Merge branch 'bpf-pkt-ptr-align'

David S. Miller says:

====================
bpf: Add alignment tracker to verifier.

First we add the alignment tracking logic to the verifier.

Next, we work on building up infrastructure to facilitate regression
testing of this facility.

Finally, we add the "test_align" test case.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/bpf_verifier.h

@@ -40,6 +40,9 @@ struct bpf_reg_state {
 	 */
 	s64 min_value;
 	u64 max_value;
+	u32 min_align;
+	u32 aux_off;
+	u32 aux_off_align;
 };
 
 enum bpf_stack_slot_type {
@@ -87,6 +90,7 @@ struct bpf_verifier_env {
 	struct bpf_prog *prog;		/* eBPF program being verified */
 	struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */
 	int stack_size;			/* number of states to be processed */
+	bool strict_alignment;		/* perform strict pointer alignment checks */
 	struct bpf_verifier_state cur_state; /* current verifier state */
 	struct bpf_verifier_state_list **explored_states; /* search pruning optimization */
 	const struct bpf_ext_analyzer_ops *analyzer_ops; /* external analyzer ops */

include/uapi/linux/bpf.h

@@ -132,6 +132,13 @@ enum bpf_attach_type {
  */
 #define BPF_F_ALLOW_OVERRIDE	(1U << 0)
 
+/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
+ * verifier will perform strict alignment checking as if the kernel
+ * has been built with CONFIG_EFFICIENT_UNALIGNED_ACCESS not set,
+ * and NET_IP_ALIGN defined to 2.
+ */
+#define BPF_F_STRICT_ALIGNMENT	(1U << 0)
+
 #define BPF_PSEUDO_MAP_FD	1
 
 /* flags for BPF_MAP_UPDATE_ELEM command */
@@ -177,6 +184,7 @@ union bpf_attr {
 		__u32		log_size;	/* size of user buffer */
 		__aligned_u64	log_buf;	/* user supplied buffer */
 		__u32		kern_version;	/* checked when prog_type=kprobe */
+		__u32		prog_flags;
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */

kernel/bpf/syscall.c

@@ -783,7 +783,7 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type)
 EXPORT_SYMBOL_GPL(bpf_prog_get_type);
 
 /* last field in 'union bpf_attr' used by this command */
-#define	BPF_PROG_LOAD_LAST_FIELD kern_version
+#define	BPF_PROG_LOAD_LAST_FIELD prog_flags
 
 static int bpf_prog_load(union bpf_attr *attr)
 {
@@ -796,6 +796,9 @@ static int bpf_prog_load(union bpf_attr *attr)
 	if (CHECK_ATTR(BPF_PROG_LOAD))
 		return -EINVAL;
 
+	if (attr->prog_flags & ~BPF_F_STRICT_ALIGNMENT)
+		return -EINVAL;
+
 	/* copy eBPF program license from user space */
 	if (strncpy_from_user(license, u64_to_user_ptr(attr->license),
 			      sizeof(license) - 1) < 0)

kernel/bpf/verifier.c

@@ -241,6 +241,12 @@ static void print_verifier_state(struct bpf_verifier_state *state)
 		if (reg->max_value != BPF_REGISTER_MAX_RANGE)
 			verbose(",max_value=%llu",
 				(unsigned long long)reg->max_value);
+		if (reg->min_align)
+			verbose(",min_align=%u", reg->min_align);
+		if (reg->aux_off)
+			verbose(",aux_off=%u", reg->aux_off);
+		if (reg->aux_off_align)
+			verbose(",aux_off_align=%u", reg->aux_off_align);
 	}
 	for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
 		if (state->stack_slot_type[i] == STACK_SPILL)
@@ -466,6 +472,9 @@ static void init_reg_state(struct bpf_reg_state *regs)
 		regs[i].imm = 0;
 		regs[i].min_value = BPF_REGISTER_MIN_RANGE;
 		regs[i].max_value = BPF_REGISTER_MAX_RANGE;
+		regs[i].min_align = 0;
+		regs[i].aux_off = 0;
+		regs[i].aux_off_align = 0;
 	}
 
 	/* frame pointer */
@@ -492,6 +501,7 @@ static void reset_reg_range_values(struct bpf_reg_state *regs, u32 regno)
 {
 	regs[regno].min_value = BPF_REGISTER_MIN_RANGE;
 	regs[regno].max_value = BPF_REGISTER_MAX_RANGE;
+	regs[regno].min_align = 0;
 }
 
 static void mark_reg_unknown_value_and_range(struct bpf_reg_state *regs,
@@ -779,17 +789,33 @@ static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
 }
 
 static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg,
-				   int off, int size)
+				   int off, int size, bool strict)
 {
-	if (reg->id && size != 1) {
-		verbose("Unknown alignment. Only byte-sized access allowed in packet access.\n");
-		return -EACCES;
+	int ip_align;
+	int reg_off;
+
+	/* Byte size accesses are always allowed. */
+	if (!strict || size == 1)
+		return 0;
+
+	reg_off = reg->off;
+	if (reg->id) {
+		if (reg->aux_off_align % size) {
+			verbose("Packet access is only %u byte aligned, %d byte access not allowed\n",
+				reg->aux_off_align, size);
+			return -EACCES;
+		}
+		reg_off += reg->aux_off;
 	}
 
-	/* skb->data is NET_IP_ALIGN-ed */
-	if ((NET_IP_ALIGN + reg->off + off) % size != 0) {
+	/* skb->data is NET_IP_ALIGN-ed, but for strict alignment checking
+	 * we force this to 2 which is universally what architectures use
+	 * when they don't set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS.
+	 */
+	ip_align = strict ? 2 : NET_IP_ALIGN;
+	if ((ip_align + reg_off + off) % size != 0) {
 		verbose("misaligned packet access off %d+%d+%d size %d\n",
-			NET_IP_ALIGN, reg->off, off, size);
+			ip_align, reg_off, off, size);
 		return -EACCES;
 	}
 
@@ -797,9 +823,9 @@ static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg,
 }
 
 static int check_val_ptr_alignment(const struct bpf_reg_state *reg,
-				   int size)
+				   int size, bool strict)
 {
-	if (size != 1) {
+	if (strict && size != 1) {
 		verbose("Unknown alignment. Only byte-sized access allowed in value access.\n");
 		return -EACCES;
 	}
@@ -807,16 +833,20 @@ static int check_val_ptr_alignment(const struct bpf_reg_state *reg,
 	return 0;
 }
 
-static int check_ptr_alignment(const struct bpf_reg_state *reg,
+static int check_ptr_alignment(struct bpf_verifier_env *env,
+			       const struct bpf_reg_state *reg,
 			       int off, int size)
 {
+	bool strict = env->strict_alignment;
+
+	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
+		strict = true;
+
 	switch (reg->type) {
 	case PTR_TO_PACKET:
-		return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 :
-		       check_pkt_ptr_alignment(reg, off, size);
+		return check_pkt_ptr_alignment(reg, off, size, strict);
 	case PTR_TO_MAP_VALUE_ADJ:
-		return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 :
-		       check_val_ptr_alignment(reg, size);
+		return check_val_ptr_alignment(reg, size, strict);
 	default:
 		if (off % size != 0) {
 			verbose("misaligned access off %d size %d\n",
@@ -849,7 +879,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off,
 	if (size < 0)
 		return size;
 
-	err = check_ptr_alignment(reg, off, size);
+	err = check_ptr_alignment(env, reg, off, size);
 	if (err)
 		return err;
 
@@ -883,6 +913,8 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off,
 							 value_regno);
 			/* note that reg.[id|off|range] == 0 */
 			state->regs[value_regno].type = reg_type;
+			state->regs[value_regno].aux_off = 0;
+			state->regs[value_regno].aux_off_align = 0;
 		}
 
 	} else if (reg->type == FRAME_PTR || reg->type == PTR_TO_STACK) {
@@ -1455,6 +1487,8 @@ static int check_packet_ptr_add(struct bpf_verifier_env *env,
 		 */
 		dst_reg->off += imm;
 	} else {
+		bool had_id;
+
 		if (src_reg->type == PTR_TO_PACKET) {
 			/* R6=pkt(id=0,off=0,r=62) R7=imm22; r7 += r6 */
 			tmp_reg = *dst_reg;  /* save r7 state */
@@ -1488,14 +1522,23 @@ static int check_packet_ptr_add(struct bpf_verifier_env *env,
 				src_reg->imm);
 			return -EACCES;
 		}
+
+		had_id = (dst_reg->id != 0);
+
 		/* dst_reg stays as pkt_ptr type and since some positive
 		 * integer value was added to the pointer, increment its 'id'
 		 */
 		dst_reg->id = ++env->id_gen;
 
-		/* something was added to pkt_ptr, set range and off to zero */
+		/* something was added to pkt_ptr, set range to zero */
+		dst_reg->aux_off = dst_reg->off;
 		dst_reg->off = 0;
 		dst_reg->range = 0;
+		if (had_id)
+			dst_reg->aux_off_align = min(dst_reg->aux_off_align,
+						     src_reg->min_align);
+		else
+			dst_reg->aux_off_align = src_reg->min_align;
 	}
 	return 0;
 }
@@ -1669,6 +1712,13 @@ static void check_reg_overflow(struct bpf_reg_state *reg)
 		reg->min_value = BPF_REGISTER_MIN_RANGE;
 }
 
+static u32 calc_align(u32 imm)
+{
+	if (!imm)
+		return 1U << 31;
+	return imm - ((imm - 1) & imm);
+}
+
 static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 				    struct bpf_insn *insn)
 {
@@ -1676,8 +1726,10 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 	s64 min_val = BPF_REGISTER_MIN_RANGE;
 	u64 max_val = BPF_REGISTER_MAX_RANGE;
 	u8 opcode = BPF_OP(insn->code);
+	u32 dst_align, src_align;
 
 	dst_reg = &regs[insn->dst_reg];
+	src_align = 0;
 	if (BPF_SRC(insn->code) == BPF_X) {
 		check_reg_overflow(&regs[insn->src_reg]);
 		min_val = regs[insn->src_reg].min_value;
@@ -1693,12 +1745,18 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 		    regs[insn->src_reg].type != UNKNOWN_VALUE) {
 			min_val = BPF_REGISTER_MIN_RANGE;
 			max_val = BPF_REGISTER_MAX_RANGE;
+			src_align = 0;
+		} else {
+			src_align = regs[insn->src_reg].min_align;
 		}
 	} else if (insn->imm < BPF_REGISTER_MAX_RANGE &&
 		   (s64)insn->imm > BPF_REGISTER_MIN_RANGE) {
 		min_val = max_val = insn->imm;
+		src_align = calc_align(insn->imm);
 	}
 
+	dst_align = dst_reg->min_align;
+
 	/* We don't know anything about what was done to this register, mark it
 	 * as unknown.
 	 */
@@ -1723,18 +1781,21 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 			dst_reg->min_value += min_val;
 		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
 			dst_reg->max_value += max_val;
+		dst_reg->min_align = min(src_align, dst_align);
 		break;
 	case BPF_SUB:
 		if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
 			dst_reg->min_value -= min_val;
 		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
 			dst_reg->max_value -= max_val;
+		dst_reg->min_align = min(src_align, dst_align);
 		break;
 	case BPF_MUL:
 		if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
 			dst_reg->min_value *= min_val;
 		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
 			dst_reg->max_value *= max_val;
+		dst_reg->min_align = max(src_align, dst_align);
 		break;
 	case BPF_AND:
 		/* Disallow AND'ing of negative numbers, ain't nobody got time
@@ -1746,17 +1807,23 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 		else
 			dst_reg->min_value = 0;
 		dst_reg->max_value = max_val;
+		dst_reg->min_align = max(src_align, dst_align);
 		break;
 	case BPF_LSH:
 		/* Gotta have special overflow logic here, if we're shifting
 		 * more than MAX_RANGE then just assume we have an invalid
 		 * range.
 		 */
-		if (min_val > ilog2(BPF_REGISTER_MAX_RANGE))
+		if (min_val > ilog2(BPF_REGISTER_MAX_RANGE)) {
 			dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
-		else if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
-			dst_reg->min_value <<= min_val;
-
+			dst_reg->min_align = 1;
+		} else {
+			if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
+				dst_reg->min_value <<= min_val;
+			if (!dst_reg->min_align)
+				dst_reg->min_align = 1;
+			dst_reg->min_align <<= min_val;
+		}
 		if (max_val > ilog2(BPF_REGISTER_MAX_RANGE))
 			dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
 		else if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
@@ -1766,11 +1833,19 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 		/* RSH by a negative number is undefined, and the BPF_RSH is an
 		 * unsigned shift, so make the appropriate casts.
 		 */
-		if (min_val < 0 || dst_reg->min_value < 0)
+		if (min_val < 0 || dst_reg->min_value < 0) {
 			dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
-		else
+		} else {
 			dst_reg->min_value =
 				(u64)(dst_reg->min_value) >> min_val;
+		}
+		if (min_val < 0) {
+			dst_reg->min_align = 1;
+		} else {
+			dst_reg->min_align >>= (u64) min_val;
+			if (!dst_reg->min_align)
+				dst_reg->min_align = 1;
+		}
 		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
 			dst_reg->max_value >>= max_val;
 		break;
@@ -1872,6 +1947,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			regs[insn->dst_reg].imm = insn->imm;
 			regs[insn->dst_reg].max_value = insn->imm;
 			regs[insn->dst_reg].min_value = insn->imm;
+			regs[insn->dst_reg].min_align = calc_align(insn->imm);
 		}
 
 	} else if (opcode > BPF_END) {
@@ -2856,8 +2932,12 @@ static int do_check(struct bpf_verifier_env *env)
 			goto process_bpf_exit;
 		}
 
-		if (log_level && do_print_state) {
-			verbose("\nfrom %d to %d:", prev_insn_idx, insn_idx);
+		if (log_level > 1 || (log_level && do_print_state)) {
+			if (log_level > 1)
+				verbose("%d:", insn_idx);
+			else
+				verbose("\nfrom %d to %d:",
+					prev_insn_idx, insn_idx);
 			print_verifier_state(&env->cur_state);
 			do_print_state = false;
 		}
@@ -3494,6 +3574,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
 	} else {
 		log_level = 0;
 	}
+	if (attr->prog_flags & BPF_F_STRICT_ALIGNMENT)
+		env->strict_alignment = true;
+	else
+		env->strict_alignment = false;
 
 	ret = replace_map_fd_with_map_ptr(env);
 	if (ret < 0)
@@ -3599,6 +3683,7 @@ int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops,
 	mutex_lock(&bpf_verifier_lock);
 
 	log_level = 0;
+	env->strict_alignment = false;
 
 	env->explored_states = kcalloc(env->prog->len,
 				       sizeof(struct bpf_verifier_state_list *),

tools/build/feature/test-bpf.c

@@ -29,6 +29,7 @@ int main(void)
 	attr.log_size = 0;
 	attr.log_level = 0;
 	attr.kern_version = 0;
+	attr.prog_flags = 0;
 
 	/*
 	 * Test existence of __NR_bpf and BPF_PROG_LOAD.

tools/include/uapi/linux/bpf.h

@@ -132,6 +132,13 @@ enum bpf_attach_type {
  */
 #define BPF_F_ALLOW_OVERRIDE	(1U << 0)
 
+/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
+ * verifier will perform strict alignment checking as if the kernel
+ * has been built with CONFIG_EFFICIENT_UNALIGNED_ACCESS not set,
+ * and NET_IP_ALIGN defined to 2.
+ */
+#define BPF_F_STRICT_ALIGNMENT	(1U << 0)
+
 #define BPF_PSEUDO_MAP_FD	1
 
 /* flags for BPF_MAP_UPDATE_ELEM command */
@@ -177,6 +184,7 @@ union bpf_attr {
 		__u32		log_size;	/* size of user buffer */
 		__aligned_u64	log_buf;	/* user supplied buffer */
 		__u32		kern_version;	/* checked when prog_type=kprobe */
+		__u32		prog_flags;
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -481,8 +489,7 @@ union bpf_attr {
  * u32 bpf_get_socket_uid(skb)
  *     Get the owner uid of the socket stored inside sk_buff.
  *     @skb: pointer to skb
- *     Return: uid of the socket owner on success or 0 if the socket pointer
- *     inside sk_buff is NULL
+ *     Return: uid of the socket owner on success or overflowuid if failed.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\

tools/lib/bpf/bpf.c

@@ -117,6 +117,28 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 	return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
 }
 
+int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
+		       size_t insns_cnt, int strict_alignment,
+		       const char *license, __u32 kern_version,
+		       char *log_buf, size_t log_buf_sz)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.prog_type = type;
+	attr.insn_cnt = (__u32)insns_cnt;
+	attr.insns = ptr_to_u64(insns);
+	attr.license = ptr_to_u64(license);
+	attr.log_buf = ptr_to_u64(log_buf);
+	attr.log_size = log_buf_sz;
+	attr.log_level = 2;
+	log_buf[0] = 0;
+	attr.kern_version = kern_version;
+	attr.prog_flags = strict_alignment ? BPF_F_STRICT_ALIGNMENT : 0;
+
+	return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+}
+
 int bpf_map_update_elem(int fd, const void *key, const void *value,
 			__u64 flags)
 {

tools/lib/bpf/bpf.h

@@ -35,6 +35,10 @@ int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 		     size_t insns_cnt, const char *license,
 		     __u32 kern_version, char *log_buf,
 		     size_t log_buf_sz);
+int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
+		       size_t insns_cnt, int strict_alignment,
+		       const char *license, __u32 kern_version,
+		       char *log_buf, size_t log_buf_sz);
 
 int bpf_map_update_elem(int fd, const void *key, const void *value,
 			__u64 flags);

tools/testing/selftests/bpf/Makefile

@@ -11,7 +11,8 @@ endif
 CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include
 LDLIBS += -lcap -lelf
 
-TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs
+TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
+	test_align
 
 TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o
 

tools/testing/selftests/bpf/test_align.c

+#include <asm/types.h>
+#include <linux/types.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <errno.h>
+#include <string.h>
+#include <stddef.h>
+#include <stdbool.h>
+
+#include <linux/unistd.h>
+#include <linux/filter.h>
+#include <linux/bpf_perf_event.h>
+#include <linux/bpf.h>
+
+#include <bpf/bpf.h>
+
+#include "../../../include/linux/filter.h"
+
+#ifndef ARRAY_SIZE
+# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#endif
+
+#define MAX_INSNS	512
+#define MAX_MATCHES	16
+
+struct bpf_align_test {
+	const char *descr;
+	struct bpf_insn	insns[MAX_INSNS];
+	enum {
+		UNDEF,
+		ACCEPT,
+		REJECT
+	} result;
+	enum bpf_prog_type prog_type;
+	const char *matches[MAX_MATCHES];
+};
+
+static struct bpf_align_test tests[] = {
+	{
+		.descr = "mov",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_3, 2),
+			BPF_MOV64_IMM(BPF_REG_3, 4),
+			BPF_MOV64_IMM(BPF_REG_3, 8),
+			BPF_MOV64_IMM(BPF_REG_3, 16),
+			BPF_MOV64_IMM(BPF_REG_3, 32),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.matches = {
+			"1: R1=ctx R3=imm2,min_value=2,max_value=2,min_align=2 R10=fp",
+			"2: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp",
+			"3: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=8 R10=fp",
+			"4: R1=ctx R3=imm16,min_value=16,max_value=16,min_align=16 R10=fp",
+			"5: R1=ctx R3=imm32,min_value=32,max_value=32,min_align=32 R10=fp",
+		},
+	},
+	{
+		.descr = "shift",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_3, 1),
+			BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+			BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+			BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+			BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+			BPF_ALU64_IMM(BPF_RSH, BPF_REG_3, 4),
+			BPF_MOV64_IMM(BPF_REG_4, 32),
+			BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+			BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+			BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+			BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.matches = {
+			"1: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R10=fp",
+			"2: R1=ctx R3=imm2,min_value=2,max_value=2,min_align=2 R10=fp",
+			"3: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp",
+			"4: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=8 R10=fp",
+			"5: R1=ctx R3=imm16,min_value=16,max_value=16,min_align=16 R10=fp",
+			"6: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R10=fp",
+			"7: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm32,min_value=32,max_value=32,min_align=32 R10=fp",
+			"8: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm16,min_value=16,max_value=16,min_align=16 R10=fp",
+			"9: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm8,min_value=8,max_value=8,min_align=8 R10=fp",
+			"10: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm4,min_value=4,max_value=4,min_align=4 R10=fp",
+			"11: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm2,min_value=2,max_value=2,min_align=2 R10=fp",
+		},
+	},
+	{
+		.descr = "addsub",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_3, 4),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 4),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 2),
+			BPF_MOV64_IMM(BPF_REG_4, 8),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.matches = {
+			"1: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp",
+			"2: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=4 R10=fp",
+			"3: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R10=fp",
+			"4: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm8,min_value=8,max_value=8,min_align=8 R10=fp",
+			"5: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm12,min_value=12,max_value=12,min_align=4 R10=fp",
+			"6: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm14,min_value=14,max_value=14,min_align=2 R10=fp",
+		},
+	},
+	{
+		.descr = "mul",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_3, 7),
+			BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, 1),
+			BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, 2),
+			BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, 4),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.matches = {
+			"1: R1=ctx R3=imm7,min_value=7,max_value=7,min_align=1 R10=fp",
+			"2: R1=ctx R3=imm7,min_value=7,max_value=7,min_align=1 R10=fp",
+			"3: R1=ctx R3=imm14,min_value=14,max_value=14,min_align=2 R10=fp",
+			"4: R1=ctx R3=imm56,min_value=56,max_value=56,min_align=4 R10=fp",
+		},
+	},
+
+#define PREP_PKT_POINTERS \
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, \
+		    offsetof(struct __sk_buff, data)), \
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, \
+		    offsetof(struct __sk_buff, data_end))
+
+#define LOAD_UNKNOWN(DST_REG) \
+	PREP_PKT_POINTERS, \
+	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), \
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), \
+	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_0, 1), \
+	BPF_EXIT_INSN(), \
+	BPF_LDX_MEM(BPF_B, DST_REG, BPF_REG_2, 0)
+
+	{
+		.descr = "unknown shift",
+		.insns = {
+			LOAD_UNKNOWN(BPF_REG_3),
+			BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+			BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+			BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+			BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+			LOAD_UNKNOWN(BPF_REG_4),
+			BPF_ALU64_IMM(BPF_LSH, BPF_REG_4, 5),
+			BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+			BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+			BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+			BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.matches = {
+			"7: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R10=fp",
+			"8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv55,min_align=2 R10=fp",
+			"9: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv54,min_align=4 R10=fp",
+			"10: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv53,min_align=8 R10=fp",
+			"11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv52,min_align=16 R10=fp",
+			"18: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv56 R10=fp",
+			"19: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv51,min_align=32 R10=fp",
+			"20: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv52,min_align=16 R10=fp",
+			"21: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv53,min_align=8 R10=fp",
+			"22: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv54,min_align=4 R10=fp",
+			"23: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv55,min_align=2 R10=fp",
+		},
+	},
+	{
+		.descr = "unknown mul",
+		.insns = {
+			LOAD_UNKNOWN(BPF_REG_3),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_3),
+			BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 1),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_3),
+			BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 2),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_3),
+			BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 4),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_3),
+			BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 8),
+			BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 2),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.matches = {
+			"7: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R10=fp",
+			"8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp",
+			"9: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv55,min_align=1 R10=fp",
+			"10: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp",
+			"11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv54,min_align=2 R10=fp",
+			"12: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp",
+			"13: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv53,min_align=4 R10=fp",
+			"14: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp",
+			"15: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv52,min_align=8 R10=fp",
+			"16: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv50,min_align=8 R10=fp"
+		},
+	},
+	{
+		.descr = "packet const offset",
+		.insns = {
+			PREP_PKT_POINTERS,
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
+
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+
+			/* Skip over ethernet header.  */
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
+			BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
+			BPF_EXIT_INSN(),
+
+			BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 0),
+			BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 2),
+			BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 3),
+			BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_5, 0),
+			BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_5, 2),
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_5, 0),
+
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.matches = {
+			"4: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R5=pkt(id=0,off=0,r=0) R10=fp",
+			"5: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R5=pkt(id=0,off=14,r=0) R10=fp",
+			"6: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R4=pkt(id=0,off=14,r=0) R5=pkt(id=0,off=14,r=0) R10=fp",
+			"10: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv56 R5=pkt(id=0,off=14,r=18) R10=fp",
+			"14: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv48 R5=pkt(id=0,off=14,r=18) R10=fp",
+			"15: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv48 R5=pkt(id=0,off=14,r=18) R10=fp",
+		},
+	},
+	{
+		.descr = "packet variable offset",
+		.insns = {
+			LOAD_UNKNOWN(BPF_REG_6),
+			BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 2),
+
+			/* First, add a constant to the R5 packet pointer,
+			 * then a variable with a known alignment.
+			 */
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
+			BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
+			BPF_EXIT_INSN(),
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_5, 0),
+
+			/* Now, test in the other direction.  Adding first
+			 * the variable offset to R5, then the constant.
+			 */
+			BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14),
+			BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
+			BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
+			BPF_EXIT_INSN(),
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_5, 0),
+
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.matches = {
+			/* Calculated offset in R6 has unknown value, but known
+			 * alignment of 4.
+			 */
+			"8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R6=inv54,min_align=4 R10=fp",
+
+			/* Offset is added to packet pointer R5, resulting in known
+			 * auxiliary alignment and offset.
+			 */
+			"11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R5=pkt(id=1,off=0,r=0),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+
+			/* At the time the word size load is performed from R5,
+			 * it's total offset is NET_IP_ALIGN + reg->off (0) +
+			 * reg->aux_off (14) which is 16.  Then the variable
+			 * offset is considered using reg->aux_off_align which
+			 * is 4 and meets the load's requirements.
+			 */
+			"15: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=pkt(id=1,off=4,r=4),aux_off=14,aux_off_align=4 R5=pkt(id=1,off=0,r=4),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+
+
+			/* Variable offset is added to R5 packet pointer,
+			 * resulting in auxiliary alignment of 4.
+			 */
+			"18: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off=14,aux_off_align=4 R5=pkt(id=2,off=0,r=0),aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+
+			/* Constant offset is added to R5, resulting in
+			 * reg->off of 14.
+			 */
+			"19: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off=14,aux_off_align=4 R5=pkt(id=2,off=14,r=0),aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+
+			/* At the time the word size load is performed from R5,
+			 * it's total offset is NET_IP_ALIGN + reg->off (14) which
+			 * is 16.  Then the variable offset is considered using
+			 * reg->aux_off_align which is 4 and meets the load's
+			 * requirements.
+			 */
+			"23: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=pkt(id=2,off=18,r=18),aux_off_align=4 R5=pkt(id=2,off=14,r=18),aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+		},
+	},
+};
+
+static int probe_filter_length(const struct bpf_insn *fp)
+{
+	int len;
+
+	for (len = MAX_INSNS - 1; len > 0; --len)
+		if (fp[len].code != 0 || fp[len].imm != 0)
+			break;
+	return len + 1;
+}
+
+static char bpf_vlog[32768];
+
+static int do_test_single(struct bpf_align_test *test)
+{
+	struct bpf_insn *prog = test->insns;
+	int prog_type = test->prog_type;
+	int prog_len, i;
+	int fd_prog;
+	int ret;
+
+	prog_len = probe_filter_length(prog);
+	fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
+				     prog, prog_len, 1, "GPL", 0,
+				     bpf_vlog, sizeof(bpf_vlog));
+	if (fd_prog < 0) {
+		printf("Failed to load program.\n");
+		printf("%s", bpf_vlog);
+		ret = 1;
+	} else {
+		ret = 0;
+		for (i = 0; i < MAX_MATCHES; i++) {
+			const char *t, *m = test->matches[i];
+
+			if (!m)
+				break;
+			t = strstr(bpf_vlog, m);
+			if (!t) {
+				printf("Failed to find match: %s\n", m);
+				ret = 1;
+				printf("%s", bpf_vlog);
+				break;
+			}
+		}
+		/* printf("%s", bpf_vlog); */
+		close(fd_prog);
+	}
+	return ret;
+}
+
+static int do_test(unsigned int from, unsigned int to)
+{
+	int all_pass = 0;
+	int all_fail = 0;
+	unsigned int i;
+
+	for (i = from; i < to; i++) {
+		struct bpf_align_test *test = &tests[i];
+		int fail;
+
+		printf("Test %3d: %s ... ",
+		       i, test->descr);
+		fail = do_test_single(test);
+		if (fail) {
+			all_fail++;
+			printf("FAIL\n");
+		} else {
+			all_pass++;
+			printf("PASS\n");
+		}
+	}
+	printf("Results: %d pass %d fail\n",
+	       all_pass, all_fail);
+	return 0;
+}
+
+int main(int argc, char **argv)
+{
+	unsigned int from = 0, to = ARRAY_SIZE(tests);
+
+	if (argc == 3) {
+		unsigned int l = atoi(argv[argc - 2]);
+		unsigned int u = atoi(argv[argc - 1]);
+
+		if (l < to && u < to) {
+			from = l;
+			to   = u + 1;
+		}
+	} else if (argc == 2) {
+		unsigned int t = atoi(argv[argc - 1]);
+
+		if (t < to) {
+			from = t;
+			to   = t + 1;
+		}
+	}
+	return do_test(from, to);
+}