all_cpu(&attr_type_raw_lock_load);
+	test_perf_event_task(&attr_type_raw_lock_load);
+
+	printf("*** PASS ***\n");
+}
+
+
+int main(int argc, char **argv)
+{
+	struct bpf_object *obj = NULL;
+	char filename[256];
+	int error = 1;
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	signal(SIGINT, err_exit);
+	signal(SIGTERM, err_exit);
+
+	if (load_kallsyms()) {
+		printf("failed to process /proc/kallsyms\n");
+		goto cleanup;
+	}
+
+	obj = bpf_object__open_file(filename, NULL);
+	if (libbpf_get_error(obj)) {
+		printf("opening BPF object file failed\n");
+		obj = NULL;
+		goto cleanup;
+	}
+
+	prog = bpf_object__find_program_by_name(obj, "bpf_prog1");
+	if (!prog) {
+		printf("finding a prog in obj file failed\n");
+		goto cleanup;
+	}
+
+	/* load BPF program */
+	if (bpf_object__load(obj)) {
+		printf("loading BPF object file failed\n");
+		goto cleanup;
+	}
+
+	map_fd[0] = bpf_object__find_map_fd_by_name(obj, "counts");
+	map_fd[1] = bpf_object__find_map_fd_by_name(obj, "stackmap");
+	if (map_fd[0] < 0 || map_fd[1] < 0) {
+		printf("finding a counts/stackmap map in obj file failed\n");
+		goto cleanup;
+	}
+
+	pid = fork();
+	if (pid == 0) {
+		read_trace_pipe();
+		return 0;
+	} else if (pid == -1) {
+		printf("couldn't spawn process\n");
+		goto cleanup;
+	}
+
+	test_bpf_perf_event();
+	error = 0;
+
+cleanup:
+	bpf_object__close(obj);
+	err_exit(error);
+}

linux-7.2.3/samples/bpf/trace_output.bpf.c

@@ -0,0 +1,29 @@
+#include "vmlinux.h"
+#include <linux/version.h>
+#include <bpf/bpf_helpers.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(u32));
+	__uint(max_entries, 2);
+} my_map SEC(".maps");
+
+SEC("ksyscall/write")
+int bpf_prog1(struct pt_regs *ctx)
+{
+	struct S {
+		u64 pid;
+		u64 cookie;
+	} data;
+
+	data.pid = bpf_get_current_pid_tgid();
+	data.cookie = 0x12345678;
+
+	bpf_perf_event_output(ctx, &my_map, 0, &data, sizeof(data));
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;

linux-7.2.3/samples/bpf/trace_output_user.c

@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <stdio.h>
+#include <fcntl.h>
+#include <poll.h>
+#include <time.h>
+#include <signal.h>
+#include <bpf/libbpf.h>
+
+static __u64 time_get_ns(void)
+{
+	struct timespec ts;
+
+	clock_gettime(CLOCK_MONOTONIC, &ts);
+	return ts.tv_sec * 1000000000ull + ts.tv_nsec;
+}
+
+static __u64 start_time;
+static __u64 cnt;
+
+#define MAX_CNT 100000ll
+
+static void print_bpf_output(void *ctx, int cpu, void *data, __u32 size)
+{
+	struct {
+		__u64 pid;
+		__u64 cookie;
+	} *e = data;
+
+	if (e->cookie != 0x12345678) {
+		printf("BUG pid %llx cookie %llx sized %d\n",
+		       e->pid, e->cookie, size);
+		return;
+	}
+
+	cnt++;
+
+	if (cnt == MAX_CNT) {
+		printf("recv %lld events per sec\n",
+		       MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
+		return;
+	}
+}
+
+int main(int argc, char **argv)
+{
+	struct bpf_link *link = NULL;
+	struct bpf_program *prog;
+	struct perf_buffer *pb;
+	struct bpf_object *obj;
+	int map_fd, ret = 0;
+	char filename[256];
+	FILE *f;
+
+	snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
+	obj = bpf_object__open_file(filename, NULL);
+	if (libbpf_get_error(obj)) {
+		fprintf(stderr, "ERROR: opening BPF object file failed\n");
+		return 0;
+	}
+
+	/* load BPF program */
+	if (bpf_object__load(obj)) {
+		fprintf(stderr, "ERROR: loading BPF object file failed\n");
+		goto cleanup;
+	}
+
+	map_fd = bpf_object__find_map_fd_by_name(obj, "my_map");
+	if (map_fd < 0) {
+		fprintf(stderr, "ERROR: finding a map in obj file failed\n");
+		goto cleanup;
+	}
+
+	prog = bpf_object__find_program_by_name(obj, "bpf_prog1");
+	if (libbpf_get_error(prog)) {
+		fprintf(stderr, "ERROR: finding a prog in obj file failed\n");
+		goto cleanup;
+	}
+
+	link = bpf_program__attach(prog);
+	if (libbpf_get_error(link)) {
+		fprintf(stderr, "ERROR: bpf_program__attach failed\n");
+		link = NULL;
+		goto cleanup;
+	}
+
+	pb = perf_buffer__new(map_fd, 8, print_bpf_output, NULL, NULL, NULL);
+	ret = libbpf_get_error(pb);
+	if (ret) {
+		printf("failed to setup perf_buffer: %d\n", ret);
+		return 1;
+	}
+
+	f = popen("taskset 1 dd if=/dev/zero of=/dev/null", "r");
+	(void) f;
+
+	start_time = time_get_ns();
+	while ((ret = perf_buffer__poll(pb, 1000)) >= 0 && cnt < MAX_CNT) {
+	}
+	kill(0, SIGINT);
+
+cleanup:
+	bpf_link__destroy(link);
+	bpf_object__close(obj);
+	return ret;
+}

linux-7.2.3/samples/bpf/tracex1.bpf.c

@@ -0,0 +1,47 @@
+/* Copyright (c) 2013-2015 PLUMgrid, http://plumgrid.com
+ *
+ * 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 "vmlinux.h"
+#include "net_shared.h"
+#include <linux/version.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_tracing.h>
+
+/* kprobe is NOT a stable ABI
+ * kernel functions can be removed, renamed or completely change semantics.
+ * Number of arguments and their positions can change, etc.
+ * In such case this bpf+kprobe example will no longer be meaningful
+ */
+SEC("kprobe.multi/__netif_receive_skb_core*")
+int bpf_prog1(struct pt_regs *ctx)
+{
+	/* attaches to kprobe __netif_receive_skb_core,
+	 * looks for packets on loopback device and prints them
+	 * (wildcard is used for avoiding symbol mismatch due to optimization)
+	 */
+	char devname[IFNAMSIZ];
+	struct net_device *dev;
+	struct sk_buff *skb;
+	int len;
+
+	bpf_core_read(&skb, sizeof(skb), (void *)PT_REGS_PARM1(ctx));
+	dev = BPF_CORE_READ(skb, dev);
+	len = BPF_CORE_READ(skb, len);
+
+	BPF_CORE_READ_STR_INTO(&devname, dev, name);
+
+	if (devname[0] == 'l' && devname[1] == 'o') {
+		char fmt[] = "skb %p len %d\n";
+		/* using bpf_trace_printk() for DEBUG ONLY */
+		bpf_trace_printk(fmt, sizeof(fmt), skb, len);
+	}
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;

linux-7.2.3/samples/bpf/tracex1_user.c

@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <unistd.h>
+#include <bpf/libbpf.h>
+#include "trace_helpers.h"
+
+int main(int ac, char **argv)
+{
+	struct bpf_link *link = NULL;
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	char filename[256];
+	FILE *f;
+
+	snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
+	obj = bpf_object__open_file(filename, NULL);
+	if (libbpf_get_error(obj)) {
+		fprintf(stderr, "ERROR: opening BPF object file failed\n");
+		return 0;
+	}
+
+	prog = bpf_object__find_program_by_name(obj, "bpf_prog1");
+	if (!prog) {
+		fprintf(stderr, "ERROR: finding a prog in obj file failed\n");
+		goto cleanup;
+	}
+
+	/* load BPF program */
+	if (bpf_object__load(obj)) {
+		fprintf(stderr, "ERROR: loading BPF object file failed\n");
+		goto cleanup;
+	}
+
+	link = bpf_program__attach(prog);
+	if (libbpf_get_error(link)) {
+		fprintf(stderr, "ERROR: bpf_program__attach failed\n");
+		link = NULL;
+		goto cleanup;
+	}
+
+	f = popen("taskset 1 ping -c5 localhost", "r");
+	(void) f;
+
+	read_trace_pipe();
+
+cleanup:
+	bpf_link__destroy(link);
+	bpf_object__close(obj);
+	return 0;
+}

linux-7.2.3/samples/bpf/tracex3.bpf.c

@@ -0,0 +1,100 @@
+/* Copyright (c) 2013-2015 PLUMgrid, http://plumgrid.com
+ *
+ * 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 "vmlinux.h"
+#include <linux/version.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+struct start_key {
+	dev_t dev;
+	u32 _pad;
+	sector_t sector;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, long);
+	__type(value, u64);
+	__uint(max_entries, 4096);
+} my_map SEC(".maps");
+
+/* from /sys/kernel/tracing/events/block/block_io_start/format */
+SEC("tracepoint/block/block_io_start")
+int bpf_prog1(struct trace_event_raw_block_rq *ctx)
+{
+	u64 val = bpf_ktime_get_ns();
+	struct start_key key = {
+		.dev = ctx->dev,
+		.sector = ctx->sector
+	};
+
+	bpf_map_update_elem(&my_map, &key, &val, BPF_ANY);
+	return 0;
+}
+
+static unsigned int log2l(unsigned long long n)
+{
+#define S(k) if (n >= (1ull << k)) { i += k; n >>= k; }
+	int i = -(n == 0);
+	S(32); S(16); S(8); S(4); S(2); S(1);
+	return i;
+#undef S
+}
+
+#define SLOTS 100
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(u64));
+	__uint(max_entries, SLOTS);
+} lat_map SEC(".maps");
+
+/* from /sys/kernel/tracing/events/block/block_io_done/format */
+SEC("tracepoint/block/block_io_done")
+int bpf_prog2(struct trace_event_raw_block_rq *ctx)
+{
+	struct start_key key = {
+		.dev = ctx->dev,
+		.sector = ctx->sector
+	};
+
+	u64 *value, l, base;
+	u32 index;
+
+	value = bpf_map_lookup_elem(&my_map, &key);
+	if (!value)
+		return 0;
+
+	u64 cur_time = bpf_ktime_get_ns();
+	u64 delta = cur_time - *value;
+
+	bpf_map_delete_elem(&my_map, &key);
+
+	/* the lines below are computing index = log10(delta)*10
+	 * using integer arithmetic
+	 * index = 29 ~ 1 usec
+	 * index = 59 ~ 1 msec
+	 * index = 89 ~ 1 sec
+	 * index = 99 ~ 10sec or more
+	 * log10(x)*10 = log2(x)*10/log2(10) = log2(x)*3
+	 */
+	l = log2l(delta);
+	base = 1ll << l;
+	index = (l * 64 + (delta - base) * 64 / base) * 3 / 64;
+
+	if (index >= SLOTS)
+		index = SLOTS - 1;
+
+	value = bpf_map_lookup_elem(&lat_map, &index);
+	if (value)
+		*value += 1;
+
+	return 0;
+}
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;

linux-7.2.3/samples/bpf/tracex3_user.c

@@ -0,0 +1,183 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2013-2015 PLUMgrid, http://plumgrid.com
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <unistd.h>
+#include <stdbool.h>
+#include <string.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "bpf_util.h"
+
+#define SLOTS 100
+
+static void clear_stats(int fd)
+{
+	unsigned int nr_cpus = bpf_num_possible_cpus();
+	__u64 values[nr_cpus];
+	__u32 key;
+
+	memset(values, 0, sizeof(values));
+	for (key = 0; key < SLOTS; key++)
+		bpf_map_update_elem(fd, &key, values, BPF_ANY);
+}
+
+const char *color[] = {
+	"\033[48;5;255m",
+	"\033[48;5;252m",
+	"\033[48;5;250m",
+	"\033[48;5;248m",
+	"\033[48;5;246m",
+	"\033[48;5;244m",
+	"\033[48;5;242m",
+	"\033[48;5;240m",
+	"\033[48;5;238m",
+	"\033[48;5;236m",
+	"\033[48;5;234m",
+	"\033[48;5;232m",
+};
+const int num_colors = ARRAY_SIZE(color);
+
+const char nocolor[] = "\033[00m";
+
+const char *sym[] = {
+	" ",
+	" ",
+	".",
+	".",
+	"*",
+	"*",
+	"o",
+	"o",
+	"O",
+	"O",
+	"#",
+	"#",
+};
+
+bool full_range = false;
+bool text_only = false;
+
+static void print_banner(void)
+{
+	if (full_range)
+		printf("|1ns     |10ns     |100ns    |1us      |10us     |100us"
+		       "    |1ms      |10ms     |100ms    |1s       |10s\n");
+	else
+		printf("|1us      |10us     |100us    |1ms      |10ms     "
+		       "|100ms    |1s       |10s\n");
+}
+
+static void print_hist(int fd)
+{
+	unsigned int nr_cpus = bpf_num_possible_cpus();
+	__u64 total_events = 0;
+	long values[nr_cpus];
+	__u64 max_cnt = 0;
+	__u64 cnt[SLOTS];
+	__u64 value;
+	__u32 key;
+	int i;
+
+	for (key = 0; key < SLOTS; key++) {
+		bpf_map_lookup_elem(fd, &key, values);
+		value = 0;
+		for (i = 0; i < nr_cpus; i++)
+			value += values[i];
+		cnt[key] = value;
+		total_events += value;
+		if (value > max_cnt)
+			max_cnt = value;
+	}
+	clear_stats(fd);
+	for (key = full_range ? 0 : 29; key < SLOTS; key++) {
+		int c = num_colors * cnt[key] / (max_cnt + 1);
+
+		if (text_only)
+			printf("%s", sym[c]);
+		else
+			printf("%s %s", color[c], nocolor);
+	}
+	printf(" # %lld\n", total_events);
+}
+
+int main(int ac, char **argv)
+{
+	struct bpf_link *links[2];
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	char filename[256];
+	int map_fd, i, j = 0;
+
+	for (i = 1; i < ac; i++) {
+		if (strcmp(argv[i], "-a") == 0) {
+			full_range = true;
+		} else if (strcmp(argv[i], "-t") == 0) {
+			text_only = true;
+		} else if (strcmp(argv[i], "-h") == 0) {
+			printf("Usage:\n"
+			       "  -a display wider latency range\n"
+			       "  -t text only\n");
+			return 1;
+		}
+	}
+
+	snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
+	obj = bpf_object__open_file(filename, NULL);
+	if (libbpf_get_error(obj)) {
+		fprintf(stderr, "ERROR: opening BPF object file failed\n");
+		return 0;
+	}
+
+	/* load BPF program */
+	if (bpf_object__load(obj)) {
+		fprintf(stderr, "ERROR: loading BPF object file failed\n");
+		goto cleanup;
+	}
+
+	map_fd = bpf_object__find_map_fd_by_name(obj, "lat_map");
+	if (map_fd < 0) {
+		fprintf(stderr, "ERROR: finding a map in obj file failed\n");
+		goto cleanup;
+	}
+
+	bpf_object__for_each_program(prog, obj) {
+		links[j] = bpf_program__attach(prog);
+		if (libbpf_get_error(links[j])) {
+			fprintf(stderr, "ERROR: bpf_program__attach failed\n");
+			links[j] = NULL;
+			goto cleanup;
+		}
+		j++;
+	}
+
+	printf("  heatmap of IO latency\n");
+	if (text_only)
+		printf("  %s", sym[num_colors - 1]);
+	else
+		printf("  %s %s", color[num_colors - 1], nocolor);
+	printf(" - many events with this latency\n");
+
+	if (text_only)
+		printf("  %s", sym[0]);
+	else
+		printf("  %s %s", color[0], nocolor);
+	printf(" - few events\n");
+
+	for (i = 0; ; i++) {
+		if (i % 20 == 0)
+			print_banner();
+		print_hist(map_fd);
+		sleep(2);
+	}
+
+cleanup:
+	for (j--; j >= 0; j--)
+		bpf_link__destroy(links[j]);
+
+	bpf_object__close(obj);
+	return 0;
+}

linux-7.2.3/samples/bpf/tracex4.bpf.c

@@ -0,0 +1,54 @@
+/* Copyright (c) 2015 PLUMgrid, http://plumgrid.com
+ *
+ * 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 "vmlinux.h"
+#include <linux/version.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+struct pair {
+	u64 val;
+	u64 ip;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, long);
+	__type(value, struct pair);
+	__uint(max_entries, 1000000);
+} my_map SEC(".maps");
+
+/* kprobe is NOT a stable ABI. If kernel internals change this bpf+kprobe
+ * example will no longer be meaningful
+ */
+SEC("kprobe/kmem_cache_free")
+int bpf_prog1(struct pt_regs *ctx)
+{
+	long ptr = PT_REGS_PARM2(ctx);
+
+	bpf_map_delete_elem(&my_map, &ptr);
+	return 0;
+}
+
+SEC("kretprobe/kmem_cache_alloc_node_noprof")
+int bpf_prog2(struct pt_regs *ctx)
+{
+	long ptr = PT_REGS_RC(ctx);
+	long ip = 0;
+
+	/* get ip address of kmem_cache_alloc_node_noprof() caller */
+	BPF_KRETPROBE_READ_RET_IP(ip, ctx);
+
+	struct pair v = {
+		.val = bpf_ktime_get_ns(),
+		.ip = ip,
+	};
+
+	bpf_map_update_elem(&my_map, &ptr, &v, BPF_ANY);
+	return 0;
+}
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;

linux-7.2.3/samples/bpf/tracex4_user.c

@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2015 PLUMgrid, http://plumgrid.com
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <unistd.h>
+#include <stdbool.h>
+#include <string.h>
+#include <time.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+struct pair {
+	long long val;
+	__u64 ip;
+};
+
+static __u64 time_get_ns(void)
+{
+	struct timespec ts;
+
+	clock_gettime(CLOCK_MONOTONIC, &ts);
+	return ts.tv_sec * 1000000000ull + ts.tv_nsec;
+}
+
+static void print_old_objects(int fd)
+{
+	long long val = time_get_ns();
+	__u64 key, next_key;
+	struct pair v;
+
+	key = write(1, "\e[1;1H\e[2J", 11); /* clear screen */
+
+	key = -1;
+	while (bpf_map_get_next_key(fd, &key, &next_key) == 0) {
+		bpf_map_lookup_elem(fd, &next_key, &v);
+		key = next_key;
+		if (val - v.val < 1000000000ll)
+			/* object was allocated more then 1 sec ago */
+			continue;
+		printf("obj 0x%llx is %2lldsec old was allocated at ip %llx\n",
+		       next_key, (val - v.val) / 1000000000ll, v.ip);
+	}
+}
+
+int main(int ac, char **argv)
+{
+	struct bpf_link *links[2];
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	char filename[256];
+	int map_fd, j = 0;
+
+	snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
+	obj = bpf_object__open_file(filename, NULL);
+	if (libbpf_get_error(obj)) {
+		fprintf(stderr, "ERROR: opening BPF object file failed\n");
+		return 0;
+	}
+
+	/* load BPF program */
+	if (bpf_object__load(obj)) {
+		fprintf(stderr, "ERROR: loading BPF object file failed\n");
+		goto cleanup;
+	}
+
+	map_fd = bpf_object__find_map_fd_by_name(obj, "my_map");
+	if (map_fd < 0) {
+		fprintf(stderr, "ERROR: finding a map in obj file failed\n");
+		goto cleanup;
+	}
+
+	bpf_object__for_each_program(prog, obj) {
+		links[j] = bpf_program__attach(prog);
+		if (libbpf_get_error(links[j])) {
+			fprintf(stderr, "ERROR: bpf_program__attach failed\n");
+			links[j] = NULL;
+			goto cleanup;
+		}
+		j++;
+	}
+
+	while (1) {
+		print_old_objects(map_fd);
+		sleep(1);
+	}
+
+cleanup:
+	for (j--; j >= 0; j--)
+		bpf_link__destroy(links[j]);
+
+	bpf_object__close(obj);
+	return 0;
+}

linux-7.2.3/samples/bpf/tracex5.bpf.c

@@ -0,0 +1,93 @@
+/* Copyright (c) 2015 PLUMgrid, http://plumgrid.com
+ *
+ * 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 "vmlinux.h"
+#include "syscall_nrs.h"
+#include <linux/version.h>
+#include <uapi/linux/unistd.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+#define __stringify(x) #x
+#define PROG(F) SEC("kprobe/"__stringify(F)) int bpf_func_##F
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(u32));
+#ifdef __mips__
+	__uint(max_entries, 6000); /* MIPS n64 syscalls start at 5000 */
+#else
+	__uint(max_entries, 1024);
+#endif
+} progs SEC(".maps");
+
+SEC("kprobe/__seccomp_filter")
+int bpf_prog1(struct pt_regs *ctx)
+{
+	int sc_nr = (int)PT_REGS_PARM1(ctx);
+
+	/* dispatch into next BPF program depending on syscall number */
+	bpf_tail_call(ctx, &progs, sc_nr);
+
+	/* fall through -> unknown syscall */
+	if (sc_nr >= __NR_getuid && sc_nr <= __NR_getsid) {
+		char fmt[] = "syscall=%d (one of get/set uid/pid/gid)\n";
+		bpf_trace_printk(fmt, sizeof(fmt), sc_nr);
+	}
+	return 0;
+}
+
+/* we jump here when syscall number == __NR_write */
+PROG(SYS__NR_write)(struct pt_regs *ctx)
+{
+	struct seccomp_data sd;
+
+	bpf_core_read(&sd, sizeof(sd), (void *)PT_REGS_PARM2(ctx));
+	if (sd.args[2] == 512) {
+		char fmt[] = "write(fd=%d, buf=%p, size=%d)\n";
+		bpf_trace_printk(fmt, sizeof(fmt),
+				 sd.args[0], sd.args[1], sd.args[2]);
+	}
+	return 0;
+}
+
+PROG(SYS__NR_read)(struct pt_regs *ctx)
+{
+	struct seccomp_data sd;
+
+	bpf_core_read(&sd, sizeof(sd), (void *)PT_REGS_PARM2(ctx));
+	if (sd.args[2] > 128 && sd.args[2] <= 1024) {
+		char fmt[] = "read(fd=%d, buf=%p, size=%d)\n";
+		bpf_trace_printk(fmt, sizeof(fmt),
+				 sd.args[0], sd.args[1], sd.args[2]);
+	}
+	return 0;
+}
+
+#ifdef __NR_mmap2
+PROG(SYS__NR_mmap2)(struct pt_regs *ctx)
+{
+	char fmt[] = "mmap2\n";
+
+	bpf_trace_printk(fmt, sizeof(fmt));
+	return 0;
+}
+#endif
+
+#ifdef __NR_mmap
+PROG(SYS__NR_mmap)(struct pt_regs *ctx)
+{
+	char fmt[] = "mmap\n";
+
+	bpf_trace_printk(fmt, sizeof(fmt));
+	return 0;
+}
+#endif
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;

linux-7.2.3/samples/bpf/tracex5_user.c

@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <linux/filter.h>
+#include <linux/seccomp.h>
+#include <sys/prctl.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "trace_helpers.h"
+#include "bpf_util.h"
+
+#ifdef __mips__
+#define	MAX_ENTRIES  6000 /* MIPS n64 syscalls start at 5000 */
+#else
+#define	MAX_ENTRIES  1024
+#endif
+
+/* install fake seccomp program to enable seccomp code path inside the kernel,
+ * so that our kprobe attached to seccomp_phase1() can be triggered
+ */
+static void install_accept_all_seccomp(void)
+{
+	struct sock_filter filter[] = {
+		BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW),
+	};
+	struct sock_fprog prog = {
+		.len = (unsigned short)ARRAY_SIZE(filter),
+		.filter = filter,
+	};
+	if (prctl(PR_SET_SECCOMP, 2, &prog))
+		perror("prctl");
+}
+
+int main(int ac, char **argv)
+{
+	struct bpf_link *link = NULL;
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	int key, fd, progs_fd;
+	const char *section;
+	char filename[256];
+	FILE *f;
+
+	snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
+	obj = bpf_object__open_file(filename, NULL);
+	if (libbpf_get_error(obj)) {
+		fprintf(stderr, "ERROR: opening BPF object file failed\n");
+		return 0;
+	}
+
+	prog = bpf_object__find_program_by_name(obj, "bpf_prog1");
+	if (!prog) {
+		printf("finding a prog in obj file failed\n");
+		goto cleanup;
+	}
+
+	/* load BPF program */
+	if (bpf_object__load(obj)) {
+		fprintf(stderr, "ERROR: loading BPF object file failed\n");
+		goto cleanup;
+	}
+
+	link = bpf_program__attach(prog);
+	if (libbpf_get_error(link)) {
+		fprintf(stderr, "ERROR: bpf_program__attach failed\n");
+		link = NULL;
+		goto cleanup;
+	}
+
+	progs_fd = bpf_object__find_map_fd_by_name(obj, "progs");
+	if (progs_fd < 0) {
+		fprintf(stderr, "ERROR: finding a map in obj file failed\n");
+		goto cleanup;
+	}
+
+	bpf_object__for_each_program(prog, obj) {
+		section = bpf_program__section_name(prog);
+		/* register only syscalls to PROG_ARRAY */
+		if (sscanf(section, "kprobe/%d", &key) != 1)
+			continue;
+
+		fd = bpf_program__fd(prog);
+		bpf_map_update_elem(progs_fd, &key, &fd, BPF_ANY);
+	}
+
+	install_accept_all_seccomp();
+
+	f = popen("dd if=/dev/zero of=/dev/null count=5", "r");
+	(void) f;
+
+	read_trace_pipe();
+
+cleanup:
+	bpf_link__destroy(link);
+	bpf_object__close(obj);
+	return 0;
+}

linux-7.2.3/samples/bpf/tracex6.bpf.c

@@ -0,0 +1,81 @@
+#include "vmlinux.h"
+#include <linux/version.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(u32));
+	__uint(max_entries, 64);
+} counters SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, int);
+	__type(value, u64);
+	__uint(max_entries, 64);
+} values SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, int);
+	__type(value, struct bpf_perf_event_value);
+	__uint(max_entries, 64);
+} values2 SEC(".maps");
+
+SEC("kprobe/htab_map_get_next_key")
+int bpf_prog1(struct pt_regs *ctx)
+{
+	u32 key = bpf_get_smp_processor_id();
+	u64 count, *val;
+	s64 error;
+
+	count = bpf_perf_event_read(&counters, key);
+	error = (s64)count;
+	if (error <= -2 && error >= -22)
+		return 0;
+
+	val = bpf_map_lookup_elem(&values, &key);
+	if (val)
+		*val = count;
+	else
+		bpf_map_update_elem(&values, &key, &count, BPF_NOEXIST);
+
+	return 0;
+}
+
+/*
+ * Since *_map_lookup_elem can't be expected to trigger bpf programs
+ * due to potential deadlocks (bpf_disable_instrumentation), this bpf
+ * program will be attached to bpf_map_copy_value (which is called
+ * from map_lookup_elem) and will only filter the hashtable type.
+ */
+SEC("kprobe/bpf_map_copy_value")
+int BPF_KPROBE(bpf_prog2, struct bpf_map *map)
+{
+	u32 key = bpf_get_smp_processor_id();
+	struct bpf_perf_event_value *val, buf;
+	enum bpf_map_type type;
+	int error;
+
+	type = BPF_CORE_READ(map, map_type);
+	if (type != BPF_MAP_TYPE_HASH)
+		return 0;
+
+	error = bpf_perf_event_read_value(&counters, key, &buf, sizeof(buf));
+	if (error)
+		return 0;
+
+	val = bpf_map_lookup_elem(&values2, &key);
+	if (val)
+		*val = buf;
+	else
+		bpf_map_update_elem(&values2, &key, &buf, BPF_NOEXIST);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;

linux-7.2.3/samples/bpf/tracex6_user.c

@@ -0,0 +1,222 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+
+#include <assert.h>
+#include <fcntl.h>
+#include <linux/perf_event.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/ioctl.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "perf-sys.h"
+
+#define SAMPLE_PERIOD  0x7fffffffffffffffULL
+
+/* counters, values, values2 */
+static int map_fd[3];
+
+static void check_on_cpu(int cpu, struct perf_event_attr *attr)
+{
+	struct bpf_perf_event_value value2;
+	int pmu_fd, error = 0;
+	cpu_set_t set;
+	__u64 value;
+
+	/* Move to target CPU */
+	CPU_ZERO(&set);
+	CPU_SET(cpu, &set);
+	assert(sched_setaffinity(0, sizeof(set), &set) == 0);
+	/* Open perf event and attach to the perf_event_array */
+	pmu_fd = sys_perf_event_open(attr, -1/*pid*/, cpu/*cpu*/, -1/*group_fd*/, 0);
+	if (pmu_fd < 0) {
+		fprintf(stderr, "sys_perf_event_open failed on CPU %d\n", cpu);
+		error = 1;
+		goto on_exit;
+	}
+	assert(bpf_map_update_elem(map_fd[0], &cpu, &pmu_fd, BPF_ANY) == 0);
+	assert(ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0) == 0);
+	/* Trigger the kprobe */
+	bpf_map_get_next_key(map_fd[1], &cpu, NULL);
+	/* Check the value */
+	if (bpf_map_lookup_elem(map_fd[1], &cpu, &value)) {
+		fprintf(stderr, "Value missing for CPU %d\n", cpu);
+		error = 1;
+		goto on_exit;
+	} else {
+		fprintf(stderr, "CPU %d: %llu\n", cpu, value);
+	}
+	/* The above bpf_map_lookup_elem should trigger the second kprobe */
+	if (bpf_map_lookup_elem(map_fd[2], &cpu, &value2)) {
+		fprintf(stderr, "Value2 missing for CPU %d\n", cpu);
+		error = 1;
+		goto on_exit;
+	} else {
+		fprintf(stderr, "CPU %d: counter: %llu, enabled: %llu, running: %llu\n", cpu,
+			value2.counter, value2.enabled, value2.running);
+	}
+
+on_exit:
+	assert(bpf_map_delete_elem(map_fd[0], &cpu) == 0 || error);
+	assert(ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE, 0) == 0 || error);
+	assert(close(pmu_fd) == 0 || error);
+	assert(bpf_map_delete_elem(map_fd[1], &cpu) == 0 || error);
+	exit(error);
+}
+
+static void test_perf_event_array(struct perf_event_attr *attr,
+				  const char *name)
+{
+	int i, status, nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+	pid_t pid[nr_cpus];
+	int err = 0;
+
+	printf("Test reading %s counters\n", name);
+
+	for (i = 0; i < nr_cpus; i++) {
+		pid[i] = fork();
+		assert(pid[i] >= 0);
+		if (pid[i] == 0) {
+			check_on_cpu(i, attr);
+			exit(1);
+		}
+	}
+
+	for (i = 0; i < nr_cpus; i++) {
+		assert(waitpid(pid[i], &status, 0) == pid[i]);
+		err |= status;
+	}
+
+	if (err)
+		printf("Test: %s FAILED\n", name);
+}
+
+static void test_bpf_perf_event(void)
+{
+	struct perf_event_attr attr_cycles = {
+		.freq = 0,
+		.sample_period = SAMPLE_PERIOD,
+		.inherit = 0,
+		.type = PERF_TYPE_HARDWARE,
+		.read_format = 0,
+		.sample_type = 0,
+		.config = PERF_COUNT_HW_CPU_CYCLES,
+	};
+	struct perf_event_attr attr_clock = {
+		.freq = 0,
+		.sample_period = SAMPLE_PERIOD,
+		.inherit = 0,
+		.type = PERF_TYPE_SOFTWARE,
+		.read_format = 0,
+		.sample_type = 0,
+		.config = PERF_COUNT_SW_CPU_CLOCK,
+	};
+	struct perf_event_attr attr_raw = {
+		.freq = 0,
+		.sample_period = SAMPLE_PERIOD,
+		.inherit = 0,
+		.type = PERF_TYPE_RAW,
+		.read_format = 0,
+		.sample_type = 0,
+		/* Intel Instruction Retired */
+		.config = 0xc0,
+	};
+	struct perf_event_attr attr_l1d_load = {
+		.freq = 0,
+		.sample_period = SAMPLE_PERIOD,
+		.inherit = 0,
+		.type = PERF_TYPE_HW_CACHE,
+		.read_format = 0,
+		.sample_type = 0,
+		.config =
+			PERF_COUNT_HW_CACHE_L1D |
+			(PERF_COUNT_HW_CACHE_OP_READ << 8) |
+			(PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16),
+	};
+	struct perf_event_attr attr_llc_miss = {
+		.freq = 0,
+		.sample_period = SAMPLE_PERIOD,
+		.inherit = 0,
+		.type = PERF_TYPE_HW_CACHE,
+		.read_format = 0,
+		.sample_type = 0,
+		.config =
+			PERF_COUNT_HW_CACHE_LL |
+			(PERF_COUNT_HW_CACHE_OP_READ << 8) |
+			(PERF_COUNT_HW_CACHE_RESULT_MISS << 16),
+	};
+	struct perf_event_attr attr_msr_tsc = {
+		.freq = 0,
+		.sample_period = 0,
+		.inherit = 0,
+		/* From /sys/bus/event_source/devices/msr/ */
+		.type = 7,
+		.read_format = 0,
+		.sample_type = 0,
+		.config = 0,
+	};
+
+	test_perf_event_array(&attr_cycles, "HARDWARE-cycles");
+	test_perf_event_array(&attr_clock, "SOFTWARE-clock");
+	test_perf_event_array(&attr_raw, "RAW-instruction-retired");
+	test_perf_event_array(&attr_l1d_load, "HW_CACHE-L1D-load");
+
+	/* below tests may fail in qemu */
+	test_perf_event_array(&attr_llc_miss, "HW_CACHE-LLC-miss");
+	test_perf_event_array(&attr_msr_tsc, "Dynamic-msr-tsc");
+}
+
+int main(int argc, char **argv)
+{
+	struct bpf_link *links[2];
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	char filename[256];
+	int i = 0;
+
+	snprintf(filename, sizeof(filename), "%s.bpf.o", argv[0]);
+	obj = bpf_object__open_file(filename, NULL);
+	if (libbpf_get_error(obj)) {
+		fprintf(stderr, "ERROR: opening BPF object file failed\n");
+		return 0;
+	}
+
+	/* load BPF program */
+	if (bpf_object__load(obj)) {
+		fprintf(stderr, "ERROR: loading BPF object file failed\n");
+		goto cleanup;
+	}
+
+	map_fd[0] = bpf_object__find_map_fd_by_name(obj, "counters");
+	map_fd[1] = bpf_object__find_map_fd_by_name(obj, "values");
+	map_fd[2] = bpf_object__find_map_fd_by_name(obj, "values2");
+	if (map_fd[0] < 0 || map_fd[1] < 0 || map_fd[2] < 0) {
+		fprintf(stderr, "ERROR: finding a map in obj file failed\n");
+		goto cleanup;
+	}
+
+	bpf_object__for_each_program(prog, obj) {
+		links[i] = bpf_program__attach(prog);
+		if (libbpf_get_error(links[i])) {
+			fprintf(stderr, "ERROR: bpf_program__attach failed\n");
+			links[i] = NULL;
+			goto cleanup;
+		}
+		i++;
+	}
+
+	test_bpf_perf_event();
+
+cleanup:
+	for (i--; i >= 0; i--)
+		bpf_link__destroy(links[i]);
+
+	bpf_object__close(obj);
+	return 0;
+}

linux-7.2.3/samples/bpf/xdp2skb_meta.sh

@@ -0,0 +1,220 @@
+#!/bin/bash
+#
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2018 Jesper Dangaard Brouer, Red Hat Inc.
+#
+# Bash-shell example on using iproute2 tools 'tc' and 'ip' to load
+# eBPF programs, both for XDP and clsbpf.  Shell script function
+# wrappers and even long options parsing is illustrated, for ease of
+# use.
+#
+# Related to sample/bpf/xdp2skb_meta_kern.c, which contains BPF-progs
+# that need to collaborate between XDP and TC hooks.  Thus, it is
+# convenient that the same tool load both programs that need to work
+# together.
+#
+BPF_FILE=xdp2skb_meta_kern.o
+DIR=$(dirname $0)
+
+[ -z "$TC" ] && TC=tc
+[ -z "$IP" ] && IP=ip
+
+function usage() {
+    echo ""
+    echo "Usage: $0 [-vfh] --dev ethX"
+    echo "  -d | --dev     :             Network device (required)"
+    echo "  --flush        :             Cleanup flush TC and XDP progs"
+    echo "  --list         : (\$LIST)     List TC and XDP progs"
+    echo "  -v | --verbose : (\$VERBOSE)  Verbose"
+    echo "  --dry-run      : (\$DRYRUN)   Dry-run only (echo commands)"
+    echo ""
+}
+
+## -- General shell logging cmds --
+function err() {
+    local exitcode=$1
+    shift
+    echo "ERROR: $@" >&2
+    exit $exitcode
+}
+
+function info() {
+    if [[ -n "$VERBOSE" ]]; then
+	echo "# $@"
+    fi
+}
+
+## -- Helper function calls --
+
+# Wrapper call for TC and IP
+# - Will display the offending command on failure
+function _call_cmd() {
+    local cmd="$1"
+    local allow_fail="$2"
+    shift 2
+    if [[ -n "$VERBOSE" ]]; then
+	echo "$cmd $@"
+    fi
+    if [[ -n "$DRYRUN" ]]; then
+	return
+    fi
+    $cmd "$@"
+    local status=$?
+    if (( $status != 0 )); then
+	if [[ "$allow_fail" == "" ]]; then
+	    err 2 "Exec error($status) occurred cmd: \"$cmd $@\""
+	fi
+    fi
+}
+function call_tc() {
+    _call_cmd "$TC" "" "$@"
+}
+function call_tc_allow_fail() {
+    _call_cmd "$TC" "allow_fail" "$@"
+}
+function call_ip() {
+    _call_cmd "$IP" "" "$@"
+}
+
+##  --- Parse command line arguments / parameters ---
+# Using external program "getopt" to get --long-options
+OPTIONS=$(getopt -o vfhd: \
+    --long verbose,flush,help,list,dev:,dry-run -- "$@")
+if (( $? != 0 )); then
+    err 4 "Error calling getopt"
+fi
+eval set -- "$OPTIONS"
+
+unset DEV
+unset FLUSH
+while true; do
+    case "$1" in
+	-d | --dev ) # device
+	    DEV=$2
+	    info "Device set to: DEV=$DEV" >&2
+	    shift 2
+	    ;;
+	-v | --verbose)
+	    VERBOSE=yes
+	    # info "Verbose mode: VERBOSE=$VERBOSE" >&2
+	    shift
+	    ;;
+	--dry-run )
+	    DRYRUN=yes
+	    VERBOSE=yes
+	    info "Dry-run mode: enable VERBOSE and don't call TC+IP" >&2
+	    shift
+            ;;
+	-f | --flush )
+	    FLUSH=yes
+	    shift
+	    ;;
+	--list )
+	    LIST=yes
+	    shift
+	    ;;
+	-- )
+	    shift
+	    break
+	    ;;
+	-h | --help )
+	    usage;
+	    exit 0
+	    ;;
+	* )
+	    shift
+	    break
+	    ;;
+    esac
+done
+
+FILE="$DIR/$BPF_FILE"
+if [[ ! -e $FILE ]]; then
+    err 3 "Missing BPF object file ($FILE)"
+fi
+
+if [[ -z $DEV ]]; then
+    usage
+    err 2 "Please specify network device -- required option --dev"
+fi
+
+## -- Function calls --
+
+function list_tc()
+{
+    local device="$1"
+    shift
+    info "Listing current TC ingress rules"
+    call_tc filter show dev $device ingress
+}
+
+function list_xdp()
+{
+    local device="$1"
+    shift
+    info "Listing current XDP device($device) setting"
+    call_ip link show dev $device | grep --color=auto xdp
+}
+
+function flush_tc()
+{
+    local device="$1"
+    shift
+    info "Flush TC on device: $device"
+    call_tc_allow_fail filter del dev $device ingress
+    call_tc_allow_fail qdisc del dev $device clsact
+}
+
+function flush_xdp()
+{
+    local device="$1"
+    shift
+    info "Flush XDP on device: $device"
+    call_ip link set dev $device xdp off
+}
+
+function attach_tc_mark()
+{
+    local device="$1"
+    local file="$2"
+    local prog="tc_mark"
+    shift 2
+
+    # Re-attach clsact to clear/flush existing role
+    call_tc_allow_fail qdisc del dev $device clsact 2> /dev/null
+    call_tc            qdisc add dev $device clsact
+
+    # Attach BPF prog
+    call_tc filter add dev $device ingress \
+	    prio 1 handle 1 bpf da obj $file sec $prog
+}
+
+function attach_xdp_mark()
+{
+    local device="$1"
+    local file="$2"
+    local prog="xdp_mark"
+    shift 2
+
+    # Remove XDP prog in-case it's already loaded
+    # TODO: Need ip-link option to override/replace existing XDP prog
+    flush_xdp $device
+
+    # Attach XDP/BPF prog
+    call_ip link set dev $device xdp obj $file sec $prog
+}
+
+if [[ -n $FLUSH ]]; then
+    flush_tc  $DEV
+    flush_xdp $DEV
+    exit 0
+fi
+
+if [[ -n $LIST ]]; then
+    list_tc  $DEV
+    list_xdp $DEV
+    exit 0
+fi
+
+attach_tc_mark  $DEV $FILE
+attach_xdp_mark $DEV $FILE

linux-7.2.3/samples/bpf/xdp2skb_meta_kern.c

@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * Copyright (c) 2018 Jesper Dangaard Brouer, Red Hat Inc.
+ *
+ * Example howto transfer info from XDP to SKB, e.g. skb->mark
+ * -----------------------------------------------------------
+ * This uses the XDP data_meta infrastructure, and is a cooperation
+ * between two bpf-programs (1) XDP and (2) clsact at TC-ingress hook.
+ *
+ * Notice: This example does not use the BPF C-loader,
+ * but instead rely on the iproute2 TC tool for loading BPF-objects.
+ */
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/pkt_cls.h>
+
+#include <bpf/bpf_helpers.h>
+
+/*
+ * This struct is stored in the XDP 'data_meta' area, which is located
+ * just in-front-of the raw packet payload data.  The meaning is
+ * specific to these two BPF programs that use it as a communication
+ * channel.  XDP adjust/increase the area via a bpf-helper, and TC use
+ * boundary checks to see if data have been provided.
+ *
+ * The struct must be 4 byte aligned, which here is enforced by the
+ * struct __attribute__((aligned(4))).
+ */
+struct meta_info {
+	__u32 mark;
+} __attribute__((aligned(4)));
+
+SEC("xdp_mark")
+int _xdp_mark(struct xdp_md *ctx)
+{
+	struct meta_info *meta;
+	void *data;
+	int ret;
+
+	/* Reserve space in-front of data pointer for our meta info.
+	 * (Notice drivers not supporting data_meta will fail here!)
+	 */
+	ret = bpf_xdp_adjust_meta(ctx, -(int)sizeof(*meta));
+	if (ret < 0)
+		return XDP_ABORTED;
+
+	/* Notice: Kernel-side verifier requires that loading of
+	 * ctx->data MUST happen _after_ helper bpf_xdp_adjust_meta(),
+	 * as pkt-data pointers are invalidated.  Helpers that require
+	 * this are determined/marked by bpf_helper_changes_pkt_data()
+	 */
+	data = (void *)(unsigned long)ctx->data;
+
+	/* Check data_meta have room for meta_info struct */
+	meta = (void *)(unsigned long)ctx->data_meta;
+	if (meta + 1 > data)
+		return XDP_ABORTED;
+
+	meta->mark = 42;
+
+	return XDP_PASS;
+}
+
+SEC("tc_mark")
+int _tc_mark(struct __sk_buff *ctx)
+{
+	void *data      = (void *)(unsigned long)ctx->data;
+	void *data_meta = (void *)(unsigned long)ctx->data_meta;
+	struct meta_info *meta = data_meta;
+
+	/* Check XDP gave us some data_meta */
+	if (meta + 1 > data) {
+		ctx->mark = 41;
+		 /* Skip "accept" if no data_meta is avail */
+		return TC_ACT_OK;
+	}
+
+	/* Hint: See func tc_cls_act_is_valid_access() for BPF_WRITE access */
+	ctx->mark = meta->mark; /* Transfer XDP-mark to SKB-mark */
+
+	return TC_ACT_OK;
+}
+
+/* Manually attaching these programs:
+export DEV=ixgbe2
+export FILE=xdp2skb_meta_kern.o
+
+# via TC command
+tc qdisc del dev $DEV clsact 2> /dev/null
+tc qdisc add dev $DEV clsact
+tc filter  add dev $DEV ingress prio 1 handle 1 bpf da obj $FILE sec tc_mark
+tc filter show dev $DEV ingress
+
+# XDP via IP command:
+ip link set dev $DEV xdp off
+ip link set dev $DEV xdp obj $FILE sec xdp_mark
+
+# Use iptable to "see" if SKBs are marked
+iptables -I INPUT -p icmp -m mark --mark 41  # == 0x29
+iptables -I INPUT -p icmp -m mark --mark 42  # == 0x2a
+
+# Hint: catch XDP_ABORTED errors via
+perf record -e xdp:*
+perf script
+
+*/

linux-7.2.3/samples/bpf/xdp_adjust_tail_kern.c

@@ -0,0 +1,156 @@
+/* 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.
+ *
+ * This program shows how to use bpf_xdp_adjust_tail() by
+ * generating ICMPv4 "packet to big" (unreachable/ df bit set frag needed
+ * to be more preice in case of v4)" where receiving packets bigger then
+ * 600 bytes.
+ */
+#define KBUILD_MODNAME "foo"
+#include <uapi/linux/bpf.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/if_vlan.h>
+#include <linux/ip.h>
+#include <linux/icmp.h>
+#include <bpf/bpf_helpers.h>
+
+#define DEFAULT_TTL 64
+#define MAX_PCKT_SIZE 600
+#define ICMP_TOOBIG_SIZE 98
+#define ICMP_TOOBIG_PAYLOAD_SIZE 92
+
+/* volatile to prevent compiler optimizations */
+static volatile __u32 max_pcktsz = MAX_PCKT_SIZE;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, __u32);
+	__type(value, __u64);
+	__uint(max_entries, 1);
+} icmpcnt SEC(".maps");
+
+static __always_inline void count_icmp(void)
+{
+	u64 key = 0;
+	u64 *icmp_count;
+
+	icmp_count = bpf_map_lookup_elem(&icmpcnt, &key);
+	if (icmp_count)
+		*icmp_count += 1;
+}
+
+static __always_inline void swap_mac(void *data, struct ethhdr *orig_eth)
+{
+	struct ethhdr *eth;
+
+	eth = data;
+	memcpy(eth->h_source, orig_eth->h_dest, ETH_ALEN);
+	memcpy(eth->h_dest, orig_eth->h_source, ETH_ALEN);
+	eth->h_proto = orig_eth->h_proto;
+}
+
+static __always_inline __u16 csum_fold_helper(__u32 csum)
+{
+	csum = (csum & 0xffff) + (csum >> 16);
+	return ~((csum & 0xffff) + (csum >> 16));
+}
+
+static __always_inline void ipv4_csum(void *data_start, int data_size,
+				      __u32 *csum)
+{
+	*csum = bpf_csum_diff(0, 0, data_start, data_size, *csum);
+	*csum = csum_fold_helper(*csum);
+}
+
+static __always_inline int send_icmp4_too_big(struct xdp_md *xdp)
+{
+	int headroom = (int)sizeof(struct iphdr) + (int)sizeof(struct icmphdr);
+
+	if (bpf_xdp_adjust_head(xdp, 0 - headroom))
+		return XDP_DROP;
+	void *data = (void *)(long)xdp->data;
+	void *data_end = (void *)(long)xdp->data_end;
+
+	if (data + (ICMP_TOOBIG_SIZE + headroom) > data_end)
+		return XDP_DROP;
+
+	struct iphdr *iph, *orig_iph;
+	struct icmphdr *icmp_hdr;
+	struct ethhdr *orig_eth;
+	__u32 csum = 0;
+	__u64 off = 0;
+
+	orig_eth = data + headroom;
+	swap_mac(data, orig_eth);
+	off += sizeof(struct ethhdr);
+	iph = data + off;
+	off += sizeof(struct iphdr);
+	icmp_hdr = data + off;
+	off += sizeof(struct icmphdr);
+	orig_iph = data + off;
+	icmp_hdr->type = ICMP_DEST_UNREACH;
+	icmp_hdr->code = ICMP_FRAG_NEEDED;
+	icmp_hdr->un.frag.mtu = htons(max_pcktsz - sizeof(struct ethhdr));
+	icmp_hdr->checksum = 0;
+	ipv4_csum(icmp_hdr, ICMP_TOOBIG_PAYLOAD_SIZE, &csum);
+	icmp_hdr->checksum = csum;
+	iph->ttl = DEFAULT_TTL;
+	iph->daddr = orig_iph->saddr;
+	iph->saddr = orig_iph->daddr;
+	iph->version = 4;
+	iph->ihl = 5;
+	iph->protocol = IPPROTO_ICMP;
+	iph->tos = 0;
+	iph->tot_len = htons(
+		ICMP_TOOBIG_SIZE + headroom - sizeof(struct ethhdr));
+	iph->check = 0;
+	csum = 0;
+	ipv4_csum(iph, sizeof(struct iphdr), &csum);
+	iph->check = csum;
+	count_icmp();
+	return XDP_TX;
+}
+
+
+static __always_inline int handle_ipv4(struct xdp_md *xdp)
+{
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+	int pckt_size = data_end - data;
+	int offset;
+
+	if (pckt_size > max(max_pcktsz, ICMP_TOOBIG_SIZE)) {
+		offset = pckt_size - ICMP_TOOBIG_SIZE;
+		if (bpf_xdp_adjust_tail(xdp, 0 - offset))
+			return XDP_PASS;
+		return send_icmp4_too_big(xdp);
+	}
+	return XDP_PASS;
+}
+
+SEC("xdp_icmp")
+int _xdp_icmp(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 == htons(ETH_P_IP))
+		return handle_ipv4(xdp);
+	else
+		return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";