Merge branch 'bpf-llvm-reg-alloc-patterns'

Alexei Starovoitov says:

====================
Make two verifier improvements:

- The llvm register allocator may use two different registers representing
  the same virtual register. Teach the verifier to recognize that.
- Track bounded scalar spill/fill.

The profiler[123] test in patch 3 will fail to load without patches 1 and 2.
The profiler[23] test may fail to load on older llvm due to speculative
code motion nd instruction combining optimizations that are fixed in
https://reviews.llvm.org/D85570

v1 -> v2:
  - fixed 32-bit mov issue spotted by John.
  - allowed r2=r1; r3=r2; sequence as suggested by John.
  - added comments, acks, more tests.
====================
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

kernel/bpf/verifier.c

@@ -2227,6 +2227,20 @@ static bool register_is_const(struct bpf_reg_state *reg)
 	return reg->type == SCALAR_VALUE && tnum_is_const(reg->var_off);
 }
 
+static bool __is_scalar_unbounded(struct bpf_reg_state *reg)
+{
+	return tnum_is_unknown(reg->var_off) &&
+	       reg->smin_value == S64_MIN && reg->smax_value == S64_MAX &&
+	       reg->umin_value == 0 && reg->umax_value == U64_MAX &&
+	       reg->s32_min_value == S32_MIN && reg->s32_max_value == S32_MAX &&
+	       reg->u32_min_value == 0 && reg->u32_max_value == U32_MAX;
+}
+
+static bool register_is_bounded(struct bpf_reg_state *reg)
+{
+	return reg->type == SCALAR_VALUE && !__is_scalar_unbounded(reg);
+}
+
 static bool __is_pointer_value(bool allow_ptr_leaks,
 			       const struct bpf_reg_state *reg)
 {
@@ -2278,7 +2292,7 @@ static int check_stack_write(struct bpf_verifier_env *env,
 	if (value_regno >= 0)
 		reg = &cur->regs[value_regno];
 
-	if (reg && size == BPF_REG_SIZE && register_is_const(reg) &&
+	if (reg && size == BPF_REG_SIZE && register_is_bounded(reg) &&
 	    !register_is_null(reg) && env->bpf_capable) {
 		if (dst_reg != BPF_REG_FP) {
 			/* The backtracking logic can only recognize explicit
@@ -6436,6 +6450,11 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 	src_reg = NULL;
 	if (dst_reg->type != SCALAR_VALUE)
 		ptr_reg = dst_reg;
+	else
+		/* Make sure ID is cleared otherwise dst_reg min/max could be
+		 * incorrectly propagated into other registers by find_equal_scalars()
+		 */
+		dst_reg->id = 0;
 	if (BPF_SRC(insn->code) == BPF_X) {
 		src_reg = &regs[insn->src_reg];
 		if (src_reg->type != SCALAR_VALUE) {
@@ -6569,6 +6588,12 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 				/* case: R1 = R2
 				 * copy register state to dest reg
 				 */
+				if (src_reg->type == SCALAR_VALUE && !src_reg->id)
+					/* Assign src and dst registers the same ID
+					 * that will be used by find_equal_scalars()
+					 * to propagate min/max range.
+					 */
+					src_reg->id = ++env->id_gen;
 				*dst_reg = *src_reg;
 				dst_reg->live |= REG_LIVE_WRITTEN;
 				dst_reg->subreg_def = DEF_NOT_SUBREG;
@@ -6581,6 +6606,11 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 					return -EACCES;
 				} else if (src_reg->type == SCALAR_VALUE) {
 					*dst_reg = *src_reg;
+					/* Make sure ID is cleared otherwise
+					 * dst_reg min/max could be incorrectly
+					 * propagated into src_reg by find_equal_scalars()
+					 */
+					dst_reg->id = 0;
 					dst_reg->live |= REG_LIVE_WRITTEN;
 					dst_reg->subreg_def = env->insn_idx + 1;
 				} else {
@@ -7369,6 +7399,30 @@ static bool try_match_pkt_pointers(const struct bpf_insn *insn,
 	return true;
 }
 
+static void find_equal_scalars(struct bpf_verifier_state *vstate,
+			       struct bpf_reg_state *known_reg)
+{
+	struct bpf_func_state *state;
+	struct bpf_reg_state *reg;
+	int i, j;
+
+	for (i = 0; i <= vstate->curframe; i++) {
+		state = vstate->frame[i];
+		for (j = 0; j < MAX_BPF_REG; j++) {
+			reg = &state->regs[j];
+			if (reg->type == SCALAR_VALUE && reg->id == known_reg->id)
+				*reg = *known_reg;
+		}
+
+		bpf_for_each_spilled_reg(j, state, reg) {
+			if (!reg)
+				continue;
+			if (reg->type == SCALAR_VALUE && reg->id == known_reg->id)
+				*reg = *known_reg;
+		}
+	}
+}
+
 static int check_cond_jmp_op(struct bpf_verifier_env *env,
 			     struct bpf_insn *insn, int *insn_idx)
 {
@@ -7497,6 +7551,11 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 				reg_combine_min_max(&other_branch_regs[insn->src_reg],
 						    &other_branch_regs[insn->dst_reg],
 						    src_reg, dst_reg, opcode);
+			if (src_reg->id) {
+				find_equal_scalars(this_branch, src_reg);
+				find_equal_scalars(other_branch, &other_branch_regs[insn->src_reg]);
+			}
+
 		}
 	} else if (dst_reg->type == SCALAR_VALUE) {
 		reg_set_min_max(&other_branch_regs[insn->dst_reg],
@@ -7504,6 +7563,11 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 					opcode, is_jmp32);
 	}
 
+	if (dst_reg->type == SCALAR_VALUE && dst_reg->id) {
+		find_equal_scalars(this_branch, dst_reg);
+		find_equal_scalars(other_branch, &other_branch_regs[insn->dst_reg]);
+	}
+
 	/* detect if R == 0 where R is returned from bpf_map_lookup_elem().
 	 * NOTE: these optimizations below are related with pointer comparison
 	 *       which will never be JMP32.

tools/testing/selftests/bpf/README.rst

@@ -7,6 +7,44 @@ General instructions on running selftests can be found in
 Additional information about selftest failures are
 documented here.
 
+profiler[23] test failures with clang/llvm <12.0.0
+==================================================
+
+With clang/llvm <12.0.0, the profiler[23] test may fail.
+The symptom looks like
+
+.. code-block:: c
+
+  // r9 is a pointer to map_value
+  // r7 is a scalar
+  17:       bf 96 00 00 00 00 00 00 r6 = r9
+  18:       0f 76 00 00 00 00 00 00 r6 += r7
+  math between map_value pointer and register with unbounded min value is not allowed
+
+  // the instructions below will not be seen in the verifier log
+  19:       a5 07 01 00 01 01 00 00 if r7 < 257 goto +1
+  20:       bf 96 00 00 00 00 00 00 r6 = r9
+  // r6 is used here
+
+The verifier will reject such code with above error.
+At insn 18 the r7 is indeed unbounded. The later insn 19 checks the bounds and
+the insn 20 undoes map_value addition. It is currently impossible for the
+verifier to understand such speculative pointer arithmetic.
+Hence
+    https://reviews.llvm.org/D85570
+addresses it on the compiler side. It was committed on llvm 12.
+
+The corresponding C code
+.. code-block:: c
+
+  for (int i = 0; i < MAX_CGROUPS_PATH_DEPTH; i++) {
+          filepart_length = bpf_probe_read_str(payload, ...);
+          if (filepart_length <= MAX_PATH) {
+                  barrier_var(filepart_length); // workaround
+                  payload += filepart_length;
+          }
+  }
+
 bpf_iter test failures with clang/llvm 10.0.0
 =============================================
 

tools/testing/selftests/bpf/prog_tests/align.c

@@ -195,13 +195,13 @@ static struct bpf_align_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
 			{7, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
-			{8, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+			{8, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"},
 			{9, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
-			{10, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+			{10, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"},
 			{11, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"},
-			{12, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+			{12, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"},
 			{13, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"},
-			{14, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"},
+			{14, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"},
 			{15, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"},
 			{16, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"},
 		},
@@ -518,7 +518,7 @@ static struct bpf_align_test tests[] = {
 			 * the total offset is 4-byte aligned and meets the
 			 * load's requirements.
 			 */
-			{20, "R5=pkt(id=1,off=0,r=4,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc)"},
+			{20, "R5=pkt(id=2,off=0,r=4,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc)"},
 
 		},
 	},
@@ -561,18 +561,18 @@ static struct bpf_align_test tests[] = {
 			/* Adding 14 makes R6 be (4n+2) */
 			{11, "R6_w=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"},
 			/* Subtracting from packet pointer overflows ubounds */
-			{13, "R5_w=pkt(id=1,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c)"},
+			{13, "R5_w=pkt(id=2,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c)"},
 			/* New unknown value in R7 is (4n), >= 76 */
 			{15, "R7_w=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"},
 			/* Adding it to packet pointer gives nice bounds again */
-			{16, "R5_w=pkt(id=2,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0xfffffffc)"},
+			{16, "R5_w=pkt(id=3,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0xfffffffc)"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (0)
 			 * which is 2.  Then the variable offset is (4n+2), so
 			 * the total offset is 4-byte aligned and meets the
 			 * load's requirements.
 			 */
-			{20, "R5=pkt(id=2,off=0,r=4,umin_value=2,umax_value=1082,var_off=(0x2; 0xfffffffc)"},
+			{20, "R5=pkt(id=3,off=0,r=4,umin_value=2,umax_value=1082,var_off=(0x2; 0xfffffffc)"},
 		},
 	},
 };

tools/testing/selftests/bpf/prog_tests/test_profiler.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <test_progs.h>
+#include "progs/profiler.h"
+#include "profiler1.skel.h"
+#include "profiler2.skel.h"
+#include "profiler3.skel.h"
+
+static int sanity_run(struct bpf_program *prog)
+{
+	struct bpf_prog_test_run_attr test_attr = {};
+	__u64 args[] = {1, 2, 3};
+	__u32 duration = 0;
+	int err, prog_fd;
+
+	prog_fd = bpf_program__fd(prog);
+	test_attr.prog_fd = prog_fd;
+	test_attr.ctx_in = args;
+	test_attr.ctx_size_in = sizeof(args);
+	err = bpf_prog_test_run_xattr(&test_attr);
+	if (CHECK(err || test_attr.retval, "test_run",
+		  "err %d errno %d retval %d duration %d\n",
+		  err, errno, test_attr.retval, duration))
+		return -1;
+	return 0;
+}
+
+void test_test_profiler(void)
+{
+	struct profiler1 *profiler1_skel = NULL;
+	struct profiler2 *profiler2_skel = NULL;
+	struct profiler3 *profiler3_skel = NULL;
+	__u32 duration = 0;
+	int err;
+
+	profiler1_skel = profiler1__open_and_load();
+	if (CHECK(!profiler1_skel, "profiler1_skel_load", "profiler1 skeleton failed\n"))
+		goto cleanup;
+
+	err = profiler1__attach(profiler1_skel);
+	if (CHECK(err, "profiler1_attach", "profiler1 attach failed: %d\n", err))
+		goto cleanup;
+
+	if (sanity_run(profiler1_skel->progs.raw_tracepoint__sched_process_exec))
+		goto cleanup;
+
+	profiler2_skel = profiler2__open_and_load();
+	if (CHECK(!profiler2_skel, "profiler2_skel_load", "profiler2 skeleton failed\n"))
+		goto cleanup;
+
+	err = profiler2__attach(profiler2_skel);
+	if (CHECK(err, "profiler2_attach", "profiler2 attach failed: %d\n", err))
+		goto cleanup;
+
+	if (sanity_run(profiler2_skel->progs.raw_tracepoint__sched_process_exec))
+		goto cleanup;
+
+	profiler3_skel = profiler3__open_and_load();
+	if (CHECK(!profiler3_skel, "profiler3_skel_load", "profiler3 skeleton failed\n"))
+		goto cleanup;
+
+	err = profiler3__attach(profiler3_skel);
+	if (CHECK(err, "profiler3_attach", "profiler3 attach failed: %d\n", err))
+		goto cleanup;
+
+	if (sanity_run(profiler3_skel->progs.raw_tracepoint__sched_process_exec))
+		goto cleanup;
+cleanup:
+	profiler1__destroy(profiler1_skel);
+	profiler2__destroy(profiler2_skel);
+	profiler3__destroy(profiler3_skel);
+}

tools/testing/selftests/bpf/progs/profiler.h

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#pragma once
+
+#define TASK_COMM_LEN 16
+#define MAX_ANCESTORS 4
+#define MAX_PATH 256
+#define KILL_TARGET_LEN 64
+#define CTL_MAXNAME 10
+#define MAX_ARGS_LEN 4096
+#define MAX_FILENAME_LEN 512
+#define MAX_ENVIRON_LEN 8192
+#define MAX_PATH_DEPTH 32
+#define MAX_FILEPATH_LENGTH (MAX_PATH_DEPTH * MAX_PATH)
+#define MAX_CGROUPS_PATH_DEPTH 8
+
+#define MAX_METADATA_PAYLOAD_LEN TASK_COMM_LEN
+
+#define MAX_CGROUP_PAYLOAD_LEN \
+	(MAX_PATH * 2 + (MAX_PATH * MAX_CGROUPS_PATH_DEPTH))
+
+#define MAX_CAP_PAYLOAD_LEN (MAX_METADATA_PAYLOAD_LEN + MAX_CGROUP_PAYLOAD_LEN)
+
+#define MAX_SYSCTL_PAYLOAD_LEN \
+	(MAX_METADATA_PAYLOAD_LEN + MAX_CGROUP_PAYLOAD_LEN + CTL_MAXNAME + MAX_PATH)
+
+#define MAX_KILL_PAYLOAD_LEN \
+	(MAX_METADATA_PAYLOAD_LEN + MAX_CGROUP_PAYLOAD_LEN + TASK_COMM_LEN + \
+	 KILL_TARGET_LEN)
+
+#define MAX_EXEC_PAYLOAD_LEN \
+	(MAX_METADATA_PAYLOAD_LEN + MAX_CGROUP_PAYLOAD_LEN + MAX_FILENAME_LEN + \
+	 MAX_ARGS_LEN + MAX_ENVIRON_LEN)
+
+#define MAX_FILEMOD_PAYLOAD_LEN \
+	(MAX_METADATA_PAYLOAD_LEN + MAX_CGROUP_PAYLOAD_LEN + MAX_FILEPATH_LENGTH + \
+	 MAX_FILEPATH_LENGTH)
+
+enum data_type {
+	INVALID_EVENT,
+	EXEC_EVENT,
+	FORK_EVENT,
+	KILL_EVENT,
+	SYSCTL_EVENT,
+	FILEMOD_EVENT,
+	MAX_DATA_TYPE_EVENT
+};
+
+enum filemod_type {
+	FMOD_OPEN,
+	FMOD_LINK,
+	FMOD_SYMLINK,
+};
+
+struct ancestors_data_t {
+	pid_t ancestor_pids[MAX_ANCESTORS];
+	uint32_t ancestor_exec_ids[MAX_ANCESTORS];
+	uint64_t ancestor_start_times[MAX_ANCESTORS];
+	uint32_t num_ancestors;
+};
+
+struct var_metadata_t {
+	enum data_type type;
+	pid_t pid;
+	uint32_t exec_id;
+	uid_t uid;
+	gid_t gid;
+	uint64_t start_time;
+	uint32_t cpu_id;
+	uint64_t bpf_stats_num_perf_events;
+	uint64_t bpf_stats_start_ktime_ns;
+	uint8_t comm_length;
+};
+
+struct cgroup_data_t {
+	ino_t cgroup_root_inode;
+	ino_t cgroup_proc_inode;
+	uint64_t cgroup_root_mtime;
+	uint64_t cgroup_proc_mtime;
+	uint16_t cgroup_root_length;
+	uint16_t cgroup_proc_length;
+	uint16_t cgroup_full_length;
+	int cgroup_full_path_root_pos;
+};
+
+struct var_sysctl_data_t {
+	struct var_metadata_t meta;
+	struct cgroup_data_t cgroup_data;
+	struct ancestors_data_t ancestors_info;
+	uint8_t sysctl_val_length;
+	uint16_t sysctl_path_length;
+	char payload[MAX_SYSCTL_PAYLOAD_LEN];
+};
+
+struct var_kill_data_t {
+	struct var_metadata_t meta;
+	struct cgroup_data_t cgroup_data;
+	struct ancestors_data_t ancestors_info;
+	pid_t kill_target_pid;
+	int kill_sig;
+	uint32_t kill_count;
+	uint64_t last_kill_time;
+	uint8_t kill_target_name_length;
+	uint8_t kill_target_cgroup_proc_length;
+	char payload[MAX_KILL_PAYLOAD_LEN];
+	size_t payload_length;
+};
+
+struct var_exec_data_t {
+	struct var_metadata_t meta;
+	struct cgroup_data_t cgroup_data;
+	pid_t parent_pid;
+	uint32_t parent_exec_id;
+	uid_t parent_uid;
+	uint64_t parent_start_time;
+	uint16_t bin_path_length;
+	uint16_t cmdline_length;
+	uint16_t environment_length;
+	char payload[MAX_EXEC_PAYLOAD_LEN];
+};
+
+struct var_fork_data_t {
+	struct var_metadata_t meta;
+	pid_t parent_pid;
+	uint32_t parent_exec_id;
+	uint64_t parent_start_time;
+	char payload[MAX_METADATA_PAYLOAD_LEN];
+};
+
+struct var_filemod_data_t {
+	struct var_metadata_t meta;
+	struct cgroup_data_t cgroup_data;
+	enum filemod_type fmod_type;
+	unsigned int dst_flags;
+	uint32_t src_device_id;
+	uint32_t dst_device_id;
+	ino_t src_inode;
+	ino_t dst_inode;
+	uint16_t src_filepath_length;
+	uint16_t dst_filepath_length;
+	char payload[MAX_FILEMOD_PAYLOAD_LEN];
+};
+
+struct profiler_config_struct {
+	bool fetch_cgroups_from_bpf;
+	ino_t cgroup_fs_inode;
+	ino_t cgroup_login_session_inode;
+	uint64_t kill_signals_mask;
+	ino_t inode_filter;
+	uint32_t stale_info_secs;
+	bool use_variable_buffers;
+	bool read_environ_from_exec;
+	bool enable_cgroup_v1_resolver;
+};
+
+struct bpf_func_stats_data {
+	uint64_t time_elapsed_ns;
+	uint64_t num_executions;
+	uint64_t num_perf_events;
+};
+
+struct bpf_func_stats_ctx {
+	uint64_t start_time_ns;
+	struct bpf_func_stats_data* bpf_func_stats_data_val;
+};
+
+enum bpf_function_id {
+	profiler_bpf_proc_sys_write,
+	profiler_bpf_sched_process_exec,
+	profiler_bpf_sched_process_exit,
+	profiler_bpf_sys_enter_kill,
+	profiler_bpf_do_filp_open_ret,
+	profiler_bpf_sched_process_fork,
+	profiler_bpf_vfs_link,
+	profiler_bpf_vfs_symlink,
+	profiler_bpf_max_function_id
+};

tools/testing/selftests/bpf/progs/profiler1.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#define barrier_var(var) asm volatile("" : "=r"(var) : "0"(var))
+#define UNROLL
+#define INLINE __always_inline
+#include "profiler.inc.h"

tools/testing/selftests/bpf/progs/profiler2.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#define barrier_var(var) /**/
+/* undef #define UNROLL */
+#define INLINE /**/
+#include "profiler.inc.h"

tools/testing/selftests/bpf/progs/profiler3.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#define barrier_var(var) /**/
+#define UNROLL
+#define INLINE __noinline
+#include "profiler.inc.h"

tools/testing/selftests/bpf/verifier/direct_packet_access.c

@@ -529,7 +529,7 @@
 	},
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.result = REJECT,
-	.errstr = "invalid access to packet, off=0 size=8, R5(id=1,off=0,r=0)",
+	.errstr = "invalid access to packet, off=0 size=8, R5(id=2,off=0,r=0)",
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {

tools/testing/selftests/bpf/verifier/regalloc.c

+{
+	"regalloc basic",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
+	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+	BPF_JMP_IMM(BPF_JSGT, BPF_REG_0, 20, 4),
+	BPF_JMP_IMM(BPF_JSLT, BPF_REG_2, 0, 3),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_2),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_hash_48b = { 4 },
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+	"regalloc negative",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
+	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+	BPF_JMP_IMM(BPF_JSGT, BPF_REG_0, 24, 4),
+	BPF_JMP_IMM(BPF_JSLT, BPF_REG_2, 0, 3),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_2),
+	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_7, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_hash_48b = { 4 },
+	.result = REJECT,
+	.errstr = "invalid access to map value, value_size=48 off=48 size=1",
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+	"regalloc src_reg mark",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
+	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+	BPF_JMP_IMM(BPF_JSGT, BPF_REG_0, 20, 5),
+	BPF_MOV64_IMM(BPF_REG_3, 0),
+	BPF_JMP_REG(BPF_JSGE, BPF_REG_3, BPF_REG_2, 3),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_2),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_hash_48b = { 4 },
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+	"regalloc src_reg negative",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
+	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+	BPF_JMP_IMM(BPF_JSGT, BPF_REG_0, 22, 5),
+	BPF_MOV64_IMM(BPF_REG_3, 0),
+	BPF_JMP_REG(BPF_JSGE, BPF_REG_3, BPF_REG_2, 3),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_2),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_hash_48b = { 4 },
+	.result = REJECT,
+	.errstr = "invalid access to map value, value_size=48 off=44 size=8",
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+	"regalloc and spill",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
+	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+	BPF_JMP_IMM(BPF_JSGT, BPF_REG_0, 20, 7),
+	/* r0 has upper bound that should propagate into r2 */
+	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -8), /* spill r2 */
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_2, 0), /* clear r0 and r2 */
+	BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_10, -8), /* fill r3 */
+	BPF_JMP_REG(BPF_JSGE, BPF_REG_0, BPF_REG_3, 2),
+	/* r3 has lower and upper bounds */
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_3),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_hash_48b = { 4 },
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+	"regalloc and spill negative",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
+	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+	BPF_JMP_IMM(BPF_JSGT, BPF_REG_0, 48, 7),
+	/* r0 has upper bound that should propagate into r2 */
+	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -8), /* spill r2 */
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_2, 0), /* clear r0 and r2 */
+	BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_10, -8), /* fill r3 */
+	BPF_JMP_REG(BPF_JSGE, BPF_REG_0, BPF_REG_3, 2),
+	/* r3 has lower and upper bounds */
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_3),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_hash_48b = { 4 },
+	.result = REJECT,
+	.errstr = "invalid access to map value, value_size=48 off=48 size=8",
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+	"regalloc three regs",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10),
+	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
+	BPF_JMP_IMM(BPF_JSGT, BPF_REG_0, 12, 5),
+	BPF_JMP_IMM(BPF_JSLT, BPF_REG_2, 0, 4),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_2),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_4),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_hash_48b = { 4 },
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+	"regalloc after call",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10),
+	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
+	BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_9, BPF_REG_0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 6),
+	BPF_JMP_IMM(BPF_JSGT, BPF_REG_8, 20, 4),
+	BPF_JMP_IMM(BPF_JSLT, BPF_REG_9, 0, 3),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_8),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_9),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_hash_48b = { 4 },
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+	"regalloc in callee",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_3, BPF_REG_7),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 20, 5),
+	BPF_JMP_IMM(BPF_JSLT, BPF_REG_2, 0, 4),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_1),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_2),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_hash_48b = { 4 },
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},