247 files changed, 2317 insertions, 1137 deletions

diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 964df31da9751..66736ff04011e 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -484,6 +484,12 @@ enum {
  */
 #define KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2	(1ULL << 0)
 
+/*
+ * Shutdown caused by a PSCI v1.3 SYSTEM_OFF2 call.
+ * Valid only when the system event has a type of KVM_SYSTEM_EVENT_SHUTDOWN.
+ */
+#define KVM_SYSTEM_EVENT_SHUTDOWN_FLAG_PSCI_OFF2	(1ULL << 0)
+
 /* run->fail_entry.hardware_entry_failure_reason codes. */
 #define KVM_EXIT_FAIL_ENTRY_CPU_UNSUPPORTED	(1ULL << 0)
 
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 23698d0f4bb47..17b6590748c00 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -215,7 +215,7 @@
 #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE	( 7*32+23) /* Disable Speculative Store Bypass. */
 #define X86_FEATURE_LS_CFG_SSBD		( 7*32+24)  /* AMD SSBD implementation via LS_CFG MSR */
 #define X86_FEATURE_IBRS		( 7*32+25) /* "ibrs" Indirect Branch Restricted Speculation */
-#define X86_FEATURE_IBPB		( 7*32+26) /* "ibpb" Indirect Branch Prediction Barrier */
+#define X86_FEATURE_IBPB		( 7*32+26) /* "ibpb" Indirect Branch Prediction Barrier without a guaranteed RSB flush */
 #define X86_FEATURE_STIBP		( 7*32+27) /* "stibp" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ZEN			( 7*32+28) /* Generic flag for all Zen and newer */
 #define X86_FEATURE_L1TF_PTEINV		( 7*32+29) /* L1TF workaround PTE inversion */
@@ -317,6 +317,9 @@
 #define X86_FEATURE_ZEN1		(11*32+31) /* CPU based on Zen1 microarchitecture */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
+#define X86_FEATURE_SHA512		(12*32+ 0) /* SHA512 instructions */
+#define X86_FEATURE_SM3			(12*32+ 1) /* SM3 instructions */
+#define X86_FEATURE_SM4			(12*32+ 2) /* SM4 instructions */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* "avx_vnni" AVX VNNI instructions */
 #define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* "avx512_bf16" AVX512 BFLOAT16 instructions */
 #define X86_FEATURE_CMPCCXADD           (12*32+ 7) /* CMPccXADD instructions */
@@ -348,6 +351,7 @@
 #define X86_FEATURE_CPPC		(13*32+27) /* "cppc" Collaborative Processor Performance Control */
 #define X86_FEATURE_AMD_PSFD            (13*32+28) /* Predictive Store Forwarding Disable */
 #define X86_FEATURE_BTC_NO		(13*32+29) /* Not vulnerable to Branch Type Confusion */
+#define X86_FEATURE_AMD_IBPB_RET	(13*32+30) /* IBPB clears return address predictor */
 #define X86_FEATURE_BRS			(13*32+31) /* "brs" Branch Sampling available */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
@@ -472,7 +476,9 @@
 #define X86_FEATURE_BHI_CTRL		(21*32+ 2) /* BHI_DIS_S HW control available */
 #define X86_FEATURE_CLEAR_BHB_HW	(21*32+ 3) /* BHI_DIS_S HW control enabled */
 #define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* Clear branch history at vmexit using SW loop */
-#define X86_FEATURE_AMD_FAST_CPPC		(21*32 + 5) /* AMD Fast CPPC */
+#define X86_FEATURE_AMD_FAST_CPPC	(21*32 + 5) /* Fast CPPC */
+#define X86_FEATURE_AMD_HETEROGENEOUS_CORES (21*32 + 6) /* Heterogeneous Core Topology */
+#define X86_FEATURE_AMD_WORKLOAD_CLASS	(21*32 + 7) /* Workload Classification */
 
 /*
  * BUG word(s)
@@ -523,4 +529,5 @@
 #define X86_BUG_DIV0			X86_BUG(1*32 + 1) /* "div0" AMD DIV0 speculation bug */
 #define X86_BUG_RFDS			X86_BUG(1*32 + 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */
 #define X86_BUG_BHI			X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */
+#define X86_BUG_IBPB_NO_RET	   	X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index a8debbf2f7028..88585c1de416f 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -440,6 +440,7 @@ struct kvm_sync_regs {
 #define KVM_X86_QUIRK_FIX_HYPERCALL_INSN	(1 << 5)
 #define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS	(1 << 6)
 #define KVM_X86_QUIRK_SLOT_ZAP_ALL		(1 << 7)
+#define KVM_X86_QUIRK_STUFF_FEATURE_MSRS	(1 << 8)
 
 #define KVM_STATE_NESTED_FORMAT_VMX	0
 #define KVM_STATE_NESTED_FORMAT_SVM	1
diff --git a/tools/hv/.gitignore b/tools/hv/.gitignore
new file mode 100644
index 0000000000000..0c5bc15d602f0
--- /dev/null
+++ b/tools/hv/.gitignore
@@ -0,0 +1,3 @@
+hv_fcopy_uio_daemon
+hv_kvp_daemon
+hv_vss_daemon
diff --git a/tools/hv/hv_fcopy_uio_daemon.c b/tools/hv/hv_fcopy_uio_daemon.c
index 7a00f3066a980..0198321d14a29 100644
--- a/tools/hv/hv_fcopy_uio_daemon.c
+++ b/tools/hv/hv_fcopy_uio_daemon.c
@@ -35,8 +35,6 @@
 #define WIN8_SRV_MINOR		1
 #define WIN8_SRV_VERSION	(WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR)
 
-#define MAX_FOLDER_NAME		15
-#define MAX_PATH_LEN		15
 #define FCOPY_UIO		"/sys/bus/vmbus/devices/eb765408-105f-49b6-b4aa-c123b64d17d4/uio"
 
 #define FCOPY_VER_COUNT		1
@@ -51,7 +49,7 @@ static const int fw_versions[] = {
 
 #define HV_RING_SIZE		0x4000 /* 16KB ring buffer size */
 
-unsigned char desc[HV_RING_SIZE];
+static unsigned char desc[HV_RING_SIZE];
 
 static int target_fd;
 static char target_fname[PATH_MAX];
@@ -409,8 +407,8 @@ int main(int argc, char *argv[])
 	struct vmbus_br txbr, rxbr;
 	void *ring;
 	uint32_t len = HV_RING_SIZE;
-	char uio_name[MAX_FOLDER_NAME] = {0};
-	char uio_dev_path[MAX_PATH_LEN] = {0};
+	char uio_name[NAME_MAX] = {0};
+	char uio_dev_path[PATH_MAX] = {0};
 
 	static struct option long_options[] = {
 		{"help",	no_argument,	   0,  'h' },
@@ -468,8 +466,10 @@ int main(int argc, char *argv[])
 		 */
 		ret = pread(fcopy_fd, &tmp, sizeof(int), 0);
 		if (ret < 0) {
+			if (errno == EINTR || errno == EAGAIN)
+				continue;
 			syslog(LOG_ERR, "pread failed: %s", strerror(errno));
-			continue;
+			goto close;
 		}
 
 		len = HV_RING_SIZE;
diff --git a/tools/hv/hv_get_dns_info.sh b/tools/hv/hv_get_dns_info.sh
index 058c17b46ffcd..268521234d4b0 100755
--- a/tools/hv/hv_get_dns_info.sh
+++ b/tools/hv/hv_get_dns_info.sh
@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/bin/sh
 
 # This example script parses /etc/resolv.conf to retrive DNS information.
 # In the interest of keeping the KVP daemon code free of distro specific
@@ -10,4 +10,4 @@
 # this script can be based on the Network Manager APIs for retrieving DNS
 # entries.
 
-cat /etc/resolv.conf 2>/dev/null | awk '/^nameserver/ { print $2 }'
+exec awk '/^nameserver/ { print $2 }' /etc/resolv.conf 2>/dev/null
diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c
index ae57bf69ad4af..04ba035d67e9d 100644
--- a/tools/hv/hv_kvp_daemon.c
+++ b/tools/hv/hv_kvp_daemon.c
@@ -725,7 +725,7 @@ static void kvp_get_ipconfig_info(char *if_name,
 	 * .
 	 */
 
-	sprintf(cmd, KVP_SCRIPTS_PATH "%s",  "hv_get_dns_info");
+	sprintf(cmd, "exec %s %s", KVP_SCRIPTS_PATH "hv_get_dns_info", if_name);
 
 	/*
 	 * Execute the command to gather DNS info.
@@ -742,7 +742,7 @@ static void kvp_get_ipconfig_info(char *if_name,
 	 * Enabled: DHCP enabled.
 	 */
 
-	sprintf(cmd, KVP_SCRIPTS_PATH "%s %s", "hv_get_dhcp_info", if_name);
+	sprintf(cmd, "exec %s %s", KVP_SCRIPTS_PATH "hv_get_dhcp_info", if_name);
 
 	file = popen(cmd, "r");
 	if (file == NULL)
@@ -1606,8 +1606,9 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val)
 	 * invoke the external script to do its magic.
 	 */
 
-	str_len = snprintf(cmd, sizeof(cmd), KVP_SCRIPTS_PATH "%s %s %s",
-			   "hv_set_ifconfig", if_filename, nm_filename);
+	str_len = snprintf(cmd, sizeof(cmd), "exec %s %s %s",
+			   KVP_SCRIPTS_PATH "hv_set_ifconfig",
+			   if_filename, nm_filename);
 	/*
 	 * This is a little overcautious, but it's necessary to suppress some
 	 * false warnings from gcc 8.0.1.
diff --git a/tools/hv/hv_set_ifconfig.sh b/tools/hv/hv_set_ifconfig.sh
index 440a91b35823b..2f8baed2b8f79 100755
--- a/tools/hv/hv_set_ifconfig.sh
+++ b/tools/hv/hv_set_ifconfig.sh
@@ -81,7 +81,7 @@ echo "ONBOOT=yes" >> $1
 
 cp $1 /etc/sysconfig/network-scripts/
 
-chmod 600 $2
+umask 0177
 interface=$(echo $2 | awk -F - '{ print $2 }')
 filename="${2##*/}"
 
diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h
index 406f7718f9ad0..51d2556af54ac 100644
--- a/tools/include/uapi/asm-generic/mman.h
+++ b/tools/include/uapi/asm-generic/mman.h
@@ -19,4 +19,8 @@
 #define MCL_FUTURE	2		/* lock all future mappings */
 #define MCL_ONFAULT	4		/* lock all pages that are faulted in */
 
+#define SHADOW_STACK_SET_TOKEN (1ULL << 0)     /* Set up a restore token in the shadow stack */
+#define SHADOW_STACK_SET_MARKER (1ULL << 1)     /* Set up a top of stack marker in the shadow stack */
+
+
 #endif /* __ASM_GENERIC_MMAN_H */
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 5bf6148cac2b9..88dc393c2bca3 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -841,8 +841,17 @@ __SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules)
 #define __NR_mseal 462
 __SYSCALL(__NR_mseal, sys_mseal)
 
+#define __NR_setxattrat 463
+__SYSCALL(__NR_setxattrat, sys_setxattrat)
+#define __NR_getxattrat 464
+__SYSCALL(__NR_getxattrat, sys_getxattrat)
+#define __NR_listxattrat 465
+__SYSCALL(__NR_listxattrat, sys_listxattrat)
+#define __NR_removexattrat 466
+__SYSCALL(__NR_removexattrat, sys_removexattrat)
+
 #undef __NR_syscalls
-#define __NR_syscalls 463
+#define __NR_syscalls 467
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 16122819edfef..7fba37b94401a 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -1024,6 +1024,13 @@ struct drm_crtc_queue_sequence {
 	__u64 user_data;	/* user data passed to event */
 };
 
+#define DRM_CLIENT_NAME_MAX_LEN		64
+struct drm_set_client_name {
+	__u64 name_len;
+	__u64 name;
+};
+
+
 #if defined(__cplusplus)
 }
 #endif
@@ -1288,6 +1295,16 @@ extern "C" {
  */
 #define DRM_IOCTL_MODE_CLOSEFB		DRM_IOWR(0xD0, struct drm_mode_closefb)
 
+/**
+ * DRM_IOCTL_SET_CLIENT_NAME - Attach a name to a drm_file
+ *
+ * Having a name allows for easier tracking and debugging.
+ * The length of the name (without null ending char) must be
+ * <= DRM_CLIENT_NAME_MAX_LEN.
+ * The call will fail if the name contains whitespaces or non-printable chars.
+ */
+#define DRM_IOCTL_SET_CLIENT_NAME	DRM_IOWR(0xD1, struct drm_set_client_name)
+
 /*
  * Device specific ioctls should only be in their respective headers
  * The device specific ioctl range is from 0x40 to 0x9f.
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 637efc0551453..502ea63b5d2e7 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -1158,7 +1158,15 @@ enum kvm_device_type {
 #define KVM_DEV_TYPE_ARM_PV_TIME	KVM_DEV_TYPE_ARM_PV_TIME
 	KVM_DEV_TYPE_RISCV_AIA,
 #define KVM_DEV_TYPE_RISCV_AIA		KVM_DEV_TYPE_RISCV_AIA
+	KVM_DEV_TYPE_LOONGARCH_IPI,
+#define KVM_DEV_TYPE_LOONGARCH_IPI	KVM_DEV_TYPE_LOONGARCH_IPI
+	KVM_DEV_TYPE_LOONGARCH_EIOINTC,
+#define KVM_DEV_TYPE_LOONGARCH_EIOINTC	KVM_DEV_TYPE_LOONGARCH_EIOINTC
+	KVM_DEV_TYPE_LOONGARCH_PCHPIC,
+#define KVM_DEV_TYPE_LOONGARCH_PCHPIC	KVM_DEV_TYPE_LOONGARCH_PCHPIC
+
 	KVM_DEV_TYPE_MAX,
+
 };
 
 struct kvm_vfio_spapr_tce {
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 4842c36fdf801..0524d541d4e3d 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -511,7 +511,16 @@ struct perf_event_attr {
 	__u16	sample_max_stack;
 	__u16	__reserved_2;
 	__u32	aux_sample_size;
-	__u32	__reserved_3;
+
+	union {
+		__u32	aux_action;
+		struct {
+			__u32	aux_start_paused :  1, /* start AUX area tracing paused */
+				aux_pause        :  1, /* on overflow, pause AUX area tracing */
+				aux_resume       :  1, /* on overflow, resume AUX area tracing */
+				__reserved_3     : 29;
+		};
+	};
 
 	/*
 	 * User provided data if sigtrap=1, passed back to user via
diff --git a/tools/include/uapi/linux/stddef.h b/tools/include/uapi/linux/stddef.h
index bb6ea517efb51..c53cde425406b 100644
--- a/tools/include/uapi/linux/stddef.h
+++ b/tools/include/uapi/linux/stddef.h
@@ -8,6 +8,13 @@
 #define __always_inline __inline__
 #endif
 
+/* Not all C++ standards support type declarations inside an anonymous union */
+#ifndef __cplusplus
+#define __struct_group_tag(TAG)		TAG
+#else
+#define __struct_group_tag(TAG)
+#endif
+
 /**
  * __struct_group() - Create a mirrored named and anonyomous struct
  *
@@ -20,14 +27,14 @@
  * and size: one anonymous and one named. The former's members can be used
  * normally without sub-struct naming, and the latter can be used to
  * reason about the start, end, and size of the group of struct members.
- * The named struct can also be explicitly tagged for layer reuse, as well
- * as both having struct attributes appended.
+ * The named struct can also be explicitly tagged for layer reuse (C only),
+ * as well as both having struct attributes appended.
  */
 #define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \
 	union { \
 		struct { MEMBERS } ATTRS; \
-		struct TAG { MEMBERS } ATTRS NAME; \
-	}
+		struct __struct_group_tag(TAG) { MEMBERS } ATTRS NAME; \
+	} ATTRS
 
 /**
  * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index c6d67fc9e57ef..83c43dc13313c 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -47,6 +47,20 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
 		 */
 		perf_cpu_map__put(evsel->cpus);
 		evsel->cpus = perf_cpu_map__intersect(evlist->user_requested_cpus, evsel->own_cpus);
+
+		/*
+		 * Empty cpu lists would eventually get opened as "any" so remove
+		 * genuinely empty ones before they're opened in the wrong place.
+		 */
+		if (perf_cpu_map__is_empty(evsel->cpus)) {
+			struct perf_evsel *next = perf_evlist__next(evlist, evsel);
+
+			perf_evlist__remove(evlist, evsel);
+			/* Keep idx contiguous */
+			if (next)
+				list_for_each_entry_from(next, &evlist->entries, node)
+					next->idx--;
+		}
 	} else if (!evsel->own_cpus || evlist->has_user_cpus ||
 		(!evsel->requires_cpu && perf_cpu_map__has_any_cpu(evlist->user_requested_cpus))) {
 		/*
@@ -80,11 +94,11 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
 
 static void perf_evlist__propagate_maps(struct perf_evlist *evlist)
 {
-	struct perf_evsel *evsel;
+	struct perf_evsel *evsel, *n;
 
 	evlist->needs_map_propagation = true;
 
-	perf_evlist__for_each_evsel(evlist, evsel)
+	list_for_each_entry_safe(evsel, n, &evlist->entries, node)
 		__perf_evlist__propagate_maps(evlist, evsel);
 }
 
diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py
index 01ec01a90e763..eea29359a899a 100644
--- a/tools/net/ynl/lib/ynl.py
+++ b/tools/net/ynl/lib/ynl.py
@@ -556,10 +556,10 @@ class YnlFamily(SpecFamily):
         if attr["type"] == 'nest':
             nl_type |= Netlink.NLA_F_NESTED
             attr_payload = b''
-            sub_attrs = SpaceAttrs(self.attr_sets[space], value, search_attrs)
+            sub_space = attr['nested-attributes']
+            sub_attrs = SpaceAttrs(self.attr_sets[sub_space], value, search_attrs)
             for subname, subvalue in value.items():
-                attr_payload += self._add_attr(attr['nested-attributes'],
-                                               subname, subvalue, sub_attrs)
+                attr_payload += self._add_attr(sub_space, subname, subvalue, sub_attrs)
         elif attr["type"] == 'flag':
             if not value:
                 # If value is absent or false then skip attribute creation.
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 4ce176ad411fb..76060da755b5c 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -3820,9 +3820,12 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
 			break;
 
 		case INSN_CONTEXT_SWITCH:
-			if (func && (!next_insn || !next_insn->hint)) {
-				WARN_INSN(insn, "unsupported instruction in callable function");
-				return 1;
+			if (func) {
+				if (!next_insn || !next_insn->hint) {
+					WARN_INSN(insn, "unsupported instruction in callable function");
+					return 1;
+				}
+				break;
 			}
 			return 0;
 
diff --git a/tools/objtool/noreturns.h b/tools/objtool/noreturns.h
index f37614cc2c1b2..b2174894f9f71 100644
--- a/tools/objtool/noreturns.h
+++ b/tools/objtool/noreturns.h
@@ -19,6 +19,7 @@ NORETURN(__x64_sys_exit_group)
 NORETURN(arch_cpu_idle_dead)
 NORETURN(bch2_trans_in_restart_error)
 NORETURN(bch2_trans_restart_error)
+NORETURN(bch2_trans_unlocked_error)
 NORETURN(cpu_bringup_and_idle)
 NORETURN(cpu_startup_entry)
 NORETURN(do_exit)
diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
index 1464c6be6eb3c..c844cd5cda620 100644
--- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
+++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
@@ -377,3 +377,7 @@
 460	n64	lsm_set_self_attr		sys_lsm_set_self_attr
 461	n64	lsm_list_modules		sys_lsm_list_modules
 462	n64	mseal				sys_mseal
+463	n64	setxattrat			sys_setxattrat
+464	n64	getxattrat			sys_getxattrat
+465	n64	listxattrat			sys_listxattrat
+466	n64	removexattrat			sys_removexattrat
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index ebae8415dfbba..d8b4ab78bef07 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -553,3 +553,7 @@
 460	common	lsm_set_self_attr		sys_lsm_set_self_attr
 461	common	lsm_list_modules		sys_lsm_list_modules
 462	common	mseal				sys_mseal
+463	common	setxattrat			sys_setxattrat
+464	common	getxattrat			sys_getxattrat
+465	common	listxattrat			sys_listxattrat
+466	common	removexattrat			sys_removexattrat
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index 01071182763e9..e9115b4d8b635 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -465,3 +465,7 @@
 460  common	lsm_set_self_attr	sys_lsm_set_self_attr		sys_lsm_set_self_attr
 461  common	lsm_list_modules	sys_lsm_list_modules		sys_lsm_list_modules
 462  common	mseal			sys_mseal			sys_mseal
+463  common	setxattrat		sys_setxattrat			sys_setxattrat
+464  common	getxattrat		sys_getxattrat			sys_getxattrat
+465  common	listxattrat		sys_listxattrat			sys_listxattrat
+466  common	removexattrat		sys_removexattrat		sys_removexattrat
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
index 534c74b14fab5..4d0fb2fba7e20 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_32.tbl
@@ -468,3 +468,7 @@
 460	i386	lsm_set_self_attr	sys_lsm_set_self_attr
 461	i386	lsm_list_modules	sys_lsm_list_modules
 462	i386	mseal 			sys_mseal
+463	i386	setxattrat		sys_setxattrat
+464	i386	getxattrat		sys_getxattrat
+465	i386	listxattrat		sys_listxattrat
+466	i386	removexattrat		sys_removexattrat
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 7093ee21c0d1c..5eb708bff1c79 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -386,6 +386,10 @@
 460	common	lsm_set_self_attr	sys_lsm_set_self_attr
 461	common	lsm_list_modules	sys_lsm_list_modules
 462 	common  mseal			sys_mseal
+463	common	setxattrat		sys_setxattrat
+464	common	getxattrat		sys_getxattrat
+465	common	listxattrat		sys_listxattrat
+466	common	removexattrat		sys_removexattrat
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index 272d3c70810e7..a56cf8b0a7d40 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -1151,8 +1151,9 @@ static int cmp_profile_data(const void *a, const void *b)
 
 	if (v1 > v2)
 		return -1;
-	else
+	if (v1 < v2)
 		return 1;
+	return 0;
 }
 
 static void print_profile_result(struct perf_ftrace *ftrace)
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 8dcf74d3c0a39..4751dd3c6f672 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -508,7 +508,7 @@ static int __cmd_test(struct test_suite **suites, int argc, const char *argv[],
 		for (size_t x = 0; x < num_tests; x++) {
 			struct child_test *child_test = child_tests[x];
 
-			if (!child_test)
+			if (!child_test || child_test->process.pid <= 0)
 				continue;
 
 			pr_debug3("Killing %d pid %d\n",
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index 41ff1affdfcdf..726cf8d4da28d 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -75,14 +75,12 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u
 	double val, num_cpus_online, num_cpus, num_cores, num_dies, num_packages;
 	int ret;
 	struct expr_parse_ctx *ctx;
-	bool is_intel = false;
 	char strcmp_cpuid_buf[256];
 	struct perf_cpu cpu = {-1};
 	char *cpuid = get_cpuid_allow_env_override(cpu);
 	char *escaped_cpuid1, *escaped_cpuid2;
 
 	TEST_ASSERT_VAL("get_cpuid", cpuid);
-	is_intel = strstr(cpuid, "Intel") != NULL;
 
 	TEST_ASSERT_EQUAL("ids_union", test_ids_union(), 0);
 
@@ -245,12 +243,19 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u
 	if (num_dies) // Some platforms do not have CPU die support, for example s390
 		TEST_ASSERT_VAL("#num_dies >= #num_packages", num_dies >= num_packages);
 
-	TEST_ASSERT_VAL("#system_tsc_freq", expr__parse(&val, ctx, "#system_tsc_freq") == 0);
-	if (is_intel)
-		TEST_ASSERT_VAL("#system_tsc_freq > 0", val > 0);
-	else
-		TEST_ASSERT_VAL("#system_tsc_freq == 0", fpclassify(val) == FP_ZERO);
 
+	if (expr__parse(&val, ctx, "#system_tsc_freq") == 0) {
+		bool is_intel = strstr(cpuid, "Intel") != NULL;
+
+		if (is_intel)
+			TEST_ASSERT_VAL("#system_tsc_freq > 0", val > 0);
+		else
+			TEST_ASSERT_VAL("#system_tsc_freq == 0", fpclassify(val) == FP_ZERO);
+	} else {
+#if defined(__i386__) || defined(__x86_64__)
+		TEST_ASSERT_VAL("#system_tsc_freq unsupported", 0);
+#endif
+	}
 	/*
 	 * Source count returns the number of events aggregating in a leader
 	 * event including the leader. Check parsing yields an id.
diff --git a/tools/perf/tests/hwmon_pmu.c b/tools/perf/tests/hwmon_pmu.c
index f8bcee9660d53..d2b066a2b557a 100644
--- a/tools/perf/tests/hwmon_pmu.c
+++ b/tools/perf/tests/hwmon_pmu.c
@@ -65,7 +65,7 @@ static struct perf_pmu *test_pmu_get(char *dir, size_t sz)
 		{ "temp2_label", "test hwmon event2\n", },
 		{ "temp2_input", "50000\n", },
 	};
-	int dirfd, file;
+	int hwmon_dirfd = -1, test_dirfd = -1, file;
 	struct perf_pmu *hwm = NULL;
 	ssize_t len;
 
@@ -76,19 +76,24 @@ static struct perf_pmu *test_pmu_get(char *dir, size_t sz)
 		dir[0] = '\0';
 		return NULL;
 	}
-	dirfd = open(dir, O_DIRECTORY);
-	if (dirfd < 0) {
+	test_dirfd = open(dir, O_PATH|O_DIRECTORY);
+	if (test_dirfd < 0) {
 		pr_err("Failed to open test directory \"%s\"\n", dir);
 		goto err_out;
 	}
 
 	/* Create the test hwmon directory and give it a name. */
-	if (mkdirat(dirfd, "hwmon1234", 0755) < 0) {
+	if (mkdirat(test_dirfd, "hwmon1234", 0755) < 0) {
 		pr_err("Failed to mkdir hwmon directory\n");
 		goto err_out;
 	}
-	file = openat(dirfd, "hwmon1234/name", O_WRONLY | O_CREAT, 0600);
-	if (!file) {
+	hwmon_dirfd = openat(test_dirfd, "hwmon1234", O_DIRECTORY);
+	if (hwmon_dirfd < 0) {
+		pr_err("Failed to open test hwmon directory \"%s/hwmon1234\"\n", dir);
+		goto err_out;
+	}
+	file = openat(hwmon_dirfd, "name", O_WRONLY | O_CREAT, 0600);
+	if (file < 0) {
 		pr_err("Failed to open for writing file \"name\"\n");
 		goto err_out;
 	}
@@ -104,8 +109,8 @@ static struct perf_pmu *test_pmu_get(char *dir, size_t sz)
 	for (size_t i = 0; i < ARRAY_SIZE(test_items); i++) {
 		const struct test_item *item = &test_items[i];
 
-		file = openat(dirfd, item->name, O_WRONLY | O_CREAT, 0600);
-		if (!file) {
+		file = openat(hwmon_dirfd, item->name, O_WRONLY | O_CREAT, 0600);
+		if (file < 0) {
 			pr_err("Failed to open for writing file \"%s\"\n", item->name);
 			goto err_out;
 		}
@@ -119,16 +124,18 @@ static struct perf_pmu *test_pmu_get(char *dir, size_t sz)
 	}
 
 	/* Make the PMU reading the files created above. */
-	hwm = perf_pmus__add_test_hwmon_pmu(dirfd, "hwmon1234", test_hwmon_name);
+	hwm = perf_pmus__add_test_hwmon_pmu(hwmon_dirfd, "hwmon1234", test_hwmon_name);
 	if (!hwm)
 		pr_err("Test hwmon creation failed\n");
 
 err_out:
 	if (!hwm) {
 		test_pmu_put(dir, hwm);
-		if (dirfd >= 0)
-			close(dirfd);
+		if (hwmon_dirfd >= 0)
+			close(hwmon_dirfd);
 	}
+	if (test_dirfd >= 0)
+		close(test_dirfd);
 	return hwm;
 }
 
diff --git a/tools/perf/trace/beauty/fs_at_flags.sh b/tools/perf/trace/beauty/fs_at_flags.sh
index e3f13f96a27c2..fac4d0c049fcc 100755
--- a/tools/perf/trace/beauty/fs_at_flags.sh
+++ b/tools/perf/trace/beauty/fs_at_flags.sh
@@ -13,13 +13,14 @@ printf "static const char *fs_at_flags[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+AT_([^_]+[[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*'
 # AT_EACCESS is only meaningful to faccessat, so we will special case it there...
 # AT_STATX_SYNC_TYPE is not a bit, its a mask of AT_STATX_SYNC_AS_STAT, AT_STATX_FORCE_SYNC and AT_STATX_DONT_SYNC
-# AT_HANDLE_FID and AT_HANDLE_MNT_ID_UNIQUE are reusing values and are valid only for name_to_handle_at()
+# AT_HANDLE_FID, AT_HANDLE_MNT_ID_UNIQUE and AT_HANDLE_CONNECTABLE are reusing values and are valid only for name_to_handle_at()
 # AT_RENAME_NOREPLACE reuses 0x1 and is valid only for renameat2()
 grep -E $regex ${linux_fcntl} | \
 	grep -v AT_EACCESS | \
 	grep -v AT_STATX_SYNC_TYPE | \
 	grep -v AT_HANDLE_FID | \
 	grep -v AT_HANDLE_MNT_ID_UNIQUE | \
+	grep -v AT_HANDLE_CONNECTABLE | \
 	grep -v AT_RENAME_NOREPLACE | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n"
diff --git a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
index 87e2dec79fea4..6e6907e63bfc2 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
@@ -153,9 +153,6 @@
 					   object identity and may not be
 					   usable with open_by_handle_at(2). */
 #define AT_HANDLE_MNT_ID_UNIQUE	0x001	/* Return the u64 unique mount ID. */
-
-#if defined(__KERNEL__)
-#define AT_GETATTR_NOSEC	0x80000000
-#endif
+#define AT_HANDLE_CONNECTABLE	0x002	/* Request a connectable file handle */
 
 #endif /* _UAPI_LINUX_FCNTL_H */
diff --git a/tools/perf/trace/beauty/include/uapi/linux/mount.h b/tools/perf/trace/beauty/include/uapi/linux/mount.h
index 225bc366ffcbf..c07008816acae 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/mount.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/mount.h
@@ -154,7 +154,7 @@ struct mount_attr {
  */
 struct statmount {
 	__u32 size;		/* Total size, including strings */
-	__u32 mnt_opts;		/* [str] Mount options of the mount */
+	__u32 mnt_opts;		/* [str] Options (comma separated, escaped) */
 	__u64 mask;		/* What results were written */
 	__u32 sb_dev_major;	/* Device ID */
 	__u32 sb_dev_minor;
@@ -173,7 +173,13 @@ struct statmount {
 	__u32 mnt_root;		/* [str] Root of mount relative to root of fs */
 	__u32 mnt_point;	/* [str] Mountpoint relative to current root */
 	__u64 mnt_ns_id;	/* ID of the mount namespace */
-	__u64 __spare2[49];
+	__u32 fs_subtype;	/* [str] Subtype of fs_type (if any) */
+	__u32 sb_source;	/* [str] Source string of the mount */
+	__u32 opt_num;		/* Number of fs options */
+	__u32 opt_array;	/* [str] Array of nul terminated fs options */
+	__u32 opt_sec_num;	/* Number of security options */
+	__u32 opt_sec_array;	/* [str] Array of nul terminated security options */
+	__u64 __spare2[46];
 	char str[];		/* Variable size part containing strings */
 };
 
@@ -207,6 +213,10 @@ struct mnt_id_req {
 #define STATMOUNT_FS_TYPE		0x00000020U	/* Want/got fs_type */
 #define STATMOUNT_MNT_NS_ID		0x00000040U	/* Want/got mnt_ns_id */
 #define STATMOUNT_MNT_OPTS		0x00000080U	/* Want/got mnt_opts */
+#define STATMOUNT_FS_SUBTYPE		0x00000100U	/* Want/got fs_subtype */
+#define STATMOUNT_SB_SOURCE		0x00000200U	/* Want/got sb_source */
+#define STATMOUNT_OPT_ARRAY		0x00000400U	/* Want/got opt_... */
+#define STATMOUNT_OPT_SEC_ARRAY		0x00000800U	/* Want/got opt_sec... */
 
 /*
  * Special @mnt_id values that can be passed to listmount
diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
index 35791791a879b..5c6080680cb27 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/prctl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
@@ -230,7 +230,7 @@ struct prctl_mm_map {
 # define PR_PAC_APDBKEY			(1UL << 3)
 # define PR_PAC_APGAKEY			(1UL << 4)
 
-/* Tagged user address controls for arm64 */
+/* Tagged user address controls for arm64 and RISC-V */
 #define PR_SET_TAGGED_ADDR_CTRL		55
 #define PR_GET_TAGGED_ADDR_CTRL		56
 # define PR_TAGGED_ADDR_ENABLE		(1UL << 0)
@@ -244,6 +244,9 @@ struct prctl_mm_map {
 # define PR_MTE_TAG_MASK		(0xffffUL << PR_MTE_TAG_SHIFT)
 /* Unused; kept only for source compatibility */
 # define PR_MTE_TCF_SHIFT		1
+/* RISC-V pointer masking tag length */
+# define PR_PMLEN_SHIFT			24
+# define PR_PMLEN_MASK			(0x7fUL << PR_PMLEN_SHIFT)
 
 /* Control reclaim behavior when allocating memory */
 #define PR_SET_IO_FLUSHER		57
@@ -328,4 +331,26 @@ struct prctl_mm_map {
 # define PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC	0x10 /* Clear the aspect on exec */
 # define PR_PPC_DEXCR_CTRL_MASK		0x1f
 
+/*
+ * Get the current shadow stack configuration for the current thread,
+ * this will be the value configured via PR_SET_SHADOW_STACK_STATUS.
+ */
+#define PR_GET_SHADOW_STACK_STATUS      74
+
+/*
+ * Set the current shadow stack configuration.  Enabling the shadow
+ * stack will cause a shadow stack to be allocated for the thread.
+ */
+#define PR_SET_SHADOW_STACK_STATUS      75
+# define PR_SHADOW_STACK_ENABLE         (1UL << 0)
+# define PR_SHADOW_STACK_WRITE		(1UL << 1)
+# define PR_SHADOW_STACK_PUSH		(1UL << 2)
+
+/*
+ * Prevent further changes to the specified shadow stack
+ * configuration.  All bits may be locked via this call, including
+ * undefined bits.
+ */
+#define PR_LOCK_SHADOW_STACK_STATUS      76
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 8982f68e7230c..e763e8d99a436 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -277,7 +277,7 @@ static int write_buildid(const char *name, size_t name_len, struct build_id *bid
 	struct perf_record_header_build_id b;
 	size_t len;
 
-	len = sizeof(b) + name_len + 1;
+	len = name_len + 1;
 	len = PERF_ALIGN(len, sizeof(u64));
 
 	memset(&b, 0, sizeof(b));
@@ -286,7 +286,7 @@ static int write_buildid(const char *name, size_t name_len, struct build_id *bid
 	misc |= PERF_RECORD_MISC_BUILD_ID_SIZE;
 	b.pid = pid;
 	b.header.misc = misc;
-	b.header.size = len;
+	b.header.size = sizeof(b) + len;
 
 	err = do_write(fd, &b, sizeof(b));
 	if (err < 0)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index f745723d486ba..d22c5df1701ec 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2571,12 +2571,12 @@ try_fallback:
 	if (err == -EMFILE && rlimit__increase_nofile(&set_rlimit))
 		goto retry_open;
 
-	if (err == -EOPNOTSUPP && evsel__precise_ip_fallback(evsel))
-		goto retry_open;
-
 	if (err == -EINVAL && evsel__detect_missing_features(evsel))
 		goto fallback_missing_features;
 
+	if (evsel__precise_ip_fallback(evsel))
+		goto retry_open;
+
 	if (evsel__handle_error_quirks(evsel, err))
 		goto retry_open;
 
diff --git a/tools/perf/util/hwmon_pmu.c b/tools/perf/util/hwmon_pmu.c
index e61429b38ba7b..4acb9bb19b846 100644
--- a/tools/perf/util/hwmon_pmu.c
+++ b/tools/perf/util/hwmon_pmu.c
@@ -258,8 +258,12 @@ static int hwmon_pmu__read_events(struct hwmon_pmu *pmu)
 	if (pmu->pmu.sysfs_aliases_loaded)
 		return 0;
 
-	/* Use a dup-ed fd as closedir will close it. */
-	dup_fd = dup(pmu->hwmon_dir_fd);
+	/*
+	 * Use a dup-ed fd as closedir will close it. Use openat so that the
+	 * directory contents are refreshed.
+	 */
+	dup_fd = openat(pmu->hwmon_dir_fd, ".", O_DIRECTORY);
+
 	if (dup_fd == -1)
 		return -ENOMEM;
 
@@ -336,6 +340,9 @@ static int hwmon_pmu__read_events(struct hwmon_pmu *pmu)
 			close(fd);
 		}
 	}
+	if (hashmap__size(&pmu->events) == 0)
+		pr_debug2("hwmon_pmu: %s has no events\n", pmu->pmu.name);
+
 	hashmap__for_each_entry_safe((&pmu->events), cur, tmp, bkt) {
 		union hwmon_pmu_event_key key = {
 			.type_and_num = cur->key,
@@ -343,8 +350,8 @@ static int hwmon_pmu__read_events(struct hwmon_pmu *pmu)
 		struct hwmon_pmu_event_value *value = cur->pvalue;
 
 		if (!test_bit(HWMON_ITEM_INPUT, value->items)) {
-			pr_debug("hwmon_pmu: removing event '%s%d' that has no input file\n",
-				hwmon_type_strs[key.type], key.num);
+			pr_debug("hwmon_pmu: %s removing event '%s%d' that has no input file\n",
+				pmu->pmu.name, hwmon_type_strs[key.type], key.num);
 			hashmap__delete(&pmu->events, key.type_and_num, &key, &value);
 			zfree(&value->label);
 			zfree(&value->name);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 4f0ac998b0ccf..27d5345d2b307 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -134,6 +134,8 @@ struct machine *machine__new_host(void)
 
 		if (machine__create_kernel_maps(machine) < 0)
 			goto out_delete;
+
+		machine->env = &perf_env;
 	}
 
 	return machine;
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 6d51a4c98ad7c..eaa0318e9b87e 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1370,7 +1370,7 @@ int parse_line_range_desc(const char *arg, struct line_range *lr)
 {
 	char *buf = strdup(arg);
 	char *p;
-	int err;
+	int err = 0;
 
 	if (!buf)
 		return -ENOMEM;
diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h
index 2f36b7b6418d1..625f5b046776c 100644
--- a/tools/sched_ext/include/scx/common.bpf.h
+++ b/tools/sched_ext/include/scx/common.bpf.h
@@ -40,9 +40,9 @@ void scx_bpf_dsq_insert(struct task_struct *p, u64 dsq_id, u64 slice, u64 enq_fl
 void scx_bpf_dsq_insert_vtime(struct task_struct *p, u64 dsq_id, u64 slice, u64 vtime, u64 enq_flags) __ksym __weak;
 u32 scx_bpf_dispatch_nr_slots(void) __ksym;
 void scx_bpf_dispatch_cancel(void) __ksym;
-bool scx_bpf_dsq_move_to_local(u64 dsq_id) __ksym;
-void scx_bpf_dsq_move_set_slice(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym;
-void scx_bpf_dsq_move_set_vtime(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym;
+bool scx_bpf_dsq_move_to_local(u64 dsq_id) __ksym __weak;
+void scx_bpf_dsq_move_set_slice(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym __weak;
+void scx_bpf_dsq_move_set_vtime(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym __weak;
 bool scx_bpf_dsq_move(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak;
 bool scx_bpf_dsq_move_vtime(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak;
 u32 scx_bpf_reenqueue_local(void) __ksym;
diff --git a/tools/sched_ext/scx_central.c b/tools/sched_ext/scx_central.c
index 21deea320bd78..e938156ed0a0d 100644
--- a/tools/sched_ext/scx_central.c
+++ b/tools/sched_ext/scx_central.c
@@ -97,7 +97,7 @@ restart:
 	SCX_BUG_ON(!cpuset, "Failed to allocate cpuset");
 	CPU_ZERO(cpuset);
 	CPU_SET(skel->rodata->central_cpu, cpuset);
-	SCX_BUG_ON(sched_setaffinity(0, sizeof(cpuset), cpuset),
+	SCX_BUG_ON(sched_setaffinity(0, sizeof(*cpuset), cpuset),
 		   "Failed to affinitize to central CPU %d (max %d)",
 		   skel->rodata->central_cpu, skel->rodata->nr_cpu_ids - 1);
 	CPU_FREE(cpuset);
diff --git a/tools/testing/selftests/alsa/Makefile b/tools/testing/selftests/alsa/Makefile
index 944279160fed2..8dab90ad22bb2 100644
--- a/tools/testing/selftests/alsa/Makefile
+++ b/tools/testing/selftests/alsa/Makefile
@@ -27,5 +27,5 @@ include ../lib.mk
 $(OUTPUT)/libatest.so: conf.c alsa-local.h
 	$(CC) $(CFLAGS) -shared -fPIC $< $(LDLIBS) -o $@
 
-$(OUTPUT)/%: %.c $(TEST_GEN_PROGS_EXTENDED) alsa-local.h
+$(OUTPUT)/%: %.c $(OUTPUT)/libatest.so alsa-local.h
 	$(CC) $(CFLAGS) $< $(LDLIBS) -latest -o $@
diff --git a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S
index df3230fdac395..66ab2e0bae5fd 100644
--- a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S
+++ b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S
@@ -81,32 +81,31 @@ do_syscall:
 	stp	x27, x28, [sp, #96]
 
 	// Set SVCR if we're doing SME
-	cbz	x1, 1f
+	cbz	x1, load_gpr
 	adrp	x2, svcr_in
 	ldr	x2, [x2, :lo12:svcr_in]
 	msr	S3_3_C4_C2_2, x2
-1:
 
 	// Load ZA and ZT0 if enabled - uses x12 as scratch due to SME LDR
-	tbz	x2, #SVCR_ZA_SHIFT, 1f
+	tbz	x2, #SVCR_ZA_SHIFT, load_gpr
 	mov	w12, #0
 	ldr	x2, =za_in
-2:	_ldr_za 12, 2
+1:	_ldr_za 12, 2
 	add	x2, x2, x1
 	add	x12, x12, #1
 	cmp	x1, x12
-	bne	2b
+	bne	1b
 
 	// ZT0
 	mrs	x2, S3_0_C0_C4_5	// ID_AA64SMFR0_EL1
 	ubfx	x2, x2, #ID_AA64SMFR0_EL1_SMEver_SHIFT, \
 			 #ID_AA64SMFR0_EL1_SMEver_WIDTH
-	cbz	x2, 1f
+	cbz	x2, load_gpr
 	adrp	x2, zt_in
 	add	x2, x2, :lo12:zt_in
 	_ldr_zt 2
-1:
 
+load_gpr:
 	// Load GPRs x8-x28, and save our SP/FP for later comparison
 	ldr	x2, =gpr_in
 	add	x2, x2, #64
@@ -125,9 +124,9 @@ do_syscall:
 	str	x30, [x2], #8		// LR
 
 	// Load FPRs if we're not doing neither SVE nor streaming SVE
-	cbnz	x0, 1f
+	cbnz	x0, check_sve_in
 	ldr	x2, =svcr_in
-	tbnz	x2, #SVCR_SM_SHIFT, 1f
+	tbnz	x2, #SVCR_SM_SHIFT, check_sve_in
 
 	ldr	x2, =fpr_in
 	ldp	q0, q1, [x2]
@@ -148,8 +147,8 @@ do_syscall:
 	ldp	q30, q31, [x2, #16 * 30]
 
 	b	2f
-1:
 
+check_sve_in:
 	// Load the SVE registers if we're doing SVE/SME
 
 	ldr	x2, =z_in
@@ -256,32 +255,31 @@ do_syscall:
 	stp	q30, q31, [x2, #16 * 30]
 
 	// Save SVCR if we're doing SME
-	cbz	x1, 1f
+	cbz	x1, check_sve_out
 	mrs	x2, S3_3_C4_C2_2
 	adrp	x3, svcr_out
 	str	x2, [x3, :lo12:svcr_out]
-1:
 
 	// Save ZA if it's enabled - uses x12 as scratch due to SME STR
-	tbz	x2, #SVCR_ZA_SHIFT, 1f
+	tbz	x2, #SVCR_ZA_SHIFT, check_sve_out
 	mov	w12, #0
 	ldr	x2, =za_out
-2:	_str_za 12, 2
+1:	_str_za 12, 2
 	add	x2, x2, x1
 	add	x12, x12, #1
 	cmp	x1, x12
-	bne	2b
+	bne	1b
 
 	// ZT0
 	mrs	x2, S3_0_C0_C4_5	// ID_AA64SMFR0_EL1
 	ubfx	x2, x2, #ID_AA64SMFR0_EL1_SMEver_SHIFT, \
 			#ID_AA64SMFR0_EL1_SMEver_WIDTH
-	cbz	x2, 1f
+	cbz	x2, check_sve_out
 	adrp	x2, zt_out
 	add	x2, x2, :lo12:zt_out
 	_str_zt 2
-1:
 
+check_sve_out:
 	// Save the SVE state if we have some
 	cbz	x0, 1f
 
diff --git a/tools/testing/selftests/bpf/prog_tests/changes_pkt_data.c b/tools/testing/selftests/bpf/prog_tests/changes_pkt_data.c
new file mode 100644
index 0000000000000..7526de3790814
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/changes_pkt_data.c
@@ -0,0 +1,107 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "bpf/libbpf.h"
+#include "changes_pkt_data_freplace.skel.h"
+#include "changes_pkt_data.skel.h"
+#include <test_progs.h>
+
+static void print_verifier_log(const char *log)
+{
+	if (env.verbosity >= VERBOSE_VERY)
+		fprintf(stdout, "VERIFIER LOG:\n=============\n%s=============\n", log);
+}
+
+static void test_aux(const char *main_prog_name,
+		     const char *to_be_replaced,
+		     const char *replacement,
+		     bool expect_load)
+{
+	struct changes_pkt_data_freplace *freplace = NULL;
+	struct bpf_program *freplace_prog = NULL;
+	struct bpf_program *main_prog = NULL;
+	LIBBPF_OPTS(bpf_object_open_opts, opts);
+	struct changes_pkt_data *main = NULL;
+	char log[16*1024];
+	int err;
+
+	opts.kernel_log_buf = log;
+	opts.kernel_log_size = sizeof(log);
+	if (env.verbosity >= VERBOSE_SUPER)
+		opts.kernel_log_level = 1 | 2 | 4;
+	main = changes_pkt_data__open_opts(&opts);
+	if (!ASSERT_OK_PTR(main, "changes_pkt_data__open"))
+		goto out;
+	main_prog = bpf_object__find_program_by_name(main->obj, main_prog_name);
+	if (!ASSERT_OK_PTR(main_prog, "main_prog"))
+		goto out;
+	bpf_program__set_autoload(main_prog, true);
+	err = changes_pkt_data__load(main);
+	print_verifier_log(log);
+	if (!ASSERT_OK(err, "changes_pkt_data__load"))
+		goto out;
+	freplace = changes_pkt_data_freplace__open_opts(&opts);
+	if (!ASSERT_OK_PTR(freplace, "changes_pkt_data_freplace__open"))
+		goto out;
+	freplace_prog = bpf_object__find_program_by_name(freplace->obj, replacement);
+	if (!ASSERT_OK_PTR(freplace_prog, "freplace_prog"))
+		goto out;
+	bpf_program__set_autoload(freplace_prog, true);
+	bpf_program__set_autoattach(freplace_prog, true);
+	bpf_program__set_attach_target(freplace_prog,
+				       bpf_program__fd(main_prog),
+				       to_be_replaced);
+	err = changes_pkt_data_freplace__load(freplace);
+	print_verifier_log(log);
+	if (expect_load) {
+		ASSERT_OK(err, "changes_pkt_data_freplace__load");
+	} else {
+		ASSERT_ERR(err, "changes_pkt_data_freplace__load");
+		ASSERT_HAS_SUBSTR(log, "Extension program changes packet data", "error log");
+	}
+
+out:
+	changes_pkt_data_freplace__destroy(freplace);
+	changes_pkt_data__destroy(main);
+}
+
+/* There are two global subprograms in both changes_pkt_data.skel.h:
+ * - one changes packet data;
+ * - another does not.
+ * It is ok to freplace subprograms that change packet data with those
+ * that either do or do not. It is only ok to freplace subprograms
+ * that do not change packet data with those that do not as well.
+ * The below tests check outcomes for each combination of such freplace.
+ * Also test a case when main subprogram itself is replaced and is a single
+ * subprogram in a program.
+ */
+void test_changes_pkt_data_freplace(void)
+{
+	struct {
+		const char *main;
+		const char *to_be_replaced;
+		bool changes;
+	} mains[] = {
+		{ "main_with_subprogs",   "changes_pkt_data",         true },
+		{ "main_with_subprogs",   "does_not_change_pkt_data", false },
+		{ "main_changes",         "main_changes",             true },
+		{ "main_does_not_change", "main_does_not_change",     false },
+	};
+	struct {
+		const char *func;
+		bool changes;
+	} replacements[] = {
+		{ "changes_pkt_data",         true },
+		{ "does_not_change_pkt_data", false }
+	};
+	char buf[64];
+
+	for (int i = 0; i < ARRAY_SIZE(mains); ++i) {
+		for (int j = 0; j < ARRAY_SIZE(replacements); ++j) {
+			snprintf(buf, sizeof(buf), "%s_with_%s",
+				 mains[i].to_be_replaced, replacements[j].func);
+			if (!test__start_subtest(buf))
+				continue;
+			test_aux(mains[i].main, mains[i].to_be_replaced, replacements[j].func,
+				 mains[i].changes || !replacements[j].changes);
+		}
+	}
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_null.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_null.c
index 6fa19449297e9..43676a9922dce 100644
--- a/tools/testing/selftests/bpf/prog_tests/raw_tp_null.c
+++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_null.c
@@ -3,11 +3,14 @@
 
 #include <test_progs.h>
 #include "raw_tp_null.skel.h"
+#include "raw_tp_null_fail.skel.h"
 
 void test_raw_tp_null(void)
 {
 	struct raw_tp_null *skel;
 
+	RUN_TESTS(raw_tp_null_fail);
+
 	skel = raw_tp_null__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "raw_tp_null__open_and_load"))
 		return;
diff --git a/tools/testing/selftests/bpf/prog_tests/socket_helpers.h b/tools/testing/selftests/bpf/prog_tests/socket_helpers.h
new file mode 100644
index 0000000000000..1bdfb79ef009b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/socket_helpers.h
@@ -0,0 +1,394 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __SOCKET_HELPERS__
+#define __SOCKET_HELPERS__
+
+#include <linux/vm_sockets.h>
+
+/* include/linux/net.h */
+#define SOCK_TYPE_MASK 0xf
+
+#define IO_TIMEOUT_SEC 30
+#define MAX_STRERR_LEN 256
+
+/* workaround for older vm_sockets.h */
+#ifndef VMADDR_CID_LOCAL
+#define VMADDR_CID_LOCAL 1
+#endif
+
+/* include/linux/cleanup.h */
+#define __get_and_null(p, nullvalue)                                           \
+	({                                                                     \
+		__auto_type __ptr = &(p);                                      \
+		__auto_type __val = *__ptr;                                    \
+		*__ptr = nullvalue;                                            \
+		__val;                                                         \
+	})
+
+#define take_fd(fd) __get_and_null(fd, -EBADF)
+
+/* Wrappers that fail the test on error and report it. */
+
+#define _FAIL(errnum, fmt...)                                                  \
+	({                                                                     \
+		error_at_line(0, (errnum), __func__, __LINE__, fmt);           \
+		CHECK_FAIL(true);                                              \
+	})
+#define FAIL(fmt...) _FAIL(0, fmt)
+#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt)
+#define FAIL_LIBBPF(err, msg)                                                  \
+	({                                                                     \
+		char __buf[MAX_STRERR_LEN];                                    \
+		libbpf_strerror((err), __buf, sizeof(__buf));                  \
+		FAIL("%s: %s", (msg), __buf);                                  \
+	})
+
+
+#define xaccept_nonblock(fd, addr, len)                                        \
+	({                                                                     \
+		int __ret =                                                    \
+			accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC);   \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("accept");                                  \
+		__ret;                                                         \
+	})
+
+#define xbind(fd, addr, len)                                                   \
+	({                                                                     \
+		int __ret = bind((fd), (addr), (len));                         \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("bind");                                    \
+		__ret;                                                         \
+	})
+
+#define xclose(fd)                                                             \
+	({                                                                     \
+		int __ret = close((fd));                                       \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("close");                                   \
+		__ret;                                                         \
+	})
+
+#define xconnect(fd, addr, len)                                                \
+	({                                                                     \
+		int __ret = connect((fd), (addr), (len));                      \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("connect");                                 \
+		__ret;                                                         \
+	})
+
+#define xgetsockname(fd, addr, len)                                            \
+	({                                                                     \
+		int __ret = getsockname((fd), (addr), (len));                  \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("getsockname");                             \
+		__ret;                                                         \
+	})
+
+#define xgetsockopt(fd, level, name, val, len)                                 \
+	({                                                                     \
+		int __ret = getsockopt((fd), (level), (name), (val), (len));   \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("getsockopt(" #name ")");                   \
+		__ret;                                                         \
+	})
+
+#define xlisten(fd, backlog)                                                   \
+	({                                                                     \
+		int __ret = listen((fd), (backlog));                           \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("listen");                                  \
+		__ret;                                                         \
+	})
+
+#define xsetsockopt(fd, level, name, val, len)                                 \
+	({                                                                     \
+		int __ret = setsockopt((fd), (level), (name), (val), (len));   \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("setsockopt(" #name ")");                   \
+		__ret;                                                         \
+	})
+
+#define xsend(fd, buf, len, flags)                                             \
+	({                                                                     \
+		ssize_t __ret = send((fd), (buf), (len), (flags));             \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("send");                                    \
+		__ret;                                                         \
+	})
+
+#define xrecv_nonblock(fd, buf, len, flags)                                    \
+	({                                                                     \
+		ssize_t __ret = recv_timeout((fd), (buf), (len), (flags),      \
+					     IO_TIMEOUT_SEC);                  \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("recv");                                    \
+		__ret;                                                         \
+	})
+
+#define xsocket(family, sotype, flags)                                         \
+	({                                                                     \
+		int __ret = socket(family, sotype, flags);                     \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("socket");                                  \
+		__ret;                                                         \
+	})
+
+static inline void close_fd(int *fd)
+{
+	if (*fd >= 0)
+		xclose(*fd);
+}
+
+#define __close_fd __attribute__((cleanup(close_fd)))
+
+static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss)
+{
+	return (struct sockaddr *)ss;
+}
+
+static inline void init_addr_loopback4(struct sockaddr_storage *ss,
+				       socklen_t *len)
+{
+	struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss));
+
+	addr4->sin_family = AF_INET;
+	addr4->sin_port = 0;
+	addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+	*len = sizeof(*addr4);
+}
+
+static inline void init_addr_loopback6(struct sockaddr_storage *ss,
+				       socklen_t *len)
+{
+	struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss));
+
+	addr6->sin6_family = AF_INET6;
+	addr6->sin6_port = 0;
+	addr6->sin6_addr = in6addr_loopback;
+	*len = sizeof(*addr6);
+}
+
+static inline void init_addr_loopback_vsock(struct sockaddr_storage *ss,
+					    socklen_t *len)
+{
+	struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss));
+
+	addr->svm_family = AF_VSOCK;
+	addr->svm_port = VMADDR_PORT_ANY;
+	addr->svm_cid = VMADDR_CID_LOCAL;
+	*len = sizeof(*addr);
+}
+
+static inline void init_addr_loopback(int family, struct sockaddr_storage *ss,
+				      socklen_t *len)
+{
+	switch (family) {
+	case AF_INET:
+		init_addr_loopback4(ss, len);
+		return;
+	case AF_INET6:
+		init_addr_loopback6(ss, len);
+		return;
+	case AF_VSOCK:
+		init_addr_loopback_vsock(ss, len);
+		return;
+	default:
+		FAIL("unsupported address family %d", family);
+	}
+}
+
+static inline int enable_reuseport(int s, int progfd)
+{
+	int err, one = 1;
+
+	err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one));
+	if (err)
+		return -1;
+	err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd,
+			  sizeof(progfd));
+	if (err)
+		return -1;
+
+	return 0;
+}
+
+static inline int socket_loopback_reuseport(int family, int sotype, int progfd)
+{
+	struct sockaddr_storage addr;
+	socklen_t len = 0;
+	int err, s;
+
+	init_addr_loopback(family, &addr, &len);
+
+	s = xsocket(family, sotype, 0);
+	if (s == -1)
+		return -1;
+
+	if (progfd >= 0)
+		enable_reuseport(s, progfd);
+
+	err = xbind(s, sockaddr(&addr), len);
+	if (err)
+		goto close;
+
+	if (sotype & SOCK_DGRAM)
+		return s;
+
+	err = xlisten(s, SOMAXCONN);
+	if (err)
+		goto close;
+
+	return s;
+close:
+	xclose(s);
+	return -1;
+}
+
+static inline int socket_loopback(int family, int sotype)
+{
+	return socket_loopback_reuseport(family, sotype, -1);
+}
+
+static inline int poll_connect(int fd, unsigned int timeout_sec)
+{
+	struct timeval timeout = { .tv_sec = timeout_sec };
+	fd_set wfds;
+	int r, eval;
+	socklen_t esize = sizeof(eval);
+
+	FD_ZERO(&wfds);
+	FD_SET(fd, &wfds);
+
+	r = select(fd + 1, NULL, &wfds, NULL, &timeout);
+	if (r == 0)
+		errno = ETIME;
+	if (r != 1)
+		return -1;
+
+	if (getsockopt(fd, SOL_SOCKET, SO_ERROR, &eval, &esize) < 0)
+		return -1;
+	if (eval != 0) {
+		errno = eval;
+		return -1;
+	}
+
+	return 0;
+}
+
+static inline int poll_read(int fd, unsigned int timeout_sec)
+{
+	struct timeval timeout = { .tv_sec = timeout_sec };
+	fd_set rfds;
+	int r;
+
+	FD_ZERO(&rfds);
+	FD_SET(fd, &rfds);
+
+	r = select(fd + 1, &rfds, NULL, NULL, &timeout);
+	if (r == 0)
+		errno = ETIME;
+
+	return r == 1 ? 0 : -1;
+}
+
+static inline int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len,
+				 unsigned int timeout_sec)
+{
+	if (poll_read(fd, timeout_sec))
+		return -1;
+
+	return accept(fd, addr, len);
+}
+
+static inline int recv_timeout(int fd, void *buf, size_t len, int flags,
+			       unsigned int timeout_sec)
+{
+	if (poll_read(fd, timeout_sec))
+		return -1;
+
+	return recv(fd, buf, len, flags);
+}
+
+
+static inline int create_pair(int family, int sotype, int *p0, int *p1)
+{
+	__close_fd int s, c = -1, p = -1;
+	struct sockaddr_storage addr;
+	socklen_t len = sizeof(addr);
+	int err;
+
+	s = socket_loopback(family, sotype);
+	if (s < 0)
+		return s;
+
+	err = xgetsockname(s, sockaddr(&addr), &len);
+	if (err)
+		return err;
+
+	c = xsocket(family, sotype, 0);
+	if (c < 0)
+		return c;
+
+	err = connect(c, sockaddr(&addr), len);
+	if (err) {
+		if (errno != EINPROGRESS) {
+			FAIL_ERRNO("connect");
+			return err;
+		}
+
+		err = poll_connect(c, IO_TIMEOUT_SEC);
+		if (err) {
+			FAIL_ERRNO("poll_connect");
+			return err;
+		}
+	}
+
+	switch (sotype & SOCK_TYPE_MASK) {
+	case SOCK_DGRAM:
+		err = xgetsockname(c, sockaddr(&addr), &len);
+		if (err)
+			return err;
+
+		err = xconnect(s, sockaddr(&addr), len);
+		if (err)
+			return err;
+
+		*p0 = take_fd(s);
+		break;
+	case SOCK_STREAM:
+	case SOCK_SEQPACKET:
+		p = xaccept_nonblock(s, NULL, NULL);
+		if (p < 0)
+			return p;
+
+		*p0 = take_fd(p);
+		break;
+	default:
+		FAIL("Unsupported socket type %#x", sotype);
+		return -EOPNOTSUPP;
+	}
+
+	*p1 = take_fd(c);
+	return 0;
+}
+
+static inline int create_socket_pairs(int family, int sotype, int *c0, int *c1,
+				      int *p0, int *p1)
+{
+	int err;
+
+	err = create_pair(family, sotype, c0, p0);
+	if (err)
+		return err;
+
+	err = create_pair(family, sotype, c1, p1);
+	if (err) {
+		close(*c0);
+		close(*p0);
+	}
+
+	return err;
+}
+
+#endif // __SOCKET_HELPERS__
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index fdff0652d7ef5..884ad87783d59 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -12,6 +12,7 @@
 #include "test_sockmap_progs_query.skel.h"
 #include "test_sockmap_pass_prog.skel.h"
 #include "test_sockmap_drop_prog.skel.h"
+#include "test_sockmap_change_tail.skel.h"
 #include "bpf_iter_sockmap.skel.h"
 
 #include "sockmap_helpers.h"
@@ -643,6 +644,54 @@ out:
 		test_sockmap_drop_prog__destroy(drop);
 }
 
+static void test_sockmap_skb_verdict_change_tail(void)
+{
+	struct test_sockmap_change_tail *skel;
+	int err, map, verdict;
+	int c1, p1, sent, recvd;
+	int zero = 0;
+	char buf[2];
+
+	skel = test_sockmap_change_tail__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+	verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+	map = bpf_map__fd(skel->maps.sock_map_rx);
+
+	err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach"))
+		goto out;
+	err = create_pair(AF_INET, SOCK_STREAM, &c1, &p1);
+	if (!ASSERT_OK(err, "create_pair()"))
+		goto out;
+	err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(c1)"))
+		goto out_close;
+	sent = xsend(p1, "Tr", 2, 0);
+	ASSERT_EQ(sent, 2, "xsend(p1)");
+	recvd = recv(c1, buf, 2, 0);
+	ASSERT_EQ(recvd, 1, "recv(c1)");
+	ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret");
+
+	sent = xsend(p1, "G", 1, 0);
+	ASSERT_EQ(sent, 1, "xsend(p1)");
+	recvd = recv(c1, buf, 2, 0);
+	ASSERT_EQ(recvd, 2, "recv(c1)");
+	ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret");
+
+	sent = xsend(p1, "E", 1, 0);
+	ASSERT_EQ(sent, 1, "xsend(p1)");
+	recvd = recv(c1, buf, 1, 0);
+	ASSERT_EQ(recvd, 1, "recv(c1)");
+	ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret");
+
+out_close:
+	close(c1);
+	close(p1);
+out:
+	test_sockmap_change_tail__destroy(skel);
+}
+
 static void test_sockmap_skb_verdict_peek_helper(int map)
 {
 	int err, c1, p1, zero = 0, sent, recvd, avail;
@@ -934,8 +983,10 @@ static void test_sockmap_same_sock(void)
 
 	err = socketpair(AF_UNIX, SOCK_STREAM, 0, stream);
 	ASSERT_OK(err, "socketpair(af_unix, sock_stream)");
-	if (err)
+	if (err) {
+		close(tcp);
 		goto out;
+	}
 
 	for (i = 0; i < 2; i++) {
 		err = bpf_map_update_elem(map, &zero, &stream[0], BPF_ANY);
@@ -954,14 +1005,14 @@ static void test_sockmap_same_sock(void)
 		ASSERT_OK(err, "bpf_map_update_elem(tcp)");
 	}
 
+	close(tcp);
 	err = bpf_map_delete_elem(map, &zero);
-	ASSERT_OK(err, "bpf_map_delete_elem(entry)");
+	ASSERT_ERR(err, "bpf_map_delete_elem(entry)");
 
 	close(stream[0]);
 	close(stream[1]);
 out:
 	close(dgram);
-	close(tcp);
 	close(udp);
 	test_sockmap_pass_prog__destroy(skel);
 }
@@ -1056,6 +1107,8 @@ void test_sockmap_basic(void)
 		test_sockmap_skb_verdict_fionread(true);
 	if (test__start_subtest("sockmap skb_verdict fionread on drop"))
 		test_sockmap_skb_verdict_fionread(false);
+	if (test__start_subtest("sockmap skb_verdict change tail"))
+		test_sockmap_skb_verdict_change_tail();
 	if (test__start_subtest("sockmap skb_verdict msg_f_peek"))
 		test_sockmap_skb_verdict_peek();
 	if (test__start_subtest("sockmap skb_verdict msg_f_peek with link"))
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
index 38e35c72bdaa2..3e5571dd578d1 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
@@ -1,139 +1,12 @@
 #ifndef __SOCKMAP_HELPERS__
 #define __SOCKMAP_HELPERS__
 
-#include <linux/vm_sockets.h>
+#include "socket_helpers.h"
 
-/* include/linux/net.h */
-#define SOCK_TYPE_MASK 0xf
-
-#define IO_TIMEOUT_SEC 30
-#define MAX_STRERR_LEN 256
 #define MAX_TEST_NAME 80
 
-/* workaround for older vm_sockets.h */
-#ifndef VMADDR_CID_LOCAL
-#define VMADDR_CID_LOCAL 1
-#endif
-
 #define __always_unused	__attribute__((__unused__))
 
-/* include/linux/cleanup.h */
-#define __get_and_null(p, nullvalue)                                           \
-	({                                                                     \
-		__auto_type __ptr = &(p);                                      \
-		__auto_type __val = *__ptr;                                    \
-		*__ptr = nullvalue;                                            \
-		__val;                                                         \
-	})
-
-#define take_fd(fd) __get_and_null(fd, -EBADF)
-
-#define _FAIL(errnum, fmt...)                                                  \
-	({                                                                     \
-		error_at_line(0, (errnum), __func__, __LINE__, fmt);           \
-		CHECK_FAIL(true);                                              \
-	})
-#define FAIL(fmt...) _FAIL(0, fmt)
-#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt)
-#define FAIL_LIBBPF(err, msg)                                                  \
-	({                                                                     \
-		char __buf[MAX_STRERR_LEN];                                    \
-		libbpf_strerror((err), __buf, sizeof(__buf));                  \
-		FAIL("%s: %s", (msg), __buf);                                  \
-	})
-
-/* Wrappers that fail the test on error and report it. */
-
-#define xaccept_nonblock(fd, addr, len)                                        \
-	({                                                                     \
-		int __ret =                                                    \
-			accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC);   \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("accept");                                  \
-		__ret;                                                         \
-	})
-
-#define xbind(fd, addr, len)                                                   \
-	({                                                                     \
-		int __ret = bind((fd), (addr), (len));                         \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("bind");                                    \
-		__ret;                                                         \
-	})
-
-#define xclose(fd)                                                             \
-	({                                                                     \
-		int __ret = close((fd));                                       \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("close");                                   \
-		__ret;                                                         \
-	})
-
-#define xconnect(fd, addr, len)                                                \
-	({                                                                     \
-		int __ret = connect((fd), (addr), (len));                      \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("connect");                                 \
-		__ret;                                                         \
-	})
-
-#define xgetsockname(fd, addr, len)                                            \
-	({                                                                     \
-		int __ret = getsockname((fd), (addr), (len));                  \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("getsockname");                             \
-		__ret;                                                         \
-	})
-
-#define xgetsockopt(fd, level, name, val, len)                                 \
-	({                                                                     \
-		int __ret = getsockopt((fd), (level), (name), (val), (len));   \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("getsockopt(" #name ")");                   \
-		__ret;                                                         \
-	})
-
-#define xlisten(fd, backlog)                                                   \
-	({                                                                     \
-		int __ret = listen((fd), (backlog));                           \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("listen");                                  \
-		__ret;                                                         \
-	})
-
-#define xsetsockopt(fd, level, name, val, len)                                 \
-	({                                                                     \
-		int __ret = setsockopt((fd), (level), (name), (val), (len));   \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("setsockopt(" #name ")");                   \
-		__ret;                                                         \
-	})
-
-#define xsend(fd, buf, len, flags)                                             \
-	({                                                                     \
-		ssize_t __ret = send((fd), (buf), (len), (flags));             \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("send");                                    \
-		__ret;                                                         \
-	})
-
-#define xrecv_nonblock(fd, buf, len, flags)                                    \
-	({                                                                     \
-		ssize_t __ret = recv_timeout((fd), (buf), (len), (flags),      \
-					     IO_TIMEOUT_SEC);                  \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("recv");                                    \
-		__ret;                                                         \
-	})
-
-#define xsocket(family, sotype, flags)                                         \
-	({                                                                     \
-		int __ret = socket(family, sotype, flags);                     \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("socket");                                  \
-		__ret;                                                         \
-	})
-
 #define xbpf_map_delete_elem(fd, key)                                          \
 	({                                                                     \
 		int __ret = bpf_map_delete_elem((fd), (key));                  \
@@ -193,130 +66,6 @@
 		__ret;                                                         \
 	})
 
-static inline void close_fd(int *fd)
-{
-	if (*fd >= 0)
-		xclose(*fd);
-}
-
-#define __close_fd __attribute__((cleanup(close_fd)))
-
-static inline int poll_connect(int fd, unsigned int timeout_sec)
-{
-	struct timeval timeout = { .tv_sec = timeout_sec };
-	fd_set wfds;
-	int r, eval;
-	socklen_t esize = sizeof(eval);
-
-	FD_ZERO(&wfds);
-	FD_SET(fd, &wfds);
-
-	r = select(fd + 1, NULL, &wfds, NULL, &timeout);
-	if (r == 0)
-		errno = ETIME;
-	if (r != 1)
-		return -1;
-
-	if (getsockopt(fd, SOL_SOCKET, SO_ERROR, &eval, &esize) < 0)
-		return -1;
-	if (eval != 0) {
-		errno = eval;
-		return -1;
-	}
-
-	return 0;
-}
-
-static inline int poll_read(int fd, unsigned int timeout_sec)
-{
-	struct timeval timeout = { .tv_sec = timeout_sec };
-	fd_set rfds;
-	int r;
-
-	FD_ZERO(&rfds);
-	FD_SET(fd, &rfds);
-
-	r = select(fd + 1, &rfds, NULL, NULL, &timeout);
-	if (r == 0)
-		errno = ETIME;
-
-	return r == 1 ? 0 : -1;
-}
-
-static inline int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len,
-				 unsigned int timeout_sec)
-{
-	if (poll_read(fd, timeout_sec))
-		return -1;
-
-	return accept(fd, addr, len);
-}
-
-static inline int recv_timeout(int fd, void *buf, size_t len, int flags,
-			       unsigned int timeout_sec)
-{
-	if (poll_read(fd, timeout_sec))
-		return -1;
-
-	return recv(fd, buf, len, flags);
-}
-
-static inline void init_addr_loopback4(struct sockaddr_storage *ss,
-				       socklen_t *len)
-{
-	struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss));
-
-	addr4->sin_family = AF_INET;
-	addr4->sin_port = 0;
-	addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK);
-	*len = sizeof(*addr4);
-}
-
-static inline void init_addr_loopback6(struct sockaddr_storage *ss,
-				       socklen_t *len)
-{
-	struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss));
-
-	addr6->sin6_family = AF_INET6;
-	addr6->sin6_port = 0;
-	addr6->sin6_addr = in6addr_loopback;
-	*len = sizeof(*addr6);
-}
-
-static inline void init_addr_loopback_vsock(struct sockaddr_storage *ss,
-					    socklen_t *len)
-{
-	struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss));
-
-	addr->svm_family = AF_VSOCK;
-	addr->svm_port = VMADDR_PORT_ANY;
-	addr->svm_cid = VMADDR_CID_LOCAL;
-	*len = sizeof(*addr);
-}
-
-static inline void init_addr_loopback(int family, struct sockaddr_storage *ss,
-				      socklen_t *len)
-{
-	switch (family) {
-	case AF_INET:
-		init_addr_loopback4(ss, len);
-		return;
-	case AF_INET6:
-		init_addr_loopback6(ss, len);
-		return;
-	case AF_VSOCK:
-		init_addr_loopback_vsock(ss, len);
-		return;
-	default:
-		FAIL("unsupported address family %d", family);
-	}
-}
-
-static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss)
-{
-	return (struct sockaddr *)ss;
-}
-
 static inline int add_to_sockmap(int sock_mapfd, int fd1, int fd2)
 {
 	u64 value;
@@ -334,136 +83,4 @@ static inline int add_to_sockmap(int sock_mapfd, int fd1, int fd2)
 	return xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
 }
 
-static inline int enable_reuseport(int s, int progfd)
-{
-	int err, one = 1;
-
-	err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one));
-	if (err)
-		return -1;
-	err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd,
-			  sizeof(progfd));
-	if (err)
-		return -1;
-
-	return 0;
-}
-
-static inline int socket_loopback_reuseport(int family, int sotype, int progfd)
-{
-	struct sockaddr_storage addr;
-	socklen_t len = 0;
-	int err, s;
-
-	init_addr_loopback(family, &addr, &len);
-
-	s = xsocket(family, sotype, 0);
-	if (s == -1)
-		return -1;
-
-	if (progfd >= 0)
-		enable_reuseport(s, progfd);
-
-	err = xbind(s, sockaddr(&addr), len);
-	if (err)
-		goto close;
-
-	if (sotype & SOCK_DGRAM)
-		return s;
-
-	err = xlisten(s, SOMAXCONN);
-	if (err)
-		goto close;
-
-	return s;
-close:
-	xclose(s);
-	return -1;
-}
-
-static inline int socket_loopback(int family, int sotype)
-{
-	return socket_loopback_reuseport(family, sotype, -1);
-}
-
-static inline int create_pair(int family, int sotype, int *p0, int *p1)
-{
-	__close_fd int s, c = -1, p = -1;
-	struct sockaddr_storage addr;
-	socklen_t len = sizeof(addr);
-	int err;
-
-	s = socket_loopback(family, sotype);
-	if (s < 0)
-		return s;
-
-	err = xgetsockname(s, sockaddr(&addr), &len);
-	if (err)
-		return err;
-
-	c = xsocket(family, sotype, 0);
-	if (c < 0)
-		return c;
-
-	err = connect(c, sockaddr(&addr), len);
-	if (err) {
-		if (errno != EINPROGRESS) {
-			FAIL_ERRNO("connect");
-			return err;
-		}
-
-		err = poll_connect(c, IO_TIMEOUT_SEC);
-		if (err) {
-			FAIL_ERRNO("poll_connect");
-			return err;
-		}
-	}
-
-	switch (sotype & SOCK_TYPE_MASK) {
-	case SOCK_DGRAM:
-		err = xgetsockname(c, sockaddr(&addr), &len);
-		if (err)
-			return err;
-
-		err = xconnect(s, sockaddr(&addr), len);
-		if (err)
-			return err;
-
-		*p0 = take_fd(s);
-		break;
-	case SOCK_STREAM:
-	case SOCK_SEQPACKET:
-		p = xaccept_nonblock(s, NULL, NULL);
-		if (p < 0)
-			return p;
-
-		*p0 = take_fd(p);
-		break;
-	default:
-		FAIL("Unsupported socket type %#x", sotype);
-		return -EOPNOTSUPP;
-	}
-
-	*p1 = take_fd(c);
-	return 0;
-}
-
-static inline int create_socket_pairs(int family, int sotype, int *c0, int *c1,
-				      int *p0, int *p1)
-{
-	int err;
-
-	err = create_pair(family, sotype, c0, p0);
-	if (err)
-		return err;
-
-	err = create_pair(family, sotype, c1, p1);
-	if (err) {
-		close(*c0);
-		close(*p0);
-	}
-
-	return err;
-}
-
 #endif // __SOCKMAP_HELPERS__
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c b/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c
new file mode 100644
index 0000000000000..74752233e779d
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <error.h>
+#include <test_progs.h>
+#include <linux/pkt_cls.h>
+
+#include "test_tc_change_tail.skel.h"
+#include "socket_helpers.h"
+
+#define LO_IFINDEX 1
+
+void test_tc_change_tail(void)
+{
+	LIBBPF_OPTS(bpf_tcx_opts, tcx_opts);
+	struct test_tc_change_tail *skel = NULL;
+	struct bpf_link *link;
+	int c1, p1;
+	char buf[2];
+	int ret;
+
+	skel = test_tc_change_tail__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tc_change_tail__open_and_load"))
+		return;
+
+	link = bpf_program__attach_tcx(skel->progs.change_tail, LO_IFINDEX,
+				     &tcx_opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_tcx"))
+		goto destroy;
+
+	skel->links.change_tail = link;
+	ret = create_pair(AF_INET, SOCK_DGRAM, &c1, &p1);
+	if (!ASSERT_OK(ret, "create_pair"))
+		goto destroy;
+
+	ret = xsend(p1, "Tr", 2, 0);
+	ASSERT_EQ(ret, 2, "xsend(p1)");
+	ret = recv(c1, buf, 2, 0);
+	ASSERT_EQ(ret, 2, "recv(c1)");
+	ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret");
+
+	ret = xsend(p1, "G", 1, 0);
+	ASSERT_EQ(ret, 1, "xsend(p1)");
+	ret = recv(c1, buf, 2, 0);
+	ASSERT_EQ(ret, 1, "recv(c1)");
+	ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret");
+
+	ret = xsend(p1, "E", 1, 0);
+	ASSERT_EQ(ret, 1, "xsend(p1)");
+	ret = recv(c1, buf, 1, 0);
+	ASSERT_EQ(ret, 1, "recv(c1)");
+	ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret");
+
+	ret = xsend(p1, "Z", 1, 0);
+	ASSERT_EQ(ret, 1, "xsend(p1)");
+	ret = recv(c1, buf, 1, 0);
+	ASSERT_EQ(ret, 1, "recv(c1)");
+	ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret");
+
+	close(c1);
+	close(p1);
+destroy:
+	test_tc_change_tail__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/changes_pkt_data.c b/tools/testing/selftests/bpf/progs/changes_pkt_data.c
new file mode 100644
index 0000000000000..43cada48b28ad
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/changes_pkt_data.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+__noinline
+long changes_pkt_data(struct __sk_buff *sk)
+{
+	return bpf_skb_pull_data(sk, 0);
+}
+
+__noinline __weak
+long does_not_change_pkt_data(struct __sk_buff *sk)
+{
+	return 0;
+}
+
+SEC("?tc")
+int main_with_subprogs(struct __sk_buff *sk)
+{
+	changes_pkt_data(sk);
+	does_not_change_pkt_data(sk);
+	return 0;
+}
+
+SEC("?tc")
+int main_changes(struct __sk_buff *sk)
+{
+	bpf_skb_pull_data(sk, 0);
+	return 0;
+}
+
+SEC("?tc")
+int main_does_not_change(struct __sk_buff *sk)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/changes_pkt_data_freplace.c b/tools/testing/selftests/bpf/progs/changes_pkt_data_freplace.c
new file mode 100644
index 0000000000000..f9a622705f1b3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/changes_pkt_data_freplace.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+SEC("?freplace")
+long changes_pkt_data(struct __sk_buff *sk)
+{
+	return bpf_skb_pull_data(sk, 0);
+}
+
+SEC("?freplace")
+long does_not_change_pkt_data(struct __sk_buff *sk)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/raw_tp_null.c b/tools/testing/selftests/bpf/progs/raw_tp_null.c
index 457f34c151e32..5927054b6dd96 100644
--- a/tools/testing/selftests/bpf/progs/raw_tp_null.c
+++ b/tools/testing/selftests/bpf/progs/raw_tp_null.c
@@ -3,6 +3,7 @@
 
 #include <vmlinux.h>
 #include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
 
 char _license[] SEC("license") = "GPL";
 
@@ -17,16 +18,14 @@ int BPF_PROG(test_raw_tp_null, struct sk_buff *skb)
 	if (task->pid != tid)
 		return 0;
 
-	i = i + skb->mark + 1;
-	/* The compiler may move the NULL check before this deref, which causes
-	 * the load to fail as deref of scalar. Prevent that by using a barrier.
+	/* If dead code elimination kicks in, the increment +=2 will be
+	 * removed. For raw_tp programs attaching to tracepoints in kernel
+	 * modules, we mark input arguments as PTR_MAYBE_NULL, so branch
+	 * prediction should never kick in.
 	 */
-	barrier();
-	/* If dead code elimination kicks in, the increment below will
-	 * be removed. For raw_tp programs, we mark input arguments as
-	 * PTR_MAYBE_NULL, so branch prediction should never kick in.
-	 */
-	if (!skb)
-		i += 2;
+	asm volatile ("%[i] += 1; if %[ctx] != 0 goto +1; %[i] += 2;"
+			: [i]"+r"(i)
+			: [ctx]"r"(skb)
+			: "memory");
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c b/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c
new file mode 100644
index 0000000000000..38d669957bf1b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+/* Ensure module parameter has PTR_MAYBE_NULL */
+SEC("tp_btf/bpf_testmod_test_raw_tp_null")
+__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'")
+int test_raw_tp_null_bpf_testmod_test_raw_tp_null_arg_1(void *ctx) {
+    asm volatile("r1 = *(u64 *)(r1 +0); r1 = *(u64 *)(r1 +0);" ::: __clobber_all);
+    return 0;
+}
+
+/* Check NULL marking */
+SEC("tp_btf/sched_pi_setprio")
+__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'")
+int test_raw_tp_null_sched_pi_setprio_arg_2(void *ctx) {
+    asm volatile("r1 = *(u64 *)(r1 +8); r1 = *(u64 *)(r1 +0);" ::: __clobber_all);
+    return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c b/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c
index d1a57f7d09bd8..fe6249d99b315 100644
--- a/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c
@@ -11,6 +11,8 @@ int subprog_tc(struct __sk_buff *skb)
 
 	__sink(skb);
 	__sink(ret);
+	/* let verifier know that 'subprog_tc' can change pointers to skb->data */
+	bpf_skb_change_proto(skb, 0, 0);
 	return ret;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c b/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c
new file mode 100644
index 0000000000000..2796dd8545eb9
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 ByteDance */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} sock_map_rx SEC(".maps");
+
+long change_tail_ret = 1;
+
+SEC("sk_skb")
+int prog_skb_verdict(struct __sk_buff *skb)
+{
+	char *data, *data_end;
+
+	bpf_skb_pull_data(skb, 1);
+	data = (char *)(unsigned long)skb->data;
+	data_end = (char *)(unsigned long)skb->data_end;
+
+	if (data + 1 > data_end)
+		return SK_PASS;
+
+	if (data[0] == 'T') { /* Trim the packet */
+		change_tail_ret = bpf_skb_change_tail(skb, skb->len - 1, 0);
+		return SK_PASS;
+	} else if (data[0] == 'G') { /* Grow the packet */
+		change_tail_ret = bpf_skb_change_tail(skb, skb->len + 1, 0);
+		return SK_PASS;
+	} else if (data[0] == 'E') { /* Error */
+		change_tail_ret = bpf_skb_change_tail(skb, 65535, 0);
+		return SK_PASS;
+	}
+	return SK_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_tc_change_tail.c b/tools/testing/selftests/bpf/progs/test_tc_change_tail.c
new file mode 100644
index 0000000000000..28edafe803f04
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_tc_change_tail.c
@@ -0,0 +1,106 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <linux/pkt_cls.h>
+
+long change_tail_ret = 1;
+
+static __always_inline struct iphdr *parse_ip_header(struct __sk_buff *skb, int *ip_proto)
+{
+	void *data_end = (void *)(long)skb->data_end;
+	void *data = (void *)(long)skb->data;
+	struct ethhdr *eth = data;
+	struct iphdr *iph;
+
+	/* Verify Ethernet header */
+	if ((void *)(data + sizeof(*eth)) > data_end)
+		return NULL;
+
+	/* Skip Ethernet header to get to IP header */
+	iph = (void *)(data + sizeof(struct ethhdr));
+
+	/* Verify IP header */
+	if ((void *)(data + sizeof(struct ethhdr) + sizeof(*iph)) > data_end)
+		return NULL;
+
+	/* Basic IP header validation */
+	if (iph->version != 4)  /* Only support IPv4 */
+		return NULL;
+
+	if (iph->ihl < 5)  /* Minimum IP header length */
+		return NULL;
+
+	*ip_proto = iph->protocol;
+	return iph;
+}
+
+static __always_inline struct udphdr *parse_udp_header(struct __sk_buff *skb, struct iphdr *iph)
+{
+	void *data_end = (void *)(long)skb->data_end;
+	void *hdr = (void *)iph;
+	struct udphdr *udp;
+
+	/* Calculate UDP header position */
+	udp = hdr + (iph->ihl * 4);
+	hdr = (void *)udp;
+
+	/* Verify UDP header bounds */
+	if ((void *)(hdr + sizeof(*udp)) > data_end)
+		return NULL;
+
+	return udp;
+}
+
+SEC("tc/ingress")
+int change_tail(struct __sk_buff *skb)
+{
+	int len = skb->len;
+	struct udphdr *udp;
+	struct iphdr *iph;
+	void *data_end;
+	char *payload;
+	int ip_proto;
+
+	bpf_skb_pull_data(skb, len);
+
+	data_end = (void *)(long)skb->data_end;
+	iph = parse_ip_header(skb, &ip_proto);
+	if (!iph)
+		return TCX_PASS;
+
+	if (ip_proto != IPPROTO_UDP)
+		return TCX_PASS;
+
+	udp = parse_udp_header(skb, iph);
+	if (!udp)
+		return TCX_PASS;
+
+	payload = (char *)udp + (sizeof(struct udphdr));
+	if (payload + 1 > (char *)data_end)
+		return TCX_PASS;
+
+	if (payload[0] == 'T') { /* Trim the packet */
+		change_tail_ret = bpf_skb_change_tail(skb, len - 1, 0);
+		if (!change_tail_ret)
+			bpf_skb_change_tail(skb, len, 0);
+		return TCX_PASS;
+	} else if (payload[0] == 'G') { /* Grow the packet */
+		change_tail_ret = bpf_skb_change_tail(skb, len + 1, 0);
+		if (!change_tail_ret)
+			bpf_skb_change_tail(skb, len, 0);
+		return TCX_PASS;
+	} else if (payload[0] == 'E') { /* Error */
+		change_tail_ret = bpf_skb_change_tail(skb, 65535, 0);
+		return TCX_PASS;
+	} else if (payload[0] == 'Z') { /* Zero */
+		change_tail_ret = bpf_skb_change_tail(skb, 0, 0);
+		return TCX_PASS;
+	}
+	return TCX_DROP;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c
index 5aaf2b065f86c..bba3e37f749b8 100644
--- a/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c
+++ b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c
@@ -7,11 +7,7 @@
 #include "bpf_misc.h"
 
 SEC("tp_btf/bpf_testmod_test_nullable_bare")
-/* This used to be a failure test, but raw_tp nullable arguments can now
- * directly be dereferenced, whether they have nullable annotation or not,
- * and don't need to be explicitly checked.
- */
-__success
+__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'")
 int BPF_PROG(handle_tp_btf_nullable_bare1, struct bpf_testmod_test_read_ctx *nullable_ctx)
 {
 	return nullable_ctx->len;
diff --git a/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c b/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c
index a570e48b917ac..28b939572cdad 100644
--- a/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c
+++ b/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c
@@ -11,7 +11,7 @@ __success __retval(0)
 __naked void btf_ctx_access_accept(void)
 {
 	asm volatile ("					\
-	r2 = *(u32*)(r1 + 8);		/* load 2nd argument value (int pointer) */\
+	r2 = *(u64 *)(r1 + 8);		/* load 2nd argument value (int pointer) */\
 	r0 = 0;						\
 	exit;						\
 "	::: __clobber_all);
@@ -23,7 +23,43 @@ __success __retval(0)
 __naked void ctx_access_u32_pointer_accept(void)
 {
 	asm volatile ("					\
-	r2 = *(u32*)(r1 + 0);		/* load 1nd argument value (u32 pointer) */\
+	r2 = *(u64 *)(r1 + 0);		/* load 1nd argument value (u32 pointer) */\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("fentry/bpf_fentry_test9")
+__description("btf_ctx_access u32 pointer reject u32")
+__failure __msg("size 4 must be 8")
+__naked void ctx_access_u32_pointer_reject_32(void)
+{
+	asm volatile ("					\
+	r2 = *(u32 *)(r1 + 0);		/* load 1st argument with narrow load */\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("fentry/bpf_fentry_test9")
+__description("btf_ctx_access u32 pointer reject u16")
+__failure __msg("size 2 must be 8")
+__naked void ctx_access_u32_pointer_reject_16(void)
+{
+	asm volatile ("					\
+	r2 = *(u16 *)(r1 + 0);		/* load 1st argument with narrow load */\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("fentry/bpf_fentry_test9")
+__description("btf_ctx_access u32 pointer reject u8")
+__failure __msg("size 1 must be 8")
+__naked void ctx_access_u32_pointer_reject_8(void)
+{
+	asm volatile ("					\
+	r2 = *(u8 *)(r1 + 0);		/* load 1st argument with narrow load */\
 	r0 = 0;						\
 	exit;						\
 "	::: __clobber_all);
diff --git a/tools/testing/selftests/bpf/progs/verifier_d_path.c b/tools/testing/selftests/bpf/progs/verifier_d_path.c
index ec79cbcfde91e..87e51a215558f 100644
--- a/tools/testing/selftests/bpf/progs/verifier_d_path.c
+++ b/tools/testing/selftests/bpf/progs/verifier_d_path.c
@@ -11,7 +11,7 @@ __success __retval(0)
 __naked void d_path_accept(void)
 {
 	asm volatile ("					\
-	r1 = *(u32*)(r1 + 0);				\
+	r1 = *(u64 *)(r1 + 0);				\
 	r2 = r10;					\
 	r2 += -8;					\
 	r6 = 0;						\
@@ -31,7 +31,7 @@ __failure __msg("helper call is not allowed in probe")
 __naked void d_path_reject(void)
 {
 	asm volatile ("					\
-	r1 = *(u32*)(r1 + 0);				\
+	r1 = *(u64 *)(r1 + 0);				\
 	r2 = r10;					\
 	r2 += -8;					\
 	r6 = 0;						\
diff --git a/tools/testing/selftests/bpf/progs/verifier_sock.c b/tools/testing/selftests/bpf/progs/verifier_sock.c
index d3e70e38e4420..0d5e56dffabb8 100644
--- a/tools/testing/selftests/bpf/progs/verifier_sock.c
+++ b/tools/testing/selftests/bpf/progs/verifier_sock.c
@@ -50,6 +50,13 @@ struct {
 	__uint(map_flags, BPF_F_NO_PREALLOC);
 } sk_storage_map SEC(".maps");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
 SEC("cgroup/skb")
 __description("skb->sk: no NULL check")
 __failure __msg("invalid mem access 'sock_common_or_null'")
@@ -1037,4 +1044,53 @@ __naked void sock_create_read_src_port(void)
 	: __clobber_all);
 }
 
+__noinline
+long skb_pull_data2(struct __sk_buff *sk, __u32 len)
+{
+	return bpf_skb_pull_data(sk, len);
+}
+
+__noinline
+long skb_pull_data1(struct __sk_buff *sk, __u32 len)
+{
+	return skb_pull_data2(sk, len);
+}
+
+/* global function calls bpf_skb_pull_data(), which invalidates packet
+ * pointers established before global function call.
+ */
+SEC("tc")
+__failure __msg("invalid mem access")
+int invalidate_pkt_pointers_from_global_func(struct __sk_buff *sk)
+{
+	int *p = (void *)(long)sk->data;
+
+	if ((void *)(p + 1) > (void *)(long)sk->data_end)
+		return TCX_DROP;
+	skb_pull_data1(sk, 0);
+	*p = 42; /* this is unsafe */
+	return TCX_PASS;
+}
+
+__noinline
+int tail_call(struct __sk_buff *sk)
+{
+	bpf_tail_call_static(sk, &jmp_table, 0);
+	return 0;
+}
+
+/* Tail calls invalidate packet pointers. */
+SEC("tc")
+__failure __msg("invalid mem access")
+int invalidate_pkt_pointers_by_tail_call(struct __sk_buff *sk)
+{
+	int *p = (void *)(long)sk->data;
+
+	if ((void *)(p + 1) > (void *)(long)sk->data_end)
+		return TCX_DROP;
+	tail_call(sk);
+	*p = 42; /* this is unsafe */
+	return TCX_PASS;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/sdt.h b/tools/testing/selftests/bpf/sdt.h
index ca0162b4dc575..1fcfa5160231d 100644
--- a/tools/testing/selftests/bpf/sdt.h
+++ b/tools/testing/selftests/bpf/sdt.h
@@ -102,6 +102,8 @@
 # define STAP_SDT_ARG_CONSTRAINT        nZr
 # elif defined __arm__
 # define STAP_SDT_ARG_CONSTRAINT        g
+# elif defined __loongarch__
+# define STAP_SDT_ARG_CONSTRAINT        nmr
 # else
 # define STAP_SDT_ARG_CONSTRAINT        nor
 # endif
diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index 2d742fdac6b97..81943c6254e6b 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -293,6 +293,10 @@ static int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *st
 	return 0;
 }
 #else
+# ifndef PROCMAP_QUERY_VMA_EXECUTABLE
+#  define PROCMAP_QUERY_VMA_EXECUTABLE 0x04
+# endif
+
 static int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, size_t *offset, int *flags)
 {
 	return -EOPNOTSUPP;
diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
index 03c1bdaed2c3c..400a696a0d212 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
@@ -86,15 +86,15 @@ echo "" > test/cpuset.cpus
 
 #
 # If isolated CPUs have been reserved at boot time (as shown in
-# cpuset.cpus.isolated), these isolated CPUs should be outside of CPUs 0-7
+# cpuset.cpus.isolated), these isolated CPUs should be outside of CPUs 0-8
 # that will be used by this script for testing purpose. If not, some of
-# the tests may fail incorrectly. These isolated CPUs will also be removed
-# before being compared with the expected results.
+# the tests may fail incorrectly. These pre-isolated CPUs should stay in
+# an isolated state throughout the testing process for now.
 #
 BOOT_ISOLCPUS=$(cat $CGROUP2/cpuset.cpus.isolated)
 if [[ -n "$BOOT_ISOLCPUS" ]]
 then
-	[[ $(echo $BOOT_ISOLCPUS | sed -e "s/[,-].*//") -le 7 ]] &&
+	[[ $(echo $BOOT_ISOLCPUS | sed -e "s/[,-].*//") -le 8 ]] &&
 		skip_test "Pre-isolated CPUs ($BOOT_ISOLCPUS) overlap CPUs to be tested"
 	echo "Pre-isolated CPUs: $BOOT_ISOLCPUS"
 fi
@@ -684,14 +684,18 @@ check_isolcpus()
 	fi
 
 	#
+	# Appending pre-isolated CPUs
+	# Even though CPU #8 isn't used for testing, it can't be pre-isolated
+	# to make appending those CPUs easier.
+	#
+	[[ -n "$BOOT_ISOLCPUS" ]] && {
+		EXPECT_VAL=${EXPECT_VAL:+${EXPECT_VAL},}${BOOT_ISOLCPUS}
+		EXPECT_VAL2=${EXPECT_VAL2:+${EXPECT_VAL2},}${BOOT_ISOLCPUS}
+	}
+
+	#
 	# Check cpuset.cpus.isolated cpumask
 	#
-	if [[ -z "$BOOT_ISOLCPUS" ]]
-	then
-		ISOLCPUS=$(cat $ISCPUS)
-	else
-		ISOLCPUS=$(cat $ISCPUS | sed -e "s/,*$BOOT_ISOLCPUS//")
-	fi
 	[[ "$EXPECT_VAL2" != "$ISOLCPUS" ]] && {
 		# Take a 50ms pause and try again
 		pause 0.05
@@ -731,8 +735,6 @@ check_isolcpus()
 		fi
 	done
 	[[ "$ISOLCPUS" = *- ]] && ISOLCPUS=${ISOLCPUS}$LASTISOLCPU
-	[[ -n "BOOT_ISOLCPUS" ]] &&
-		ISOLCPUS=$(echo $ISOLCPUS | sed -e "s/,*$BOOT_ISOLCPUS//")
 
 	[[ "$EXPECT_VAL" = "$ISOLCPUS" ]]
 }
@@ -836,8 +838,11 @@ run_state_test()
 		# if available
 		[[ -n "$ICPUS" ]] && {
 			check_isolcpus $ICPUS
-			[[ $? -ne 0 ]] && test_fail $I "isolated CPU" \
-				"Expect $ICPUS, get $ISOLCPUS instead"
+			[[ $? -ne 0 ]] && {
+				[[ -n "$BOOT_ISOLCPUS" ]] && ICPUS=${ICPUS},${BOOT_ISOLCPUS}
+				test_fail $I "isolated CPU" \
+					"Expect $ICPUS, get $ISOLCPUS instead"
+			}
 		}
 		reset_cgroup_states
 		#
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh
index 0c47faff9274b..c068e6c2a580e 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh
@@ -22,20 +22,34 @@ SB_ITC=0
 h1_create()
 {
 	simple_if_init $h1 192.0.1.1/24
+	tc qdisc add dev $h1 clsact
+
+	# Add egress filter on $h1 that will guarantee that the packet sent,
+	# will be the only packet being passed to the device.
+	tc filter add dev $h1 egress pref 2 handle 102 matchall action drop
 }
 
 h1_destroy()
 {
+	tc filter del dev $h1 egress pref 2 handle 102 matchall action drop
+	tc qdisc del dev $h1 clsact
 	simple_if_fini $h1 192.0.1.1/24
 }
 
 h2_create()
 {
 	simple_if_init $h2 192.0.1.2/24
+	tc qdisc add dev $h2 clsact
+
+	# Add egress filter on $h2 that will guarantee that the packet sent,
+	# will be the only packet being passed to the device.
+	tc filter add dev $h2 egress pref 1 handle 101 matchall action drop
 }
 
 h2_destroy()
 {
+	tc filter del dev $h2 egress pref 1 handle 101 matchall action drop
+	tc qdisc del dev $h2 clsact
 	simple_if_fini $h2 192.0.1.2/24
 }
 
@@ -101,6 +115,11 @@ port_pool_test()
 	local exp_max_occ=$(devlink_cell_size_get)
 	local max_occ
 
+	tc filter add dev $h1 egress protocol ip pref 1 handle 101 flower \
+		src_mac $h1mac dst_mac $h2mac \
+		src_ip 192.0.1.1 dst_ip 192.0.1.2 \
+		action pass
+
 	devlink sb occupancy clearmax $DEVLINK_DEV
 
 	$MZ $h1 -c 1 -p 10 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \
@@ -109,11 +128,6 @@ port_pool_test()
 	devlink sb occupancy snapshot $DEVLINK_DEV
 
 	RET=0
-	max_occ=$(sb_occ_pool_check $dl_port1 $SB_POOL_ING $exp_max_occ)
-	check_err $? "Expected iPool($SB_POOL_ING) max occupancy to be $exp_max_occ, but got $max_occ"
-	log_test "physical port's($h1) ingress pool"
-
-	RET=0
 	max_occ=$(sb_occ_pool_check $dl_port2 $SB_POOL_ING $exp_max_occ)
 	check_err $? "Expected iPool($SB_POOL_ING) max occupancy to be $exp_max_occ, but got $max_occ"
 	log_test "physical port's($h2) ingress pool"
@@ -122,6 +136,11 @@ port_pool_test()
 	max_occ=$(sb_occ_pool_check $cpu_dl_port $SB_POOL_EGR_CPU $exp_max_occ)
 	check_err $? "Expected ePool($SB_POOL_EGR_CPU) max occupancy to be $exp_max_occ, but got $max_occ"
 	log_test "CPU port's egress pool"
+
+	tc filter del dev $h1 egress protocol ip pref 1 handle 101 flower \
+		src_mac $h1mac dst_mac $h2mac \
+		src_ip 192.0.1.1 dst_ip 192.0.1.2 \
+		action pass
 }
 
 port_tc_ip_test()
@@ -129,6 +148,11 @@ port_tc_ip_test()
 	local exp_max_occ=$(devlink_cell_size_get)
 	local max_occ
 
+	tc filter add dev $h1 egress protocol ip pref 1 handle 101 flower \
+		src_mac $h1mac dst_mac $h2mac \
+		src_ip 192.0.1.1 dst_ip 192.0.1.2 \
+		action pass
+
 	devlink sb occupancy clearmax $DEVLINK_DEV
 
 	$MZ $h1 -c 1 -p 10 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \
@@ -139,17 +163,17 @@ port_tc_ip_test()
 	RET=0
 	max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ)
 	check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ"
-	log_test "physical port's($h1) ingress TC - IP packet"
-
-	RET=0
-	max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ)
-	check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ"
 	log_test "physical port's($h2) ingress TC - IP packet"
 
 	RET=0
 	max_occ=$(sb_occ_etc_check $cpu_dl_port $SB_ITC_CPU_IP $exp_max_occ)
 	check_err $? "Expected egress TC($SB_ITC_CPU_IP) max occupancy to be $exp_max_occ, but got $max_occ"
 	log_test "CPU port's egress TC - IP packet"
+
+	tc filter del dev $h1 egress protocol ip pref 1 handle 101 flower \
+		src_mac $h1mac dst_mac $h2mac \
+		src_ip 192.0.1.1 dst_ip 192.0.1.2 \
+		action pass
 }
 
 port_tc_arp_test()
@@ -157,6 +181,9 @@ port_tc_arp_test()
 	local exp_max_occ=$(devlink_cell_size_get)
 	local max_occ
 
+	tc filter add dev $h1 egress protocol arp pref 1 handle 101 flower \
+		src_mac $h1mac action pass
+
 	devlink sb occupancy clearmax $DEVLINK_DEV
 
 	$MZ $h1 -c 1 -p 10 -a $h1mac -A 192.0.1.1 -t arp -q
@@ -166,17 +193,15 @@ port_tc_arp_test()
 	RET=0
 	max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ)
 	check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ"
-	log_test "physical port's($h1) ingress TC - ARP packet"
-
-	RET=0
-	max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ)
-	check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ"
 	log_test "physical port's($h2) ingress TC - ARP packet"
 
 	RET=0
 	max_occ=$(sb_occ_etc_check $cpu_dl_port $SB_ITC_CPU_ARP $exp_max_occ)
 	check_err $? "Expected egress TC($SB_ITC_IP2ME) max occupancy to be $exp_max_occ, but got $max_occ"
 	log_test "CPU port's egress TC - ARP packet"
+
+	tc filter del dev $h1 egress protocol arp pref 1 handle 101 flower \
+		src_mac $h1mac action pass
 }
 
 setup_prepare()
diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py
index 30f29096e27c2..38303da957ee5 100755
--- a/tools/testing/selftests/drivers/net/queues.py
+++ b/tools/testing/selftests/drivers/net/queues.py
@@ -1,32 +1,37 @@
 #!/usr/bin/env python3
 # SPDX-License-Identifier: GPL-2.0
 
-from lib.py import ksft_run, ksft_exit, ksft_eq, KsftSkipEx
-from lib.py import EthtoolFamily, NetdevFamily
+from lib.py import ksft_disruptive, ksft_exit, ksft_run
+from lib.py import ksft_eq, ksft_raises, KsftSkipEx
+from lib.py import EthtoolFamily, NetdevFamily, NlError
 from lib.py import NetDrvEnv
-from lib.py import cmd
+from lib.py import cmd, defer, ip
+import errno
 import glob
 
 
-def sys_get_queues(ifname) -> int:
-    folders = glob.glob(f'/sys/class/net/{ifname}/queues/rx-*')
+def sys_get_queues(ifname, qtype='rx') -> int:
+    folders = glob.glob(f'/sys/class/net/{ifname}/queues/{qtype}-*')
     return len(folders)
 
 
-def nl_get_queues(cfg, nl):
+def nl_get_queues(cfg, nl, qtype='rx'):
     queues = nl.queue_get({'ifindex': cfg.ifindex}, dump=True)
     if queues:
-        return len([q for q in queues if q['type'] == 'rx'])
+        return len([q for q in queues if q['type'] == qtype])
     return None
 
 
 def get_queues(cfg, nl) -> None:
-    queues = nl_get_queues(cfg, nl)
-    if not queues:
-        raise KsftSkipEx('queue-get not supported by device')
+    snl = NetdevFamily(recv_size=4096)
 
-    expected = sys_get_queues(cfg.dev['ifname'])
-    ksft_eq(queues, expected)
+    for qtype in ['rx', 'tx']:
+        queues = nl_get_queues(cfg, snl, qtype)
+        if not queues:
+            raise KsftSkipEx('queue-get not supported by device')
+
+        expected = sys_get_queues(cfg.dev['ifname'], qtype)
+        ksft_eq(queues, expected)
 
 
 def addremove_queues(cfg, nl) -> None:
@@ -56,9 +61,27 @@ def addremove_queues(cfg, nl) -> None:
     ksft_eq(queues, expected)
 
 
+@ksft_disruptive
+def check_down(cfg, nl) -> None:
+    # Check the NAPI IDs before interface goes down and hides them
+    napis = nl.napi_get({'ifindex': cfg.ifindex}, dump=True)
+
+    ip(f"link set dev {cfg.dev['ifname']} down")
+    defer(ip, f"link set dev {cfg.dev['ifname']} up")
+
+    with ksft_raises(NlError) as cm:
+        nl.queue_get({'ifindex': cfg.ifindex, 'id': 0, 'type': 'rx'})
+    ksft_eq(cm.exception.nl_msg.error, -errno.ENOENT)
+
+    if napis:
+        with ksft_raises(NlError) as cm:
+            nl.napi_get({'id': napis[0]['id']})
+        ksft_eq(cm.exception.nl_msg.error, -errno.ENOENT)
+
+
 def main() -> None:
-    with NetDrvEnv(__file__, queue_count=3) as cfg:
-        ksft_run([get_queues, addremove_queues], args=(cfg, NetdevFamily()))
+    with NetDrvEnv(__file__, queue_count=100) as cfg:
+        ksft_run([get_queues, addremove_queues, check_down], args=(cfg, NetdevFamily()))
     ksft_exit()
 
 
diff --git a/tools/testing/selftests/drivers/net/stats.py b/tools/testing/selftests/drivers/net/stats.py
index 63e3c045a3b25..031ac9def6c01 100755
--- a/tools/testing/selftests/drivers/net/stats.py
+++ b/tools/testing/selftests/drivers/net/stats.py
@@ -110,6 +110,23 @@ def qstat_by_ifindex(cfg) -> None:
             ksft_ge(triple[1][key], triple[0][key], comment="bad key: " + key)
             ksft_ge(triple[2][key], triple[1][key], comment="bad key: " + key)
 
+    # Sanity check the dumps
+    queues = NetdevFamily(recv_size=4096).qstats_get({"scope": "queue"}, dump=True)
+    # Reformat the output into {ifindex: {rx: [id, id, ...], tx: [id, id, ...]}}
+    parsed = {}
+    for entry in queues:
+        ifindex = entry["ifindex"]
+        if ifindex not in parsed:
+            parsed[ifindex] = {"rx":[], "tx": []}
+        parsed[ifindex][entry["queue-type"]].append(entry['queue-id'])
+    # Now, validate
+    for ifindex, queues in parsed.items():
+        for qtype in ['rx', 'tx']:
+            ksft_eq(len(queues[qtype]), len(set(queues[qtype])),
+                    comment="repeated queue keys")
+            ksft_eq(len(queues[qtype]), max(queues[qtype]) + 1,
+                    comment="missing queue keys")
+
     # Test invalid dumps
     # 0 is invalid
     with ksft_raises(NlError) as cm:
@@ -158,7 +175,7 @@ def check_down(cfg) -> None:
 
 
 def main() -> None:
-    with NetDrvEnv(__file__) as cfg:
+    with NetDrvEnv(__file__, queue_count=100) as cfg:
         ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex,
                   check_down],
                  args=(cfg, ))
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
index a16c6a6f6055c..8f1c58f0c2397 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
@@ -111,7 +111,7 @@ check_error 'p vfs_read $arg* ^$arg*'		# DOUBLE_ARGS
 if !grep -q 'kernel return probes support:' README; then
 check_error 'r vfs_read ^$arg*'			# NOFENTRY_ARGS
 fi
-check_error 'p vfs_read+8 ^$arg*'		# NOFENTRY_ARGS
+check_error 'p vfs_read+20 ^$arg*'		# NOFENTRY_ARGS
 check_error 'p vfs_read ^hoge'			# NO_BTFARG
 check_error 'p kfree ^$arg10'			# NO_BTFARG (exceed the number of parameters)
 check_error 'r kfree ^$retval'			# NO_RETVAL
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 7f57abf936e73..1d41a046a7bfd 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -9,3 +9,4 @@
 !config
 !settings
 !Makefile
+!Makefile.kvm
\ No newline at end of file
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 41593d2e7de94..20af35a91d6f0 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -1,347 +1,16 @@
 # SPDX-License-Identifier: GPL-2.0-only
-include ../../../build/Build.include
-
-all:
-
 top_srcdir = ../../../..
 include $(top_srcdir)/scripts/subarch.include
 ARCH            ?= $(SUBARCH)
 
-ifeq ($(ARCH),x86)
-	ARCH_DIR := x86_64
-else ifeq ($(ARCH),arm64)
-	ARCH_DIR := aarch64
-else ifeq ($(ARCH),s390)
-	ARCH_DIR := s390x
-else
-	ARCH_DIR := $(ARCH)
-endif
-
-LIBKVM += lib/assert.c
-LIBKVM += lib/elf.c
-LIBKVM += lib/guest_modes.c
-LIBKVM += lib/io.c
-LIBKVM += lib/kvm_util.c
-LIBKVM += lib/memstress.c
-LIBKVM += lib/guest_sprintf.c
-LIBKVM += lib/rbtree.c
-LIBKVM += lib/sparsebit.c
-LIBKVM += lib/test_util.c
-LIBKVM += lib/ucall_common.c
-LIBKVM += lib/userfaultfd_util.c
-
-LIBKVM_STRING += lib/string_override.c
-
-LIBKVM_x86_64 += lib/x86_64/apic.c
-LIBKVM_x86_64 += lib/x86_64/handlers.S
-LIBKVM_x86_64 += lib/x86_64/hyperv.c
-LIBKVM_x86_64 += lib/x86_64/memstress.c
-LIBKVM_x86_64 += lib/x86_64/pmu.c
-LIBKVM_x86_64 += lib/x86_64/processor.c
-LIBKVM_x86_64 += lib/x86_64/sev.c
-LIBKVM_x86_64 += lib/x86_64/svm.c
-LIBKVM_x86_64 += lib/x86_64/ucall.c
-LIBKVM_x86_64 += lib/x86_64/vmx.c
-
-LIBKVM_aarch64 += lib/aarch64/gic.c
-LIBKVM_aarch64 += lib/aarch64/gic_v3.c
-LIBKVM_aarch64 += lib/aarch64/gic_v3_its.c
-LIBKVM_aarch64 += lib/aarch64/handlers.S
-LIBKVM_aarch64 += lib/aarch64/processor.c
-LIBKVM_aarch64 += lib/aarch64/spinlock.c
-LIBKVM_aarch64 += lib/aarch64/ucall.c
-LIBKVM_aarch64 += lib/aarch64/vgic.c
-
-LIBKVM_s390x += lib/s390x/diag318_test_handler.c
-LIBKVM_s390x += lib/s390x/processor.c
-LIBKVM_s390x += lib/s390x/ucall.c
-LIBKVM_s390x += lib/s390x/facility.c
-
-LIBKVM_riscv += lib/riscv/handlers.S
-LIBKVM_riscv += lib/riscv/processor.c
-LIBKVM_riscv += lib/riscv/ucall.c
-
-# Non-compiled test targets
-TEST_PROGS_x86_64 += x86_64/nx_huge_pages_test.sh
-
-# Compiled test targets
-TEST_GEN_PROGS_x86_64 = x86_64/cpuid_test
-TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test
-TEST_GEN_PROGS_x86_64 += x86_64/dirty_log_page_splitting_test
-TEST_GEN_PROGS_x86_64 += x86_64/feature_msrs_test
-TEST_GEN_PROGS_x86_64 += x86_64/exit_on_emulation_failure_test
-TEST_GEN_PROGS_x86_64 += x86_64/fix_hypercall_test
-TEST_GEN_PROGS_x86_64 += x86_64/hwcr_msr_test
-TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock
-TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
-TEST_GEN_PROGS_x86_64 += x86_64/hyperv_evmcs
-TEST_GEN_PROGS_x86_64 += x86_64/hyperv_extended_hypercalls
-TEST_GEN_PROGS_x86_64 += x86_64/hyperv_features
-TEST_GEN_PROGS_x86_64 += x86_64/hyperv_ipi
-TEST_GEN_PROGS_x86_64 += x86_64/hyperv_svm_test
-TEST_GEN_PROGS_x86_64 += x86_64/hyperv_tlb_flush
-TEST_GEN_PROGS_x86_64 += x86_64/kvm_clock_test
-TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test
-TEST_GEN_PROGS_x86_64 += x86_64/monitor_mwait_test
-TEST_GEN_PROGS_x86_64 += x86_64/nested_exceptions_test
-TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test
-TEST_GEN_PROGS_x86_64 += x86_64/pmu_counters_test
-TEST_GEN_PROGS_x86_64 += x86_64/pmu_event_filter_test
-TEST_GEN_PROGS_x86_64 += x86_64/private_mem_conversions_test
-TEST_GEN_PROGS_x86_64 += x86_64/private_mem_kvm_exits_test
-TEST_GEN_PROGS_x86_64 += x86_64/set_boot_cpu_id
-TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
-TEST_GEN_PROGS_x86_64 += x86_64/smaller_maxphyaddr_emulation_test
-TEST_GEN_PROGS_x86_64 += x86_64/smm_test
-TEST_GEN_PROGS_x86_64 += x86_64/state_test
-TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test
-TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test
-TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test
-TEST_GEN_PROGS_x86_64 += x86_64/svm_nested_shutdown_test
-TEST_GEN_PROGS_x86_64 += x86_64/svm_nested_soft_inject_test
-TEST_GEN_PROGS_x86_64 += x86_64/tsc_scaling_sync
-TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
-TEST_GEN_PROGS_x86_64 += x86_64/ucna_injection_test
-TEST_GEN_PROGS_x86_64 += x86_64/userspace_io_test
-TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test
-TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test
-TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test
-TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test
-TEST_GEN_PROGS_x86_64 += x86_64/vmx_exception_with_invalid_guest_state
-TEST_GEN_PROGS_x86_64 += x86_64/vmx_msrs_test
-TEST_GEN_PROGS_x86_64 += x86_64/vmx_invalid_nested_guest_state
-TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test
-TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
-TEST_GEN_PROGS_x86_64 += x86_64/vmx_nested_tsc_scaling_test
-TEST_GEN_PROGS_x86_64 += x86_64/apic_bus_clock_test
-TEST_GEN_PROGS_x86_64 += x86_64/xapic_ipi_test
-TEST_GEN_PROGS_x86_64 += x86_64/xapic_state_test
-TEST_GEN_PROGS_x86_64 += x86_64/xcr0_cpuid_test
-TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test
-TEST_GEN_PROGS_x86_64 += x86_64/debug_regs
-TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test
-TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_caps_test
-TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test
-TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test
-TEST_GEN_PROGS_x86_64 += x86_64/sev_init2_tests
-TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests
-TEST_GEN_PROGS_x86_64 += x86_64/sev_smoke_test
-TEST_GEN_PROGS_x86_64 += x86_64/amx_test
-TEST_GEN_PROGS_x86_64 += x86_64/max_vcpuid_cap_test
-TEST_GEN_PROGS_x86_64 += x86_64/triple_fault_event_test
-TEST_GEN_PROGS_x86_64 += x86_64/recalc_apic_map_test
-TEST_GEN_PROGS_x86_64 += access_tracking_perf_test
-TEST_GEN_PROGS_x86_64 += coalesced_io_test
-TEST_GEN_PROGS_x86_64 += demand_paging_test
-TEST_GEN_PROGS_x86_64 += dirty_log_test
-TEST_GEN_PROGS_x86_64 += dirty_log_perf_test
-TEST_GEN_PROGS_x86_64 += guest_memfd_test
-TEST_GEN_PROGS_x86_64 += guest_print_test
-TEST_GEN_PROGS_x86_64 += hardware_disable_test
-TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus
-TEST_GEN_PROGS_x86_64 += kvm_page_table_test
-TEST_GEN_PROGS_x86_64 += max_guest_memory_test
-TEST_GEN_PROGS_x86_64 += memslot_modification_stress_test
-TEST_GEN_PROGS_x86_64 += memslot_perf_test
-TEST_GEN_PROGS_x86_64 += rseq_test
-TEST_GEN_PROGS_x86_64 += set_memory_region_test
-TEST_GEN_PROGS_x86_64 += steal_time
-TEST_GEN_PROGS_x86_64 += kvm_binary_stats_test
-TEST_GEN_PROGS_x86_64 += system_counter_offset_test
-TEST_GEN_PROGS_x86_64 += pre_fault_memory_test
-
-# Compiled outputs used by test targets
-TEST_GEN_PROGS_EXTENDED_x86_64 += x86_64/nx_huge_pages_test
-
-TEST_GEN_PROGS_aarch64 += aarch64/aarch32_id_regs
-TEST_GEN_PROGS_aarch64 += aarch64/arch_timer_edge_cases
-TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions
-TEST_GEN_PROGS_aarch64 += aarch64/hypercalls
-TEST_GEN_PROGS_aarch64 += aarch64/mmio_abort
-TEST_GEN_PROGS_aarch64 += aarch64/page_fault_test
-TEST_GEN_PROGS_aarch64 += aarch64/psci_test
-TEST_GEN_PROGS_aarch64 += aarch64/set_id_regs
-TEST_GEN_PROGS_aarch64 += aarch64/smccc_filter
-TEST_GEN_PROGS_aarch64 += aarch64/vcpu_width_config
-TEST_GEN_PROGS_aarch64 += aarch64/vgic_init
-TEST_GEN_PROGS_aarch64 += aarch64/vgic_irq
-TEST_GEN_PROGS_aarch64 += aarch64/vgic_lpi_stress
-TEST_GEN_PROGS_aarch64 += aarch64/vpmu_counter_access
-TEST_GEN_PROGS_aarch64 += aarch64/no-vgic-v3
-TEST_GEN_PROGS_aarch64 += access_tracking_perf_test
-TEST_GEN_PROGS_aarch64 += arch_timer
-TEST_GEN_PROGS_aarch64 += coalesced_io_test
-TEST_GEN_PROGS_aarch64 += demand_paging_test
-TEST_GEN_PROGS_aarch64 += dirty_log_test
-TEST_GEN_PROGS_aarch64 += dirty_log_perf_test
-TEST_GEN_PROGS_aarch64 += guest_print_test
-TEST_GEN_PROGS_aarch64 += get-reg-list
-TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus
-TEST_GEN_PROGS_aarch64 += kvm_page_table_test
-TEST_GEN_PROGS_aarch64 += memslot_modification_stress_test
-TEST_GEN_PROGS_aarch64 += memslot_perf_test
-TEST_GEN_PROGS_aarch64 += rseq_test
-TEST_GEN_PROGS_aarch64 += set_memory_region_test
-TEST_GEN_PROGS_aarch64 += steal_time
-TEST_GEN_PROGS_aarch64 += kvm_binary_stats_test
-
-TEST_GEN_PROGS_s390x = s390x/memop
-TEST_GEN_PROGS_s390x += s390x/resets
-TEST_GEN_PROGS_s390x += s390x/sync_regs_test
-TEST_GEN_PROGS_s390x += s390x/tprot
-TEST_GEN_PROGS_s390x += s390x/cmma_test
-TEST_GEN_PROGS_s390x += s390x/debug_test
-TEST_GEN_PROGS_s390x += s390x/cpumodel_subfuncs_test
-TEST_GEN_PROGS_s390x += s390x/shared_zeropage_test
-TEST_GEN_PROGS_s390x += s390x/ucontrol_test
-TEST_GEN_PROGS_s390x += demand_paging_test
-TEST_GEN_PROGS_s390x += dirty_log_test
-TEST_GEN_PROGS_s390x += guest_print_test
-TEST_GEN_PROGS_s390x += kvm_create_max_vcpus
-TEST_GEN_PROGS_s390x += kvm_page_table_test
-TEST_GEN_PROGS_s390x += rseq_test
-TEST_GEN_PROGS_s390x += set_memory_region_test
-TEST_GEN_PROGS_s390x += kvm_binary_stats_test
-
-TEST_GEN_PROGS_riscv += riscv/sbi_pmu_test
-TEST_GEN_PROGS_riscv += riscv/ebreak_test
-TEST_GEN_PROGS_riscv += arch_timer
-TEST_GEN_PROGS_riscv += coalesced_io_test
-TEST_GEN_PROGS_riscv += demand_paging_test
-TEST_GEN_PROGS_riscv += dirty_log_test
-TEST_GEN_PROGS_riscv += get-reg-list
-TEST_GEN_PROGS_riscv += guest_print_test
-TEST_GEN_PROGS_riscv += kvm_binary_stats_test
-TEST_GEN_PROGS_riscv += kvm_create_max_vcpus
-TEST_GEN_PROGS_riscv += kvm_page_table_test
-TEST_GEN_PROGS_riscv += set_memory_region_test
-TEST_GEN_PROGS_riscv += steal_time
-
-SPLIT_TESTS += arch_timer
-SPLIT_TESTS += get-reg-list
-
-TEST_PROGS += $(TEST_PROGS_$(ARCH_DIR))
-TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(ARCH_DIR))
-TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(ARCH_DIR))
-LIBKVM += $(LIBKVM_$(ARCH_DIR))
-
-OVERRIDE_TARGETS = 1
-
-# lib.mak defines $(OUTPUT), prepends $(OUTPUT)/ to $(TEST_GEN_PROGS), and most
-# importantly defines, i.e. overwrites, $(CC) (unless `make -e` or `make CC=`,
-# which causes the environment variable to override the makefile).
-include ../lib.mk
-
-INSTALL_HDR_PATH = $(top_srcdir)/usr
-LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
-LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include
+ifeq ($(ARCH),$(filter $(ARCH),arm64 s390 riscv x86 x86_64))
+# Top-level selftests allows ARCH=x86_64 :-(
 ifeq ($(ARCH),x86_64)
-LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/x86/include
-else
-LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include
+	ARCH := x86
 endif
-CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
-	-Wno-gnu-variable-sized-type-not-at-end -MD -MP -DCONFIG_64BIT \
-	-fno-builtin-memcmp -fno-builtin-memcpy \
-	-fno-builtin-memset -fno-builtin-strnlen \
-	-fno-stack-protector -fno-PIE -fno-strict-aliasing \
-	-I$(LINUX_TOOL_INCLUDE) -I$(LINUX_TOOL_ARCH_INCLUDE) \
-	-I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(ARCH_DIR) \
-	-I ../rseq -I.. $(EXTRA_CFLAGS) $(KHDR_INCLUDES)
-ifeq ($(ARCH),s390)
-	CFLAGS += -march=z10
-endif
-ifeq ($(ARCH),x86)
-ifeq ($(shell echo "void foo(void) { }" | $(CC) -march=x86-64-v2 -x c - -c -o /dev/null 2>/dev/null; echo "$$?"),0)
-	CFLAGS += -march=x86-64-v2
-endif
-endif
-ifeq ($(ARCH),arm64)
-tools_dir := $(top_srcdir)/tools
-arm64_tools_dir := $(tools_dir)/arch/arm64/tools/
-
-ifneq ($(abs_objdir),)
-arm64_hdr_outdir := $(abs_objdir)/tools/
+include Makefile.kvm
 else
-arm64_hdr_outdir := $(tools_dir)/
-endif
-
-GEN_HDRS := $(arm64_hdr_outdir)arch/arm64/include/generated/
-CFLAGS += -I$(GEN_HDRS)
-
-$(GEN_HDRS): $(wildcard $(arm64_tools_dir)/*)
-	$(MAKE) -C $(arm64_tools_dir) OUTPUT=$(arm64_hdr_outdir)
+# Empty targets for unsupported architectures
+all:
+clean:
 endif
-
-no-pie-option := $(call try-run, echo 'int main(void) { return 0; }' | \
-        $(CC) -Werror $(CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie)
-
-# On s390, build the testcases KVM-enabled
-pgste-option = $(call try-run, echo 'int main(void) { return 0; }' | \
-	$(CC) -Werror -Wl$(comma)--s390-pgste -x c - -o "$$TMP",-Wl$(comma)--s390-pgste)
-
-LDLIBS += -ldl
-LDFLAGS += -pthread $(no-pie-option) $(pgste-option)
-
-LIBKVM_C := $(filter %.c,$(LIBKVM))
-LIBKVM_S := $(filter %.S,$(LIBKVM))
-LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C))
-LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S))
-LIBKVM_STRING_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_STRING))
-LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(LIBKVM_STRING_OBJ)
-SPLIT_TEST_GEN_PROGS := $(patsubst %, $(OUTPUT)/%, $(SPLIT_TESTS))
-SPLIT_TEST_GEN_OBJ := $(patsubst %, $(OUTPUT)/$(ARCH_DIR)/%.o, $(SPLIT_TESTS))
-
-TEST_GEN_OBJ = $(patsubst %, %.o, $(TEST_GEN_PROGS))
-TEST_GEN_OBJ += $(patsubst %, %.o, $(TEST_GEN_PROGS_EXTENDED))
-TEST_DEP_FILES = $(patsubst %.o, %.d, $(TEST_GEN_OBJ))
-TEST_DEP_FILES += $(patsubst %.o, %.d, $(LIBKVM_OBJS))
-TEST_DEP_FILES += $(patsubst %.o, %.d, $(SPLIT_TEST_GEN_OBJ))
--include $(TEST_DEP_FILES)
-
-$(shell mkdir -p $(sort $(OUTPUT)/$(ARCH_DIR) $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ))))
-
-$(filter-out $(SPLIT_TEST_GEN_PROGS), $(TEST_GEN_PROGS)) \
-$(TEST_GEN_PROGS_EXTENDED): %: %.o
-	$(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $< $(LIBKVM_OBJS) $(LDLIBS) -o $@
-$(TEST_GEN_OBJ): $(OUTPUT)/%.o: %.c
-	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
-
-$(SPLIT_TEST_GEN_PROGS): $(OUTPUT)/%: $(OUTPUT)/%.o $(OUTPUT)/$(ARCH_DIR)/%.o
-	$(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $^ $(LDLIBS) -o $@
-$(SPLIT_TEST_GEN_OBJ): $(OUTPUT)/$(ARCH_DIR)/%.o: $(ARCH_DIR)/%.c
-	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
-
-EXTRA_CLEAN += $(GEN_HDRS) \
-	       $(LIBKVM_OBJS) \
-	       $(SPLIT_TEST_GEN_OBJ) \
-	       $(TEST_DEP_FILES) \
-	       $(TEST_GEN_OBJ) \
-	       cscope.*
-
-$(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c $(GEN_HDRS)
-	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
-
-$(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S $(GEN_HDRS)
-	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
-
-# Compile the string overrides as freestanding to prevent the compiler from
-# generating self-referential code, e.g. without "freestanding" the compiler may
-# "optimize" memcmp() by invoking memcmp(), thus causing infinite recursion.
-$(LIBKVM_STRING_OBJ): $(OUTPUT)/%.o: %.c
-	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c -ffreestanding $< -o $@
-
-$(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS))))
-$(SPLIT_TEST_GEN_OBJ): $(GEN_HDRS)
-$(TEST_GEN_PROGS): $(LIBKVM_OBJS)
-$(TEST_GEN_PROGS_EXTENDED): $(LIBKVM_OBJS)
-$(TEST_GEN_OBJ): $(GEN_HDRS)
-
-cscope: include_paths = $(LINUX_TOOL_INCLUDE) $(LINUX_HDR_PATH) include lib ..
-cscope:
-	$(RM) cscope.*
-	(find $(include_paths) -name '*.h' \
-		-exec realpath --relative-base=$(PWD) {} \;; \
-	find . -name '*.c' \
-		-exec realpath --relative-base=$(PWD) {} \;) | sort -u > cscope.files
-	cscope -b
diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm
new file mode 100644
index 0000000000000..4277b983cace5
--- /dev/null
+++ b/tools/testing/selftests/kvm/Makefile.kvm
@@ -0,0 +1,330 @@
+# SPDX-License-Identifier: GPL-2.0-only
+include ../../../build/Build.include
+
+all:
+
+LIBKVM += lib/assert.c
+LIBKVM += lib/elf.c
+LIBKVM += lib/guest_modes.c
+LIBKVM += lib/io.c
+LIBKVM += lib/kvm_util.c
+LIBKVM += lib/memstress.c
+LIBKVM += lib/guest_sprintf.c
+LIBKVM += lib/rbtree.c
+LIBKVM += lib/sparsebit.c
+LIBKVM += lib/test_util.c
+LIBKVM += lib/ucall_common.c
+LIBKVM += lib/userfaultfd_util.c
+
+LIBKVM_STRING += lib/string_override.c
+
+LIBKVM_x86 += lib/x86/apic.c
+LIBKVM_x86 += lib/x86/handlers.S
+LIBKVM_x86 += lib/x86/hyperv.c
+LIBKVM_x86 += lib/x86/memstress.c
+LIBKVM_x86 += lib/x86/pmu.c
+LIBKVM_x86 += lib/x86/processor.c
+LIBKVM_x86 += lib/x86/sev.c
+LIBKVM_x86 += lib/x86/svm.c
+LIBKVM_x86 += lib/x86/ucall.c
+LIBKVM_x86 += lib/x86/vmx.c
+
+LIBKVM_arm64 += lib/arm64/gic.c
+LIBKVM_arm64 += lib/arm64/gic_v3.c
+LIBKVM_arm64 += lib/arm64/gic_v3_its.c
+LIBKVM_arm64 += lib/arm64/handlers.S
+LIBKVM_arm64 += lib/arm64/processor.c
+LIBKVM_arm64 += lib/arm64/spinlock.c
+LIBKVM_arm64 += lib/arm64/ucall.c
+LIBKVM_arm64 += lib/arm64/vgic.c
+
+LIBKVM_s390 += lib/s390/diag318_test_handler.c
+LIBKVM_s390 += lib/s390/processor.c
+LIBKVM_s390 += lib/s390/ucall.c
+LIBKVM_s390 += lib/s390/facility.c
+
+LIBKVM_riscv += lib/riscv/handlers.S
+LIBKVM_riscv += lib/riscv/processor.c
+LIBKVM_riscv += lib/riscv/ucall.c
+
+# Non-compiled test targets
+TEST_PROGS_x86 += x86/nx_huge_pages_test.sh
+
+# Compiled test targets
+TEST_GEN_PROGS_x86 = x86/cpuid_test
+TEST_GEN_PROGS_x86 += x86/cr4_cpuid_sync_test
+TEST_GEN_PROGS_x86 += x86/dirty_log_page_splitting_test
+TEST_GEN_PROGS_x86 += x86/feature_msrs_test
+TEST_GEN_PROGS_x86 += x86/exit_on_emulation_failure_test
+TEST_GEN_PROGS_x86 += x86/fix_hypercall_test
+TEST_GEN_PROGS_x86 += x86/hwcr_msr_test
+TEST_GEN_PROGS_x86 += x86/hyperv_clock
+TEST_GEN_PROGS_x86 += x86/hyperv_cpuid
+TEST_GEN_PROGS_x86 += x86/hyperv_evmcs
+TEST_GEN_PROGS_x86 += x86/hyperv_extended_hypercalls
+TEST_GEN_PROGS_x86 += x86/hyperv_features
+TEST_GEN_PROGS_x86 += x86/hyperv_ipi
+TEST_GEN_PROGS_x86 += x86/hyperv_svm_test
+TEST_GEN_PROGS_x86 += x86/hyperv_tlb_flush
+TEST_GEN_PROGS_x86 += x86/kvm_clock_test
+TEST_GEN_PROGS_x86 += x86/kvm_pv_test
+TEST_GEN_PROGS_x86 += x86/monitor_mwait_test
+TEST_GEN_PROGS_x86 += x86/nested_exceptions_test
+TEST_GEN_PROGS_x86 += x86/platform_info_test
+TEST_GEN_PROGS_x86 += x86/pmu_counters_test
+TEST_GEN_PROGS_x86 += x86/pmu_event_filter_test
+TEST_GEN_PROGS_x86 += x86/private_mem_conversions_test
+TEST_GEN_PROGS_x86 += x86/private_mem_kvm_exits_test
+TEST_GEN_PROGS_x86 += x86/set_boot_cpu_id
+TEST_GEN_PROGS_x86 += x86/set_sregs_test
+TEST_GEN_PROGS_x86 += x86/smaller_maxphyaddr_emulation_test
+TEST_GEN_PROGS_x86 += x86/smm_test
+TEST_GEN_PROGS_x86 += x86/state_test
+TEST_GEN_PROGS_x86 += x86/vmx_preemption_timer_test
+TEST_GEN_PROGS_x86 += x86/svm_vmcall_test
+TEST_GEN_PROGS_x86 += x86/svm_int_ctl_test
+TEST_GEN_PROGS_x86 += x86/svm_nested_shutdown_test
+TEST_GEN_PROGS_x86 += x86/svm_nested_soft_inject_test
+TEST_GEN_PROGS_x86 += x86/tsc_scaling_sync
+TEST_GEN_PROGS_x86 += x86/sync_regs_test
+TEST_GEN_PROGS_x86 += x86/ucna_injection_test
+TEST_GEN_PROGS_x86 += x86/userspace_io_test
+TEST_GEN_PROGS_x86 += x86/userspace_msr_exit_test
+TEST_GEN_PROGS_x86 += x86/vmx_apic_access_test
+TEST_GEN_PROGS_x86 += x86/vmx_close_while_nested_test
+TEST_GEN_PROGS_x86 += x86/vmx_dirty_log_test
+TEST_GEN_PROGS_x86 += x86/vmx_exception_with_invalid_guest_state
+TEST_GEN_PROGS_x86 += x86/vmx_msrs_test
+TEST_GEN_PROGS_x86 += x86/vmx_invalid_nested_guest_state
+TEST_GEN_PROGS_x86 += x86/vmx_set_nested_state_test
+TEST_GEN_PROGS_x86 += x86/vmx_tsc_adjust_test
+TEST_GEN_PROGS_x86 += x86/vmx_nested_tsc_scaling_test
+TEST_GEN_PROGS_x86 += x86/apic_bus_clock_test
+TEST_GEN_PROGS_x86 += x86/xapic_ipi_test
+TEST_GEN_PROGS_x86 += x86/xapic_state_test
+TEST_GEN_PROGS_x86 += x86/xcr0_cpuid_test
+TEST_GEN_PROGS_x86 += x86/xss_msr_test
+TEST_GEN_PROGS_x86 += x86/debug_regs
+TEST_GEN_PROGS_x86 += x86/tsc_msrs_test
+TEST_GEN_PROGS_x86 += x86/vmx_pmu_caps_test
+TEST_GEN_PROGS_x86 += x86/xen_shinfo_test
+TEST_GEN_PROGS_x86 += x86/xen_vmcall_test
+TEST_GEN_PROGS_x86 += x86/sev_init2_tests
+TEST_GEN_PROGS_x86 += x86/sev_migrate_tests
+TEST_GEN_PROGS_x86 += x86/sev_smoke_test
+TEST_GEN_PROGS_x86 += x86/amx_test
+TEST_GEN_PROGS_x86 += x86/max_vcpuid_cap_test
+TEST_GEN_PROGS_x86 += x86/triple_fault_event_test
+TEST_GEN_PROGS_x86 += x86/recalc_apic_map_test
+TEST_GEN_PROGS_x86 += access_tracking_perf_test
+TEST_GEN_PROGS_x86 += coalesced_io_test
+TEST_GEN_PROGS_x86 += demand_paging_test
+TEST_GEN_PROGS_x86 += dirty_log_test
+TEST_GEN_PROGS_x86 += dirty_log_perf_test
+TEST_GEN_PROGS_x86 += guest_memfd_test
+TEST_GEN_PROGS_x86 += guest_print_test
+TEST_GEN_PROGS_x86 += hardware_disable_test
+TEST_GEN_PROGS_x86 += kvm_create_max_vcpus
+TEST_GEN_PROGS_x86 += kvm_page_table_test
+TEST_GEN_PROGS_x86 += memslot_modification_stress_test
+TEST_GEN_PROGS_x86 += memslot_perf_test
+TEST_GEN_PROGS_x86 += mmu_stress_test
+TEST_GEN_PROGS_x86 += rseq_test
+TEST_GEN_PROGS_x86 += set_memory_region_test
+TEST_GEN_PROGS_x86 += steal_time
+TEST_GEN_PROGS_x86 += kvm_binary_stats_test
+TEST_GEN_PROGS_x86 += system_counter_offset_test
+TEST_GEN_PROGS_x86 += pre_fault_memory_test
+
+# Compiled outputs used by test targets
+TEST_GEN_PROGS_EXTENDED_x86 += x86/nx_huge_pages_test
+
+TEST_GEN_PROGS_arm64 += arm64/aarch32_id_regs
+TEST_GEN_PROGS_arm64 += arm64/arch_timer_edge_cases
+TEST_GEN_PROGS_arm64 += arm64/debug-exceptions
+TEST_GEN_PROGS_arm64 += arm64/hypercalls
+TEST_GEN_PROGS_arm64 += arm64/mmio_abort
+TEST_GEN_PROGS_arm64 += arm64/page_fault_test
+TEST_GEN_PROGS_arm64 += arm64/psci_test
+TEST_GEN_PROGS_arm64 += arm64/set_id_regs
+TEST_GEN_PROGS_arm64 += arm64/smccc_filter
+TEST_GEN_PROGS_arm64 += arm64/vcpu_width_config
+TEST_GEN_PROGS_arm64 += arm64/vgic_init
+TEST_GEN_PROGS_arm64 += arm64/vgic_irq
+TEST_GEN_PROGS_arm64 += arm64/vgic_lpi_stress
+TEST_GEN_PROGS_arm64 += arm64/vpmu_counter_access
+TEST_GEN_PROGS_arm64 += arm64/no-vgic-v3
+TEST_GEN_PROGS_arm64 += access_tracking_perf_test
+TEST_GEN_PROGS_arm64 += arch_timer
+TEST_GEN_PROGS_arm64 += coalesced_io_test
+TEST_GEN_PROGS_arm64 += demand_paging_test
+TEST_GEN_PROGS_arm64 += dirty_log_test
+TEST_GEN_PROGS_arm64 += dirty_log_perf_test
+TEST_GEN_PROGS_arm64 += guest_print_test
+TEST_GEN_PROGS_arm64 += get-reg-list
+TEST_GEN_PROGS_arm64 += kvm_create_max_vcpus
+TEST_GEN_PROGS_arm64 += kvm_page_table_test
+TEST_GEN_PROGS_arm64 += memslot_modification_stress_test
+TEST_GEN_PROGS_arm64 += memslot_perf_test
+TEST_GEN_PROGS_arm64 += mmu_stress_test
+TEST_GEN_PROGS_arm64 += rseq_test
+TEST_GEN_PROGS_arm64 += set_memory_region_test
+TEST_GEN_PROGS_arm64 += steal_time
+TEST_GEN_PROGS_arm64 += kvm_binary_stats_test
+
+TEST_GEN_PROGS_s390 = s390/memop
+TEST_GEN_PROGS_s390 += s390/resets
+TEST_GEN_PROGS_s390 += s390/sync_regs_test
+TEST_GEN_PROGS_s390 += s390/tprot
+TEST_GEN_PROGS_s390 += s390/cmma_test
+TEST_GEN_PROGS_s390 += s390/debug_test
+TEST_GEN_PROGS_s390 += s390/cpumodel_subfuncs_test
+TEST_GEN_PROGS_s390 += s390/shared_zeropage_test
+TEST_GEN_PROGS_s390 += s390/ucontrol_test
+TEST_GEN_PROGS_s390 += demand_paging_test
+TEST_GEN_PROGS_s390 += dirty_log_test
+TEST_GEN_PROGS_s390 += guest_print_test
+TEST_GEN_PROGS_s390 += kvm_create_max_vcpus
+TEST_GEN_PROGS_s390 += kvm_page_table_test
+TEST_GEN_PROGS_s390 += rseq_test
+TEST_GEN_PROGS_s390 += set_memory_region_test
+TEST_GEN_PROGS_s390 += kvm_binary_stats_test
+
+TEST_GEN_PROGS_riscv += riscv/sbi_pmu_test
+TEST_GEN_PROGS_riscv += riscv/ebreak_test
+TEST_GEN_PROGS_riscv += arch_timer
+TEST_GEN_PROGS_riscv += coalesced_io_test
+TEST_GEN_PROGS_riscv += demand_paging_test
+TEST_GEN_PROGS_riscv += dirty_log_test
+TEST_GEN_PROGS_riscv += get-reg-list
+TEST_GEN_PROGS_riscv += guest_print_test
+TEST_GEN_PROGS_riscv += kvm_binary_stats_test
+TEST_GEN_PROGS_riscv += kvm_create_max_vcpus
+TEST_GEN_PROGS_riscv += kvm_page_table_test
+TEST_GEN_PROGS_riscv += set_memory_region_test
+TEST_GEN_PROGS_riscv += steal_time
+
+SPLIT_TESTS += arch_timer
+SPLIT_TESTS += get-reg-list
+
+TEST_PROGS += $(TEST_PROGS_$(ARCH))
+TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(ARCH))
+TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(ARCH))
+LIBKVM += $(LIBKVM_$(ARCH))
+
+OVERRIDE_TARGETS = 1
+
+# lib.mak defines $(OUTPUT), prepends $(OUTPUT)/ to $(TEST_GEN_PROGS), and most
+# importantly defines, i.e. overwrites, $(CC) (unless `make -e` or `make CC=`,
+# which causes the environment variable to override the makefile).
+include ../lib.mk
+
+INSTALL_HDR_PATH = $(top_srcdir)/usr
+LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
+LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include
+LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include
+CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
+	-Wno-gnu-variable-sized-type-not-at-end -MD -MP -DCONFIG_64BIT \
+	-fno-builtin-memcmp -fno-builtin-memcpy \
+	-fno-builtin-memset -fno-builtin-strnlen \
+	-fno-stack-protector -fno-PIE -fno-strict-aliasing \
+	-I$(LINUX_TOOL_INCLUDE) -I$(LINUX_TOOL_ARCH_INCLUDE) \
+	-I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(ARCH) \
+	-I ../rseq -I.. $(EXTRA_CFLAGS) $(KHDR_INCLUDES)
+ifeq ($(ARCH),s390)
+	CFLAGS += -march=z10
+endif
+ifeq ($(ARCH),x86)
+ifeq ($(shell echo "void foo(void) { }" | $(CC) -march=x86-64-v2 -x c - -c -o /dev/null 2>/dev/null; echo "$$?"),0)
+	CFLAGS += -march=x86-64-v2
+endif
+endif
+ifeq ($(ARCH),arm64)
+tools_dir := $(top_srcdir)/tools
+arm64_tools_dir := $(tools_dir)/arch/arm64/tools/
+
+ifneq ($(abs_objdir),)
+arm64_hdr_outdir := $(abs_objdir)/tools/
+else
+arm64_hdr_outdir := $(tools_dir)/
+endif
+
+GEN_HDRS := $(arm64_hdr_outdir)arch/arm64/include/generated/
+CFLAGS += -I$(GEN_HDRS)
+
+$(GEN_HDRS): $(wildcard $(arm64_tools_dir)/*)
+	$(MAKE) -C $(arm64_tools_dir) OUTPUT=$(arm64_hdr_outdir)
+endif
+
+no-pie-option := $(call try-run, echo 'int main(void) { return 0; }' | \
+        $(CC) -Werror $(CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie)
+
+# On s390, build the testcases KVM-enabled
+pgste-option = $(call try-run, echo 'int main(void) { return 0; }' | \
+	$(CC) -Werror -Wl$(comma)--s390-pgste -x c - -o "$$TMP",-Wl$(comma)--s390-pgste)
+
+LDLIBS += -ldl
+LDFLAGS += -pthread $(no-pie-option) $(pgste-option)
+
+LIBKVM_C := $(filter %.c,$(LIBKVM))
+LIBKVM_S := $(filter %.S,$(LIBKVM))
+LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C))
+LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S))
+LIBKVM_STRING_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_STRING))
+LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(LIBKVM_STRING_OBJ)
+SPLIT_TEST_GEN_PROGS := $(patsubst %, $(OUTPUT)/%, $(SPLIT_TESTS))
+SPLIT_TEST_GEN_OBJ := $(patsubst %, $(OUTPUT)/$(ARCH)/%.o, $(SPLIT_TESTS))
+
+TEST_GEN_OBJ = $(patsubst %, %.o, $(TEST_GEN_PROGS))
+TEST_GEN_OBJ += $(patsubst %, %.o, $(TEST_GEN_PROGS_EXTENDED))
+TEST_DEP_FILES = $(patsubst %.o, %.d, $(TEST_GEN_OBJ))
+TEST_DEP_FILES += $(patsubst %.o, %.d, $(LIBKVM_OBJS))
+TEST_DEP_FILES += $(patsubst %.o, %.d, $(SPLIT_TEST_GEN_OBJ))
+-include $(TEST_DEP_FILES)
+
+$(shell mkdir -p $(sort $(OUTPUT)/$(ARCH) $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ))))
+
+$(filter-out $(SPLIT_TEST_GEN_PROGS), $(TEST_GEN_PROGS)) \
+$(TEST_GEN_PROGS_EXTENDED): %: %.o
+	$(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $< $(LIBKVM_OBJS) $(LDLIBS) -o $@
+$(TEST_GEN_OBJ): $(OUTPUT)/%.o: %.c
+	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
+
+$(SPLIT_TEST_GEN_PROGS): $(OUTPUT)/%: $(OUTPUT)/%.o $(OUTPUT)/$(ARCH)/%.o
+	$(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $^ $(LDLIBS) -o $@
+$(SPLIT_TEST_GEN_OBJ): $(OUTPUT)/$(ARCH)/%.o: $(ARCH)/%.c
+	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
+
+EXTRA_CLEAN += $(GEN_HDRS) \
+	       $(LIBKVM_OBJS) \
+	       $(SPLIT_TEST_GEN_OBJ) \
+	       $(TEST_DEP_FILES) \
+	       $(TEST_GEN_OBJ) \
+	       cscope.*
+
+$(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c $(GEN_HDRS)
+	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
+
+$(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S $(GEN_HDRS)
+	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
+
+# Compile the string overrides as freestanding to prevent the compiler from
+# generating self-referential code, e.g. without "freestanding" the compiler may
+# "optimize" memcmp() by invoking memcmp(), thus causing infinite recursion.
+$(LIBKVM_STRING_OBJ): $(OUTPUT)/%.o: %.c
+	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c -ffreestanding $< -o $@
+
+$(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS))))
+$(SPLIT_TEST_GEN_OBJ): $(GEN_HDRS)
+$(TEST_GEN_PROGS): $(LIBKVM_OBJS)
+$(TEST_GEN_PROGS_EXTENDED): $(LIBKVM_OBJS)
+$(TEST_GEN_OBJ): $(GEN_HDRS)
+
+cscope: include_paths = $(LINUX_TOOL_INCLUDE) $(LINUX_HDR_PATH) include lib ..
+cscope:
+	$(RM) cscope.*
+	(find $(include_paths) -name '*.h' \
+		-exec realpath --relative-base=$(PWD) {} \;; \
+	find . -name '*.c' \
+		-exec realpath --relative-base=$(PWD) {} \;) | sort -u > cscope.files
+	cscope -b
diff --git a/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c b/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c
index 8e5bd07a3727c..447d61cae4db1 100644
--- a/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c
+++ b/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c
@@ -97,7 +97,7 @@ static void test_user_raz_wi(struct kvm_vcpu *vcpu)
 		uint64_t reg_id = raz_wi_reg_ids[i];
 		uint64_t val;
 
-		vcpu_get_reg(vcpu, reg_id, &val);
+		val = vcpu_get_reg(vcpu, reg_id);
 		TEST_ASSERT_EQ(val, 0);
 
 		/*
@@ -106,7 +106,7 @@ static void test_user_raz_wi(struct kvm_vcpu *vcpu)
 		 */
 		vcpu_set_reg(vcpu, reg_id, BAD_ID_REG_VAL);
 
-		vcpu_get_reg(vcpu, reg_id, &val);
+		val = vcpu_get_reg(vcpu, reg_id);
 		TEST_ASSERT_EQ(val, 0);
 	}
 }
@@ -126,14 +126,14 @@ static void test_user_raz_invariant(struct kvm_vcpu *vcpu)
 		uint64_t reg_id = raz_invariant_reg_ids[i];
 		uint64_t val;
 
-		vcpu_get_reg(vcpu, reg_id, &val);
+		val = vcpu_get_reg(vcpu, reg_id);
 		TEST_ASSERT_EQ(val, 0);
 
 		r = __vcpu_set_reg(vcpu, reg_id, BAD_ID_REG_VAL);
 		TEST_ASSERT(r < 0 && errno == EINVAL,
 			    "unexpected KVM_SET_ONE_REG error: r=%d, errno=%d", r, errno);
 
-		vcpu_get_reg(vcpu, reg_id, &val);
+		val = vcpu_get_reg(vcpu, reg_id);
 		TEST_ASSERT_EQ(val, 0);
 	}
 }
@@ -144,7 +144,7 @@ static bool vcpu_aarch64_only(struct kvm_vcpu *vcpu)
 {
 	uint64_t val, el0;
 
-	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1), &val);
+	val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1));
 
 	el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), val);
 	return el0 == ID_AA64PFR0_EL1_ELx_64BIT_ONLY;
diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/arm64/arch_timer.c
index eeba1cc87ff82..eeba1cc87ff82 100644
--- a/tools/testing/selftests/kvm/aarch64/arch_timer.c
+++ b/tools/testing/selftests/kvm/arm64/arch_timer.c
diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer_edge_cases.c b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c
index a36a7e2db434b..a36a7e2db434b 100644
--- a/tools/testing/selftests/kvm/aarch64/arch_timer_edge_cases.c
+++ b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c
diff --git a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c b/tools/testing/selftests/kvm/arm64/debug-exceptions.c
index ff7a949fc96ad..c7fb55c9135ba 100644
--- a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
+++ b/tools/testing/selftests/kvm/arm64/debug-exceptions.c
@@ -501,7 +501,7 @@ void test_single_step_from_userspace(int test_cnt)
 		TEST_ASSERT(ss_enable, "Unexpected KVM_EXIT_DEBUG");
 
 		/* Check if the current pc is expected. */
-		vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc), &pc);
+		pc = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc));
 		TEST_ASSERT(!test_pc || pc == test_pc,
 			    "Unexpected pc 0x%lx (expected 0x%lx)",
 			    pc, test_pc);
@@ -583,7 +583,7 @@ int main(int argc, char *argv[])
 	uint64_t aa64dfr0;
 
 	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
-	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1), &aa64dfr0);
+	aa64dfr0 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1));
 	__TEST_REQUIRE(debug_version(aa64dfr0) >= 6,
 		       "Armv8 debug architecture not supported.");
 	kvm_vm_free(vm);
diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/arm64/get-reg-list.c
index d43fb3f49050b..d43fb3f49050b 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/arm64/get-reg-list.c
diff --git a/tools/testing/selftests/kvm/aarch64/hypercalls.c b/tools/testing/selftests/kvm/arm64/hypercalls.c
index 9d192ce0078d6..ec54ec7726e9c 100644
--- a/tools/testing/selftests/kvm/aarch64/hypercalls.c
+++ b/tools/testing/selftests/kvm/arm64/hypercalls.c
@@ -173,7 +173,7 @@ static void test_fw_regs_before_vm_start(struct kvm_vcpu *vcpu)
 		const struct kvm_fw_reg_info *reg_info = &fw_reg_info[i];
 
 		/* First 'read' should be an upper limit of the features supported */
-		vcpu_get_reg(vcpu, reg_info->reg, &val);
+		val = vcpu_get_reg(vcpu, reg_info->reg);
 		TEST_ASSERT(val == FW_REG_ULIMIT_VAL(reg_info->max_feat_bit),
 			"Expected all the features to be set for reg: 0x%lx; expected: 0x%lx; read: 0x%lx",
 			reg_info->reg, FW_REG_ULIMIT_VAL(reg_info->max_feat_bit), val);
@@ -184,7 +184,7 @@ static void test_fw_regs_before_vm_start(struct kvm_vcpu *vcpu)
 			"Failed to clear all the features of reg: 0x%lx; ret: %d",
 			reg_info->reg, errno);
 
-		vcpu_get_reg(vcpu, reg_info->reg, &val);
+		val = vcpu_get_reg(vcpu, reg_info->reg);
 		TEST_ASSERT(val == 0,
 			"Expected all the features to be cleared for reg: 0x%lx", reg_info->reg);
 
@@ -214,7 +214,7 @@ static void test_fw_regs_after_vm_start(struct kvm_vcpu *vcpu)
 		 * Before starting the VM, the test clears all the bits.
 		 * Check if that's still the case.
 		 */
-		vcpu_get_reg(vcpu, reg_info->reg, &val);
+		val = vcpu_get_reg(vcpu, reg_info->reg);
 		TEST_ASSERT(val == 0,
 			"Expected all the features to be cleared for reg: 0x%lx",
 			reg_info->reg);
diff --git a/tools/testing/selftests/kvm/aarch64/mmio_abort.c b/tools/testing/selftests/kvm/arm64/mmio_abort.c
index 8b7a80a51b1c4..8b7a80a51b1c4 100644
--- a/tools/testing/selftests/kvm/aarch64/mmio_abort.c
+++ b/tools/testing/selftests/kvm/arm64/mmio_abort.c
diff --git a/tools/testing/selftests/kvm/aarch64/no-vgic-v3.c b/tools/testing/selftests/kvm/arm64/no-vgic-v3.c
index 58304bbc2036a..ebd70430c89de 100644
--- a/tools/testing/selftests/kvm/aarch64/no-vgic-v3.c
+++ b/tools/testing/selftests/kvm/arm64/no-vgic-v3.c
@@ -164,7 +164,7 @@ int main(int argc, char *argv[])
 	uint64_t pfr0;
 
 	vm = vm_create_with_one_vcpu(&vcpu, NULL);
-	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1), &pfr0);
+	pfr0 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1));
 	__TEST_REQUIRE(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_GIC), pfr0),
 		       "GICv3 not supported.");
 	kvm_vm_free(vm);
diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/arm64/page_fault_test.c
index ec33a8f9c908c..ec33a8f9c908c 100644
--- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c
+++ b/tools/testing/selftests/kvm/arm64/page_fault_test.c
diff --git a/tools/testing/selftests/kvm/aarch64/psci_test.c b/tools/testing/selftests/kvm/arm64/psci_test.c
index eaa7655fefc12..ab491ee9e5f75 100644
--- a/tools/testing/selftests/kvm/aarch64/psci_test.c
+++ b/tools/testing/selftests/kvm/arm64/psci_test.c
@@ -111,8 +111,8 @@ static void assert_vcpu_reset(struct kvm_vcpu *vcpu)
 {
 	uint64_t obs_pc, obs_x0;
 
-	vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc), &obs_pc);
-	vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.regs[0]), &obs_x0);
+	obs_pc = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc));
+	obs_x0 = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.regs[0]));
 
 	TEST_ASSERT(obs_pc == CPU_ON_ENTRY_ADDR,
 		    "unexpected target cpu pc: %lx (expected: %lx)",
@@ -152,7 +152,7 @@ static void host_test_cpu_on(void)
 	 */
 	vcpu_power_off(target);
 
-	vcpu_get_reg(target, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1), &target_mpidr);
+	target_mpidr = vcpu_get_reg(target, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1));
 	vcpu_args_set(source, 1, target_mpidr & MPIDR_HWID_BITMASK);
 	enter_guest(source);
 
@@ -244,7 +244,7 @@ static void host_test_system_off2(void)
 
 	setup_vm(guest_test_system_off2, &source, &target);
 
-	vcpu_get_reg(target, KVM_REG_ARM_PSCI_VERSION, &psci_version);
+	psci_version = vcpu_get_reg(target, KVM_REG_ARM_PSCI_VERSION);
 
 	TEST_ASSERT(psci_version >= PSCI_VERSION(1, 3),
 		    "Unexpected PSCI version %lu.%lu",
diff --git a/tools/testing/selftests/kvm/aarch64/set_id_regs.c b/tools/testing/selftests/kvm/arm64/set_id_regs.c
index a79b7f18452d2..3dd85ce8551c6 100644
--- a/tools/testing/selftests/kvm/aarch64/set_id_regs.c
+++ b/tools/testing/selftests/kvm/arm64/set_id_regs.c
@@ -152,7 +152,6 @@ static const struct reg_ftr_bits ftr_id_aa64mmfr0_el1[] = {
 	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, BIGENDEL0, 0),
 	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, SNSMEM, 0),
 	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, BIGEND, 0),
-	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, ASIDBITS, 0),
 	REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, PARANGE, 0),
 	REG_FTR_END,
 };
@@ -346,7 +345,7 @@ static uint64_t test_reg_set_success(struct kvm_vcpu *vcpu, uint64_t reg,
 	uint64_t mask = ftr_bits->mask;
 	uint64_t val, new_val, ftr;
 
-	vcpu_get_reg(vcpu, reg, &val);
+	val = vcpu_get_reg(vcpu, reg);
 	ftr = (val & mask) >> shift;
 
 	ftr = get_safe_value(ftr_bits, ftr);
@@ -356,7 +355,7 @@ static uint64_t test_reg_set_success(struct kvm_vcpu *vcpu, uint64_t reg,
 	val |= ftr;
 
 	vcpu_set_reg(vcpu, reg, val);
-	vcpu_get_reg(vcpu, reg, &new_val);
+	new_val = vcpu_get_reg(vcpu, reg);
 	TEST_ASSERT_EQ(new_val, val);
 
 	return new_val;
@@ -370,7 +369,7 @@ static void test_reg_set_fail(struct kvm_vcpu *vcpu, uint64_t reg,
 	uint64_t val, old_val, ftr;
 	int r;
 
-	vcpu_get_reg(vcpu, reg, &val);
+	val = vcpu_get_reg(vcpu, reg);
 	ftr = (val & mask) >> shift;
 
 	ftr = get_invalid_value(ftr_bits, ftr);
@@ -384,7 +383,7 @@ static void test_reg_set_fail(struct kvm_vcpu *vcpu, uint64_t reg,
 	TEST_ASSERT(r < 0 && errno == EINVAL,
 		    "Unexpected KVM_SET_ONE_REG error: r=%d, errno=%d", r, errno);
 
-	vcpu_get_reg(vcpu, reg, &val);
+	val = vcpu_get_reg(vcpu, reg);
 	TEST_ASSERT_EQ(val, old_val);
 }
 
@@ -471,7 +470,7 @@ static void test_user_set_mpam_reg(struct kvm_vcpu *vcpu)
 	}
 
 	/* Get the id register value */
-	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1), &val);
+	val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1));
 
 	/* Try to set MPAM=0. This should always be possible. */
 	val &= ~ID_AA64PFR0_EL1_MPAM_MASK;
@@ -508,7 +507,7 @@ static void test_user_set_mpam_reg(struct kvm_vcpu *vcpu)
 	}
 
 	/* Get the id register value */
-	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR1_EL1), &val);
+	val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR1_EL1));
 
 	/* Try to set MPAM_frac=0. This should always be possible. */
 	val &= ~ID_AA64PFR1_EL1_MPAM_frac_MASK;
@@ -576,7 +575,7 @@ static void test_clidr(struct kvm_vcpu *vcpu)
 	uint64_t clidr;
 	int level;
 
-	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CLIDR_EL1), &clidr);
+	clidr = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CLIDR_EL1));
 
 	/* find the first empty level in the cache hierarchy */
 	for (level = 1; level < 7; level++) {
@@ -601,7 +600,7 @@ static void test_ctr(struct kvm_vcpu *vcpu)
 {
 	u64 ctr;
 
-	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CTR_EL0), &ctr);
+	ctr = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CTR_EL0));
 	ctr &= ~CTR_EL0_DIC_MASK;
 	if (ctr & CTR_EL0_IminLine_MASK)
 		ctr--;
@@ -617,7 +616,7 @@ static void test_vcpu_ftr_id_regs(struct kvm_vcpu *vcpu)
 	test_clidr(vcpu);
 	test_ctr(vcpu);
 
-	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1), &val);
+	val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1));
 	val++;
 	vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1), val);
 
@@ -630,7 +629,7 @@ static void test_assert_id_reg_unchanged(struct kvm_vcpu *vcpu, uint32_t encodin
 	size_t idx = encoding_to_range_idx(encoding);
 	uint64_t observed;
 
-	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(encoding), &observed);
+	observed = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(encoding));
 	TEST_ASSERT_EQ(test_reg_vals[idx], observed);
 }
 
@@ -665,7 +664,7 @@ int main(void)
 	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
 
 	/* Check for AARCH64 only system */
-	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1), &val);
+	val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1));
 	el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), val);
 	aarch64_only = (el0 == ID_AA64PFR0_EL1_ELx_64BIT_ONLY);
 
diff --git a/tools/testing/selftests/kvm/aarch64/smccc_filter.c b/tools/testing/selftests/kvm/arm64/smccc_filter.c
index 2d189f3da228c..2d189f3da228c 100644
--- a/tools/testing/selftests/kvm/aarch64/smccc_filter.c
+++ b/tools/testing/selftests/kvm/arm64/smccc_filter.c
diff --git a/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c b/tools/testing/selftests/kvm/arm64/vcpu_width_config.c
index 80b74c6f152b8..80b74c6f152b8 100644
--- a/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c
+++ b/tools/testing/selftests/kvm/arm64/vcpu_width_config.c
diff --git a/tools/testing/selftests/kvm/aarch64/vgic_init.c b/tools/testing/selftests/kvm/arm64/vgic_init.c
index b3b5fb0ff0a9a..b3b5fb0ff0a9a 100644
--- a/tools/testing/selftests/kvm/aarch64/vgic_init.c
+++ b/tools/testing/selftests/kvm/arm64/vgic_init.c
diff --git a/tools/testing/selftests/kvm/aarch64/vgic_irq.c b/tools/testing/selftests/kvm/arm64/vgic_irq.c
index f4ac28d537473..f4ac28d537473 100644
--- a/tools/testing/selftests/kvm/aarch64/vgic_irq.c
+++ b/tools/testing/selftests/kvm/arm64/vgic_irq.c
diff --git a/tools/testing/selftests/kvm/aarch64/vgic_lpi_stress.c b/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c
index fc4fe52fb6f84..fc4fe52fb6f84 100644
--- a/tools/testing/selftests/kvm/aarch64/vgic_lpi_stress.c
+++ b/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c
diff --git a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c b/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c
index f9c0c86d7e854..f16b3b27e32ed 100644
--- a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c
+++ b/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c
@@ -440,8 +440,7 @@ static void create_vpmu_vm(void *guest_code)
 		       "Failed to create vgic-v3, skipping");
 
 	/* Make sure that PMUv3 support is indicated in the ID register */
-	vcpu_get_reg(vpmu_vm.vcpu,
-		     KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1), &dfr0);
+	dfr0 = vcpu_get_reg(vpmu_vm.vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1));
 	pmuver = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), dfr0);
 	TEST_ASSERT(pmuver != ID_AA64DFR0_EL1_PMUVer_IMP_DEF &&
 		    pmuver >= ID_AA64DFR0_EL1_PMUVer_IMP,
@@ -484,7 +483,7 @@ static void test_create_vpmu_vm_with_pmcr_n(uint64_t pmcr_n, bool expect_fail)
 	create_vpmu_vm(guest_code);
 	vcpu = vpmu_vm.vcpu;
 
-	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), &pmcr_orig);
+	pmcr_orig = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0));
 	pmcr = pmcr_orig;
 
 	/*
@@ -493,7 +492,7 @@ static void test_create_vpmu_vm_with_pmcr_n(uint64_t pmcr_n, bool expect_fail)
 	 */
 	set_pmcr_n(&pmcr, pmcr_n);
 	vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), pmcr);
-	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), &pmcr);
+	pmcr = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0));
 
 	if (expect_fail)
 		TEST_ASSERT(pmcr_orig == pmcr,
@@ -521,7 +520,7 @@ static void run_access_test(uint64_t pmcr_n)
 	vcpu = vpmu_vm.vcpu;
 
 	/* Save the initial sp to restore them later to run the guest again */
-	vcpu_get_reg(vcpu, ARM64_CORE_REG(sp_el1), &sp);
+	sp = vcpu_get_reg(vcpu, ARM64_CORE_REG(sp_el1));
 
 	run_vcpu(vcpu, pmcr_n);
 
@@ -572,12 +571,12 @@ static void run_pmregs_validity_test(uint64_t pmcr_n)
 		 * Test if the 'set' and 'clr' variants of the registers
 		 * are initialized based on the number of valid counters.
 		 */
-		vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), &reg_val);
+		reg_val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id));
 		TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
 			    "Initial read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx",
 			    KVM_ARM64_SYS_REG(set_reg_id), reg_val);
 
-		vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id), &reg_val);
+		reg_val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id));
 		TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
 			    "Initial read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx",
 			    KVM_ARM64_SYS_REG(clr_reg_id), reg_val);
@@ -589,12 +588,12 @@ static void run_pmregs_validity_test(uint64_t pmcr_n)
 		 */
 		vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), max_counters_mask);
 
-		vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), &reg_val);
+		reg_val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id));
 		TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
 			    "Read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx",
 			    KVM_ARM64_SYS_REG(set_reg_id), reg_val);
 
-		vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id), &reg_val);
+		reg_val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id));
 		TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
 			    "Read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx",
 			    KVM_ARM64_SYS_REG(clr_reg_id), reg_val);
@@ -625,7 +624,7 @@ static uint64_t get_pmcr_n_limit(void)
 	uint64_t pmcr;
 
 	create_vpmu_vm(guest_code);
-	vcpu_get_reg(vpmu_vm.vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), &pmcr);
+	pmcr = vcpu_get_reg(vpmu_vm.vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0));
 	destroy_vpmu_vm();
 	return get_pmcr_n(pmcr);
 }
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index 9f24303acb8cb..e79817bd0e29e 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -21,7 +21,7 @@
 #include "ucall_common.h"
 
 #ifdef __aarch64__
-#include "aarch64/vgic.h"
+#include "arm64/vgic.h"
 
 static int gic_fd;
 
diff --git a/tools/testing/selftests/kvm/include/aarch64/arch_timer.h b/tools/testing/selftests/kvm/include/arm64/arch_timer.h
index bf461de34785a..bf461de34785a 100644
--- a/tools/testing/selftests/kvm/include/aarch64/arch_timer.h
+++ b/tools/testing/selftests/kvm/include/arm64/arch_timer.h
diff --git a/tools/testing/selftests/kvm/include/aarch64/delay.h b/tools/testing/selftests/kvm/include/arm64/delay.h
index 329e4f5079ea5..329e4f5079ea5 100644
--- a/tools/testing/selftests/kvm/include/aarch64/delay.h
+++ b/tools/testing/selftests/kvm/include/arm64/delay.h
diff --git a/tools/testing/selftests/kvm/include/aarch64/gic.h b/tools/testing/selftests/kvm/include/arm64/gic.h
index baeb3c859389d..baeb3c859389d 100644
--- a/tools/testing/selftests/kvm/include/aarch64/gic.h
+++ b/tools/testing/selftests/kvm/include/arm64/gic.h
diff --git a/tools/testing/selftests/kvm/include/aarch64/gic_v3.h b/tools/testing/selftests/kvm/include/arm64/gic_v3.h
index a76615fa39a1a..a76615fa39a1a 100644
--- a/tools/testing/selftests/kvm/include/aarch64/gic_v3.h
+++ b/tools/testing/selftests/kvm/include/arm64/gic_v3.h
diff --git a/tools/testing/selftests/kvm/include/aarch64/gic_v3_its.h b/tools/testing/selftests/kvm/include/arm64/gic_v3_its.h
index 3722ed9c8f96e..3722ed9c8f96e 100644
--- a/tools/testing/selftests/kvm/include/aarch64/gic_v3_its.h
+++ b/tools/testing/selftests/kvm/include/arm64/gic_v3_its.h
diff --git a/tools/testing/selftests/kvm/include/aarch64/kvm_util_arch.h b/tools/testing/selftests/kvm/include/arm64/kvm_util_arch.h
index e43a57d99b56c..e43a57d99b56c 100644
--- a/tools/testing/selftests/kvm/include/aarch64/kvm_util_arch.h
+++ b/tools/testing/selftests/kvm/include/arm64/kvm_util_arch.h
diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/arm64/processor.h
index 1e8d0d531fbd3..1e8d0d531fbd3 100644
--- a/tools/testing/selftests/kvm/include/aarch64/processor.h
+++ b/tools/testing/selftests/kvm/include/arm64/processor.h
diff --git a/tools/testing/selftests/kvm/include/aarch64/spinlock.h b/tools/testing/selftests/kvm/include/arm64/spinlock.h
index cf0984106d14b..cf0984106d14b 100644
--- a/tools/testing/selftests/kvm/include/aarch64/spinlock.h
+++ b/tools/testing/selftests/kvm/include/arm64/spinlock.h
diff --git a/tools/testing/selftests/kvm/include/aarch64/ucall.h b/tools/testing/selftests/kvm/include/arm64/ucall.h
index 4ec801f37f00e..4ec801f37f00e 100644
--- a/tools/testing/selftests/kvm/include/aarch64/ucall.h
+++ b/tools/testing/selftests/kvm/include/arm64/ucall.h
diff --git a/tools/testing/selftests/kvm/include/aarch64/vgic.h b/tools/testing/selftests/kvm/include/arm64/vgic.h
index c481d0c00a5d2..c481d0c00a5d2 100644
--- a/tools/testing/selftests/kvm/include/aarch64/vgic.h
+++ b/tools/testing/selftests/kvm/include/arm64/vgic.h
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index bc7c242480d69..4c4e5a847f67c 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -702,16 +702,22 @@ static inline int __vcpu_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t va
 
 	return __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, &reg);
 }
-static inline void vcpu_get_reg(struct kvm_vcpu *vcpu, uint64_t id, void *addr)
+static inline uint64_t vcpu_get_reg(struct kvm_vcpu *vcpu, uint64_t id)
 {
-	struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)addr };
+	uint64_t val;
+	struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val };
+
+	TEST_ASSERT(KVM_REG_SIZE(id) <= sizeof(val), "Reg %lx too big", id);
 
 	vcpu_ioctl(vcpu, KVM_GET_ONE_REG, &reg);
+	return val;
 }
 static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val)
 {
 	struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val };
 
+	TEST_ASSERT(KVM_REG_SIZE(id) <= sizeof(val), "Reg %lx too big", id);
+
 	vcpu_ioctl(vcpu, KVM_SET_ONE_REG, &reg);
 }
 
diff --git a/tools/testing/selftests/kvm/include/s390x/debug_print.h b/tools/testing/selftests/kvm/include/s390/debug_print.h
index 1bf275631cc69..1bf275631cc69 100644
--- a/tools/testing/selftests/kvm/include/s390x/debug_print.h
+++ b/tools/testing/selftests/kvm/include/s390/debug_print.h
diff --git a/tools/testing/selftests/kvm/include/s390x/diag318_test_handler.h b/tools/testing/selftests/kvm/include/s390/diag318_test_handler.h
index b0ed71302722a..b0ed71302722a 100644
--- a/tools/testing/selftests/kvm/include/s390x/diag318_test_handler.h
+++ b/tools/testing/selftests/kvm/include/s390/diag318_test_handler.h
diff --git a/tools/testing/selftests/kvm/include/s390x/facility.h b/tools/testing/selftests/kvm/include/s390/facility.h
index 00a1ced6538b2..00a1ced6538b2 100644
--- a/tools/testing/selftests/kvm/include/s390x/facility.h
+++ b/tools/testing/selftests/kvm/include/s390/facility.h
diff --git a/tools/testing/selftests/kvm/include/s390x/kvm_util_arch.h b/tools/testing/selftests/kvm/include/s390/kvm_util_arch.h
index e43a57d99b56c..e43a57d99b56c 100644
--- a/tools/testing/selftests/kvm/include/s390x/kvm_util_arch.h
+++ b/tools/testing/selftests/kvm/include/s390/kvm_util_arch.h
diff --git a/tools/testing/selftests/kvm/include/s390x/processor.h b/tools/testing/selftests/kvm/include/s390/processor.h
index 33fef6fd96174..33fef6fd96174 100644
--- a/tools/testing/selftests/kvm/include/s390x/processor.h
+++ b/tools/testing/selftests/kvm/include/s390/processor.h
diff --git a/tools/testing/selftests/kvm/include/s390x/sie.h b/tools/testing/selftests/kvm/include/s390/sie.h
index 160acd4a1db92..160acd4a1db92 100644
--- a/tools/testing/selftests/kvm/include/s390x/sie.h
+++ b/tools/testing/selftests/kvm/include/s390/sie.h
diff --git a/tools/testing/selftests/kvm/include/s390x/ucall.h b/tools/testing/selftests/kvm/include/s390/ucall.h
index 8035a872a351b..8035a872a351b 100644
--- a/tools/testing/selftests/kvm/include/s390x/ucall.h
+++ b/tools/testing/selftests/kvm/include/s390/ucall.h
diff --git a/tools/testing/selftests/kvm/include/x86_64/apic.h b/tools/testing/selftests/kvm/include/x86/apic.h
index 51990094effda..80fe9f69b38db 100644
--- a/tools/testing/selftests/kvm/include/x86_64/apic.h
+++ b/tools/testing/selftests/kvm/include/x86/apic.h
@@ -1,7 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * tools/testing/selftests/kvm/include/x86_64/apic.h
- *
  * Copyright (C) 2021, Google LLC.
  */
 
diff --git a/tools/testing/selftests/kvm/include/x86_64/evmcs.h b/tools/testing/selftests/kvm/include/x86/evmcs.h
index 901caf0e0939b..5a74bb30e2f8e 100644
--- a/tools/testing/selftests/kvm/include/x86_64/evmcs.h
+++ b/tools/testing/selftests/kvm/include/x86/evmcs.h
@@ -1,9 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
- * tools/testing/selftests/kvm/include/x86_64/evmcs.h
- *
  * Copyright (C) 2018, Red Hat, Inc.
- *
  */
 
 #ifndef SELFTEST_KVM_EVMCS_H
diff --git a/tools/testing/selftests/kvm/include/x86_64/hyperv.h b/tools/testing/selftests/kvm/include/x86/hyperv.h
index 6849e2552f1bf..f13e532be2406 100644
--- a/tools/testing/selftests/kvm/include/x86_64/hyperv.h
+++ b/tools/testing/selftests/kvm/include/x86/hyperv.h
@@ -1,9 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
- * tools/testing/selftests/kvm/include/x86_64/hyperv.h
- *
  * Copyright (C) 2021, Red Hat, Inc.
- *
  */
 
 #ifndef SELFTEST_KVM_HYPERV_H
diff --git a/tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h b/tools/testing/selftests/kvm/include/x86/kvm_util_arch.h
index 972bb1c4ab4c2..972bb1c4ab4c2 100644
--- a/tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h
+++ b/tools/testing/selftests/kvm/include/x86/kvm_util_arch.h
diff --git a/tools/testing/selftests/kvm/include/x86_64/mce.h b/tools/testing/selftests/kvm/include/x86/mce.h
index 6119321f3f5dd..295f2d5547549 100644
--- a/tools/testing/selftests/kvm/include/x86_64/mce.h
+++ b/tools/testing/selftests/kvm/include/x86/mce.h
@@ -1,7 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * tools/testing/selftests/kvm/include/x86_64/mce.h
- *
  * Copyright (C) 2022, Google LLC.
  */
 
diff --git a/tools/testing/selftests/kvm/include/x86_64/pmu.h b/tools/testing/selftests/kvm/include/x86/pmu.h
index 3c10c4dc0ae8f..3c10c4dc0ae8f 100644
--- a/tools/testing/selftests/kvm/include/x86_64/pmu.h
+++ b/tools/testing/selftests/kvm/include/x86/pmu.h
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h
index 645200e95f898..9ec984cf86742 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86/processor.h
@@ -1,7 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * tools/testing/selftests/kvm/include/x86_64/processor.h
- *
  * Copyright (C) 2018, Google LLC.
  */
 
diff --git a/tools/testing/selftests/kvm/include/x86_64/sev.h b/tools/testing/selftests/kvm/include/x86/sev.h
index 82c11c81a9563..82c11c81a9563 100644
--- a/tools/testing/selftests/kvm/include/x86_64/sev.h
+++ b/tools/testing/selftests/kvm/include/x86/sev.h
diff --git a/tools/testing/selftests/kvm/include/x86_64/svm.h b/tools/testing/selftests/kvm/include/x86/svm.h
index 4803e10560558..29cffd0a91816 100644
--- a/tools/testing/selftests/kvm/include/x86_64/svm.h
+++ b/tools/testing/selftests/kvm/include/x86/svm.h
@@ -1,10 +1,4 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*
- * tools/testing/selftests/kvm/include/x86_64/svm.h
- * This is a copy of arch/x86/include/asm/svm.h
- *
- */
-
 #ifndef SELFTEST_KVM_SVM_H
 #define SELFTEST_KVM_SVM_H
 
diff --git a/tools/testing/selftests/kvm/include/x86_64/svm_util.h b/tools/testing/selftests/kvm/include/x86/svm_util.h
index 044f0f872ba9d..b74c6dcddcbd6 100644
--- a/tools/testing/selftests/kvm/include/x86_64/svm_util.h
+++ b/tools/testing/selftests/kvm/include/x86/svm_util.h
@@ -1,8 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * tools/testing/selftests/kvm/include/x86_64/svm_utils.h
- * Header for nested SVM testing
- *
  * Copyright (C) 2020, Red Hat, Inc.
  */
 
diff --git a/tools/testing/selftests/kvm/include/x86_64/ucall.h b/tools/testing/selftests/kvm/include/x86/ucall.h
index d3825dcc3cd93..d3825dcc3cd93 100644
--- a/tools/testing/selftests/kvm/include/x86_64/ucall.h
+++ b/tools/testing/selftests/kvm/include/x86/ucall.h
diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86/vmx.h
index 5f0c0a29c556e..edb3c391b9824 100644
--- a/tools/testing/selftests/kvm/include/x86_64/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86/vmx.h
@@ -1,7 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * tools/testing/selftests/kvm/include/x86_64/vmx.h
- *
  * Copyright (C) 2018, Google LLC.
  */
 
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic.c b/tools/testing/selftests/kvm/lib/arm64/gic.c
index 7abbf8866512a..7abbf8866512a 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/gic.c
+++ b/tools/testing/selftests/kvm/lib/arm64/gic.c
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_private.h b/tools/testing/selftests/kvm/lib/arm64/gic_private.h
index d24e9ecc96c6d..d24e9ecc96c6d 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/gic_private.h
+++ b/tools/testing/selftests/kvm/lib/arm64/gic_private.h
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c b/tools/testing/selftests/kvm/lib/arm64/gic_v3.c
index 66d05506f78b1..66d05506f78b1 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c
+++ b/tools/testing/selftests/kvm/lib/arm64/gic_v3.c
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3_its.c b/tools/testing/selftests/kvm/lib/arm64/gic_v3_its.c
index 09f2705456469..09f2705456469 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/gic_v3_its.c
+++ b/tools/testing/selftests/kvm/lib/arm64/gic_v3_its.c
diff --git a/tools/testing/selftests/kvm/lib/aarch64/handlers.S b/tools/testing/selftests/kvm/lib/arm64/handlers.S
index 0e443eadfac60..0e443eadfac60 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/handlers.S
+++ b/tools/testing/selftests/kvm/lib/arm64/handlers.S
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/arm64/processor.c
index 698e34f392419..7ba3aa3755f35 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/arm64/processor.c
@@ -281,8 +281,8 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init)
 	 */
 	vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CPACR_EL1), 3 << 20);
 
-	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), &sctlr_el1);
-	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1), &tcr_el1);
+	sctlr_el1 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1));
+	tcr_el1 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1));
 
 	/* Configure base granule size */
 	switch (vm->mode) {
@@ -360,8 +360,8 @@ void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent)
 {
 	uint64_t pstate, pc;
 
-	vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pstate), &pstate);
-	vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc), &pc);
+	pstate = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pstate));
+	pc = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc));
 
 	fprintf(stream, "%*spstate: 0x%.16lx pc: 0x%.16lx\n",
 		indent, "", pstate, pc);
diff --git a/tools/testing/selftests/kvm/lib/aarch64/spinlock.c b/tools/testing/selftests/kvm/lib/arm64/spinlock.c
index a076e780be5dd..a076e780be5dd 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/spinlock.c
+++ b/tools/testing/selftests/kvm/lib/arm64/spinlock.c
diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/arm64/ucall.c
index ddab0ce89d4df..ddab0ce89d4df 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c
+++ b/tools/testing/selftests/kvm/lib/arm64/ucall.c
diff --git a/tools/testing/selftests/kvm/lib/aarch64/vgic.c b/tools/testing/selftests/kvm/lib/arm64/vgic.c
index 4427f43f73ea1..4427f43f73ea1 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/vgic.c
+++ b/tools/testing/selftests/kvm/lib/arm64/vgic.c
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 480e3a40d1975..33fefeb3ca441 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -1648,7 +1648,8 @@ int _vcpu_run(struct kvm_vcpu *vcpu)
 		rc = __vcpu_run(vcpu);
 	} while (rc == -1 && errno == EINTR);
 
-	assert_on_unhandled_exception(vcpu);
+	if (!rc)
+		assert_on_unhandled_exception(vcpu);
 
 	return rc;
 }
diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c
index 6ae47b3d6b25f..dd663bcf0cc09 100644
--- a/tools/testing/selftests/kvm/lib/riscv/processor.c
+++ b/tools/testing/selftests/kvm/lib/riscv/processor.c
@@ -221,39 +221,39 @@ void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent)
 {
 	struct kvm_riscv_core core;
 
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(mode), &core.mode);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.pc), &core.regs.pc);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.ra), &core.regs.ra);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.sp), &core.regs.sp);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.gp), &core.regs.gp);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.tp), &core.regs.tp);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t0), &core.regs.t0);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t1), &core.regs.t1);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t2), &core.regs.t2);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s0), &core.regs.s0);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s1), &core.regs.s1);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a0), &core.regs.a0);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a1), &core.regs.a1);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a2), &core.regs.a2);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a3), &core.regs.a3);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a4), &core.regs.a4);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a5), &core.regs.a5);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a6), &core.regs.a6);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a7), &core.regs.a7);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s2), &core.regs.s2);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s3), &core.regs.s3);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s4), &core.regs.s4);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s5), &core.regs.s5);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s6), &core.regs.s6);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s7), &core.regs.s7);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s8), &core.regs.s8);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s9), &core.regs.s9);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s10), &core.regs.s10);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s11), &core.regs.s11);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t3), &core.regs.t3);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t4), &core.regs.t4);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t5), &core.regs.t5);
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t6), &core.regs.t6);
+	core.mode = vcpu_get_reg(vcpu, RISCV_CORE_REG(mode));
+	core.regs.pc = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.pc));
+	core.regs.ra = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.ra));
+	core.regs.sp = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.sp));
+	core.regs.gp = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.gp));
+	core.regs.tp = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.tp));
+	core.regs.t0 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t0));
+	core.regs.t1 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t1));
+	core.regs.t2 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t2));
+	core.regs.s0 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s0));
+	core.regs.s1 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s1));
+	core.regs.a0 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a0));
+	core.regs.a1 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a1));
+	core.regs.a2 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a2));
+	core.regs.a3 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a3));
+	core.regs.a4 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a4));
+	core.regs.a5 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a5));
+	core.regs.a6 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a6));
+	core.regs.a7 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a7));
+	core.regs.s2 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s2));
+	core.regs.s3 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s3));
+	core.regs.s4 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s4));
+	core.regs.s5 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s5));
+	core.regs.s6 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s6));
+	core.regs.s7 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s7));
+	core.regs.s8 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s8));
+	core.regs.s9 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s9));
+	core.regs.s10 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s10));
+	core.regs.s11 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s11));
+	core.regs.t3 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t3));
+	core.regs.t4 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t4));
+	core.regs.t5 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t5));
+	core.regs.t6 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t6));
 
 	fprintf(stream,
 		" MODE:  0x%lx\n", core.mode);
diff --git a/tools/testing/selftests/kvm/lib/s390x/diag318_test_handler.c b/tools/testing/selftests/kvm/lib/s390/diag318_test_handler.c
index 2c432fa164f19..2c432fa164f19 100644
--- a/tools/testing/selftests/kvm/lib/s390x/diag318_test_handler.c
+++ b/tools/testing/selftests/kvm/lib/s390/diag318_test_handler.c
diff --git a/tools/testing/selftests/kvm/lib/s390x/facility.c b/tools/testing/selftests/kvm/lib/s390/facility.c
index d540812d911ae..d540812d911ae 100644
--- a/tools/testing/selftests/kvm/lib/s390x/facility.c
+++ b/tools/testing/selftests/kvm/lib/s390/facility.c
diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390/processor.c
index 20cfe970e3e34..20cfe970e3e34 100644
--- a/tools/testing/selftests/kvm/lib/s390x/processor.c
+++ b/tools/testing/selftests/kvm/lib/s390/processor.c
diff --git a/tools/testing/selftests/kvm/lib/s390x/ucall.c b/tools/testing/selftests/kvm/lib/s390/ucall.c
index cca98734653d4..cca98734653d4 100644
--- a/tools/testing/selftests/kvm/lib/s390x/ucall.c
+++ b/tools/testing/selftests/kvm/lib/s390/ucall.c
diff --git a/tools/testing/selftests/kvm/lib/x86_64/apic.c b/tools/testing/selftests/kvm/lib/x86/apic.c
index 89153a333e83c..89153a333e83c 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/apic.c
+++ b/tools/testing/selftests/kvm/lib/x86/apic.c
diff --git a/tools/testing/selftests/kvm/lib/x86_64/handlers.S b/tools/testing/selftests/kvm/lib/x86/handlers.S
index 7629819734afd..7629819734afd 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/handlers.S
+++ b/tools/testing/selftests/kvm/lib/x86/handlers.S
diff --git a/tools/testing/selftests/kvm/lib/x86_64/hyperv.c b/tools/testing/selftests/kvm/lib/x86/hyperv.c
index 15bc8cd583aa4..15bc8cd583aa4 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/hyperv.c
+++ b/tools/testing/selftests/kvm/lib/x86/hyperv.c
diff --git a/tools/testing/selftests/kvm/lib/x86_64/memstress.c b/tools/testing/selftests/kvm/lib/x86/memstress.c
index d61e623afc8cf..7f5d62a65c68a 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/memstress.c
+++ b/tools/testing/selftests/kvm/lib/x86/memstress.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * x86_64-specific extensions to memstress.c.
+ * x86-specific extensions to memstress.c.
  *
  * Copyright (C) 2022, Google, Inc.
  */
diff --git a/tools/testing/selftests/kvm/lib/x86_64/pmu.c b/tools/testing/selftests/kvm/lib/x86/pmu.c
index f31f0427c17cb..f31f0427c17cb 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/pmu.c
+++ b/tools/testing/selftests/kvm/lib/x86/pmu.c
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c
index 636b29ba89857..bd5a802fa7a56 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86/processor.c
@@ -1,7 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * tools/testing/selftests/kvm/lib/x86_64/processor.c
- *
  * Copyright (C) 2018, Google LLC.
  */
 
diff --git a/tools/testing/selftests/kvm/lib/x86_64/sev.c b/tools/testing/selftests/kvm/lib/x86/sev.c
index e9535ee20b7fc..e9535ee20b7fc 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/sev.c
+++ b/tools/testing/selftests/kvm/lib/x86/sev.c
diff --git a/tools/testing/selftests/kvm/lib/x86_64/svm.c b/tools/testing/selftests/kvm/lib/x86/svm.c
index 5495a92dfd5a4..d239c20973918 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/svm.c
+++ b/tools/testing/selftests/kvm/lib/x86/svm.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * tools/testing/selftests/kvm/lib/x86_64/svm.c
  * Helpers used for nested SVM testing
  * Largely inspired from KVM unit test svm.c
  *
diff --git a/tools/testing/selftests/kvm/lib/x86_64/ucall.c b/tools/testing/selftests/kvm/lib/x86/ucall.c
index 1265cecc7dd10..1265cecc7dd10 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/ucall.c
+++ b/tools/testing/selftests/kvm/lib/x86/ucall.c
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86/vmx.c
index d7ac122820bfe..d4d1208dd0238 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86/vmx.c
@@ -1,7 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * tools/testing/selftests/kvm/lib/x86_64/vmx.c
- *
  * Copyright (C) 2018, Google LLC.
  */
 
diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/mmu_stress_test.c
index 0b9678858b6d7..d9c76b4c0d88a 100644
--- a/tools/testing/selftests/kvm/max_guest_memory_test.c
+++ b/tools/testing/selftests/kvm/mmu_stress_test.c
@@ -15,16 +15,62 @@
 #include "test_util.h"
 #include "guest_modes.h"
 #include "processor.h"
+#include "ucall_common.h"
+
+static bool mprotect_ro_done;
 
 static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride)
 {
 	uint64_t gpa;
+	int i;
 
-	for (;;) {
+	for (i = 0; i < 2; i++) {
 		for (gpa = start_gpa; gpa < end_gpa; gpa += stride)
-			*((volatile uint64_t *)gpa) = gpa;
-		GUEST_SYNC(0);
+			vcpu_arch_put_guest(*((volatile uint64_t *)gpa), gpa);
+		GUEST_SYNC(i);
 	}
+
+	for (gpa = start_gpa; gpa < end_gpa; gpa += stride)
+		*((volatile uint64_t *)gpa);
+	GUEST_SYNC(2);
+
+	/*
+	 * Write to the region while mprotect(PROT_READ) is underway.  Keep
+	 * looping until the memory is guaranteed to be read-only, otherwise
+	 * vCPUs may complete their writes and advance to the next stage
+	 * prematurely.
+	 *
+	 * For architectures that support skipping the faulting instruction,
+	 * generate the store via inline assembly to ensure the exact length
+	 * of the instruction is known and stable (vcpu_arch_put_guest() on
+	 * fixed-length architectures should work, but the cost of paranoia
+	 * is low in this case).  For x86, hand-code the exact opcode so that
+	 * there is no room for variability in the generated instruction.
+	 */
+	do {
+		for (gpa = start_gpa; gpa < end_gpa; gpa += stride)
+#ifdef __x86_64__
+			asm volatile(".byte 0x48,0x89,0x00" :: "a"(gpa) : "memory"); /* mov %rax, (%rax) */
+#elif defined(__aarch64__)
+			asm volatile("str %0, [%0]" :: "r" (gpa) : "memory");
+#else
+			vcpu_arch_put_guest(*((volatile uint64_t *)gpa), gpa);
+#endif
+	} while (!READ_ONCE(mprotect_ro_done));
+
+	/*
+	 * Only architectures that write the entire range can explicitly sync,
+	 * as other architectures will be stuck on the write fault.
+	 */
+#if defined(__x86_64__) || defined(__aarch64__)
+	GUEST_SYNC(3);
+#endif
+
+	for (gpa = start_gpa; gpa < end_gpa; gpa += stride)
+		vcpu_arch_put_guest(*((volatile uint64_t *)gpa), gpa);
+	GUEST_SYNC(4);
+
+	GUEST_ASSERT(0);
 }
 
 struct vcpu_info {
@@ -51,34 +97,100 @@ static void rendezvous_with_boss(void)
 	}
 }
 
-static void run_vcpu(struct kvm_vcpu *vcpu)
+static void assert_sync_stage(struct kvm_vcpu *vcpu, int stage)
+{
+	struct ucall uc;
+
+	TEST_ASSERT_EQ(get_ucall(vcpu, &uc), UCALL_SYNC);
+	TEST_ASSERT_EQ(uc.args[1], stage);
+}
+
+static void run_vcpu(struct kvm_vcpu *vcpu, int stage)
 {
 	vcpu_run(vcpu);
-	TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_SYNC);
+	assert_sync_stage(vcpu, stage);
 }
 
 static void *vcpu_worker(void *data)
 {
+	struct kvm_sregs __maybe_unused sregs;
 	struct vcpu_info *info = data;
 	struct kvm_vcpu *vcpu = info->vcpu;
 	struct kvm_vm *vm = vcpu->vm;
-	struct kvm_sregs sregs;
+	int r;
 
 	vcpu_args_set(vcpu, 3, info->start_gpa, info->end_gpa, vm->page_size);
 
 	rendezvous_with_boss();
 
-	run_vcpu(vcpu);
+	/* Stage 0, write all of guest memory. */
+	run_vcpu(vcpu, 0);
 	rendezvous_with_boss();
-	vcpu_sregs_get(vcpu, &sregs);
 #ifdef __x86_64__
+	vcpu_sregs_get(vcpu, &sregs);
 	/* Toggle CR0.WP to trigger a MMU context reset. */
 	sregs.cr0 ^= X86_CR0_WP;
-#endif
 	vcpu_sregs_set(vcpu, &sregs);
+#endif
 	rendezvous_with_boss();
 
-	run_vcpu(vcpu);
+	/* Stage 1, re-write all of guest memory. */
+	run_vcpu(vcpu, 1);
+	rendezvous_with_boss();
+
+	/* Stage 2, read all of guest memory, which is now read-only. */
+	run_vcpu(vcpu, 2);
+
+	/*
+	 * Stage 3, write guest memory and verify KVM returns -EFAULT for once
+	 * the mprotect(PROT_READ) lands.  Only architectures that support
+	 * validating *all* of guest memory sync for this stage, as vCPUs will
+	 * be stuck on the faulting instruction for other architectures.  Go to
+	 * stage 3 without a rendezvous
+	 */
+	do {
+		r = _vcpu_run(vcpu);
+	} while (!r);
+	TEST_ASSERT(r == -1 && errno == EFAULT,
+		    "Expected EFAULT on write to RO memory, got r = %d, errno = %d", r, errno);
+
+#if defined(__x86_64__) || defined(__aarch64__)
+	/*
+	 * Verify *all* writes from the guest hit EFAULT due to the VMA now
+	 * being read-only.  x86 and arm64 only at this time as skipping the
+	 * instruction that hits the EFAULT requires advancing the program
+	 * counter, which is arch specific and relies on inline assembly.
+	 */
+#ifdef __x86_64__
+	vcpu->run->kvm_valid_regs = KVM_SYNC_X86_REGS;
+#endif
+	for (;;) {
+		r = _vcpu_run(vcpu);
+		if (!r)
+			break;
+		TEST_ASSERT_EQ(errno, EFAULT);
+#if defined(__x86_64__)
+		WRITE_ONCE(vcpu->run->kvm_dirty_regs, KVM_SYNC_X86_REGS);
+		vcpu->run->s.regs.regs.rip += 3;
+#elif defined(__aarch64__)
+		vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.pc),
+			     vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc)) + 4);
+#endif
+
+	}
+	assert_sync_stage(vcpu, 3);
+#endif /* __x86_64__ || __aarch64__ */
+	rendezvous_with_boss();
+
+	/*
+	 * Stage 4.  Run to completion, waiting for mprotect(PROT_WRITE) to
+	 * make the memory writable again.
+	 */
+	do {
+		r = _vcpu_run(vcpu);
+	} while (r && errno == EFAULT);
+	TEST_ASSERT_EQ(r, 0);
+	assert_sync_stage(vcpu, 4);
 	rendezvous_with_boss();
 
 	return NULL;
@@ -161,7 +273,7 @@ int main(int argc, char *argv[])
 	const uint64_t start_gpa = SZ_4G;
 	const int first_slot = 1;
 
-	struct timespec time_start, time_run1, time_reset, time_run2;
+	struct timespec time_start, time_run1, time_reset, time_run2, time_ro, time_rw;
 	uint64_t max_gpa, gpa, slot_size, max_mem, i;
 	int max_slots, slot, opt, fd;
 	bool hugepages = false;
@@ -209,7 +321,13 @@ int main(int argc, char *argv[])
 	vcpus = malloc(nr_vcpus * sizeof(*vcpus));
 	TEST_ASSERT(vcpus, "Failed to allocate vCPU array");
 
-	vm = vm_create_with_vcpus(nr_vcpus, guest_code, vcpus);
+	vm = __vm_create_with_vcpus(VM_SHAPE_DEFAULT, nr_vcpus,
+#ifdef __x86_64__
+				    max_mem / SZ_1G,
+#else
+				    max_mem / vm_guest_mode_params[VM_MODE_DEFAULT].page_size,
+#endif
+				    guest_code, vcpus);
 
 	max_gpa = vm->max_gfn << vm->page_shift;
 	TEST_ASSERT(max_gpa > (4 * slot_size), "MAXPHYADDR <4gb ");
@@ -259,14 +377,28 @@ int main(int argc, char *argv[])
 	rendezvous_with_vcpus(&time_reset, "reset");
 	rendezvous_with_vcpus(&time_run2, "run 2");
 
+	mprotect(mem, slot_size, PROT_READ);
+	usleep(10);
+	mprotect_ro_done = true;
+	sync_global_to_guest(vm, mprotect_ro_done);
+
+	rendezvous_with_vcpus(&time_ro, "mprotect RO");
+	mprotect(mem, slot_size, PROT_READ | PROT_WRITE);
+	rendezvous_with_vcpus(&time_rw, "mprotect RW");
+
+	time_rw    = timespec_sub(time_rw,     time_ro);
+	time_ro    = timespec_sub(time_ro,     time_run2);
 	time_run2  = timespec_sub(time_run2,   time_reset);
-	time_reset = timespec_sub(time_reset, time_run1);
+	time_reset = timespec_sub(time_reset,  time_run1);
 	time_run1  = timespec_sub(time_run1,   time_start);
 
-	pr_info("run1 = %ld.%.9lds, reset = %ld.%.9lds, run2 =  %ld.%.9lds\n",
+	pr_info("run1 = %ld.%.9lds, reset = %ld.%.9lds, run2 = %ld.%.9lds, "
+		"ro = %ld.%.9lds, rw = %ld.%.9lds\n",
 		time_run1.tv_sec, time_run1.tv_nsec,
 		time_reset.tv_sec, time_reset.tv_nsec,
-		time_run2.tv_sec, time_run2.tv_nsec);
+		time_run2.tv_sec, time_run2.tv_nsec,
+		time_ro.tv_sec, time_ro.tv_nsec,
+		time_rw.tv_sec, time_rw.tv_nsec);
 
 	/*
 	 * Delete even numbered slots (arbitrary) and unmap the first half of
diff --git a/tools/testing/selftests/kvm/riscv/arch_timer.c b/tools/testing/selftests/kvm/riscv/arch_timer.c
index 2c792228ac0be..9e370800a6a29 100644
--- a/tools/testing/selftests/kvm/riscv/arch_timer.c
+++ b/tools/testing/selftests/kvm/riscv/arch_timer.c
@@ -93,7 +93,7 @@ struct kvm_vm *test_vm_create(void)
 		vcpu_init_vector_tables(vcpus[i]);
 
 	/* Initialize guest timer frequency. */
-	vcpu_get_reg(vcpus[0], RISCV_TIMER_REG(frequency), &timer_freq);
+	timer_freq = vcpu_get_reg(vcpus[0], RISCV_TIMER_REG(frequency));
 	sync_global_to_guest(vm, timer_freq);
 	pr_debug("timer_freq: %lu\n", timer_freq);
 
diff --git a/tools/testing/selftests/kvm/riscv/ebreak_test.c b/tools/testing/selftests/kvm/riscv/ebreak_test.c
index 0e07128549538..cfed6c727bfca 100644
--- a/tools/testing/selftests/kvm/riscv/ebreak_test.c
+++ b/tools/testing/selftests/kvm/riscv/ebreak_test.c
@@ -60,7 +60,7 @@ int main(void)
 
 	TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_DEBUG);
 
-	vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.pc), &pc);
+	pc = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.pc));
 	TEST_ASSERT_EQ(pc, LABEL_ADDRESS(sw_bp_1));
 
 	/* skip sw_bp_1 */
diff --git a/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c b/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c
index f299cbfd23ca0..f45c0ecc902d6 100644
--- a/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c
+++ b/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c
@@ -608,7 +608,7 @@ static void test_vm_events_overflow(void *guest_code)
 
 	vcpu_init_vector_tables(vcpu);
 	/* Initialize guest timer frequency. */
-	vcpu_get_reg(vcpu, RISCV_TIMER_REG(frequency), &timer_freq);
+	timer_freq = vcpu_get_reg(vcpu, RISCV_TIMER_REG(frequency));
 	sync_global_to_guest(vm, timer_freq);
 
 	run_vcpu(vcpu);
diff --git a/tools/testing/selftests/kvm/s390x/cmma_test.c b/tools/testing/selftests/kvm/s390/cmma_test.c
index e32dd59703a08..e32dd59703a08 100644
--- a/tools/testing/selftests/kvm/s390x/cmma_test.c
+++ b/tools/testing/selftests/kvm/s390/cmma_test.c
diff --git a/tools/testing/selftests/kvm/s390x/config b/tools/testing/selftests/kvm/s390/config
index 23270f2d679f0..23270f2d679f0 100644
--- a/tools/testing/selftests/kvm/s390x/config
+++ b/tools/testing/selftests/kvm/s390/config
diff --git a/tools/testing/selftests/kvm/s390x/cpumodel_subfuncs_test.c b/tools/testing/selftests/kvm/s390/cpumodel_subfuncs_test.c
index 27255880dabd0..27255880dabd0 100644
--- a/tools/testing/selftests/kvm/s390x/cpumodel_subfuncs_test.c
+++ b/tools/testing/selftests/kvm/s390/cpumodel_subfuncs_test.c
diff --git a/tools/testing/selftests/kvm/s390x/debug_test.c b/tools/testing/selftests/kvm/s390/debug_test.c
index ad80959686014..ad80959686014 100644
--- a/tools/testing/selftests/kvm/s390x/debug_test.c
+++ b/tools/testing/selftests/kvm/s390/debug_test.c
diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390/memop.c
index 4374b4cd2a807..4374b4cd2a807 100644
--- a/tools/testing/selftests/kvm/s390x/memop.c
+++ b/tools/testing/selftests/kvm/s390/memop.c
diff --git a/tools/testing/selftests/kvm/s390x/resets.c b/tools/testing/selftests/kvm/s390/resets.c
index 357943f2bea87..b58f75b381e5a 100644
--- a/tools/testing/selftests/kvm/s390x/resets.c
+++ b/tools/testing/selftests/kvm/s390/resets.c
@@ -61,7 +61,7 @@ static void test_one_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t value)
 {
 	uint64_t eval_reg;
 
-	vcpu_get_reg(vcpu, id, &eval_reg);
+	eval_reg = vcpu_get_reg(vcpu, id);
 	TEST_ASSERT(eval_reg == value, "value == 0x%lx", value);
 }
 
diff --git a/tools/testing/selftests/kvm/s390x/shared_zeropage_test.c b/tools/testing/selftests/kvm/s390/shared_zeropage_test.c
index bba0d9a6dcc87..bba0d9a6dcc87 100644
--- a/tools/testing/selftests/kvm/s390x/shared_zeropage_test.c
+++ b/tools/testing/selftests/kvm/s390/shared_zeropage_test.c
diff --git a/tools/testing/selftests/kvm/s390x/sync_regs_test.c b/tools/testing/selftests/kvm/s390/sync_regs_test.c
index 53def355ccba4..53def355ccba4 100644
--- a/tools/testing/selftests/kvm/s390x/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/s390/sync_regs_test.c
diff --git a/tools/testing/selftests/kvm/s390x/tprot.c b/tools/testing/selftests/kvm/s390/tprot.c
index 12d5e1cb62e34..12d5e1cb62e34 100644
--- a/tools/testing/selftests/kvm/s390x/tprot.c
+++ b/tools/testing/selftests/kvm/s390/tprot.c
diff --git a/tools/testing/selftests/kvm/s390x/ucontrol_test.c b/tools/testing/selftests/kvm/s390/ucontrol_test.c
index 0c112319dab1e..135ee22856cf1 100644
--- a/tools/testing/selftests/kvm/s390x/ucontrol_test.c
+++ b/tools/testing/selftests/kvm/s390/ucontrol_test.c
@@ -210,10 +210,13 @@ TEST_F(uc_kvm, uc_attr_mem_limit)
 	struct kvm_device_attr attr = {
 		.group = KVM_S390_VM_MEM_CTRL,
 		.attr = KVM_S390_VM_MEM_LIMIT_SIZE,
-		.addr = (unsigned long)&limit,
+		.addr = (u64)&limit,
 	};
 	int rc;
 
+	rc = ioctl(self->vm_fd, KVM_HAS_DEVICE_ATTR, &attr);
+	EXPECT_EQ(0, rc);
+
 	rc = ioctl(self->vm_fd, KVM_GET_DEVICE_ATTR, &attr);
 	EXPECT_EQ(0, rc);
 	EXPECT_EQ(~0UL, limit);
@@ -635,4 +638,171 @@ TEST_F(uc_kvm, uc_skey)
 	uc_assert_diag44(self);
 }
 
+static char uc_flic_b[PAGE_SIZE];
+static struct kvm_s390_io_adapter uc_flic_ioa = { .id = 0 };
+static struct kvm_s390_io_adapter_req uc_flic_ioam = { .id = 0 };
+static struct kvm_s390_ais_req uc_flic_asim = { .isc = 0 };
+static struct kvm_s390_ais_all uc_flic_asima = { .simm = 0 };
+static struct uc_flic_attr_test {
+	char *name;
+	struct kvm_device_attr a;
+	int hasrc;
+	int geterrno;
+	int seterrno;
+} uc_flic_attr_tests[] = {
+	{
+		.name = "KVM_DEV_FLIC_GET_ALL_IRQS",
+		.seterrno = EINVAL,
+		.a = {
+			.group = KVM_DEV_FLIC_GET_ALL_IRQS,
+			.addr = (u64)&uc_flic_b,
+			.attr = PAGE_SIZE,
+		},
+	},
+	{
+		.name = "KVM_DEV_FLIC_ENQUEUE",
+		.geterrno = EINVAL,
+		.a = { .group = KVM_DEV_FLIC_ENQUEUE, },
+	},
+	{
+		.name = "KVM_DEV_FLIC_CLEAR_IRQS",
+		.geterrno = EINVAL,
+		.a = { .group = KVM_DEV_FLIC_CLEAR_IRQS, },
+	},
+	{
+		.name = "KVM_DEV_FLIC_ADAPTER_REGISTER",
+		.geterrno = EINVAL,
+		.a = {
+			.group = KVM_DEV_FLIC_ADAPTER_REGISTER,
+			.addr = (u64)&uc_flic_ioa,
+		},
+	},
+	{
+		.name = "KVM_DEV_FLIC_ADAPTER_MODIFY",
+		.geterrno = EINVAL,
+		.seterrno = EINVAL,
+		.a = {
+			.group = KVM_DEV_FLIC_ADAPTER_MODIFY,
+			.addr = (u64)&uc_flic_ioam,
+			.attr = sizeof(uc_flic_ioam),
+		},
+	},
+	{
+		.name = "KVM_DEV_FLIC_CLEAR_IO_IRQ",
+		.geterrno = EINVAL,
+		.seterrno = EINVAL,
+		.a = {
+			.group = KVM_DEV_FLIC_CLEAR_IO_IRQ,
+			.attr = 32,
+		},
+	},
+	{
+		.name = "KVM_DEV_FLIC_AISM",
+		.geterrno = EINVAL,
+		.seterrno = ENOTSUP,
+		.a = {
+			.group = KVM_DEV_FLIC_AISM,
+			.addr = (u64)&uc_flic_asim,
+		},
+	},
+	{
+		.name = "KVM_DEV_FLIC_AIRQ_INJECT",
+		.geterrno = EINVAL,
+		.a = { .group = KVM_DEV_FLIC_AIRQ_INJECT, },
+	},
+	{
+		.name = "KVM_DEV_FLIC_AISM_ALL",
+		.geterrno = ENOTSUP,
+		.seterrno = ENOTSUP,
+		.a = {
+			.group = KVM_DEV_FLIC_AISM_ALL,
+			.addr = (u64)&uc_flic_asima,
+			.attr = sizeof(uc_flic_asima),
+		},
+	},
+	{
+		.name = "KVM_DEV_FLIC_APF_ENABLE",
+		.geterrno = EINVAL,
+		.seterrno = EINVAL,
+		.a = { .group = KVM_DEV_FLIC_APF_ENABLE, },
+	},
+	{
+		.name = "KVM_DEV_FLIC_APF_DISABLE_WAIT",
+		.geterrno = EINVAL,
+		.seterrno = EINVAL,
+		.a = { .group = KVM_DEV_FLIC_APF_DISABLE_WAIT, },
+	},
+};
+
+TEST_F(uc_kvm, uc_flic_attrs)
+{
+	struct kvm_create_device cd = { .type = KVM_DEV_TYPE_FLIC };
+	struct kvm_device_attr attr;
+	u64 value;
+	int rc, i;
+
+	rc = ioctl(self->vm_fd, KVM_CREATE_DEVICE, &cd);
+	ASSERT_EQ(0, rc) TH_LOG("create device failed with err %s (%i)",
+				strerror(errno), errno);
+
+	for (i = 0; i < ARRAY_SIZE(uc_flic_attr_tests); i++) {
+		TH_LOG("test %s", uc_flic_attr_tests[i].name);
+		attr = (struct kvm_device_attr) {
+			.group = uc_flic_attr_tests[i].a.group,
+			.attr = uc_flic_attr_tests[i].a.attr,
+			.addr = uc_flic_attr_tests[i].a.addr,
+		};
+		if (attr.addr == 0)
+			attr.addr = (u64)&value;
+
+		rc = ioctl(cd.fd, KVM_HAS_DEVICE_ATTR, &attr);
+		EXPECT_EQ(uc_flic_attr_tests[i].hasrc, !!rc)
+			TH_LOG("expected dev attr missing %s",
+			       uc_flic_attr_tests[i].name);
+
+		rc = ioctl(cd.fd, KVM_GET_DEVICE_ATTR, &attr);
+		EXPECT_EQ(!!uc_flic_attr_tests[i].geterrno, !!rc)
+			TH_LOG("get dev attr rc not expected on %s %s (%i)",
+			       uc_flic_attr_tests[i].name,
+			       strerror(errno), errno);
+		if (uc_flic_attr_tests[i].geterrno)
+			EXPECT_EQ(uc_flic_attr_tests[i].geterrno, errno)
+				TH_LOG("get dev attr errno not expected on %s %s (%i)",
+				       uc_flic_attr_tests[i].name,
+				       strerror(errno), errno);
+
+		rc = ioctl(cd.fd, KVM_SET_DEVICE_ATTR, &attr);
+		EXPECT_EQ(!!uc_flic_attr_tests[i].seterrno, !!rc)
+			TH_LOG("set sev attr rc not expected on %s %s (%i)",
+			       uc_flic_attr_tests[i].name,
+			       strerror(errno), errno);
+		if (uc_flic_attr_tests[i].seterrno)
+			EXPECT_EQ(uc_flic_attr_tests[i].seterrno, errno)
+				TH_LOG("set dev attr errno not expected on %s %s (%i)",
+				       uc_flic_attr_tests[i].name,
+				       strerror(errno), errno);
+	}
+
+	close(cd.fd);
+}
+
+TEST_F(uc_kvm, uc_set_gsi_routing)
+{
+	struct kvm_irq_routing *routing = kvm_gsi_routing_create();
+	struct kvm_irq_routing_entry ue = {
+		.type = KVM_IRQ_ROUTING_S390_ADAPTER,
+		.gsi = 1,
+		.u.adapter = (struct kvm_irq_routing_s390_adapter) {
+			.ind_addr = 0,
+		},
+	};
+	int rc;
+
+	routing->entries[0] = ue;
+	routing->nr = 1;
+	rc = ioctl(self->vm_fd, KVM_SET_GSI_ROUTING, routing);
+	ASSERT_EQ(-1, rc) TH_LOG("err %s (%i)", strerror(errno), errno);
+	ASSERT_EQ(EINVAL, errno) TH_LOG("err %s (%i)", strerror(errno), errno);
+}
+
 TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index a8267628e9ed1..86ee3385e860b 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -17,9 +17,9 @@
 #include <processor.h>
 
 /*
- * s390x needs at least 1MB alignment, and the x86_64 MOVE/DELETE tests need a
- * 2MB sized and aligned region so that the initial region corresponds to
- * exactly one large page.
+ * s390 needs at least 1MB alignment, and the x86 MOVE/DELETE tests need a 2MB
+ * sized and aligned region so that the initial region corresponds to exactly
+ * one large page.
  */
 #define MEM_REGION_SIZE		0x200000
 
diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c
index a8d3afa0b86b2..cce2520af720e 100644
--- a/tools/testing/selftests/kvm/steal_time.c
+++ b/tools/testing/selftests/kvm/steal_time.c
@@ -269,9 +269,8 @@ static void guest_code(int cpu)
 static bool is_steal_time_supported(struct kvm_vcpu *vcpu)
 {
 	uint64_t id = RISCV_SBI_EXT_REG(KVM_RISCV_SBI_EXT_STA);
-	unsigned long enabled;
+	unsigned long enabled = vcpu_get_reg(vcpu, id);
 
-	vcpu_get_reg(vcpu, id, &enabled);
 	TEST_ASSERT(enabled == 0 || enabled == 1, "Expected boolean result");
 
 	return enabled;
diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86/amx_test.c
index f4ce5a185a7dd..f4ce5a185a7dd 100644
--- a/tools/testing/selftests/kvm/x86_64/amx_test.c
+++ b/tools/testing/selftests/kvm/x86/amx_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/apic_bus_clock_test.c b/tools/testing/selftests/kvm/x86/apic_bus_clock_test.c
index f8916bb344050..f8916bb344050 100644
--- a/tools/testing/selftests/kvm/x86_64/apic_bus_clock_test.c
+++ b/tools/testing/selftests/kvm/x86/apic_bus_clock_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/cpuid_test.c b/tools/testing/selftests/kvm/x86/cpuid_test.c
index 7b3fda6842bce..7b3fda6842bce 100644
--- a/tools/testing/selftests/kvm/x86_64/cpuid_test.c
+++ b/tools/testing/selftests/kvm/x86/cpuid_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86/cr4_cpuid_sync_test.c
index 28cc664546019..28cc664546019 100644
--- a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
+++ b/tools/testing/selftests/kvm/x86/cr4_cpuid_sync_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86/debug_regs.c
index 2d814c1d1dc44..2d814c1d1dc44 100644
--- a/tools/testing/selftests/kvm/x86_64/debug_regs.c
+++ b/tools/testing/selftests/kvm/x86/debug_regs.c
diff --git a/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c b/tools/testing/selftests/kvm/x86/dirty_log_page_splitting_test.c
index 2929c067c2078..2929c067c2078 100644
--- a/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c
+++ b/tools/testing/selftests/kvm/x86/dirty_log_page_splitting_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c b/tools/testing/selftests/kvm/x86/exit_on_emulation_failure_test.c
index 81055476d3942..81055476d3942 100644
--- a/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c
+++ b/tools/testing/selftests/kvm/x86/exit_on_emulation_failure_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/feature_msrs_test.c b/tools/testing/selftests/kvm/x86/feature_msrs_test.c
index a72f13ae2edbb..a72f13ae2edbb 100644
--- a/tools/testing/selftests/kvm/x86_64/feature_msrs_test.c
+++ b/tools/testing/selftests/kvm/x86/feature_msrs_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c b/tools/testing/selftests/kvm/x86/fix_hypercall_test.c
index 762628f7d4ba3..762628f7d4ba3 100644
--- a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c
+++ b/tools/testing/selftests/kvm/x86/fix_hypercall_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/flds_emulation.h b/tools/testing/selftests/kvm/x86/flds_emulation.h
index 37b1a9f528644..37b1a9f528644 100644
--- a/tools/testing/selftests/kvm/x86_64/flds_emulation.h
+++ b/tools/testing/selftests/kvm/x86/flds_emulation.h
diff --git a/tools/testing/selftests/kvm/x86_64/hwcr_msr_test.c b/tools/testing/selftests/kvm/x86/hwcr_msr_test.c
index 10b1b0ba374e6..10b1b0ba374e6 100644
--- a/tools/testing/selftests/kvm/x86_64/hwcr_msr_test.c
+++ b/tools/testing/selftests/kvm/x86/hwcr_msr_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86/hyperv_clock.c
index e058bc676cd69..e058bc676cd69 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
+++ b/tools/testing/selftests/kvm/x86/hyperv_clock.c
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86/hyperv_cpuid.c
index 4f5881d4ef66d..4f5881d4ef66d 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
+++ b/tools/testing/selftests/kvm/x86/hyperv_cpuid.c
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c b/tools/testing/selftests/kvm/x86/hyperv_evmcs.c
index 74cf196613090..74cf196613090 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c
+++ b/tools/testing/selftests/kvm/x86/hyperv_evmcs.c
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c b/tools/testing/selftests/kvm/x86/hyperv_extended_hypercalls.c
index 949e08e98f315..949e08e98f315 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c
+++ b/tools/testing/selftests/kvm/x86/hyperv_extended_hypercalls.c
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86/hyperv_features.c
index 068e9c69710d2..068e9c69710d2 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c
+++ b/tools/testing/selftests/kvm/x86/hyperv_features.c
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c b/tools/testing/selftests/kvm/x86/hyperv_ipi.c
index 22c0c124582fd..22c0c124582fd 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c
+++ b/tools/testing/selftests/kvm/x86/hyperv_ipi.c
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86/hyperv_svm_test.c
index 0ddb63229bcbb..0ddb63229bcbb 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c
+++ b/tools/testing/selftests/kvm/x86/hyperv_svm_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c b/tools/testing/selftests/kvm/x86/hyperv_tlb_flush.c
index 077cd0ec3040e..077cd0ec3040e 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c
+++ b/tools/testing/selftests/kvm/x86/hyperv_tlb_flush.c
diff --git a/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c b/tools/testing/selftests/kvm/x86/kvm_clock_test.c
index 5bc12222d87af..5bc12222d87af 100644
--- a/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c
+++ b/tools/testing/selftests/kvm/x86/kvm_clock_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86/kvm_pv_test.c
index 78878b3a27252..78878b3a27252 100644
--- a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c
+++ b/tools/testing/selftests/kvm/x86/kvm_pv_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/max_vcpuid_cap_test.c b/tools/testing/selftests/kvm/x86/max_vcpuid_cap_test.c
index 7e2bfb3c3f3ba..7e2bfb3c3f3ba 100644
--- a/tools/testing/selftests/kvm/x86_64/max_vcpuid_cap_test.c
+++ b/tools/testing/selftests/kvm/x86/max_vcpuid_cap_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86/monitor_mwait_test.c
index 2b550eff35f1b..2b550eff35f1b 100644
--- a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c
+++ b/tools/testing/selftests/kvm/x86/monitor_mwait_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c b/tools/testing/selftests/kvm/x86/nested_exceptions_test.c
index 3eb0313ffa397..3eb0313ffa397 100644
--- a/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c
+++ b/tools/testing/selftests/kvm/x86/nested_exceptions_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86/nx_huge_pages_test.c
index e7efb2b35f8bd..e7efb2b35f8bd 100644
--- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
+++ b/tools/testing/selftests/kvm/x86/nx_huge_pages_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh b/tools/testing/selftests/kvm/x86/nx_huge_pages_test.sh
index caad084b8bfdb..caad084b8bfdb 100755
--- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh
+++ b/tools/testing/selftests/kvm/x86/nx_huge_pages_test.sh
diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86/platform_info_test.c
index 9cbf283ebc55f..9cbf283ebc55f 100644
--- a/tools/testing/selftests/kvm/x86_64/platform_info_test.c
+++ b/tools/testing/selftests/kvm/x86/platform_info_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c b/tools/testing/selftests/kvm/x86/pmu_counters_test.c
index 698cb36989db1..698cb36989db1 100644
--- a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c
+++ b/tools/testing/selftests/kvm/x86/pmu_counters_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c
index c15513cd74d11..c15513cd74d11 100644
--- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
+++ b/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c
index 82a8d88b5338e..82a8d88b5338e 100644
--- a/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c
+++ b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/private_mem_kvm_exits_test.c b/tools/testing/selftests/kvm/x86/private_mem_kvm_exits_test.c
index 13e72fcec8dd2..13e72fcec8dd2 100644
--- a/tools/testing/selftests/kvm/x86_64/private_mem_kvm_exits_test.c
+++ b/tools/testing/selftests/kvm/x86/private_mem_kvm_exits_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c b/tools/testing/selftests/kvm/x86/recalc_apic_map_test.c
index cbc92a862ea9c..cbc92a862ea9c 100644
--- a/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c
+++ b/tools/testing/selftests/kvm/x86/recalc_apic_map_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c b/tools/testing/selftests/kvm/x86/set_boot_cpu_id.c
index 49913784bc82a..49913784bc82a 100644
--- a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c
+++ b/tools/testing/selftests/kvm/x86/set_boot_cpu_id.c
diff --git a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c b/tools/testing/selftests/kvm/x86/set_sregs_test.c
index c021c0795a966..c021c0795a966 100644
--- a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c
+++ b/tools/testing/selftests/kvm/x86/set_sregs_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/sev_init2_tests.c b/tools/testing/selftests/kvm/x86/sev_init2_tests.c
index 3fb967f40c6a1..3fb967f40c6a1 100644
--- a/tools/testing/selftests/kvm/x86_64/sev_init2_tests.c
+++ b/tools/testing/selftests/kvm/x86/sev_init2_tests.c
diff --git a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86/sev_migrate_tests.c
index 0a6dfba3905b6..0a6dfba3905b6 100644
--- a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c
+++ b/tools/testing/selftests/kvm/x86/sev_migrate_tests.c
diff --git a/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c b/tools/testing/selftests/kvm/x86/sev_smoke_test.c
index ae77698e6e976..ae77698e6e976 100644
--- a/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c
+++ b/tools/testing/selftests/kvm/x86/sev_smoke_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c b/tools/testing/selftests/kvm/x86/smaller_maxphyaddr_emulation_test.c
index fabeeaddfb3ac..fabeeaddfb3ac 100644
--- a/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c
+++ b/tools/testing/selftests/kvm/x86/smaller_maxphyaddr_emulation_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86/smm_test.c
index 55c88d664a945..55c88d664a945 100644
--- a/tools/testing/selftests/kvm/x86_64/smm_test.c
+++ b/tools/testing/selftests/kvm/x86/smm_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86/state_test.c
index 141b7fc0c965b..141b7fc0c965b 100644
--- a/tools/testing/selftests/kvm/x86_64/state_test.c
+++ b/tools/testing/selftests/kvm/x86/state_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c b/tools/testing/selftests/kvm/x86/svm_int_ctl_test.c
index 916e04248fbbd..916e04248fbbd 100644
--- a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c
+++ b/tools/testing/selftests/kvm/x86/svm_int_ctl_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c b/tools/testing/selftests/kvm/x86/svm_nested_shutdown_test.c
index 00135cbba35ea..00135cbba35ea 100644
--- a/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c
+++ b/tools/testing/selftests/kvm/x86/svm_nested_shutdown_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c b/tools/testing/selftests/kvm/x86/svm_nested_soft_inject_test.c
index 7b6481d6c0d3d..7b6481d6c0d3d 100644
--- a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
+++ b/tools/testing/selftests/kvm/x86/svm_nested_soft_inject_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c b/tools/testing/selftests/kvm/x86/svm_vmcall_test.c
index 8a62cca28cfbb..8a62cca28cfbb 100644
--- a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c
+++ b/tools/testing/selftests/kvm/x86/svm_vmcall_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86/sync_regs_test.c
index 8fa3948b0170e..8fa3948b0170e 100644
--- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/x86/sync_regs_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c b/tools/testing/selftests/kvm/x86/triple_fault_event_test.c
index 56306a19144a7..56306a19144a7 100644
--- a/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c
+++ b/tools/testing/selftests/kvm/x86/triple_fault_event_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c b/tools/testing/selftests/kvm/x86/tsc_msrs_test.c
index 12b0964f4f131..12b0964f4f131 100644
--- a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
+++ b/tools/testing/selftests/kvm/x86/tsc_msrs_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c b/tools/testing/selftests/kvm/x86/tsc_scaling_sync.c
index 59c7304f805ef..59c7304f805ef 100644
--- a/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c
+++ b/tools/testing/selftests/kvm/x86/tsc_scaling_sync.c
diff --git a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c b/tools/testing/selftests/kvm/x86/ucna_injection_test.c
index 57f157c06b393..57f157c06b393 100644
--- a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c
+++ b/tools/testing/selftests/kvm/x86/ucna_injection_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c b/tools/testing/selftests/kvm/x86/userspace_io_test.c
index 9481cbcf284f6..9481cbcf284f6 100644
--- a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c
+++ b/tools/testing/selftests/kvm/x86/userspace_io_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c b/tools/testing/selftests/kvm/x86/userspace_msr_exit_test.c
index 32b2794b78fec..32b2794b78fec 100644
--- a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c
+++ b/tools/testing/selftests/kvm/x86/userspace_msr_exit_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c b/tools/testing/selftests/kvm/x86/vmx_apic_access_test.c
index a81a24761aac0..a81a24761aac0 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c
+++ b/tools/testing/selftests/kvm/x86/vmx_apic_access_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c b/tools/testing/selftests/kvm/x86/vmx_close_while_nested_test.c
index dad988351493e..dad988351493e 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c
+++ b/tools/testing/selftests/kvm/x86/vmx_close_while_nested_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86/vmx_dirty_log_test.c
index fa512d033205f..fa512d033205f 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
+++ b/tools/testing/selftests/kvm/x86/vmx_dirty_log_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c b/tools/testing/selftests/kvm/x86/vmx_exception_with_invalid_guest_state.c
index 3fd6eceab46f5..3fd6eceab46f5 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c
+++ b/tools/testing/selftests/kvm/x86/vmx_exception_with_invalid_guest_state.c
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_invalid_nested_guest_state.c b/tools/testing/selftests/kvm/x86/vmx_invalid_nested_guest_state.c
index a100ee5f00093..a100ee5f00093 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_invalid_nested_guest_state.c
+++ b/tools/testing/selftests/kvm/x86/vmx_invalid_nested_guest_state.c
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_msrs_test.c b/tools/testing/selftests/kvm/x86/vmx_msrs_test.c
index 90720b6205f4e..90720b6205f4e 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_msrs_test.c
+++ b/tools/testing/selftests/kvm/x86/vmx_msrs_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c b/tools/testing/selftests/kvm/x86/vmx_nested_tsc_scaling_test.c
index 1759fa5cb3f29..1759fa5cb3f29 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c
+++ b/tools/testing/selftests/kvm/x86/vmx_nested_tsc_scaling_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86/vmx_pmu_caps_test.c
index a1f5ff45d518d..a1f5ff45d518d 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
+++ b/tools/testing/selftests/kvm/x86/vmx_pmu_caps_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c b/tools/testing/selftests/kvm/x86/vmx_preemption_timer_test.c
index 00dd2ac07a61e..00dd2ac07a61e 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c
+++ b/tools/testing/selftests/kvm/x86/vmx_preemption_timer_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86/vmx_set_nested_state_test.c
index 67a62a5a88951..67a62a5a88951 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
+++ b/tools/testing/selftests/kvm/x86/vmx_set_nested_state_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86/vmx_tsc_adjust_test.c
index 2ceb5c78c4427..2ceb5c78c4427 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
+++ b/tools/testing/selftests/kvm/x86/vmx_tsc_adjust_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c b/tools/testing/selftests/kvm/x86/xapic_ipi_test.c
index a76078a08ff82..a76078a08ff82 100644
--- a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c
+++ b/tools/testing/selftests/kvm/x86/xapic_ipi_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86/xapic_state_test.c
index 88bcca188799b..88bcca188799b 100644
--- a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c
+++ b/tools/testing/selftests/kvm/x86/xapic_state_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c b/tools/testing/selftests/kvm/x86/xcr0_cpuid_test.c
index c8a5c5e516619..c8a5c5e516619 100644
--- a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c
+++ b/tools/testing/selftests/kvm/x86/xcr0_cpuid_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86/xen_shinfo_test.c
index a59b3c799bb27..a59b3c799bb27 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86/xen_shinfo_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c b/tools/testing/selftests/kvm/x86/xen_vmcall_test.c
index 2585087cdf5cb..2585087cdf5cb 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c
+++ b/tools/testing/selftests/kvm/x86/xen_vmcall_test.c
diff --git a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c b/tools/testing/selftests/kvm/x86/xss_msr_test.c
index f331a4e9bae3b..f331a4e9bae3b 100644
--- a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c
+++ b/tools/testing/selftests/kvm/x86/xss_msr_test.c
diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c
index 95af2d78fd318..c0c53451a16dc 100644
--- a/tools/testing/selftests/memfd/memfd_test.c
+++ b/tools/testing/selftests/memfd/memfd_test.c
@@ -9,6 +9,7 @@
 #include <fcntl.h>
 #include <linux/memfd.h>
 #include <sched.h>
+#include <stdbool.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <signal.h>
@@ -281,6 +282,24 @@ static void *mfd_assert_mmap_shared(int fd)
 	return p;
 }
 
+static void *mfd_assert_mmap_read_shared(int fd)
+{
+	void *p;
+
+	p = mmap(NULL,
+		 mfd_def_size,
+		 PROT_READ,
+		 MAP_SHARED,
+		 fd,
+		 0);
+	if (p == MAP_FAILED) {
+		printf("mmap() failed: %m\n");
+		abort();
+	}
+
+	return p;
+}
+
 static void *mfd_assert_mmap_private(int fd)
 {
 	void *p;
@@ -979,6 +998,30 @@ static void test_seal_future_write(void)
 	close(fd);
 }
 
+static void test_seal_write_map_read_shared(void)
+{
+	int fd;
+	void *p;
+
+	printf("%s SEAL-WRITE-MAP-READ\n", memfd_str);
+
+	fd = mfd_assert_new("kern_memfd_seal_write_map_read",
+			    mfd_def_size,
+			    MFD_CLOEXEC | MFD_ALLOW_SEALING);
+
+	mfd_assert_add_seals(fd, F_SEAL_WRITE);
+	mfd_assert_has_seals(fd, F_SEAL_WRITE);
+
+	p = mfd_assert_mmap_read_shared(fd);
+
+	mfd_assert_read(fd);
+	mfd_assert_read_shared(fd);
+	mfd_fail_write(fd);
+
+	munmap(p, mfd_def_size);
+	close(fd);
+}
+
 /*
  * Test SEAL_SHRINK
  * Test whether SEAL_SHRINK actually prevents shrinking
@@ -1557,6 +1600,11 @@ static void test_share_fork(char *banner, char *b_suffix)
 	close(fd);
 }
 
+static bool pid_ns_supported(void)
+{
+	return access("/proc/self/ns/pid", F_OK) == 0;
+}
+
 int main(int argc, char **argv)
 {
 	pid_t pid;
@@ -1587,12 +1635,17 @@ int main(int argc, char **argv)
 
 	test_seal_write();
 	test_seal_future_write();
+	test_seal_write_map_read_shared();
 	test_seal_shrink();
 	test_seal_grow();
 	test_seal_resize();
 
-	test_sysctl_simple();
-	test_sysctl_nested();
+	if (pid_ns_supported()) {
+		test_sysctl_simple();
+		test_sysctl_nested();
+	} else {
+		printf("PID namespaces are not supported; skipping sysctl tests\n");
+	}
 
 	test_share_dup("SHARE-DUP", "");
 	test_share_mmap("SHARE-MMAP", "");
diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh
index c35548767756d..ecd34f364125c 100755
--- a/tools/testing/selftests/net/forwarding/local_termination.sh
+++ b/tools/testing/selftests/net/forwarding/local_termination.sh
@@ -7,7 +7,6 @@ ALL_TESTS="standalone vlan_unaware_bridge vlan_aware_bridge test_vlan \
 NUM_NETIFS=2
 PING_COUNT=1
 REQUIRE_MTOOLS=yes
-REQUIRE_MZ=no
 
 source lib.sh
 
diff --git a/tools/testing/selftests/net/lib/py/ynl.py b/tools/testing/selftests/net/lib/py/ynl.py
index a0d689d58c573..076a7e8dc3ebe 100644
--- a/tools/testing/selftests/net/lib/py/ynl.py
+++ b/tools/testing/selftests/net/lib/py/ynl.py
@@ -32,23 +32,23 @@ except ModuleNotFoundError as e:
 # Set schema='' to avoid jsonschema validation, it's slow
 #
 class EthtoolFamily(YnlFamily):
-    def __init__(self):
+    def __init__(self, recv_size=0):
         super().__init__((SPEC_PATH / Path('ethtool.yaml')).as_posix(),
-                         schema='')
+                         schema='', recv_size=recv_size)
 
 
 class RtnlFamily(YnlFamily):
-    def __init__(self):
+    def __init__(self, recv_size=0):
         super().__init__((SPEC_PATH / Path('rt_link.yaml')).as_posix(),
-                         schema='')
+                         schema='', recv_size=recv_size)
 
 
 class NetdevFamily(YnlFamily):
-    def __init__(self):
+    def __init__(self, recv_size=0):
         super().__init__((SPEC_PATH / Path('netdev.yaml')).as_posix(),
-                         schema='')
+                         schema='', recv_size=recv_size)
 
 class NetshaperFamily(YnlFamily):
-    def __init__(self):
+    def __init__(self, recv_size=0):
         super().__init__((SPEC_PATH / Path('net_shaper.yaml')).as_posix(),
-                         schema='')
+                         schema='', recv_size=recv_size)
diff --git a/tools/testing/selftests/net/netfilter/rpath.sh b/tools/testing/selftests/net/netfilter/rpath.sh
index 4485fd7675ed7..86ec4e68594dc 100755
--- a/tools/testing/selftests/net/netfilter/rpath.sh
+++ b/tools/testing/selftests/net/netfilter/rpath.sh
@@ -61,9 +61,20 @@ ip -net "$ns2" a a 192.168.42.1/24 dev d0
 ip -net "$ns1" a a fec0:42::2/64 dev v0 nodad
 ip -net "$ns2" a a fec0:42::1/64 dev d0 nodad
 
+# avoid neighbor lookups and enable martian IPv6 pings
+ns2_hwaddr=$(ip -net "$ns2" link show dev v0 | \
+	     sed -n 's, *link/ether \([^ ]*\) .*,\1,p')
+ns1_hwaddr=$(ip -net "$ns1" link show dev v0 | \
+	     sed -n 's, *link/ether \([^ ]*\) .*,\1,p')
+ip -net "$ns1" neigh add fec0:42::1 lladdr "$ns2_hwaddr" nud permanent dev v0
+ip -net "$ns1" neigh add fec0:23::1 lladdr "$ns2_hwaddr" nud permanent dev v0
+ip -net "$ns2" neigh add fec0:42::2 lladdr "$ns1_hwaddr" nud permanent dev d0
+ip -net "$ns2" neigh add fec0:23::2 lladdr "$ns1_hwaddr" nud permanent dev v0
+
 # firewall matches to test
 [ -n "$iptables" ] && {
 	common='-t raw -A PREROUTING -s 192.168.0.0/16'
+	common+=' -p icmp --icmp-type echo-request'
 	if ! ip netns exec "$ns2" "$iptables" $common -m rpfilter;then
 		echo "Cannot add rpfilter rule"
 		exit $ksft_skip
@@ -72,6 +83,7 @@ ip -net "$ns2" a a fec0:42::1/64 dev d0 nodad
 }
 [ -n "$ip6tables" ] && {
 	common='-t raw -A PREROUTING -s fec0::/16'
+	common+=' -p icmpv6 --icmpv6-type echo-request'
 	if ! ip netns exec "$ns2" "$ip6tables" $common -m rpfilter;then
 		echo "Cannot add rpfilter rule"
 		exit $ksft_skip
@@ -82,8 +94,10 @@ ip -net "$ns2" a a fec0:42::1/64 dev d0 nodad
 table inet t {
 	chain c {
 		type filter hook prerouting priority raw;
-		ip saddr 192.168.0.0/16 fib saddr . iif oif exists counter
-		ip6 saddr fec0::/16 fib saddr . iif oif exists counter
+		ip saddr 192.168.0.0/16 icmp type echo-request \
+			fib saddr . iif oif exists counter
+		ip6 saddr fec0::/16 icmpv6 type echo-request \
+			fib saddr . iif oif exists counter
 	}
 }
 EOF
diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh
index cc0bfae2bafa1..960e1ab4dd04b 100755
--- a/tools/testing/selftests/net/openvswitch/openvswitch.sh
+++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh
@@ -171,8 +171,10 @@ ovs_add_netns_and_veths () {
 		ovs_add_if "$1" "$2" "$4" -u || return 1
 	fi
 
-	[ $TRACING -eq 1 ] && ovs_netns_spawn_daemon "$1" "$ns" \
-			tcpdump -i any -s 65535
+	if [ $TRACING -eq 1 ]; then
+		ovs_netns_spawn_daemon "$1" "$3" tcpdump -l -i any -s 6553
+		ovs_wait grep -q "listening on any" ${ovs_dir}/stderr
+	fi
 
 	return 0
 }
diff --git a/tools/testing/selftests/riscv/abi/pointer_masking.c b/tools/testing/selftests/riscv/abi/pointer_masking.c
index dee41b7ee3e32..059d2e87eb1f7 100644
--- a/tools/testing/selftests/riscv/abi/pointer_masking.c
+++ b/tools/testing/selftests/riscv/abi/pointer_masking.c
@@ -185,8 +185,20 @@ static void test_fork_exec(void)
 	}
 }
 
+static bool pwrite_wrapper(int fd, void *buf, size_t count, const char *msg)
+{
+	int ret = pwrite(fd, buf, count, 0);
+
+	if (ret != count) {
+		ksft_perror(msg);
+		return false;
+	}
+	return true;
+}
+
 static void test_tagged_addr_abi_sysctl(void)
 {
+	char *err_pwrite_msg = "failed to write to /proc/sys/abi/tagged_addr_disabled\n";
 	char value;
 	int fd;
 
@@ -200,14 +212,18 @@ static void test_tagged_addr_abi_sysctl(void)
 	}
 
 	value = '1';
-	pwrite(fd, &value, 1, 0);
-	ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == -EINVAL,
-			 "sysctl disabled\n");
+	if (!pwrite_wrapper(fd, &value, 1, "write '1'"))
+		ksft_test_result_fail(err_pwrite_msg);
+	else
+		ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == -EINVAL,
+				 "sysctl disabled\n");
 
 	value = '0';
-	pwrite(fd, &value, 1, 0);
-	ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == 0,
-			 "sysctl enabled\n");
+	if (!pwrite_wrapper(fd, &value, 1, "write '0'"))
+		ksft_test_result_fail(err_pwrite_msg);
+	else
+		ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == 0,
+				 "sysctl enabled\n");
 
 	set_tagged_addr_ctrl(0, false);
 
diff --git a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c b/tools/testing/selftests/riscv/vector/v_initval_nolibc.c
index 1dd94197da30c..6174ffe016dc1 100644
--- a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c
+++ b/tools/testing/selftests/riscv/vector/v_initval_nolibc.c
@@ -25,6 +25,8 @@ int main(void)
 	unsigned long vl;
 	char *datap, *tmp;
 
+	ksft_set_plan(1);
+
 	datap = malloc(MAX_VSIZE);
 	if (!datap) {
 		ksft_test_result_fail("fail to allocate memory for size = %d\n", MAX_VSIZE);
@@ -63,6 +65,8 @@ int main(void)
 	}
 
 	free(datap);
+
+	ksft_test_result_pass("tests for v_initval_nolibc pass\n");
 	ksft_exit_pass();
 	return 0;
 }
diff --git a/tools/testing/selftests/riscv/vector/vstate_prctl.c b/tools/testing/selftests/riscv/vector/vstate_prctl.c
index 895177f6bf4c8..40b3bffcbb409 100644
--- a/tools/testing/selftests/riscv/vector/vstate_prctl.c
+++ b/tools/testing/selftests/riscv/vector/vstate_prctl.c
@@ -76,6 +76,8 @@ int main(void)
 	long flag, expected;
 	long rc;
 
+	ksft_set_plan(1);
+
 	pair.key = RISCV_HWPROBE_KEY_IMA_EXT_0;
 	rc = riscv_hwprobe(&pair, 1, 0, NULL, 0);
 	if (rc < 0) {
diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c
index 37d9bf6fb7458..6f4c3f5a1c5d9 100644
--- a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c
+++ b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c
@@ -20,7 +20,7 @@ s32 BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_select_cpu, struct task_struct *p,
 		 * If we dispatch to a bogus DSQ that will fall back to the
 		 * builtin global DSQ, we fail gracefully.
 		 */
-		scx_bpf_dispatch_vtime(p, 0xcafef00d, SCX_SLICE_DFL,
+		scx_bpf_dsq_insert_vtime(p, 0xcafef00d, SCX_SLICE_DFL,
 				       p->scx.dsq_vtime, 0);
 		return cpu;
 	}
diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c
index dffc97d9cdf14..e4a55027778fd 100644
--- a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c
+++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c
@@ -17,8 +17,8 @@ s32 BPF_STRUCT_OPS(ddsp_vtimelocal_fail_select_cpu, struct task_struct *p,
 
 	if (cpu >= 0) {
 		/* Shouldn't be allowed to vtime dispatch to a builtin DSQ. */
-		scx_bpf_dispatch_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL,
-				       p->scx.dsq_vtime, 0);
+		scx_bpf_dsq_insert_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL,
+					 p->scx.dsq_vtime, 0);
 		return cpu;
 	}
 
diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c
index 6a7db1502c29e..fbda6bf546712 100644
--- a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c
+++ b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c
@@ -43,9 +43,12 @@ void BPF_STRUCT_OPS(dsp_local_on_dispatch, s32 cpu, struct task_struct *prev)
 	if (!p)
 		return;
 
-	target = bpf_get_prandom_u32() % nr_cpus;
+	if (p->nr_cpus_allowed == nr_cpus)
+		target = bpf_get_prandom_u32() % nr_cpus;
+	else
+		target = scx_bpf_task_cpu(p);
 
-	scx_bpf_dispatch(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0);
+	scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0);
 	bpf_task_release(p);
 }
 
diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.c b/tools/testing/selftests/sched_ext/dsp_local_on.c
index 472851b568548..0ff27e57fe430 100644
--- a/tools/testing/selftests/sched_ext/dsp_local_on.c
+++ b/tools/testing/selftests/sched_ext/dsp_local_on.c
@@ -34,9 +34,10 @@ static enum scx_test_status run(void *ctx)
 	/* Just sleeping is fine, plenty of scheduling events happening */
 	sleep(1);
 
-	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_ERROR));
 	bpf_link__destroy(link);
 
+	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_UNREG));
+
 	return SCX_TEST_PASS;
 }
 
@@ -50,7 +51,7 @@ static void cleanup(void *ctx)
 struct scx_test dsp_local_on = {
 	.name = "dsp_local_on",
 	.description = "Verify we can directly dispatch tasks to a local DSQs "
-		       "from osp.dispatch()",
+		       "from ops.dispatch()",
 	.setup = setup,
 	.run = run,
 	.cleanup = cleanup,
diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c
index 1efb50d61040a..a7cf868d5e311 100644
--- a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c
+++ b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c
@@ -31,7 +31,7 @@ void BPF_STRUCT_OPS(enq_select_cpu_fails_enqueue, struct task_struct *p,
 	/* Can only call from ops.select_cpu() */
 	scx_bpf_select_cpu_dfl(p, 0, 0, &found);
 
-	scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
 }
 
 SEC(".struct_ops.link")
diff --git a/tools/testing/selftests/sched_ext/exit.bpf.c b/tools/testing/selftests/sched_ext/exit.bpf.c
index d75d4faf07f6d..4bc36182d3ffc 100644
--- a/tools/testing/selftests/sched_ext/exit.bpf.c
+++ b/tools/testing/selftests/sched_ext/exit.bpf.c
@@ -33,7 +33,7 @@ void BPF_STRUCT_OPS(exit_enqueue, struct task_struct *p, u64 enq_flags)
 	if (exit_point == EXIT_ENQUEUE)
 		EXIT_CLEANLY();
 
-	scx_bpf_dispatch(p, DSQ_ID, SCX_SLICE_DFL, enq_flags);
+	scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags);
 }
 
 void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p)
@@ -41,7 +41,7 @@ void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p)
 	if (exit_point == EXIT_DISPATCH)
 		EXIT_CLEANLY();
 
-	scx_bpf_consume(DSQ_ID);
+	scx_bpf_dsq_move_to_local(DSQ_ID);
 }
 
 void BPF_STRUCT_OPS(exit_enable, struct task_struct *p)
diff --git a/tools/testing/selftests/sched_ext/maximal.bpf.c b/tools/testing/selftests/sched_ext/maximal.bpf.c
index 4d4cd8d966dba..430f5e13bf554 100644
--- a/tools/testing/selftests/sched_ext/maximal.bpf.c
+++ b/tools/testing/selftests/sched_ext/maximal.bpf.c
@@ -12,6 +12,8 @@
 
 char _license[] SEC("license") = "GPL";
 
+#define DSQ_ID 0
+
 s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu,
 		   u64 wake_flags)
 {
@@ -20,7 +22,7 @@ s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu,
 
 void BPF_STRUCT_OPS(maximal_enqueue, struct task_struct *p, u64 enq_flags)
 {
-	scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+	scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags);
 }
 
 void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags)
@@ -28,7 +30,7 @@ void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags)
 
 void BPF_STRUCT_OPS(maximal_dispatch, s32 cpu, struct task_struct *prev)
 {
-	scx_bpf_consume(SCX_DSQ_GLOBAL);
+	scx_bpf_dsq_move_to_local(DSQ_ID);
 }
 
 void BPF_STRUCT_OPS(maximal_runnable, struct task_struct *p, u64 enq_flags)
@@ -123,7 +125,7 @@ void BPF_STRUCT_OPS(maximal_cgroup_set_weight, struct cgroup *cgrp, u32 weight)
 
 s32 BPF_STRUCT_OPS_SLEEPABLE(maximal_init)
 {
-	return 0;
+	return scx_bpf_create_dsq(DSQ_ID, -1);
 }
 
 void BPF_STRUCT_OPS(maximal_exit, struct scx_exit_info *info)
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c
index f171ac4709706..13d0f5be788d1 100644
--- a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c
+++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c
@@ -30,7 +30,7 @@ void BPF_STRUCT_OPS(select_cpu_dfl_enqueue, struct task_struct *p,
 	}
 	scx_bpf_put_idle_cpumask(idle_mask);
 
-	scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
 }
 
 SEC(".struct_ops.link")
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c
index 9efdbb7da9288..815f1d5d61ac4 100644
--- a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c
+++ b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c
@@ -67,7 +67,7 @@ void BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_enqueue, struct task_struct *p,
 		saw_local = true;
 	}
 
-	scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, enq_flags);
+	scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, enq_flags);
 }
 
 s32 BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_init_task,
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c
index 59bfc4f36167a..4bb99699e9209 100644
--- a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c
+++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c
@@ -29,7 +29,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_select_cpu, struct task_struct *p,
 	cpu = prev_cpu;
 
 dispatch:
-	scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, 0);
+	scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, 0);
 	return cpu;
 }
 
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c
index 3bbd5fcdfb18e..2a75de11b2cfd 100644
--- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c
+++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c
@@ -18,7 +18,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_bad_dsq_select_cpu, struct task_struct *p
 		   s32 prev_cpu, u64 wake_flags)
 {
 	/* Dispatching to a random DSQ should fail. */
-	scx_bpf_dispatch(p, 0xcafef00d, SCX_SLICE_DFL, 0);
+	scx_bpf_dsq_insert(p, 0xcafef00d, SCX_SLICE_DFL, 0);
 
 	return prev_cpu;
 }
diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c
index 0fda57fe0ecfa..99d075695c974 100644
--- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c
+++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c
@@ -18,8 +18,8 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_dbl_dsp_select_cpu, struct task_struct *p
 		   s32 prev_cpu, u64 wake_flags)
 {
 	/* Dispatching twice in a row is disallowed. */
-	scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
-	scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
+	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
+	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0);
 
 	return prev_cpu;
 }
diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c
index e6c67bcf5e6e3..bfcb96cd4954b 100644
--- a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c
+++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c
@@ -2,8 +2,8 @@
 /*
  * A scheduler that validates that enqueue flags are properly stored and
  * applied at dispatch time when a task is directly dispatched from
- * ops.select_cpu(). We validate this by using scx_bpf_dispatch_vtime(), and
- * making the test a very basic vtime scheduler.
+ * ops.select_cpu(). We validate this by using scx_bpf_dsq_insert_vtime(),
+ * and making the test a very basic vtime scheduler.
  *
  * Copyright (c) 2024 Meta Platforms, Inc. and affiliates.
  * Copyright (c) 2024 David Vernet <dvernet@meta.com>
@@ -47,13 +47,13 @@ s32 BPF_STRUCT_OPS(select_cpu_vtime_select_cpu, struct task_struct *p,
 	cpu = prev_cpu;
 	scx_bpf_test_and_clear_cpu_idle(cpu);
 ddsp:
-	scx_bpf_dispatch_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0);
+	scx_bpf_dsq_insert_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0);
 	return cpu;
 }
 
 void BPF_STRUCT_OPS(select_cpu_vtime_dispatch, s32 cpu, struct task_struct *p)
 {
-	if (scx_bpf_consume(VTIME_DSQ))
+	if (scx_bpf_dsq_move_to_local(VTIME_DSQ))
 		consumed = true;
 }
 
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json
index 996448afe31b3..91d120548bf50 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json
@@ -78,10 +78,10 @@
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
-        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 protocol ip flow map key dst rshift 0xff",
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 protocol ip flow map key dst rshift 0x1f",
         "expExitCode": "0",
         "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 protocol ip prio 1 flow",
-        "matchPattern": "filter parent ffff: protocol ip pref 1 flow chain [0-9]+ handle 0x1 map keys dst rshift 255 baseclass",
+        "matchPattern": "filter parent ffff: protocol ip pref 1 flow chain [0-9]+ handle 0x1 map keys dst rshift 31 baseclass",
         "matchCount": "1",
         "teardown": [
             "$TC qdisc del dev $DEV1 ingress"
diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c
index 8b66387e5f35c..4403cc4eba302 100644
--- a/tools/tracing/rtla/src/timerlat_hist.c
+++ b/tools/tracing/rtla/src/timerlat_hist.c
@@ -282,6 +282,21 @@ static void timerlat_hist_header(struct osnoise_tool *tool)
 }
 
 /*
+ * format_summary_value - format a line of summary value (min, max or avg)
+ * of hist data
+ */
+static void format_summary_value(struct trace_seq *seq,
+				 int count,
+				 unsigned long long val,
+				 bool avg)
+{
+	if (count)
+		trace_seq_printf(seq, "%9llu ", avg ? val / count : val);
+	else
+		trace_seq_printf(seq, "%9c ", '-');
+}
+
+/*
  * timerlat_print_summary - print the summary of the hist data to the output
  */
 static void
@@ -328,29 +343,23 @@ timerlat_print_summary(struct timerlat_hist_params *params,
 		if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
 			continue;
 
-		if (!params->no_irq) {
-			if (data->hist[cpu].irq_count)
-				trace_seq_printf(trace->seq, "%9llu ",
-						data->hist[cpu].min_irq);
-			else
-				trace_seq_printf(trace->seq, "        - ");
-		}
+		if (!params->no_irq)
+			format_summary_value(trace->seq,
+					     data->hist[cpu].irq_count,
+					     data->hist[cpu].min_irq,
+					     false);
 
-		if (!params->no_thread) {
-			if (data->hist[cpu].thread_count)
-				trace_seq_printf(trace->seq, "%9llu ",
-						data->hist[cpu].min_thread);
-			else
-				trace_seq_printf(trace->seq, "        - ");
-		}
+		if (!params->no_thread)
+			format_summary_value(trace->seq,
+					     data->hist[cpu].thread_count,
+					     data->hist[cpu].min_thread,
+					     false);
 
-		if (params->user_hist) {
-			if (data->hist[cpu].user_count)
-				trace_seq_printf(trace->seq, "%9llu ",
-						data->hist[cpu].min_user);
-			else
-				trace_seq_printf(trace->seq, "        - ");
-		}
+		if (params->user_hist)
+			format_summary_value(trace->seq,
+					     data->hist[cpu].user_count,
+					     data->hist[cpu].min_user,
+					     false);
 	}
 	trace_seq_printf(trace->seq, "\n");
 
@@ -364,29 +373,23 @@ timerlat_print_summary(struct timerlat_hist_params *params,
 		if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
 			continue;
 
-		if (!params->no_irq) {
-			if (data->hist[cpu].irq_count)
-				trace_seq_printf(trace->seq, "%9llu ",
-						 data->hist[cpu].sum_irq / data->hist[cpu].irq_count);
-			else
-				trace_seq_printf(trace->seq, "        - ");
-		}
+		if (!params->no_irq)
+			format_summary_value(trace->seq,
+					     data->hist[cpu].irq_count,
+					     data->hist[cpu].sum_irq,
+					     true);
 
-		if (!params->no_thread) {
-			if (data->hist[cpu].thread_count)
-				trace_seq_printf(trace->seq, "%9llu ",
-						 data->hist[cpu].sum_thread / data->hist[cpu].thread_count);
-			else
-				trace_seq_printf(trace->seq, "        - ");
-		}
+		if (!params->no_thread)
+			format_summary_value(trace->seq,
+					     data->hist[cpu].thread_count,
+					     data->hist[cpu].sum_thread,
+					     true);
 
-		if (params->user_hist) {
-			if (data->hist[cpu].user_count)
-				trace_seq_printf(trace->seq, "%9llu ",
-						 data->hist[cpu].sum_user / data->hist[cpu].user_count);
-			else
-				trace_seq_printf(trace->seq, "        - ");
-		}
+		if (params->user_hist)
+			format_summary_value(trace->seq,
+					     data->hist[cpu].user_count,
+					     data->hist[cpu].sum_user,
+					     true);
 	}
 	trace_seq_printf(trace->seq, "\n");
 
@@ -400,29 +403,23 @@ timerlat_print_summary(struct timerlat_hist_params *params,
 		if (!data->hist[cpu].irq_count && !data->hist[cpu].thread_count)
 			continue;
 
-		if (!params->no_irq) {
-			if (data->hist[cpu].irq_count)
-				trace_seq_printf(trace->seq, "%9llu ",
-						 data->hist[cpu].max_irq);
-			else
-				trace_seq_printf(trace->seq, "        - ");
-		}
+		if (!params->no_irq)
+			format_summary_value(trace->seq,
+					     data->hist[cpu].irq_count,
+					     data->hist[cpu].max_irq,
+					     false);
 
-		if (!params->no_thread) {
-			if (data->hist[cpu].thread_count)
-				trace_seq_printf(trace->seq, "%9llu ",
-						data->hist[cpu].max_thread);
-			else
-				trace_seq_printf(trace->seq, "        - ");
-		}
+		if (!params->no_thread)
+			format_summary_value(trace->seq,
+					     data->hist[cpu].thread_count,
+					     data->hist[cpu].max_thread,
+					     false);
 
-		if (params->user_hist) {
-			if (data->hist[cpu].user_count)
-				trace_seq_printf(trace->seq, "%9llu ",
-						data->hist[cpu].max_user);
-			else
-				trace_seq_printf(trace->seq, "        - ");
-		}
+		if (params->user_hist)
+			format_summary_value(trace->seq,
+					     data->hist[cpu].user_count,
+					     data->hist[cpu].max_user,
+					     false);
 	}
 	trace_seq_printf(trace->seq, "\n");
 	trace_seq_do_printf(trace->seq);
@@ -506,16 +503,22 @@ timerlat_print_stats_all(struct timerlat_hist_params *params,
 		trace_seq_printf(trace->seq, "min:  ");
 
 	if (!params->no_irq)
-		trace_seq_printf(trace->seq, "%9llu ",
-				 sum.min_irq);
+		format_summary_value(trace->seq,
+				     sum.irq_count,
+				     sum.min_irq,
+				     false);
 
 	if (!params->no_thread)
-		trace_seq_printf(trace->seq, "%9llu ",
-				 sum.min_thread);
+		format_summary_value(trace->seq,
+				     sum.thread_count,
+				     sum.min_thread,
+				     false);
 
 	if (params->user_hist)
-		trace_seq_printf(trace->seq, "%9llu ",
-				 sum.min_user);
+		format_summary_value(trace->seq,
+				     sum.user_count,
+				     sum.min_user,
+				     false);
 
 	trace_seq_printf(trace->seq, "\n");
 
@@ -523,16 +526,22 @@ timerlat_print_stats_all(struct timerlat_hist_params *params,
 		trace_seq_printf(trace->seq, "avg:  ");
 
 	if (!params->no_irq)
-		trace_seq_printf(trace->seq, "%9llu ",
-				 sum.sum_irq / sum.irq_count);
+		format_summary_value(trace->seq,
+				     sum.irq_count,
+				     sum.sum_irq,
+				     true);
 
 	if (!params->no_thread)
-		trace_seq_printf(trace->seq, "%9llu ",
-				 sum.sum_thread / sum.thread_count);
+		format_summary_value(trace->seq,
+				     sum.thread_count,
+				     sum.sum_thread,
+				     true);
 
 	if (params->user_hist)
-		trace_seq_printf(trace->seq, "%9llu ",
-				 sum.sum_user / sum.user_count);
+		format_summary_value(trace->seq,
+				     sum.user_count,
+				     sum.sum_user,
+				     true);
 
 	trace_seq_printf(trace->seq, "\n");
 
@@ -540,16 +549,22 @@ timerlat_print_stats_all(struct timerlat_hist_params *params,
 		trace_seq_printf(trace->seq, "max:  ");
 
 	if (!params->no_irq)
-		trace_seq_printf(trace->seq, "%9llu ",
-				 sum.max_irq);
+		format_summary_value(trace->seq,
+				     sum.irq_count,
+				     sum.max_irq,
+				     false);
 
 	if (!params->no_thread)
-		trace_seq_printf(trace->seq, "%9llu ",
-				 sum.max_thread);
+		format_summary_value(trace->seq,
+				     sum.thread_count,
+				     sum.max_thread,
+				     false);
 
 	if (params->user_hist)
-		trace_seq_printf(trace->seq, "%9llu ",
-				 sum.max_user);
+		format_summary_value(trace->seq,
+				     sum.user_count,
+				     sum.max_user,
+				     false);
 
 	trace_seq_printf(trace->seq, "\n");
 	trace_seq_do_printf(trace->seq);