Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-02-26

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) Various improvements for BPF kselftests: i) skip unprivileged tests
   when kernel.unprivileged_bpf_disabled sysctl knob is set, ii) count
   the number of skipped tests from unprivileged, iii) when a test case
   had an unexpected error then print the actual but also the unexpected
   one for better comparison, from Joe.

2) Add a sample program for collecting CPU state statistics with regards
   to how long the CPU resides in cstate and pstate levels. Based on
   cpu_idle and cpu_frequency trace points, from Leo.

3) Various x64 BPF JIT optimizations to further shrink the generated
   image size in order to make it more icache friendly. When tested on
   the Cilium generated programs, image size reduced by approx 4-5% in
   best case mainly due to how LLVM emits unsigned 32 bit constants,
   from Daniel.

4) Improvements and fixes on the BPF sockmap sample programs: i) fix
   the sockmap's Makefile to include nlattr.o for libbpf, ii) detach
   the sock ops programs from the cgroup before exit, from Prashant.

5) Avoid including xdp.h in filter.h by just forward declaring the
   struct xdp_rxq_info in filter.h, from Jesper.

6) Fix the BPF kselftests Makefile for cgroup_helpers.c by only declaring
   it a dependency for test_dev_cgroup.c but not every other test case
   where it is not needed, from Jesper.

7) Adjust rlimit RLIMIT_MEMLOCK for test_tcpbpf_user selftest since the
   default is insufficient for creating the 'global_map' used in the
   corresponding BPF program, from Yonghong.

8) Likewise, for the xdp_redirect sample, Tushar ran into the same when
   invoking xdp_redirect and xdp_monitor at the same time, therefore
   in order to have the sample generically work bump the limit here,
   too. Fix from Tushar.

9) Avoid an unnecessary NULL check in BPF_CGROUP_RUN_PROG_INET_SOCK()
   since sk is always guaranteed to be non-NULL, from Yafang.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

arch/x86/net/bpf_jit_comp.c

@@ -61,7 +61,12 @@ static bool is_imm8(int value)
 
 static bool is_simm32(s64 value)
 {
-	return value == (s64) (s32) value;
+	return value == (s64)(s32)value;
+}
+
+static bool is_uimm32(u64 value)
+{
+	return value == (u64)(u32)value;
 }
 
 /* mov dst, src */
@@ -212,7 +217,7 @@ struct jit_context {
 /* emit x64 prologue code for BPF program and check it's size.
  * bpf_tail_call helper will skip it while jumping into another program
  */
-static void emit_prologue(u8 **pprog, u32 stack_depth)
+static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf)
 {
 	u8 *prog = *pprog;
 	int cnt = 0;
@@ -247,18 +252,21 @@ static void emit_prologue(u8 **pprog, u32 stack_depth)
 	/* mov qword ptr [rbp+24],r15 */
 	EMIT4(0x4C, 0x89, 0x7D, 24);
 
-	/* Clear the tail call counter (tail_call_cnt): for eBPF tail calls
-	 * we need to reset the counter to 0. It's done in two instructions,
-	 * resetting rax register to 0 (xor on eax gets 0 extended), and
-	 * moving it to the counter location.
-	 */
+	if (!ebpf_from_cbpf) {
+		/* Clear the tail call counter (tail_call_cnt): for eBPF tail
+		 * calls we need to reset the counter to 0. It's done in two
+		 * instructions, resetting rax register to 0, and moving it
+		 * to the counter location.
+		 */
+
+		/* xor eax, eax */
+		EMIT2(0x31, 0xc0);
+		/* mov qword ptr [rbp+32], rax */
+		EMIT4(0x48, 0x89, 0x45, 32);
 
-	/* xor eax, eax */
-	EMIT2(0x31, 0xc0);
-	/* mov qword ptr [rbp+32], rax */
-	EMIT4(0x48, 0x89, 0x45, 32);
+		BUILD_BUG_ON(cnt != PROLOGUE_SIZE);
+	}
 
-	BUILD_BUG_ON(cnt != PROLOGUE_SIZE);
 	*pprog = prog;
 }
 
@@ -356,6 +364,86 @@ static void emit_load_skb_data_hlen(u8 **pprog)
 	*pprog = prog;
 }
 
+static void emit_mov_imm32(u8 **pprog, bool sign_propagate,
+			   u32 dst_reg, const u32 imm32)
+{
+	u8 *prog = *pprog;
+	u8 b1, b2, b3;
+	int cnt = 0;
+
+	/* optimization: if imm32 is positive, use 'mov %eax, imm32'
+	 * (which zero-extends imm32) to save 2 bytes.
+	 */
+	if (sign_propagate && (s32)imm32 < 0) {
+		/* 'mov %rax, imm32' sign extends imm32 */
+		b1 = add_1mod(0x48, dst_reg);
+		b2 = 0xC7;
+		b3 = 0xC0;
+		EMIT3_off32(b1, b2, add_1reg(b3, dst_reg), imm32);
+		goto done;
+	}
+
+	/* optimization: if imm32 is zero, use 'xor %eax, %eax'
+	 * to save 3 bytes.
+	 */
+	if (imm32 == 0) {
+		if (is_ereg(dst_reg))
+			EMIT1(add_2mod(0x40, dst_reg, dst_reg));
+		b2 = 0x31; /* xor */
+		b3 = 0xC0;
+		EMIT2(b2, add_2reg(b3, dst_reg, dst_reg));
+		goto done;
+	}
+
+	/* mov %eax, imm32 */
+	if (is_ereg(dst_reg))
+		EMIT1(add_1mod(0x40, dst_reg));
+	EMIT1_off32(add_1reg(0xB8, dst_reg), imm32);
+done:
+	*pprog = prog;
+}
+
+static void emit_mov_imm64(u8 **pprog, u32 dst_reg,
+			   const u32 imm32_hi, const u32 imm32_lo)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	if (is_uimm32(((u64)imm32_hi << 32) | (u32)imm32_lo)) {
+		/* For emitting plain u32, where sign bit must not be
+		 * propagated LLVM tends to load imm64 over mov32
+		 * directly, so save couple of bytes by just doing
+		 * 'mov %eax, imm32' instead.
+		 */
+		emit_mov_imm32(&prog, false, dst_reg, imm32_lo);
+	} else {
+		/* movabsq %rax, imm64 */
+		EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg));
+		EMIT(imm32_lo, 4);
+		EMIT(imm32_hi, 4);
+	}
+
+	*pprog = prog;
+}
+
+static void emit_mov_reg(u8 **pprog, bool is64, u32 dst_reg, u32 src_reg)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	if (is64) {
+		/* mov dst, src */
+		EMIT_mov(dst_reg, src_reg);
+	} else {
+		/* mov32 dst, src */
+		if (is_ereg(dst_reg) || is_ereg(src_reg))
+			EMIT1(add_2mod(0x40, dst_reg, src_reg));
+		EMIT2(0x89, add_2reg(0xC0, dst_reg, src_reg));
+	}
+
+	*pprog = prog;
+}
+
 static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		  int oldproglen, struct jit_context *ctx)
 {
@@ -369,7 +457,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 	int proglen = 0;
 	u8 *prog = temp;
 
-	emit_prologue(&prog, bpf_prog->aux->stack_depth);
+	emit_prologue(&prog, bpf_prog->aux->stack_depth,
+		      bpf_prog_was_classic(bpf_prog));
 
 	if (seen_ld_abs)
 		emit_load_skb_data_hlen(&prog);
@@ -378,7 +467,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		const s32 imm32 = insn->imm;
 		u32 dst_reg = insn->dst_reg;
 		u32 src_reg = insn->src_reg;
-		u8 b1 = 0, b2 = 0, b3 = 0;
+		u8 b2 = 0, b3 = 0;
 		s64 jmp_offset;
 		u8 jmp_cond;
 		bool reload_skb_data;
@@ -414,16 +503,11 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			EMIT2(b2, add_2reg(0xC0, dst_reg, src_reg));
 			break;
 
-			/* mov dst, src */
 		case BPF_ALU64 | BPF_MOV | BPF_X:
-			EMIT_mov(dst_reg, src_reg);
-			break;
-
-			/* mov32 dst, src */
 		case BPF_ALU | BPF_MOV | BPF_X:
-			if (is_ereg(dst_reg) || is_ereg(src_reg))
-				EMIT1(add_2mod(0x40, dst_reg, src_reg));
-			EMIT2(0x89, add_2reg(0xC0, dst_reg, src_reg));
+			emit_mov_reg(&prog,
+				     BPF_CLASS(insn->code) == BPF_ALU64,
+				     dst_reg, src_reg);
 			break;
 
 			/* neg dst */
@@ -486,58 +570,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			break;
 
 		case BPF_ALU64 | BPF_MOV | BPF_K:
-			/* optimization: if imm32 is positive,
-			 * use 'mov eax, imm32' (which zero-extends imm32)
-			 * to save 2 bytes
-			 */
-			if (imm32 < 0) {
-				/* 'mov rax, imm32' sign extends imm32 */
-				b1 = add_1mod(0x48, dst_reg);
-				b2 = 0xC7;
-				b3 = 0xC0;
-				EMIT3_off32(b1, b2, add_1reg(b3, dst_reg), imm32);
-				break;
-			}
-
 		case BPF_ALU | BPF_MOV | BPF_K:
-			/* optimization: if imm32 is zero, use 'xor <dst>,<dst>'
-			 * to save 3 bytes.
-			 */
-			if (imm32 == 0) {
-				if (is_ereg(dst_reg))
-					EMIT1(add_2mod(0x40, dst_reg, dst_reg));
-				b2 = 0x31; /* xor */
-				b3 = 0xC0;
-				EMIT2(b2, add_2reg(b3, dst_reg, dst_reg));
-				break;
-			}
-
-			/* mov %eax, imm32 */
-			if (is_ereg(dst_reg))
-				EMIT1(add_1mod(0x40, dst_reg));
-			EMIT1_off32(add_1reg(0xB8, dst_reg), imm32);
+			emit_mov_imm32(&prog, BPF_CLASS(insn->code) == BPF_ALU64,
+				       dst_reg, imm32);
 			break;
 
 		case BPF_LD | BPF_IMM | BPF_DW:
-			/* optimization: if imm64 is zero, use 'xor <dst>,<dst>'
-			 * to save 7 bytes.
-			 */
-			if (insn[0].imm == 0 && insn[1].imm == 0) {
-				b1 = add_2mod(0x48, dst_reg, dst_reg);
-				b2 = 0x31; /* xor */
-				b3 = 0xC0;
-				EMIT3(b1, b2, add_2reg(b3, dst_reg, dst_reg));
-
-				insn++;
-				i++;
-				break;
-			}
-
-			/* movabsq %rax, imm64 */
-			EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg));
-			EMIT(insn[0].imm, 4);
-			EMIT(insn[1].imm, 4);
-
+			emit_mov_imm64(&prog, dst_reg, insn[1].imm, insn[0].imm);
 			insn++;
 			i++;
 			break;
@@ -594,36 +633,38 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 		case BPF_ALU | BPF_MUL | BPF_X:
 		case BPF_ALU64 | BPF_MUL | BPF_K:
 		case BPF_ALU64 | BPF_MUL | BPF_X:
-			EMIT1(0x50); /* push rax */
-			EMIT1(0x52); /* push rdx */
+		{
+			bool is64 = BPF_CLASS(insn->code) == BPF_ALU64;
+
+			if (dst_reg != BPF_REG_0)
+				EMIT1(0x50); /* push rax */
+			if (dst_reg != BPF_REG_3)
+				EMIT1(0x52); /* push rdx */
 
 			/* mov r11, dst_reg */
 			EMIT_mov(AUX_REG, dst_reg);
 
 			if (BPF_SRC(insn->code) == BPF_X)
-				/* mov rax, src_reg */
-				EMIT_mov(BPF_REG_0, src_reg);
+				emit_mov_reg(&prog, is64, BPF_REG_0, src_reg);
 			else
-				/* mov rax, imm32 */
-				EMIT3_off32(0x48, 0xC7, 0xC0, imm32);
+				emit_mov_imm32(&prog, is64, BPF_REG_0, imm32);
 
-			if (BPF_CLASS(insn->code) == BPF_ALU64)
+			if (is64)
 				EMIT1(add_1mod(0x48, AUX_REG));
 			else if (is_ereg(AUX_REG))
 				EMIT1(add_1mod(0x40, AUX_REG));
 			/* mul(q) r11 */
 			EMIT2(0xF7, add_1reg(0xE0, AUX_REG));
 
-			/* mov r11, rax */
-			EMIT_mov(AUX_REG, BPF_REG_0);
-
-			EMIT1(0x5A); /* pop rdx */
-			EMIT1(0x58); /* pop rax */
-
-			/* mov dst_reg, r11 */
-			EMIT_mov(dst_reg, AUX_REG);
+			if (dst_reg != BPF_REG_3)
+				EMIT1(0x5A); /* pop rdx */
+			if (dst_reg != BPF_REG_0) {
+				/* mov dst_reg, rax */
+				EMIT_mov(dst_reg, BPF_REG_0);
+				EMIT1(0x58); /* pop rax */
+			}
 			break;
-
+		}
 			/* shifts */
 		case BPF_ALU | BPF_LSH | BPF_K:
 		case BPF_ALU | BPF_RSH | BPF_K:
@@ -641,7 +682,11 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
 			case BPF_RSH: b3 = 0xE8; break;
 			case BPF_ARSH: b3 = 0xF8; break;
 			}
-			EMIT3(0xC1, add_1reg(b3, dst_reg), imm32);
+
+			if (imm32 == 1)
+				EMIT2(0xD1, add_1reg(b3, dst_reg));
+			else
+				EMIT3(0xC1, add_1reg(b3, dst_reg), imm32);
 			break;
 
 		case BPF_ALU | BPF_LSH | BPF_X:

include/linux/bpf-cgroup.h

@@ -96,7 +96,7 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk)				       \
 ({									       \
 	int __ret = 0;							       \
-	if (cgroup_bpf_enabled && sk) {					       \
+	if (cgroup_bpf_enabled) {					       \
 		__ret = __cgroup_bpf_run_filter_sk(sk,			       \
 						 BPF_CGROUP_INET_SOCK_CREATE); \
 	}								       \

include/linux/filter.h

@@ -20,7 +20,6 @@
 #include <linux/set_memory.h>
 #include <linux/kallsyms.h>
 
-#include <net/xdp.h>
 #include <net/sch_generic.h>
 
 #include <uapi/linux/filter.h>
@@ -30,6 +29,7 @@ struct sk_buff;
 struct sock;
 struct seccomp_data;
 struct bpf_prog_aux;
+struct xdp_rxq_info;
 
 /* ArgX, context and stack frame pointer register positions. Note,
  * Arg1, Arg2, Arg3, etc are used as argument mappings of function

kernel/bpf/verifier.c

@@ -508,10 +508,6 @@ static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
 static const int caller_saved[CALLER_SAVED_REGS] = {
 	BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5
 };
-#define CALLEE_SAVED_REGS 5
-static const int callee_saved[CALLEE_SAVED_REGS] = {
-	BPF_REG_6, BPF_REG_7, BPF_REG_8, BPF_REG_9
-};
 
 static void __mark_reg_not_init(struct bpf_reg_state *reg);
 

samples/bpf/Makefile

@@ -43,6 +43,7 @@ hostprogs-y += xdp_redirect_cpu
 hostprogs-y += xdp_monitor
 hostprogs-y += xdp_rxq_info
 hostprogs-y += syscall_tp
+hostprogs-y += cpustat
 
 # Libbpf dependencies
 LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o
@@ -93,6 +94,7 @@ xdp_redirect_cpu-objs := bpf_load.o $(LIBBPF) xdp_redirect_cpu_user.o
 xdp_monitor-objs := bpf_load.o $(LIBBPF) xdp_monitor_user.o
 xdp_rxq_info-objs := bpf_load.o $(LIBBPF) xdp_rxq_info_user.o
 syscall_tp-objs := bpf_load.o $(LIBBPF) syscall_tp_user.o
+cpustat-objs := bpf_load.o $(LIBBPF) cpustat_user.o
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
@@ -144,6 +146,7 @@ always += xdp_monitor_kern.o
 always += xdp_rxq_info_kern.o
 always += xdp2skb_meta_kern.o
 always += syscall_tp_kern.o
+always += cpustat_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 HOSTCFLAGS += -I$(srctree)/tools/lib/
@@ -188,6 +191,7 @@ HOSTLOADLIBES_xdp_redirect_cpu += -lelf
 HOSTLOADLIBES_xdp_monitor += -lelf
 HOSTLOADLIBES_xdp_rxq_info += -lelf
 HOSTLOADLIBES_syscall_tp += -lelf
+HOSTLOADLIBES_cpustat += -lelf
 
 # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
 #  make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang

samples/bpf/cpustat_kern.c

+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/version.h>
+#include <linux/ptrace.h>
+#include <uapi/linux/bpf.h>
+#include "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 bpf_map_def SEC("maps") my_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(u64),
+	.max_entries = MAX_CPU * MAP_OFF_NUM,
+};
+
+/* cstate_duration records duration time for every idle state per CPU */
+struct bpf_map_def SEC("maps") cstate_duration = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(u64),
+	.max_entries = MAX_CPU * MAX_CSTATE_ENTRIES,
+};
+
+/* pstate_duration records duration time for every operating point per CPU */
+struct bpf_map_def SEC("maps") pstate_duration = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(u32),
+	.value_size = sizeof(u64),
+	.max_entries = MAX_CPU * MAX_PSTATE_ENTRIES,
+};
+
+/*
+ * The trace events for cpu_idle and cpu_frequency are taken from:
+ * /sys/kernel/debug/tracing/events/power/cpu_idle/format
+ * /sys/kernel/debug/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, prev_state, 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;
+
+	prev_state = *pstate;
+	*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;

samples/bpf/cpustat_user.c

+// 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 <linux/bpf.h>
+#include <locale.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <sys/wait.h>
+
+#include "libbpf.h"
+#include "bpf_load.h"
+
+#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("%-11ld ", data->cstate[i] / 1000000);
+
+		for (i = 0; i < MAX_PSTATE_ENTRIES; i++)
+			printf("%-11ld ", 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(map_fd[1], map_fd[2]);
+	cpu_stat_print();
+	exit(0);
+}
+
+int main(int argc, char **argv)
+{
+	char filename[256];
+	int ret;
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	if (load_bpf_file(filename)) {
+		printf("%s", bpf_log_buf);
+		return 1;
+	}
+
+	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(map_fd[1], map_fd[2]);
+		cpu_stat_print();
+		sleep(5);
+	}
+
+	return 0;
+}

samples/bpf/xdp_redirect_user.c

@@ -20,6 +20,7 @@
 #include <string.h>
 #include <unistd.h>
 #include <libgen.h>
+#include <sys/resource.h>
 
 #include "bpf_load.h"
 #include "bpf_util.h"
@@ -75,6 +76,7 @@ static void usage(const char *prog)
 
 int main(int argc, char **argv)
 {
+	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
 	const char *optstr = "SN";
 	char filename[256];
 	int ret, opt, key = 0;
@@ -98,6 +100,11 @@ int main(int argc, char **argv)
 		return 1;
 	}
 
+	if (setrlimit(RLIMIT_MEMLOCK, &r)) {
+		perror("setrlimit(RLIMIT_MEMLOCK)");
+		return 1;
+	}
+
 	ifindex_in = strtoul(argv[optind], NULL, 0);
 	ifindex_out = strtoul(argv[optind + 1], NULL, 0);
 	printf("input: %d output: %d\n", ifindex_in, ifindex_out);

samples/sockmap/Makefile

@@ -2,7 +2,7 @@
 hostprogs-y := sockmap
 
 # Libbpf dependencies
-LIBBPF := ../../tools/lib/bpf/bpf.o
+LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 HOSTCFLAGS += -I$(srctree)/tools/lib/

samples/sockmap/sockmap_user.c

@@ -566,6 +566,7 @@ int main(int argc, char **argv)
 	else
 		fprintf(stderr, "unknown test\n");
 out:
+	bpf_prog_detach2(prog_fd[2], cg_fd, BPF_CGROUP_SOCK_OPS);
 	close(s1);
 	close(s2);
 	close(p1);

tools/testing/selftests/bpf/Makefile

@@ -35,12 +35,14 @@ TEST_GEN_PROGS_EXTENDED = test_libbpf_open
 
 include ../lib.mk
 
-BPFOBJ := $(OUTPUT)/libbpf.a cgroup_helpers.c
+BPFOBJ := $(OUTPUT)/libbpf.a
 
 $(TEST_GEN_PROGS): $(BPFOBJ)
 
 $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/libbpf.a
 
+$(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
+
 .PHONY: force
 
 # force a rebuild of BPFOBJ when its dependencies are updated

tools/testing/selftests/bpf/test_tcpbpf_user.c

@@ -11,6 +11,8 @@
 #include <linux/ptrace.h>
 #include <linux/bpf.h>
 #include <sys/ioctl.h>
+#include <sys/time.h>
+#include <sys/resource.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
@@ -42,6 +44,7 @@ static int bpf_find_map(const char *test, struct bpf_object *obj,
 
 int main(int argc, char **argv)
 {
+	struct rlimit limit  = { RLIM_INFINITY, RLIM_INFINITY };
 	const char *file = "test_tcpbpf_kern.o";
 	struct tcpbpf_globals g = {0};
 	int cg_fd, prog_fd, map_fd;
@@ -54,6 +57,9 @@ int main(int argc, char **argv)
 	int pid;
 	int rv;
 
+	if (setrlimit(RLIMIT_MEMLOCK, &limit) < 0)
+		perror("Unable to lift memlock rlimit");
+
 	if (argc > 1 && strcmp(argv[1], "-d") == 0)
 		debug_flag = true;
 

tools/testing/selftests/bpf/test_verifier.c

@@ -57,6 +57,9 @@
 #define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS	(1 << 0)
 #define F_LOAD_WITH_STRICT_ALIGNMENT		(1 << 1)
 
+#define UNPRIV_SYSCTL "kernel/unprivileged_bpf_disabled"
+static bool unpriv_disabled = false;
+
 struct bpf_test {
 	const char *descr;
 	struct bpf_insn	insns[MAX_INSNS];
@@ -11163,6 +11166,95 @@ static struct bpf_test tests[] = {
 		.result = REJECT,
 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
 	},
+	{
+		"jit: lsh, rsh, arsh by 1",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_MOV64_IMM(BPF_REG_1, 0xff),
+			BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 1),
+			BPF_ALU32_IMM(BPF_LSH, BPF_REG_1, 1),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0x3fc, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 1),
+			BPF_ALU32_IMM(BPF_RSH, BPF_REG_1, 1),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0xff, 1),
+			BPF_EXIT_INSN(),
+			BPF_ALU64_IMM(BPF_ARSH, BPF_REG_1, 1),
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0x7f, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 2),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.retval = 2,
+	},
+	{
+		"jit: mov32 for ldimm64, 1",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 2),
+			BPF_LD_IMM64(BPF_REG_1, 0xfeffffffffffffffULL),
+			BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 32),
+			BPF_LD_IMM64(BPF_REG_2, 0xfeffffffULL),
+			BPF_JMP_REG(BPF_JEQ, BPF_REG_1, BPF_REG_2, 1),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.retval = 2,
+	},
+	{
+		"jit: mov32 for ldimm64, 2",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_LD_IMM64(BPF_REG_1, 0x1ffffffffULL),
+			BPF_LD_IMM64(BPF_REG_2, 0xffffffffULL),
+			BPF_JMP_REG(BPF_JEQ, BPF_REG_1, BPF_REG_2, 1),
+			BPF_MOV64_IMM(BPF_REG_0, 2),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.retval = 2,
+	},
+	{
+		"jit: various mul tests",
+		.insns = {
+			BPF_LD_IMM64(BPF_REG_2, 0xeeff0d413122ULL),
+			BPF_LD_IMM64(BPF_REG_0, 0xfefefeULL),
+			BPF_LD_IMM64(BPF_REG_1, 0xefefefULL),
+			BPF_ALU64_REG(BPF_MUL, BPF_REG_0, BPF_REG_1),
+			BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_2, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_LD_IMM64(BPF_REG_3, 0xfefefeULL),
+			BPF_ALU64_REG(BPF_MUL, BPF_REG_3, BPF_REG_1),
+			BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_REG(BPF_REG_2, BPF_REG_2),
+			BPF_LD_IMM64(BPF_REG_0, 0xfefefeULL),
+			BPF_ALU32_REG(BPF_MUL, BPF_REG_0, BPF_REG_1),
+			BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_2, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_LD_IMM64(BPF_REG_3, 0xfefefeULL),
+			BPF_ALU32_REG(BPF_MUL, BPF_REG_3, BPF_REG_1),
+			BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_LD_IMM64(BPF_REG_0, 0x952a7bbcULL),
+			BPF_LD_IMM64(BPF_REG_1, 0xfefefeULL),
+			BPF_LD_IMM64(BPF_REG_2, 0xeeff0d413122ULL),
+			BPF_ALU32_REG(BPF_MUL, BPF_REG_2, BPF_REG_1),
+			BPF_JMP_REG(BPF_JEQ, BPF_REG_2, BPF_REG_0, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 2),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.retval = 2,
+	},
+
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
@@ -11317,7 +11409,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 			goto fail_log;
 		}
 		if (!strstr(bpf_vlog, expected_err) && !reject_from_alignment) {
-			printf("FAIL\nUnexpected error message!\n");
+			printf("FAIL\nUnexpected error message!\n\tEXP: %s\n\tRES: %s\n",
+			      expected_err, bpf_vlog);
 			goto fail_log;
 		}
 	}
@@ -11401,9 +11494,20 @@ static int set_admin(bool admin)
 	return ret;
 }
 
+static void get_unpriv_disabled()
+{
+	char buf[2];
+	FILE *fd;
+
+	fd = fopen("/proc/sys/"UNPRIV_SYSCTL, "r");
+	if (fgets(buf, 2, fd) == buf && atoi(buf))
+		unpriv_disabled = true;
+	fclose(fd);
+}
+
 static int do_test(bool unpriv, unsigned int from, unsigned int to)
 {
-	int i, passes = 0, errors = 0;
+	int i, passes = 0, errors = 0, skips = 0;
 
 	for (i = from; i < to; i++) {
 		struct bpf_test *test = &tests[i];
@@ -11411,7 +11515,10 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to)
 		/* Program types that are not supported by non-root we
 		 * skip right away.
 		 */
-		if (!test->prog_type) {
+		if (!test->prog_type && unpriv_disabled) {
+			printf("#%d/u %s SKIP\n", i, test->descr);
+			skips++;
+		} else if (!test->prog_type) {
 			if (!unpriv)
 				set_admin(false);
 			printf("#%d/u %s ", i, test->descr);
@@ -11420,13 +11527,17 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to)
 				set_admin(true);
 		}
 
-		if (!unpriv) {
+		if (unpriv) {
+			printf("#%d/p %s SKIP\n", i, test->descr);
+			skips++;
+		} else {
 			printf("#%d/p %s ", i, test->descr);
 			do_test_single(test, false, &passes, &errors);
 		}
 	}
 
-	printf("Summary: %d PASSED, %d FAILED\n", passes, errors);
+	printf("Summary: %d PASSED, %d SKIPPED, %d FAILED\n", passes,
+	       skips, errors);
 	return errors ? EXIT_FAILURE : EXIT_SUCCESS;
 }
 
@@ -11454,6 +11565,13 @@ int main(int argc, char **argv)
 		}
 	}
 
+	get_unpriv_disabled();
+	if (unpriv && unpriv_disabled) {
+		printf("Cannot run as unprivileged user with sysctl %s.\n",
+		       UNPRIV_SYSCTL);
+		return EXIT_FAILURE;
+	}
+
 	setrlimit(RLIMIT_MEMLOCK, unpriv ? &rlim : &rinf);
 	return do_test(unpriv, from, to);
 }