selftests/bpf: Enable timed may_goto tests for arm64

As arm64 JIT now supports timed may_goto instruction, make sure all
relevant tests run on this architecture. Some tests were enabled and
other required modifications to work properly on arm64.

 $ ./test_progs -a "stream*","*may_goto*",verifier_bpf_fastcall

 #404     stream_errors:OK
 [...]
 #406/2   stream_success/stream_cond_break:OK
 [...]
 #494/23  verifier_bpf_fastcall/may_goto_interaction_x86_64:SKIP
 #494/24  verifier_bpf_fastcall/may_goto_interaction_arm64:OK
 [...]
 #539/1   verifier_may_goto_1/may_goto 0:OK
 #539/2   verifier_may_goto_1/batch 2 of may_goto 0:OK
 #539/3   verifier_may_goto_1/may_goto batch with offsets 2/1/0:OK
 #539/4   verifier_may_goto_1/may_goto batch with offsets 2/0:OK
 #539     verifier_may_goto_1:OK
 #540/1   verifier_may_goto_2/C code with may_goto 0:OK
 #540     verifier_may_goto_2:OK
 Summary: 7/16 PASSED, 25 SKIPPED, 0 FAILED

Signed-off-by: Puranjay Mohan <[email protected]>
Acked-by: Kumar Kartikeya Dwivedi <[email protected]>
Acked-by: Xu Kuohai <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Alexei Starovoitov <[email protected]>

Author: puranjaymohan

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

@@ -77,7 +77,7 @@ void test_stream_errors(void)
 		ASSERT_OK(ret, "ret");
 		ASSERT_OK(opts.retval, "retval");
 
-#if !defined(__x86_64__) && !defined(__s390x__)
+#if !defined(__x86_64__) && !defined(__s390x__) && !defined(__aarch64__)
 		ASSERT_TRUE(1, "Timed may_goto unsupported, skip.");
 		if (i == 0) {
 			ret = bpf_prog_stream_read(prog_fd, 2, buf, sizeof(buf), &ropts);

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

@@ -660,19 +660,24 @@ __naked void may_goto_interaction_x86_64(void)
 
 SEC("raw_tp")
 __arch_arm64
-__log_level(4) __msg("stack depth 16")
-/* may_goto counter at -16 */
-__xlated("0: *(u64 *)(r10 -16) =")
-__xlated("1: r1 = 1")
-__xlated("2: call bpf_get_smp_processor_id")
+__log_level(4) __msg("stack depth 24")
+/* may_goto counter at -24 */
+__xlated("0: *(u64 *)(r10 -24) =")
+/* may_goto timestamp at -16 */
+__xlated("1: *(u64 *)(r10 -16) =")
+__xlated("2: r1 = 1")
+__xlated("3: call bpf_get_smp_processor_id")
 /* may_goto expansion starts */
-__xlated("3: r11 = *(u64 *)(r10 -16)")
-__xlated("4: if r11 == 0x0 goto pc+3")
-__xlated("5: r11 -= 1")
-__xlated("6: *(u64 *)(r10 -16) = r11")
+__xlated("4: r11 = *(u64 *)(r10 -24)")
+__xlated("5: if r11 == 0x0 goto pc+6")
+__xlated("6: r11 -= 1")
+__xlated("7: if r11 != 0x0 goto pc+2")
+__xlated("8: r11 = -24")
+__xlated("9: call unknown")
+__xlated("10: *(u64 *)(r10 -24) = r11")
 /* may_goto expansion ends */
-__xlated("7: *(u64 *)(r10 -8) = r1")
-__xlated("8: exit")
+__xlated("11: *(u64 *)(r10 -8) = r1")
+__xlated("12: exit")
 __success
 __naked void may_goto_interaction_arm64(void)
 {

tools/testing/selftests/bpf/progs/verifier_may_goto_1.c

@@ -10,6 +10,7 @@ SEC("raw_tp")
 __description("may_goto 0")
 __arch_x86_64
 __arch_s390x
+__arch_arm64
 __xlated("0: r0 = 1")
 __xlated("1: exit")
 __success
@@ -29,6 +30,7 @@ SEC("raw_tp")
 __description("batch 2 of may_goto 0")
 __arch_x86_64
 __arch_s390x
+__arch_arm64
 __xlated("0: r0 = 1")
 __xlated("1: exit")
 __success
@@ -50,6 +52,7 @@ SEC("raw_tp")
 __description("may_goto batch with offsets 2/1/0")
 __arch_x86_64
 __arch_s390x
+__arch_arm64
 __xlated("0: r0 = 1")
 __xlated("1: exit")
 __success
@@ -72,9 +75,10 @@ __naked void may_goto_batch_1(void)
 }
 
 SEC("raw_tp")
-__description("may_goto batch with offsets 2/0 - x86_64 and s390x")
+__description("may_goto batch with offsets 2/0")
 __arch_x86_64
 __arch_s390x
+__arch_arm64
 __xlated("0: *(u64 *)(r10 -16) = 65535")
 __xlated("1: *(u64 *)(r10 -8) = 0")
 __xlated("2: r11 = *(u64 *)(r10 -16)")
@@ -88,33 +92,7 @@ __xlated("9: r0 = 1")
 __xlated("10: r0 = 2")
 __xlated("11: exit")
 __success
-__naked void may_goto_batch_2_x86_64_s390x(void)
-{
-	asm volatile (
-	".8byte %[may_goto1];"
-	".8byte %[may_goto3];"
-	"r0 = 1;"
-	"r0 = 2;"
-	"exit;"
-	:
-	: __imm_insn(may_goto1, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 2 /* offset */, 0)),
-	  __imm_insn(may_goto3, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 0 /* offset */, 0))
-	: __clobber_all);
-}
-
-SEC("raw_tp")
-__description("may_goto batch with offsets 2/0 - arm64")
-__arch_arm64
-__xlated("0: *(u64 *)(r10 -8) = 8388608")
-__xlated("1: r11 = *(u64 *)(r10 -8)")
-__xlated("2: if r11 == 0x0 goto pc+3")
-__xlated("3: r11 -= 1")
-__xlated("4: *(u64 *)(r10 -8) = r11")
-__xlated("5: r0 = 1")
-__xlated("6: r0 = 2")
-__xlated("7: exit")
-__success
-__naked void may_goto_batch_2_arm64(void)
+__naked void may_goto_batch_2(void)
 {
 	asm volatile (
 	".8byte %[may_goto1];"