Merge branch 'implement-cpuv4-support-for-s390x'

Ilya Leoshkevich says:

====================
Implement cpuv4 support for s390x

v1: https://lore.kernel.org/bpf/20230830011128.1415752-1-iii@linux.ibm.com/
v1 -> v2:
- Redo Disable zero-extension for BPF_MEMSX as Puranjay and Alexei
  suggested.
- Drop the bpf_ct_insert_entry() patch, it went in via the bpf tree.
- Rebase, don't apply A-bs because there were fixed conflicts.

Hi,

This series adds the cpuv4 support to the s390x eBPF JIT.
Patches 1-3 are preliminary bugfixes.
Patches 4-8 implement the new instructions.
Patches 9-10 enable the tests.

Best regards,
Ilya
====================

Link: https://lore.kernel.org/r/20230919101336.2223655-1-iii@linux.ibm.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

8 files changed, 128 insertions, 100 deletions

diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x
index ce6f291665cf..1a63996c0304 100644
--- a/tools/testing/selftests/bpf/DENYLIST.s390x
+++ b/tools/testing/selftests/bpf/DENYLIST.s390x
@@ -1,30 +1,5 @@
 # TEMPORARY
 # Alphabetical order
-bloom_filter_map                         # failed to find kernel BTF type ID of '__x64_sys_getpgid': -3                (?)
-bpf_cookie                               # failed to open_and_load program: -524 (trampoline)
-bpf_loop                                 # attaches to __x64_sys_nanosleep
-cgrp_local_storage                       # prog_attach unexpected error: -524                                          (trampoline)
-dynptr/test_dynptr_skb_data
-dynptr/test_skb_readonly
 exceptions				 # JIT does not support calling kfunc bpf_throw				       (exceptions)
-fexit_sleep                              # fexit_skel_load fexit skeleton failed                                       (trampoline)
 get_stack_raw_tp                         # user_stack corrupted user stack                                             (no backchain userspace)
-iters/testmod_seq*                       # s390x doesn't support kfuncs in modules yet
-kprobe_multi_bench_attach                # bpf_program__attach_kprobe_multi_opts unexpected error: -95
-kprobe_multi_test                        # relies on fentry
-ksyms_btf/weak_ksyms*                    # test_ksyms_weak__open_and_load unexpected error: -22                        (kfunc)
-ksyms_module                             # test_ksyms_module__open_and_load unexpected error: -9                       (?)
-ksyms_module_libbpf                      # JIT does not support calling kernel function                                (kfunc)
-ksyms_module_lskel                       # test_ksyms_module_lskel__open_and_load unexpected error: -9                 (?)
-module_attach                            # skel_attach skeleton attach failed: -524                                    (trampoline)
-ringbuf                                  # skel_load skeleton load failed                                              (?)
 stacktrace_build_id                      # compare_map_keys stackid_hmap vs. stackmap err -2 errno 2                   (?)
-test_lsm                                 # attach unexpected error: -524                                               (trampoline)
-trace_printk                             # trace_printk__load unexpected error: -2 (errno 2)                           (?)
-trace_vprintk                            # trace_vprintk__open_and_load unexpected error: -9                           (?)
-unpriv_bpf_disabled                      # fentry
-user_ringbuf                             # failed to find kernel BTF type ID of '__s390x_sys_prctl': -3                (?)
-verif_stats                              # trace_vprintk__open_and_load unexpected error: -9                           (?)
-xdp_bonding                              # failed to auto-attach program 'trace_on_entry': -524                        (trampoline)
-xdp_metadata                             # JIT does not support calling kernel function                                (kfunc)
-test_task_under_cgroup                   # JIT does not support calling kernel function                                (kfunc)
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index 2caee8423ee0..24ba56d42f2d 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -49,6 +49,10 @@
 	snprintf(buf, sizeof(buf), "%s%s", NETCLS_MOUNT_PATH,	\
 		 CGROUP_WORK_DIR)
 
+static __thread bool cgroup_workdir_mounted;
+
+static void __cleanup_cgroup_environment(void);
+
 static int __enable_controllers(const char *cgroup_path, const char *controllers)
 {
 	char path[PATH_MAX + 1];
@@ -209,9 +213,10 @@ int setup_cgroup_environment(void)
 		log_err("mount cgroup2");
 		return 1;
 	}
+	cgroup_workdir_mounted = true;
 
 	/* Cleanup existing failed runs, now that the environment is setup */
-	cleanup_cgroup_environment();
+	__cleanup_cgroup_environment();
 
 	if (mkdir(cgroup_workdir, 0777) && errno != EEXIST) {
 		log_err("mkdir cgroup work dir");
@@ -306,10 +311,25 @@ int join_parent_cgroup(const char *relative_path)
 }
 
 /**
+ * __cleanup_cgroup_environment() - Delete temporary cgroups
+ *
+ * This is a helper for cleanup_cgroup_environment() that is responsible for
+ * deletion of all temporary cgroups that have been created during the test.
+ */
+static void __cleanup_cgroup_environment(void)
+{
+	char cgroup_workdir[PATH_MAX + 1];
+
+	format_cgroup_path(cgroup_workdir, "");
+	join_cgroup_from_top(CGROUP_MOUNT_PATH);
+	nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT);
+}
+
+/**
  * cleanup_cgroup_environment() - Cleanup Cgroup Testing Environment
  *
  * This is an idempotent function to delete all temporary cgroups that
- * have been created during the test, including the cgroup testing work
+ * have been created during the test and unmount the cgroup testing work
  * directory.
  *
  * At call time, it moves the calling process to the root cgroup, and then
@@ -320,11 +340,10 @@ int join_parent_cgroup(const char *relative_path)
  */
 void cleanup_cgroup_environment(void)
 {
-	char cgroup_workdir[PATH_MAX + 1];
-
-	format_cgroup_path(cgroup_workdir, "");
-	join_cgroup_from_top(CGROUP_MOUNT_PATH);
-	nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT);
+	__cleanup_cgroup_environment();
+	if (cgroup_workdir_mounted && umount(CGROUP_MOUNT_PATH))
+		log_err("umount cgroup2");
+	cgroup_workdir_mounted = false;
 }
 
 /**
diff --git a/tools/testing/selftests/bpf/progs/test_ldsx_insn.c b/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
index 67c14ba1e87b..3ddcb3777912 100644
--- a/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
+++ b/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
@@ -6,7 +6,8 @@
 #include <bpf/bpf_tracing.h>
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
-     (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) && __clang_major__ >= 18
+     (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) ||       \
+     defined(__TARGET_ARCH_s390)) && __clang_major__ >= 18
 const volatile int skip = 0;
 #else
 const volatile int skip = 1;
@@ -104,7 +105,11 @@ int _tc(volatile struct __sk_buff *skb)
 		      "%[tmp_mark] = r1"
 		      : [tmp_mark]"=r"(tmp_mark)
 		      : [ctx]"r"(skb),
-			[off_mark]"i"(offsetof(struct __sk_buff, mark))
+			[off_mark]"i"(offsetof(struct __sk_buff, mark)
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+			+ sizeof(skb->mark) - 1
+#endif
+			)
 		      : "r1");
 #else
 	tmp_mark = (char)skb->mark;
diff --git a/tools/testing/selftests/bpf/progs/verifier_bswap.c b/tools/testing/selftests/bpf/progs/verifier_bswap.c
index 5d54f8eae6a1..107525fb4a6a 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bswap.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bswap.c
@@ -5,7 +5,8 @@
 #include "bpf_misc.h"
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
-	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || defined(__TARGET_ARCH_arm)) && \
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
+        defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390)) && \
 	__clang_major__ >= 18
 
 SEC("socket")
diff --git a/tools/testing/selftests/bpf/progs/verifier_gotol.c b/tools/testing/selftests/bpf/progs/verifier_gotol.c
index aa54ecd5829e..9f202eda952f 100644
--- a/tools/testing/selftests/bpf/progs/verifier_gotol.c
+++ b/tools/testing/selftests/bpf/progs/verifier_gotol.c
@@ -5,7 +5,8 @@
 #include "bpf_misc.h"
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
-	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || defined(__TARGET_ARCH_arm)) && \
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
+        defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390)) && \
 	__clang_major__ >= 18
 
 SEC("socket")
diff --git a/tools/testing/selftests/bpf/progs/verifier_ldsx.c b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
index 1e1bc379c44f..f90016a57eec 100644
--- a/tools/testing/selftests/bpf/progs/verifier_ldsx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
@@ -5,7 +5,8 @@
 #include "bpf_misc.h"
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
-	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || defined(__TARGET_ARCH_arm)) && \
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
+        defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390)) && \
 	__clang_major__ >= 18
 
 SEC("socket")
@@ -13,12 +14,16 @@ __description("LDSX, S8")
 __success __success_unpriv __retval(-2)
 __naked void ldsx_s8(void)
 {
-	asm volatile ("					\
-	r1 = 0x3fe;					\
-	*(u64 *)(r10 - 8) = r1;				\
-	r0 = *(s8 *)(r10 - 8);				\
-	exit;						\
-"	::: __clobber_all);
+	asm volatile (
+	"r1 = 0x3fe;"
+	"*(u64 *)(r10 - 8) = r1;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r0 = *(s8 *)(r10 - 8);"
+#else
+	"r0 = *(s8 *)(r10 - 1);"
+#endif
+	"exit;"
+	::: __clobber_all);
 }
 
 SEC("socket")
@@ -26,12 +31,16 @@ __description("LDSX, S16")
 __success __success_unpriv __retval(-2)
 __naked void ldsx_s16(void)
 {
-	asm volatile ("					\
-	r1 = 0x3fffe;					\
-	*(u64 *)(r10 - 8) = r1;				\
-	r0 = *(s16 *)(r10 - 8);				\
-	exit;						\
-"	::: __clobber_all);
+	asm volatile (
+	"r1 = 0x3fffe;"
+	"*(u64 *)(r10 - 8) = r1;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r0 = *(s16 *)(r10 - 8);"
+#else
+	"r0 = *(s16 *)(r10 - 2);"
+#endif
+	"exit;"
+	::: __clobber_all);
 }
 
 SEC("socket")
@@ -39,13 +48,17 @@ __description("LDSX, S32")
 __success __success_unpriv __retval(-1)
 __naked void ldsx_s32(void)
 {
-	asm volatile ("					\
-	r1 = 0xfffffffe;				\
-	*(u64 *)(r10 - 8) = r1;				\
-	r0 = *(s32 *)(r10 - 8);				\
-	r0 >>= 1;					\
-	exit;						\
-"	::: __clobber_all);
+	asm volatile (
+	"r1 = 0xfffffffe;"
+	"*(u64 *)(r10 - 8) = r1;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r0 = *(s32 *)(r10 - 8);"
+#else
+	"r0 = *(s32 *)(r10 - 4);"
+#endif
+	"r0 >>= 1;"
+	"exit;"
+	::: __clobber_all);
 }
 
 SEC("socket")
@@ -54,20 +67,24 @@ __log_level(2) __success __retval(1)
 __msg("R1_w=scalar(smin=-128,smax=127)")
 __naked void ldsx_s8_range_priv(void)
 {
-	asm volatile ("					\
-	call %[bpf_get_prandom_u32];			\
-	*(u64 *)(r10 - 8) = r0;				\
-	r1 = *(s8 *)(r10 - 8);				\
-	/* r1 with s8 range */				\
-	if r1 s> 0x7f goto l0_%=;			\
-	if r1 s< -0x80 goto l0_%=;			\
-	r0 = 1;						\
-l1_%=:							\
-	exit;						\
-l0_%=:							\
-	r0 = 2;						\
-	goto l1_%=;					\
-"	:
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"*(u64 *)(r10 - 8) = r0;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r1 = *(s8 *)(r10 - 8);"
+#else
+	"r1 = *(s8 *)(r10 - 1);"
+#endif
+	/* r1 with s8 range */
+	"if r1 s> 0x7f goto l0_%=;"
+	"if r1 s< -0x80 goto l0_%=;"
+	"r0 = 1;"
+"l1_%=:"
+	"exit;"
+"l0_%=:"
+	"r0 = 2;"
+	"goto l1_%=;"
+	:
 	: __imm(bpf_get_prandom_u32)
 	: __clobber_all);
 }
@@ -77,20 +94,24 @@ __description("LDSX, S16 range checking")
 __success __success_unpriv __retval(1)
 __naked void ldsx_s16_range(void)
 {
-	asm volatile ("					\
-	call %[bpf_get_prandom_u32];			\
-	*(u64 *)(r10 - 8) = r0;				\
-	r1 = *(s16 *)(r10 - 8);				\
-	/* r1 with s16 range */				\
-	if r1 s> 0x7fff goto l0_%=;			\
-	if r1 s< -0x8000 goto l0_%=;			\
-	r0 = 1;						\
-l1_%=:							\
-	exit;						\
-l0_%=:							\
-	r0 = 2;						\
-	goto l1_%=;					\
-"	:
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"*(u64 *)(r10 - 8) = r0;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r1 = *(s16 *)(r10 - 8);"
+#else
+	"r1 = *(s16 *)(r10 - 2);"
+#endif
+	/* r1 with s16 range */
+	"if r1 s> 0x7fff goto l0_%=;"
+	"if r1 s< -0x8000 goto l0_%=;"
+	"r0 = 1;"
+"l1_%=:"
+	"exit;"
+"l0_%=:"
+	"r0 = 2;"
+	"goto l1_%=;"
+	:
 	: __imm(bpf_get_prandom_u32)
 	: __clobber_all);
 }
@@ -100,20 +121,24 @@ __description("LDSX, S32 range checking")
 __success __success_unpriv __retval(1)
 __naked void ldsx_s32_range(void)
 {
-	asm volatile ("					\
-	call %[bpf_get_prandom_u32];			\
-	*(u64 *)(r10 - 8) = r0;				\
-	r1 = *(s32 *)(r10 - 8);				\
-	/* r1 with s16 range */				\
-	if r1 s> 0x7fffFFFF goto l0_%=;			\
-	if r1 s< -0x80000000 goto l0_%=;		\
-	r0 = 1;						\
-l1_%=:							\
-	exit;						\
-l0_%=:							\
-	r0 = 2;						\
-	goto l1_%=;					\
-"	:
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"*(u64 *)(r10 - 8) = r0;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r1 = *(s32 *)(r10 - 8);"
+#else
+	"r1 = *(s32 *)(r10 - 4);"
+#endif
+	/* r1 with s16 range */
+	"if r1 s> 0x7fffFFFF goto l0_%=;"
+	"if r1 s< -0x80000000 goto l0_%=;"
+	"r0 = 1;"
+"l1_%=:"
+	"exit;"
+"l0_%=:"
+	"r0 = 2;"
+	"goto l1_%=;"
+	:
 	: __imm(bpf_get_prandom_u32)
 	: __clobber_all);
 }
diff --git a/tools/testing/selftests/bpf/progs/verifier_movsx.c b/tools/testing/selftests/bpf/progs/verifier_movsx.c
index ca11fd5dafd1..b2a04d1179d0 100644
--- a/tools/testing/selftests/bpf/progs/verifier_movsx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_movsx.c
@@ -5,7 +5,8 @@
 #include "bpf_misc.h"
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
-	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || defined(__TARGET_ARCH_arm)) && \
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
+        defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390)) && \
 	__clang_major__ >= 18
 
 SEC("socket")
diff --git a/tools/testing/selftests/bpf/progs/verifier_sdiv.c b/tools/testing/selftests/bpf/progs/verifier_sdiv.c
index fb039722b639..8fc5174808b2 100644
--- a/tools/testing/selftests/bpf/progs/verifier_sdiv.c
+++ b/tools/testing/selftests/bpf/progs/verifier_sdiv.c
@@ -5,7 +5,8 @@
 #include "bpf_misc.h"
 
 #if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
-	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || defined(__TARGET_ARCH_arm)) && \
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
+        defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390)) && \
 	__clang_major__ >= 18
 
 SEC("socket")