Merge tag 'kvmarm-fixes-for-5.3' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm fixes for 5.3

- A bunch of switch/case fall-through annotation, fixing one actual bug
- Fix PMU reset bug
- Add missing exception class debug strings

44 files changed, 1097 insertions, 212 deletions

diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c
index 076df22e4bda..cd040b5abffe 100644
--- a/tools/testing/nvdimm/test/iomap.c
+++ b/tools/testing/nvdimm/test/iomap.c
@@ -100,25 +100,60 @@ static void nfit_test_kill(void *_pgmap)
 {
 	struct dev_pagemap *pgmap = _pgmap;
 
-	WARN_ON(!pgmap || !pgmap->ref || !pgmap->kill || !pgmap->cleanup);
-	pgmap->kill(pgmap->ref);
-	pgmap->cleanup(pgmap->ref);
+	WARN_ON(!pgmap || !pgmap->ref);
+
+	if (pgmap->ops && pgmap->ops->kill)
+		pgmap->ops->kill(pgmap);
+	else
+		percpu_ref_kill(pgmap->ref);
+
+	if (pgmap->ops && pgmap->ops->cleanup) {
+		pgmap->ops->cleanup(pgmap);
+	} else {
+		wait_for_completion(&pgmap->done);
+		percpu_ref_exit(pgmap->ref);
+	}
+}
+
+static void dev_pagemap_percpu_release(struct percpu_ref *ref)
+{
+	struct dev_pagemap *pgmap =
+		container_of(ref, struct dev_pagemap, internal_ref);
+
+	complete(&pgmap->done);
 }
 
 void *__wrap_devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 {
+	int error;
 	resource_size_t offset = pgmap->res.start;
 	struct nfit_test_resource *nfit_res = get_nfit_res(offset);
 
-	if (nfit_res) {
-		int rc;
-
-		rc = devm_add_action_or_reset(dev, nfit_test_kill, pgmap);
-		if (rc)
-			return ERR_PTR(rc);
-		return nfit_res->buf + offset - nfit_res->res.start;
+	if (!nfit_res)
+		return devm_memremap_pages(dev, pgmap);
+
+	pgmap->dev = dev;
+	if (!pgmap->ref) {
+		if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup))
+			return ERR_PTR(-EINVAL);
+
+		init_completion(&pgmap->done);
+		error = percpu_ref_init(&pgmap->internal_ref,
+				dev_pagemap_percpu_release, 0, GFP_KERNEL);
+		if (error)
+			return ERR_PTR(error);
+		pgmap->ref = &pgmap->internal_ref;
+	} else {
+		if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) {
+			WARN(1, "Missing reference count teardown definition\n");
+			return ERR_PTR(-EINVAL);
+		}
 	}
-	return devm_memremap_pages(dev, pgmap);
+
+	error = devm_add_action_or_reset(dev, nfit_test_kill, pgmap);
+	if (error)
+		return ERR_PTR(error);
+	return nfit_res->buf + offset - nfit_res->res.start;
 }
 EXPORT_SYMBOL_GPL(__wrap_devm_memremap_pages);
 
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 2620406a53ec..11c9c62c3362 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -1,4 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
+include ../../../../scripts/Kbuild.include
+include ../../../scripts/Makefile.arch
 
 LIBDIR := ../../../lib
 BPFDIR := $(LIBDIR)/bpf
@@ -81,13 +83,14 @@ all: $(TEST_CUSTOM_PROGS)
 $(OUTPUT)/urandom_read: $(OUTPUT)/%: %.c
 	$(CC) -o $@ $< -Wl,--build-id
 
-$(OUTPUT)/test_maps: map_tests/*.c
+$(OUTPUT)/test_stub.o: test_stub.c
+	$(CC) $(TEST_PROGS_CFLAGS) $(CFLAGS) -c -o $@ $<
 
 BPFOBJ := $(OUTPUT)/libbpf.a
 
-$(TEST_GEN_PROGS): test_stub.o $(BPFOBJ)
+$(TEST_GEN_PROGS): $(OUTPUT)/test_stub.o $(BPFOBJ)
 
-$(TEST_GEN_PROGS_EXTENDED): test_stub.o $(OUTPUT)/libbpf.a
+$(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/test_stub.o $(OUTPUT)/libbpf.a
 
 $(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
 $(OUTPUT)/test_skb_cgroup_id_user: cgroup_helpers.c
@@ -138,7 +141,8 @@ CLANG_SYS_INCLUDES := $(shell $(CLANG) -v -E - </dev/null 2>&1 \
 
 CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \
 	      $(CLANG_SYS_INCLUDES) \
-	      -Wno-compare-distinct-pointer-types
+	      -Wno-compare-distinct-pointer-types \
+	      -D__TARGET_ARCH_$(SRCARCH)
 
 $(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline
 $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline
@@ -172,6 +176,7 @@ endif
 endif
 
 TEST_PROGS_CFLAGS := -I. -I$(OUTPUT)
+TEST_MAPS_CFLAGS := -I. -I$(OUTPUT)
 TEST_VERIFIER_CFLAGS := -I. -I$(OUTPUT) -Iverifier
 
 ifneq ($(SUBREG_CODEGEN),)
@@ -180,12 +185,12 @@ TEST_CUSTOM_PROGS += $(ALU32_BUILD_DIR)/test_progs_32
 $(ALU32_BUILD_DIR):
 	mkdir -p $@
 
-$(ALU32_BUILD_DIR)/urandom_read: $(OUTPUT)/urandom_read
+$(ALU32_BUILD_DIR)/urandom_read: $(OUTPUT)/urandom_read | $(ALU32_BUILD_DIR)
 	cp $< $@
 
 $(ALU32_BUILD_DIR)/test_progs_32: test_progs.c $(OUTPUT)/libbpf.a\
-						$(ALU32_BUILD_DIR) \
-						$(ALU32_BUILD_DIR)/urandom_read
+						$(ALU32_BUILD_DIR)/urandom_read \
+						| $(ALU32_BUILD_DIR)
 	$(CC) $(TEST_PROGS_CFLAGS) $(CFLAGS) \
 		-o $(ALU32_BUILD_DIR)/test_progs_32 \
 		test_progs.c test_stub.c trace_helpers.c prog_tests/*.c \
@@ -194,10 +199,10 @@ $(ALU32_BUILD_DIR)/test_progs_32: test_progs.c $(OUTPUT)/libbpf.a\
 $(ALU32_BUILD_DIR)/test_progs_32: $(PROG_TESTS_H)
 $(ALU32_BUILD_DIR)/test_progs_32: prog_tests/*.c
 
-$(ALU32_BUILD_DIR)/%.o: progs/%.c $(ALU32_BUILD_DIR) \
-					$(ALU32_BUILD_DIR)/test_progs_32
-	$(CLANG) $(CLANG_FLAGS) \
-		 -O2 -target bpf -emit-llvm -c $< -o - |      \
+$(ALU32_BUILD_DIR)/%.o: progs/%.c $(ALU32_BUILD_DIR)/test_progs_32 \
+					| $(ALU32_BUILD_DIR)
+	($(CLANG) $(CLANG_FLAGS) -O2 -target bpf -emit-llvm -c $< -o - || \
+		echo "clang failed") | \
 	$(LLC) -march=bpf -mattr=+alu32 -mcpu=$(CPU) $(LLC_FLAGS) \
 		-filetype=obj -o $@
 ifeq ($(DWARF2BTF),y)
@@ -208,32 +213,30 @@ endif
 # Have one program compiled without "-target bpf" to test whether libbpf loads
 # it successfully
 $(OUTPUT)/test_xdp.o: progs/test_xdp.c
-	$(CLANG) $(CLANG_FLAGS) \
-		-O2 -emit-llvm -c $< -o - | \
+	($(CLANG) $(CLANG_FLAGS) -O2 -emit-llvm -c $< -o - || \
+		echo "clang failed") | \
 	$(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
 ifeq ($(DWARF2BTF),y)
 	$(BTF_PAHOLE) -J $@
 endif
 
 $(OUTPUT)/%.o: progs/%.c
-	$(CLANG) $(CLANG_FLAGS) \
-		 -O2 -target bpf -emit-llvm -c $< -o - |      \
+	($(CLANG) $(CLANG_FLAGS) -O2 -target bpf -emit-llvm -c $< -o - || \
+		echo "clang failed") | \
 	$(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
 ifeq ($(DWARF2BTF),y)
 	$(BTF_PAHOLE) -J $@
 endif
 
-PROG_TESTS_H := $(OUTPUT)/prog_tests/tests.h
-test_progs.c: $(PROG_TESTS_H)
-$(OUTPUT)/test_progs: CFLAGS += $(TEST_PROGS_CFLAGS)
-$(OUTPUT)/test_progs: prog_tests/*.c
-
 PROG_TESTS_DIR = $(OUTPUT)/prog_tests
 $(PROG_TESTS_DIR):
 	mkdir -p $@
-
+PROG_TESTS_H := $(PROG_TESTS_DIR)/tests.h
 PROG_TESTS_FILES := $(wildcard prog_tests/*.c)
-$(PROG_TESTS_H): $(PROG_TESTS_DIR) $(PROG_TESTS_FILES)
+test_progs.c: $(PROG_TESTS_H)
+$(OUTPUT)/test_progs: CFLAGS += $(TEST_PROGS_CFLAGS)
+$(OUTPUT)/test_progs: test_progs.c $(PROG_TESTS_H) $(PROG_TESTS_FILES)
+$(PROG_TESTS_H): $(PROG_TESTS_FILES) | $(PROG_TESTS_DIR)
 	$(shell ( cd prog_tests/; \
 		  echo '/* Generated header, do not edit */'; \
 		  echo '#ifdef DECLARE'; \
@@ -246,15 +249,15 @@ $(PROG_TESTS_H): $(PROG_TESTS_DIR) $(PROG_TESTS_FILES)
 		  echo '#endif' \
 		 ) > $(PROG_TESTS_H))
 
-TEST_MAPS_CFLAGS := -I. -I$(OUTPUT)
 MAP_TESTS_DIR = $(OUTPUT)/map_tests
 $(MAP_TESTS_DIR):
 	mkdir -p $@
 MAP_TESTS_H := $(MAP_TESTS_DIR)/tests.h
+MAP_TESTS_FILES := $(wildcard map_tests/*.c)
 test_maps.c: $(MAP_TESTS_H)
 $(OUTPUT)/test_maps: CFLAGS += $(TEST_MAPS_CFLAGS)
-MAP_TESTS_FILES := $(wildcard map_tests/*.c)
-$(MAP_TESTS_H): $(MAP_TESTS_DIR) $(MAP_TESTS_FILES)
+$(OUTPUT)/test_maps: test_maps.c $(MAP_TESTS_H) $(MAP_TESTS_FILES)
+$(MAP_TESTS_H): $(MAP_TESTS_FILES) | $(MAP_TESTS_DIR)
 	$(shell ( cd map_tests/; \
 		  echo '/* Generated header, do not edit */'; \
 		  echo '#ifdef DECLARE'; \
@@ -267,16 +270,15 @@ $(MAP_TESTS_H): $(MAP_TESTS_DIR) $(MAP_TESTS_FILES)
 		  echo '#endif' \
 		 ) > $(MAP_TESTS_H))
 
-VERIFIER_TESTS_H := $(OUTPUT)/verifier/tests.h
-test_verifier.c: $(VERIFIER_TESTS_H)
-$(OUTPUT)/test_verifier: CFLAGS += $(TEST_VERIFIER_CFLAGS)
-
 VERIFIER_TESTS_DIR = $(OUTPUT)/verifier
 $(VERIFIER_TESTS_DIR):
 	mkdir -p $@
-
+VERIFIER_TESTS_H := $(VERIFIER_TESTS_DIR)/tests.h
 VERIFIER_TEST_FILES := $(wildcard verifier/*.c)
-$(OUTPUT)/verifier/tests.h: $(VERIFIER_TESTS_DIR) $(VERIFIER_TEST_FILES)
+test_verifier.c: $(VERIFIER_TESTS_H)
+$(OUTPUT)/test_verifier: CFLAGS += $(TEST_VERIFIER_CFLAGS)
+$(OUTPUT)/test_verifier: test_verifier.c $(VERIFIER_TESTS_H)
+$(VERIFIER_TESTS_H): $(VERIFIER_TEST_FILES) | $(VERIFIER_TESTS_DIR)
 	$(shell ( cd verifier/; \
 		  echo '/* Generated header, do not edit */'; \
 		  echo '#ifdef FILL_ARRAY'; \
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 5a3d92c8bec8..f804f210244e 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -315,8 +315,8 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
 #if defined(__TARGET_ARCH_x86)
 	#define bpf_target_x86
 	#define bpf_target_defined
-#elif defined(__TARGET_ARCH_s930x)
-	#define bpf_target_s930x
+#elif defined(__TARGET_ARCH_s390)
+	#define bpf_target_s390
 	#define bpf_target_defined
 #elif defined(__TARGET_ARCH_arm)
 	#define bpf_target_arm
@@ -341,8 +341,8 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
 #ifndef bpf_target_defined
 #if defined(__x86_64__)
 	#define bpf_target_x86
-#elif defined(__s390x__)
-	#define bpf_target_s930x
+#elif defined(__s390__)
+	#define bpf_target_s390
 #elif defined(__arm__)
 	#define bpf_target_arm
 #elif defined(__aarch64__)
@@ -358,6 +358,7 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
 
 #if defined(bpf_target_x86)
 
+#ifdef __KERNEL__
 #define PT_REGS_PARM1(x) ((x)->di)
 #define PT_REGS_PARM2(x) ((x)->si)
 #define PT_REGS_PARM3(x) ((x)->dx)
@@ -368,19 +369,49 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
 #define PT_REGS_RC(x) ((x)->ax)
 #define PT_REGS_SP(x) ((x)->sp)
 #define PT_REGS_IP(x) ((x)->ip)
+#else
+#ifdef __i386__
+/* i386 kernel is built with -mregparm=3 */
+#define PT_REGS_PARM1(x) ((x)->eax)
+#define PT_REGS_PARM2(x) ((x)->edx)
+#define PT_REGS_PARM3(x) ((x)->ecx)
+#define PT_REGS_PARM4(x) 0
+#define PT_REGS_PARM5(x) 0
+#define PT_REGS_RET(x) ((x)->esp)
+#define PT_REGS_FP(x) ((x)->ebp)
+#define PT_REGS_RC(x) ((x)->eax)
+#define PT_REGS_SP(x) ((x)->esp)
+#define PT_REGS_IP(x) ((x)->eip)
+#else
+#define PT_REGS_PARM1(x) ((x)->rdi)
+#define PT_REGS_PARM2(x) ((x)->rsi)
+#define PT_REGS_PARM3(x) ((x)->rdx)
+#define PT_REGS_PARM4(x) ((x)->rcx)
+#define PT_REGS_PARM5(x) ((x)->r8)
+#define PT_REGS_RET(x) ((x)->rsp)
+#define PT_REGS_FP(x) ((x)->rbp)
+#define PT_REGS_RC(x) ((x)->rax)
+#define PT_REGS_SP(x) ((x)->rsp)
+#define PT_REGS_IP(x) ((x)->rip)
+#endif
+#endif
 
-#elif defined(bpf_target_s390x)
+#elif defined(bpf_target_s390)
 
-#define PT_REGS_PARM1(x) ((x)->gprs[2])
-#define PT_REGS_PARM2(x) ((x)->gprs[3])
-#define PT_REGS_PARM3(x) ((x)->gprs[4])
-#define PT_REGS_PARM4(x) ((x)->gprs[5])
-#define PT_REGS_PARM5(x) ((x)->gprs[6])
-#define PT_REGS_RET(x) ((x)->gprs[14])
-#define PT_REGS_FP(x) ((x)->gprs[11]) /* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_RC(x) ((x)->gprs[2])
-#define PT_REGS_SP(x) ((x)->gprs[15])
-#define PT_REGS_IP(x) ((x)->psw.addr)
+/* s390 provides user_pt_regs instead of struct pt_regs to userspace */
+struct pt_regs;
+#define PT_REGS_S390 const volatile user_pt_regs
+#define PT_REGS_PARM1(x) (((PT_REGS_S390 *)(x))->gprs[2])
+#define PT_REGS_PARM2(x) (((PT_REGS_S390 *)(x))->gprs[3])
+#define PT_REGS_PARM3(x) (((PT_REGS_S390 *)(x))->gprs[4])
+#define PT_REGS_PARM4(x) (((PT_REGS_S390 *)(x))->gprs[5])
+#define PT_REGS_PARM5(x) (((PT_REGS_S390 *)(x))->gprs[6])
+#define PT_REGS_RET(x) (((PT_REGS_S390 *)(x))->gprs[14])
+/* Works only with CONFIG_FRAME_POINTER */
+#define PT_REGS_FP(x) (((PT_REGS_S390 *)(x))->gprs[11])
+#define PT_REGS_RC(x) (((PT_REGS_S390 *)(x))->gprs[2])
+#define PT_REGS_SP(x) (((PT_REGS_S390 *)(x))->gprs[15])
+#define PT_REGS_IP(x) (((PT_REGS_S390 *)(x))->psw.addr)
 
 #elif defined(bpf_target_arm)
 
@@ -397,16 +428,20 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
 
 #elif defined(bpf_target_arm64)
 
-#define PT_REGS_PARM1(x) ((x)->regs[0])
-#define PT_REGS_PARM2(x) ((x)->regs[1])
-#define PT_REGS_PARM3(x) ((x)->regs[2])
-#define PT_REGS_PARM4(x) ((x)->regs[3])
-#define PT_REGS_PARM5(x) ((x)->regs[4])
-#define PT_REGS_RET(x) ((x)->regs[30])
-#define PT_REGS_FP(x) ((x)->regs[29]) /* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_RC(x) ((x)->regs[0])
-#define PT_REGS_SP(x) ((x)->sp)
-#define PT_REGS_IP(x) ((x)->pc)
+/* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */
+struct pt_regs;
+#define PT_REGS_ARM64 const volatile struct user_pt_regs
+#define PT_REGS_PARM1(x) (((PT_REGS_ARM64 *)(x))->regs[0])
+#define PT_REGS_PARM2(x) (((PT_REGS_ARM64 *)(x))->regs[1])
+#define PT_REGS_PARM3(x) (((PT_REGS_ARM64 *)(x))->regs[2])
+#define PT_REGS_PARM4(x) (((PT_REGS_ARM64 *)(x))->regs[3])
+#define PT_REGS_PARM5(x) (((PT_REGS_ARM64 *)(x))->regs[4])
+#define PT_REGS_RET(x) (((PT_REGS_ARM64 *)(x))->regs[30])
+/* Works only with CONFIG_FRAME_POINTER */
+#define PT_REGS_FP(x) (((PT_REGS_ARM64 *)(x))->regs[29])
+#define PT_REGS_RC(x) (((PT_REGS_ARM64 *)(x))->regs[0])
+#define PT_REGS_SP(x) (((PT_REGS_ARM64 *)(x))->sp)
+#define PT_REGS_IP(x) (((PT_REGS_ARM64 *)(x))->pc)
 
 #elif defined(bpf_target_mips)
 
@@ -452,10 +487,10 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
 
 #endif
 
-#ifdef bpf_target_powerpc
+#if defined(bpf_target_powerpc)
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = (ctx)->link; })
 #define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
-#elif bpf_target_sparc
+#elif defined(bpf_target_sparc)
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)		({ (ip) = PT_REGS_RET(ctx); })
 #define BPF_KRETPROBE_READ_RET_IP		BPF_KPROBE_READ_RET_IP
 #else
diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
index a4686395522c..5ecc267d98b0 100644
--- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c
+++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
@@ -21,12 +21,6 @@ ssize_t get_base_addr() {
 	return -EINVAL;
 }
 
-#ifdef __x86_64__
-#define SYS_KPROBE_NAME "__x64_sys_nanosleep"
-#else
-#define SYS_KPROBE_NAME "sys_nanosleep"
-#endif
-
 void test_attach_probe(void)
 {
 	const char *kprobe_name = "kprobe/sys_nanosleep";
@@ -84,7 +78,7 @@ void test_attach_probe(void)
 
 	kprobe_link = bpf_program__attach_kprobe(kprobe_prog,
 						 false /* retprobe */,
-						 SYS_KPROBE_NAME);
+						 SYS_NANOSLEEP_KPROBE_NAME);
 	if (CHECK(IS_ERR(kprobe_link), "attach_kprobe",
 		  "err %ld\n", PTR_ERR(kprobe_link))) {
 		kprobe_link = NULL;
@@ -92,7 +86,7 @@ void test_attach_probe(void)
 	}
 	kretprobe_link = bpf_program__attach_kprobe(kretprobe_prog,
 						    true /* retprobe */,
-						    SYS_KPROBE_NAME);
+						    SYS_NANOSLEEP_KPROBE_NAME);
 	if (CHECK(IS_ERR(kretprobe_link), "attach_kretprobe",
 		  "err %ld\n", PTR_ERR(kretprobe_link))) {
 		kretprobe_link = NULL;
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
index 3f1ef95865ff..3003fddc0613 100644
--- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
+++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
@@ -5,12 +5,6 @@
 #include <sys/socket.h>
 #include <test_progs.h>
 
-#ifdef __x86_64__
-#define SYS_KPROBE_NAME "__x64_sys_nanosleep"
-#else
-#define SYS_KPROBE_NAME "sys_nanosleep"
-#endif
-
 static void on_sample(void *ctx, int cpu, void *data, __u32 size)
 {
 	int cpu_data = *(int *)data, duration = 0;
@@ -56,7 +50,7 @@ void test_perf_buffer(void)
 
 	/* attach kprobe */
 	link = bpf_program__attach_kprobe(prog, false /* retprobe */,
-					  SYS_KPROBE_NAME);
+					  SYS_NANOSLEEP_KPROBE_NAME);
 	if (CHECK(IS_ERR(link), "attach_kprobe", "err %ld\n", PTR_ERR(link)))
 		goto out_close;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c
index 67cea1686305..54218ee3c004 100644
--- a/tools/testing/selftests/bpf/prog_tests/send_signal.c
+++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c
@@ -173,6 +173,18 @@ static int test_send_signal_tracepoint(void)
 	return test_send_signal_common(&attr, BPF_PROG_TYPE_TRACEPOINT, "tracepoint");
 }
 
+static int test_send_signal_perf(void)
+{
+	struct perf_event_attr attr = {
+		.sample_period = 1,
+		.type = PERF_TYPE_SOFTWARE,
+		.config = PERF_COUNT_SW_CPU_CLOCK,
+	};
+
+	return test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT,
+				       "perf_sw_event");
+}
+
 static int test_send_signal_nmi(void)
 {
 	struct perf_event_attr attr = {
@@ -181,8 +193,26 @@ static int test_send_signal_nmi(void)
 		.type = PERF_TYPE_HARDWARE,
 		.config = PERF_COUNT_HW_CPU_CYCLES,
 	};
+	int pmu_fd;
+
+	/* Some setups (e.g. virtual machines) might run with hardware
+	 * perf events disabled. If this is the case, skip this test.
+	 */
+	pmu_fd = syscall(__NR_perf_event_open, &attr, 0 /* pid */,
+			 -1 /* cpu */, -1 /* group_fd */, 0 /* flags */);
+	if (pmu_fd == -1) {
+		if (errno == ENOENT) {
+			printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n",
+				__func__);
+			return 0;
+		}
+		/* Let the test fail with a more informative message */
+	} else {
+		close(pmu_fd);
+	}
 
-	return test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT, "perf_event");
+	return test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT,
+				       "perf_hw_event");
 }
 
 void test_send_signal(void)
@@ -190,6 +220,7 @@ void test_send_signal(void)
 	int ret = 0;
 
 	ret |= test_send_signal_tracepoint();
+	ret |= test_send_signal_perf();
 	ret |= test_send_signal_nmi();
 	if (!ret)
 		printf("test_send_signal:OK\n");
diff --git a/tools/testing/selftests/bpf/progs/loop1.c b/tools/testing/selftests/bpf/progs/loop1.c
index dea395af9ea9..7cdb7f878310 100644
--- a/tools/testing/selftests/bpf/progs/loop1.c
+++ b/tools/testing/selftests/bpf/progs/loop1.c
@@ -18,7 +18,7 @@ int nested_loops(volatile struct pt_regs* ctx)
 	for (j = 0; j < 300; j++)
 		for (i = 0; i < j; i++) {
 			if (j & 1)
-				m = ctx->rax;
+				m = PT_REGS_RC(ctx);
 			else
 				m = j;
 			sum += i * m;
diff --git a/tools/testing/selftests/bpf/progs/loop2.c b/tools/testing/selftests/bpf/progs/loop2.c
index 0637bd8e8bcf..9b2f808a2863 100644
--- a/tools/testing/selftests/bpf/progs/loop2.c
+++ b/tools/testing/selftests/bpf/progs/loop2.c
@@ -16,7 +16,7 @@ int while_true(volatile struct pt_regs* ctx)
 	int i = 0;
 
 	while (true) {
-		if (ctx->rax & 1)
+		if (PT_REGS_RC(ctx) & 1)
 			i += 3;
 		else
 			i += 7;
diff --git a/tools/testing/selftests/bpf/progs/loop3.c b/tools/testing/selftests/bpf/progs/loop3.c
index 30a0f6cba080..d727657d51e2 100644
--- a/tools/testing/selftests/bpf/progs/loop3.c
+++ b/tools/testing/selftests/bpf/progs/loop3.c
@@ -16,7 +16,7 @@ int while_true(volatile struct pt_regs* ctx)
 	__u64 i = 0, sum = 0;
 	do {
 		i++;
-		sum += ctx->rax;
+		sum += PT_REGS_RC(ctx);
 	} while (i < 0x100000000ULL);
 	return sum;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
index d06b47a09097..33254b771384 100644
--- a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
+++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
@@ -47,11 +47,12 @@ struct {
  * issue and avoid complicated C programming massaging.
  * This is an acceptable workaround since there is one entry here.
  */
+typedef __u64 raw_stack_trace_t[2 * MAX_STACK_RAWTP];
 struct {
 	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
 	__uint(max_entries, 1);
 	__type(key, __u32);
-	__u64 (*value)[2 * MAX_STACK_RAWTP];
+	__type(value, raw_stack_trace_t);
 } rawdata_map SEC(".maps");
 
 SEC("tracepoint/raw_syscalls/sys_enter")
diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
index bbfc8337b6f0..f5638e26865d 100644
--- a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
+++ b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
@@ -36,8 +36,7 @@ struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
 	__uint(max_entries, 128);
 	__type(key, __u32);
-	/* there seems to be a bug in kernel not handling typedef properly */
-	struct bpf_stack_build_id (*value)[PERF_MAX_STACK_DEPTH];
+	__type(value, stack_trace_t);
 } stack_amap SEC(".maps");
 
 /* taken from /sys/kernel/debug/tracing/events/random/urandom_read/format */
diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
index 803c15dc109d..fa0be3e10a10 100644
--- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
+++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
@@ -35,7 +35,7 @@ struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
 	__uint(max_entries, 16384);
 	__type(key, __u32);
-	__u64 (*value)[PERF_MAX_STACK_DEPTH];
+	__type(value, stack_trace_t);
 } stack_amap SEC(".maps");
 
 /* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
index dad8a7e33eaa..e88d7b9d65ab 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
@@ -14,6 +14,7 @@
 #include <linux/tcp.h>
 #include <linux/udp.h>
 #include "bpf_helpers.h"
+#include "bpf_endian.h"
 
 static __u32 rol32(__u32 word, unsigned int shift)
 {
@@ -305,7 +306,7 @@ bool encap_v6(struct xdp_md *xdp, struct ctl_value *cval,
 	ip6h->nexthdr = IPPROTO_IPV6;
 	ip_suffix = pckt->flow.srcv6[3] ^ pckt->flow.port16[0];
 	ip6h->payload_len =
-	    __builtin_bswap16(pkt_bytes + sizeof(struct ipv6hdr));
+	    bpf_htons(pkt_bytes + sizeof(struct ipv6hdr));
 	ip6h->hop_limit = 4;
 
 	ip6h->saddr.in6_u.u6_addr32[0] = 1;
@@ -322,7 +323,7 @@ bool encap_v4(struct xdp_md *xdp, struct ctl_value *cval,
 	      struct real_definition *dst, __u32 pkt_bytes)
 {
 
-	__u32 ip_suffix = __builtin_bswap16(pckt->flow.port16[0]);
+	__u32 ip_suffix = bpf_ntohs(pckt->flow.port16[0]);
 	struct eth_hdr *new_eth;
 	struct eth_hdr *old_eth;
 	__u16 *next_iph_u16;
@@ -352,7 +353,7 @@ bool encap_v4(struct xdp_md *xdp, struct ctl_value *cval,
 	iph->protocol = IPPROTO_IPIP;
 	iph->check = 0;
 	iph->tos = 1;
-	iph->tot_len = __builtin_bswap16(pkt_bytes + sizeof(struct iphdr));
+	iph->tot_len = bpf_htons(pkt_bytes + sizeof(struct iphdr));
 	/* don't update iph->daddr, since it will overwrite old eth_proto
 	 * and multiple iterations of bpf_prog_run() will fail
 	 */
@@ -639,7 +640,7 @@ static int process_l3_headers_v6(struct packet_description *pckt,
 	iph_len = sizeof(struct ipv6hdr);
 	*protocol = ip6h->nexthdr;
 	pckt->flow.proto = *protocol;
-	*pkt_bytes = __builtin_bswap16(ip6h-&g