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

KVM/arm fixes for 5.3

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

228 files changed, 5860 insertions, 840 deletions

diff --git a/tools/Makefile b/tools/Makefile
index 3dfd72ae6c1a..68defd7ecf5d 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -19,6 +19,7 @@ help:
         @echo '  gpio                   - GPIO tools'
         @echo '  hv                     - tools used when in Hyper-V clients'
         @echo '  iio                    - IIO tools'
+        @echo '  intel-speed-select     - Intel Speed Select tool'
         @echo '  kvm_stat               - top-like utility for displaying kvm statistics'
         @echo '  leds                   - LEDs  tools'
         @echo '  liblockdep             - user-space wrapper for kernel locking-validator'
@@ -82,7 +83,7 @@ perf: FORCE
 selftests: FORCE
         $(call descend,testing/$@)
 
-turbostat x86_energy_perf_policy: FORCE
+turbostat x86_energy_perf_policy intel-speed-select: FORCE
         $(call descend,power/x86/$@)
 
 tmon: FORCE
@@ -115,7 +116,7 @@ liblockdep_install:
 selftests_install:
         $(call descend,testing/$(@:_install=),install)
 
-turbostat_install x86_energy_perf_policy_install:
+turbostat_install x86_energy_perf_policy_install intel-speed-select_install:
         $(call descend,power/x86/$(@:_install=),install)
 
 tmon_install:
@@ -132,7 +133,7 @@ install: acpi_install cgroup_install cpupower_install gpio_install \
                 perf_install selftests_install turbostat_install usb_install \
                 virtio_install vm_install bpf_install x86_energy_perf_policy_install \
                 tmon_install freefall_install objtool_install kvm_stat_install \
-                wmi_install pci_install debugging_install
+                wmi_install pci_install debugging_install intel-speed-select_install
 
 acpi_clean:
         $(call descend,power/acpi,clean)
@@ -162,7 +163,7 @@ perf_clean:
 selftests_clean:
         $(call descend,testing/$(@:_clean=),clean)
 
-turbostat_clean x86_energy_perf_policy_clean:
+turbostat_clean x86_energy_perf_policy_clean intel-speed-select_clean:
         $(call descend,power/x86/$(@:_clean=),clean)
 
 tmon_clean:
@@ -178,6 +179,7 @@ clean: acpi_clean cgroup_clean cpupower_clean hv_clean firewire_clean \
                 perf_clean selftests_clean turbostat_clean spi_clean usb_clean virtio_clean \
                 vm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \
                 freefall_clean build_clean libbpf_clean libsubcmd_clean liblockdep_clean \
-                gpio_clean objtool_clean leds_clean wmi_clean pci_clean firmware_clean debugging_clean
+                gpio_clean objtool_clean leds_clean wmi_clean pci_clean firmware_clean debugging_clean \
+                intel-speed-select_clean
 
 .PHONY: FORCE
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 3ef0d9051e10..7031a4bf87a0 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -74,6 +74,7 @@ static const char * const prog_type_name[] = {
         [BPF_PROG_TYPE_SK_REUSEPORT]            = "sk_reuseport",
         [BPF_PROG_TYPE_FLOW_DISSECTOR]          = "flow_dissector",
         [BPF_PROG_TYPE_CGROUP_SYSCTL]           = "cgroup_sysctl",
+        [BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE] = "raw_tracepoint_writable",
         [BPF_PROG_TYPE_CGROUP_SOCKOPT]          = "cgroup_sockopt",
 };
 
diff --git a/tools/include/linux/zalloc.h b/tools/include/linux/zalloc.h
new file mode 100644
index 000000000000..81099c84043f
--- /dev/null
+++ b/tools/include/linux/zalloc.h
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: LGPL-2.1
+#ifndef __TOOLS_LINUX_ZALLOC_H
+#define __TOOLS_LINUX_ZALLOC_H
+
+#include <stddef.h>
+
+void *zalloc(size_t size);
+void __zfree(void **ptr);
+
+#define zfree(ptr) __zfree((void **)(ptr))
+
+#endif // __TOOLS_LINUX_ZALLOC_H
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index f506c68b2612..4e455018da65 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -806,7 +806,7 @@ union bpf_attr {
  *              based on a user-provided identifier for all traffic coming from
  *              the tasks belonging to the related cgroup. See also the related
  *              kernel documentation, available from the Linux sources in file
- *              *Documentation/cgroup-v1/net_cls.rst*.
+ *              *Documentation/admin-guide/cgroup-v1/net_cls.rst*.
  *
  *              The Linux kernel has two versions for cgroups: there are
  *              cgroups v1 and cgroups v2. Both are available to users, who can
@@ -3245,7 +3245,7 @@ struct bpf_sock_addr {
         __u32 user_ip4;         /* Allows 1,2,4-byte read and 4-byte write.
                                  * Stored in network byte order.
                                  */
-        __u32 user_ip6[4];      /* Allows 1,2,4-byte read and 4,8-byte write.
+        __u32 user_ip6[4];      /* Allows 1,2,4,8-byte read and 4,8-byte write.
                                  * Stored in network byte order.
                                  */
         __u32 user_port;        /* Allows 4-byte read and write.
@@ -3257,7 +3257,7 @@ struct bpf_sock_addr {
         __u32 msg_src_ip4;      /* Allows 1,2,4-byte read and 4-byte write.
                                  * Stored in network byte order.
                                  */
-        __u32 msg_src_ip6[4];   /* Allows 1,2,4-byte read and 4,8-byte write.
+        __u32 msg_src_ip6[4];   /* Allows 1,2,4,8-byte read and 4,8-byte write.
                                  * Stored in network byte order.
                                  */
         __bpf_md_ptr(struct bpf_sock *, sk);
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index ed07789b3e62..794dd5064ae8 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -4126,8 +4126,8 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name,
         }
         attr.size = sizeof(attr);
         attr.type = type;
-        attr.config1 = (uint64_t)(void *)name; /* kprobe_func or uprobe_path */
-        attr.config2 = offset;                 /* kprobe_addr or probe_offset */
+        attr.config1 = ptr_to_u64(name); /* kprobe_func or uprobe_path */
+        attr.config2 = offset;           /* kprobe_addr or probe_offset */
 
         /* pid filter is meaningful only for uprobes */
         pfd = syscall(__NR_perf_event_open, &attr,
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index b33740221b7e..5007b5d4fd2c 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -517,7 +517,8 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
                 err = -errno;
                 goto out_socket;
         }
-        strncpy(xsk->ifname, ifname, IFNAMSIZ);
+        strncpy(xsk->ifname, ifname, IFNAMSIZ - 1);
+        xsk->ifname[IFNAMSIZ - 1] = '\0';
 
         err = xsk_set_xdp_socket_config(&xsk->config, usr_config);
         if (err)
diff --git a/tools/lib/zalloc.c b/tools/lib/zalloc.c
new file mode 100644
index 000000000000..9c856d59f56e
--- /dev/null
+++ b/tools/lib/zalloc.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: LGPL-2.1
+
+#include <stdlib.h>
+#include <linux/zalloc.h>
+
+void *zalloc(size_t size)
+{
+        return calloc(1, size);
+}
+
+void __zfree(void **ptr)
+{
+        free(*ptr);
+        *ptr = NULL;
+}
diff --git a/tools/objtool/arch.h b/tools/objtool/arch.h
index 580e344db3dd..ced3765c4f44 100644
--- a/tools/objtool/arch.h
+++ b/tools/objtool/arch.h
@@ -11,22 +11,24 @@
 #include "elf.h"
 #include "cfi.h"
 
-#define INSN_JUMP_CONDITIONAL   1
-#define INSN_JUMP_UNCONDITIONAL 2
-#define INSN_JUMP_DYNAMIC       3
-#define INSN_CALL               4
-#define INSN_CALL_DYNAMIC       5
-#define INSN_RETURN             6
-#define INSN_CONTEXT_SWITCH     7
-#define INSN_STACK              8
-#define INSN_BUG                9
-#define INSN_NOP                10
-#define INSN_STAC               11
-#define INSN_CLAC               12
-#define INSN_STD                13
-#define INSN_CLD                14
-#define INSN_OTHER              15
-#define INSN_LAST               INSN_OTHER
+enum insn_type {
+        INSN_JUMP_CONDITIONAL,
+        INSN_JUMP_UNCONDITIONAL,
+        INSN_JUMP_DYNAMIC,
+        INSN_JUMP_DYNAMIC_CONDITIONAL,
+        INSN_CALL,
+        INSN_CALL_DYNAMIC,
+        INSN_RETURN,
+        INSN_CONTEXT_SWITCH,
+        INSN_STACK,
+        INSN_BUG,
+        INSN_NOP,
+        INSN_STAC,
+        INSN_CLAC,
+        INSN_STD,
+        INSN_CLD,
+        INSN_OTHER,
+};
 
 enum op_dest_type {
         OP_DEST_REG,
@@ -68,7 +70,7 @@ void arch_initial_func_cfi_state(struct cfi_state *state);
 
 int arch_decode_instruction(struct elf *elf, struct section *sec,
                             unsigned long offset, unsigned int maxlen,
-                            unsigned int *len, unsigned char *type,
+                            unsigned int *len, enum insn_type *type,
                             unsigned long *immediate, struct stack_op *op);
 
 bool arch_callee_saved_reg(unsigned char reg);
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 584568f27a83..0567c47a91b1 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -68,7 +68,7 @@ bool arch_callee_saved_reg(unsigned char reg)
 
 int arch_decode_instruction(struct elf *elf, struct section *sec,
                             unsigned long offset, unsigned int maxlen,
-                            unsigned int *len, unsigned char *type,
+                            unsigned int *len, enum insn_type *type,
                             unsigned long *immediate, struct stack_op *op)
 {
         struct insn insn;
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 172f99195726..5f26620f13f5 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -18,6 +18,8 @@
 
 #define FAKE_JUMP_OFFSET -1
 
+#define C_JUMP_TABLE_SECTION ".rodata..c_jump_table"
+
 struct alternative {
         struct list_head list;
         struct instruction *insn;
@@ -95,6 +97,20 @@ static struct instruction *next_insn_same_func(struct objtool_file *file,
         for (insn = next_insn_same_sec(file, insn); insn;               \
              insn = next_insn_same_sec(file, insn))
 
+static bool is_sibling_call(struct instruction *insn)
+{
+        /* An indirect jump is either a sibling call or a jump to a table. */
+        if (insn->type == INSN_JUMP_DYNAMIC)
+                return list_empty(&insn->alts);
+
+        if (insn->type != INSN_JUMP_CONDITIONAL &&
+            insn->type != INSN_JUMP_UNCONDITIONAL)
+                return false;
+
+        /* add_jump_destinations() sets insn->call_dest for sibling calls. */
+        return !!insn->call_dest;
+}
+
 /*
  * This checks to see if the given function is a "noreturn" function.
  *
@@ -103,14 +119,9 @@ static struct instruction *next_insn_same_func(struct objtool_file *file,
  *
  * For local functions, we have to detect them manually by simply looking for
  * the lack of a return instruction.
- *
- * Returns:
- *  -1: error
- *   0: no dead end
- *   1: dead end
  */
-static int __dead_end_function(struct objtool_file *file, struct symbol *func,
-                               int recursion)
+static bool __dead_end_function(struct objtool_file *file, struct symbol *func,
+                                int recursion)
 {
         int i;
         struct instruction *insn;
@@ -136,30 +147,33 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func,
                 "rewind_stack_do_exit",
         };
 
+        if (!func)
+                return false;
+
         if (func->bind == STB_WEAK)
-                return 0;
+                return false;
 
         if (func->bind == STB_GLOBAL)
                 for (i = 0; i < ARRAY_SIZE(global_noreturns); i++)
                         if (!strcmp(func->name, global_noreturns[i]))
-                                return 1;
+                                return true;
 
         if (!func->len)
-                return 0;
+                return false;
 
         insn = find_insn(file, func->sec, func->offset);
         if (!insn->func)
-                return 0;
+                return false;
 
         func_for_each_insn_all(file, func, insn) {
                 empty = false;
 
                 if (insn->type == INSN_RETURN)
-                        return 0;
+                        return false;
         }
 
         if (empty)
-                return 0;
+                return false;
 
         /*
          * A function can have a sibling call instead of a return.  In that
@@ -167,40 +181,31 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func,
          * of the sibling call returns.
          */
         func_for_each_insn_all(file, func, insn) {
-                if (insn->type == INSN_JUMP_UNCONDITIONAL) {
+                if (is_sibling_call(insn)) {
                         struct instruction *dest = insn->jump_dest;
 
                         if (!dest)
                                 /* sibling call to another file */
-                                return 0;
-
-                        if (dest->func && dest->func->pfunc != insn->func->pfunc) {
+                                return false;
 
-                                /* local sibling call */
-                                if (recursion == 5) {
-                                        /*
-                                         * Infinite recursion: two functions
-                                         * have sibling calls to each other.
-                                         * This is a very rare case.  It means
-                                         * they aren't dead ends.
-                                         */
-                                        return 0;
-                                }
-
-                                return __dead_end_function(file, dest->func,
-                                                           recursion + 1);
+                        /* local sibling call */
+                        if (recursion == 5) {
+                                /*
+                                 * Infinite recursion: two functions have
+                                 * sibling calls to each other.  This is a very
+                                 * rare case.  It means they aren't dead ends.
+                                 */
+                                return false;
                         }
-                }
 
-                if (insn->type == INSN_JUMP_DYNAMIC && list_empty(&insn->alts))
-                        /* sibling call */
-                        return 0;
+                        return __dead_end_function(file, dest->func, recursion+1);
+                }
         }
 
-        return 1;
+        return true;
 }
 
-static int dead_end_function(struct objtool_file *file, struct symbol *func)
+static bool dead_end_function(struct objtool_file *file, struct symbol *func)
 {
         return __dead_end_function(file, func, 0);
 }
@@ -262,19 +267,12 @@ static int decode_instructions(struct objtool_file *file)
                         if (ret)
                                 goto err;
 
-                        if (!insn->type || insn->type > INSN_LAST) {
-                                WARN_FUNC("invalid instruction type %d",
-                                          insn->sec, insn->offset, insn->type);
-                                ret = -1;
-                                goto err;
-                        }
-
                         hash_add(file->insn_hash, &insn->hash, insn->offset);
                         list_add_tail(&insn->list, &file->insn_list);
                 }
 
                 list_for_each_entry(func, &sec->symbol_list, list) {
-                        if (func->type != STT_FUNC)
+                        if (func->type != STT_FUNC || func->alias != func)
                                 continue;
 
                         if (!find_insn(file, sec, func->offset)) {
@@ -284,8 +282,7 @@ static int decode_instructions(struct objtool_file *file)
                         }
 
                         func_for_each_insn(file, func, insn)
-                                if (!insn->func)
-                                        insn->func = func;
+                                insn->func = func;
                 }
         }
 
@@ -488,6 +485,7 @@ static const char *uaccess_safe_builtin[] = {
         /* misc */
         "csum_partial_copy_generic",
         "__memcpy_mcsafe",
+        "mcsafe_handle_tail",
         "ftrace_likely_update", /* CONFIG_TRACE_BRANCH_PROFILING */
         NULL
 };
@@ -505,7 +503,7 @@ static void add_uaccess_safe(struct objtool_file *file)
                 if (!func)
                         continue;
 
-                func->alias->uaccess_safe = true;
+                func->uaccess_safe = true;
         }
 }
 
@@ -577,13 +575,16 @@ static int add_jump_destinations(struct objtool_file *file)
                          * Retpoline jumps are really dynamic jumps in
                          * disguise, so convert them accordingly.
                          */
-                        insn->type = INSN_JUMP_DYNAMIC;
+                        if (insn->type == INSN_JUMP_UNCONDITIONAL)
+                                insn->type = INSN_JUMP_DYNAMIC;
+                        else
+                                insn->type = INSN_JUMP_DYNAMIC_CONDITIONAL;
+
                         insn->retpoline_safe = true;
                         continue;
                 } else {
-                        /* sibling call */
+                        /* external sibling call */
                         insn->call_dest = rela->sym;
-                        insn->jump_dest = NULL;
                         continue;
                 }
 
@@ -623,7 +624,7 @@ static int add_jump_destinations(struct objtool_file *file)
                          * However this code can't completely replace the
                          * read_symbols() code because this doesn't detect the
                          * case where the parent function's only reference to a
-                         * subfunction is through a switch table.
+                         * subfunction is through a jump table.
                          */
                         if (!strstr(insn->func->name, ".cold.") &&
                             strstr(insn->jump_dest->func->name, ".cold.")) {
@@ -633,9 +634,8 @@ static int add_jump_destinations(struct objtool_file *file)
                         } else if (insn->jump_dest->func->pfunc != insn->func->pfunc &&
                                    insn->jump_dest->offset == insn->jump_dest->func->offset) {
 
-                                /* sibling class */
+                                /* internal sibling call */
                                 insn->call_dest = insn->jump_dest->func;
-                                insn->jump_dest = NULL;
                         }
                 }
         }
@@ -896,20 +896,26 @@ out:
         return ret;
 }
 
-static int add_switch_table(struct objtool_file *file, struct instruction *insn,
-                            struct rela *table, struct rela *next_table)
+static int add_jump_table(struct objtool_file *file, struct instruction *insn,
+                            struct rela *table)
 {
         struct rela *rela = table;
-        struct instruction *alt_insn;
+        struct instruction *dest_insn;
         struct alternative *alt;
         struct symbol *pfunc = insn->func->pfunc;
         unsigned int prev_offset = 0;
 
-        list_for_each_entry_from(rela, &table->rela_sec->rela_list, list) {
-                if (rela == next_table)
+        /*
+         * Each @rela is a switch table relocation which points to the target
+         * instruction.
+         */
+        list_for_each_entry_from(rela, &table->sec->rela_list, list) {
+
+                /* Check for the end of the table: */
+                if (rela != table && rela->jump_table_start)
                         break;
 
-                /* Make sure the switch table entries are consecutive: */
+                /* Make sure the table entries are consecutive: */
                 if (prev_offset && rela->offset != prev_offset + 8)
                         break;
 
@@ -918,12 +924,12 @@ static int add_switch_table(struct objtool_file *file, struct instruction *insn,
                     rela->addend == pfunc->offset)
                         break;
 
-                alt_insn = find_insn(file, rela->sym->sec, rela->addend);
-                if (!alt_insn)
+                dest_insn = find_insn(file, rela->sym->sec, rela->addend);
+                if (!dest_insn)
                         break;
 
-                /* Make sure the jmp dest is in the function or subfunction: */
-                if (alt_insn->func->pfunc != pfunc)
+                /* Make sure the destination is in the same function: */
+                if (!dest_insn->func || dest_insn->func->pfunc != pfunc)
                         break;
 
                 alt = malloc(sizeof(*alt));
@@ -932,7 +938,7 @@ static int add_switch_table(struct objtool_file *file, struct instruction *insn,
                         return -1;
                 }
 
-                alt->insn = alt_insn;
+                alt->insn = dest_insn;
                 list_add_tail(&alt->list, &insn->alts);
                 prev_offset = rela->offset;
         }
@@ -947,7 +953,7 @@ static int add_switch_table(struct objtool_file *file, struct instruction *insn,
 }
 
 /*
- * find_switch_table() - Given a dynamic jump, find the switch jump table in
+ * find_jump_table() - Given a dynamic jump, find the switch jump table in
  * .rodata associated with it.
  *
  * There are 3 basic patterns:
@@ -989,13 +995,13 @@ static int add_switch_table(struct objtool_file *file, struct instruction *insn,
  *
  *    NOTE: RETPOLINE made it harder still to decode dynamic jumps.
  */
-static struct rela *find_switch_table(struct objtool_file *file,
+static struct rela *find_jump_table(struct objtool_file *file,
                                       struct symbol *func,
                                       struct instruction *insn)
 {
-        struct rela *text_rela, *rodata_rela;
+        struct rela *text_rela, *table_rela;
         struct instruction *orig_insn = insn;
-        struct section *rodata_sec;
+        struct section *table_sec;
         unsigned long table_offset;
 
         /*
@@ -1028,42 +1034,52 @@ static struct rela *find_switch_table(struct objtool_file *file,
                         continue;
 
                 table_offset = text_rela->addend;
-                rodata_sec = text_rela->sym->sec;
+                table_sec = text_rela->sym->sec;
 
                 if (text_rela->type == R_X86_64_PC32)
                         table_offset += 4;
 
                 /*
                  * Make sure the .rodata address isn't associated with a
-                 * symbol.  gcc jump tables are anonymous data.
+                 * symbol.  GCC jump tables are anonymous data.
+                 *
+                 * Also support C jump tables which are in the same format as
+                 * switch jump tables.  For objtool to recognize them, they
+                 * need to be placed in the C_JUMP_TABLE_SECTION section.  They
+                 * have symbols associated with them.
                  */
-                if (find_symbol_containing(rodata_sec, table_offset))
+                if (find_symbol_containing(table_sec, table_offset) &&
+                    strcmp(table_sec->name, C_JUMP_TABLE_SECTION))
                         continue;
 
-                rodata_rela = find_rela_by_dest(rodata_sec, table_offset);
-                if (rodata_rela) {
-                        /*
-                         * Use of RIP-relative switch jumps is quite rare, and
-                         * indicates a rare GCC quirk/bug which can leave dead
-                         * code behind.
-                         */
-                        if (text_rela->type == R_X86_64_PC32)
-                                file->ignore_unreachables = true;
+                /* Each table entry has a rela associated with it. */
+                table_rela = find_rela_by_dest(table_sec, table_offset);
+                if (!table_rela)
+                        continue;
 
-                        return rodata_rela;
-                }
+                /*
+                 * Use of RIP-relative switch jumps is quite rare, and
+                 * indicates a rare GCC quirk/bug which can leave dead code
+                 * behind.
+                 */
+                if (text_rela->type == R_X86_64_PC32)
+                        file->ignore_unreachables = true;
+
+                return table_rela;
         }
 
         return NULL;
 }
 
-
-static int add_func_switch_tables(struct objtool_file *file,
-                                  struct symbol *func)
+/*
+ * First pass: Mark the head of each jump table so that in the next pass,
+ * we know when a given jump table ends and the next one starts.
+ */
+static void mark_func_jump_tables(struct objtool_file *file,
+                                    struct symbol *func)
 {
-        struct instruction *insn, *last = NULL, *prev_jump = NULL;
-        struct rela *rela, *prev_rela = NULL;
-        int ret;
+        struct instruction *insn, *last = NULL;
+        struct rela *rela;
 
         func_for_each_insn_all(file, func, insn) {
                 if (!last)
@@ -1071,7 +1087,7 @@ static int add_func_switch_tables(struct objtool_file *file,
 
                 /*
                  * Store back-pointers for unconditional forward jumps such
-                 * that find_switch_table() can back-track using those and
+                 * that find_jump_table() can back-track using those and
                  * avoid some potentially confusing code.
                  */
                 if (insn->type == INSN_JUMP_UNCONDITIONAL && insn->jump_dest &&
@@ -1086,27 +1102,25 @@ static int add_func_switch_tables(struct objtool_file *file,
                 if (insn->type != INSN_JUMP_DYNAMIC)
                         continue;
 
-                rela = find_switch_table(file, func, insn);
-                if (!rela)
-                        continue;
-
-                /*
-                 * We found a switch table, but we don't know yet how big it
-                 * is.  Don't add it until we reach the end of the function or
-                 * the beginning of another switch table in the same function.
-                 */
-                if (prev_jump) {
-                        ret = add_switch_table(file, prev_jump, prev_rela, rela);
-                        if (ret)
-                                return ret;
+                rela = find_jump_table(file, func, insn);
+                if (rela) {
+                        rela->jump_table_start = true;
+                        insn->jump_table = rela;
                 }
-
-                prev_jump = insn;
-                prev_rela = rela;
         }
+}
+
+static int add_func_jump_tables(struct objtool_file *file,
+                                  struct symbol *func)
+{
+        struct instruction *insn;
+        int ret;
 
-        if (prev_jump) {
-                ret = add_switch_table(file, prev_jump, prev_rela, NULL);
+        func_for_each_insn_all(file, func, insn) {
+                if (!insn->jump_table)
+                        continue;
+
+                ret = add_jump_table(file, insn, insn->jump_table);
                 if (ret)
                         return ret;
         }
@@ -1119,7 +1133,7 @@ static int add_func_switch_tables(struct objtool_file *file,
  * section which contains a list of addresses within the function to jump to.
  * This finds these jump tables and adds them to the insn->alts lists.
  */
-static int add_switch_table_alts(struct objtool_file *file)
+static int add_jump_table_alts(struct objtool_file *file)
 {
         struct section *sec;
         struct symbol *func;
@@ -1133,7 +1147,8 @@ static int add_switch_table_alts(struct objtool_file *file)
                         if (func->type != STT_FUNC)
                                 continue;
 
-                        ret = add_func_switch_tables(file, func);
+                        mark_func_jump_tables(file, func);
+                        ret = add_func_jump_tables(file, func);
                         if (ret)
                                 return ret;
                 }
@@ -1277,13 +1292,18 @@ static void mark_rodata(struct objtool_file *file)
         bool found = false;
 
         /*
-         * This searches for the .rodata section or multiple .rodata.func_name
-         * sections if -fdata-sections is being used. The .str.1.1 and .str.1.8
-         * rodata sections are ignored as they don't contain jump tables.
+         * Search for the following rodata sections, each of which can
+         * potentially contain jump tables:
+         *
+         * - .rodata: can contain GCC switch tables
+         * - .rodata.<func>: same, if -fdata-sections is being used
+         * - .rodata..c_jump_table: contains C annotated jump tables
+         *
+         * .rodata.str1.* sections are ignored; they don't contain jump tables.
          */
         for_each_sec(file, sec) {
-                if (!strncmp(sec->name, ".rodata", 7) &&
-                    !strstr(sec->name, ".str1.")) {
+                if ((!strncmp(sec->name, ".rodata", 7) && !strstr(sec->name, ".str1.")) ||
+                    !strcmp(sec->name, C_JUMP_TABLE_SECTION)) {
                         sec->rodata = true;
                         found = true;
                 }
@@ -1325,7 +1345,7 @@ static int decode_sections(struct objtool_file *file)
         if (ret)
                 return ret;
 
-        ret = add_switch_table_alts(file);
+        ret = add_jump_table_alts(file);
         if (ret)
                 return ret;
 
@@ -1873,12 +1893,12 @@ static bool insn_state_match(struct instruction *insn, struct insn_state *state)
 static inline bool func_uaccess_safe(struct symbol *func)
 {
         if (func)
-                return func->alias->uaccess_safe;
+                return func->uaccess_safe;
 
         return false;
 }
 
-static inline const char *insn_dest_name(struct instruction *insn)
+static inline const char *call_dest_name(struct instruction *insn)
 {
         if (insn->call_dest)
                 return insn->call_dest->name;
@@ -1890,13 +1910,13 @@ static int validate_call(struct instruction *insn, struct insn_state *state)
 {
         if (state->uaccess && !func_uaccess_safe(insn->call_dest)) {
                 WARN_FUNC("call to %s() with UACCESS enabled",
-                                insn->sec, insn->offset, insn_dest_name(insn));
+                                insn->sec, insn->offset, call_dest_name(insn));
                 return 1;
         }
 
         if (state->df) {
                 WARN_FUNC("call to %s() with DF set",
-                                insn->sec, insn->offset, insn_dest_name(insn));
+                                insn->sec, insn->offset, call_dest_name(insn));
                 return 1;
         }
 
@@ -1920,13 +1940,12 @@ static int validate_sibling_call(struct instruction *insn, struct insn_state *st
  * each instruction and validate all the rules described in
  * tools/objtool/Documentation/stack-validation.txt.
  */
-static int validate_branch(struct objtool_file *file, struct instruction *first,
-                           struct insn_state state)
+static int validate_branch(struct objtool_file *file, struct symbol *func,
+                           struct instruction *first, struct insn_state state)
 {
         struct alternative *alt;
         struct instruction *insn, *next_insn;
         struct section *sec;
-        struct symbol *func = NULL;
         int ret;
 
         insn = first;
@@ -1947,9 +1966,6 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
                         return 1;
                 }
 
-                if (insn->func)
-                        func = insn->func->pfunc;
-
                 if (func && insn->ignore) {
                         WARN_FUNC("BUG: why am I validating an ignored function?",
                                   sec, insn->offset);
@@ -1971,7 +1987,7 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
 
                                 i = insn;
                                 save_insn = NULL;
-                                func_for_each_insn_continue_reverse(file, insn->func, i) {
+                                func_for_each_insn_continue_reverse(file, func, i) {
                                         if (i->save) {
                                                 save_insn = i;
                                                 break;
@@ -2017,7 +2033,7 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
                                 if (alt->skip_orig)
                                         skip_orig = true;
 
-                                ret = validate_branch(file, alt->insn, state);
+                                ret = validate_branch(file, func, alt->insn, state);
                                 if (ret) {
                                         if (backtrace)
                                                 BT_FUNC("(alt)", insn);
@@ -2055,7 +2071,7 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
 
                         if (state.bp_scratch) {
                                 WARN("%s uses BP as a scratch register",
-                                     insn->func->name);
+                                     func->name);
                                 return 1;
                         }
 
@@ -2067,36 +2083,28 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
                         if (ret)
                                 return ret;
 
-                        if (insn->type == INSN_CALL) {
-                                if (is_fentry_call(insn))
-                                        break;
-
-                                ret = dead_end_function(file, insn->call_dest);
-                                if (ret == 1)
-                                        return 0;
-                                if (ret == -1)
-                                        return 1;
-                        }
-
-                        if (!no_fp && func && !has_valid_stack_frame(&state)) {
+                        if (!no_fp && func && !is_fentry_call(insn) &&
+                            !has_valid_stack_frame(&state)) {
                                 WARN_FUNC("call without frame pointer save/setup",
                                           sec, insn->offset);
                                 return 1;
                         }
+
+                        if (dead_end_function(file, insn->call_dest))
+                                return 0;
+
                         break;
 
                 case INSN_JUMP_CONDITIONAL:
                 case INSN_JUMP_UNCONDITIONAL:
-                        if (func && !insn->jump_dest) {
+                        if (func && is_sibling_call(insn)) {
                                 ret = validate_sibling_call(insn, &state);
                                 if (ret)
                                         return ret;
 
-                        } else if (insn->jump_dest &&
-                                   (!func || !insn->jump_dest->func ||
-                                    insn->jump_dest->func->pfunc == func)) {
-                                ret = validate_branch(file, insn->jump_dest,
-                                                      state);
+                        } else if (insn->jump_dest) {
+                                ret = validate_branch(file, func,
+                                                      insn->jump_dest, state);
                                 if (ret) {
                                         if (backtrace)
                                                 BT_FUNC("(branch)", insn);
@@ -2110,13 +2118,17 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
                         break;
 
                 case INSN_JUMP_DYNAMIC:
-                        if (func && list_empty(&insn->alts)) {
+                case INSN_JUMP_DYNAMIC_CONDITIONAL:
+                        if (func && is_sibling_call(insn)) {
                                 ret = validate_sibling_call(insn, &state);
                                 if (ret)
                                         return ret;
                         }
 
-                        return 0;
+                        if (insn->type == INSN_JUMP_DYNAMIC)
+                                return 0;
+
+                        break;
 
                 case INSN_CONTEXT_SWITCH:
                         if (func && (!next_insn || !next_insn->hint)) {
@@ -2162,7 +2174,7 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
                         break;
 
                 case INSN_CLAC:
-                        if (!state.uaccess && insn->func) {
+                        if (!state.uaccess && func) {
                                 WARN_FUNC("redundant UACCESS disable", sec, insn->offset);
                                 return 1;
                         }
@@ -2183,7 +2195,7 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
                         break;
 
                 case INSN_CLD:
-                        if (!state.df && insn->func)
+                        if (!state.df && func)
                                 WARN_FUNC("redundant CLD", sec, insn->offset);
 
                         state.df = false;
@@ -2222,7 +2234,7 @@ static int validate_unwind_hints(struct objtool_file *file)
 
         for_each_insn(file, insn) {
                 if (insn->hint && !insn->visited) {
-                        ret = validate_branch(file, insn, state);
+                        ret = validate_branch(file, insn->func, insn, state);
                         if (ret && backtrace)
                                 BT_FUNC("<=== (hint)", insn);
                         warnings += ret;
@@ -2345,16 +2357,25 @@ static int validate_functions(struct objtool_file *file)
 
         for_each_sec(file, sec) {
                 list_for_each_entry(func, &sec->symbol_list, list) {
-                        if (func->type != STT_FUNC || func->pfunc != func)
+                        if (func->type != STT_FUNC)
+                                continue;
+
+                        if (!func->len) {
+                                WARN("%s() is missing an ELF size annotation",
+                                     func->name);
+                                warnings++;
+                        }
+
+                        if (func->pfunc != func || func->alias != func)
                                 continue;
 
                         insn = find_insn(file, sec, func->offset);
-                        if (!insn || insn->ignore)
+                        if (!insn || insn->ignore || insn->visited)
                                 continue;
 
-                        state.uaccess = func->alias->uaccess_safe;
+                        state.uaccess = func->uaccess_safe;
 
-                        ret = validate_branch(file, insn, state);
+                        ret = validate_branch(file, func, insn, state);
                         if (ret && backtrace)
                                 BT_FUNC("<=== (func)", insn);
                         warnings += ret;
@@ -2407,7 +2428,7 @@ int check(const char *_objname, bool orc)
 
         objname = _objname;
 
-        file.elf = elf_open(objname, orc ? O_RDWR : O_RDONLY);
+        file.elf = elf_read(objname, orc ? O_RDWR : O_RDONLY);
         if (!file.elf)
                 return 1;
 
diff --git a/tools/objtool/check.h b/tools/objtool/check.h
index cb60b9acf5cf..b881fafcf55d 100644
--- a/tools/objtool/check.h
+++ b/tools/objtool/check.h
@@ -31,13 +31,14 @@ struct instruction {
         struct section *sec;
         unsigned long offset;
         unsigned int len;
-        unsigned char type;
+        enum insn_type type;
         unsigned long immediate;
         bool alt_group, visited, dead_end, ignore, hint, save, restore, ignore_alts;
         bool retpoline_safe;
         struct symbol *call_dest;
         struct instruction *jump_dest;
         struct instruction *first_jump_src;
+        struct rela *jump_table;
         struct list_head alts;
         struct symbol *func;
         struct stack_op stack_op;
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index e99e1be19ad9..edba4745f25a 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -278,7 +278,7 @@ static int read_symbols(struct elf *elf)
                         }
 
                         if (sym->offset == s->offset) {
-                                if (sym->len == s->len && alias == sym)
+                                if (sym->len && sym->len == s->len && alias == sym)
                                         alias = s;
 
                                 if (sym->len >= s->len) {
@@ -385,7 +385,7 @@ static int read_relas(struct elf *elf)
                         rela->offset = rela->rela.r_offset;
                         symndx = GELF_R_SYM(rela->rela.r_info);
                         rela->sym = find_symbol_by_index(elf, symndx);
-                        rela->rela_sec = sec;
+                        rela->sec = sec;
                         if (!rela->sym) {
                                 WARN("can't find rela entry symbol %d for %s",
                                      symndx, sec->name);
@@ -401,7 +401,7 @@ static int read_relas(struct elf *elf)
         return 0;
 }
 
-struct elf *elf_open(const char *name, int flags)
+struct elf *elf_read(const char *name, int flags)
 {
         struct elf *elf;
         Elf_Cmd cmd;
@@ -463,7 +463,7 @@ struct section *elf_create_section(struct elf *elf, const char *name,
 {
         struct section *sec, *shstrtab;
         size_t size = entsize * nr;
-        struct Elf_Scn *s;
+        Elf_Scn *s;
         Elf_Data *data;
 
         sec = malloc(sizeof(*sec));
diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h
index e44ca5d51871..44150204db4d 100644
--- a/tools/objtool/elf.h
+++ b/tools/objtool/elf.h
@@ -57,11 +57,12 @@ struct rela {
         struct list_head list;
         struct hlist_node hash;
         GElf_Rela rela;
-        struct section *rela_sec;
+        struct section *sec;
         struct symbol *sym;
         unsigned int type;
         unsigned long offset;
         int addend;
+        bool jump_table_start;
 };
 
 struct elf {
@@ -74,7 +75,7 @@ struct elf {
 };
 
 
-struct elf *elf_open(const char *name, int flags);
+struct elf *elf_read(const char *name, int flags);
 struct section *find_section_by_name(struct elf *elf, const char *name);
 struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset);
 struct symbol *find_symbol_by_name(struct elf *elf, const char *name);
diff --git a/tools/pci/Makefile b/tools/pci/Makefile
index 6876ee4bd78c..4b95a5176355 100644
--- a/tools/pci/Makefile
+++ b/tools/pci/Makefile
@@ -18,7 +18,6 @@ ALL_TARGETS := pcitest
 ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS))
 
 SCRIPTS := pcitest.sh
-ALL_SCRIPTS := $(patsubst %,$(OUTPUT)%,$(SCRIPTS))
 
 all: $(ALL_PROGRAMS)
 
@@ -47,10 +46,10 @@ clean:
 
 install: $(ALL_PROGRAMS)
         install -d -m 755 $(DESTDIR)$(bindir);          \
-        for program in $(ALL_PROGRAMS) pcitest.sh; do   \
+        for program in $(ALL_PROGRAMS); do              \
                 install $$program $(DESTDIR)$(bindir);  \
         done;                                           \
-        for script in $(ALL_SCRIPTS); do                \
+        for script in $(SCRIPTS); do                    \
                 install $$script $(DESTDIR)$(bindir);   \
         done
 
diff --git a/tools/pci/pcitest.c b/tools/pci/pcitest.c
index cb7a47dfd8b6..cb1e51fcc84e 100644
--- a/tools/pci/pcitest.c
+++ b/tools/pci/pcitest.c
@@ -36,15 +36,15 @@ struct pci_test {
         unsigned long   size;
 };
 
-static void run_test(struct pci_test *test)
+static int run_test(struct pci_test *test)
 {
-        long ret;
+        int ret = -EINVAL;
         int fd;
 
         fd = open(test->device, O_RDWR);
         if (fd < 0) {
                 perror("can't open PCI Endpoint Test device");
-                return;
+                return -ENODEV;
         }
 
         if (test->barnum >= 0 && test->barnum <= 5) {
@@ -212,7 +212,7 @@ usage:
                         "\t-r                   Read buffer test\n"
                         "\t-w                   Write buffer test\n"
                         "\t-c                   Copy buffer test\n"
-                        "\t-s <size>            Size of buffer {default: 100KB}\n",
+                        "\t-s <size>            Size of buffer {default: 100KB}\n"
                         "\t-h                   Print this help message\n",
                         argv[0]);
                 return -EINVAL;
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index b6866a05edd2..ed3ecfa422e1 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -194,12 +194,13 @@ PROBE ARGUMENT
 --------------
 Each probe argument follows below syntax.
 
- [NAME=]LOCALVAR|$retval|%REG|@SYMBOL[:TYPE]
+ [NAME=]LOCALVAR|$retval|%REG|@SYMBOL[:TYPE][@user]
 
 'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.)
 '$vars' and '$params' special arguments are also available for NAME, '$vars' is expanded to the local variables (including function parameters) which can access at given probe point. '$params' is expanded to only the function parameters.
 'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo (*). Currently, basic types (u8/u16/u32/u64/s8/s16/s32/s64), hexadecimal integers (x/x8/x16/x32/x64), signedness casting (u/s), "string" and bitfield are supported. (see TYPES for detail)
 On x86 systems %REG is always the short form of the register: for example %AX. %RAX or %EAX is not valid.
+"@user" is a special attribute which means the LOCALVAR will be treated as a user-space memory. This is only valid for kprobe event.
 
 TYPES
 -----
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 6a5de44b2de9..70f1ff4e2eb4 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -18,3 +18,4 @@ tools/lib/find_bit.c
 tools/lib/bitmap.c
 tools/lib/str_error_r.c
 tools/lib/vsprintf.c
+tools/lib/zalloc.c
diff --git a/tools/perf/arch/arm/annotate/instructions.c b/tools/perf/arch/arm/annotate/instructions.c
index f64516d5b23e..c7d1a69b894f 100644
--- a/tools/perf/arch/arm/annotate/instructions.c
+++ b/tools/perf/arch/arm/annotate/instructions.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
+#include <linux/zalloc.h>
 #include <sys/types.h>
 #include <regex.h>
 
diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c
index 1ce6bdbda561..02014740a1aa 100644
--- a/tools/perf/arch/arm/util/auxtrace.c
+++ b/tools/perf/arch/arm/util/auxtrace.c
@@ -6,6 +6,7 @@
 
 #include <stdbool.h>
 #include <linux/coresight-pmu.h>
+#include <linux/zalloc.h>
 
 #include "../../util/auxtrace.h"
 #include "../../util/evlist.h"
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 2b83cc8e4796..4208974c24f8 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/log2.h>
 #include <linux/types.h>
+#include <linux/zalloc.h>
 
 #include "cs-etm.h"
 #include "../../perf.h"
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index 5ccfce87e693..2c009aa74633 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -8,6 +8,7 @@
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include <linux/log2.h>
+#include <linux/zalloc.h>
 #include <time.h>
 
 #include "../../util/cpumap.h"
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index f3824ca7c20b..1a9e22f78c22 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -1,9 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
+#include <stdlib.h>
 #include "common.h"
 #include "../util/env.h"
-#include "../util/util.h"
 #include "../util/debug.h"
+#include <linux/zalloc.h>
 
 const char *const arc_triplets[] = {
         "arc-linux-",
diff --git a/tools/perf/arch/powerpc/util/perf_regs.c b/tools/perf/arch/powerpc/util/perf_regs.c
index 34d5134681d9..f14102b85509 100644
--- a/tools/perf/arch/powerpc/util/perf_regs.c
+++ b/tools/perf/arch/powerpc/util/perf_regs.c
@@ -2,12 +2,14 @@
 #include <errno.h>
 #include <string.h>
 #include <regex.h>
+#include <linux/zalloc.h>
 
 #include "../../perf.h"
-#include "../../util/util.h"
 #include "../../util/perf_regs.h"
 #include "../../util/debug.h"
 
+#include <linux/kernel.h>
+
 const struct sample_reg sample_reg_masks[] = {
         SMPL_REG(r0, PERF_REG_POWERPC_R0),
         SMPL_REG(r1, PERF_REG_POWERPC_R1),
diff --git a/tools/perf/arch/s390/util/auxtrace.c b/tools/perf/arch/s390/util/auxtrace.c
index 44c857388897..0fe1be93f375 100644
--- a/tools/perf/arch/s390/util/auxtrace.c
+++ b/tools/perf/arch/s390/util/auxtrace.c
@@ -3,6 +3,7 @@
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include <linux/log2.h>
+#include <linux/zalloc.h>
 
 #include "../../util/evlist.h"
 #include "../../util/auxtrace.h"
diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c
index a25896135abe..8b0b018d896a 100644
--- a/tools/perf/arch/s390/util/header.c
+++ b/tools/perf/arch/s390/util/header.c
@@ -12,9 +12,10 @@
 #include <stdio.h>
 #include <string.h>
 #include <linux/ctype.h>
+#include <linux/kernel.h>
+#include <linux/zalloc.h>
 
 #include "../../util/header.h"
-#include "../../util/util.h"
 
 #define SYSINFO_MANU    "Manufacturer:"
 #define SYSINFO_TYPE    "Type:"
diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c
index 675a0213044d..a3a0b6884779 100644
--- a/tools/perf/arch/x86/util/event.c
+++ b/tools/perf/arch/x86/util/event.c
@@ -1,11 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/types.h>
 #include <linux/string.h>
+#include <linux/zalloc.h>
 
 #include "../../util/machine.h"
 #include "../../util/tool.h"
 #include "../../util/map.h"
-#include "../../util/util.h"
 #include "../../util/debug.h"
 
 #if defined(__x86_64__)
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index e6d4d9591c79..ec5c1bb84095 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -9,12 +9,12 @@
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include <linux/log2.h>
+#include <linux/zalloc.h>
 
 #include "../../util/cpumap.h"
 #include "../../util/evsel.h"
 #include "../../util/evlist.h"
 #include "../../util/session.h"
-#include "../../util/util.h"
 #include "../../util/pmu.h"
 #include "../../util/debug.h"
 #include "../../util/tsc.h"
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 9804098dcefb..609088c01e3a 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -10,6 +10,7 @@
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include <linux/log2.h>
+#include <linux/zalloc.h>
 #include <cpuid.h>
 
 #include "../../perf.h"
@@ -25,7 +26,6 @@
 #include "../../util/auxtrace.h"
 #include "../../util/tsc.h"
 #include "../../util/intel-pt.h"
-#include "../../util/util.h"
 
 #define KiB(x) ((x) * 1024)
 #define MiB(x) ((x) * 1024 * 1024)
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index 3666c0076df9..0d7b77ff0ae6 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -2,9 +2,9 @@
 #include <errno.h>
 #include <string.h>
 #include <regex.h>
+#include <linux/zalloc.h>
 
 #include "../../perf.h"
-#include "../../util/util.h"
 #include "../../util/perf_regs.h"
 #include "../../util/debug.h"
 
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index 9aa3a674829b..a80797763e1f 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -18,6 +18,7 @@
 #include <stdlib.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
+#include <linux/zalloc.h>
 #include <sys/time.h>
 
 #include "../util/stat.h"
@@ -214,7 +215,7 @@ int bench_futex_hash(int argc, const char **argv)
                                        &worker[i].futex[nfutexes-1], t);
                 }
 
-                free(worker[i].futex);
+                zfree(&worker[i].futex);
         }
 
         print_summary();
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 8e9c4753e304..d02330a69745 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -12,6 +12,7 @@
 #include <subcmd/parse-options.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
+#include <linux/zalloc.h>
 #include <errno.h>
 #include "bench.h"
 #include "futex.h"
@@ -217,7 +218,7 @@ int bench_futex_lock_pi(int argc, const char **argv)
                                worker[i].tid, worker[i].futex, t);
 
                 if (multi)
-                        free(worker[i].futex);
+                        zfree(&worker[i].futex);
         }
 
         print_summary();
diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c
index 0251dd348124..64dc994c72ea 100644
--- a/tools/perf/bench/mem-functions.c
+++ b/tools/perf/bench/mem-functions.c
@@ -9,7 +9,6 @@
 
 #include "debug.h"
 #include "../perf.h"
-#include "../util/util.h"
 #include <subcmd/parse-options.h>
 #include "../util/header.h"
 #include "../util/cloexec.h"
@@ -24,6 +23,7 @@
 #include <sys/time.h>
 #include <errno.h>
 #include <linux/time64.h>
+#include <linux/zalloc.h>
 
 #define K 1024
 
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index a7784554a80d..a640ca7aaada 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -11,7 +11,6 @@
 
 #include "../perf.h"
 #include "../builtin.h"
-#include "../util/util.h"
 #include <subcmd/parse-options.h>
 #include "../util/cloexec.h"
 
@@ -35,6 +34,7 @@
 #include <linux/kernel.h>
 #include <linux/time64.h>
 #include <linux/numa.h>
+#include <linux/zalloc.h>
 
 #include <numa.h>
 #include <numaif.h>
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 77deb3a40596..e0aa14faf2b5 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -8,11 +8,11 @@
  */
 #include "builtin.h"
 
-#include "util/util.h"
 #include "util/color.h"
 #include <linux/list.h>
 #include "util/cache.h"
 #include <linux/rbtree.h>
+#include <linux/zalloc.h>
 #include "util/symbol.h"
 
 #include "perf.h"
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index 334c77ffc1d9..b8e7c38ef221 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -17,7 +17,6 @@
  *  epoll ... Event poll performance
  */
 #include "perf.h"
-#include "util/util.h"
 #include <subcmd/parse-options.h>
 #include "builtin.h"
 #include "bench/bench.h"
@@ -26,6 +25,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <sys/prctl.h>
+#include <linux/zalloc.h>
 
 typedef int (*bench_fn_t)(int argc, const char **argv);
 
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 9e6cc868bdb4..e3776f5c2e01 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -15,9 +15,9 @@
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/stringify.h>
+#include <linux/zalloc.h>
 #include <asm/bug.h>
 #include <sys/param.h>
-#include "util.h"
 #include "debug.h"
 #include "builtin.h"
 #include <subcmd/parse-options.h>
diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c
index d76f831f94c7..6c1284c87aaa 100644
--- a/tools/perf/builtin-config.c
+++ b/tools/perf/builtin-config.c
@@ -15,6 +15,7 @@
 #include "util/debug.h"
 #include "util/config.h"
 #include <linux/string.h>
+#include <stdlib.h>
 
 static bool use_system_config, use_user_config;
 
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index f924b46910b5..f6f5dd15bea7 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -16,12 +16,12 @@
 #include "util/tool.h"
 #include "util/sort.h"
 #include "util/symbol.h"
-#include "util/util.h"
 #include "util/data.h"
 #include "util/config.h"
 #include "util/time-utils.h"
 #include "util/annotate.h"
 #include "util/map.h"
+#include <linux/zalloc.h>
 
 #include <errno.h>
 #include <inttypes.h>
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index 9c228c55e1fb..66d5a6658daf 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -431,7 +431,7 @@ static void delete_filter_func(struct list_head *head)
         struct filter_entry *pos, *tmp;
 
         list_for_each_entry_safe(pos, tmp, head, list) {
-                list_del(&pos->list);
+                list_del_init(&pos->list);
                 free(pos);
         }
 }
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 3d29d0524a89..a83af92fb0d1 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -14,8 +14,10 @@
 #include <subcmd/help.h>
 #include "util/debug.h"
 #include <linux/kernel.h>
+#include <linux/zalloc.h>
 #include <errno.h>
 #include <stdio.h>
+#include <stdlib.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <unistd.h>
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 8e0e06d3edfc..f4591a1438b4 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -224,7 +224,7 @@ static int perf_event__repipe_sample(struct perf_tool *tool,
                                      struct perf_evsel *evsel,
                                      struct machine *machine)
 {
-        if (evsel->handler) {
+        if (evsel && evsel->handler) {
                 inject_handler f = evsel->handler;
                 return f(tool, event, sample, evsel, machine);
         }
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 9bd3829de76d..9e5e60898083 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -4,7 +4,6 @@
 
 #include "util/evlist.h"
 #include "util/evsel.h"
-#include "util/util.h"
 #include "util/config.h"
 #include "util/map.h"
 #include "util/symbol.h"
@@ -26,6 +25,7 @@
 #include <linux/kernel.h>
 #include <linux/rbtree.h>
 #include <linux/string.h>
+#include <linux/zalloc.h>
 #include <errno.h>
 #include <inttypes.h>
 #include <locale.h>
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index dbb6f737a3e2..b33c83489120 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -5,7 +5,6 @@
 #include "util/evsel.h"
 #include "util/evlist.h"
 #include "util/term.h"
-#include "util/util.h"
 #include "util/cache.h"
 #include "util/symbol.h"
 #include "util/thread.h"
@@ -32,6 +31,7 @@
 
 #include <linux/kernel.h>
 #include <linux/time64.h>
+#include <linux/zalloc.h>
 #include <errno.h>
 #include <inttypes.h>
 #include <poll.h>
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index b9810a8d350a..574e30ec6d7c 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -6,7 +6,6 @@
 
 #include "util/evlist.h"
 #include "util/evsel.h"
-#include "util/util.h"
 #include "util/cache.h"
 #include "util/symbol.h"
 #include "util/thread.h"
@@ -30,6 +29,7 @@
 #include <linux/list.h>
 #include <linux/hash.h>
 #include <linux/kernel.h>
+#include <linux/zalloc.h>
 
 static struct perf_session *session;
 
@@ -454,7 +454,7 @@ broken:
                 /* broken lock sequence, discard it */
                 ls->discard = 1;
                 bad_hist[BROKEN_ACQUIRE]++;
-                list_del(&seq->list);
+                list_del_init(&seq->list);
                 free(seq);
                 goto end;
         default:
@@ -515,7 +515,7 @@ static int report_lock_acquired_event(struct perf_evsel *evsel,
                 /* broken lock sequence, discard it */
                 ls->discard = 1;
                 bad_hist[BROKEN_ACQUIRED]++;
-                list_del(&seq->list);
+                list_del_init(&seq->list);
                 free(seq);
                 goto end;
         default:
@@ -570,7 +570,7 @@ static int report_lock_contended_event(struct perf_evsel *evsel,
                 /* broken lock sequence, discard it */
                 ls->discard = 1;
                 bad_hist[BROKEN_CONTENDED]++;
-                list_del(&seq->list);
+                list_del_init(&seq->list);
                 free(seq);
                 goto end;
         default:
@@ -639,7 +639,7 @@ static int report_lock_release_event(struct perf_evsel *evsel,
 
         ls->nr_release++;
 free_seq:
-        list_del(&seq->list);
+        list_del_init(&seq->list);
         free(seq);
 end:
         return 0;
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 8bb124e55c6d..6418782951a4 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -19,7 +19,6 @@
 #include "perf.h"
 #include "builtin.h"
 #include "namespaces.h"
-#include "util/util.h"
 #include "util/strlist.h"
 #include "util/strfilter.h"
 #include "util/symbol.h"
@@ -28,6 +27,7 @@
 #include "util/probe-finder.h"
 #include "util/probe-event.h"
 #include "util/probe-file.h"
+#include <linux/zalloc.h>
 
 #define DEFAULT_VAR_FILTER "!__k???tab_* & !__crc_*"
 #define DEFAULT_FUNC_FILTER "!_*"
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index dca55997934e..8779cee58185 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -11,7 +11,6 @@
 #include "perf.h"
 
 #include "util/build-id.h"
-#include "util/util.h"
 #include <subcmd/parse-options.h>
 #include "util/parse-events.h"
 #include "util/config.h"
@@ -54,6 +53,7 @@
 #include <sys/mman.h>
 #include <sys/wait.h>
 #include <linux/time64.h>
+#include <linux/zalloc.h>
 
 struct switch_output {
         bool             enabled;
@@ -1110,7 +1110,7 @@ record__switch_output(struct record *rec, bool at_exit)
                 rec->switch_output.cur_file = n;
                 if (rec->switch_output.filenames[n]) {
                         remove(rec->switch_output.filenames[n]);
-                        free(rec->switch_output.filenames[n]);
+                        zfree(&rec->switch_output.filenames[n]);
                 }
                 rec->switch_output.filenames[n] = new_filename;
         } else {
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index aef59f318a67..abf0b9b8f566 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -8,7 +8,6 @@
  */
 #include "builtin.h"
 
-#include "util/util.h"
 #include "util/config.h"
 
 #include "util/annotate.h"
@@ -16,6 +15,7 @@
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include <linux/err.h>
+#include <linux/zalloc.h>
 #include "util/map.h"
 #include "util/symbol.h"
 #include "util/callchain.h"
@@ -298,7 +298,7 @@ static int process_read_event(struct perf_tool *tool,
         struct report *rep = container_of(tool, struct report, tool);
 
         if (rep->show_threads) {
-                const char *name = evsel ? perf_evsel__name(evsel) : "unknown";
+                const char *name = perf_evsel__name(evsel);
                 int err = perf_read_values_add_value(&rep->show_threads_values,
                                            event->read.pid, event->read.tid,
                                            evsel->idx,
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 1519989961ff..56d1907b1215 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -2,7 +2,6 @@
 #include "builtin.h"
 #include "perf.h"
 
-#include "util/util.h"
 #include "util/evlist.h"
 #include "util/cache.h"
 #include "util/evsel.h"
@@ -26,6 +25,7 @@
 
 #include <linux/kernel.h>
 #include <linux/log2.h>
+#include <linux/zalloc.h>
 #include <sys/prctl.h>
 #include <sys/resource.h>
 #include <inttypes.h>
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 2f6232f1bfdc..8f24865596af 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -14,7 +14,6 @@
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/trace-event.h"
-#include "util/util.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/sort.h"
@@ -34,6 +33,7 @@
 #include <linux/kernel.h>
 #include <linux/stringify.h>
 #include <linux/time64.h>
+#include <linux/zalloc.h>
 #include <sys/utsname.h>
 #include "asm/bug.h"
 #include "util/mem-events.h"
@@ -2289,6 +2289,12 @@ static int process_switch_event(struct perf_tool *tool,
         if (perf_event__process_switch(tool, event, sample, machine) < 0)
                 return -1;
 
+        if (scripting_ops && scripting_ops->process_switch)
+                scripting_ops->process_switch(event, sample, machine);
+
+        if (!script->show_switch_events)
+                return 0;
+
         thread = machine__findnew_thread(machine, sample->pid,
                                          sample->tid);
         if (thread == NULL) {
@@ -2467,7 +2473,7 @@ static int __cmd_script(struct perf_script *script)
                 script->tool.mmap = process_mmap_event;
                 script->tool.mmap2 = process_mmap2_event;
         }
-        if (script->show_switch_events)
+        if (script->show_switch_events || (scripting_ops && scripting_ops->process_switch))
                 script->tool.context_switch = process_switch_event;
         if (script->show_namespace_events)
                 script->tool.namespaces = process_namespaces_event;
@@ -3752,7 +3758,8 @@ int cmd_script(int argc, const char **argv)
                 goto out_delete;
 
         uname(&uts);
-        if (!strcmp(uts.machine, session->header.env.arch) ||
+        if (data.is_pipe ||  /* assume pipe_mode indicates native_arch */
+            !strcmp(uts.machine, session->header.env.arch) ||
             (!strcmp(uts.machine, "x86_64") &&
              !strcmp(session->header.env.arch, "i386")))
                 native_arch = true;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e5e19b461061..b55a534b4de0 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -43,7 +43,6 @@
 #include "perf.h"
 #include "builtin.h"
 #include "util/cgroup.h"
-#include "util/util.h"
 #include <subcmd/parse-options.h>
 #include "util/parse-events.h"
 #include "util/pmu.h"
@@ -67,6 +66,7 @@
 #include "asm/bug.h"
 
 #include <linux/time64.h>
+#include <linux/zalloc.h>
 #include <api/fs/fs.h>
 #include <errno.h>
 #include <signal.h>
@@ -1349,8 +1349,8 @@ static int add_default_attributes(void)
                                 fprintf(stderr,
                                         "Cannot set up top down events %s: %d\n",
                                         str, err);
-                                free(str);
                                 parse_events_print_error(&errinfo, str);
+                                free(str);
                                 return -1;
                         }
                 } else {
@@ -1586,7 +1586,7 @@ static void runtime_stat_delete(struct perf_stat_config *config)
         for (i = 0; i < config->stats_num; i++)
                 runtime_stat__exit(&config->stats[i]);
 
-        free(config->stats);
+        zfree(&config->stats);
 }
 
 static const char * const stat_report_usage[] = {
@@ -2003,7 +2003,7 @@ int cmd_stat(int argc, const char **argv)
         perf_stat__exit_aggr_mode();
         perf_evlist__free_stats(evsel_list);
 out:
-        free(stat_config.walltime_run);
+        zfree(&stat_config.walltime_run);
 
         if (smi_cost && smi_reset)
                 sysfs__write_int(FREEZE_ON_SMI_PATH, 0);
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 145a19668114..4bde3fa245d1 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -13,9 +13,6 @@
 #include <traceevent/event-parse.h>
 
 #include "builtin.h"
-
-#include "util/util.h"
-
 #include "util/color.h"
 #include <linux/list.h>
 #include "util/cache.h"
@@ -24,6 +21,7 @@
 #include <linux/kernel.h>
 #include <linux/rbtree.h>
 #include <linux/time64.h>
+#include <linux/zalloc.h>
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/callchain.h"
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 6d40a4ef58c5..b46b3c9f57a0 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -101,7 +101,7 @@ static void perf_top__resize(struct perf_top *top)
 
 static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 {
-        struct perf_evsel *evsel = hists_to_evsel(he->hists);
+        struct perf_evsel *evsel;
         struct symbol *sym;
         struct annotation *notes;
         struct map *map;
@@ -110,6 +110,8 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
         if (!he || !he->ms.sym)
                 return -1;
 
+        evsel = hists_to_evsel(he->hists);
+
         sym = he->ms.sym;
         map = he->ms.map;
 
@@ -226,7 +228,7 @@ static void perf_top__record_precise_ip(struct perf_top *top,
 static void perf_top__show_details(struct perf_top *top)
 {
         struct hist_entry *he = top->sym_filter_entry;
-        struct perf_evsel *evsel = hists_to_evsel(he->hists);
+        struct perf_evsel *evsel;
         struct annotation *notes;
         struct symbol *symbol;
         int more;
@@ -234,6 +236,8 @@ static void perf_top__show_details(struct perf_top *top)
         if (!he)
                 return;
 
+        evsel = hists_to_evsel(he->hists);
+
         symbol = he->ms.sym;
         notes = symbol__annotation(symbol);
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index d0eb7224dd36..4f0bbffee05f 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -19,6 +19,7 @@
 #include <api/fs/tracing_path.h>
 #include <bpf/bpf.h>
 #include "util/bpf_map.h"
+#include "util/rlimit.h"
 #include "builtin.h"
 #include "util/cgroup.h"
 #include "util/color.h"
@@ -61,6 +62,7 @@
 #include <linux/random.h>
 #include <linux/stringify.h>
 #include <linux/time64.h>
+#include <linux/zalloc.h>
 #include <fcntl.h>
 #include <sys/sysmacros.h>
 
@@ -1038,10 +1040,10 @@ static struct thread_trace *thread_trace__new(void)
 {
         struct thread_trace *ttrace =  zalloc(sizeof(struct thread_trace));
 
-        if (ttrace)
+        if (ttrace) {
                 ttrace->files.max = -1;
-
-        ttrace->syscall_stats = intlist__new(NULL);
+                ttrace->syscall_stats = intlist__new(NULL);
+        }
 
         return ttrace;
 }
@@ -3863,6 +3865,15 @@ int cmd_trace(int argc, const char **argv)
                 goto out;
         }
 
+        /*
+         * Parsing .perfconfig may entail creating a BPF event, that may need
+         * to create BPF maps, so bump RLIM_MEMLOCK as the default 64K setting
+         * is too small. This affects just this process, not touching the
+         * global setting. If it fails we'll get something in 'perf trace -v'
+         * to help diagnose the problem.
+         */
+        rlimit__bump_memlock();
+
         err = perf_config(trace__config, &trace);
         if (err)
                 goto out;
diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c
index f470144d1a70..bf114ca9ca87 100644
--- a/tools/perf/builtin-version.c
+++ b/tools/perf/builtin-version.c
@@ -19,6 +19,7 @@ static struct version version;
 static struct option version_options[] = {
         OPT_BOOLEAN(0, "build-options", &version.build_options,
                     "display the build options"),
+        OPT_END(),
 };
 
 static const char * const version_usage[] = {
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 2123b3cc4dcf..97e2628ea5dd 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -18,7 +18,6 @@
 #include "util/bpf-loader.h"
 #include "util/debug.h"
 #include "util/event.h"
-#include "util/util.h"
 #include <api/fs/fs.h>
 #include <api/fs/tracing_path.h>
 #include <errno.h>
@@ -30,6 +29,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 #include <linux/kernel.h>
+#include <linux/zalloc.h>
 
 const char perf_usage_string[] =
         "perf [--version] [--help] [OPTIONS] COMMAND [ARGS]";
diff --git a/tools/perf/pmu-events/arch/s390/cf_m8561/basic.json b/tools/perf/pmu-events/arch/s390/cf_m8561/basic.json
new file mode 100644
index 000000000000..17fb5241928b
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_m8561/basic.json
@@ -0,0 +1,58 @@
+[
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "0",
+                "EventName": "CPU_CYCLES",
+                "BriefDescription": "CPU Cycles",
+                "PublicDescription": "Cycle Count"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "1",
+                "EventName": "INSTRUCTIONS",
+                "BriefDescription": "Instructions",
+                "PublicDescription": "Instruction Count"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "2",
+                "EventName": "L1I_DIR_WRITES",
+                "BriefDescription": "L1I Directory Writes",
+                "PublicDescription": "Level-1 I-Cache Directory Write Count"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "3",
+                "EventName": "L1I_PENALTY_CYCLES",
+                "BriefDescription": "L1I Penalty Cycles",
+                "PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "4",
+                "EventName": "L1D_DIR_WRITES",
+                "BriefDescription": "L1D Directory Writes",
+                "PublicDescription": "Level-1 D-Cache Directory Write Count"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "5",
+                "EventName": "L1D_PENALTY_CYCLES",
+                "BriefDescription": "L1D Penalty Cycles",
+                "PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "32",
+                "EventName": "PROBLEM_STATE_CPU_CYCLES",
+                "BriefDescription": "Problem-State CPU Cycles",
+                "PublicDescription": "Problem-State Cycle Count"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "33",
+                "EventName": "PROBLEM_STATE_INSTRUCTIONS",
+                "BriefDescription": "Problem-State Instructions",
+                "PublicDescription": "Problem-State Instruction Count"
+        },
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_m8561/crypto.json b/tools/perf/pmu-events/arch/s390/cf_m8561/crypto.json
new file mode 100644
index 000000000000..db286f19e7b6
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_m8561/crypto.json
@@ -0,0 +1,114 @@
+[
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "64",
+                "EventName": "PRNG_FUNCTIONS",
+                "BriefDescription": "PRNG Functions",
+                "PublicDescription": "Total number of the PRNG functions issued by the CPU"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "65",
+                "EventName": "PRNG_CYCLES",
+                "BriefDescription": "PRNG Cycles",
+                "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "66",
+                "EventName": "PRNG_BLOCKED_FUNCTIONS",
+                "BriefDescription": "PRNG Blocked Functions",
+                "PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "67",
+                "EventName": "PRNG_BLOCKED_CYCLES",
+                "BriefDescription": "PRNG Blocked Cycles",
+                "PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "68",
+                "EventName": "SHA_FUNCTIONS",
+                "BriefDescription": "SHA Functions",
+                "PublicDescription": "Total number of SHA functions issued by the CPU"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "69",
+                "EventName": "SHA_CYCLES",
+                "BriefDescription": "SHA Cycles",
+                "PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "70",
+                "EventName": "SHA_BLOCKED_FUNCTIONS",
+                "BriefDescription": "SHA Blocked Functions",
+                "PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "71",
+                "EventName": "SHA_BLOCKED_CYCLES",
+                "BriefDescription": "SHA Bloced Cycles",
+                "PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "72",
+                "EventName": "DEA_FUNCTIONS",
+                "BriefDescription": "DEA Functions",
+                "PublicDescription": "Total number of the DEA functions issued by the CPU"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "73",
+                "EventName": "DEA_CYCLES",
+                "BriefDescription": "DEA Cycles",
+                "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "74",
+                "EventName": "DEA_BLOCKED_FUNCTIONS",
+                "BriefDescription": "DEA Blocked Functions",
+                "PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "75",
+                "EventName": "DEA_BLOCKED_CYCLES",
+                "BriefDescription": "DEA Blocked Cycles",
+                "PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "76",
+                "EventName": "AES_FUNCTIONS",
+                "BriefDescription": "AES Functions",
+                "PublicDescription": "Total number of AES functions issued by the CPU"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "77",
+                "EventName": "AES_CYCLES",
+                "BriefDescription": "AES Cycles",
+                "PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "78",
+                "EventName": "AES_BLOCKED_FUNCTIONS",
+                "BriefDescription": "AES Blocked Functions",
+                "PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "79",
+                "EventName": "AES_BLOCKED_CYCLES",
+                "BriefDescription": "AES Blocked Cycles",
+                "PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+        },
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_m8561/crypto6.json b/tools/perf/pmu-events/arch/s390/cf_m8561/crypto6.json
new file mode 100644
index 000000000000..5e36bc2468d0
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_m8561/crypto6.json
@@ -0,0 +1,30 @@
+[
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "80",
+                "EventName": "ECC_FUNCTION_COUNT",
+                "BriefDescription": "ECC Function Count",
+                "PublicDescription": "Long ECC function Count"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "81",
+                "EventName": "ECC_CYCLES_COUNT",
+                "BriefDescription": "ECC Cycles Count",
+                "PublicDescription": "Long ECC Function cycles count"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "82",
+                "EventName": "ECC_BLOCKED_FUNCTION_COUNT",
+                "BriefDescription": "Ecc Blocked Function Count",
+                "PublicDescription": "Long ECC blocked function count"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "83",
+                "EventName": "ECC_BLOCKED_CYCLES_COUNT",
+                "BriefDescription": "ECC Blocked Cycles Count",
+                "PublicDescription": "Long ECC blocked cycles count"
+        },
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_m8561/extended.json b/tools/perf/pmu-events/arch/s390/cf_m8561/extended.json
new file mode 100644
index 000000000000..89e070727e1b
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_m8561/extended.json
@@ -0,0 +1,373 @@
+[
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "128",
+                "EventName": "L1D_RO_EXCL_WRITES",
+                "BriefDescription": "L1D Read-only Exclusive Writes",
+                "PublicDescription": "A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "129",
+                "EventName": "DTLB2_WRITES",
+                "BriefDescription": "DTLB2 Writes",
+                "PublicDescription": "A translation has been written into The Translation Lookaside Buffer 2 (TLB2) and the request was made by the data cache"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "130",
+                "EventName": "DTLB2_MISSES",
+                "BriefDescription": "DTLB2 Misses",
+                "PublicDescription": "A TLB2 miss is in progress for a request made by the data cache. Incremented by one for every TLB2 miss in progress for the Level-1 Data cache on this cycle"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "131",
+                "EventName": "DTLB2_HPAGE_WRITES",
+                "BriefDescription": "DTLB2 One-Megabyte Page Writes",
+                "PublicDescription": "A translation entry was written into the Combined Region and Segment Table Entry array in the Level-2 TLB for a one-megabyte page or a Last Host Translation was done"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "132",
+                "EventName": "DTLB2_GPAGE_WRITES",
+                "BriefDescription": "DTLB2 Two-Gigabyte Page Writes",
+                "PublicDescription": "A translation entry for a two-gigabyte page was written into the Level-2 TLB"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "133",
+                "EventName": "L1D_L2D_SOURCED_WRITES",
+                "BriefDescription": "L1D L2D Sourced Writes",
+                "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "134",
+                "EventName": "ITLB2_WRITES",
+                "BriefDescription": "ITLB2 Writes",
+                "PublicDescription": "A translation entry has been written into the Translation Lookaside Buffer 2 (TLB2) and the request was made by the instruction cache"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "135",
+                "EventName": "ITLB2_MISSES",
+                "BriefDescription": "ITLB2 Misses",
+                "PublicDescription": "A TLB2 miss is in progress for a request made by the instruction cache. Incremented by one for every TLB2 miss in progress for the Level-1 Instruction cache in a cycle"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "136",
+                "EventName": "L1I_L2I_SOURCED_WRITES",
+                "BriefDescription": "L1I L2I Sourced Writes",
+                "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "137",
+                "EventName": "TLB2_PTE_WRITES",
+                "BriefDescription": "TLB2 PTE Writes",
+                "PublicDescription": "A translation entry was written into the Page Table Entry array in the Level-2 TLB"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "138",
+                "EventName": "TLB2_CRSTE_WRITES",
+                "BriefDescription": "TLB2 CRSTE Writes",
+                "PublicDescription": "Translation entries were written into the Combined Region and Segment Table Entry array and the Page Table Entry array in the Level-2 TLB"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "139",
+                "EventName": "TLB2_ENGINES_BUSY",
+                "BriefDescription": "TLB2 Engines Busy",
+                "PublicDescription": "The number of Level-2 TLB translation engines busy in a cycle"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "140",
+                "EventName": "TX_C_TEND",
+                "BriefDescription": "Completed TEND instructions in constrained TX mode",
+                "PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "141",
+                "EventName": "TX_NC_TEND",
+                "BriefDescription": "Completed TEND instructions in non-constrained TX mode",
+                "PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "143",
+                "EventName": "L1C_TLB2_MISSES",
+                "BriefDescription": "L1C TLB2 Misses",
+                "PublicDescription": "Increments by one for any cycle where a level-1 cache or level-2 TLB miss is in progress"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "144",
+                "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
+                "BriefDescription": "L1D On-Chip L3 Sourced Writes",
+                "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "145",
+                "EventName": "L1D_ONCHIP_MEMORY_SOURCED_WRITES",
+                "BriefDescription": "L1D On-Chip Memory Sourced Writes",
+                "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "146",
+                "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
+                "BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
+                "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "147",
+                "EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES",
+                "BriefDescription": "L1D On-Cluster L3 Sourced Writes",
+                "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Cluster Level-3 cache withountervention"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "148",
+                "EventName": "L1D_ONCLUSTER_MEMORY_SOURCED_WRITES",
+                "BriefDescription": "L1D On-Cluster Memory Sourced Writes",
+                "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster memory"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "149",
+                "EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES_IV",
+                "BriefDescription": "L1D On-Cluster L3 Sourced Writes with Intervention",
+                "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache with intervention"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "150",
+                "EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES",
+                "BriefDescription": "L1D Off-Cluster L3 Sourced Writes",
+                "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "151",
+                "EventName": "L1D_OFFCLUSTER_MEMORY_SOURCED_WRITES",
+                "BriefDescription": "L1D Off-Cluster Memory Sourced Writes",
+                "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Cluster memory"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "152",
+                "EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES_IV",
+                "BriefDescription": "L1D Off-Cluster L3 Sourced Writes with Intervention",
+                "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "153",
+                "EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES",
+                "BriefDescription": "L1D Off-Drawer L3 Sourced Writes",
+                "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "154",
+                "EventName": "L1D_OFFDRAWER_MEMORY_SOURCED_WRITES",
+                "BriefDescription": "L1D Off-Drawer Memory Sourced Writes",
+                "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer memory"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "155",
+                "EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES_IV",
+                "BriefDescription": "L1D Off-Drawer L3 Sourced Writes with Intervention",
+                "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "156",
+                "EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES",
+                "BriefDescription": "L1D On-Drawer L4 Sourced Writes",
+                "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer Level-4 cache"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "157",
+                "EventName": "L1D_OFFDRAWER_L4_SOURCED_WRITES",
+                "BriefDescription": "L1D Off-Drawer L4 Sourced Writes",
+                "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "158",
+                "EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_RO",
+                "BriefDescription": "L1D On-Chip L3 Sourced Writes read-only",
+                "PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip L3 but a read-only invalidate was done to remove other copies of the cache line"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "162",
+                "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
+                "BriefDescription": "L1I On-Chip L3 Sourced Writes",
+                "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache without intervention"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "163",
+                "EventName": "L1I_ONCHIP_MEMORY_SOURCED_WRITES",
+                "BriefDescription": "L1I On-Chip Memory Sourced Writes",
+                "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from On-Chip memory"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "164",
+                "EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
+                "BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
+                "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache with intervention"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "165",
+                "EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES",
+                "BriefDescription": "L1I On-Cluster L3 Sourced Writes",
+                "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache without intervention"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "166",
+                "EventName": "L1I_ONCLUSTER_MEMORY_SOURCED_WRITES",
+                "BriefDescription": "L1I On-Cluster Memory Sourced Writes",
+                "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster memory"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "167",
+                "EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES_IV",
+                "BriefDescription": "L1I On-Cluster L3 Sourced Writes with Intervention",
+                "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Cluster Level-3 cache with intervention"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "168",
+                "EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES",
+                "BriefDescription": "L1I Off-Cluster L3 Sourced Writes",
+                "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "169",
+                "EventName": "L1I_OFFCLUSTER_MEMORY_SOURCED_WRITES",
+                "BriefDescription": "L1I Off-Cluster Memory Sourced Writes",
+                "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Cluster memory"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "170",
+                "EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES_IV",
+                "BriefDescription": "L1I Off-Cluster L3 Sourced Writes with Intervention",
+                "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "171",
+                "EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES",
+                "BriefDescription": "L1I Off-Drawer L3 Sourced Writes",
+                "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "172",
+                "EventName": "L1I_OFFDRAWER_MEMORY_SOURCED_WRITES",
+                "BriefDescription": "L1I Off-Drawer Memory Sourced Writes",
+                "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer memory"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "173",
+                "EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES_IV",
+                "BriefDescription": "L1I Off-Drawer L3 Sourced Writes with Intervention",
+                "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "174",
+                "EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES",
+                "BriefDescription": "L1I On-Drawer L4 Sourced Writes",
+                "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer Level-4 cache"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "175",
+                "EventName": "L1I_OFFDRAWER_L4_SOURCED_WRITES",
+                "BriefDescription": "L1I Off-Drawer L4 Sourced Writes",
+                "PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "224",
+                "EventName": "BCD_DFP_EXECUTION_SLOTS",
+                "BriefDescription": "BCD DFP Execution Slots",
+                "PublicDescription": "Count of floating point execution slots used for finished Binary Coded Decimal to Decimal Floating Point conversions. Instructions: CDZT, CXZT, CZDT, CZXT"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "225",
+                "EventName": "VX_BCD_EXECUTION_SLOTS",
+                "BriefDescription": "VX BCD Execution Slots",
+                "PublicDescription": "Count of floating point execution slots used for finished vector arithmetic Binary Coded Decimal instructions. Instructions: VAP, VSP, VMPVMSP, VDP, VSDP, VRP, VLIP, VSRP, VPSOPVCP, VTP, VPKZ, VUPKZ, VCVB, VCVBG, VCVDVCVDG"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "226",
+                "EventName": "DECIMAL_INSTRUCTIONS",
+                "BriefDescription": "Decimal Instructions",
+                "PublicDescription": "Decimal instructions dispatched. Instructions: CVB, CVD, AP, CP, DP, ED, EDMK, MP, SRP, SP, ZAP"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "232",
+                "EventName": "LAST_HOST_TRANSLATIONS",
+                "BriefDescription": "Last host translation done",
+                "PublicDescription": "Last Host Translation done"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "243",
+                "EventName": "TX_NC_TABORT",
+                "BriefDescription": "Aborted transactions in non-constrained TX mode",
+                "PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "244",
+                "EventName": "TX_C_TABORT_NO_SPECIAL",
+                "BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
+                "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "245",
+                "EventName": "TX_C_TABORT_SPECIAL",
+                "BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
+                "PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "448",
+                "EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE",
+                "BriefDescription": "Cycle count with one thread active",
+                "PublicDescription": "Cycle count with one thread active"
+        },
+        {
+                "Unit": "CPU-M-CF",
+                "EventCode": "449",
+                "EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE",
+                "BriefDescription": "Cycle count with two threads active",
+                "PublicDescription": "Cycle count with two threads active"
+        },
+]
diff --git a/tools/perf/pmu-events/arch/s390/mapfile.csv b/tools/perf/pmu-events/arch/s390/mapfile.csv
index 78bcf7f8e206..bd3fc577139c 100644
--- a/tools/perf/pmu-events/arch/s390/mapfile.csv
+++ b/tools/perf/pmu-events/arch/s390/mapfile.csv
@@ -4,3 +4,4 @@ Family-model,Version,Filename,EventType
 ^IBM.282[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_zec12,core
 ^IBM.296[45].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z13,core
 ^IBM.390[67].*[13]\.[1-5].[[:xdigit:]]+$,3,cf_z14,core
+^IBM.856[12].*3\.6.[[:xdigit:]]+$,3,cf_m8561,core
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index 287a6f10ca48..1a91a197cafb 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -407,7 +407,7 @@ static void free_arch_std_events(void)
 
         list_for_each_entry_safe(es, next, &arch_std_events, list) {
                 FOR_ALL_EVENT_STRUCT_FIELDS(FREE_EVENT_FIELD);
-                list_del(&es->list);
+                list_del_init(&es->list);
                 free(es);
         }
 }
diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
index 4447f0d7c754..7bd73a904b4e 100644
--- a/tools/perf/scripts/python/export-to-postgresql.py
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -353,7 +353,10 @@ do_query(query, 'CREATE TABLE threads ('
                 'tid            integer)')
 do_query(query, 'CREATE TABLE comms ('
                 'id             bigint          NOT NULL,'
-                'comm           varchar(16))')
+                'comm           varchar(16),'
+                'c_thread_id    bigint,'
+                'c_time         bigint,'
+                'exec_flag      boolean)')
 do_query(query, 'CREATE TABLE comm_threads ('
                 'id             bigint          NOT NULL,'
                 'comm_id        bigint,'
@@ -479,6 +482,17 @@ do_query(query, 'CREATE TABLE pwrx ('
         'last_cstate    integer,'
         'wake_reason    integer)')
 
+do_query(query, 'CREATE TABLE context_switches ('
+                'id             bigint          NOT NULL,'
+                'machine_id     bigint,'
+                'time           bigint,'
+                'cpu            integer,'
+                'thread_out_id  bigint,'
+                'comm_out_id    bigint,'
+                'thread_in_id   bigint,'
+                'comm_in_id     bigint,'
+                'flags          integer)')
+
 do_query(query, 'CREATE VIEW machines_view AS '
         'SELECT '
                 'id,'
@@ -692,6 +706,29 @@ do_query(query, 'CREATE VIEW power_events_view AS '
         ' INNER JOIN selected_events ON selected_events.id = samples.evsel_id'
         ' ORDER BY samples.id')
 
+do_query(query, 'CREATE VIEW context_switches_view AS '
+        'SELECT '
+                'context_switches.id,'
+                'context_switches.machine_id,'
+                'context_switches.time,'
+                'context_switches.cpu,'
+                'th_out.pid AS pid_out,'
+                'th_out.tid AS tid_out,'
+                'comm_out.comm AS comm_out,'
+                'th_in.pid AS pid_in,'
+                'th_in.tid AS tid_in,'
+                'comm_in.comm AS comm_in,'
+                'CASE     WHEN context_switches.flags = 0 THEN \'in\''
+                        ' WHEN context_switches.flags = 1 THEN \'out\''
+                        ' WHEN context_switches.flags = 3 THEN \'out preempt\''
+                        ' ELSE CAST ( context_switches.flags AS VARCHAR(11) )'
+                'END AS flags'
+        ' FROM context_switches'
+        ' INNER JOIN threads AS th_out ON th_out.id   = context_switches.thread_out_id'
+        ' INNER JOIN threads AS th_in  ON th_in.id    = context_switches.thread_in_id'
+        ' INNER JOIN comms AS comm_out ON comm_out.id = context_switches.comm_out_id'
+        ' INNER JOIN comms AS comm_in  ON comm_in.id  = context_switches.comm_in_id')
+
 file_header = struct.pack("!11sii", b"PGCOPY\n\377\r\n\0", 0, 0)
 file_trailer = b"\377\377"
 
@@ -756,6 +793,7 @@ mwait_file		= open_output_file("mwait_table.bin")
 pwre_file               = open_output_file("pwre_table.bin")
 exstop_file             = open_output_file("exstop_table.bin")
 pwrx_file               = open_output_file("pwrx_table.bin")
+context_switches_file   = open_output_file("context_switches_table.bin")
 
 def trace_begin():
         printdate("Writing to intermediate files...")
@@ -763,7 +801,7 @@ def trace_begin():
         evsel_table(0, "unknown")
         machine_table(0, 0, "unknown")
         thread_table(0, 0, 0, -1, -1)
-        comm_table(0, "unknown")
+        comm_table(0, "unknown", 0, 0, 0)
         dso_table(0, 0, "unknown", "unknown", "")
         symbol_table(0, 0, 0, 0, 0, "unknown")
         sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
@@ -804,6 +842,7 @@ def trace_end():
         copy_output_file(pwre_file,             "pwre")
         copy_output_file(exstop_file,           "exstop")
         copy_output_file(pwrx_file,             "pwrx")
+        copy_output_file(context_switches_file, "context_switches")
 
         printdate("Removing intermediate files...")
         remove_output_file(evsel_file)
@@ -825,6 +864,7 @@ def trace_end():
         remove_output_file(pwre_file)
         remove_output_file(exstop_file)
         remove_output_file(pwrx_file)
+        remove_output_file(context_switches_file)
         os.rmdir(output_dir_name)
         printdate("Adding primary keys")
         do_query(query, 'ALTER TABLE selected_events ADD PRIMARY KEY (id)')
@@ -846,11 +886,14 @@ def trace_end():
         do_query(query, 'ALTER TABLE pwre            ADD PRIMARY KEY (id)')
         do_query(query, 'ALTER TABLE exstop          ADD PRIMARY KEY (id)')
         do_query(query, 'ALTER TABLE pwrx            ADD PRIMARY KEY (id)')
+        do_query(query, 'ALTER TABLE context_switches ADD PRIMARY KEY (id)')
 
         printdate("Adding foreign keys")
         do_query(query, 'ALTER TABLE threads '
                                         'ADD CONSTRAINT machinefk  FOREIGN KEY (machine_id)   REFERENCES machines   (id),'
                                         'ADD CONSTRAINT processfk  FOREIGN KEY (process_id)   REFERENCES threads    (id)')
+        do_query(query, 'ALTER TABLE comms '
+                                        'ADD CONSTRAINT threadfk   FOREIGN KEY (c_thread_id)  REFERENCES threads    (id)')
         do_query(query, 'ALTER TABLE comm_threads '
                                         'ADD CONSTRAINT commfk     FOREIGN KEY (comm_id)      REFERENCES comms      (id),'
                                         'ADD CONSTRAINT threadfk   FOREIGN KEY (thread_id)    REFERENCES threads    (id)')
@@ -881,6 +924,8 @@ def trace_end():
                                         'ADD CONSTRAINT parent_call_pathfk FOREIGN KEY (parent_call_path_id) REFERENCES call_paths (id)')
                 do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)')
                 do_query(query, 'CREATE INDEX pid_idx ON calls (parent_id)')
+                do_query(query, 'ALTER TABLE comms ADD has_calls boolean')
+                do_query(query, 'UPDATE comms SET has_calls = TRUE WHERE comms.id IN (SELECT DISTINCT comm_id FROM calls)')
         do_query(query, 'ALTER TABLE ptwrite '
                                         'ADD CONSTRAINT idfk        FOREIGN KEY (id)           REFERENCES samples   (id)')
         do_query(query, 'ALTER TABLE  cbr '
@@ -893,18 +938,26 @@ def trace_end():
                                         'ADD CONSTRAINT idfk        FOREIGN KEY (id)           REFERENCES samples   (id)')
         do_query(query, 'ALTER TABLE  pwrx '
                                         'ADD CONSTRAINT idfk        FOREIGN KEY (id)           REFERENCES samples   (id)')
+        do_query(query, 'ALTER TABLE  context_switches '
+                                        'ADD CONSTRAINT machinefk   FOREIGN KEY (machine_id)    REFERENCES machines (id),'
+                                        'ADD CONSTRAINT toutfk      FOREIGN KEY (thread_out_id) REFERENCES threads  (id),'
+                                        'ADD CONSTRAINT tinfk       FOREIGN KEY (thread_in_id)  REFERENCES threads  (id),'
+                                        'ADD CONSTRAINT coutfk      FOREIGN KEY (comm_out_id)   REFERENCES comms    (id),'
+                                        'ADD CONSTRAINT cinfk       FOREIGN KEY (comm_in_id)    REFERENCES comms    (id)')
 
         printdate("Dropping unused tables")
         if is_table_empty("ptwrite"):
                 drop("ptwrite")
         if is_table_empty("mwait") and is_table_empty("pwre") and is_table_empty("exstop") and is_table_empty("pwrx"):
+                do_query(query, 'DROP VIEW power_events_view');
                 drop("mwait")
                 drop("pwre")
                 drop("exstop")
                 drop("pwrx")
-                do_query(query, 'DROP VIEW power_events_view');
                 if is_table_empty("cbr"):
                         drop("cbr")
+        if is_table_empty("context_switches"):
+                drop("context_switches")
 
         if (unhandled_count):
                 printdate("Warning: ", unhandled_count, " unhandled events")
@@ -935,11 +988,11 @@ def thread_table(thread_id, machine_id, process_id, pid, tid, *x):
         value = struct.pack("!hiqiqiqiiii", 5, 8, thread_id, 8, machine_id, 8, process_id, 4, pid, 4, tid)
         thread_file.write(value)
 
-def comm_table(comm_id, comm_str, *x):
+def comm_table(comm_id, comm_str, thread_id, time, exec_flag, *x):
         comm_str = toserverstr(comm_str)
         n = len(comm_str)
-        fmt = "!hiqi" + str(n) + "s"
-        value = struct.pack(fmt, 2, 8, comm_id, n, comm_str)
+        fmt = "!hiqi" + str(n) + "s" + "iqiqiB"
+        value = struct.pack(fmt, 5, 8, comm_id, n, comm_str, 8, thread_id, 8, time, 1, exec_flag)
         comm_file.write(value)
 
 def comm_thread_table(comm_thread_id, comm_id, thread_id, *x):
@@ -1051,3 +1104,8 @@ def synth_data(id, config, raw_buf, *x):
                 pwrx(id, raw_buf)
         elif config == 5:
                 cbr(id, raw_buf)
+
+def context_switch_table(id, machine_id, time, cpu, thread_out_id, comm_out_id, thread_in_id, comm_in_id, flags, *x):
+        fmt = "!hiqiqiqiiiqiqiqiqii"
+        value = struct.pack(fmt, 9, 8, id, 8, machine_id, 8, time, 4, cpu, 8, thread_out_id, 8, comm_out_id, 8, thread_in_id, 8, comm_in_id, 4, flags)
+        context_switches_file.write(value)
diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py
index 3222a83f4184..8043a7272a56 100644
--- a/tools/perf/scripts/python/export-to-sqlite.py
+++ b/tools/perf/scripts/python/export-to-sqlite.py
@@ -177,7 +177,10 @@ do_query(query, 'CREATE TABLE threads ('
                 'tid            integer)')
 do_query(query, 'CREATE TABLE comms ('
                 'id             integer         NOT NULL        PRIMARY KEY,'
-                'comm           varchar(16))')
+                'comm           varchar(16),'
+                'c_thread_id    bigint,'
+                'c_time         bigint,'
+                'exec_flag      boolean)')
 do_query(query, 'CREATE TABLE comm_threads ('
                 'id             integer         NOT NULL        PRIMARY KEY,'
                 'comm_id        bigint,'
@@ -303,6 +306,17 @@ do_query(query, 'CREATE TABLE pwrx ('
                 'last_cstate    integer,'
                 'wake_reason    integer)')
 
+do_query(query, 'CREATE TABLE context_switches ('
+                'id             integer         NOT NULL        PRIMARY KEY,'
+                'machine_id     bigint,'
+                'time           bigint,'
+                'cpu            integer,'
+                'thread_out_id  bigint,'
+                'comm_out_id    bigint,'
+                'thread_in_id   bigint,'
+                'comm_in_id     bigint,'
+                'flags          integer)')
+
 # printf was added to sqlite in version 3.8.3
 sqlite_has_printf = False
 try:
@@ -527,6 +541,29 @@ do_query(query, 'CREATE VIEW power_events_view AS '
         ' INNER JOIN selected_events ON selected_events.id = evsel_id'
         ' WHERE selected_events.name IN (\'cbr\',\'mwait\',\'exstop\',\'pwre\',\'pwrx\')')
 
+do_query(query, 'CREATE VIEW context_switches_view AS '
+        'SELECT '
+                'context_switches.id,'
+                'context_switches.machine_id,'
+                'context_switches.time,'
+                'context_switches.cpu,'
+                'th_out.pid AS pid_out,'
+                'th_out.tid AS tid_out,'
+                'comm_out.comm AS comm_out,'
+                'th_in.pid AS pid_in,'
+                'th_in.tid AS tid_in,'
+                'comm_in.comm AS comm_in,'
+                'CASE     WHEN context_switches.flags = 0 THEN \'in\''
+                        ' WHEN context_switches.flags = 1 THEN \'out\''
+                        ' WHEN context_switches.flags = 3 THEN \'out preempt\''
+                        ' ELSE context_switches.flags '
+                'END AS flags'
+        ' FROM context_switches'
+        ' INNER JOIN threads AS th_out ON th_out.id   = context_switches.thread_out_id'
+        ' INNER JOIN threads AS th_in  ON th_in.id    = context_switches.thread_in_id'
+        ' INNER JOIN comms AS comm_out ON comm_out.id = context_switches.comm_out_id'
+        ' INNER JOIN comms AS comm_in  ON comm_in.id  = context_switches.comm_in_id')
+
 do_query(query, 'END TRANSACTION')
 
 evsel_query = QSqlQuery(db)
@@ -536,7 +573,7 @@ machine_query.prepare("INSERT INTO machines VALUES (?, ?, ?)")
 thread_query = QSqlQuery(db)
 thread_query.prepare("INSERT INTO threads VALUES (?, ?, ?, ?, ?)")
 comm_query = QSqlQuery(db)
-comm_query.prepare("INSERT INTO comms VALUES (?, ?)")
+comm_query.prepare("INSERT INTO comms VALUES (?, ?, ?, ?, ?)")
 comm_thread_query = QSqlQuery(db)
 comm_thread_query.prepare("INSERT INTO comm_threads VALUES (?, ?, ?)")
 dso_query = QSqlQuery(db)
@@ -568,6 +605,8 @@ exstop_query = QSqlQuery(db)
 exstop_query.prepare("INSERT INTO exstop VALUES (?, ?)")
 pwrx_query = QSqlQuery(db)
 pwrx_query.prepare("INSERT INTO pwrx VALUES (?, ?, ?, ?)")
+context_switch_query = QSqlQuery(db)
+context_switch_query.prepare("INSERT INTO context_switches VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)")
 
 def trace_begin():
         printdate("Writing records...")
@@ -576,7 +615,7 @@ def trace_begin():
         evsel_table(0, "unknown")
         machine_table(0, 0, "unknown")
         thread_table(0, 0, 0, -1, -1)
-        comm_table(0, "unknown")
+        comm_table(0, "unknown", 0, 0, 0)
         dso_table(0, 0, "unknown", "unknown", "")
         symbol_table(0, 0, 0, 0, 0, "unknown")
         sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
@@ -603,18 +642,22 @@ def trace_end():
         if perf_db_export_calls:
                 do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)')
                 do_query(query, 'CREATE INDEX pid_idx ON calls (parent_id)')
+                do_query(query, 'ALTER TABLE comms ADD has_calls boolean')
+                do_query(query, 'UPDATE comms SET has_calls = 1 WHERE comms.id IN (SELECT DISTINCT comm_id FROM calls)')
 
         printdate("Dropping unused tables")
         if is_table_empty("ptwrite"):
                 drop("ptwrite")
         if is_table_empty("mwait") and is_table_empty("pwre") and is_table_empty("exstop") and is_table_empty("pwrx"):
+                do_query(query, 'DROP VIEW power_events_view');
                 drop("mwait")
                 drop("pwre")
                 drop("exstop")
                 drop("pwrx")
-                do_query(query, 'DROP VIEW power_events_view');
                 if is_table_empty("cbr"):
                         drop("cbr")
+        if is_table_empty("context_switches"):
+                drop("context_switches")
 
         if (unhandled_count):
                 printdate("Warning: ", unhandled_count, " unhandled events")
@@ -642,7 +685,7 @@ def thread_table(*x):
         bind_exec(thread_query, 5, x)
 
 def comm_table(*x):
-        bind_exec(comm_query, 2, x)
+        bind_exec(comm_query, 5, x)
 
 def comm_thread_table(*x):
         bind_exec(comm_thread_query, 3, x)
@@ -748,3 +791,6 @@ def synth_data(id, config, raw_buf, *x):
                 pwrx(id, raw_buf)
         elif config == 5:
                 cbr(id, raw_buf)
+
+def context_switch_table(*x):
+        bind_exec(context_switch_query, 9, x)
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index 6e7934f2ac9a..61b3911d91e6 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -392,7 +392,7 @@ class FindBar():
                 self.hbox.addWidget(self.close_button)
 
                 self.bar = QWidget()
-                self.bar.setLayout(self.hbox);
+                self.bar.setLayout(self.hbox)
                 self.bar.hide()
 
         def Widget(self):
@@ -470,7 +470,7 @@ class CallGraphLevelItemBase(object):
                 self.params = params
                 self.row = row
                 self.parent_item = parent_item
-                self.query_done = False;
+                self.query_done = False
                 self.child_count = 0
                 self.child_items = []
                 if parent_item:
@@ -517,7 +517,7 @@ class CallGraphLevelTwoPlusItemBase(CallGraphLevelItemBase):
                 self.time = time
 
         def Select(self):
-                self.query_done = True;
+                self.query_done = True
                 query = QSqlQuery(self.glb.db)
                 if self.params.have_ipc:
                         ipc_str = ", SUM(insn_count), SUM(cyc_count)"
@@ -604,7 +604,7 @@ class CallGraphLevelOneItem(CallGraphLevelItemBase):
                 self.dbid = comm_id
 
         def Select(self):
-                self.query_done = True;
+                self.query_done = True
                 query = QSqlQuery(self.glb.db)
                 QueryExec(query, "SELECT thread_id, pid, tid"
                                         " FROM comm_threads"
@@ -622,9 +622,12 @@ class CallGraphRootItem(CallGraphLevelItemBase):
         def __init__(self, glb, params):
                 super(CallGraphRootItem, self).__init__(glb, params, 0, None)
                 self.dbid = 0
-                self.query_done = True;
+                self.query_done = True
+                if_has_calls = ""
+                if IsSelectable(glb.db, "comms", columns = "has_calls"):
+                        if_has_calls = " WHERE has_calls = TRUE"
                 query = QSqlQuery(glb.db)
-                QueryExec(query, "SELECT id, comm FROM comms")
+                QueryExec(query, "SELECT id, comm FROM comms" + if_has_calls)
                 while query.next():
                         if not query.value(0):
                                 continue
@@ -793,7 +796,7 @@ class CallTreeLevelTwoPlusItemBase(CallGraphLevelItemBase):
                 self.time = time
 
         def Select(self):
-                self.query_done = True;
+                self.query_done = True
                 if self.calls_id == 0:
                         comm_thread = " AND comm_id = " + str(self.comm_id) + " AND thread_id = " + str(self.thread_id)
                 else:
@@ -881,7 +884,7 @@ class CallTreeLevelOneItem(CallGraphLevelItemBase):
                 self.dbid = comm_id
 
         def Select(self):
-                self.query_done = True;
+                self.query_done = True
                 query = QSqlQuery(self.glb.db)
                 QueryExec(query, "SELECT thread_id, pid, tid"
                                         " FROM comm_threads"
@@ -899,9 +902,12 @@ class CallTreeRootItem(CallGraphLevelItemBase):
         def __init__(self, glb, params):
                 super(CallTreeRootItem, self).__init__(glb, params, 0, None)
                 self.dbid = 0
-                self.query_done = True;
+                self.query_done = True
+                if_has_calls = ""
+                if IsSelectable(glb.db, "comms", columns = "has_calls"):
+                        if_has_calls = " WHERE has_calls = TRUE"
                 query = QSqlQuery(glb.db)
-                QueryExec(query, "SELECT id, comm FROM comms")
+                QueryExec(query, "SELECT id, comm FROM comms" + if_has_calls)
                 while query.next():
                         if not query.value(0):
                                 continue
@@ -971,7 +977,7 @@ class VBox():
 
         def __init__(self, w1, w2, w3=None):
                 self.vbox = QWidget()
-                self.vbox.setLayout(QVBoxLayout());
+                self.vbox.setLayout(QVBoxLayout())
 
                 self.vbox.layout().setContentsMargins(0, 0, 0, 0)
 
@@ -1391,7 +1397,7 @@ class FetchMoreRecordsBar():
                 self.hbox.addWidget(self.close_button)
 
                 self.bar = QWidget()
-                self.bar.setLayout(self.hbox);
+                self.bar.setLayout(self.hbox)
                 self.bar.show()
 
                 self.in_progress = False
@@ -2206,7 +2212,7 @@ class ReportDialogBase(QDialog):
                 self.vbox.addLayout(self.grid)
                 self.vbox.addLayout(self.hbox)
 
-                self.setLayout(self.vbox);
+                self.setLayout(self.vbox)
 
         def Ok(self):
                 vars = self.report_vars
@@ -3139,7 +3145,7 @@ class AboutDialog(QDialog):
                 self.vbox = QVBoxLayout()
                 self.vbox.addWidget(self.text)
 
-                self.setLayout(self.vbox);
+                self.setLayout(self.vbox)
 
 # Font resize
 
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 66a82badc1d1..c3bec9d2c201 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -21,6 +21,7 @@
 #include <subcmd/parse-options.h>
 #include "string2.h"
 #include "symbol.h"
+#include "util/rlimit.h"
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <subcmd/exec-cmd.h>
@@ -727,6 +728,11 @@ int cmd_test(int argc, const char **argv)
 
         if (skip != NULL)
                 skiplist = intlist__new(skip);
+        /*
+         * Tests that create BPF maps, for instance, need more than the 64K
+         * default:
+         */
+        rlimit__bump_memlock();
 
         return __cmd_test(argc, argv, skiplist);
 }
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 077c306c1cae..f33709a79335 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include <linux/types.h>
+#include <linux/zalloc.h>
 #include <inttypes.h>
 #include <unistd.h>
 #include "tests.h"
@@ -115,8 +116,8 @@ noinline int test_dwarf_unwind__thread(struct thread *thread)
         }
 
  out:
-        free(sample.user_stack.data);
-        free(sample.user_regs.regs);
+        zfree(&sample.user_stack.data);
+        zfree(&sample.user_regs.regs);
         return err;
 }
 
diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c
index 9acc1e80b936..ee1d88650e69 100644
--- a/tools/perf/tests/expr.c
+++ b/tools/perf/tests/expr.c
@@ -3,6 +3,7 @@
 #include "util/expr.h"
 #include "tests.h"
 #include <stdlib.h>
+#include <linux/zalloc.h>
 
 static int test(struct parse_ctx *ctx, const char *e, double val2)
 {
@@ -58,7 +59,7 @@ int test__expr(struct test *t __maybe_unused, int subtest __maybe_unused)
         TEST_ASSERT_VAL("find other", other[3] == NULL);
 
         for (i = 0; i < num_other; i++)
-                free((void *)other[i]);
+                zfree(&other[i]);
         free((void *)other);
 
         return 0;
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index a039f93199e5..ca5a5f94ce79 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
+#include <stdlib.h>
 #include <bpf/libbpf.h>
 #include <util/llvm-utils.h>
 #include <util/cache.h>
diff --git a/tools/perf/tests/mem2node.c b/tools/perf/tests/mem2node.c
index d23ff1b68eba..520cc91af256 100644
--- a/tools/perf/tests/mem2node.c
+++ b/tools/perf/tests/mem2node.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include <linux/bitmap.h>
+#include <linux/zalloc.h>
 #include "cpumap.h"
 #include "mem2node.h"
 #include "tests.h"
@@ -67,7 +68,7 @@ int test__mem2node(struct test *t __maybe_unused, int subtest __maybe_unused)
         T("failed: mem2node__node", -1 == mem2node__node(&map, 0x1050));
 
         for (i = 0; i < ARRAY_SIZE(nodes); i++)
-                free(nodes[i].set);
+                zfree(&nodes[i].set);
 
         mem2node__exit(&map);
         return 0;
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index ba87e6e8d18c..0a4301a5155c 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -53,7 +53,7 @@ static void *thread_fn(void *arg)
 {
         struct thread_data *td = arg;
         ssize_t ret;
-        int go;
+        int go = 0;
 
         if (thread_init(td))
                 return NULL;
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 236ce0d6c826..361714e2583c 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <stdbool.h>
 #include <inttypes.h>
+#include <stdlib.h>
 #include <linux/bitops.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index 9b5be51e5e7b..6cdab5f4812a 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -4,6 +4,7 @@
 #include <errno.h>
 #include <time.h>
 #include <stdlib.h>
+#include <linux/zalloc.h>
 
 #include "parse-events.h"
 #include "evlist.h"
@@ -237,7 +238,7 @@ static void free_event_nodes(struct list_head *events)
 
         while (!list_empty(events)) {
                 node = list_entry(events->next, struct event_node, list);
-                list_del(&node->list);
+                list_del_init(&node->list);
                 free(node);
         }
 }
diff --git a/tools/perf/tests/thread-map.c b/tools/perf/tests/thread-map.c
index 4de1939b58ba..ccc17aced49e 100644
--- a/tools/perf/tests/thread-map.c
+++ b/tools/perf/tests/thread-map.c
@@ -6,6 +6,7 @@
 #include "tests.h"
 #include "thread_map.h"
 #include "debug.h"
+#include <linux/zalloc.h>
 
 #define NAME    (const char *) "perf"
 #define NAMEUL  (unsigned long) NAME
@@ -133,7 +134,7 @@ int test__thread_map_remove(struct test *test __maybe_unused, int subtest __mayb
                         thread_map__remove(threads, 0));
 
         for (i = 0; i < threads->nr; i++)
-                free(threads->map[i].comm);
+                zfree(&threads->map[i].comm);
 
         free(threads);
         return 0;
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index f101576d1c72..5e8834fc7dec 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -3,6 +3,7 @@
 #include <linux/rbtree.h>
 #include <inttypes.h>
 #include <string.h>
+#include <stdlib.h>
 #include "map.h"
 #include "symbol.h"
 #include "util.h"
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index 55ff05a46e0b..f80c51d53565 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -1,5 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "../util.h"
 #include "../string2.h"
 #include "../config.h"
 #include "../../perf.h"
@@ -17,6 +16,7 @@
 #include "keysyms.h"
 #include "../color.h"
 #include <linux/ctype.h>
+#include <linux/zalloc.h>
 
 static int ui_browser__percent_color(struct ui_browser *browser,
                                      double percent, bool current)
diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h
index aa5932e1d62e..dc1444136658 100644
--- a/tools/perf/ui/browser.h
+++ b/tools/perf/ui/browser.h
@@ -4,6 +4,7 @@
 
 #include <linux/types.h>
 #include <stdarg.h>
+#include <sys/types.h>
 
 #define HE_COLORSET_TOP         50
 #define HE_COLORSET_MEDIUM      51
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index b0d089a95dac..e67880bf1efe 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -1,5 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "../../util/util.h"
 #include "../browser.h"
 #include "../helpline.h"
 #include "../ui.h"
@@ -15,6 +14,7 @@
 #include <pthread.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
+#include <linux/zalloc.h>
 #include <sys/ttydefaults.h>
 #include <asm/bug.h>
 
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 33e67aa91347..a94eb0755e8b 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -9,6 +9,7 @@
 #include <linux/string.h>
 #include <sys/ttydefaults.h>
 #include <linux/time64.h>
+#include <linux/zalloc.h>
 
 #include "../../util/callchain.h"
 #include "../../util/evsel.h"
@@ -18,7 +19,6 @@
 #include "../../util/symbol.h"
 #include "../../util/pstack.h"
 #include "../../util/sort.h"
-#include "../../util/util.h"
 #include "../../util/top.h"
 #include "../../util/thread.h"
 #include "../../arch/common.h"
@@ -639,7 +639,11 @@ int hist_browser__run(struct hist_browser *browser, const char *help,
                 switch (key) {
                 case K_TIMER: {
                         u64 nr_entries;
-                        hbt->timer(hbt->arg);
+
+                        WARN_ON_ONCE(!hbt);
+
+                        if (hbt)
+                                hbt->timer(hbt->arg);
 
                         if (hist_browser__has_filter(browser) ||
                             symbol_conf.report_hierarchy)
@@ -2821,7 +2825,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 {
         struct hists *hists = evsel__hists(evsel);
         struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env, annotation_opts);
-        struct branch_info *bi;
+        struct branch_info *bi = NULL;
 #define MAX_OPTIONS  16
         char *options[MAX_OPTIONS];
         struct popup_action actions[MAX_OPTIONS];
@@ -3087,7 +3091,9 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
                         goto skip_annotation;
 
                 if (sort__mode == SORT_MODE__BRANCH) {
-                        bi = browser->he_selection->branch_info;
+
+                        if (browser->he_selection)
+                                bi = browser->he_selection->branch_info;
 
                         if (bi == NULL)
                                 goto skip_annotation;
@@ -3271,7 +3277,8 @@ static int perf_evsel_menu__run(struct perf_evsel_menu *menu,
 
                 switch (key) {
                 case K_TIMER:
-                        hbt->timer(hbt->arg);
+                        if (hbt)
+                                hbt->timer(hbt->arg);
 
                         if (!menu->lost_events_warned &&
                             menu->lost_events &&
diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c
index 5f6529c9eb8e..4c545b92e20d 100644
--- a/tools/perf/ui/browsers/map.c
+++ b/tools/perf/ui/browsers/map.c
@@ -2,6 +2,7 @@
 #include <elf.h>
 #include <inttypes.h>
 #include <sys/ttydefaults.h>
+#include <stdlib.h>
 #include <string.h>
 #include <linux/bitops.h>
 #include "../../util/util.h"
diff --git a/tools/perf/ui/browsers/res_sample.c b/tools/perf/ui/browsers/res_sample.c
index c0dd73176d42..8aa3547bb9ff 100644
--- a/tools/perf/ui/browsers/res_sample.c
+++ b/tools/perf/ui/browsers/res_sample.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Display a menu with individual samples to browse with perf script */
-#include "util.h"
 #include "hist.h"
 #include "evsel.h"
 #include "hists.h"
@@ -8,6 +7,7 @@
 #include "config.h"
 #include "time-utils.h"
 #include <linux/time64.h>
+#include <linux/zalloc.h>
 
 static u64 context_len = 10 * NSEC_PER_MSEC;
 
@@ -46,14 +46,14 @@ int res_sample_browse(struct res_sample *res_samples, int num_res,
                 if (asprintf(&names[i], "%s: CPU %d tid %d", tbuf,
                              res_samples[i].cpu, res_samples[i].tid) < 0) {
                         while (--i >= 0)
-                                free(names[i]);
+                                zfree(&names[i]);
                         free(names);
                         return -1;
                 }
         }
         choice = ui__popup_menu(num_res, names);
         for (i = 0; i < num_res; i++)
-                free(names[i]);
+                zfree(&names[i]);
         free(names);
 
         if (choice < 0 || choice >= num_res)
diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c
index 27cf3ab88d13..4d565cc14076 100644
--- a/tools/perf/ui/browsers/scripts.c
+++ b/tools/perf/ui/browsers/scripts.c
@@ -1,12 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "../../util/sort.h"
-#include "../../util/util.h"
 #include "../../util/hist.h"
 #include "../../util/debug.h"
 #include "../../util/symbol.h"
 #include "../browser.h"
 #include "../libslang.h"
 #include "config.h"
+#include <linux/zalloc.h>
 
 #define SCRIPT_NAMELEN  128
 #define SCRIPT_MAX_NO   64
@@ -142,7 +142,7 @@ static int list_scripts(char *script_name, bool *custom,
 out:
         free(buf);
         for (i = 0; i < max_std; i++)
-                free(paths[i]);
+                zfree(&paths[i]);
         return ret;
 }
 
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index df49c9ba1785..3af87c18a914 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -152,7 +152,7 @@ static int perf_gtk__annotate_symbol(GtkWidget *window, struct symbol *sym,
         gtk_container_add(GTK_CONTAINER(window), view);
 
         list_for_each_entry_safe(pos, n, &notes->src->source, al.node) {
-                list_del(&pos->al.node);
+                list_del_init(&pos->al.node);
                 disasm_line__free(pos);
         }
 
diff --git a/tools/perf/ui/gtk/util.c b/tools/perf/ui/gtk/util.c
index 7250d8101c8f..c28bdb7517ac 100644
--- a/tools/perf/ui/gtk/util.c
+++ b/tools/perf/ui/gtk/util.c
@@ -1,11 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "../util.h"
-#include "../../util/util.h"
 #include "../../util/debug.h"
 #include "gtk.h"
 
 #include <string.h>
-
+#include <linux/zalloc.h>
 
 struct perf_gtk_context *pgctx;
 
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 89393c79d870..ee7ea6deed21 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -3,7 +3,6 @@
 #include <linux/string.h>
 
 #include "../../util/callchain.h"
-#include "../../util/util.h"
 #include "../../util/hist.h"
 #include "../../util/map.h"
 #include "../../util/map_groups.h"
@@ -14,6 +13,7 @@
 #include "../../util/string2.h"
 #include "../../util/thread.h"
 #include <linux/ctype.h>
+#include <linux/zalloc.h>
 
 static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
 {
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index d4ac41679721..3ad0d3363ac6 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -2,6 +2,7 @@
 #include <errno.h>
 #include <signal.h>
 #include <stdbool.h>
+#include <stdlib.h>
 #include <linux/kernel.h>
 #ifdef HAVE_BACKTRACE_SUPPORT
 #include <execinfo.h>
diff --git a/tools/perf/ui/tui/util.c b/tools/perf/ui/tui/util.c
index b9794d6185af..fe5e571816fc 100644
--- a/tools/perf/ui/tui/util.c
+++ b/tools/perf/ui/tui/util.c
@@ -1,8 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "../../util/util.h"
 #include <signal.h>
 #include <stdbool.h>
 #include <string.h>
+#include <stdlib.h>
 #include <sys/ttydefaults.h>
 
 #include "../../util/cache.h"
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index d3408a463060..14f812bb07a7 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -20,11 +20,13 @@ perf-y += parse-events.o
 perf-y += perf_regs.o
 perf-y += path.o
 perf-y += print_binary.o
+perf-y += rlimit.o
 perf-y += argv_split.o
 perf-y += rbtree.o
 perf-y += libstring.o
 perf-y += bitmap.o
 perf-y += hweight.o
+perf-y += zalloc.o
 perf-y += smt.o
 perf-y += strbuf.o
 perf-y += string.o
@@ -241,3 +243,7 @@ $(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE
 $(OUTPUT)util/vsprintf.o: ../lib/vsprintf.c FORCE
         $(call rule_mkdir)
         $(call if_changed_dep,cc_o_c)
+
+$(OUTPUT)util/zalloc.o: ../lib/zalloc.c FORCE
+        $(call rule_mkdir)
+        $(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index ec7aaf31c2b2..ac9ad2330f93 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1119,16 +1119,14 @@ static int disasm_line__parse(char *line, const char **namep, char **rawp)
         *namep = strdup(name);
 
         if (*namep == NULL)
-                goto out_free_name;
+                goto out;
 
         (*rawp)[0] = tmp;
         *rawp = skip_spaces(*rawp);
 
         return 0;
 
-out_free_name:
-        free((void *)namep);
-        *namep = NULL;
+out:
         return -1;
 }
 
@@ -1237,8 +1235,7 @@ void disasm_line__free(struct disasm_line *dl)
                 dl->ins.ops->free(&dl->ops);
         else
                 ins__delete(&dl->ops);
-        free((void *)dl->ins.name);
-        dl->ins.name = NULL;
+        zfree(&dl->ins.name);
         annotation_line__delete(&dl->al);
 }
 
@@ -1589,7 +1586,7 @@ static void delete_last_nop(struct symbol *sym)
                                 return;
                 }
 
-                list_del(&dl->al.node);
+                list_del_init(&dl->al.node);
                 disasm_line__free(dl);
         }
 }
@@ -2466,7 +2463,7 @@ void annotated_source__purge(struct annotated_source *as)
         struct annotation_line *al, *n;
 
         list_for_each_entry_safe(al, n, &as->source, node) {
-                list_del(&al->node);
+                list_del_init(&al->node);
                 disasm_line__free(disasm_line(al));
         }
 }
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 6067267cc76c..a314e5b26e9d 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -12,6 +12,7 @@
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include <linux/log2.h>
+#include <linux/zalloc.h>
 
 #include "cpumap.h"
 #include "color.h"
@@ -19,7 +20,6 @@
 #include "evlist.h"
 #include "machine.h"
 #include "session.h"
-#include "util.h"
 #include "thread.h"
 #include "debug.h"
 #include "auxtrace.h"
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index bc215fe0b4b4..ec0af36697c4 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -24,9 +24,9 @@
 #include <stdlib.h>
 #include <stdio.h>
 #include <linux/list.h>
+#include <linux/zalloc.h>
 
 #include "../perf.h"
-#include "util.h"
 #include "evlist.h"
 #include "dso.h"
 #include "map.h"
@@ -408,7 +408,7 @@ void auxtrace_queues__free(struct auxtrace_queues *queues)
 
                         buffer = list_entry(queues->queue_array[i].head.next,
                                             struct auxtrace_buffer, list);
-                        list_del(&buffer->list);
+                        list_del_init(&buffer->list);
                         auxtrace_buffer__free(buffer);
                 }
         }
@@ -612,7 +612,7 @@ void auxtrace_index__free(struct list_head *head)
         struct auxtrace_index *auxtrace_index, *n;
 
         list_for_each_entry_safe(auxtrace_index, n, head, list) {
-                list_del(&auxtrace_index->list);
+                list_del_init(&auxtrace_index->list);
                 free(auxtrace_index);
         }
 }
@@ -1413,7 +1413,7 @@ void auxtrace_cache__free(struct auxtrace_cache *c)
                 return;
 
         auxtrace_cache__drop(c);
-        free(c->hashtable);
+        zfree(&c->hashtable);
         free(c);
 }
 
@@ -1459,12 +1459,11 @@ void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key)
 
 static void addr_filter__free_str(struct addr_filter *filt)
 {
-        free(filt->str);
+        zfree(&filt->str);
         filt->action   = NULL;
         filt->sym_from = NULL;
         filt->sym_to   = NULL;
         filt->filename = NULL;
-        filt->str      = NULL;
 }
 
 static struct addr_filter *addr_filter__new(void)
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 251d9ea6252f..c61974a50aa5 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -12,6 +12,7 @@
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
+#include <linux/zalloc.h>
 #include <errno.h>
 #include "perf.h"
 #include "debug.h"
@@ -828,7 +829,7 @@ static void
 bpf_map_op__delete(struct bpf_map_op *op)
 {
         if (!list_empty(&op->list))
-                list_del(&op->list);
+                list_del_init(&op->list);
         if (op->key_type == BPF_MAP_KEY_RANGES)
                 parse_events__clear_array(&op->k.array);
         free(op);
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 89c6913dfc25..f1abfab7aa8c 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -30,6 +30,7 @@
 #include "strlist.h"
 
 #include <linux/ctype.h>
+#include <linux/zalloc.h>
 
 static bool no_buildid_cache;
 
diff --git a/tools/perf/util/call-path.c b/tools/perf/util/call-path.c
index c5b90300304d..5c60b8be1cf6 100644
--- a/tools/perf/util/call-path.c
+++ b/tools/perf/util/call-path.c
@@ -6,8 +6,9 @@
 
 #include <linux/rbtree.h>
 #include <linux/list.h>
+#include <linux/zalloc.h>
+#include <stdlib.h>
 
-#include "util.h"
 #include "call-path.h"
 
 static void call_path__init(struct call_path *cp, struct call_path *parent,
@@ -39,7 +40,7 @@ void call_path_root__free(struct call_path_root *cpr)
         struct call_path_block *pos, *n;
 
         list_for_each_entry_safe(pos, n, &cpr->blocks, node) {
-                list_del(&pos->node);
+                list_del_init(&pos->node);
                 free(pos);
         }
         free(cpr);
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index abb608b09269..8d7d8f62fcca 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -16,11 +16,11 @@
 #include <stdbool.h>
 #include <errno.h>
 #include <math.h>
+#include <linux/zalloc.h>
 
 #include "asm/bug.h"
 
 #include "hist.h"
-#include "util.h"
 #include "sort.h"
 #include "machine.h"
 #include "map.h"
@@ -636,7 +636,7 @@ add_child(struct callchain_node *parent,
                 struct callchain_list *call, *tmp;
 
                 list_for_each_entry_safe(call, tmp, &new->val, list) {
-                        list_del(&call->list);
+                        list_del_init(&call->list);
                         map__zput(call->ms.map);
                         free(call);
                 }
@@ -1002,7 +1002,7 @@ merge_chain_branch(struct callchain_cursor *cursor,
                 callchain_cursor_append(cursor, list->ip,
                                         list->ms.map, list->ms.sym,
                                         false, NULL, 0, 0, 0, list->srcline);
-                list_del(&list->list);
+                list_del_init(&list->list);
                 map__zput(list->ms.map);
                 free(list);
         }
@@ -1453,13 +1453,13 @@ static void free_callchain_node(struct callchain_node *node)
         struct rb_node *n;
 
         list_for_each_entry_safe(list, tmp, &node->parent_val, list) {
-                list_del(&list->list);
+                list_del_init(&list->list);
                 map__zput(list->ms.map);
                 free(list);
         }
 
         list_for_each_entry_safe(list, tmp, &node->val, list) {
-                list_del(&list->list);
+                list_del_init(&list->list);
                 map__zput(list->ms.map);
                 free(list);
         }
@@ -1544,7 +1544,7 @@ int callchain_node__make_parent_list(struct callchain_node *node)
 
 out:
         list_for_each_entry_safe(chain, new, &head, list) {
-                list_del(&chain->list);
+                list_del_init(&chain->list);
                 map__zput(chain->ms.map);
                 free(chain);
         }
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index ccd02634a616..484c29830a81 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -1,11 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "util.h"
 #include "../perf.h"
 #include <subcmd/parse-options.h>
 #include "evsel.h"
 #include "cgroup.h"
 #include "evlist.h"
 #include <linux/stringify.h>
+#include <linux/zalloc.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
@@ -124,7 +124,7 @@ static struct cgroup *cgroup__new(const char *name)
         return cgroup;
 
 out_free_name:
-        free(cgroup->name);
+        zfree(&cgroup->name);
 out_err:
         free(cgroup);
         return NULL;
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index 1066de92af12..afb8d4fd2644 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -1,12 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "comm.h"
-#include "util.h"
 #include <errno.h>
 #include <stdlib.h>
 #include <stdio.h>
 #include <string.h>
 #include <linux/refcount.h>
 #include <linux/rbtree.h>
+#include <linux/zalloc.h>
 #include "rwsem.h"
 
 struct comm_str {
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 752cce853e51..042ffbc8c53f 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -11,7 +11,6 @@
  */
 #include <errno.h>
 #include <sys/param.h>
-#include "util.h"
 #include "cache.h"
 #include "callchain.h"
 #include <subcmd/exec-cmd.h>
@@ -23,7 +22,7 @@
 #include <sys/stat.h>
 #include <unistd.h>
 #include <linux/string.h>
-
+#include <linux/zalloc.h>
 #include <linux/ctype.h>
 
 #define MAXNAME (256)
diff --git a/tools/perf/util/counts.c b/tools/perf/util/counts.c
index 03032b410c29..88be9c4365e0 100644
--- a/tools/perf/util/counts.c
+++ b/tools/perf/util/counts.c
@@ -3,7 +3,7 @@
 #include <stdlib.h>
 #include "evsel.h"
 #include "counts.h"
-#include "util.h"
+#include <linux/zalloc.h>
 
 struct perf_counts *perf_counts__new(int ncpus, int nthreads)
 {
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 0d8fbedf7bd5..3acfbe34ebaf 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -1,5 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "util.h"
 #include <api/fs/fs.h>
 #include "../perf.h"
 #include "cpumap.h"
@@ -11,6 +10,7 @@
 #include "asm/bug.h"
 
 #include <linux/ctype.h>
+#include <linux/zalloc.h>
 
 static int max_cpu_num;
 static int max_present_cpu_num;
diff --git a/tools/perf/util/cputopo.c b/tools/perf/util/cputopo.c
index 26e73a4bd4fe..64336a280967 100644
--- a/tools/perf/util/cputopo.c
+++ b/tools/perf/util/cputopo.c
@@ -2,11 +2,12 @@
 #include <sys/param.h>
 #include <sys/utsname.h>
 #include <inttypes.h>
+#include <stdlib.h>
 #include <api/fs/fs.h>
+#include <linux/zalloc.h>
 
 #include "cputopo.h"
 #include "cpumap.h"
-#include "util.h"
 #include "env.h"
 
 #define CORE_SIB_FMT \
@@ -343,7 +344,7 @@ void numa_topology__delete(struct numa_topology *tp)
         u32 i;
 
         for (i = 0; i < tp->nr; i++)
-                free(tp->nodes[i].cpus);
+                zfree(&tp->nodes[i].cpus);
 
         free(tp);
 }
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index bb45e23018ee..37d7c492b155 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -8,6 +8,7 @@
 
 #include <linux/err.h>
 #include <linux/list.h>
+#include <linux/zalloc.h>
 #include <stdlib.h>
 #include <opencsd/c_api/opencsd_c_api.h>
 #include <opencsd/etmv4/trc_pkt_types_etmv4.h>
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 0c7776b51045..3d1c34fc4d68 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/log2.h>
 #include <linux/types.h>
+#include <linux/zalloc.h>
 
 #include <opencsd/ocsd_if_types.h>
 #include <stdlib.h>
@@ -554,8 +555,7 @@ static void cs_etm__free_traceid_queues(struct cs_etm_queue *etmq)
         etmq->traceid_queues_list = NULL;
 
         /* finally free the traceid_queues array */
-        free(etmq->traceid_queues);
-        etmq->traceid_queues = NULL;
+        zfree(&etmq->traceid_queues);
 }
 
 static void cs_etm__free_queue(void *priv)
@@ -2460,7 +2460,7 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
 
                 /* Something went wrong, no need to continue */
                 if (!inode) {
-                        err = PTR_ERR(inode);
+                        err = -ENOMEM;
                         goto err_free_metadata;
                 }
 
@@ -2517,8 +2517,10 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
         session->auxtrace = &etm->auxtrace;
 
         etm->unknown_thread = thread__new(999999999, 999999999);
-        if (!etm->unknown_thread)
+        if (!etm->unknown_thread) {
+                err = -ENOMEM;
                 goto err_free_queues;
+        }
 
         /*
          * Initialize list node so that at thread__zput() we can avoid
@@ -2530,15 +2532,17 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
         if (err)
                 goto err_delete_thread;
 
-        if (thread__init_map_groups(etm->unknown_thread, etm->machine))
+        if (thread__init_map_groups(etm->unknown_thread, etm->machine)) {
+                err = -ENOMEM;
                 goto err_delete_thread;
+        }
 
         if (dump_trace) {
                 cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu);
                 return 0;
         }
 
-        if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
+        if (session->itrace_synth_opts->set) {
                 etm->synth_opts = *session->itrace_synth_opts;
         } else {
                 itrace_synth_opts__set_default(&etm->synth_opts,
@@ -2568,12 +2572,12 @@ err_free_etm:
 err_free_metadata:
         /* No need to check @metadata[j], free(NULL) is supported */
         for (j = 0; j < num_cpu; j++)
-                free(metadata[j]);
+                zfree(&metadata[j]);
         zfree(&metadata);
 err_free_traceid_list:
         intlist__delete(traceid_list);
 err_free_hdr:
         zfree(&hdr);
 
-        return -EINVAL;
+        return err;
 }
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 7b06e7373b9e..ddbcd59f2d9b 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -10,6 +10,7 @@
 #include <inttypes.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
+#include <linux/zalloc.h>
 #include <babeltrace/ctf-writer/writer.h>
 #include <babeltrace/ctf-writer/clock.h>
 #include <babeltrace/ctf-writer/stream.h>
@@ -22,7 +23,6 @@
 #include "asm/bug.h"
 #include "data-convert-bt.h"
 #include "session.h"
-#include "util.h"
 #include "debug.h"
 #include "tool.h"
 #include "evlist.h"
@@ -1353,7 +1353,7 @@ static void free_streams(struct ctf_writer *cw)
         for (cpu = 0; cpu < cw->stream_cnt; cpu++)
                 ctf_stream__delete(cw->stream[cpu]);
 
-        free(cw->stream);
+        zfree(&cw->stream);
 }
 
 static int ctf_writer__setup_env(struct ctf_writer *cw,
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index 6a64f713710d..1d1b97a92c3f 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 #include <linux/kernel.h>
+#include <linux/zalloc.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <errno.h>
@@ -20,7 +21,7 @@ static void close_dir(struct perf_data_file *files, int nr)
 {
         while (--nr >= 1) {
                 close(files[nr].fd);
-                free(files[nr].path);
+                zfree(&files[nr].path);
         }
         free(files);
 }
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index 2182f552aac6..ffbb3e7d3288 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -5,6 +5,7 @@
  */
 
 #include <errno.h>
+#include <stdlib.h>
 
 #include "evsel.h"
 #include "machine.h"
@@ -13,76 +14,20 @@
 #include "symbol.h"
 #include "map.h"
 #include "event.h"
-#include "util.h"
 #include "thread-stack.h"
 #include "callchain.h"
 #include "call-path.h"
 #include "db-export.h"
-
-struct deferred_export {
-        struct list_head node;
-        struct comm *comm;
-};
-
-static int db_export__deferred(struct db_export *dbe)
-{
-        struct deferred_export *de;
-        int err;
-
-        while (!list_empty(&dbe->deferred)) {
-                de = list_entry(dbe->deferred.next, struct deferred_export,
-                                node);
-                err = dbe->export_comm(dbe, de->comm);
-                list_del(&de->node);
-                free(de);
-                if (err)
-                        return err;
-        }
-
-        return 0;
-}
-
-static void db_export__free_deferred(struct db_export *dbe)
-{
-        struct deferred_export *de;
-
-        while (!list_empty(&dbe->deferred)) {
-                de = list_entry(dbe->deferred.next, struct deferred_export,
-                                node);
-                list_del(&de->node);
-                free(de);
-        }
-}
-
-static int db_export__defer_comm(struct db_export *dbe, struct comm *comm)
-{
-        struct deferred_export *de;
-
-        de = zalloc(sizeof(struct deferred_export));
-        if (!de)
-                return -ENOMEM;
-
-        de->comm = comm;
-        list_add_tail(&de->node, &dbe->deferred);
-
-        return 0;
-}
+#include <linux/zalloc.h>
 
 int db_export__init(struct db_export *dbe)
 {
         memset(dbe, 0, sizeof(struct db_export));
-        INIT_LIST_HEAD(&dbe->deferred);
         return 0;
 }
 
-int db_export__flush(struct db_export *dbe)
-{
-        return db_export__deferred(dbe);
-}
-
 void db_export__exit(struct db_export *dbe)
 {
-        db_export__free_deferred(dbe);
         call_return_processor__free(dbe->crp);
         dbe->crp = NULL;
 }
@@ -114,71 +59,73 @@ int db_export__machine(struct db_export *dbe, struct machine *machine)
 }
 
 int db_export__thread(struct db_export *dbe, struct thread *thread,
-                      struct machine *machine, struct comm *comm)
+                      struct machine *machine, struct thread *main_thread)
 {
-        struct thread *main_thread;
         u64 main_thread_db_id = 0;
-        int err;
 
         if (thread->db_id)
                 return 0;
 
         thread->db_id = ++dbe->thread_last_db_id;
 
-        if (thread->pid_ != -1) {
-                if (thread->pid_ == thread->tid) {
-                        main_thread = thread;
-                } else {
-                        main_thread = machine__findnew_thread(machine,
-                                                              thread->pid_,
-                                                              thread->pid_);
-                        if (!main_thread)
-                                return -ENOMEM;
-                        err = db_export__thread(dbe, main_thread, machine,
-                                                comm);
-                        if (err)
-                                goto out_put;
-                        if (comm) {
-                                err = db_export__comm_thread(dbe, comm, thread);
-                                if (err)
-                                        goto out_put;
-                        }
-                }
+        if (main_thread)
                 main_thread_db_id = main_thread->db_id;
-                if (main_thread != thread)
-                        thread__put(main_thread);
-        }
 
         if (dbe->export_thread)
                 return dbe->export_thread(dbe, thread, main_thread_db_id,
                                           machine);
 
         return 0;
+}
 
-out_put:
-        thread__put(main_thread);
-        return err;
+static int __db_export__comm(struct db_export *dbe, struct comm *comm,
+                             struct thread *thread)
+{
+        comm->db_id = ++dbe->comm_last_db_id;
+
+        if (dbe->export_comm)
+                return dbe->export_comm(dbe, comm, thread);
+
+        return 0;
 }
 
 int db_export__comm(struct db_export *dbe, struct comm *comm,
-                    struct thread *main_thread)
+                    struct thread *thread)
+{
+        if (comm->db_id)
+                return 0;
+
+        return __db_export__comm(dbe, comm, thread);
+}
+
+/*
+ * Export the "exec" comm. The "exec" comm is the program / application command
+ * name at the time it first executes. It is used to group threads for the same
+ * program. Note that the main thread pid (or thread group id tgid) cannot be
+ * used because it does not change when a new program is exec'ed.
+ */
+int db_export__exec_comm(struct db_export *dbe, struct comm *comm,
+                         struct thread *main_thread)
 {
         int err;
 
         if (comm->db_id)
                 return 0;
 
-        comm->db_id = ++dbe->comm_last_db_id;
-
-        if (dbe->export_comm) {
-                if (main_thread->comm_set)
-                        err = dbe->export_comm(dbe, comm);
-                else
-                        err = db_export__defer_comm(dbe, comm);
-                if (err)
-                        return err;
-        }
+        err = __db_export__comm(dbe, comm, main_thread);
+        if (err)
+                return err;
 
+        /*
+         * Record the main thread for this comm. Note that the main thread can
+         * have many "exec" comms because there will be a new one every time it
+         * exec's. An "exec" comm however will only ever have 1 main thread.
+         * That is different to any other threads for that same program because
+         * exec() will effectively kill them, so the relationship between the
+         * "exec" comm and non-main threads is 1-to-1. That is why
+         * db_export__comm_thread() is called here for the main thread, but it
+         * is called for non-main threads when they are exported.
+         */
         return db_export__comm_thread(dbe, comm, main_thread);
 }
 
@@ -339,11 +286,65 @@ int db_export__branch_type(struct db_export *dbe, u32 branch_type,
         return 0;
 }
 
+static int db_export__threads(struct db_export *dbe, struct thread *thread,
+                              struct thread *main_thread,
+                              struct machine *machine, struct comm **comm_ptr)
+{
+        struct comm *comm = NULL;
+        struct comm *curr_comm;
+        int err;
+
+        if (main_thread) {
+                /*
+                 * A thread has a reference to the main thread, so export the
+                 * main thread first.
+                 */
+                err = db_export__thread(dbe, main_thread, machine, main_thread);
+                if (err)
+                        return err;
+                /*
+                 * Export comm before exporting the non-main thread because
+                 * db_export__comm_thread() can be called further below.
+                 */
+                comm = machine__thread_exec_comm(machine, main_thread);
+                if (comm) {
+                        err = db_export__exec_comm(dbe, comm, main_thread);
+                        if (err)
+                                return err;
+                        *comm_ptr = comm;
+                }
+        }
+
+        if (thread != main_thread) {
+                /*
+                 * For a non-main thread, db_export__comm_thread() must be
+                 * called only if thread has not previously been exported.
+                 */
+                bool export_comm_thread = comm && !thread->db_id;
+
+                err = db_export__thread(dbe, thread, machine, main_thread);
+                if (err)
+                        return err;
+
+                if (export_comm_thread) {
+                        err = db_export__comm_thread(dbe, comm, thread);
+                        if (err)
+                                return err;
+                }
+        }
+
+        curr_comm = thread__comm(thread);
+        if (curr_comm)
+                return db_export__comm(dbe, curr_comm, thread);
+
+        return 0;
+}
+
 int db_export__sample(struct db_export *dbe, union perf_event *event,
                       struct perf_sample *sample, struct perf_evsel *evsel,
                       struct addr_location *al)
 {
-        struct thread* thread = al->thread;
+        struct thread *thread = al->thread;
         struct export_sample es = {
                 .event = event,
                 .sample = sample,
@@ -363,19 +364,13 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
                 return err;
 
         main_thread = thread__main_thread(al->machine, thread);
-        if (main_thread)
-                comm = machine__thread_exec_comm(al->machine, main_thread);
 
-        err = db_export__thread(dbe, thread, al->machine, comm);
+        err = db_export__threads(dbe, thread, main_thread, al->machine, &comm);
         if (err)
                 goto out_put;
 
-        if (comm) {
-                err = db_export__comm(dbe, comm, main_thread);
-                if (err)
-                        goto out_put;
+        if (comm)
                 es.comm_db_id = comm->db_id;
-        }
 
         es.db_id = ++dbe->sample_last_db_id;
 
@@ -524,3 +519,92 @@ int db_export__call_return(struct db_export *dbe, struct call_return *cr,
 
         return 0;
 }
+
+static int db_export__pid_tid(struct db_export *dbe, struct machine *machine,
+                              pid_t pid, pid_t tid, u64 *db_id,
+                              struct comm **comm_ptr, bool *is_idle)
+{
+        struct thread *thread = machine__find_thread(machine, pid, tid);
+        struct thread *main_thread;
+        int err = 0;
+
+        if (!thread || !thread->comm_set)
+                goto out_put;
+
+        *is_idle = !thread->pid_ && !thread->tid;
+
+        main_thread = thread__main_thread(machine, thread);
+
+        err = db_export__threads(dbe, thread, main_thread, machine, comm_ptr);
+
+        *db_id = thread->db_id;
+
+        thread__put(main_thread);
+out_put:
+        thread__put(thread);
+
+        return err;
+}
+
+int db_export__switch(struct db_export *dbe, union perf_event *event,
+                      struct perf_sample *sample, struct machine *machine)
+{
+        bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT;
+        bool out_preempt = out &&
+                (event->header.misc & PERF_RECORD_MISC_SWITCH_OUT_PREEMPT);
+        int flags = out | (out_preempt << 1);
+        bool is_idle_a = false, is_idle_b = false;
+        u64 th_a_id = 0, th_b_id = 0;
+        u64 comm_out_id, comm_in_id;
+        struct comm *comm_a = NULL;
+        struct comm *comm_b = NULL;
+        u64 th_out_id, th_in_id;
+        u64 db_id;
+        int err;
+
+        err = db_export__machine(dbe, machine);
+        if (err)
+                return err;
+
+        err = db_export__pid_tid(dbe, machine, sample->pid, sample->tid,
+                                 &th_a_id, &comm_a, &is_idle_a);
+        if (err)
+                return err;
+
+        if (event->header.type == PERF_RECORD_SWITCH_CPU_WIDE) {
+                pid_t pid = event->context_switch.next_prev_pid;
+                pid_t tid = event->context_switch.next_prev_tid;
+
+                err = db_export__pid_tid(dbe, machine, pid, tid, &th_b_id,
+                                         &comm_b, &is_idle_b);
+                if (err)
+                        return err;
+        }
+
+        /*
+         * Do not export if both threads are unknown (i.e. not being traced),
+         * or one is unknown and the other is the idle task.
+         */
+        if ((!th_a_id || is_idle_a) && (!th_b_id || is_idle_b))
+                return 0;
+
+        db_id = ++dbe->context_switch_last_db_id;
+
+        if (out) {
+                th_out_id   = th_a_id;
+                th_in_id    = th_b_id;
+                comm_out_id = comm_a ? comm_a->db_id : 0;
+                comm_in_id  = comm_b ? comm_b->db_id : 0;
+        } else {
+                th_out_id   = th_b_id;
+                th_in_id    = th_a_id;
+                comm_out_id = comm_b ? comm_b->db_id : 0;
+                comm_in_id  = comm_a ? comm_a->db_id : 0;
+        }
+
+        if (dbe->export_context_switch)
+                return dbe->export_context_switch(dbe, db_id, machine, sample,
+                                                  th_out_id, comm_out_id,
+                                                  th_in_id, comm_in_id, flags);
+        return 0;
+}
diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h
index e8a64028a386..ba1f62a5fe10 100644
--- a/tools/perf/util/db-export.h
+++ b/tools/perf/util/db-export.h
@@ -43,7 +43,8 @@ struct db_export {
         int (*export_machine)(struct db_export *dbe, struct machine *machine);
         int (*export_thread)(struct db_export *dbe, struct thread *thread,
                              u64 main_thread_db_id, struct machine *machine);
-        int (*export_comm)(struct db_export *dbe, struct comm *comm);
+        int (*export_comm)(struct db_export *dbe, struct comm *comm,
+                           struct thread *thread);
         int (*export_comm_thread)(struct db_export *dbe, u64 db_id,
                                   struct comm *comm, struct thread *thread);
         int (*export_dso)(struct db_export *dbe, struct dso *dso,
@@ -56,6 +57,11 @@ struct db_export {
         int (*export_call_path)(struct db_export *dbe, struct call_path *cp);
         int (*export_call_return)(struct db_export *dbe,
                                   struct call_return *cr);
+        int (*export_context_switch)(struct db_export *dbe, u64 db_id,
+                                     struct machine *machine,
+                                     struct perf_sample *sample,
+                                     u64 th_out_id, u64 comm_out_id,
+                                     u64 th_in_id, u64 comm_in_id, int flags);
         struct call_return_processor *crp;
         struct call_path_root *cpr;
         u64 evsel_last_db_id;
@@ -68,18 +74,19 @@ struct db_export {
         u64 sample_last_db_id;
         u64 call_path_last_db_id;
         u64 call_return_last_db_id;
-        struct list_head deferred;
+        u64 context_switch_last_db_id;
 };
 
 int db_export__init(struct db_export *dbe);
-int db_export__flush(struct db_export *dbe);
 void db_export__exit(struct db_export *dbe);
 int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel);
 int db_export__machine(struct db_export *dbe, struct machine *machine);
 int db_export__thread(struct db_export *dbe, struct thread *thread,
-                      struct machine *machine, struct comm *comm);
+                      struct machine *machine, struct thread *main_thread);
 int db_export__comm(struct db_export *dbe, struct comm *comm,
-                    struct thread *main_thread);
+                    struct thread *thread);
+int db_export__exec_comm(struct db_export *dbe, struct comm *comm,
+                         struct thread *main_thread);
 int db_export__comm_thread(struct db_export *dbe, struct comm *comm,
                            struct thread *thread);
 int db_export__dso(struct db_export *dbe, struct dso *dso,
@@ -97,5 +104,7 @@ int db_export__branch_types(struct db_export *dbe);
 int db_export__call_path(struct db_export *dbe, struct call_path *cp);
 int db_export__call_return(struct db_export *dbe, struct call_return *cr,
                            u64 *parent_db_id);
+int db_export__switch(struct db_export *dbe, union perf_event *event,
+                      struct perf_sample *sample, struct machine *machine);
 
 #endif
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 3cc578343f48..3780fe42453b 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -7,6 +7,7 @@
 #include <string.h>
 #include <stdarg.h>
 #include <stdio.h>
+#include <stdlib.h>
 #include <sys/wait.h>
 #include <api/debug.h>
 #include <linux/time64.h>
diff --git a/tools/perf/util/demangle-java.c b/tools/perf/util/demangle-java.c
index 5b4900d67c80..763328c151e9 100644
--- a/tools/perf/util/demangle-java.c
+++ b/tools/perf/util/demangle-java.c
@@ -1,14 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <sys/types.h>
 #include <stdio.h>
+#include <stdlib.h>
 #include <string.h>
-#include "util.h"
 #include "debug.h"
 #include "symbol.h"
 
 #include "demangle-java.h"
 
 #include <linux/ctype.h>
+#include <linux/kernel.h>
 
 enum {
         MODE_PREFIX = 0,
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index c7fde04400f7..ebc9d46c15a7 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -2,6 +2,7 @@
 #include <asm/bug.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
+#include <linux/zalloc.h>
 #include <sys/time.h>
 #include <sys/resource.h>
 #include <sys/types.h>
@@ -21,7 +22,7 @@
 #include "dso.h"
 #include "machine.h"
 #include "auxtrace.h"
-#include "util.h"
+#include "util.h" /* O_CLOEXEC for older systems */
 #include "debug.h"
 #include "string2.h"
 #include "vdso.h"
@@ -433,7 +434,7 @@ static void dso__list_add(struct dso *dso)
 
 static void dso__list_del(struct dso *dso)
 {
-        list_del(&dso->data.open_entry);
+        list_del_init(&dso->data.open_entry);
         WARN_ONCE(dso__data_open_cnt <= 0,
                   "DSO data fd counter out of bounds.");
         dso__data_open_cnt--;
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 218bfea8f8a8..03b2de1f5a35 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -6,7 +6,7 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <stdbool.h>
-#include "util.h"
+#include <stdlib.h>
 #include "debug.h"
 #include "dwarf-aux.h"
 #include "string2.h"
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 22eee8942527..9909ec40c6d2 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -2,11 +2,12 @@
 #include "cpumap.h"
 #include "env.h"
 #include <linux/ctype.h>
-#include "util.h"
+#include <linux/zalloc.h>
 #include "bpf-event.h"
 #include <errno.h>
 #include <sys/utsname.h>
 #include <bpf/libbpf.h>
+#include <stdlib.h>
 
 struct perf_env perf_env;
 
@@ -186,7 +187,7 @@ void perf_env__exit(struct perf_env *env)
         zfree(&env->caches);
 
         for (i = 0; i < env->nr_memory_nodes; i++)
-                free(env->memory_nodes[i].set);
+                zfree(&env->memory_nodes[i].set);
         zfree(&env->memory_nodes);
 }
 
@@ -286,9 +287,9 @@ int perf_env__nr_cpus_avail(struct perf_env *env)
 
 void cpu_cache_level__free(struct cpu_cache_level *cache)
 {
-        free(cache->type);
-        free(cache->map);
-        free(cache->size);
+        zfree(&cache->type);
+        zfree(&cache->map);
+        zfree(&cache->size);
 }
 
 /*
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index e1d0c5ba1f92..f1f4848947ce 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -11,6 +11,7 @@
 #include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
 #include <api/fs/fs.h>
 #include <linux/perf_event.h>
+#include <linux/zalloc.h>
 #include "event.h"
 #include "debug.h"
 #include "hist.h"
@@ -855,7 +856,7 @@ free_threads:
         free(synthesize_threads);
 free_dirent:
         for (i = 0; i < n; i++)
-                free(dirent[i]);
+                zfree(&dirent[i]);
         free(dirent);
 
         return err;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index a474ede17cd6..b0364d923f76 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -5,7 +5,6 @@
  * Parts came from builtin-{top,stat,record}.c, see those files for further
  * copyright notes.
  */
-#include "util.h"
 #include <api/fs/fs.h>
 #include <errno.h>
 #include <inttypes.h>
@@ -33,6 +32,7 @@
 #include <linux/hash.h>
 #include <linux/log2.h>
 #include <linux/err.h>
+#include <linux/zalloc.h>
 
 #ifdef LACKS_SIGQUEUE_PROTOTYPE
 int sigqueue(pid_t pid, int sig, const union sigval value);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 7fb4ae82f34c..ebb46da4dfe5 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -17,6 +17,7 @@
 #include <linux/perf_event.h>
 #include <linux/compiler.h>
 #include <linux/err.h>
+#include <linux/zalloc.h>
 #include <sys/ioctl.h>
 #include <sys/resource.h>
 #include <sys/types.h>
@@ -27,7 +28,6 @@
 #include "event.h"
 #include "evsel.h"
 #include "evlist.h"
-#include "util.h"
 #include "cpumap.h"
 #include "thread_map.h"
 #include "target.h"
@@ -1298,7 +1298,7 @@ static void perf_evsel__free_config_terms(struct perf_evsel *evsel)
         struct perf_evsel_config_term *term, *h;
 
         list_for_each_entry_safe(term, h, &evsel->config_terms, list) {
-                list_del(&term->list);
+                list_del_init(&term->list);
                 free(term);
         }
 }
diff --git a/tools/perf/util/get_current_dir_name.c b/tools/perf/util/get_current_dir_name.c
index 267aa609a582..01f32f26552d 100644
--- a/tools/perf/util/get_current_dir_name.c
+++ b/tools/perf/util/get_current_dir_name.c
@@ -1,8 +1,8 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+// SPDX-License-Identifier: LGPL-2.1
+// Copyright (C) 2018, 2019 Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
 //
 #ifndef HAVE_GET_CURRENT_DIR_NAME
-#include "util.h"
+#include "get_current_dir_name.h"
 #include <unistd.h>
 #include <stdlib.h>
 #include <stdlib.h>
diff --git a/tools/perf/util/get_current_dir_name.h b/tools/perf/util/get_current_dir_name.h
new file mode 100644
index 000000000000..69f7d5537d32
--- /dev/null
+++ b/tools/perf/util/get_current_dir_name.h
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
+// Copyright (C) 2018, 2019 Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+//
+#ifndef __PERF_GET_CURRENT_DIR_NAME_H
+#ifndef HAVE_GET_CURRENT_DIR_NAME
+char *get_current_dir_name(void);
+#endif // HAVE_GET_CURRENT_DIR_NAME
+#endif // __PERF_GET_CURRENT_DIR_NAME_H
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 6a93ff5d8db5..c24db7f4909c 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
 #include <inttypes.h>
-#include "util.h"
 #include "string2.h"
 #include <sys/param.h>
 #include <sys/types.h>
@@ -15,6 +14,7 @@
 #include <linux/bitops.h>
 #include <linux/string.h>
 #include <linux/stringify.h>
+#include <linux/zalloc.h>
 #include <sys/stat.h>
 #include <sys/utsname.h>
 #include <linux/time64.h>
@@ -1052,7 +1052,7 @@ static int cpu_cache_level__read(struct cpu_cache_level *cache, u32 cpu, u16 lev
 
         scnprintf(file, PATH_MAX, "%s/size", path);
         if (sysfs__read_str(file, &cache->size, &len)) {
-                free(cache->type);
+                zfree(&cache->type);
                 return -1;
         }
 
@@ -1061,8 +1061,8 @@ static int cpu_cache_level__read(struct cpu_cache_level *cache, u32 cpu, u16 lev
 
         scnprintf(file, PATH_MAX, "%s/shared_cpu_list", path);
         if (sysfs__read_str(file, &cache->map, &len)) {
-                free(cache->map);
-                free(cache->type);
+                zfree(&cache->map);
+                zfree(&cache->type);
                 return -1;
         }
 
diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c
index 4f07a5ba5030..ab9e16123626 100644
--- a/tools/perf/util/help-unknown-cmd.c
+++ b/tools/perf/util/help-unknown-cmd.c
@@ -3,9 +3,11 @@
 #include "config.h"
 #include <poll.h>
 #include <stdio.h>
+#include <stdlib.h>
 #include <subcmd/help.h>
 #include "../builtin.h"
 #include "levenshtein.h"
+#include <linux/zalloc.h>
 
 static int autocorrect;
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 27cecb59f866..f24fd1954f6c 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "callchain.h"
-#include "util.h"
 #include "build-id.h"
 #include "hist.h"
 #include "map.h"
@@ -20,6 +19,7 @@
 #include <inttypes.h>
 #include <sys/param.h>
 #include <linux/time64.h>
+#include <linux/zalloc.h>
 
 static bool hists__filter_entry_by_dso(struct hists *hists,
                                        struct hist_entry *he);
@@ -472,16 +472,16 @@ static int hist_entry__init(struct hist_entry *he,
         return 0;
 
 err_srcline:
-        free(he->srcline);
+        zfree(&he->srcline);
 
 err_rawdata:
-        free(he->raw_data);
+        zfree(&he->raw_data);
 
 err_infos:
         if (he->branch_info) {
                 map__put(he->branch_info->from.map);
                 map__put(he->branch_info->to.map);
-                free(he->branch_info);
+                zfree(&he->branch_info);
         }
         if (he->mem_info) {
                 map__put(he->mem_info->iaddr.map);
@@ -489,7 +489,7 @@ err_infos:
         }
 err:
         map__zput(he->ms.map);
-        free(he->stat_acc);
+        zfree(&he->stat_acc);
         return -ENOMEM;
 }
 
@@ -1254,10 +1254,10 @@ void hist_entry__delete(struct hist_entry *he)
         zfree(&he->stat_acc);
         free_srcline(he->srcline);
         if (he->srcfile && he->srcfile[0])
-                free(he->srcfile);
+                zfree(&he->srcfile);
         free_callchain(he->callchain);
-        free(he->trace_output);
-        free(he->raw_data);
+        zfree(&he->trace_output);
+        zfree(&he->raw_data);
         ops->free(he);
 }
 
@@ -2741,10 +2741,10 @@ static void hists_evsel__exit(struct perf_evsel *evsel)
 
         list_for_each_entry_safe(node, tmp, &hists->hpp_formats, list) {
                 perf_hpp_list__for_each_format_safe(&node->hpp, fmt, pos) {
-                        list_del(&fmt->list);
+                        list_del_init(&fmt->list);
                         free(fmt);
                 }
-                list_del(&node->list);
+                list_del_init(&node->list);
                 free(node);
         }
 }
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index e32dbffebb2f..5560e95afdda 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -12,6 +12,7 @@
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include <linux/log2.h>
+#include <linux/zalloc.h>
 
 #include "cpumap.h"
 #include "color.h"
@@ -21,7 +22,6 @@
 #include "map.h"
 #include "symbol.h"
 #include "session.h"
-#include "util.h"
 #include "thread.h"
 #include "thread-stack.h"
 #include "debug.h"
@@ -891,13 +891,12 @@ int intel_bts_process_auxtrace_info(union perf_event *event,
         if (dump_trace)
                 return 0;
 
-        if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
+        if (session->itrace_synth_opts->set) {
                 bts->synth_opts = *session->itrace_synth_opts;
         } else {
                 itrace_synth_opts__set_default(&bts->synth_opts,
                                 session->itrace_synth_opts->default_no_sample);
-                if (session->itrace_synth_opts)
-                        bts->synth_opts.thread_stack =
+                bts->synth_opts.thread_stack =
                                 session->itrace_synth_opts->thread_stack;
         }
 
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 4d14e78c5927..3bfdf2b7a96a 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -14,9 +14,9 @@
 #include <stdint.h>
 #include <inttypes.h>
 #include <linux/compiler.h>
+#include <linux/zalloc.h>
 
 #include "../cache.h"
-#include "../util.h"
 #include "../auxtrace.h"
 
 #include "intel-pt-insn-decoder.h"
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 470aaae9d930..df061599fef4 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -10,6 +10,7 @@
 #include <errno.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
+#include <linux/zalloc.h>
 
 #include "../perf.h"
 #include "session.h"
@@ -22,7 +23,6 @@
 #include "evsel.h"
 #include "map.h"
 #include "color.h"
-#include "util.h"
 #include "thread.h"
 #include "thread-stack.h"
 #include "symbol.h"
@@ -3210,7 +3210,7 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
                 goto err_delete_thread;
         }
 
-        if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
+        if (session->itrace_synth_opts->set) {
                 pt->synth_opts = *session->itrace_synth_opts;
         } else {
                 itrace_synth_opts__set_default(&pt->synth_opts,
@@ -3220,8 +3220,7 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
                         pt->synth_opts.branches = false;
                         pt->synth_opts.callchain = true;
                 }
-                if (session->itrace_synth_opts)
-                        pt->synth_opts.thread_stack =
+                pt->synth_opts.thread_stack =
                                 session->itrace_synth_opts->thread_stack;
         }
 
@@ -3241,11 +3240,9 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
                 pt->cbr2khz = tsc_freq / pt->max_non_turbo_ratio / 1000;
         }
 
-        if (session->itrace_synth_opts) {
-                err = intel_pt_setup_time_ranges(pt, session->itrace_synth_opts);
-                if (err)
-                        goto err_delete_thread;
-        }
+        err = intel_pt_setup_time_ranges(pt, session->itrace_synth_opts);
+        if (err)
+                goto err_delete_thread;
 
         if (pt->synth_opts.calls)
                 pt->branches_filter |= PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC |
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index 28908afedec4..18c34f0c1966 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -29,6 +29,7 @@
 #include "../builtin.h"
 
 #include <linux/ctype.h>
+#include <linux/zalloc.h>
 
 struct jit_buf_desc {
         struct perf_data *output;
@@ -431,14 +432,12 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
                            jd->unwinding_data, jd->eh_frame_hdr_size, jd->unwinding_size);
 
         if (jd->debug_data && jd->nr_debug_entries) {
-                free(jd->debug_data);
-                jd->debug_data = NULL;
+                zfree(&jd->debug_data);
                 jd->nr_debug_entries = 0;
         }
 
         if (jd->unwinding_data && jd->eh_frame_hdr_size) {
-                free(jd->unwinding_data);
-                jd->unwinding_data = NULL;
+                zfree(&jd->unwinding_data);
                 jd->eh_frame_hdr_size = 0;
                 jd->unwinding_mapped_size = 0;
                 jd->unwinding_size = 0;
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 5b0b60f00275..9f0470ecbca9 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -9,6 +9,7 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <linux/err.h>
+#include <linux/zalloc.h>
 #include "debug.h"
 #include "llvm-utils.h"
 #include "config.h"
@@ -352,8 +353,7 @@ void llvm__get_kbuild_opts(char **kbuild_dir, char **kbuild_include_opts)
 "     \toption in [llvm] to \"\" to suppress this detection.\n\n",
                         *kbuild_dir);
 
-                free(*kbuild_dir);
-                *kbuild_dir = NULL;
+                zfree(kbuild_dir);
                 goto errout;
         }
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 147ed85ea2bc..cf826eca3aaf 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -15,7 +15,6 @@
 #include "strlist.h"
 #include "thread.h"
 #include "vdso.h"
-#include "util.h"
 #include <stdbool.h>
 #include <sys/types.h>
 #include <sys/stat.h>
@@ -28,6 +27,7 @@
 #include <linux/ctype.h>
 #include <symbol/kallsyms.h>
 #include <linux/mman.h>
+#include <linux/zalloc.h>
 
 static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock);
 
@@ -810,7 +810,7 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 out:
         /* put the dso here, corresponding to  machine__findnew_module_dso */
         dso__put(dso);
-        free(m.name);
+        zfree(&m.name);
         return map;
 }
 
@@ -1350,7 +1350,7 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg,
                         if (m.kmod)
                                 ret = map_groups__set_module_path(mg, path, &m);
 
-                        free(m.name);
+                        zfree(&m.name);
 
                         if (ret)
                                 goto out;
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 6fce983c6115..668410b1d426 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -12,10 +12,10 @@
 #include "thread.h"
 #include "vdso.h"
 #include "build-id.h"
-#include "util.h"
 #include "debug.h"
 #include "machine.h"
 #include <linux/string.h>
+#include <linux/zalloc.h>
 #include "srcline.h"
 #include "namespaces.h"
 #include "unwind.h"
@@ -476,8 +476,11 @@ int map__fprintf_srccode(struct map *map, u64 addr,
                 goto out_free_line;
 
         ret = fprintf(fp, "|%-8d %.*s", line, len, srccode);
-        state->srcfile = srcfile;
-        state->line = line;
+
+        if (state) {
+                state->srcfile = srcfile;
+                state->line = line;
+        }
         return ret;
 
 out_free_line:
diff --git a/tools/perf/util/mem2node.c b/tools/perf/util/mem2node.c
index c6fd81c02586..cacc2fc4dcbd 100644
--- a/tools/perf/util/mem2node.c
+++ b/tools/perf/util/mem2node.c
@@ -1,8 +1,8 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <linux/bitmap.h>
+#include <linux/zalloc.h>
 #include "mem2node.h"
-#include "util.h"
 
 struct phys_entry {
         struct rb_node  rb_node;
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index d8164574cb16..416a9015405e 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -18,6 +18,7 @@
 #include "strlist.h"
 #include <assert.h>
 #include <linux/ctype.h>
+#include <linux/zalloc.h>
 
 struct metric_event *metricgroup__lookup(struct rblist *metric_events,
                                          struct perf_evsel *evsel,
@@ -235,7 +236,7 @@ static struct rb_node *mep_new(struct rblist *rl __maybe_unused,
                 goto out_name;
         return &me->nd;
 out_name:
-        free((char *)me->name);
+        zfree(&me->name);
 out_me:
         free(me);
         return NULL;
@@ -263,7 +264,7 @@ static void mep_delete(struct rblist *rl __maybe_unused,
         struct mep *me = container_of(nd, struct mep, nd);
 
         strlist__delete(me->metrics);
-        free((void *)me->name);
+        zfree(&me->name);
         free(me);
 }
 
@@ -489,8 +490,9 @@ static void metricgroup__free_egroups(struct list_head *group_list)
 
         list_for_each_entry_safe (eg, egtmp, group_list, nd) {
                 for (i = 0; i < eg->idnum; i++)
-                        free((char *)eg->ids[i]);
-                free(eg->ids);
+                        zfree(&eg->ids[i]);
+                zfree(&eg->ids);
+                list_del_init(&eg->nd);
                 free(eg);
         }
 }
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 768c632b0d82..9f0b6391af33 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -9,6 +9,7 @@
 #include <sys/mman.h>
 #include <inttypes.h>
 #include <asm/bug.h>
+#include <linux/zalloc.h>
 #ifdef HAVE_LIBNUMA_SUPPORT
 #include <numaif.h>
 #endif
diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c
index 023c4efd788d..46d3a7754897 100644
--- a/tools/perf/util/namespaces.c
+++ b/tools/perf/util/namespaces.c
@@ -5,8 +5,8 @@
  */
 
 #include "namespaces.h"
-#include "util.h"
 #include "event.h"
+#include "get_current_dir_name.h"
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
@@ -17,6 +17,7 @@
 #include <string.h>
 #include <unistd.h>
 #include <asm/bug.h>
+#include <linux/zalloc.h>
 
 struct namespaces *namespaces__new(struct namespaces_event *event)
 {
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
index 15a5a276c478..004430c0de93 100644
--- a/tools/perf/util/namespaces.h
+++ b/tools/perf/util/namespaces.h
@@ -13,6 +13,10 @@
 #include <linux/refcount.h>
 #include <linux/types.h>
 
+#ifndef HAVE_SETNS_SUPPORT
+int setns(int fd, int nstype);
+#endif
+
 struct namespaces_event;
 
 struct namespaces {
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index 989fed6f43b5..bb5f34b7ab44 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -138,7 +138,7 @@ static struct ordered_event *alloc_event(struct ordered_events *oe,
 
         if (!list_empty(cache)) {
                 new = list_entry(cache->next, struct ordered_event, list);
-                list_del(&new->list);
+                list_del_init(&new->list);
         } else if (oe->buffer) {
                 new = &oe->buffer->event[oe->buffer_idx];
                 if (++oe->buffer_idx == MAX_SAMPLE_BUFFER)
@@ -394,13 +394,13 @@ void ordered_events__free(struct ordered_events *oe)
          * yet, we need to free only allocated ones ...
          */
         if (oe->buffer) {
-                list_del(&oe->buffer->list);
+                list_del_init(&oe->buffer->list);
                 ordered_events_buffer__free(oe->buffer, oe->buffer_idx, oe);
         }
 
         /* ... and continue with the rest */
         list_for_each_entry_safe(buffer, tmp, &oe->to_free, list) {
-                list_del(&buffer->list);
+                list_del_init(&buffer->list);
                 ordered_events_buffer__free(buffer, MAX_SAMPLE_BUFFER, oe);
         }
 }
diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c
index bd779d9f4d1e..726e8d9e8c54 100644
--- a/tools/perf/util/parse-branch-options.c
+++ b/tools/perf/util/parse-branch-options.c
@@ -1,9 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "perf.h"
-#include "util/util.h"
 #include "util/debug.h"
 #include <subcmd/parse-options.h>
 #include "util/parse-branch-options.h"
+#include <stdlib.h>
 
 #define BRANCH_OPT(n, m) \
         { .name = n, .mode = (m) }
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index cf0b9b81c5aa..371ff3aee769 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/hw_breakpoint.h>
 #include <linux/err.h>
+#include <linux/zalloc.h>
 #include <dirent.h>
 #include <errno.h>
 #include <sys/ioctl.h>
@@ -651,7 +652,7 @@ static int add_bpf_event(const char *group, const char *event, int fd,
                 pr_debug("Failed to add BPF event %s:%s\n",
                          group, event);
                 list_for_each_entry_safe(evsel, tmp, &new_evsels, node) {
-                        list_del(&evsel->node);
+                        list_del_init(&evsel->node);
                         perf_evsel__delete(evsel);
                 }
                 return err;
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 6ad8d4914969..f1c36ed1cf36 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -480,7 +480,6 @@ event_bpf_file:
 PE_BPF_OBJECT opt_event_config
 {
         struct parse_events_state *parse_state = _parse_state;
-        struct parse_events_error *error = parse_state->error;
         struct list_head *list;
 
         ALLOC_LIST(list);
@@ -626,7 +625,6 @@ PE_TERM
 PE_NAME array '=' PE_NAME
 {
         struct parse_events_term *term;
-        int i;
 
         ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
                                         $1, $4, &@1, &@4));
diff --git a/tools/perf/util/parse-regs-options.c b/tools/perf/util/parse-regs-options.c
index 08581e276225..ef46c2848808 100644
--- a/tools/perf/util/parse-regs-options.c
+++ b/tools/perf/util/parse-regs-options.c
@@ -1,8 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "perf.h"
-#include "util/util.h"
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <string.h>
+#include <stdio.h>
 #include "util/debug.h"
 #include <subcmd/parse-options.h>
+#include "util/perf_regs.h"
 #include "util/parse-regs-options.h"
 
 static int
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 55f4de6442e3..f32b710347db 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -2,6 +2,7 @@
 #include <linux/list.h>
 #include <linux/compiler.h>
 #include <linux/string.h>
+#include <linux/zalloc.h>
 #include <sys/types.h>
 #include <errno.h>
 #include <fcntl.h>
@@ -14,7 +15,6 @@
 #include <api/fs/fs.h>
 #include <locale.h>
 #include <regex.h>
-#include "util.h"
 #include "pmu.h"
 #include "parse-events.h"
 #include "cpumap.h"
@@ -1245,7 +1245,7 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
                 info->metric_expr = alias->metric_expr;
                 info->metric_name = alias->metric_name;
 
-                list_del(&term->list);
+                list_del_init(&term->list);
                 free(term);
         }
 
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 6f24eaf6e504..cd1eb73cfe83 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -19,7 +19,6 @@
 #include <limits.h>
 #include <elf.h>
 
-#include "util.h"
 #include "event.h"
 #include "namespaces.h"
 #include "strlist.h"
@@ -40,6 +39,7 @@
 #include "string2.h"
 
 #include <linux/ctype.h>
+#include <linux/zalloc.h>
 
 #define PERFPROBE_GROUP "probe"
 
@@ -214,9 +214,9 @@ out:
 
 static void clear_perf_probe_point(struct perf_probe_point *pp)
 {
-        free(pp->file);
-        free(pp->function);
-        free(pp->lazy_line);
+        zfree(&pp->file);
+        zfree(&pp->function);
+        zfree(&pp->lazy_line);
 }
 
 static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
@@ -1175,12 +1175,11 @@ int show_available_vars(struct perf_probe_event *pevs __maybe_unused,
 
 void line_range__clear(struct line_range *lr)
 {
-        free(lr->function);
-        free(lr->file);
-        free(lr->path);
-        free(lr->comp_dir);
+        zfree(&lr->function);
+        zfree(&lr->file);
+        zfree(&lr->path);
+        zfree(&lr->comp_dir);
         intlist__delete(lr->line_list);
-        memset(lr, 0, sizeof(*lr));
 }
 
 int line_range__init(struct line_range *lr)
@@ -1563,6 +1562,17 @@ static int parse_perf_probe_arg(char *str, struct perf_probe_arg *arg)
                 str = tmp + 1;
         }
 
+        tmp = strchr(str, '@');
+        if (tmp && tmp != str && strcmp(tmp + 1, "user")) { /* user attr */
+                if (!user_access_is_supported()) {
+                        semantic_error("ftrace does not support user access\n");
+                        return -EINVAL;
+                }
+                *tmp = '\0';
+                arg->user_access = true;
+                pr_debug("user_access ");
+        }
+
         tmp = strchr(str, ':');
         if (tmp) {      /* Type setting */
                 *tmp = '\0';
@@ -2203,15 +2213,15 @@ void clear_perf_probe_event(struct perf_probe_event *pev)
         struct perf_probe_arg_field *field, *next;
         int i;
 
-        free(pev->event);
-        free(pev->group);
-        free(pev->target);
+        zfree(&pev->event);
+        zfree(&pev->group);
+        zfree(&pev->target);
         clear_perf_probe_point(&pev->point);
 
         for (i = 0; i < pev->nargs; i++) {
-                free(pev->args[i].name);
-                free(pev->args[i].var);
-                free(pev->args[i].type);
+                zfree(&pev->args[i].name);
+                zfree(&pev->args[i].var);
+                zfree(&pev->args[i].type);
                 field = pev->args[i].field;
                 while (field) {
                         next = field->next;
@@ -2220,8 +2230,7 @@ void clear_perf_probe_event(struct perf_probe_event *pev)
                         field = next;
                 }
         }
-        free(pev->args);
-        memset(pev, 0, sizeof(*pev));
+        zfree(&pev->args);
 }
 
 #define strdup_or_goto(str, label)      \
@@ -2302,15 +2311,15 @@ void clear_probe_trace_event(struct probe_trace_event *tev)
         struct probe_trace_arg_ref *ref, *next;
         int i;
 
-        free(tev->event);
-        free(tev->group);
-        free(tev->point.symbol);
-        free(tev->point.realname);
-        free(tev->point.module);
+        zfree(&tev->event);
+        zfree(&tev->group);
+        zfree(&tev->point.symbol);
+        zfree(&tev->point.realname);
+        zfree(&tev->point.module);
         for (i = 0; i < tev->nargs; i++) {
-                free(tev->args[i].name);
-                free(tev->args[i].value);
-                free(tev->args[i].type);
+                zfree(&tev->args[i].name);
+                zfree(&tev->args[i].value);
+                zfree(&tev->args[i].type);
                 ref = tev->args[i].ref;
                 while (ref) {
                         next = ref->next;
@@ -2318,8 +2327,7 @@ void clear_probe_trace_event(struct probe_trace_event *tev)
                         ref = next;
                 }
         }
-        free(tev->args);
-        memset(tev, 0, sizeof(*tev));
+        zfree(&tev->args);
 }
 
 struct kprobe_blacklist_node {
@@ -2336,8 +2344,8 @@ static void kprobe_blacklist__delete(struct list_head *blacklist)
         while (!list_empty(blacklist)) {
                 node = list_first_entry(blacklist,
                                         struct kprobe_blacklist_node, list);
-                list_del(&node->list);
-                free(node->symbol);
+                list_del_init(&node->list);
+                zfree(&node->symbol);
                 free(node);
         }
 }
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 05c8d571a901..96a319cd2378 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -37,6 +37,7 @@ struct probe_trace_point {
 struct probe_trace_arg_ref {
         struct probe_trace_arg_ref      *next;  /* Next reference */
         long                            offset; /* Offset value */
+        bool                            user_access;    /* User-memory access */
 };
 
 /* kprobe-tracer and uprobe-tracer tracing argument */
@@ -82,6 +83,7 @@ struct perf_probe_arg {
         char                            *var;   /* Variable name */
         char                            *type;  /* Type name */
         struct perf_probe_arg_field     *field; /* Structure fields */
+        bool                            user_access;    /* User-memory access */
 };
 
 /* Perf probe probing event (point + arg) */
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 0ed1900454eb..5b4d49382932 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -10,8 +10,8 @@
 #include <sys/types.h>
 #include <sys/uio.h>
 #include <unistd.h>
+#include <linux/zalloc.h>
 #include "namespaces.h"
-#include "util.h"
 #include "event.h"
 #include "strlist.h"
 #include "strfilter.h"
@@ -1005,6 +1005,7 @@ enum ftrace_readme {
         FTRACE_README_PROBE_TYPE_X = 0,
         FTRACE_README_KRETPROBE_OFFSET,
         FTRACE_README_UPROBE_REF_CTR,
+        FTRACE_README_USER_ACCESS,
         FTRACE_README_END,
 };
 
@@ -1017,6 +1018,7 @@ static struct {
         DEFINE_TYPE(FTRACE_README_PROBE_TYPE_X, "*type: * x8/16/32/64,*"),
         DEFINE_TYPE(FTRACE_README_KRETPROBE_OFFSET, "*place (kretprobe): *"),
         DEFINE_TYPE(FTRACE_README_UPROBE_REF_CTR, "*ref_ctr_offset*"),
+        DEFINE_TYPE(FTRACE_README_USER_ACCESS, "*[u]<offset>*"),
 };
 
 static bool scan_ftrace_readme(enum ftrace_readme type)
@@ -1077,3 +1079,8 @@ bool uprobe_ref_ctr_is_supported(void)
 {
         return scan_ftrace_readme(FTRACE_README_UPROBE_REF_CTR);
 }
+
+bool user_access_is_supported(void)
+{
+        return scan_ftrace_readme(FTRACE_README_USER_ACCESS);
+}
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index 2a249182f2a6..986c1c94f64f 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -70,6 +70,7 @@ int probe_cache__show_all_caches(struct strfilter *filter);
 bool probe_type_is_available(enum probe_type type);
 bool kretprobe_offset_is_supported(void);
 bool uprobe_ref_ctr_is_supported(void);
+bool user_access_is_supported(void);
 #else   /* ! HAVE_LIBELF_SUPPORT */
 static inline struct probe_cache *probe_cache__new(const char *tgt __maybe_unused, struct nsinfo *nsi __maybe_unused)
 {
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 6b40cc691a2d..025fc4491993 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -19,11 +19,11 @@
 #include <dwarf-regs.h>
 
 #include <linux/bitops.h>
+#include <linux/zalloc.h>
 #include "event.h"
 #include "dso.h"
 #include "debug.h"
 #include "intlist.h"
-#include "util.h"
 #include "strlist.h"
 #include "symbol.h"
 #include "probe-finder.h"
@@ -280,7 +280,7 @@ static_var:
 
 static int convert_variable_type(Dwarf_Die *vr_die,
                                  struct probe_trace_arg *tvar,
-                                 const char *cast)
+                                 const char *cast, bool user_access)
 {
         struct probe_trace_arg_ref **ref_ptr = &tvar->ref;
         Dwarf_Die type;
@@ -320,7 +320,8 @@ static int convert_variable_type(Dwarf_Die *vr_die,
         pr_debug("%s type is %s.\n",
                  dwarf_diename(vr_die), dwarf_diename(&type));
 
-        if (cast && strcmp(cast, "string") == 0) {      /* String type */
+        if (cast && (!strcmp(cast, "string") || !strcmp(cast, "ustring"))) {
+                /* String type */
                 ret = dwarf_tag(&type);
                 if (ret != DW_TAG_pointer_type &&
                     ret != DW_TAG_array_type) {
@@ -343,6 +344,7 @@ static int convert_variable_type(Dwarf_Die *vr_die,
                                 pr_warning("Out of memory error\n");
                                 return -ENOMEM;
                         }
+                        (*ref_ptr)->user_access = user_access;
                 }
                 if (!die_compare_name(&type, "char") &&
                     !die_compare_name(&type, "unsigned char")) {
@@ -397,7 +399,7 @@ formatted:
 static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
                                     struct perf_probe_arg_field *field,
                                     struct probe_trace_arg_ref **ref_ptr,
-                                    Dwarf_Die *die_mem)
+                                    Dwarf_Die *die_mem, bool user_access)
 {
         struct probe_trace_arg_ref *ref = *ref_ptr;
         Dwarf_Die type;
@@ -434,6 +436,7 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
                                 *ref_ptr = ref;
                 }
                 ref->offset += dwarf_bytesize(&type) * field->index;
+                ref->user_access = user_access;
                 goto next;
         } else if (tag == DW_TAG_pointer_type) {
                 /* Check the pointer and dereference */
@@ -505,17 +508,18 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
                 }
         }
         ref->offset += (long)offs;
+        ref->user_access = user_access;
 
         /* If this member is unnamed, we need to reuse this field */
         if (!dwarf_diename(die_mem))
                 return convert_variable_fields(die_mem, varname, field,
-                                                &ref, die_mem);
+                                                &ref, die_mem, user_access);
 
 next:
         /* Converting next field */
         if (field->next)
                 return convert_variable_fields(die_mem, field->name,
-                                        field->next, &ref, die_mem);
+                                field->next, &ref, die_mem, user_access);
         else
                 return 0;
 }
@@ -541,11 +545,12 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
         else if (ret == 0 && pf->pvar->field) {
                 ret = convert_variable_fields(vr_die, pf->pvar->var,
                                               pf->pvar->field, &pf->tvar->ref,
-                                              &die_mem);
+                                              &die_mem, pf->pvar->user_access);
                 vr_die = &die_mem;
         }
         if (ret == 0)
-                ret = convert_variable_type(vr_die, pf->tvar, pf->pvar->type);
+                ret = convert_variable_type(vr_die, pf->tvar, pf->pvar->type,
+                                            pf->pvar->user_access);
         /* *expr will be cached in libdw. Don't free it. */
         return ret;
 }
diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c
index 797fe1ae2d2e..28de8a4c2ce8 100644
--- a/tools/perf/util/pstack.c
+++ b/tools/perf/util/pstack.c
@@ -5,10 +5,10 @@
  * (c) 2010 Arnaldo Carvalho de Melo <acme@redhat.com>
  */
 
-#include "util.h"
 #include "pstack.h"
 #include "debug.h"
 #include <linux/kernel.h>
+#include <linux/zalloc.h>
 #include <stdlib.h>
 
 struct pstack {
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 2237bac9fadb..ceb8afdf9a89 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -18,6 +18,7 @@ util/namespaces.c
 ../lib/hweight.c
 ../lib/string.c
 ../lib/vsprintf.c
+../lib/zalloc.c
 util/thread_map.c
 util/util.c
 util/xyarray.c
diff --git a/tools/perf/util/rlimit.c b/tools/perf/util/rlimit.c
new file mode 100644
index 000000000000..13521d392a22
--- /dev/null
+++ b/tools/perf/util/rlimit.c
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: LGPL-2.1 */
+
+#include "util/debug.h"
+#include "util/rlimit.h"
+#include <sys/time.h>
+#include <sys/resource.h>
+
+/*
+ * Bump the memlock so that we can get bpf maps of a reasonable size,
+ * like the ones used with 'perf trace' and with 'perf test bpf',
+ * improve this to some specific request if needed.
+ */
+void rlimit__bump_memlock(void)
+{
+        struct rlimit rlim;
+
+        if (getrlimit(RLIMIT_MEMLOCK, &rlim) == 0) {
+                rlim.rlim_cur *= 4;
+                rlim.rlim_max *= 4;
+
+                if (setrlimit(RLIMIT_MEMLOCK, &rlim) < 0) {
+                        rlim.rlim_cur /= 2;
+                        rlim.rlim_max /= 2;
+
+                        if (setrlimit(RLIMIT_MEMLOCK, &rlim) < 0)
+                                pr_debug("Couldn't bump rlimit(MEMLOCK), failures may take place when creating BPF maps, etc\n");
+                }
+        }
+}
diff --git a/tools/perf/util/rlimit.h b/tools/perf/util/rlimit.h
new file mode 100644
index 000000000000..9f59d8e710a3
--- /dev/null
+++ b/tools/perf/util/rlimit.h
@@ -0,0 +1,6 @@
+#ifndef __PERF_RLIMIT_H_
+#define __PERF_RLIMIT_H_
+/* SPDX-License-Identifier: LGPL-2.1 */
+
+void rlimit__bump_memlock(void);
+#endif // __PERF_RLIMIT_H_
diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c
index 10d36d9b7909..83d2e149ef19 100644
--- a/tools/perf/util/s390-cpumsf.c
+++ b/tools/perf/util/s390-cpumsf.c
@@ -146,6 +146,7 @@
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include <linux/log2.h>
+#include <linux/zalloc.h>
 
 #include <sys/stat.h>
 #include <sys/types.h>
@@ -156,7 +157,6 @@
 #include "evlist.h"
 #include "machine.h"
 #include "session.h"
-#include "util.h"
 #include "thread.h"
 #include "debug.h"
 #include "auxtrace.h"
@@ -756,7 +756,7 @@ static int s390_cpumsf_run_decoder(struct s390_cpumsf_queue *sfq,
          */
         if (err) {
                 sfq->buffer = NULL;
-                list_del(&buffer->list);
+                list_del_init(&buffer->list);
                 auxtrace_buffer__free(buffer);
                 if (err > 0)            /* Buffer done, no error */
                         err = 0;
@@ -1044,7 +1044,7 @@ static void s390_cpumsf_free(struct perf_session *session)
         auxtrace_heap__free(&sf->heap);
         s390_cpumsf_free_queues(session);
         session->auxtrace = NULL;
-        free(sf->logdir);
+        zfree(&sf->logdir);
         free(sf);
 }
 
@@ -1101,8 +1101,7 @@ static int s390_cpumsf__config(const char *var, const char *value, void *cb)
         if (rc == -1 || !S_ISDIR(stbuf.st_mode)) {
                 pr_err("Missing auxtrace log directory %s,"
                        " continue with current directory...\n", value);
-                free(sf->logdir);
-                sf->logdir = NULL;
+                zfree(&sf->logdir);
         }
         return 1;
 }
@@ -1162,7 +1161,7 @@ err_free_queues:
         auxtrace_queues__free(&sf->queues);
         session->auxtrace = NULL;
 err_free:
-        free(sf->logdir);
+        zfree(&sf->logdir);
         free(sf);
         return err;
 }
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 112bed65232f..25dc1d765553 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -113,6 +113,7 @@ struct tables {
         PyObject                *call_path_handler;
         PyObject                *call_return_handler;
         PyObject                *synth_handler;
+        PyObject                *context_switch_handler;
         bool                    db_export_mode;
 };
 
@@ -1011,15 +1012,19 @@ static int python_export_thread(struct db_export *dbe, struct thread *thread,
         return 0;
 }
 
-static int python_export_comm(struct db_export *dbe, struct comm *comm)
+static int python_export_comm(struct db_export *dbe, struct comm *comm,
+                              struct thread *thread)
 {
         struct tables *tables = container_of(dbe, struct tables, dbe);
         PyObject *t;
 
-        t = tuple_new(2);
+        t = tuple_new(5);
 
         tuple_set_u64(t, 0, comm->db_id);
         tuple_set_string(t, 1, comm__str(comm));
+        tuple_set_u64(t, 2, thread->db_id);
+        tuple_set_u64(t, 3, comm->start);
+        tuple_set_s32(t, 4, comm->exec);
 
         call_object(tables->comm_handler, t, "comm_table");
 
@@ -1233,6 +1238,34 @@ static int python_export_call_return(struct db_export *dbe,
         return 0;
 }
 
+static int python_export_context_switch(struct db_export *dbe, u64 db_id,
+                                        struct machine *machine,
+                                        struct perf_sample *sample,
+                                        u64 th_out_id, u64 comm_out_id,
+                                        u64 th_in_id, u64 comm_in_id, int flags)
+{
+        struct tables *tables = container_of(dbe, struct tables, dbe);
+        PyObject *t;
+
+        t = tuple_new(9);
+
+        tuple_set_u64(t, 0, db_id);
+        tuple_set_u64(t, 1, machine->db_id);
+        tuple_set_u64(t, 2, sample->time);
+        tuple_set_s32(t, 3, sample->cpu);
+        tuple_set_u64(t, 4, th_out_id);
+        tuple_set_u64(t, 5, comm_out_id);
+        tuple_set_u64(t, 6, th_in_id);
+        tuple_set_u64(t, 7, comm_in_id);
+        tuple_set_s32(t, 8, flags);
+
+        call_object(tables->context_switch_handler, t, "context_switch");
+
+        Py_DECREF(t);
+
+        return 0;
+}
+
 static int python_process_call_return(struct call_return *cr, u64 *parent_db_id,
                                       void *data)
 {
@@ -1296,6 +1329,16 @@ static void python_process_event(union perf_event *event,
         }
 }
 
+static void python_process_switch(union perf_event *event,
+                                  struct perf_sample *sample,
+                                  struct machine *machine)
+{
+        struct tables *tables = &tables_global;
+
+        if (tables->db_export_mode)
+                db_export__switch(&tables->dbe, event, sample, machine);
+}
+
 static void get_handler_name(char *str, size_t size,
                              struct perf_evsel *evsel)
 {
@@ -1511,6 +1554,7 @@ static void set_table_handlers(struct tables *tables)
         SET_TABLE_HANDLER(sample);
         SET_TABLE_HANDLER(call_path);
         SET_TABLE_HANDLER(call_return);
+        SET_TABLE_HANDLER(context_switch);
 
         /*
          * Synthesized events are samples but with architecture-specific data
@@ -1620,9 +1664,7 @@ error:
 
 static int python_flush_script(void)
 {
-        struct tables *tables = &tables_global;
-
-        return db_export__flush(&tables->dbe);
+        return 0;
 }
 
 /*
@@ -1831,6 +1873,7 @@ struct scripting_ops python_scripting_ops = {
         .flush_script           = python_flush_script,
         .stop_script            = python_stop_script,
         .process_event          = python_process_event,
+        .process_switch         = python_process_switch,
         .process_stat           = python_process_stat,
         .process_stat_interval  = python_process_stat_interval,
         .generate_script        = python_generate_script,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 54cf163347f7..d0fd6c614e68 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -2,6 +2,7 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <linux/kernel.h>
+#include <linux/zalloc.h>
 #include <traceevent/event-parse.h>
 #include <api/fs/fs.h>
 
@@ -18,7 +19,6 @@
 #include "session.h"
 #include "tool.h"
 #include "sort.h"
-#include "util.h"
 #include "cpumap.h"
 #include "perf_regs.h"
 #include "asm/bug.h"
@@ -1246,9 +1246,12 @@ static void dump_read(struct perf_evsel *evsel, union perf_event *event)
                 return;
 
         printf(": %d %d %s %" PRIu64 "\n", event->read.pid, event->read.tid,
-               evsel ? perf_evsel__name(evsel) : "FAIL",
+               perf_evsel__name(evsel),
                event->read.value);
 
+        if (!evsel)
+                return;
+
         read_format = evsel->attr.read_format;
 
         if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
diff --git a/tools/perf/util/setns.c b/tools/perf/util/setns.c
index ce8fc290fce8..48f9c0af63b2 100644
--- a/tools/perf/util/setns.c
+++ b/tools/perf/util/setns.c
@@ -1,4 +1,6 @@
-#include "util.h"
+// SPDX-License-Identifier: LGPL-2.1
+
+#include "namespaces.h"
 #include <unistd.h>
 #include <sys/syscall.h>
 
diff --git a/tools/perf/util/srccode.c b/tools/perf/util/srccode.c
index 684b155c222a..adfcf1ff464c 100644
--- a/tools/perf/util/srccode.c
+++ b/tools/perf/util/srccode.c
@@ -4,7 +4,8 @@
  * Copyright (c) 2017, Intel Corporation.
  * Author: Andi Kleen
  */
-#include "linux/list.h"
+#include <linux/list.h>
+#include <linux/zalloc.h>
 #include <stdlib.h>
 #include <sys/mman.h>
 #include <sys/stat.h>
@@ -82,12 +83,12 @@ static void fill_lines(char **lines, int maxline, char *map, int maplen)
 
 static void free_srcfile(struct srcfile *sf)
 {
-        list_del(&sf->nd);
+        list_del_init(&sf->nd);
         hlist_del(&sf->hash_nd);
         map_total_sz -= sf->maplen;
         munmap(sf->map, sf->maplen);
-        free(sf->lines);
-        free(sf->fn);
+        zfree(&sf->lines);
+        zfree(&sf->fn);
         free(sf);
         num_srcfiles--;
 }
@@ -153,7 +154,7 @@ static struct srcfile *find_srcfile(char *fn)
 out_map:
         munmap(h->map, sz);
 out_fn:
-        free(h->fn);
+        zfree(&h->fn);
 out_h:
         free(h);
         return NULL;
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index dcad75daf5e4..6ccf6f6d09df 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -6,9 +6,9 @@
 
 #include <linux/kernel.h>
 #include <linux/string.h>
+#include <linux/zalloc.h>
 
 #include "util/dso.h"
-#include "util/util.h"
 #include "util/debug.h"
 #include "util/callchain.h"
 #include "util/symbol_conf.h"
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index cb891e5c2969..656065af4971 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -8,6 +8,7 @@
 #include "evlist.h"
 #include "expr.h"
 #include "metricgroup.h"
+#include <linux/zalloc.h>
 
 /*
  * AGGR_GLOBAL: Use CPU 0
@@ -775,7 +776,7 @@ static void generic_metric(struct perf_stat_config *config,
                 print_metric(config, ctxp, NULL, NULL, "", 0);
 
         for (i = 1; i < pctx.num_ids; i++)
-                free((void *)pctx.ids[i].name);
+                zfree(&pctx.ids[i].name);
 }
 
 void perf_stat__print_shadow_stats(struct perf_stat_config *config,
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index d91fe754b6d2..db8a6cf336be 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -6,6 +6,7 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "thread_map.h"
+#include <linux/zalloc.h>
 
 void update_stats(struct stats *stats, u64 val)
 {
@@ -132,7 +133,7 @@ static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
         struct perf_stat_evsel *ps = evsel->stats;
 
         if (ps)
-                free(ps->group_data);
+                zfree(&ps->group_data);
         zfree(&evsel->stats);
 }
 
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index 23092fd6451d..2ce0dc887364 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -1,8 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "debug.h"
-#include "util.h"
 #include <linux/kernel.h>
+#include <linux/zalloc.h>
 #include <errno.h>
+#include <stdlib.h>
 
 /*
  * Used as the default ->buf value, so that people can always assume
diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c
index 90ea2b209cbb..78aa4c3b990d 100644
--- a/tools/perf/util/strfilter.c
+++ b/tools/perf/util/strfilter.c
@@ -1,11 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "util.h"
 #include "string2.h"
 #include "strfilter.h"
 
 #include <errno.h>
+#include <stdlib.h>
 #include <linux/ctype.h>
 #include <linux/string.h>
+#include <linux/zalloc.h>
 
 /* Operators */
 static const char *OP_and       = "&";  /* Logical AND */
diff --git a/tools/perf/util/strlist.c b/tools/perf/util/strlist.c
index af45c6fd97db..8a868cbeffae 100644
--- a/tools/perf/util/strlist.c
+++ b/tools/perf/util/strlist.c
@@ -4,12 +4,12 @@
  */
 
 #include "strlist.h"
-#include "util.h"
 #include <errno.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
+#include <linux/zalloc.h>
 
 static
 struct rb_node *strlist__node_new(struct rblist *rblist, const void *entry)
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index fab8a048d31b..76cc54000483 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -15,10 +15,10 @@
 #include <string.h>
 #include <linux/bitmap.h>
 #include <linux/time64.h>
+#include <linux/zalloc.h>
 
 #include "perf.h"
 #include "svghelper.h"
-#include "util.h"
 #include "cpumap.h"
 
 static u64 first_time, last_time;
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 62008756d8cc..7d504dc22108 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -2,6 +2,7 @@
 #include <fcntl.h>
 #include <stdio.h>
 #include <errno.h>
+#include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
 #include <inttypes.h>
@@ -16,6 +17,7 @@
 #include "debug.h"
 #include "util.h"
 #include <linux/ctype.h>
+#include <linux/zalloc.h>
 #include <symbol/kallsyms.h>
 
 #ifndef EM_AARCH64
@@ -1476,7 +1478,7 @@ static void kcore_copy__free_phdrs(struct kcore_copy_info *kci)
         struct phdr_data *p, *tmp;
 
         list_for_each_entry_safe(p, tmp, &kci->phdrs, node) {
-                list_del(&p->node);
+                list_del_init(&p->node);
                 free(p);
         }
 }
@@ -1499,7 +1501,7 @@ static void kcore_copy__free_syms(struct kcore_copy_info *kci)
         struct sym_data *s, *tmp;
 
         list_for_each_entry_safe(s, tmp, &kci->syms, node) {
-                list_del(&s->node);
+                list_del_init(&s->node);
                 free(s);
         }
 }
@@ -2131,11 +2133,11 @@ static int populate_sdt_note(Elf **elf, const char *data, size_t len,
         return 0;
 
 out_free_args:
-        free(tmp->args);
+        zfree(&tmp->args);
 out_free_name:
-        free(tmp->name);
+        zfree(&tmp->name);
 out_free_prov:
-        free(tmp->provider);
+        zfree(&tmp->provider);
 out_free_note:
         free(tmp);
 out_err:
@@ -2250,9 +2252,9 @@ int cleanup_sdt_note_list(struct list_head *sdt_notes)
         int nr_free = 0;
 
         list_for_each_entry_safe(pos, tmp, sdt_notes, note_list) {
-                list_del(&pos->note_list);
-                free(pos->name);
-                free(pos->provider);
+                list_del_init(&pos->note_list);
+                zfree(&pos->name);
+                zfree(&pos->provider);
                 free(pos);
                 nr_free++;
         }
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 17edbd4f6f85..3bc8b7e3300e 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -7,9 +7,10 @@
 #include <stdio.h>
 #include <fcntl.h>
 #include <string.h>
+#include <stdlib.h>
 #include <byteswap.h>
 #include <sys/stat.h>
-
+#include <linux/zalloc.h>
 
 static bool check_need_swap(int file_endian)
 {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index ae2ce255e848..173f3378aaa0 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -26,6 +26,7 @@
 #include "header.h"
 #include "path.h"
 #include <linux/ctype.h>
+#include <linux/zalloc.h>
 
 #include <elf.h>
 #include <limits.h>
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
index c2037ac533f3..022a9c670338 100644
--- a/tools/perf/util/syscalltbl.c
+++ b/tools/perf/util/syscalltbl.c
@@ -10,9 +10,9 @@
 #include <linux/compiler.h>
 
 #ifdef HAVE_SYSCALL_TABLE_SUPPORT
+#include <linux/zalloc.h>
 #include <string.h>
 #include "string2.h"
-#include "util.h"
 
 #if defined(__x86_64__)
 #include <asm/syscalls_64.c>
diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c
index 3852d07c49bd..3adc65480349 100644
--- a/tools/perf/util/target.c
+++ b/tools/perf/util/target.c
@@ -10,9 +10,9 @@
 #include "debug.h"
 
 #include <pwd.h>
+#include <stdlib.h>
 #include <string.h>
 
-
 enum target_errno target__validate(struct target *target)
 {
         enum target_errno ret = TARGET_ERRNO__SUCCESS;
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index 6ff1ff4d4ce7..15134ac9b8f1 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -7,12 +7,13 @@
 #include <linux/rbtree.h>
 #include <linux/list.h>
 #include <linux/log2.h>
+#include <linux/zalloc.h>
 #include <errno.h>
+#include <stdlib.h>
 #include "thread.h"
 #include "event.h"
 #include "machine.h"
 #include "env.h"
-#include "util.h"
 #include "debug.h"
 #include "symbol.h"
 #include "comm.h"
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 3e29a4e8b5e6..873ab505ca80 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -5,10 +5,10 @@
 #include <stdio.h>
 #include <string.h>
 #include <linux/kernel.h>
+#include <linux/zalloc.h>
 #include "session.h"
 #include "thread.h"
 #include "thread-stack.h"
-#include "util.h"
 #include "debug.h"
 #include "namespaces.h"
 #include "comm.h"
@@ -93,14 +93,14 @@ void thread__delete(struct thread *thread)
         down_write(&thread->namespaces_lock);
         list_for_each_entry_safe(namespaces, tmp_namespaces,
                                  &thread->namespaces_list, list) {
-                list_del(&namespaces->list);
+                list_del_init(&namespaces->list);
                 namespaces__free(namespaces);
         }
         up_write(&thread->namespaces_lock);
 
         down_write(&thread->comm_lock);
         list_for_each_entry_safe(comm, tmp_comm, &thread->comm_list, list) {
-                list_del(&comm->list);
+                list_del_init(&comm->list);
                 comm__free(comm);
         }
         up_write(&thread->comm_lock);
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 281bf06f10f2..5b3511f2b6b1 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -13,9 +13,9 @@
 #include <string.h>
 #include <api/fs/fs.h>
 #include <linux/string.h>
+#include <linux/zalloc.h>
 #include "asm/bug.h"
 #include "thread_map.h"
-#include "util.h"
 #include "debug.h"
 #include "event.h"
 
@@ -480,7 +480,7 @@ int thread_map__remove(struct thread_map *threads, int idx)
         /*
          * Free the 'idx' item and shift the rest up.
          */
-        free(threads->map[idx].comm);
+        zfree(&threads->map[idx].comm);
 
         for (i = idx; i < threads->nr - 1; i++)
                 threads->map[i] = threads->map[i + 1];
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index 806a11b334d3..4550015b9d5d 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -18,6 +18,7 @@
 #include <stdbool.h>
 #include <linux/list.h>
 #include <linux/kernel.h>
+#include <linux/zalloc.h>
 
 #include "../perf.h"
 #include "trace-event.h"
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index b023db136ef3..ba58f69777a1 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -12,8 +12,8 @@
 
 #include "../perf.h"
 #include "debug.h"
-#include "util.h"
 #include "trace-event.h"
+#include <linux/zalloc.h>
 
 struct scripting_context *scripting_context;
 
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index d9b0a942090a..c7002fe11673 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -81,6 +81,9 @@ struct scripting_ops {
                                struct perf_sample *sample,
                                struct perf_evsel *evsel,
                                struct addr_location *al);
+        void (*process_switch)(union perf_event *event,
+                               struct perf_sample *sample,
+                               struct machine *machine);
         void (*process_stat)(struct perf_stat_config *config,
                              struct perf_evsel *evsel, u64 tstamp);
         void (*process_stat_interval)(u64 tstamp);
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 407d0167b942..28f71ca6ce1c 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -12,6 +12,7 @@
 #include "symbol.h"
 #include "thread.h"
 #include <linux/types.h>
+#include <linux/zalloc.h>
 #include "event.h"
 #include "perf_regs.h"
 #include "callchain.h"
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 25e1406b1f8b..71a788921b62 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -25,6 +25,7 @@
 #include <unistd.h>
 #include <sys/mman.h>
 #include <linux/list.h>
+#include <linux/zalloc.h>
 #ifndef REMOTE_UNWIND_LIBUNWIND
 #include <libunwind.h>
 #include <libunwind-ptrace.h>
@@ -345,7 +346,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
                                                         __func__,
                                                         dso->symsrc_filename,
                                                         debuglink);
-                                        free(dso->symsrc_filename);
+                                        zfree(&dso->symsrc_filename);
                                 }
                                 dso->symsrc_filename = debuglink;
                         } else {
diff --git a/tools/perf/util/usage.c b/tools/perf/util/usage.c
index 070d25ceea6a..3949a60b00ae 100644
--- a/tools/perf/util/usage.c
+++ b/tools/perf/util/usage.c
@@ -9,6 +9,9 @@
  */
 #include "util.h"
 #include "debug.h"
+#include <stdio.h>
+#include <stdlib.h>
+#include <linux/compiler.h>
 
 static __noreturn void usage_builtin(const char *err)
 {
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 125e215dd3d8..dc7a469921e9 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -9,8 +9,6 @@
 #include <fcntl.h>
 #include <stdbool.h>
 #include <stddef.h>
-#include <stdlib.h>
-#include <stdarg.h>
 #include <linux/compiler.h>
 #include <sys/types.h>
 
@@ -18,13 +16,6 @@
 void usage(const char *err) __noreturn;
 void die(const char *err, ...) __noreturn __printf(1, 2);
 
-static inline void *zalloc(size_t size)
-{
-        return calloc(1, size);
-}
-
-#define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
-
 struct dirent;
 struct nsinfo;
 struct strlist;
@@ -59,18 +50,10 @@ int fetch_kernel_version(unsigned int *puint,
 
 const char *perf_tip(const char *dirpath);
 
-#ifndef HAVE_GET_CURRENT_DIR_NAME
-char *get_current_dir_name(void);
-#endif
-
 #ifndef HAVE_SCHED_GETCPU_SUPPORT
 int sched_getcpu(void);
 #endif
 
-#ifndef HAVE_SETNS_SUPPORT
-int setns(int fd, int nstype);
-#endif
-
 extern bool perf_singlethreaded;
 
 void perf_set_singlethreaded(void);
diff --git a/tools/perf/util/values.c b/tools/perf/util/values.c
index 4b7a303e4ba8..c59154e2d124 100644
--- a/tools/perf/util/values.c
+++ b/tools/perf/util/values.c
@@ -3,8 +3,8 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <errno.h>
+#include <linux/zalloc.h>
 
-#include "util.h"
 #include "values.h"
 #include "debug.h"
 
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 5031b7b22bbd..7f427bab6c12 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -16,6 +16,7 @@
 #include "machine.h"
 #include "thread.h"
 #include "linux/string.h"
+#include <linux/zalloc.h>
 #include "debug.h"
 
 /*
diff --git a/tools/perf/util/xyarray.c b/tools/perf/util/xyarray.c
index dc95154f5646..86889ebc3514 100644
--- a/tools/perf/util/xyarray.c
+++ b/tools/perf/util/xyarray.c
@@ -1,8 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "xyarray.h"
-#include "util.h"
 #include <stdlib.h>
 #include <string.h>
+#include <linux/zalloc.h>
 
 struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size)
 {
diff --git a/tools/power/cpupower/debug/kernel/Makefile b/tools/power/cpupower/debug/kernel/Makefile
index c23e5a6ceb7e..7b5c43684be1 100644
--- a/tools/power/cpupower/debug/kernel/Makefile
+++ b/tools/power/cpupower/debug/kernel/Makefile
@@ -12,8 +12,8 @@ default:
         $(MAKE) -C $(KDIR) M=$(CURDIR)
 
 clean:
-        - rm -rf *.o *.ko .tmp-versions .*.cmd .*.mod.* *.mod.c
-        - rm -rf .tmp_versions* Module.symvers modules.order
+        - rm -rf *.o *.ko .*.cmd .*.mod.* *.mod.c
+        - rm -rf Module.symvers modules.order
 
 install: default
         install -d $(KMISC)
diff --git a/tools/power/x86/intel-speed-select/.gitignore b/tools/power/x86/intel-speed-select/.gitignore
new file mode 100644
index 000000000000..f61145925ce9
--- /dev/null
+++ b/tools/power/x86/intel-speed-select/.gitignore
@@ -0,0 +1,2 @@
+include/
+intel-speed-select
diff --git a/tools/power/x86/intel-speed-select/Build b/tools/power/x86/intel-speed-select/Build
new file mode 100644
index 000000000000..b61456d75190
--- /dev/null
+++ b/tools/power/x86/intel-speed-select/Build
@@ -0,0 +1 @@
+intel-speed-select-y +=  isst-config.o isst-core.o isst-display.o
diff --git a/tools/power/x86/intel-speed-select/Makefile b/tools/power/x86/intel-speed-select/Makefile
new file mode 100644
index 000000000000..12c6939dca2a
--- /dev/null
+++ b/tools/power/x86/intel-speed-select/Makefile
@@ -0,0 +1,56 @@
+# SPDX-License-Identifier: GPL-2.0
+include ../../../scripts/Makefile.include
+
+bindir ?= /usr/bin
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+endif
+
+# Do not use make's built-in rules
+# (this improves performance and avoids hard-to-debug behaviour);
+MAKEFLAGS += -r
+
+override CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include
+
+ALL_TARGETS := intel-speed-select
+ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS))
+
+all: $(ALL_PROGRAMS)
+
+export srctree OUTPUT CC LD CFLAGS
+include $(srctree)/tools/build/Makefile.include
+
+#
+# We need the following to be outside of kernel tree
+#
+$(OUTPUT)include/linux/isst_if.h: ../../../../include/uapi/linux/isst_if.h
+        mkdir -p $(OUTPUT)include/linux 2>&1 || true
+        ln -sf $(CURDIR)/../../../../include/uapi/linux/isst_if.h $@
+
+prepare: $(OUTPUT)include/linux/isst_if.h
+
+ISST_IN := $(OUTPUT)intel-speed-select-in.o
+
+$(ISST_IN): prepare FORCE
+        $(Q)$(MAKE) $(build)=intel-speed-select
+$(OUTPUT)intel-speed-select: $(ISST_IN)
+        $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@
+
+clean:
+        rm -f $(ALL_PROGRAMS)
+        rm -rf $(OUTPUT)include/linux/isst_if.h
+        find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete
+
+install: $(ALL_PROGRAMS)
+        install -d -m 755 $(DESTDIR)$(bindir);          \
+        for program in $(ALL_PROGRAMS); do              \
+                install $$program $(DESTDIR)$(bindir);  \
+        done
+
+FORCE:
+
+.PHONY: all install clean FORCE prepare
diff --git a/tools/power/x86/intel-speed-select/isst-config.c b/tools/power/x86/intel-speed-select/isst-config.c
new file mode 100644
index 000000000000..91c5ad1685a1
--- /dev/null
+++ b/tools/power/x86/intel-speed-select/isst-config.c
@@ -0,0 +1,1607 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel Speed Select -- Enumerate and control features
+ * Copyright (c) 2019 Intel Corporation.
+ */
+
+#include <linux/isst_if.h>
+
+#include "isst.h"
+
+struct process_cmd_struct {
+        char *feature;
+        char *command;
+        void (*process_fn)(void);
+};
+
+static const char *version_str = "v1.0";
+static const int supported_api_ver = 1;
+static struct isst_if_platform_info isst_platform_info;
+static char *progname;
+static int debug_flag;
+static FILE *outf;
+
+static int cpu_model;
+
+#define MAX_CPUS_IN_ONE_REQ 64
+static short max_target_cpus;
+static unsigned short target_cpus[MAX_CPUS_IN_ONE_REQ];
+
+static int topo_max_cpus;
+static size_t present_cpumask_size;
+static cpu_set_t *present_cpumask;
+static size_t target_cpumask_size;
+static cpu_set_t *target_cpumask;
+static int tdp_level = 0xFF;
+static int fact_bucket = 0xFF;
+static int fact_avx = 0xFF;
+static unsigned long long fact_trl;
+static int out_format_json;
+static int cmd_help;
+
+/* clos related */
+static int current_clos = -1;
+static int clos_epp = -1;
+static int clos_prop_prio = -1;
+static int clos_min = -1;
+static int clos_max = -1;
+static int clos_desired = -1;
+static int clos_priority_type;
+
+struct _cpu_map {
+        unsigned short core_id;
+        unsigned short pkg_id;
+        unsigned short die_id;
+        unsigned short punit_cpu;
+        unsigned short punit_cpu_core;
+};
+struct _cpu_map *cpu_map;
+
+void debug_printf(const char *format, ...)
+{
+        va_list args;
+
+        va_start(args, format);
+
+        if (debug_flag)
+                vprintf(format, args);
+
+        va_end(args);
+}
+
+static void update_cpu_model(void)
+{
+        unsigned int ebx, ecx, edx;
+        unsigned int fms, family;
+
+        __cpuid(1, fms, ebx, ecx, edx);
+        family = (fms >> 8) & 0xf;
+        cpu_model = (fms >> 4) & 0xf;
+        if (family == 6 || family == 0xf)
+                cpu_model += ((fms >> 16) & 0xf) << 4;
+}
+
+/* Open a file, and exit on failure */
+static FILE *fopen_or_exit(const char *path, const char *mode)
+{
+        FILE *filep = fopen(path, mode);
+
+        if (!filep)
+                err(1, "%s: open failed", path);
+
+        return filep;
+}
+
+/* Parse a file containing a single int */
+static int parse_int_file(int fatal, const char *fmt, ...)
+{
+        va_list args;
+        char path[PATH_MAX];
+        FILE *filep;
+        int value;
+
+        va_start(args, fmt);
+        vsnprintf(path, sizeof(path), fmt, args);
+        va_end(args);
+        if (fatal) {
+                filep = fopen_or_exit(path, "r");
+        } else {
+                filep = fopen(path, "r");
+                if (!filep)
+                        return -1;
+        }
+        if (fscanf(filep, "%d", &value) != 1)
+                err(1, "%s: failed to parse number from file", path);
+        fclose(filep);
+
+        return value;
+}
+
+int cpufreq_sysfs_present(void)
+{
+        DIR *dir;
+
+        dir = opendir("/sys/devices/system/cpu/cpu0/cpufreq");
+        if (dir) {
+                closedir(dir);
+                return 1;
+        }
+
+        return 0;
+}
+
+int out_format_is_json(void)
+{
+        return out_format_json;
+}
+
+int get_physical_package_id(int cpu)
+{
+        return parse_int_file(
+                1, "/sys/devices/system/cpu/cpu%d/topology/physical_package_id",
+                cpu);
+}
+
+int get_physical_core_id(int cpu)
+{
+        return parse_int_file(
+                1, "/sys/devices/system/cpu/cpu%d/topology/core_id", cpu);
+}
+
+int get_physical_die_id(int cpu)
+{
+        int ret;
+
+        ret = parse_int_file(0, "/sys/devices/system/cpu/cpu%d/topology/die_id",
+                             cpu);
+        if (ret < 0)
+                ret = 0;
+
+        return ret;
+}
+
+int get_topo_max_cpus(void)
+{
+        return topo_max_cpus;
+}
+
+#define MAX_PACKAGE_COUNT 8
+#define MAX_DIE_PER_PACKAGE 2
+static void for_each_online_package_in_set(void (*callback)(int, void *, void *,
+                                                            void *, void *),
+                                           void *arg1, void *arg2, void *arg3,
+                                           void *arg4)
+{
+        int max_packages[MAX_PACKAGE_COUNT * MAX_PACKAGE_COUNT];
+        int pkg_index = 0, i;
+
+        memset(max_packages, 0xff, sizeof(max_packages));
+        for (i = 0; i < topo_max_cpus; ++i) {
+                int j, online, pkg_id, die_id = 0, skip = 0;
+
+                if (!CPU_ISSET_S(i, present_cpumask_size, present_cpumask))
+                        continue;
+                if (i)
+                        online = parse_int_file(
+                                1, "/sys/devices/system/cpu/cpu%d/online", i);
+                else
+                        online =
+                                1; /* online entry for CPU 0 needs some special configs */
+
+                die_id = get_physical_die_id(i);
+                if (die_id < 0)
+                        die_id = 0;
+                pkg_id = get_physical_package_id(i);
+                /* Create an unique id for package, die combination to store */
+                pkg_id = (MAX_PACKAGE_COUNT * pkg_id + die_id);
+
+                for (j = 0; j < pkg_index; ++j) {
+                        if (max_packages[j] == pkg_id) {
+                                skip = 1;
+                                break;
+                        }
+                }
+
+                if (!skip && online && callback) {
+                        callback(i, arg1, arg2, arg3, arg4);
+                        max_packages[pkg_index++] = pkg_id;
+                }
+        }
+}
+
+static void for_each_online_target_cpu_in_set(
+        void (*callback)(int, void *, void *, void *, void *), void *arg1,
+        void *arg2, void *arg3, void *arg4)
+{
+        int i;
+
+        for (i = 0; i < topo_max_cpus; ++i) {
+                int online;
+
+                if (!CPU_ISSET_S(i, target_cpumask_size, target_cpumask))
+                        continue;
+                if (i)
+                        online = parse_int_file(
+                                1, "/sys/devices/system/cpu/cpu%d/online", i);
+                else
+                        online =
+                                1; /* online entry for CPU 0 needs some special configs */
+
+                if (online && callback)
+                        callback(i, arg1, arg2, arg3, arg4);
+        }
+}
+
+#define BITMASK_SIZE 32
+static void set_max_cpu_num(void)
+{
+        FILE *filep;
+        unsigned long dummy;
+
+        topo_max_cpus = 0;
+        filep = fopen_or_exit(
+                "/sys/devices/system/cpu/cpu0/topology/thread_siblings", "r");
+        while (fscanf(filep, "%lx,", &dummy) == 1)
+                topo_max_cpus += BITMASK_SIZE;
+        fclose(filep);
+        topo_max_cpus--; /* 0 based */
+
+        debug_printf("max cpus %d\n", topo_max_cpus);
+}
+
+size_t alloc_cpu_set(cpu_set_t **cpu_set)
+{
+        cpu_set_t *_cpu_set;
+        size_t size;
+
+        _cpu_set = CPU_ALLOC((topo_max_cpus + 1));
+        if (_cpu_set == NULL)
+                err(3, "CPU_ALLOC");
+        size = CPU_ALLOC_SIZE((topo_max_cpus + 1));
+        CPU_ZERO_S(size, _cpu_set);
+
+        *cpu_set = _cpu_set;
+        return size;
+}
+
+void free_cpu_set(cpu_set_t *cpu_set)
+{
+        CPU_FREE(cpu_set);
+}
+
+static int cpu_cnt[MAX_PACKAGE_COUNT][MAX_DIE_PER_PACKAGE];
+static void set_cpu_present_cpu_mask(void)
+{
+        size_t size;
+        DIR *dir;
+        int i;
+
+        size = alloc_cpu_set(&present_cpumask);
+        present_cpumask_size = size;
+        for (i = 0; i < topo_max_cpus; ++i) {
+                char buffer[256];
+
+                snprintf(buffer, sizeof(buffer),
+                         "/sys/devices/system/cpu/cpu%d", i);
+                dir = opendir(buffer);
+                if (dir) {
+                        int pkg_id, die_id;
+
+                        CPU_SET_S(i, size, present_cpumask);
+                        die_id = get_physical_die_id(i);
+                        if (die_id < 0)
+                                die_id = 0;
+
+                        pkg_id = get_physical_package_id(i);
+                        if (pkg_id < MAX_PACKAGE_COUNT &&
+                            die_id < MAX_DIE_PER_PACKAGE)
+                                cpu_cnt[pkg_id][die_id]++;
+                }
+                closedir(dir);
+        }
+}
+
+int get_cpu_count(int pkg_id, int die_id)
+{
+        if (pkg_id < MAX_PACKAGE_COUNT && die_id < MAX_DIE_PER_PACKAGE)
+                return cpu_cnt[pkg_id][die_id] + 1;
+
+        return 0;
+}
+
+static void set_cpu_target_cpu_mask(void)
+{
+        size_t size;
+        int i;
+
+        size = alloc_cpu_set(&target_cpumask);
+        target_cpumask_size = size;
+        for (i = 0; i < max_target_cpus; ++i) {
+                if (!CPU_ISSET_S(target_cpus[i], present_cpumask_size,
+                                 present_cpumask))
+                        continue;
+
+                CPU_SET_S(target_cpus[i], size, target_cpumask);
+        }
+}
+
+static void create_cpu_map(void)
+{
+        const char *pathname = "/dev/isst_interface";
+        int i, fd = 0;
+        struct isst_if_cpu_maps map;
+
+        cpu_map = malloc(sizeof(*cpu_map) * topo_max_cpus);
+        if (!cpu_map)
+                err(3, "cpumap");
+
+        fd = open(pathname, O_RDWR);
+        if (fd < 0)
+                err(-1, "%s open failed", pathname);
+
+        for (i = 0; i < topo_max_cpus; ++i) {
+                if (!CPU_ISSET_S(i, present_cpumask_size, present_cpumask))
+                        continue;
+
+                map.cmd_count = 1;
+                map.cpu_map[0].logical_cpu = i;
+
+                debug_printf(" map logical_cpu:%d\n",
+                             map.cpu_map[0].logical_cpu);
+                if (ioctl(fd, ISST_IF_GET_PHY_ID, &map) == -1) {
+                        perror("ISST_IF_GET_PHY_ID");
+                        fprintf(outf, "Error: map logical_cpu:%d\n",
+                                map.cpu_map[0].logical_cpu);
+                        continue;
+                }
+                cpu_map[i].core_id = get_physical_core_id(i);
+                cpu_map[i].pkg_id = get_physical_package_id(i);
+                cpu_map[i].die_id = get_physical_die_id(i);
+                cpu_map[i].punit_cpu = map.cpu_map[0].physical_cpu;
+                cpu_map[i].punit_cpu_core = (map.cpu_map[0].physical_cpu >>
+                                             1); // shift to get core id
+
+                debug_printf(
+                        "map logical_cpu:%d core: %d die:%d pkg:%d punit_cpu:%d punit_core:%d\n",
+                        i, cpu_map[i].core_id, cpu_map[i].die_id,
+                        cpu_map[i].pkg_id, cpu_map[i].punit_cpu,
+                        cpu_map[i].punit_cpu_core);
+        }
+
+        if (fd)
+                close(fd);
+}
+
+int find_logical_cpu(int pkg_id, int die_id, int punit_core_id)
+{
+        int i;
+
+        for (i = 0; i < topo_max_cpus; ++i) {
+                if (cpu_map[i].pkg_id == pkg_id &&
+                    cpu_map[i].die_id == die_id &&
+                    cpu_map[i].punit_cpu_core == punit_core_id)
+                        return i;
+        }
+
+        return -EINVAL;
+}
+
+void set_cpu_mask_from_punit_coremask(int cpu, unsigned long long core_mask,
+                                      size_t core_cpumask_size,
+                                      cpu_set_t *core_cpumask, int *cpu_cnt)
+{
+        int i, cnt = 0;
+        int die_id, pkg_id;
+
+        *cpu_cnt = 0;
+        die_id = get_physical_die_id(cpu);
+        pkg_id = get_physical_package_id(cpu);
+
+        for (i = 0; i < 64; ++i) {
+                if (core_mask & BIT(i)) {
+                        int j;
+
+                        for (j = 0; j < topo_max_cpus; ++j) {
+                                if (cpu_map[j].pkg_id == pkg_id &&
+                                    cpu_map[j].die_id == die_id &&
+                                    cpu_map[j].punit_cpu_core == i) {
+                                        CPU_SET_S(j, core_cpumask_size,
+                                                  core_cpumask);
+                                        ++cnt;
+                                }
+                        }
+                }
+        }
+
+        *cpu_cnt = cnt;
+}
+
+int find_phy_core_num(int logical_cpu)
+{
+        if (logical_cpu < topo_max_cpus)
+                return cpu_map[logical_cpu].punit_cpu_core;
+
+        return -EINVAL;
+}
+
+static int isst_send_mmio_command(unsigned int cpu, unsigned int reg, int write,
+                                  unsigned int *value)
+{
+        struct isst_if_io_regs io_regs;
+        const char *pathname = "/dev/isst_interface";
+        int cmd;
+        int fd;
+
+        debug_printf("mmio_cmd cpu:%d reg:%d write:%d\n", cpu, reg, write);
+
+        fd = open(pathname, O_RDWR);
+        if (fd < 0)
+                err(-1, "%s open failed", pathname);
+
+        io_regs.req_count = 1;
+        io_regs.io_reg[0].logical_cpu = cpu;
+        io_regs.io_reg[0].reg = reg;
+        cmd = ISST_IF_IO_CMD;
+        if (write) {
+                io_regs.io_reg[0].read_write = 1;
+                io_regs.io_reg[0].value = *value;
+        } else {
+                io_regs.io_reg[0].read_write = 0;
+        }
+
+        if (ioctl(fd, cmd, &io_regs) == -1) {
+                perror("ISST_IF_IO_CMD");
+                fprintf(outf, "Error: mmio_cmd cpu:%d reg:%x read_write:%x\n",
+                        cpu, reg, write);
+        } else {
+                if (!write)
+                        *value = io_regs.io_reg[0].value;
+
+                debug_printf(
+                        "mmio_cmd response: cpu:%d reg:%x rd_write:%x resp:%x\n",
+                        cpu, reg, write, *value);
+        }
+
+        close(fd);
+
+        return 0;
+}
+
+int isst_send_mbox_command(unsigned int cpu, unsigned char command,
+                           unsigned char sub_command, unsigned int parameter,
+                           unsigned int req_data, unsigned int *resp)
+{
+        const char *pathname = "/dev/isst_interface";
+        int fd;
+        struct isst_if_mbox_cmds mbox_cmds = { 0 };
+
+        debug_printf(
+                "mbox_send: cpu:%d command:%x sub_command:%x parameter:%x req_data:%x\n",
+                cpu, command, sub_command, parameter, req_data);
+
+        if (isst_platform_info.mmio_supported && command == CONFIG_CLOS) {
+                unsigned int value;
+                int write = 0;
+                int clos_id, core_id, ret = 0;
+
+                debug_printf("CLOS %d\n", cpu);
+
+                if (parameter & BIT(MBOX_CMD_WRITE_BIT)) {
+                        value = req_data;
+                        write = 1;
+                }
+
+                switch (sub_command) {
+                case CLOS_PQR_ASSOC:
+                        core_id = parameter & 0xff;
+                        ret = isst_send_mmio_command(
+                                cpu, PQR_ASSOC_OFFSET + core_id * 4, write,
+                                &value);
+                        if (!ret && !write)
+                                *resp = value;
+                        break;
+                case CLOS_PM_CLOS:
+                        clos_id = parameter & 0x03;
+                        ret = isst_send_mmio_command(
+                                cpu, PM_CLOS_OFFSET + clos_id * 4, write,
+                                &value);
+                        if (!ret && !write)
+                                *resp = value;
+                        break;
+                case CLOS_PM_QOS_CONFIG:
+                        ret = isst_send_mmio_command(cpu, PM_QOS_CONFIG_OFFSET,
+                                                     write, &value);
+                        if (!ret && !write)
+                                *resp = value;
+                        break;
+                case CLOS_STATUS:
+                        break;
+                default:
+                        break;
+                }
+                return ret;
+        }
+
+        mbox_cmds.cmd_count = 1;
+        mbox_cmds.mbox_cmd[0].logical_cpu = cpu;
+        mbox_cmds.mbox_cmd[0].command = command;
+        mbox_cmds.mbox_cmd[0].sub_command = sub_command;
+        mbox_cmds.mbox_cmd[0].parameter = parameter;
+        mbox_cmds.mbox_cmd[0].req_data = req_data;
+
+        fd = open(pathname, O_RDWR);
+        if (fd < 0)
+                err(-1, "%s open failed", pathname);
+
+        if (ioctl(fd, ISST_IF_MBOX_COMMAND, &mbox_cmds) == -1) {
+                perror("ISST_IF_MBOX_COMMAND");
+                fprintf(outf,
+                        "Error: mbox_cmd cpu:%d command:%x sub_command:%x parameter:%x req_data:%x\n",
+                        cpu, command, sub_command, parameter, req_data);
+        } else {
+                *resp = mbox_cmds.mbox_cmd[0].resp_data;
+                debug_printf(
+                        "mbox_cmd response: cpu:%d command:%x sub_command:%x parameter:%x req_data:%x resp:%x\n",
+                        cpu, command, sub_command, parameter, req_data, *resp);
+        }
+
+        close(fd);
+
+        return 0;
+}
+
+int isst_send_msr_command(unsigned int cpu, unsigned int msr, int write,
+                          unsigned long long *req_resp)
+{
+        struct isst_if_msr_cmds msr_cmds;
+        const char *pathname = "/dev/isst_interface";
+        int fd;
+
+        fd = open(pathname, O_RDWR);
+        if (fd < 0)
+                err(-1, "%s open failed", pathname);
+
+        msr_cmds.cmd_count = 1;
+        msr_cmds.msr_cmd[0].logical_cpu = cpu;
+        msr_cmds.msr_cmd[0].msr = msr;
+        msr_cmds.msr_cmd[0].read_write = write;
+        if (write)
+                msr_cmds.msr_cmd[0].data = *req_resp;
+
+        if (ioctl(fd, ISST_IF_MSR_COMMAND, &msr_cmds) == -1) {
+                perror("ISST_IF_MSR_COMMAD");
+                fprintf(outf, "Error: msr_cmd cpu:%d msr:%x read_write:%d\n",
+                        cpu, msr, write);
+        } else {
+                if (!write)
+                        *req_resp = msr_cmds.msr_cmd[0].data;
+
+                debug_printf(
+                        "msr_cmd response: cpu:%d msr:%x rd_write:%x resp:%llx %llx\n",
+                        cpu, msr, write, *req_resp, msr_cmds.msr_cmd[0].data);
+        }
+
+        close(fd);
+
+        return 0;
+}
+
+static int isst_fill_platform_info(void)
+{
+        const char *pathname = "/dev/isst_interface";
+        int fd;
+
+        fd = open(pathname, O_RDWR);
+        if (fd < 0)
+                err(-1, "%s open failed", pathname);
+
+        if (ioctl(fd, ISST_IF_GET_PLATFORM_INFO, &isst_platform_info) == -1) {
+                perror("ISST_IF_GET_PLATFORM_INFO");
+                close(fd);
+                return -1;
+        }
+
+        close(fd);
+
+        return 0;
+}
+
+static void isst_print_platform_information(void)
+{
+        struct isst_if_platform_info platform_info;
+        const char *pathname = "/dev/isst_interface";
+        int fd;
+
+        fd = open(pathname, O_RDWR);
+        if (fd < 0)
+                err(-1, "%s open failed", pathname);
+
+        if (ioctl(fd, ISST_IF_GET_PLATFORM_INFO, &platform_info) == -1) {
+                perror("ISST_IF_GET_PLATFORM_INFO");
+        } else {
+                fprintf(outf, "Platform: API version : %d\n",
+                        platform_info.api_version);
+                fprintf(outf, "Platform: Driver version : %d\n",
+                        platform_info.driver_version);
+                fprintf(outf, "Platform: mbox supported : %d\n",
+                        platform_info.mbox_supported);
+                fprintf(outf, "Platform: mmio supported : %d\n",
+                        platform_info.mmio_supported);
+        }
+
+        close(fd);
+
+        exit(0);
+}
+
+static void exec_on_get_ctdp_cpu(int cpu, void *arg1, void *arg2, void *arg3,
+                                 void *arg4)
+{
+        int (*fn_ptr)(int cpu, void *arg);
+        int ret;
+
+        fn_ptr = arg1;
+        ret = fn_ptr(cpu, arg2);
+        if (ret)
+                perror("get_tdp_*");
+        else
+                isst_display_result(cpu, outf, "perf-profile", (char *)arg3,
+                                    *(unsigned int *)arg4);
+}
+
+#define _get_tdp_level(desc, suffix, object, help)                                \
+        static void get_tdp_##object(void)                                        \
+        {                                                                         \
+                struct isst_pkg_ctdp ctdp;                                        \
+\
+                if (cmd_help) {                                                   \
+                        fprintf(stderr,                                           \
+                                "Print %s [No command arguments are required]\n", \
+                                help);                                            \
+                        exit(0);                                                  \
+                }                                                                 \
+                isst_ctdp_display_information_start(outf);                        \
+                if (max_target_cpus)                                              \
+                        for_each_online_target_cpu_in_set(                        \
+                                exec_on_get_ctdp_cpu, isst_get_ctdp_##suffix,     \
+                                &ctdp, desc, &ctdp.object);                       \
+                else                                                              \
+                        for_each_online_package_in_set(exec_on_get_ctdp_cpu,      \
+                                                       isst_get_ctdp_##suffix,    \
+                                                       &ctdp, desc,               \
+                                                       &ctdp.object);             \
+                isst_ctdp_display_information_end(outf);                          \
+        }
+
+_get_tdp_level("get-config-levels", levels, levels, "TDP levels");
+_get_tdp_level("get-config-version", levels, version, "TDP version");
+_get_tdp_level("get-config-enabled", levels, enabled, "TDP enable status");
+_get_tdp_level("get-config-current_level", levels, current_level,
+               "Current TDP Level");
+_get_tdp_level("get-lock-status", levels, locked, "TDP lock status");
+
+static void dump_isst_config_for_cpu(int cpu, void *arg1, void *arg2,
+                                     void *arg3, void *arg4)
+{
+        struct isst_pkg_ctdp pkg_dev;
+        int ret;
+
+        memset(&pkg_dev, 0, sizeof(pkg_dev));
+        ret = isst_get_process_ctdp(cpu, tdp_level, &pkg_dev);
+        if (ret) {
+                perror("isst_get_process_ctdp");
+        } else {
+                isst_ctdp_display_information(cpu, outf, tdp_level, &pkg_dev);
+                isst_get_process_ctdp_complete(cpu, &pkg_dev);
+        }
+}
+
+static void dump_isst_config(void)
+{
+        if (cmd_help) {
+                fprintf(stderr,
+                        "Print Intel(R) Speed Select Technology Performance profile configuration\n");
+                fprintf(stderr,
+                        "including base frequency and turbo frequency configurations\n");
+                fprintf(stderr, "Optional: -l|--level : Specify tdp level\n");
+                fprintf(stderr,
+                        "\tIf no arguments, dump information for all TDP levels\n");
+                exit(0);
+        }
+
+        isst_ctdp_display_information_start(outf);
+
+        if (max_target_cpus)
+                for_each_online_target_cpu_in_set(dump_isst_config_for_cpu,
+                                                  NULL, NULL, NULL, NULL);
+        else
+                for_each_online_package_in_set(dump_isst_config_for_cpu, NULL,
+                                               NULL, NULL, NULL);
+
+        isst_ctdp_display_information_end(outf);
+}
+
+static void set_tdp_level_for_cpu(int cpu, void *arg1, void *arg2, void *arg3,
+                                  void *arg4)
+{
+        int ret;
+
+        ret = isst_set_tdp_level(cpu, tdp_level);
+        if (ret)
+                perror("set_tdp_level_for_cpu");
+        else
+                isst_display_result(cpu, outf, "perf-profile", "set_tdp_level",
+                                    ret);
+}
+
+static void set_tdp_level(void)
+{
+        if (cmd_help) {
+                fprintf(stderr, "Set Config TDP level\n");
+                fprintf(stderr,
+                        "\t Arguments: -l|--level : Specify tdp level\n");
+                exit(0);
+        }
+
+        if (tdp_level == 0xff) {
+                fprintf(outf, "Invalid command: specify tdp_level\n");
+                exit(1);
+        }
+        isst_ctdp_display_information_start(outf);
+        if (max_target_cpus)
+                for_each_online_target_cpu_in_set(set_tdp_level_for_cpu, NULL,
+                                                  NULL, NULL, NULL);
+        else
+                for_each_online_package_in_set(set_tdp_level_for_cpu, NULL,
+                                               NULL, NULL, NULL);
+        isst_ctdp_display_information_end(outf);
+}
+
+static void dump_pbf_config_for_cpu(int cpu, void *arg1, void *arg2, void *arg3,
+                                    void *arg4)
+{
+        struct isst_pbf_info pbf_info;
+        int ret;
+
+        ret = isst_get_pbf_info(cpu, tdp_level, &pbf_info);
+        if (ret) {
+                perror("isst_get_pbf_info");
+        } else {
+                isst_pbf_display_information(cpu, outf, tdp_level, &pbf_info);
+                isst_get_pbf_info_complete(&pbf_info);
+        }
+}
+
+static void dump_pbf_config(void)
+{
+        if (cmd_help) {
+                fprintf(stderr,
+                        "Print Intel(R) Speed Select Technology base frequency configuration for a TDP level\n");
+                fprintf(stderr,
+                        "\tArguments: -l|--level : Specify tdp level\n");
+                exit(0);
+        }
+
+        if (tdp_level == 0xff) {
+                fprintf(outf, "Invalid command: specify tdp_level\n");
+                exit(1);
+        }
+
+        isst_ctdp_display_information_start(outf);
+        if (max_target_cpus)
+                for_each_online_target_cpu_in_set(dump_pbf_config_for_cpu, NULL,
+                                                  NULL, NULL, NULL);
+        else
+                for_each_online_package_in_set(dump_pbf_config_for_cpu, NULL,
+                                               NULL, NULL, NULL);
+        isst_ctdp_display_information_end(outf);
+}
+
+static void set_pbf_for_cpu(int cpu, void *arg1, void *arg2, void *arg3,
+                            void *arg4)
+{
+        int ret;
+        int status = *(int *)arg4;
+
+        ret = isst_set_pbf_fact_status(cpu, 1, status);
+        if (ret) {
+                perror("isst_set_pbf");
+        } else {
+                if (status)
+                        isst_display_result(cpu, outf, "base-freq", "enable",
+                                            ret);
+                else
+                        isst_display_result(cpu, outf, "base-freq", "disable",
+                                            ret);
+        }
+}
+
+static void set_pbf_enable(void)
+{
+        int status = 1;
+
+        if (cmd_help) {
+                fprintf(stderr,
+                        "Enable Intel Speed Select Technology base frequency feature [No command arguments are required]\n");
+                exit(0);
+        }
+
+        isst_ctdp_display_information_start(outf);
+        if (max_target_cpus)
+                for_each_online_target_cpu_in_set(set_pbf_for_cpu, NULL, NULL,
+                                                  NULL, &status);
+        else
+                for_each_online_package_in_set(set_pbf_for_cpu, NULL, NULL,
+                                               NULL, &status);
+        isst_ctdp_display_information_end(outf);
+}
+
+static void set_pbf_disable(void)
+{
+        int status = 0;
+
+        if (cmd_help) {
+                fprintf(stderr,
+                        "Disable Intel Speed Select Technology base frequency feature [No command arguments are required]\n");
+                exit(0);
+        }
+
+        isst_ctdp_display_information_start(outf);
+        if (max_target_cpus)
+                for_each_online_target_cpu_in_set(set_pbf_for_cpu, NULL, NULL,
+                                                  NULL, &status);
+        else
+                for_each_online_package_in_set(set_pbf_for_cpu, NULL, NULL,
+                                               NULL, &status);
+        isst_ctdp_display_information_end(outf);
+}
+
+static void dump_fact_config_for_cpu(int cpu, void *arg1, void *arg2,
+                                     void *arg3, void *arg4)
+{
+        struct isst_fact_info fact_info;
+        int ret;
+
+        ret = isst_get_fact_info(cpu, tdp_level, &fact_info);
+        if (ret)
+                perror("isst_get_fact_bucket_info");
+        else
+                isst_fact_display_information(cpu, outf, tdp_level, fact_bucket,
+                                              fact_avx, &fact_info);
+}
+
+static void dump_fact_config(void)
+{
+        if (cmd_help) {
+                fprintf(stderr,
+                        "Print complete Intel Speed Select Technology turbo frequency configuration for a TDP level. Other arguments are optional.\n");
+                fprintf(stderr,
+                        "\tArguments: -l|--level : Specify tdp level\n");
+                fprintf(stderr,
+                        "\tArguments: -b|--bucket : Bucket index to dump\n");
+                fprintf(stderr,
+                        "\tArguments: -r|--trl-type : Specify trl type: sse|avx2|avx512\n");
+                exit(0);
+        }
+
+        if (tdp_level == 0xff) {
+                fprintf(outf, "Invalid command: specify tdp_level\n");
+                exit(1);
+        }
+
+        isst_ctdp_display_information_start(outf);
+        if (max_target_cpus)
+                for_each_online_target_cpu_in_set(dump_fact_config_for_cpu,
+                                                  NULL, NULL, NULL, NULL);
+        else
+                for_each_online_package_in_set(dump_fact_config_for_cpu, NULL,
+                                               NULL, NULL, NULL);
+        isst_ctdp_display_information_end(outf);
+}
+
+static void set_fact_for_cpu(int cpu, void *arg1, void *arg2, void *arg3,
+                             void *arg4)
+{
+        int ret;
+        int status = *(int *)arg4;
+
+        ret = isst_set_pbf_fact_status(cpu, 0, status);
+        if (ret)
+                perror("isst_set_fact");
+        else {
+                if (status) {
+                        struct isst_pkg_ctdp pkg_dev;
+
+                        ret = isst_get_ctdp_levels(cpu, &pkg_dev);
+                        if (ret) {
+                                isst_display_result(cpu, outf, "turbo-freq",
+                                                    "enable", ret);
+                                return;
+                        }
+                        ret = isst_set_trl(cpu, fact_trl);
+                        isst_display_result(cpu, outf, "turbo-freq", "enable",
+                                            ret);
+                } else {
+                        /* Since we modified TRL during Fact enable, restore it */
+                        isst_set_trl_from_current_tdp(cpu, fact_trl);
+                        isst_display_result(cpu, outf, "turbo-freq", "disable",
+                                            ret);
+                }
+        }
+}
+
+static void set_fact_enable(void)
+{
+        int status = 1;
+
+        if (cmd_help) {
+                fprintf(stderr,
+                        "Enable Intel Speed Select Technology Turbo frequency feature\n");
+                fprintf(stderr,
+                        "Optional: -t|--trl : Specify turbo ratio limit\n");
+                exit(0);
+        }
+
+        isst_ctdp_display_information_start(outf);
+        if (max_target_cpus)
+                for_each_online_target_cpu_in_set(set_fact_for_cpu, NULL, NULL,
+                                                  NULL, &status);
+        else
+                for_each_online_package_in_set(set_fact_for_cpu, NULL, NULL,
+                                               NULL, &status);
+        isst_ctdp_display_information_end(outf);
+}
+
+static void set_fact_disable(void)
+{
+        int status = 0;
+
+        if (cmd_help) {
+                fprintf(stderr,
+                        "Disable Intel Speed Select Technology turbo frequency feature\n");
+                fprintf(stderr,
+                        "Optional: -t|--trl : Specify turbo ratio limit\n");
+                exit(0);
+        }
+
+        isst_ctdp_display_information_start(outf);
+        if (max_target_cpus)
+                for_each_online_target_cpu_in_set(set_fact_for_cpu, NULL, NULL,
+                                                  NULL, &status);
+        else
+                for_each_online_package_in_set(set_fact_for_cpu, NULL, NULL,
+                                               NULL, &status);
+        isst_ctdp_display_information_end(outf);
+}
+
+static void enable_clos_qos_config(int cpu, void *arg1, void *arg2, void *arg3,
+                                   void *arg4)
+{
+        int ret;
+        int status = *(int *)arg4;
+
+        ret = isst_pm_qos_config(cpu, status, clos_priority_type);
+        if (ret) {
+                perror("isst_pm_qos_config");
+        } else {
+                if (status)
+                        isst_display_result(cpu, outf, "core-power", "enable",
+                                            ret);
+                else
+                        isst_display_result(cpu, outf, "core-power", "disable",
+                                            ret);
+        }
+}
+
+static void set_clos_enable(void)
+{
+        int status = 1;
+
+        if (cmd_help) {
+                fprintf(stderr, "Enable core-power for a package/die\n");
+                fprintf(stderr,
+                        "\tClos Enable: Specify priority type with [--priority|-p]\n");
+                fprintf(stderr, "\t\t 0: Proportional, 1: Ordered\n");
+                exit(0);
+        }
+
+        if (cpufreq_sysfs_present()) {
+                fprintf(stderr,
+                        "cpufreq subsystem and core-power enable will interfere with each other!\n");
+        }
+
+        isst_ctdp_display_information_start(outf);
+        if (max_target_cpus)
+                for_each_online_target_cpu_in_set(enable_clos_qos_config, NULL,
+                                                  NULL, NULL, &status);
+        else
+                for_each_online_package_in_set(enable_clos_qos_config, NULL,
+                                               NULL, NULL, &status);
+        isst_ctdp_display_information_end(outf);
+}
+
+static void set_clos_disable(void)
+{
+        int status = 0;
+
+        if (cmd_help) {
+                fprintf(stderr,
+                        "Disable core-power: [No command arguments are required]\n");
+                exit(0);
+        }
+
+        isst_ctdp_display_information_start(outf);
+        if (max_target_cpus)
+                for_each_online_target_cpu_in_set(enable_clos_qos_config, NULL,
+                                                  NULL, NULL, &status);
+        else
+                for_each_online_package_in_set(enable_clos_qos_config, NULL,
+                                               NULL, NULL, &status);
+        isst_ctdp_display_information_end(outf);
+}
+
+static void dump_clos_config_for_cpu(int cpu, void *arg1, void *arg2,
+                                     void *arg3, void *arg4)
+{
+        struct isst_clos_config clos_config;
+        int ret;
+
+        ret = isst_pm_get_clos(cpu, current_clos, &clos_config);
+        if (ret)
+                perror("isst_pm_get_clos");
+        else
+                isst_clos_display_information(cpu, outf, current_clos,
+                                              &clos_config);
+}
+
+static void dump_clos_config(void)
+{
+        if (cmd_help) {
+                fprintf(stderr,
+                        "Print Intel Speed Select Technology core power configuration\n");
+                fprintf(stderr,
+                        "\tArguments: [-c | --clos]: Specify clos id\n");
+                exit(0);
+        }
+        if (current_clos < 0 || current_clos > 3) {
+                fprintf(stderr, "Invalid clos id\n");
+                exit(0);
+        }
+
+        isst_ctdp_display_information_start(outf);
+        if (max_target_cpus)
+                for_each_online_target_cpu_in_set(dump_clos_config_for_cpu,
+                                                  NULL, NULL, NULL, NULL);
+        else
+                for_each_online_package_in_set(dump_clos_config_for_cpu, NULL,
+                                               NULL, NULL, NULL);
+        isst_ctdp_display_information_end(outf);
+}
+
+static void set_clos_config_for_cpu(int cpu, void *arg1, void *arg2, void *arg3,
+                                    void *arg4)
+{
+        struct isst_clos_config clos_config;
+        int ret;
+
+        clos_config.pkg_id = get_physical_package_id(cpu);
+        clos_config.die_id = get_physical_die_id(cpu);
+
+        clos_config.epp = clos_epp;
+        clos_config.clos_prop_prio = clos_prop_prio;
+        clos_config.clos_min = clos_min;
+        clos_config.clos_max = clos_max;
+        clos_config.clos_desired = clos_desired;
+        ret = isst_set_clos(cpu, current_clos, &clos_config);
+        if (ret)
+                perror("isst_set_clos");
+        else
+                isst_display_result(cpu, outf, "core-power", "config", ret);
+}
+
+static void set_clos_config(void)
+{
+        if (cmd_help) {
+                fprintf(stderr,
+                        "Set core-power configuration for one of the four clos ids\n");
+                fprintf(stderr,
+                        "\tSpecify targeted clos id with [--clos|-c]\n");
+                fprintf(stderr, "\tSpecify clos EPP with [--epp|-e]\n");
+                fprintf(stderr,
+                        "\tSpecify clos Proportional Priority [--weight|-w]\n");
+                fprintf(stderr, "\tSpecify clos min with [--min|-n]\n");
+                fprintf(stderr, "\tSpecify clos max with [--max|-m]\n");
+                fprintf(stderr, "\tSpecify clos desired with [--desired|-d]\n");
+                exit(0);
+        }
+
+        if (current_clos < 0 || current_clos > 3) {
+                fprintf(stderr, "Invalid clos id\n");
+                exit(0);
+        }
+        if (clos_epp < 0 || clos_epp > 0x0F) {
+                fprintf(stderr, "clos epp is not specified, default: 0\n");
+                clos_epp = 0;
+        }
+        if (clos_prop_prio < 0 || clos_prop_prio > 0x0F) {
+                fprintf(stderr,
+                        "clos frequency weight is not specified, default: 0\n");
+                clos_prop_prio = 0;
+        }
+        if (clos_min < 0) {
+                fprintf(stderr, "clos min is not specified, default: 0\n");
+                clos_min = 0;
+        }
+        if (clos_max < 0) {
+                fprintf(stderr, "clos max is not specified, default: 0xff\n");
+                clos_max = 0xff;
+        }
+        if (clos_desired < 0) {
+                fprintf(stderr, "clos desired is not specified, default: 0\n");
+                clos_desired = 0x00;
+        }
+
+        isst_ctdp_display_information_start(outf);
+        if (max_target_cpus)
+                for_each_online_target_cpu_in_set(set_clos_config_for_cpu, NULL,
+                                                  NULL, NULL, NULL);
+        else
+                for_each_online_package_in_set(set_clos_config_for_cpu, NULL,
+                                               NULL, NULL, NULL);
+        isst_ctdp_display_information_end(outf);
+}
+
+static void set_clos_assoc_for_cpu(int cpu, void *arg1, void *arg2, void *arg3,
+                                   void *arg4)
+{
+        int ret;
+
+        ret = isst_clos_associate(cpu, current_clos);
+        if (ret)
+                perror("isst_clos_associate");
+        else
+                isst_display_result(cpu, outf, "core-power", "assoc", ret);
+}
+
+static void set_clos_assoc(void)
+{
+        if (cmd_help) {
+                fprintf(stderr, "Associate a clos id to a CPU\n");
+                fprintf(stderr,
+                        "\tSpecify targeted clos id with [--clos|-c]\n");
+                exit(0);
+        }
+
+        if (current_clos < 0 || current_clos > 3) {
+                fprintf(stderr, "Invalid clos id\n");
+                exit(0);
+        }
+        if (max_target_cpus)
+                for_each_online_target_cpu_in_set(set_clos_assoc_for_cpu, NULL,
+                                                  NULL, NULL, NULL);
+        else {
+                fprintf(stderr,
+                        "Invalid target cpu. Specify with [-c|--cpu]\n");
+        }
+}
+
+static void get_clos_assoc_for_cpu(int cpu, void *arg1, void *arg2, void *arg3,
+                                   void *arg4)
+{
+        int clos, ret;
+
+        ret = isst_clos_get_assoc_status(cpu, &clos);
+        if (ret)
+                perror("isst_clos_get_assoc_status");
+        else
+                isst_display_result(cpu, outf, "core-power", "get-assoc", clos);
+}
+
+static void get_clos_assoc(void)
+{
+        if (cmd_help) {
+                fprintf(stderr, "Get associate clos id to a CPU\n");
+                fprintf(stderr, "\tSpecify targeted cpu id with [--cpu|-c]\n");
+                exit(0);
+        }
+        if (max_target_cpus)
+                for_each_online_target_cpu_in_set(get_clos_assoc_for_cpu, NULL,
+                                                  NULL, NULL, NULL);
+        else {
+                fprintf(stderr,
+                        "Invalid target cpu. Specify with [-c|--cpu]\n");
+        }
+}
+
+static struct process_cmd_struct isst_cmds[] = {
+        { "perf-profile", "get-lock-status", get_tdp_locked },
+        { "perf-profile", "get-config-levels", get_tdp_levels },
+        { "perf-profile", "get-config-version", get_tdp_version },
+        { "perf-profile", "get-config-enabled", get_tdp_enabled },
+        { "perf-profile", "get-config-current-level", get_tdp_current_level },
+        { "perf-profile", "set-config-level", set_tdp_level },
+        { "perf-profile", "info", dump_isst_config },
+        { "base-freq", "info", dump_pbf_config },
+        { "base-freq", "enable", set_pbf_enable },
+        { "base-freq", "disable", set_pbf_disable },
+        { "turbo-freq", "info", dump_fact_config },
+        { "turbo-freq", "enable", set_fact_enable },
+        { "turbo-freq", "disable", set_fact_disable },
+        { "core-power", "info", dump_clos_config },
+        { "core-power", "enable", set_clos_enable },
+        { "core-power", "disable", set_clos_disable },
+        { "core-power", "config", set_clos_config },
+        { "core-power", "assoc", set_clos_assoc },
+        { "core-power", "get-assoc", get_clos_assoc },
+        { NULL, NULL, NULL }
+};
+
+/*
+ * parse cpuset with following syntax
+ * 1,2,4..6,8-10 and set bits in cpu_subset
+ */
+void parse_cpu_command(char *optarg)
+{
+        unsigned int start, end;
+        char *next;
+
+        next = optarg;
+
+        while (next && *next) {
+                if (*next == '-') /* no negative cpu numbers */
+                        goto error;
+
+                start = strtoul(next, &next, 10);
+
+                if (max_target_cpus < MAX_CPUS_IN_ONE_REQ)
+                        target_cpus[max_target_cpus++] = start;
+
+                if (*next == '\0')
+                        break;
+
+                if (*next == ',') {
+                        next += 1;
+                        continue;
+                }
+
+                if (*next == '-') {
+                        next += 1; /* start range */
+                } else if (*next == '.') {
+                        next += 1;
+                        if (*next == '.')
+                                next += 1; /* start range */
+                        else
+                                goto error;
+                }
+
+                end = strtoul(next, &next, 10);
+                if (end <= start)
+                        goto error;
+
+                while (++start <= end) {
+                        if (max_target_cpus < MAX_CPUS_IN_ONE_REQ)
+                                target_cpus[max_target_cpus++] = start;
+                }
+
+                if (*next == ',')
+                        next += 1;
+                else if (*next != '\0')
+                        goto error;
+        }
+
+#ifdef DEBUG
+        {
+                int i;
+
+                for (i = 0; i < max_target_cpus; ++i)
+                        printf("cpu [%d] in arg\n", target_cpus[i]);
+        }
+#endif
+        return;
+
+error:
+        fprintf(stderr, "\"--cpu %s\" malformed\n", optarg);
+        exit(-1);
+}
+
+static void parse_cmd_args(int argc, int start, char **argv)
+{
+        int opt;
+        int option_index;
+
+        static struct option long_options[] = {
+                { "bucket", required_argument, 0, 'b' },
+                { "level", required_argument, 0, 'l' },
+                { "trl-type", required_argument, 0, 'r' },
+                { "trl", required_argument, 0, 't' },
+                { "help", no_argument, 0, 'h' },
+                { "clos", required_argument, 0, 'c' },
+                { "desired", required_argument, 0, 'd' },
+                { "epp", required_argument, 0, 'e' },
+                { "min", required_argument, 0, 'n' },
+                { "max", required_argument, 0, 'm' },
+                { "priority", required_argument, 0, 'p' },
+                { "weight", required_argument, 0, 'w' },
+                { 0, 0, 0, 0 }
+        };
+
+        option_index = start;
+
+        optind = start + 1;
+        while ((opt = getopt_long(argc, argv, "b:l:t:c:d:e:n:m:p:w:h",
+                                  long_options, &option_index)) != -1) {
+                switch (opt) {
+                case 'b':
+                        fact_bucket = atoi(optarg);
+                        break;
+                case 'h':
+                        cmd_help = 1;
+                        break;
+                case 'l':
+                        tdp_level = atoi(optarg);
+                        break;
+                case 't':
+                        sscanf(optarg, "0x%llx", &fact_trl);
+                        break;
+                case 'r':
+                        if (!strncmp(optarg, "sse", 3)) {
+                                fact_avx = 0x01;
+                        } else if (!strncmp(optarg, "avx2", 4)) {
+                                fact_avx = 0x02;
+                        } else if (!strncmp(optarg, "avx512", 4)) {
+                                fact_avx = 0x04;
+                        } else {
+                                fprintf(outf, "Invalid sse,avx options\n");
+                                exit(1);
+                        }
+                        break;
+                /* CLOS related */
+                case 'c':
+                        current_clos = atoi(optarg);
+                        printf("clos %d\n", current_clos);
+                        break;
+                case 'd':
+                        clos_desired = atoi(optarg);
+                        break;
+                case 'e':
+                        clos_epp = atoi(optarg);
+                        break;
+                case 'n':
+                        clos_min = atoi(optarg);
+                        break;
+                case 'm':
+                        clos_max = atoi(optarg);
+                        break;
+                case 'p':
+                        clos_priority_type = atoi(optarg);
+                        break;
+                case 'w':
+                        clos_prop_prio = atoi(optarg);
+                        break;
+                default:
+                        printf("no match\n");
+                }
+        }
+}
+
+static void isst_help(void)
+{
+        printf("perf-profile:\tAn architectural mechanism that allows multiple optimized \n\
+                performance profiles per system via static and/or dynamic\n\
+                adjustment of core count, workload, Tjmax, and\n\
+                TDP, etc.\n");
+        printf("\nCommands : For feature=perf-profile\n");
+        printf("\tinfo\n");
+        printf("\tget-lock-status\n");
+        printf("\tget-config-levels\n");
+        printf("\tget-config-version\n");
+        printf("\tget-config-enabled\n");
+        printf("\tget-config-current-level\n");
+        printf("\tset-config-level\n");
+}
+
+static void pbf_help(void)
+{
+        printf("base-freq:\tEnables users to increase guaranteed base frequency\n\
+                on certain cores (high priority cores) in exchange for lower\n\
+                base frequency on remaining cores (low priority cores).\n");
+        printf("\tcommand : info\n");
+        printf("\tcommand : enable\n");
+        printf("\tcommand : disable\n");
+}
+
+static void fact_help(void)
+{
+        printf("turbo-freq:\tEnables the ability to set different turbo ratio\n\
+                limits to cores based on priority.\n");
+        printf("\nCommand: For feature=turbo-freq\n");
+        printf("\tcommand : info\n");
+        printf("\tcommand : enable\n");
+        printf("\tcommand : disable\n");
+}
+
+static void core_power_help(void)
+{
+        printf("core-power:\tInterface that allows user to define per core/tile\n\
+                priority.\n");
+        printf("\nCommands : For feature=core-power\n");
+        printf("\tinfo\n");
+        printf("\tenable\n");
+        printf("\tdisable\n");
+        printf("\tconfig\n");
+        printf("\tassoc\n");
+        printf("\tget-assoc\n");
+}
+
+struct process_cmd_help_struct {
+        char *feature;
+        void (*process_fn)(void);
+};
+
+static struct process_cmd_help_struct isst_help_cmds[] = {
+        { "perf-profile", isst_help },
+        { "base-freq", pbf_help },
+        { "turbo-freq", fact_help },
+        { "core-power", core_power_help },
+        { NULL, NULL }
+};
+
+void process_command(int argc, char **argv)
+{
+        int i = 0, matched = 0;
+        char *feature = argv[optind];
+        char *cmd = argv[optind + 1];
+
+        if (!feature || !cmd)
+                return;
+
+        debug_printf("feature name [%s] command [%s]\n", feature, cmd);
+        if (!strcmp(cmd, "-h") || !strcmp(cmd, "--help")) {
+                while (isst_help_cmds[i].feature) {
+                        if (!strcmp(isst_help_cmds[i].feature, feature)) {
+                                isst_help_cmds[i].process_fn();
+                                exit(0);
+                        }
+                        ++i;
+                }
+        }
+
+        create_cpu_map();
+
+        i = 0;
+        while (isst_cmds[i].feature) {
+                if (!strcmp(isst_cmds[i].feature, feature) &&
+                    !strcmp(isst_cmds[i].command, cmd)) {
+                        parse_cmd_args(argc, optind + 1, argv);
+                        isst_cmds[i].process_fn();
+                        matched = 1;
+                        break;
+                }
+                ++i;
+        }
+
+        if (!matched)
+                fprintf(stderr, "Invalid command\n");
+}
+
+static void usage(void)
+{
+        printf("Intel(R) Speed Select Technology\n");
+        printf("\nUsage:\n");
+        printf("intel-speed-select [OPTIONS] FEATURE COMMAND COMMAND_ARGUMENTS\n");
+        printf("\nUse this tool to enumerate and control the Intel Speed Select Technology features,\n");
+        printf("\nFEATURE : [perf-profile|base-freq|turbo-freq|core-power]\n");
+        printf("\nFor help on each feature, use --h|--help\n");
+        printf("\tFor example:  intel-speed-select perf-profile -h\n");
+
+        printf("\nFor additional help on each command for a feature, use --h|--help\n");
+        printf("\tFor example:  intel-speed-select perf-profile get-lock-status -h\n");
+        printf("\t\t This will print help for the command \"get-lock-status\" for the feature \"perf-profile\"\n");
+
+        printf("\nOPTIONS\n");
+        printf("\t[-c|--cpu] : logical cpu number\n");
+        printf("\t\tDefault: Die scoped for all dies in the system with multiple dies/package\n");
+        printf("\t\t\t Or Package scoped for all Packages when each package contains one die\n");
+        printf("\t[-d|--debug] : Debug mode\n");
+        printf("\t[-h|--help] : Print help\n");
+        printf("\t[-i|--info] : Print platform information\n");
+        printf("\t[-o|--out] : Output file\n");
+        printf("\t\t\tDefault : stderr\n");
+        printf("\t[-f|--format] : output format [json|text]. Default: text\n");
+        printf("\t[-v|--version] : Print version\n");
+
+        printf("\nResult format\n");
+        printf("\tResult display uses a common format for each command:\n");
+        printf("\tResults are formatted in text/JSON with\n");
+        printf("\t\tPackage, Die, CPU, and command specific results.\n");
+        printf("\t\t\tFor Set commands, status is 0 for success and rest for failures\n");
+        exit(1);
+}
+
+static void print_version(void)
+{
+        fprintf(outf, "Version %s\n", version_str);
+        fprintf(outf, "Build date %s time %s\n", __DATE__, __TIME__);
+        exit(0);
+}
+
+static void cmdline(int argc, char **argv)
+{
+        int opt;
+        int option_index = 0;
+
+        static struct option long_options[] = {
+                { "cpu", required_argument, 0, 'c' },
+                { "debug", no_argument, 0, 'd' },
+                { "format", required_argument, 0, 'f' },
+                { "help", no_argument, 0, 'h' },
+                { "info", no_argument, 0, 'i' },
+                { "out", required_argument, 0, 'o' },
+                { "version", no_argument, 0, 'v' },
+                { 0, 0, 0, 0 }
+        };
+
+        progname = argv[0];
+        while ((opt = getopt_long_only(argc, argv, "+c:df:hio:v", long_options,
+                                       &option_index)) != -1) {
+                switch (opt) {
+                case 'c':
+                        parse_cpu_command(optarg);
+                        break;
+                case 'd':
+                        debug_flag = 1;
+                        printf("Debug Mode ON\n");
+                        break;
+                case 'f':
+                        if (!strncmp(optarg, "json", 4))
+                                out_format_json = 1;
+                        break;
+                case 'h':
+                        usage();
+                        break;
+                case 'i':
+                        isst_print_platform_information();
+                        break;
+                case 'o':
+                        if (outf)
+                                fclose(outf);
+                        outf = fopen_or_exit(optarg, "w");
+                        break;
+                case 'v':
+                        print_version();
+                        break;
+                default:
+                        usage();
+                }
+        }
+
+        if (geteuid() != 0) {
+                fprintf(stderr, "Must run as root\n");
+                exit(0);
+        }
+
+        if (optind > (argc - 2)) {
+                fprintf(stderr, "Feature name and|or command not specified\n");
+                exit(0);
+        }
+        update_cpu_model();
+        printf("Intel(R) Speed Select Technology\n");
+        printf("Executing on CPU model:%d[0x%x]\n", cpu_model, cpu_model);
+        set_max_cpu_num();
+        set_cpu_present_cpu_mask();
+        set_cpu_target_cpu_mask();
+        isst_fill_platform_info();
+        if (isst_platform_info.api_version > supported_api_ver) {
+                printf("Incompatible API versions; Upgrade of tool is required\n");
+                exit(0);
+        }
+
+        process_command(argc, argv);
+}
+
+int main(int argc, char **argv)
+{
+        outf = stderr;
+        cmdline(argc, argv);
+        return 0;
+}
diff --git a/tools/power/x86/intel-speed-select/isst-core.c b/tools/power/x86/intel-speed-select/isst-core.c
new file mode 100644
index 000000000000..8de4ac39a008
--- /dev/null
+++ b/tools/power/x86/intel-speed-select/isst-core.c
@@ -0,0 +1,721 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel Speed Select -- Enumerate and control features
+ * Copyright (c) 2019 Intel Corporation.
+ */
+
+#include "isst.h"
+
+int isst_get_ctdp_levels(int cpu, struct isst_pkg_ctdp *pkg_dev)
+{
+        unsigned int resp;
+        int ret;
+
+        ret = isst_send_mbox_command(cpu, CONFIG_TDP,
+                                     CONFIG_TDP_GET_LEVELS_INFO, 0, 0, &resp);
+        if (ret)
+                return ret;
+
+        debug_printf("cpu:%d CONFIG_TDP_GET_LEVELS_INFO resp:%x\n", cpu, resp);
+
+        pkg_dev->version = resp & 0xff;
+        pkg_dev->levels = (resp >> 8) & 0xff;
+        pkg_dev->current_level = (resp >> 16) & 0xff;
+        pkg_dev->locked = !!(resp & BIT(24));
+        pkg_dev->enabled = !!(resp & BIT(31));
+
+        return 0;
+}
+
+int isst_get_ctdp_control(int cpu, int config_index,
+                          struct isst_pkg_ctdp_level_info *ctdp_level)
+{
+        unsigned int resp;
+        int ret;
+
+        ret = isst_send_mbox_command(cpu, CONFIG_TDP,
+                                     CONFIG_TDP_GET_TDP_CONTROL, 0,
+                                     config_index, &resp);
+        if (ret)
+                return ret;
+
+        ctdp_level->fact_support = resp & BIT(0);
+        ctdp_level->pbf_support = !!(resp & BIT(1));
+        ctdp_level->fact_enabled = !!(resp & BIT(16));
+        ctdp_level->pbf_enabled = !!(resp & BIT(17));
+
+        debug_printf(
+                "cpu:%d CONFIG_TDP_GET_TDP_CONTROL resp:%x fact_support:%d pbf_support: %d fact_enabled:%d pbf_enabled:%d\n",
+                cpu, resp, ctdp_level->fact_support, ctdp_level->pbf_support,
+                ctdp_level->fact_enabled, ctdp_level->pbf_enabled);
+
+        return 0;
+}
+
+int isst_get_tdp_info(int cpu, int config_index,
+                      struct isst_pkg_ctdp_level_info *ctdp_level)
+{
+        unsigned int resp;
+        int ret;
+
+        ret = isst_send_mbox_command(cpu, CONFIG_TDP, CONFIG_TDP_GET_TDP_INFO,
+                                     0, config_index, &resp);
+        if (ret)
+                return ret;
+
+        ctdp_level->pkg_tdp = resp & GENMASK(14, 0);
+        ctdp_level->tdp_ratio = (resp & GENMASK(23, 16)) >> 16;
+
+        debug_printf(
+                "cpu:%d ctdp:%d CONFIG_TDP_GET_TDP_INFO resp:%x tdp_ratio:%d pkg_tdp:%d\n",
+                cpu, config_index, resp, ctdp_level->tdp_ratio,
+                ctdp_level->pkg_tdp);
+        return 0;
+}
+
+int isst_get_pwr_info(int cpu, int config_index,
+                      struct isst_pkg_ctdp_level_info *ctdp_level)
+{
+        unsigned int resp;
+        int ret;
+
+        ret = isst_send_mbox_command(cpu, CONFIG_TDP, CONFIG_TDP_GET_PWR_INFO,
+                                     0, config_index, &resp);
+        if (ret)
+                return ret;
+
+        ctdp_level->pkg_max_power = resp & GENMASK(14, 0);
+        ctdp_level->pkg_min_power = (resp & GENMASK(30, 16)) >> 16;
+
+        debug_printf(
+                "cpu:%d ctdp:%d CONFIG_TDP_GET_PWR_INFO resp:%x pkg_max_power:%d pkg_min_power:%d\n",
+                cpu, config_index, resp, ctdp_level->pkg_max_power,
+                ctdp_level->pkg_min_power);
+
+        return 0;
+}
+
+int isst_get_tjmax_info(int cpu, int config_index,
+                        struct isst_pkg_ctdp_level_info *ctdp_level)
+{
+        unsigned int resp;
+        int ret;
+
+        ret = isst_send_mbox_command(cpu, CONFIG_TDP, CONFIG_TDP_GET_TJMAX_INFO,
+                                     0, config_index, &resp);
+        if (ret)
+                return ret;
+
+        ctdp_level->t_proc_hot = resp & GENMASK(7, 0);
+
+        debug_printf(
+                "cpu:%d ctdp:%d CONFIG_TDP_GET_TJMAX_INFO resp:%x t_proc_hot:%d\n",
+                cpu, config_index, resp, ctdp_level->t_proc_hot);
+
+        return 0;
+}
+
+int isst_get_coremask_info(int cpu, int config_index,
+                           struct isst_pkg_ctdp_level_info *ctdp_level)
+{
+        unsigned int resp;
+        int i, ret;
+
+        ctdp_level->cpu_count = 0;
+        for (i = 0; i < 2; ++i) {
+                unsigned long long mask;
+                int cpu_count = 0;
+
+                ret = isst_send_mbox_command(cpu, CONFIG_TDP,
+                                             CONFIG_TDP_GET_CORE_MASK, 0,
+                                             (i << 8) | config_index, &resp);
+                if (ret)
+                        return ret;
+
+                debug_printf(
+                        "cpu:%d ctdp:%d mask:%d CONFIG_TDP_GET_CORE_MASK resp:%x\n",
+                        cpu, config_index, i, resp);
+
+                mask = (unsigned long long)resp << (32 * i);
+                set_cpu_mask_from_punit_coremask(cpu, mask,
+                                                 ctdp_level->core_cpumask_size,
+                                                 ctdp_level->core_cpumask,
+                                                 &cpu_count);
+                ctdp_level->cpu_count += cpu_count;
+                debug_printf("cpu:%d ctdp:%d mask:%d cpu count:%d\n", cpu,
+                             config_index, i, ctdp_level->cpu_count);
+        }
+
+        return 0;
+}
+
+int isst_get_get_trl(int cpu, int level, int avx_level, int *trl)
+{
+        unsigned int req, resp;
+        int ret;
+
+        req = level | (avx_level << 16);
+        ret = isst_send_mbox_command(cpu, CONFIG_TDP,
+                                     CONFIG_TDP_GET_TURBO_LIMIT_RATIOS, 0, req,
+                                     &resp);
+        if (ret)
+                return ret;
+
+        debug_printf(
+                "cpu:%d CONFIG_TDP_GET_TURBO_LIMIT_RATIOS req:%x resp:%x\n",
+                cpu, req, resp);
+
+        trl[0] = resp & GENMASK(7, 0);
+        trl[1] = (resp & GENMASK(15, 8)) >> 8;
+        trl[2] = (resp & GENMASK(23, 16)) >> 16;
+        trl[3] = (resp & GENMASK(31, 24)) >> 24;
+
+        req = level | BIT(8) | (avx_level << 16);
+        ret = isst_send_mbox_command(cpu, CONFIG_TDP,
+                                     CONFIG_TDP_GET_TURBO_LIMIT_RATIOS, 0, req,
+                                     &resp);
+        if (ret)
+                return ret;
+
+        debug_printf("cpu:%d CONFIG_TDP_GET_TURBO_LIMIT req:%x resp:%x\n", cpu,
+                     req, resp);
+
+        trl[4] = resp & GENMASK(7, 0);
+        trl[5] = (resp & GENMASK(15, 8)) >> 8;
+        trl[6] = (resp & GENMASK(23, 16)) >> 16;
+        trl[7] = (resp & GENMASK(31, 24)) >> 24;
+
+        return 0;
+}
+
+int isst_set_tdp_level_msr(int cpu, int tdp_level)
+{
+        int ret;
+
+        debug_printf("cpu: tdp_level via MSR %d\n", cpu, tdp_level);
+
+        if (isst_get_config_tdp_lock_status(cpu)) {
+                debug_printf("cpu: tdp_locked %d\n", cpu);
+                return -1;
+        }
+
+        if (tdp_level > 2)
+                return -1; /* invalid value */
+
+        ret = isst_send_msr_command(cpu, 0x64b, 1,
+                                    (unsigned long long *)&tdp_level);
+        if (ret)
+                return ret;
+
+        debug_printf("cpu: tdp_level via MSR successful %d\n", cpu, tdp_level);
+
+        return 0;
+}
+
+int isst_set_tdp_level(int cpu, int tdp_level)
+{
+        unsigned int resp;
+        int ret;
+
+        ret = isst_send_mbox_command(cpu, CONFIG_TDP, CONFIG_TDP_SET_LEVEL, 0,
+                                     tdp_level, &resp);
+        if (ret)
+                return isst_set_tdp_level_msr(cpu, tdp_level);
+
+        return 0;
+}
+
+int isst_get_pbf_info(int cpu, int level, struct isst_pbf_info *pbf_info)
+{
+        unsigned int req, resp;
+        int i, ret;
+
+        pbf_info->core_cpumask_size = alloc_cpu_set(&pbf_info->core_cpumask);
+
+        for (i = 0; i < 2; ++i) {
+                unsigned long long mask;
+                int count;
+
+                ret = isst_send_mbox_command(cpu, CONFIG_TDP,
+                                             CONFIG_TDP_PBF_GET_CORE_MASK_INFO,
+                                             0, (i << 8) | level, &resp);
+                if (ret)
+                        return ret;
+
+                debug_printf(
+                        "cpu:%d CONFIG_TDP_PBF_GET_CORE_MASK_INFO resp:%x\n",
+                        cpu, resp);
+
+                mask = (unsigned long long)resp << (32 * i);
+                set_cpu_mask_from_punit_coremask(cpu, mask,
+                                                 pbf_info->core_cpumask_size,
+                                                 pbf_info->core_cpumask,
+                                                 &count);
+        }
+
+        req = level;
+        ret = isst_send_mbox_command(cpu, CONFIG_TDP,
+                                     CONFIG_TDP_PBF_GET_P1HI_P1LO_INFO, 0, req,
+                                     &resp);
+        if (ret)
+                return ret;
+
+        debug_printf("cpu:%d CONFIG_TDP_PBF_GET_P1HI_P1LO_INFO resp:%x\n", cpu,
+                     resp);
+
+        pbf_info->p1_low = resp & 0xff;
+        pbf_info->p1_high = (resp & GENMASK(15, 8)) >> 8;
+
+        req = level;
+        ret = isst_send_mbox_command(
+                cpu, CONFIG_TDP, CONFIG_TDP_PBF_GET_TDP_INFO, 0, req, &resp);
+        if (ret)
+                return ret;
+
+        debug_printf("cpu:%d CONFIG_TDP_PBF_GET_TDP_INFO resp:%x\n", cpu, resp);
+
+        pbf_info->tdp = resp & 0xffff;
+
+        req = level;
+        ret = isst_send_mbox_command(
+                cpu, CONFIG_TDP, CONFIG_TDP_PBF_GET_TJ_MAX_INFO, 0, req, &resp);
+        if (ret)
+                return ret;
+
+        debug_printf("cpu:%d CONFIG_TDP_PBF_GET_TJ_MAX_INFO resp:%x\n", cpu,
+                     resp);
+        pbf_info->t_control = (resp >> 8) & 0xff;
+        pbf_info->t_prochot = resp & 0xff;
+
+        return 0;
+}
+
+void isst_get_pbf_info_complete(struct isst_pbf_info *pbf_info)
+{
+        free_cpu_set(pbf_info->core_cpumask);
+}
+
+int isst_set_pbf_fact_status(int cpu, int pbf, int enable)
+{
+        struct isst_pkg_ctdp pkg_dev;
+        struct isst_pkg_ctdp_level_info ctdp_level;
+        int current_level;
+        unsigned int req = 0, resp;
+        int ret;
+
+        ret = isst_get_ctdp_levels(cpu, &pkg_dev);
+        if (ret)
+                return ret;
+
+        current_level = pkg_dev.current_level;
+
+        ret = isst_get_ctdp_control(cpu, current_level, &ctdp_level);
+        if (ret)
+                return ret;
+
+        if (pbf) {
+                if (ctdp_level.fact_enabled)
+                        req = BIT(16);
+
+                if (enable)
+                        req |= BIT(17);
+                else
+                        req &= ~BIT(17);
+        } else {
+                if (ctdp_level.pbf_enabled)
+                        req = BIT(17);
+
+                if (enable)
+                        req |= BIT(16);
+                else
+                        req &= ~BIT(16);
+        }
+
+        ret = isst_send_mbox_command(cpu, CONFIG_TDP,
+                                     CONFIG_TDP_SET_TDP_CONTROL, 0, req, &resp);
+        if (ret)
+                return ret;
+
+        debug_printf("cpu:%d CONFIG_TDP_SET_TDP_CONTROL pbf/fact:%d req:%x\n",
+                     cpu, pbf, req);
+
+        return 0;
+}
+
+int isst_get_fact_bucket_info(int cpu, int level,
+                              struct isst_fact_bucket_info *bucket_info)
+{
+        unsigned int resp;
+        int i, k, ret;
+
+        for (i = 0; i < 2; ++i) {
+                int j;
+
+                ret = isst_send_mbox_command(
+                        cpu, CONFIG_TDP,
+                        CONFIG_TDP_GET_FACT_HP_TURBO_LIMIT_NUMCORES, 0,
+                        (i << 8) | level, &resp);
+                if (ret)
+                        return ret;
+
+                debug_printf(
+                        "cpu:%d CONFIG_TDP_GET_FACT_HP_TURBO_LIMIT_NUMCORES index:%d level:%d resp:%x\n",
+                        cpu, i, level, resp);
+
+                for (j = 0; j < 4; ++j) {
+                        bucket_info[j + (i * 4)].high_priority_cores_count =
+                                (resp >> (j * 8)) & 0xff;
+                }
+        }
+
+        for (k = 0; k < 3; ++k) {
+                for (i = 0; i < 2; ++i) {
+                        int j;
+
+                        ret = isst_send_mbox_command(
+                                cpu, CONFIG_TDP,
+                                CONFIG_TDP_GET_FACT_HP_TURBO_LIMIT_RATIOS, 0,
+                                (k << 16) | (i << 8) | level, &resp);
+                        if (ret)
+                                return ret;
+
+                        debug_printf(
+                                "cpu:%d CONFIG_TDP_GET_FACT_HP_TURBO_LIMIT_RATIOS index:%d level:%d avx:%d resp:%x\n",
+                                cpu, i, level, k, resp);
+
+                        for (j = 0; j < 4; ++j) {
+                                switch (k) {
+                                case 0:
+                                        bucket_info[j + (i * 4)].sse_trl =
+                                                (resp >> (j * 8)) & 0xff;
+                                        break;
+                                case 1:
+                                        bucket_info[j + (i * 4)].avx_trl =
+                                                (resp >> (j * 8)) & 0xff;
+                                        break;
+                                case 2:
+                                        bucket_info[j + (i * 4)].avx512_trl =
+                                                (resp >> (j * 8)) & 0xff;
+                                        break;
+                                default:
+                                        break;
+                                }
+                        }
+                }
+        }
+
+        return 0;
+}
+
+int isst_get_fact_info(int cpu, int level, struct isst_fact_info *fact_info)
+{
+        unsigned int resp;
+        int ret;
+
+        ret = isst_send_mbox_command(cpu, CONFIG_TDP,
+                                     CONFIG_TDP_GET_FACT_LP_CLIPPING_RATIO, 0,
+                                     level, &resp);
+        if (ret)
+                return ret;
+
+        debug_printf("cpu:%d CONFIG_TDP_GET_FACT_LP_CLIPPING_RATIO resp:%x\n",
+                     cpu, resp);
+
+        fact_info->lp_clipping_ratio_license_sse = resp & 0xff;
+        fact_info->lp_clipping_ratio_license_avx2 = (resp >> 8) & 0xff;
+        fact_info->lp_clipping_ratio_license_avx512 = (resp >> 16) & 0xff;
+
+        ret = isst_get_fact_bucket_info(cpu, level, fact_info->bucket_info);
+
+        return ret;
+}
+
+int isst_set_trl(int cpu, unsigned long long trl)
+{
+        int ret;
+
+        if (!trl)
+                trl = 0xFFFFFFFFFFFFFFFFULL;
+
+        ret = isst_send_msr_command(cpu, 0x1AD, 1, &trl);
+        if (ret)
+                return ret;
+
+        return 0;
+}
+
+int isst_set_trl_from_current_tdp(int cpu, unsigned long long trl)
+{
+        unsigned long long msr_trl;
+        int ret;
+
+        if (trl) {
+                msr_trl = trl;
+        } else {
+                struct isst_pkg_ctdp pkg_dev;
+                int trl[8];
+                int i;
+
+                ret = isst_get_ctdp_levels(cpu, &pkg_dev);
+                if (ret)
+                        return ret;
+
+                ret = isst_get_get_trl(cpu, pkg_dev.current_level, 0, trl);
+                if (ret)
+                        return ret;
+
+                msr_trl = 0;
+                for (i = 0; i < 8; ++i) {
+                        unsigned long long _trl = trl[i];
+
+                        msr_trl |= (_trl << (i * 8));
+                }
+        }
+        ret = isst_send_msr_command(cpu, 0x1AD, 1, &msr_trl);
+        if (ret)
+                return ret;
+
+        return 0;
+}
+
+/* Return 1 if locked */
+int isst_get_config_tdp_lock_status(int cpu)
+{
+        unsigned long long tdp_control = 0;
+        int ret;
+
+        ret = isst_send_msr_command(cpu, 0x64b, 0, &tdp_control);
+        if (ret)
+                return ret;
+
+        ret = !!(tdp_control & BIT(31));
+
+        return ret;
+}
+
+void isst_get_process_ctdp_complete(int cpu, struct isst_pkg_ctdp *pkg_dev)
+{
+        int i;
+
+        if (!pkg_dev->processed)
+                return;
+
+        for (i = 0; i < pkg_dev->levels; ++i) {
+                struct isst_pkg_ctdp_level_info *ctdp_level;
+
+                ctdp_level = &pkg_dev->ctdp_level[i];
+                if (ctdp_level->pbf_support)
+                        free_cpu_set(ctdp_level->pbf_info.core_cpumask);
+                free_cpu_set(ctdp_level->core_cpumask);
+        }
+}
+
+int isst_get_process_ctdp(int cpu, int tdp_level, struct isst_pkg_ctdp *pkg_dev)
+{
+        int i, ret;
+
+        if (pkg_dev->processed)
+                return 0;
+
+        ret = isst_get_ctdp_levels(cpu, pkg_dev);
+        if (ret)
+                return ret;
+
+        debug_printf("cpu: %d ctdp enable:%d current level: %d levels:%d\n",
+                     cpu, pkg_dev->enabled, pkg_dev->current_level,
+                     pkg_dev->levels);
+
+        for (i = 0; i <= pkg_dev->levels; ++i) {
+                struct isst_pkg_ctdp_level_info *ctdp_level;
+
+                if (tdp_level != 0xff && i != tdp_level)
+                        continue;
+
+                debug_printf("cpu:%d Get Information for TDP level:%d\n", cpu,
+                             i);
+                ctdp_level = &pkg_dev->ctdp_level[i];
+
+                ctdp_level->processed = 1;
+                ctdp_level->level = i;
+                ctdp_level->control_cpu = cpu;
+                ctdp_level->pkg_id = get_physical_package_id(cpu);
+                ctdp_level->die_id = get_physical_die_id(cpu);
+
+                ret = isst_get_ctdp_control(cpu, i, ctdp_level);
+                if (ret)
+                        return ret;
+
+                ret = isst_get_tdp_info(cpu, i, ctdp_level);
+                if (ret)
+                        return ret;
+
+                ret = isst_get_pwr_info(cpu, i, ctdp_level);
+                if (ret)
+                        return ret;
+
+                ret = isst_get_tjmax_info(cpu, i, ctdp_level);
+                if (ret)
+                        return ret;
+
+                ctdp_level->core_cpumask_size =
+                        alloc_cpu_set(&ctdp_level->core_cpumask);
+                ret = isst_get_coremask_info(cpu, i, ctdp_level);
+                if (ret)
+                        return ret;
+
+                ret = isst_get_get_trl(cpu, i, 0,
+                                       ctdp_level->trl_sse_active_cores);
+                if (ret)
+                        return ret;
+
+                ret = isst_get_get_trl(cpu, i, 1,
+                                       ctdp_level->trl_avx_active_cores);
+                if (ret)
+                        return ret;
+
+                ret = isst_get_get_trl(cpu, i, 2,
+                                       ctdp_level->trl_avx_512_active_cores);
+                if (ret)
+                        return ret;
+
+                if (ctdp_level->pbf_support) {
+                        ret = isst_get_pbf_info(cpu, i, &ctdp_level->pbf_info);
+                        if (!ret)
+                                ctdp_level->pbf_found = 1;
+                }
+
+                if (ctdp_level->fact_support) {
+                        ret = isst_get_fact_info(cpu, i,
+                                                 &ctdp_level->fact_info);
+                        if (ret)
+                                return ret;
+                }
+        }
+
+        pkg_dev->processed = 1;
+
+        return 0;
+}
+
+int isst_pm_qos_config(int cpu, int enable_clos, int priority_type)
+{
+        unsigned int req, resp;
+        int ret;
+
+        ret = isst_send_mbox_command(cpu, CONFIG_CLOS, CLOS_PM_QOS_CONFIG, 0, 0,
+                                     &resp);
+        if (ret)
+                return ret;
+
+        debug_printf("cpu:%d CLOS_PM_QOS_CONFIG resp:%x\n", cpu, resp);
+
+        req = resp;
+
+        if (enable_clos)
+                req = req | BIT(1);
+        else
+                req = req & ~BIT(1);
+
+        if (priority_type)
+                req = req | BIT(2);
+        else
+                req = req & ~BIT(2);
+
+        ret = isst_send_mbox_command(cpu, CONFIG_CLOS, CLOS_PM_QOS_CONFIG,
+                                     BIT(MBOX_CMD_WRITE_BIT), req, &resp);
+        if (ret)
+                return ret;
+
+        debug_printf("cpu:%d CLOS_PM_QOS_CONFIG priority type:%d req:%x\n", cpu,
+                     priority_type, req);
+
+        return 0;
+}
+
+int isst_pm_get_clos(int cpu, int clos, struct isst_clos_config *clos_config)
+{
+        unsigned int resp;
+        int ret;
+
+        ret = isst_send_mbox_command(cpu, CONFIG_CLOS, CLOS_PM_CLOS, clos, 0,
+                                     &resp);
+        if (ret)
+                return ret;
+
+        clos_config->pkg_id = get_physical_package_id(cpu);
+        clos_config->die_id = get_physical_die_id(cpu);
+
+        clos_config->epp = resp & 0x0f;
+        clos_config->clos_prop_prio = (resp >> 4) & 0x0f;
+        clos_config->clos_min = (resp >> 8) & 0xff;
+        clos_config->clos_max = (resp >> 16) & 0xff;
+        clos_config->clos_desired = (resp >> 24) & 0xff;
+
+        return 0;
+}
+
+int isst_set_clos(int cpu, int clos, struct isst_clos_config *clos_config)
+{
+        unsigned int req, resp;
+        unsigned int param;
+        int ret;
+
+        req = clos_config->epp & 0x0f;
+        req |= (clos_config->clos_prop_prio & 0x0f) << 4;
+        req |= (clos_config->clos_min & 0xff) << 8;
+        req |= (clos_config->clos_max & 0xff) << 16;
+        req |= (clos_config->clos_desired & 0xff) << 24;
+
+        param = BIT(MBOX_CMD_WRITE_BIT) | clos;
+
+        ret = isst_send_mbox_command(cpu, CONFIG_CLOS, CLOS_PM_CLOS, param, req,
+                                     &resp);
+        if (ret)
+                return ret;
+
+        debug_printf("cpu:%d CLOS_PM_CLOS param:%x req:%x\n", cpu, param, req);
+
+        return 0;
+}
+
+int isst_clos_get_assoc_status(int cpu, int *clos_id)
+{
+        unsigned int resp;
+        unsigned int param;
+        int core_id, ret;
+
+        core_id = find_phy_core_num(cpu);
+        param = core_id;
+
+        ret = isst_send_mbox_command(cpu, CONFIG_CLOS, CLOS_PQR_ASSOC, param, 0,
+                                     &resp);
+        if (ret)
+                return ret;
+
+        debug_printf("cpu:%d CLOS_PQR_ASSOC param:%x resp:%x\n", cpu, param,
+                     resp);
+        *clos_id = (resp >> 16) & 0x03;
+
+        return 0;
+}
+
+int isst_clos_associate(int cpu, int clos_id)
+{
+        unsigned int req, resp;
+        unsigned int param;
+        int core_id, ret;
+
+        req = (clos_id & 0x03) << 16;
+        core_id = find_phy_core_num(cpu);
+        param = BIT(MBOX_CMD_WRITE_BIT) | core_id;
+
+        ret = isst_send_mbox_command(cpu, CONFIG_CLOS, CLOS_PQR_ASSOC, param,
+                                     req, &resp);
+        if (ret)
+                return ret;
+
+        debug_printf("cpu:%d CLOS_PQR_ASSOC param:%x req:%x\n", cpu, param,
+                     req);
+
+        return 0;
+}
diff --git a/tools/power/x86/intel-speed-select/isst-display.c b/tools/power/x86/intel-speed-select/isst-display.c
new file mode 100644
index 000000000000..f368b8323742
--- /dev/null
+++ b/tools/power/x86/intel-speed-select/isst-display.c
@@ -0,0 +1,479 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel dynamic_speed_select -- Enumerate and control features
+ * Copyright (c) 2019 Intel Corporation.
+ */
+
+#include "isst.h"
+
+#define DISP_FREQ_MULTIPLIER 100000
+
+static void printcpumask(int str_len, char *str, int mask_size,
+                         cpu_set_t *cpu_mask)
+{
+        int i, max_cpus = get_topo_max_cpus();
+        unsigned int *mask;
+        int size, index, curr_index;
+
+        size = max_cpus / (sizeof(unsigned int) * 8);
+        if (max_cpus % (sizeof(unsigned int) * 8))
+                size++;
+
+        mask = calloc(size, sizeof(unsigned int));
+        if (!mask)
+                return;
+
+        for (i = 0; i < max_cpus; ++i) {
+                int mask_index, bit_index;
+
+                if (!CPU_ISSET_S(i, mask_size, cpu_mask))
+                        continue;
+
+                mask_index = i / (sizeof(unsigned int) * 8);
+                bit_index = i % (sizeof(unsigned int) * 8);
+                mask[mask_index] |= BIT(bit_index);
+        }
+
+        curr_index = 0;
+        for (i = size - 1; i >= 0; --i) {
+                index = snprintf(&str[curr_index], str_len - curr_index, "%08x",
+                                 mask[i]);
+                curr_index += index;
+                if (i) {
+                        strncat(&str[curr_index], ",", str_len - curr_index);
+                        curr_index++;
+                }
+        }
+
+        free(mask);
+}
+
+static void format_and_print_txt(FILE *outf, int level, char *header,
+                                 char *value)
+{
+        char *spaces = "  ";
+        static char delimiters[256];
+        int i, j = 0;
+
+        if (!level)
+                return;
+
+        if (level == 1) {
+                strcpy(delimiters, " ");
+        } else {
+                for (i = 0; i < level - 1; ++i)
+                        j += snprintf(&delimiters[j], sizeof(delimiters) - j,
+                                      "%s", spaces);
+        }
+
+        if (header && value) {
+                fprintf(outf, "%s", delimiters);
+                fprintf(outf, "%s:%s\n", header, value);
+        } else if (header) {
+                fprintf(outf, "%s", delimiters);
+                fprintf(outf, "%s\n", header);
+        }
+}
+
+static int last_level;
+static void format_and_print(FILE *outf, int level, char *header, char *value)
+{
+        char *spaces = "  ";
+        static char delimiters[256];
+        int i;
+
+        if (!out_format_is_json()) {
+                format_and_print_txt(outf, level, header, value);
+                return;
+        }
+
+        if (level == 0) {
+                if (header)
+                        fprintf(outf, "{");
+                else
+                        fprintf(outf, "\n}\n");
+
+        } else {
+                int j = 0;
+
+                for (i = 0; i < level; ++i)
+                        j += snprintf(&delimiters[j], sizeof(delimiters) - j,
+                                      "%s", spaces);
+
+                if (last_level == level)
+                        fprintf(outf, ",\n");
+
+                if (value) {
+                        if (last_level != level)
+                                fprintf(outf, "\n");
+
+                        fprintf(outf, "%s\"%s\": ", delimiters, header);
+                        fprintf(outf, "\"%s\"", value);
+                } else {
+                        for (i = last_level - 1; i >= level; --i) {
+                                int k = 0;
+
+                                for (j = i; j > 0; --j)
+                                        k += snprintf(&delimiters[k],
+                                                      sizeof(delimiters) - k,
+                                                      "%s", spaces);
+                                if (i == level && header)
+                                        fprintf(outf, "\n%s},", delimiters);
+                                else
+                                        fprintf(outf, "\n%s}", delimiters);
+                        }
+                        if (abs(last_level - level) < 3)
+                                fprintf(outf, "\n");
+                        if (header)
+                                fprintf(outf, "%s\"%s\": {", delimiters,
+                                        header);
+                }
+        }
+
+        last_level = level;
+}
+
+static void print_packag_info(int cpu, FILE *outf)
+{
+        char header[256];
+
+        snprintf(header, sizeof(header), "package-%d",
+                 get_physical_package_id(cpu));
+        format_and_print(outf, 1, header, NULL);
+        snprintf(header, sizeof(header), "die-%d", get_physical_die_id(cpu));
+        format_and_print(outf, 2, header, NULL);
+        snprintf(header, sizeof(header), "cpu-%d", cpu);
+        format_and_print(outf, 3, header, NULL);
+}
+
+static void _isst_pbf_display_information(int cpu, FILE *outf, int level,
+                                          struct isst_pbf_info *pbf_info,
+                                          int disp_level)
+{
+        char header[256];
+        char value[256];
+
+        snprintf(header, sizeof(header), "speed-select-base-freq");
+        format_and_print(outf, disp_level, header, NULL);
+
+        snprintf(header, sizeof(header), "high-priority-base-frequency(KHz)");
+        snprintf(value, sizeof(value), "%d",
+                 pbf_info->p1_high * DISP_FREQ_MULTIPLIER);
+        format_and_print(outf, disp_level + 1, header, value);
+
+        snprintf(header, sizeof(header), "high-priority-cpu-mask");
+        printcpumask(sizeof(value), value, pbf_info->core_cpumask_size,
+                     pbf_info->core_cpumask);
+        format_and_print(outf, disp_level + 1, header, value);
+
+        snprintf(header, sizeof(header), "low-priority-base-frequency(KHz)");
+        snprintf(value, sizeof(value), "%d",
+                 pbf_info->p1_low * DISP_FREQ_MULTIPLIER);
+        format_and_print(outf, disp_level + 1, header, value);
+
+        snprintf(header, sizeof(header), "tjunction-temperature(C)");
+        snprintf(value, sizeof(value), "%d", pbf_info->t_prochot);
+        format_and_print(outf, disp_level + 1, header, value);
+
+        snprintf(header, sizeof(header), "thermal-design-power(W)");
+        snprintf(value, sizeof(value), "%d", pbf_info->tdp);
+        format_and_print(outf, disp_level + 1, header, value);
+}
+
+static void _isst_fact_display_information(int cpu, FILE *outf, int level,
+                                           int fact_bucket, int fact_avx,
+                                           struct isst_fact_info *fact_info,
+                                           int base_level)
+{
+        struct isst_fact_bucket_info *bucket_info = fact_info->bucket_info;
+        char header[256];
+        char value[256];
+        int j;
+
+        snprintf(header, sizeof(header), "speed-select-turbo-freq");
+        format_and_print(outf, base_level, header, NULL);
+        for (j = 0; j < ISST_FACT_MAX_BUCKETS; ++j) {
+                if (fact_bucket != 0xff && fact_bucket != j)
+                        continue;
+
+                if (!bucket_info[j].high_priority_cores_count)
+                        break;
+
+                snprintf(header, sizeof(header), "bucket-%d", j);
+                format_and_print(outf, base_level + 1, header, NULL);
+
+                snprintf(header, sizeof(header), "high-priority-cores-count");
+                snprintf(value, sizeof(value), "%d",
+                         bucket_info[j].high_priority_cores_count);
+                format_and_print(outf, base_level + 2, header, value);
+
+                if (fact_avx & 0x01) {
+                        snprintf(header, sizeof(header),
+                                 "high-priority-max-frequency(KHz)");
+                        snprintf(value, sizeof(value), "%d",
+                                 bucket_info[j].sse_trl * DISP_FREQ_MULTIPLIER);
+                        format_and_print(outf, base_level + 2, header, value);
+                }
+
+                if (fact_avx & 0x02) {
+                        snprintf(header, sizeof(header),
+                                 "high-priority-max-avx2-frequency(KHz)");
+                        snprintf(value, sizeof(value), "%d",
+                                 bucket_info[j].avx_trl * DISP_FREQ_MULTIPLIER);
+                        format_and_print(outf, base_level + 2, header, value);
+                }
+
+                if (fact_avx & 0x04) {
+                        snprintf(header, sizeof(header),
+                                 "high-priority-max-avx512-frequency(KHz)");
+                        snprintf(value, sizeof(value), "%d",
+                                 bucket_info[j].avx512_trl *
+                                         DISP_FREQ_MULTIPLIER);
+                        format_and_print(outf, base_level + 2, header, value);
+                }
+        }
+        snprintf(header, sizeof(header),
+                 "speed-select-turbo-freq-clip-frequencies");
+        format_and_print(outf, base_level + 1, header, NULL);
+        snprintf(header, sizeof(header), "low-priority-max-frequency(KHz)");
+        snprintf(value, sizeof(value), "%d",
+                 fact_info->lp_clipping_ratio_license_sse *
+                         DISP_FREQ_MULTIPLIER);
+        format_and_print(outf, base_level + 2, header, value);
+        snprintf(header, sizeof(header),
+                 "low-priority-max-avx2-frequency(KHz)");
+        snprintf(value, sizeof(value), "%d",
+                 fact_info->lp_clipping_ratio_license_avx2 *
+                         DISP_FREQ_MULTIPLIER);
+        format_and_print(outf, base_level + 2, header, value);
+        snprintf(header, sizeof(header),
+                 "low-priority-max-avx512-frequency(KHz)");
+        snprintf(value, sizeof(value), "%d",
+                 fact_info->lp_clipping_ratio_license_avx512 *
+                         DISP_FREQ_MULTIPLIER);
+        format_and_print(outf, base_level + 2, header, value);
+}
+
+void isst_ctdp_display_information(int cpu, FILE *outf, int tdp_level,
+                                   struct isst_pkg_ctdp *pkg_dev)
+{
+        char header[256];
+        char value[256];
+        int i, base_level = 1;
+
+        print_packag_info(cpu, outf);
+
+        for (i = 0; i <= pkg_dev->levels; ++i) {
+                struct isst_pkg_ctdp_level_info *ctdp_level;
+                int j;
+
+                ctdp_level = &pkg_dev->ctdp_level[i];
+                if (!ctdp_level->processed)
+                        continue;
+
+                snprintf(header, sizeof(header), "perf-profile-level-%d",
+                         ctdp_level->level);
+                format_and_print(outf, base_level + 3, header, NULL);
+
+                snprintf(header, sizeof(header), "cpu-count");
+                j = get_cpu_count(get_physical_die_id(cpu),
+                                  get_physical_die_id(cpu));
+                snprintf(value, sizeof(value), "%d", j);
+                format_and_print(outf, base_level + 4, header, value);
+
+                snprintf(header, sizeof(header), "enable-cpu-mask");
+                printcpumask(sizeof(value), value,
+                             ctdp_level->core_cpumask_size,
+                             ctdp_level->core_cpumask);
+                format_and_print(outf, base_level + 4, header, value);
+
+                snprintf(header, sizeof(header), "thermal-design-power-ratio");
+                snprintf(value, sizeof(value), "%d", ctdp_level->tdp_ratio);
+                format_and_print(outf, base_level + 4, header, value);
+
+                snprintf(header, sizeof(header), "base-frequency(KHz)");
+                snprintf(value, sizeof(value), "%d",
+                         ctdp_level->tdp_ratio * DISP_FREQ_MULTIPLIER);
+                format_and_print(outf, base_level + 4, header, value);
+
+                snprintf(header, sizeof(header),
+                         "speed-select-turbo-freq-support");
+                snprintf(value, sizeof(value), "%d", ctdp_level->fact_support);
+                format_and_print(outf, base_level + 4, header, value);
+
+                snprintf(header, sizeof(header),
+                         "speed-select-base-freq-support");
+                snprintf(value, sizeof(value), "%d", ctdp_level->pbf_support);
+                format_and_print(outf, base_level + 4, header, value);
+
+                snprintf(header, sizeof(header),
+                         "speed-select-base-freq-enabled");
+                snprintf(value, sizeof(value), "%d", ctdp_level->pbf_enabled);
+                format_and_print(outf, base_level + 4, header, value);
+
+                snprintf(header, sizeof(header),
+                         "speed-select-turbo-freq-enabled");
+                snprintf(value, sizeof(value), "%d", ctdp_level->fact_enabled);
+                format_and_print(outf, base_level + 4, header, value);
+
+                snprintf(header, sizeof(header), "thermal-design-power(W)");
+                snprintf(value, sizeof(value), "%d", ctdp_level->pkg_tdp);
+                format_and_print(outf, base_level + 4, header, value);
+
+                snprintf(header, sizeof(header), "tjunction-max(C)");
+                snprintf(value, sizeof(value), "%d", ctdp_level->t_proc_hot);
+                format_and_print(outf, base_level + 4, header, value);
+
+                snprintf(header, sizeof(header), "turbo-ratio-limits-sse");
+                format_and_print(outf, base_level + 4, header, NULL);
+                for (j = 0; j < 8; ++j) {
+                        snprintf(header, sizeof(header), "bucket-%d", j);
+                        format_and_print(outf, base_level + 5, header, NULL);
+
+                        snprintf(header, sizeof(header), "core-count");
+                        snprintf(value, sizeof(value), "%d", j);
+                        format_and_print(outf, base_level + 6, header, value);
+
+                        snprintf(header, sizeof(header), "turbo-ratio");
+                        snprintf(value, sizeof(value), "%d",
+                                 ctdp_level->trl_sse_active_cores[j]);
+                        format_and_print(outf, base_level + 6, header, value);
+                }
+                snprintf(header, sizeof(header), "turbo-ratio-limits-avx");
+                format_and_print(outf, base_level + 4, header, NULL);
+                for (j = 0; j < 8; ++j) {
+                        snprintf(header, sizeof(header), "bucket-%d", j);
+                        format_and_print(outf, base_level + 5, header, NULL);
+
+                        snprintf(header, sizeof(header), "core-count");
+                        snprintf(value, sizeof(value), "%d", j);
+                        format_and_print(outf, base_level + 6, header, value);
+
+                        snprintf(header, sizeof(header), "turbo-ratio");
+                        snprintf(value, sizeof(value), "%d",
+                                 ctdp_level->trl_avx_active_cores[j]);
+                        format_and_print(outf, base_level + 6, header, value);
+                }
+
+                snprintf(header, sizeof(header), "turbo-ratio-limits-avx512");
+                format_and_print(outf, base_level + 4, header, NULL);
+                for (j = 0; j < 8; ++j) {
+                        snprintf(header, sizeof(header), "bucket-%d", j);
+                        format_and_print(outf, base_level + 5, header, NULL);
+
+                        snprintf(header, sizeof(header), "core-count");
+                        snprintf(value, sizeof(value), "%d", j);
+                        format_and_print(outf, base_level + 6, header, value);
+
+                        snprintf(header, sizeof(header), "turbo-ratio");
+                        snprintf(value, sizeof(value), "%d",
+                                 ctdp_level->trl_avx_512_active_cores[j]);
+                        format_and_print(outf, base_level + 6, header, value);
+                }
+                if (ctdp_level->pbf_support)
+                        _isst_pbf_display_information(cpu, outf, i,
+                                                      &ctdp_level->pbf_info,
+                                                      base_level + 4);
+                if (ctdp_level->fact_support)
+                        _isst_fact_display_information(cpu, outf, i, 0xff, 0xff,
+                                                       &ctdp_level->fact_info,
+                                                       base_level + 4);
+        }
+
+        format_and_print(outf, 1, NULL, NULL);
+}
+
+void isst_ctdp_display_information_start(FILE *outf)
+{
+        last_level = 0;
+        format_and_print(outf, 0, "start", NULL);
+}
+
+void isst_ctdp_display_information_end(FILE *outf)
+{
+        format_and_print(outf, 0, NULL, NULL);
+}
+
+void isst_pbf_display_information(int cpu, FILE *outf, int level,
+                                  struct isst_pbf_info *pbf_info)
+{
+        print_packag_info(cpu, outf);
+        _isst_pbf_display_information(cpu, outf, level, pbf_info, 4);
+        format_and_print(outf, 1, NULL, NULL);
+}
+
+void isst_fact_display_information(int cpu, FILE *outf, int level,
+                                   int fact_bucket, int fact_avx,
+                                   struct isst_fact_info *fact_info)
+{
+        print_packag_info(cpu, outf);
+        _isst_fact_display_information(cpu, outf, level, fact_bucket, fact_avx,
+                                       fact_info, 4);
+        format_and_print(outf, 1, NULL, NULL);
+}
+
+void isst_clos_display_information(int cpu, FILE *outf, int clos,
+                                   struct isst_clos_config *clos_config)
+{
+        char header[256];
+        char value[256];
+
+        snprintf(header, sizeof(header), "package-%d",
+                 get_physical_package_id(cpu));
+        format_and_print(outf, 1, header, NULL);
+        snprintf(header, sizeof(header), "die-%d", get_physical_die_id(cpu));
+        format_and_print(outf, 2, header, NULL);
+        snprintf(header, sizeof(header), "cpu-%d", cpu);
+        format_and_print(outf, 3, header, NULL);
+
+        snprintf(header, sizeof(header), "core-power");
+        format_and_print(outf, 4, header, NULL);
+
+        snprintf(header, sizeof(header), "clos");
+        snprintf(value, sizeof(value), "%d", clos);
+        format_and_print(outf, 5, header, value);
+
+        snprintf(header, sizeof(header), "epp");
+        snprintf(value, sizeof(value), "%d", clos_config->epp);
+        format_and_print(outf, 5, header, value);
+
+        snprintf(header, sizeof(header), "clos-proportional-priority");
+        snprintf(value, sizeof(value), "%d", clos_config->clos_prop_prio);
+        format_and_print(outf, 5, header, value);
+
+        snprintf(header, sizeof(header), "clos-min");
+        snprintf(value, sizeof(value), "%d", clos_config->clos_min);
+        format_and_print(outf, 5, header, value);
+
+        snprintf(header, sizeof(header), "clos-max");
+        snprintf(value, sizeof(value), "%d", clos_config->clos_max);
+        format_and_print(outf, 5, header, value);
+
+        snprintf(header, sizeof(header), "clos-desired");
+        snprintf(value, sizeof(value), "%d", clos_config->clos_desired);
+        format_and_print(outf, 5, header, value);
+
+        format_and_print(outf, 1, NULL, NULL);
+}
+
+void isst_display_result(int cpu, FILE *outf, char *feature, char *cmd,
+                         int result)
+{
+        char header[256];
+        char value[256];
+
+        snprintf(header, sizeof(header), "package-%d",
+                 get_physical_package_id(cpu));
+        format_and_print(outf, 1, header, NULL);
+        snprintf(header, sizeof(header), "die-%d", get_physical_die_id(cpu));
+        format_and_print(outf, 2, header, NULL);
+        snprintf(header, sizeof(header), "cpu-%d", cpu);
+        format_and_print(outf, 3, header, NULL);
+        snprintf(header, sizeof(header), "%s", feature);
+        format_and_print(outf, 4, header, NULL);
+        snprintf(header, sizeof(header), "%s", cmd);
+        snprintf(value, sizeof(value), "%d", result);
+        format_and_print(outf, 5, header, value);
+
+        format_and_print(outf, 1, NULL, NULL);
+}
diff --git a/tools/power/x86/intel-speed-select/isst.h b/tools/power/x86/intel-speed-select/isst.h
new file mode 100644
index 000000000000..221881761609
--- /dev/null
+++ b/tools/power/x86/intel-speed-select/isst.h
@@ -0,0 +1,231 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Intel Speed Select -- Enumerate and control features
+ * Copyright (c) 2019 Intel Corporation.
+ */
+
+#ifndef _ISST_H_
+#define _ISST_H_
+
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sched.h>
+#include <sys/stat.h>
+#include <sys/resource.h>
+#include <getopt.h>
+#include <err.h>
+#include <fcntl.h>
+#include <signal.h>
+#include <sys/time.h>
+#include <limits.h>
+#include <stdlib.h>
+#include <string.h>
+#include <cpuid.h>
+#include <dirent.h>
+#include <errno.h>
+
+#include <stdarg.h>
+#include <sys/ioctl.h>
+
+#define BIT(x) (1 << (x))
+#define GENMASK(h, l) (((~0UL) << (l)) & (~0UL >> (sizeof(long) * 8 - 1 - (h))))
+#define GENMASK_ULL(h, l)                                                      \
+        (((~0ULL) << (l)) & (~0ULL >> (sizeof(long long) * 8 - 1 - (h))))
+
+#define CONFIG_TDP                              0x7f
+#define CONFIG_TDP_GET_LEVELS_INFO              0x00
+#define CONFIG_TDP_GET_TDP_CONTROL              0x01
+#define CONFIG_TDP_SET_TDP_CONTROL              0x02
+#define CONFIG_TDP_GET_TDP_INFO                 0x03
+#define CONFIG_TDP_GET_PWR_INFO                 0x04
+#define CONFIG_TDP_GET_TJMAX_INFO               0x05
+#define CONFIG_TDP_GET_CORE_MASK                0x06
+#define CONFIG_TDP_GET_TURBO_LIMIT_RATIOS       0x07
+#define CONFIG_TDP_SET_LEVEL                    0x08
+#define CONFIG_TDP_GET_UNCORE_P0_P1_INFO        0X09
+#define CONFIG_TDP_GET_P1_INFO                  0x0a
+#define CONFIG_TDP_GET_MEM_FREQ                 0x0b
+
+#define CONFIG_TDP_GET_FACT_HP_TURBO_LIMIT_NUMCORES     0x10
+#define CONFIG_TDP_GET_FACT_HP_TURBO_LIMIT_RATIOS       0x11
+#define CONFIG_TDP_GET_FACT_LP_CLIPPING_RATIO           0x12
+
+#define CONFIG_TDP_PBF_GET_CORE_MASK_INFO       0x20
+#define CONFIG_TDP_PBF_GET_P1HI_P1LO_INFO       0x21
+#define CONFIG_TDP_PBF_GET_TJ_MAX_INFO          0x22
+#define CONFIG_TDP_PBF_GET_TDP_INFO             0X23
+
+#define CONFIG_CLOS                             0xd0
+#define CLOS_PQR_ASSOC                          0x00
+#define CLOS_PM_CLOS                            0x01
+#define CLOS_PM_QOS_CONFIG                      0x02
+#define CLOS_STATUS                             0x03
+
+#define MBOX_CMD_WRITE_BIT                      0x08
+
+#define PM_QOS_INFO_OFFSET                      0x00
+#define PM_QOS_CONFIG_OFFSET                    0x04
+#define PM_CLOS_OFFSET                          0x08
+#define PQR_ASSOC_OFFSET                        0x20
+
+struct isst_clos_config {
+        int pkg_id;
+        int die_id;
+        unsigned char epp;
+        unsigned char clos_prop_prio;
+        unsigned char clos_min;
+        unsigned char clos_max;
+        unsigned char clos_desired;
+};
+
+struct isst_fact_bucket_info {
+        int high_priority_cores_count;
+        int sse_trl;
+        int avx_trl;
+        int avx512_trl;
+};
+
+struct isst_pbf_info {
+        int pbf_acticated;
+        int pbf_available;
+        size_t core_cpumask_size;
+        cpu_set_t *core_cpumask;
+        int p1_high;
+        int p1_low;
+        int t_control;
+        int t_prochot;
+        int tdp;
+};
+
+#define ISST_TRL_MAX_ACTIVE_CORES       8
+#define ISST_FACT_MAX_BUCKETS           8
+struct isst_fact_info {
+        int lp_clipping_ratio_license_sse;
+        int lp_clipping_ratio_license_avx2;
+        int lp_clipping_ratio_license_avx512;
+        struct isst_fact_bucket_info bucket_info[ISST_FACT_MAX_BUCKETS];
+};
+
+struct isst_pkg_ctdp_level_info {
+        int processed;
+        int control_cpu;
+        int pkg_id;
+        int die_id;
+        int level;
+        int fact_support;
+        int pbf_support;
+        int fact_enabled;
+        int pbf_enabled;
+        int tdp_ratio;
+        int active;
+        int tdp_control;
+        int pkg_tdp;
+        int pkg_min_power;
+        int pkg_max_power;
+        int fact;
+        int t_proc_hot;
+        int uncore_p0;
+        int uncore_p1;
+        int sse_p1;
+        int avx2_p1;
+        int avx512_p1;
+        int mem_freq;
+        size_t core_cpumask_size;
+        cpu_set_t *core_cpumask;
+        int cpu_count;
+        int trl_sse_active_cores[ISST_TRL_MAX_ACTIVE_CORES];
+        int trl_avx_active_cores[ISST_TRL_MAX_ACTIVE_CORES];
+        int trl_avx_512_active_cores[ISST_TRL_MAX_ACTIVE_CORES];
+        int kobj_bucket_index;
+        int active_bucket;
+        int fact_max_index;
+        int fact_max_config;
+        int pbf_found;
+        int pbf_active;
+        struct isst_pbf_info pbf_info;
+        struct isst_fact_info fact_info;
+};
+
+#define ISST_MAX_TDP_LEVELS     (4 + 1) /* +1 for base config */
+struct isst_pkg_ctdp {
+        int locked;
+        int version;
+        int processed;
+        int levels;
+        int current_level;
+        int enabled;
+        struct isst_pkg_ctdp_level_info ctdp_level[ISST_MAX_TDP_LEVELS];
+};
+
+extern int get_topo_max_cpus(void);
+extern int get_cpu_count(int pkg_id, int die_id);
+
+/* Common interfaces */
+extern void debug_printf(const char *format, ...);
+extern int out_format_is_json(void);
+extern int get_physical_package_id(int cpu);
+extern int get_physical_die_id(int cpu);
+extern size_t alloc_cpu_set(cpu_set_t **cpu_set);
+extern void free_cpu_set(cpu_set_t *cpu_set);
+extern int find_logical_cpu(int pkg_id, int die_id, int phy_cpu);
+extern int find_phy_cpu_num(int logical_cpu);
+extern int find_phy_core_num(int logical_cpu);
+extern void set_cpu_mask_from_punit_coremask(int cpu,
+                                             unsigned long long core_mask,
+                                             size_t core_cpumask_size,
+                                             cpu_set_t *core_cpumask,
+                                             int *cpu_cnt);
+
+extern int isst_send_mbox_command(unsigned int cpu, unsigned char command,
+                                  unsigned char sub_command,
+                                  unsigned int write,
+                                  unsigned int req_data, unsigned int *resp);
+
+extern int isst_send_msr_command(unsigned int cpu, unsigned int command,
+                                 int write, unsigned long long *req_resp);
+
+extern int isst_get_ctdp_levels(int cpu, struct isst_pkg_ctdp *pkg_dev);
+extern int isst_get_process_ctdp(int cpu, int tdp_level,
+                                 struct isst_pkg_ctdp *pkg_dev);
+extern void isst_get_process_ctdp_complete(int cpu,
+                                           struct isst_pkg_ctdp *pkg_dev);
+extern void isst_ctdp_display_information(int cpu, FILE *outf, int tdp_level,
+                                          struct isst_pkg_ctdp *pkg_dev);
+extern void isst_ctdp_display_information_start(FILE *outf);
+extern void isst_ctdp_display_information_end(FILE *outf);
+extern void isst_pbf_display_information(int cpu, FILE *outf, int level,
+                                         struct isst_pbf_info *info);
+extern int isst_set_tdp_level(int cpu, int tdp_level);
+extern int isst_set_tdp_level_msr(int cpu, int tdp_level);
+extern int isst_set_pbf_fact_status(int cpu, int pbf, int enable);
+extern int isst_get_pbf_info(int cpu, int level,
+                             struct isst_pbf_info *pbf_info);
+extern void isst_get_pbf_info_complete(struct isst_pbf_info *pbf_info);
+extern int isst_get_fact_info(int cpu, int level,
+                              struct isst_fact_info *fact_info);
+extern int isst_get_fact_bucket_info(int cpu, int level,
+                                     struct isst_fact_bucket_info *bucket_info);
+extern void isst_fact_display_information(int cpu, FILE *outf, int level,
+                                          int fact_bucket, int fact_avx,
+                                          struct isst_fact_info *fact_info);
+extern int isst_set_trl(int cpu, unsigned long long trl);
+extern int isst_set_trl_from_current_tdp(int cpu, unsigned long long trl);
+extern int isst_get_config_tdp_lock_status(int cpu);
+
+extern int isst_pm_qos_config(int cpu, int enable_clos, int priority_type);
+extern int isst_pm_get_clos(int cpu, int clos,
+                            struct isst_clos_config *clos_config);
+extern int isst_set_clos(int cpu, int clos,
+                         struct isst_clos_config *clos_config);
+extern int isst_clos_associate(int cpu, int clos);
+extern int isst_clos_get_assoc_status(int cpu, int *clos_id);
+extern void isst_clos_display_information(int cpu, FILE *outf, int clos,
+                                          struct isst_clos_config *clos_config);
+
+extern int isst_read_reg(unsigned short reg, unsigned int *val);
+extern int isst_write_reg(int reg, unsigned int val);
+
+extern void isst_display_result(int cpu, FILE *outf, char *feature, char *cmd,
+                                int result);
+#endif
diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c
index 076df22e4bda..cd040b5abffe 100644
--- a/tools/testing/nvdimm/test/iomap.c
+++ b/tools/testing/nvdimm/test/iomap.c
@@ -100,25 +100,60 @@ static void nfit_test_kill(void *_pgmap)
 {
         struct dev_pagemap *pgmap = _pgmap;
 
-        WARN_ON(!pgmap || !pgmap->ref || !pgmap->kill || !pgmap->cleanup);
-        pgmap->kill(pgmap->ref);
-        pgmap->cleanup(pgmap->ref);
+        WARN_ON(!pgmap || !pgmap->ref);
+
+        if (pgmap->ops && pgmap->ops->kill)
+                pgmap->ops->kill(pgmap);
+        else
+                percpu_ref_kill(pgmap->ref);
+
+        if (pgmap->ops && pgmap->ops->cleanup) {
+                pgmap->ops->cleanup(pgmap);
+        } else {
+                wait_for_completion(&pgmap->done);
+                percpu_ref_exit(pgmap->ref);
+        }
+}
+
+static void dev_pagemap_percpu_release(struct percpu_ref *ref)
+{
+        struct dev_pagemap *pgmap =
+                container_of(ref, struct dev_pagemap, internal_ref);
+
+        complete(&pgmap->done);
 }
 
 void *__wrap_devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 {
+        int error;
         resource_size_t offset = pgmap->res.start;
         struct nfit_test_resource *nfit_res = get_nfit_res(offset);
 
-        if (nfit_res) {
-                int rc;
-
-                rc = devm_add_action_or_reset(dev, nfit_test_kill, pgmap);
-                if (rc)
-                        return ERR_PTR(rc);
-                return nfit_res->buf + offset - nfit_res->res.start;
+        if (!nfit_res)
+                return devm_memremap_pages(dev, pgmap);
+
+        pgmap->dev = dev;
+        if (!pgmap->ref) {
+                if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup))
+                        return ERR_PTR(-EINVAL);
+
+                init_completion(&pgmap->done);
+                error = percpu_ref_init(&pgmap->internal_ref,
+                                dev_pagemap_percpu_release, 0, GFP_KERNEL);
+                if (error)
+                        return ERR_PTR(error);
+                pgmap->ref = &pgmap->internal_ref;
+        } else {
+                if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) {
+                        WARN(1, "Missing reference count teardown definition\n");
+                        return ERR_PTR(-EINVAL);
+                }
         }
-        return devm_memremap_pages(dev, pgmap);
+
+        error = devm_add_action_or_reset(dev, nfit_test_kill, pgmap);
+        if (error)
+                return ERR_PTR(error);
+        return nfit_res->buf + offset - nfit_res->res.start;
 }
 EXPORT_SYMBOL_GPL(__wrap_devm_memremap_pages);
 
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 2620406a53ec..11c9c62c3362 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -1,4 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
+include ../../../../scripts/Kbuild.include
+include ../../../scripts/Makefile.arch
 
 LIBDIR := ../../../lib
 BPFDIR := $(LIBDIR)/bpf
@@ -81,13 +83,14 @@ all: $(TEST_CUSTOM_PROGS)
 $(OUTPUT)/urandom_read: $(OUTPUT)/%: %.c
         $(CC) -o $@ $< -Wl,--build-id
 
-$(OUTPUT)/test_maps: map_tests/*.c
+$(OUTPUT)/test_stub.o: test_stub.c
+        $(CC) $(TEST_PROGS_CFLAGS) $(CFLAGS) -c -o $@ $<
 
 BPFOBJ := $(OUTPUT)/libbpf.a
 
-$(TEST_GEN_PROGS): test_stub.o $(BPFOBJ)
+$(TEST_GEN_PROGS): $(OUTPUT)/test_stub.o $(BPFOBJ)
 
-$(TEST_GEN_PROGS_EXTENDED): test_stub.o $(OUTPUT)/libbpf.a
+$(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/test_stub.o $(OUTPUT)/libbpf.a
 
 $(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
 $(OUTPUT)/test_skb_cgroup_id_user: cgroup_helpers.c
@@ -138,7 +141,8 @@ CLANG_SYS_INCLUDES := $(shell $(CLANG) -v -E - </dev/null 2>&1 \
 
 CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \
               $(CLANG_SYS_INCLUDES) \
-              -Wno-compare-distinct-pointer-types
+              -Wno-compare-distinct-pointer-types \
+              -D__TARGET_ARCH_$(SRCARCH)
 
 $(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline
 $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline
@@ -172,6 +176,7 @@ endif
 endif
 
 TEST_PROGS_CFLAGS := -I. -I$(OUTPUT)
+TEST_MAPS_CFLAGS := -I. -I$(OUTPUT)
 TEST_VERIFIER_CFLAGS := -I. -I$(OUTPUT) -Iverifier
 
 ifneq ($(SUBREG_CODEGEN),)
@@ -180,12 +185,12 @@ TEST_CUSTOM_PROGS += $(ALU32_BUILD_DIR)/test_progs_32
 $(ALU32_BUILD_DIR):
         mkdir -p $@
 
-$(ALU32_BUILD_DIR)/urandom_read: $(OUTPUT)/urandom_read
+$(ALU32_BUILD_DIR)/urandom_read: $(OUTPUT)/urandom_read | $(ALU32_BUILD_DIR)
         cp $< $@
 
 $(ALU32_BUILD_DIR)/test_progs_32: test_progs.c $(OUTPUT)/libbpf.a\
-                                                $(ALU32_BUILD_DIR) \
-                                                $(ALU32_BUILD_DIR)/urandom_read
+                                                $(ALU32_BUILD_DIR)/urandom_read \
+                                                | $(ALU32_BUILD_DIR)
         $(CC) $(TEST_PROGS_CFLAGS) $(CFLAGS) \
                 -o $(ALU32_BUILD_DIR)/test_progs_32 \
                 test_progs.c test_stub.c trace_helpers.c prog_tests/*.c \
@@ -194,10 +199,10 @@ $(ALU32_BUILD_DIR)/test_progs_32: test_progs.c $(OUTPUT)/libbpf.a\
 $(ALU32_BUILD_DIR)/test_progs_32: $(PROG_TESTS_H)
 $(ALU32_BUILD_DIR)/test_progs_32: prog_tests/*.c
 
-$(ALU32_BUILD_DIR)/%.o: progs/%.c $(ALU32_BUILD_DIR) \
-                                        $(ALU32_BUILD_DIR)/test_progs_32
-        $(CLANG) $(CLANG_FLAGS) \
-                 -O2 -target bpf -emit-llvm -c $< -o - |      \
+$(ALU32_BUILD_DIR)/%.o: progs/%.c $(ALU32_BUILD_DIR)/test_progs_32 \
+                                        | $(ALU32_BUILD_DIR)
+        ($(CLANG) $(CLANG_FLAGS) -O2 -target bpf -emit-llvm -c $< -o - || \
+                echo "clang failed") | \
         $(LLC) -march=bpf -mattr=+alu32 -mcpu=$(CPU) $(LLC_FLAGS) \
                 -filetype=obj -o $@
 ifeq ($(DWARF2BTF),y)
@@ -208,32 +213,30 @@ endif
 # Have one program compiled without "-target bpf" to test whether libbpf loads
 # it successfully
 $(OUTPUT)/test_xdp.o: progs/test_xdp.c
-        $(CLANG) $(CLANG_FLAGS) \
-                -O2 -emit-llvm -c $< -o - | \
+        ($(CLANG) $(CLANG_FLAGS) -O2 -emit-llvm -c $< -o - || \
+                echo "clang failed") | \
         $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
 ifeq ($(DWARF2BTF),y)
         $(BTF_PAHOLE) -J $@
 endif
 
 $(OUTPUT)/%.o: progs/%.c
-        $(CLANG) $(CLANG_FLAGS) \
-                 -O2 -target bpf -emit-llvm -c $< -o - |      \
+        ($(CLANG) $(CLANG_FLAGS) -O2 -target bpf -emit-llvm -c $< -o - || \
+                echo "clang failed") | \
         $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
 ifeq ($(DWARF2BTF),y)
         $(BTF_PAHOLE) -J $@
 endif
 
-PROG_TESTS_H := $(OUTPUT)/prog_tests/tests.h
-test_progs.c: $(PROG_TESTS_H)
-$(OUTPUT)/test_progs: CFLAGS += $(TEST_PROGS_CFLAGS)
-$(OUTPUT)/test_progs: prog_tests/*.c
-
 PROG_TESTS_DIR = $(OUTPUT)/prog_tests
 $(PROG_TESTS_DIR):
         mkdir -p $@
-
+PROG_TESTS_H := $(PROG_TESTS_DIR)/tests.h
 PROG_TESTS_FILES := $(wildcard prog_tests/*.c)
-$(PROG_TESTS_H): $(PROG_TESTS_DIR) $(PROG_TESTS_FILES)
+test_progs.c: $(PROG_TESTS_H)
+$(OUTPUT)/test_progs: CFLAGS += $(TEST_PROGS_CFLAGS)
+$(OUTPUT)/test_progs: test_progs.c $(PROG_TESTS_H) $(PROG_TESTS_FILES)
+$(PROG_TESTS_H): $(PROG_TESTS_FILES) | $(PROG_TESTS_DIR)
         $(shell ( cd prog_tests/; \
                   echo '/* Generated header, do not edit */'; \
                   echo '#ifdef DECLARE'; \
@@ -246,15 +249,15 @@ $(PROG_TESTS_H): $(PROG_TESTS_DIR) $(PROG_TESTS_FILES)
                   echo '#endif' \
                  ) > $(PROG_TESTS_H))
 
-TEST_MAPS_CFLAGS := -I. -I$(OUTPUT)
 MAP_TESTS_DIR = $(OUTPUT)/map_tests
 $(MAP_TESTS_DIR):
         mkdir -p $@
 MAP_TESTS_H := $(MAP_TESTS_DIR)/tests.h
+MAP_TESTS_FILES := $(wildcard map_tests/*.c)
 test_maps.c: $(MAP_TESTS_H)
 $(OUTPUT)/test_maps: CFLAGS += $(TEST_MAPS_CFLAGS)
-MAP_TESTS_FILES := $(wildcard map_tests/*.c)
-$(MAP_TESTS_H): $(MAP_TESTS_DIR) $(MAP_TESTS_FILES)
+$(OUTPUT)/test_maps: test_maps.c $(MAP_TESTS_H) $(MAP_TESTS_FILES)
+$(MAP_TESTS_H): $(MAP_TESTS_FILES) | $(MAP_TESTS_DIR)
         $(shell ( cd map_tests/; \
                   echo '/* Generated header, do not edit */'; \
                   echo '#ifdef DECLARE'; \
@@ -267,16 +270,15 @@ $(MAP_TESTS_H): $(MAP_TESTS_DIR) $(MAP_TESTS_FILES)
                   echo '#endif' \
                  ) > $(MAP_TESTS_H))
 
-VERIFIER_TESTS_H := $(OUTPUT)/verifier/tests.h
-test_verifier.c: $(VERIFIER_TESTS_H)
-$(OUTPUT)/test_verifier: CFLAGS += $(TEST_VERIFIER_CFLAGS)
-
 VERIFIER_TESTS_DIR = $(OUTPUT)/verifier
 $(VERIFIER_TESTS_DIR):
         mkdir -p $@
-
+VERIFIER_TESTS_H := $(VERIFIER_TESTS_DIR)/tests.h
 VERIFIER_TEST_FILES := $(wildcard verifier/*.c)
-$(OUTPUT)/verifier/tests.h: $(VERIFIER_TESTS_DIR) $(VERIFIER_TEST_FILES)
+test_verifier.c: $(VERIFIER_TESTS_H)
+$(OUTPUT)/test_verifier: CFLAGS += $(TEST_VERIFIER_CFLAGS)
+$(OUTPUT)/test_verifier: test_verifier.c $(VERIFIER_TESTS_H)
+$(VERIFIER_TESTS_H): $(VERIFIER_TEST_FILES) | $(VERIFIER_TESTS_DIR)
         $(shell ( cd verifier/; \
                   echo '/* Generated header, do not edit */'; \
                   echo '#ifdef FILL_ARRAY'; \
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 5a3d92c8bec8..f804f210244e 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -315,8 +315,8 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
 #if defined(__TARGET_ARCH_x86)
         #define bpf_target_x86
         #define bpf_target_defined
-#elif defined(__TARGET_ARCH_s930x)
-        #define bpf_target_s930x
+#elif defined(__TARGET_ARCH_s390)
+        #define bpf_target_s390
         #define bpf_target_defined
 #elif defined(__TARGET_ARCH_arm)
         #define bpf_target_arm
@@ -341,8 +341,8 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
 #ifndef bpf_target_defined
 #if defined(__x86_64__)
         #define bpf_target_x86
-#elif defined(__s390x__)
-        #define bpf_target_s930x
+#elif defined(__s390__)
+        #define bpf_target_s390
 #elif defined(__arm__)
         #define bpf_target_arm
 #elif defined(__aarch64__)
@@ -358,6 +358,7 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
 
 #if defined(bpf_target_x86)
 
+#ifdef __KERNEL__
 #define PT_REGS_PARM1(x) ((x)->di)
 #define PT_REGS_PARM2(x) ((x)->si)
 #define PT_REGS_PARM3(x) ((x)->dx)
@@ -368,19 +369,49 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
 #define PT_REGS_RC(x) ((x)->ax)
 #define PT_REGS_SP(x) ((x)->sp)
 #define PT_REGS_IP(x) ((x)->ip)
+#else
+#ifdef __i386__
+/* i386 kernel is built with -mregparm=3 */
+#define PT_REGS_PARM1(x) ((x)->eax)
+#define PT_REGS_PARM2(x) ((x)->edx)
+#define PT_REGS_PARM3(x) ((x)->ecx)
+#define PT_REGS_PARM4(x) 0
+#define PT_REGS_PARM5(x) 0
+#define PT_REGS_RET(x) ((x)->esp)
+#define PT_REGS_FP(x) ((x)->ebp)
+#define PT_REGS_RC(x) ((x)->eax)
+#define PT_REGS_SP(x) ((x)->esp)
+#define PT_REGS_IP(x) ((x)->eip)
+#else
+#define PT_REGS_PARM1(x) ((x)->rdi)
+#define PT_REGS_PARM2(x) ((x)->rsi)
+#define PT_REGS_PARM3(x) ((x)->rdx)
+#define PT_REGS_PARM4(x) ((x)->rcx)
+#define PT_REGS_PARM5(x) ((x)->r8)
+#define PT_REGS_RET(x) ((x)->rsp)
+#define PT_REGS_FP(x) ((x)->rbp)
+#define PT_REGS_RC(x) ((x)->rax)
+#define PT_REGS_SP(x) ((x)->rsp)
+#define PT_REGS_IP(x) ((x)->rip)
+#endif
+#endif
 
-#elif defined(bpf_target_s390x)
+#elif defined(bpf_target_s390)
 
-#define PT_REGS_PARM1(x) ((x)->gprs[2])
-#define PT_REGS_PARM2(x) ((x)->gprs[3])
-#define PT_REGS_PARM3(x) ((x)->gprs[4])
-#define PT_REGS_PARM4(x) ((x)->gprs[5])
-#define PT_REGS_PARM5(x) ((x)->gprs[6])
-#define PT_REGS_RET(x) ((x)->gprs[14])
-#define PT_REGS_FP(x) ((x)->gprs[11]) /* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_RC(x) ((x)->gprs[2])
-#define PT_REGS_SP(x) ((x)->gprs[15])
-#define PT_REGS_IP(x) ((x)->psw.addr)
+/* s390 provides user_pt_regs instead of struct pt_regs to userspace */
+struct pt_regs;
+#define PT_REGS_S390 const volatile user_pt_regs
+#define PT_REGS_PARM1(x) (((PT_REGS_S390 *)(x))->gprs[2])
+#define PT_REGS_PARM2(x) (((PT_REGS_S390 *)(x))->gprs[3])
+#define PT_REGS_PARM3(x) (((PT_REGS_S390 *)(x))->gprs[4])
+#define PT_REGS_PARM4(x) (((PT_REGS_S390 *)(x))->gprs[5])
+#define PT_REGS_PARM5(x) (((PT_REGS_S390 *)(x))->gprs[6])
+#define PT_REGS_RET(x) (((PT_REGS_S390 *)(x))->gprs[14])
+/* Works only with CONFIG_FRAME_POINTER */
+#define PT_REGS_FP(x) (((PT_REGS_S390 *)(x))->gprs[11])
+#define PT_REGS_RC(x) (((PT_REGS_S390 *)(x))->gprs[2])
+#define PT_REGS_SP(x) (((PT_REGS_S390 *)(x))->gprs[15])
+#define PT_REGS_IP(x) (((PT_REGS_S390 *)(x))->psw.addr)
 
 #elif defined(bpf_target_arm)
 
@@ -397,16 +428,20 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
 
 #elif defined(bpf_target_arm64)
 
-#define PT_REGS_PARM1(x) ((x)->regs[0])
-#define PT_REGS_PARM2(x) ((x)->regs[1])
-#define PT_REGS_PARM3(x) ((x)->regs[2])
-#define PT_REGS_PARM4(x) ((x)->regs[3])
-#define PT_REGS_PARM5(x) ((x)->regs[4])
-#define PT_REGS_RET(x) ((x)->regs[30])
-#define PT_REGS_FP(x) ((x)->regs[29]) /* Works only with CONFIG_FRAME_POINTER */
-#define PT_REGS_RC(x) ((x)->regs[0])
-#define PT_REGS_SP(x) ((x)->sp)
-#define PT_REGS_IP(x) ((x)->pc)
+/* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */
+struct pt_regs;
+#define PT_REGS_ARM64 const volatile struct user_pt_regs
+#define PT_REGS_PARM1(x) (((PT_REGS_ARM64 *)(x))->regs[0])
+#define PT_REGS_PARM2(x) (((PT_REGS_ARM64 *)(x))->regs[1])
+#define PT_REGS_PARM3(x) (((PT_REGS_ARM64 *)(x))->regs[2])
+#define PT_REGS_PARM4(x) (((PT_REGS_ARM64 *)(x))->regs[3])
+#define PT_REGS_PARM5(x) (((PT_REGS_ARM64 *)(x))->regs[4])
+#define PT_REGS_RET(x) (((PT_REGS_ARM64 *)(x))->regs[30])
+/* Works only with CONFIG_FRAME_POINTER */
+#define PT_REGS_FP(x) (((PT_REGS_ARM64 *)(x))->regs[29])
+#define PT_REGS_RC(x) (((PT_REGS_ARM64 *)(x))->regs[0])
+#define PT_REGS_SP(x) (((PT_REGS_ARM64 *)(x))->sp)
+#define PT_REGS_IP(x) (((PT_REGS_ARM64 *)(x))->pc)
 
 #elif defined(bpf_target_mips)
 
@@ -452,10 +487,10 @@ static int (*bpf_skb_adjust_room)(void *ctx, __s32 len_diff, __u32 mode,
 
 #endif
 
-#ifdef bpf_target_powerpc
+#if defined(bpf_target_powerpc)
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)         ({ (ip) = (ctx)->link; })
 #define BPF_KRETPROBE_READ_RET_IP               BPF_KPROBE_READ_RET_IP
-#elif bpf_target_sparc
+#elif defined(bpf_target_sparc)
 #define BPF_KPROBE_READ_RET_IP(ip, ctx)         ({ (ip) = PT_REGS_RET(ctx); })
 #define BPF_KRETPROBE_READ_RET_IP               BPF_KPROBE_READ_RET_IP
 #else
diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
index a4686395522c..5ecc267d98b0 100644
--- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c
+++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
@@ -21,12 +21,6 @@ ssize_t get_base_addr() {
         return -EINVAL;
 }
 
-#ifdef __x86_64__
-#define SYS_KPROBE_NAME "__x64_sys_nanosleep"
-#else
-#define SYS_KPROBE_NAME "sys_nanosleep"
-#endif
-
 void test_attach_probe(void)
 {
         const char *kprobe_name = "kprobe/sys_nanosleep";
@@ -84,7 +78,7 @@ void test_attach_probe(void)
 
         kprobe_link = bpf_program__attach_kprobe(kprobe_prog,
                                                  false /* retprobe */,
-                                                 SYS_KPROBE_NAME);
+                                                 SYS_NANOSLEEP_KPROBE_NAME);
         if (CHECK(IS_ERR(kprobe_link), "attach_kprobe",
                   "err %ld\n", PTR_ERR(kprobe_link))) {
                 kprobe_link = NULL;
@@ -92,7 +86,7 @@ void test_attach_probe(void)
         }
         kretprobe_link = bpf_program__attach_kprobe(kretprobe_prog,
                                                     true /* retprobe */,
-                                                    SYS_KPROBE_NAME);
+                                                    SYS_NANOSLEEP_KPROBE_NAME);
         if (CHECK(IS_ERR(kretprobe_link), "attach_kretprobe",
                   "err %ld\n", PTR_ERR(kretprobe_link))) {
                 kretprobe_link = NULL;
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
index 3f1ef95865ff..3003fddc0613 100644
--- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
+++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
@@ -5,12 +5,6 @@
 #include <sys/socket.h>
 #include <test_progs.h>
 
-#ifdef __x86_64__
-#define SYS_KPROBE_NAME "__x64_sys_nanosleep"
-#else
-#define SYS_KPROBE_NAME "sys_nanosleep"
-#endif
-
 static void on_sample(void *ctx, int cpu, void *data, __u32 size)
 {
         int cpu_data = *(int *)data, duration = 0;
@@ -56,7 +50,7 @@ void test_perf_buffer(void)
 
         /* attach kprobe */
         link = bpf_program__attach_kprobe(prog, false /* retprobe */,
-                                          SYS_KPROBE_NAME);
+                                          SYS_NANOSLEEP_KPROBE_NAME);
         if (CHECK(IS_ERR(link), "attach_kprobe", "err %ld\n", PTR_ERR(link)))
                 goto out_close;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c
index 67cea1686305..54218ee3c004 100644
--- a/tools/testing/selftests/bpf/prog_tests/send_signal.c
+++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c
@@ -173,6 +173,18 @@ static int test_send_signal_tracepoint(void)
         return test_send_signal_common(&attr, BPF_PROG_TYPE_TRACEPOINT, "tracepoint");
 }
 
+static int test_send_signal_perf(void)
+{
+        struct perf_event_attr attr = {
+                .sample_period = 1,
+                .type = PERF_TYPE_SOFTWARE,
+                .config = PERF_COUNT_SW_CPU_CLOCK,
+        };
+
+        return test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT,
+                                       "perf_sw_event");
+}
+
 static int test_send_signal_nmi(void)
 {
         struct perf_event_attr attr = {
@@ -181,8 +193,26 @@ static int test_send_signal_nmi(void)
                 .type = PERF_TYPE_HARDWARE,
                 .config = PERF_COUNT_HW_CPU_CYCLES,
         };
+        int pmu_fd;
+
+        /* Some setups (e.g. virtual machines) might run with hardware
+         * perf events disabled. If this is the case, skip this test.
+         */
+        pmu_fd = syscall(__NR_perf_event_open, &attr, 0 /* pid */,
+                         -1 /* cpu */, -1 /* group_fd */, 0 /* flags */);
+        if (pmu_fd == -1) {
+                if (errno == ENOENT) {
+                        printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n",
+                                __func__);
+                        return 0;
+                }
+                /* Let the test fail with a more informative message */
+        } else {
+                close(pmu_fd);
+        }
 
-        return test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT, "perf_event");
+        return test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT,
+                                       "perf_hw_event");
 }
 
 void test_send_signal(void)
@@ -190,6 +220,7 @@ void test_send_signal(void)
         int ret = 0;
 
         ret |= test_send_signal_tracepoint();
+        ret |= test_send_signal_perf();
         ret |= test_send_signal_nmi();
         if (!ret)
                 printf("test_send_signal:OK\n");
diff --git a/tools/testing/selftests/bpf/progs/loop1.c b/tools/testing/selftests/bpf/progs/loop1.c
index dea395af9ea9..7cdb7f878310 100644
--- a/tools/testing/selftests/bpf/progs/loop1.c
+++ b/tools/testing/selftests/bpf/progs/loop1.c
@@ -18,7 +18,7 @@ int nested_loops(volatile struct pt_regs* ctx)
         for (j = 0; j < 300; j++)
                 for (i = 0; i < j; i++) {
                         if (j & 1)
-                                m = ctx->rax;
+                                m = PT_REGS_RC(ctx);
                         else
                                 m = j;
                         sum += i * m;
diff --git a/tools/testing/selftests/bpf/progs/loop2.c b/tools/testing/selftests/bpf/progs/loop2.c
index 0637bd8e8bcf..9b2f808a2863 100644
--- a/tools/testing/selftests/bpf/progs/loop2.c
+++ b/tools/testing/selftests/bpf/progs/loop2.c
@@ -16,7 +16,7 @@ int while_true(volatile struct pt_regs* ctx)
         int i = 0;
 
         while (true) {
-                if (ctx->rax & 1)
+                if (PT_REGS_RC(ctx) & 1)
                         i += 3;
                 else
                         i += 7;
diff --git a/tools/testing/selftests/bpf/progs/loop3.c b/tools/testing/selftests/bpf/progs/loop3.c
index 30a0f6cba080..d727657d51e2 100644
--- a/tools/testing/selftests/bpf/progs/loop3.c
+++ b/tools/testing/selftests/bpf/progs/loop3.c
@@ -16,7 +16,7 @@ int while_true(volatile struct pt_regs* ctx)
         __u64 i = 0, sum = 0;
         do {
                 i++;
-                sum += ctx->rax;
+                sum += PT_REGS_RC(ctx);
         } while (i < 0x100000000ULL);
         return sum;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
index d06b47a09097..33254b771384 100644
--- a/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
+++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c
@@ -47,11 +47,12 @@ struct {
  * issue and avoid complicated C programming massaging.
  * This is an acceptable workaround since there is one entry here.
  */
+typedef __u64 raw_stack_trace_t[2 * MAX_STACK_RAWTP];
 struct {
         __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
         __uint(max_entries, 1);
         __type(key, __u32);
-        __u64 (*value)[2 * MAX_STACK_RAWTP];
+        __type(value, raw_stack_trace_t);
 } rawdata_map SEC(".maps");
 
 SEC("tracepoint/raw_syscalls/sys_enter")
diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
index bbfc8337b6f0..f5638e26865d 100644
--- a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
+++ b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
@@ -36,8 +36,7 @@ struct {
         __uint(type, BPF_MAP_TYPE_ARRAY);
         __uint(max_entries, 128);
         __type(key, __u32);
-        /* there seems to be a bug in kernel not handling typedef properly */
-        struct bpf_stack_build_id (*value)[PERF_MAX_STACK_DEPTH];
+        __type(value, stack_trace_t);
 } stack_amap SEC(".maps");
 
 /* taken from /sys/kernel/debug/tracing/events/random/urandom_read/format */
diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
index 803c15dc109d..fa0be3e10a10 100644
--- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
+++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
@@ -35,7 +35,7 @@ struct {
         __uint(type, BPF_MAP_TYPE_ARRAY);
         __uint(max_entries, 16384);
         __type(key, __u32);
-        __u64 (*value)[PERF_MAX_STACK_DEPTH];
+        __type(value, stack_trace_t);
 } stack_amap SEC(".maps");
 
 /* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
index dad8a7e33eaa..e88d7b9d65ab 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
@@ -14,6 +14,7 @@
 #include <linux/tcp.h>
 #include <linux/udp.h>
 #include "bpf_helpers.h"
+#include "bpf_endian.h"
 
 static __u32 rol32(__u32 word, unsigned int shift)
 {
@@ -305,7 +306,7 @@ bool encap_v6(struct xdp_md *xdp, struct ctl_value *cval,
         ip6h->nexthdr = IPPROTO_IPV6;
         ip_suffix = pckt->flow.srcv6[3] ^ pckt->flow.port16[0];
         ip6h->payload_len =
-            __builtin_bswap16(pkt_bytes + sizeof(struct ipv6hdr));
+            bpf_htons(pkt_bytes + sizeof(struct ipv6hdr));
         ip6h->hop_limit = 4;
 
         ip6h->saddr.in6_u.u6_addr32[0] = 1;
@@ -322,7 +323,7 @@ bool encap_v4(struct xdp_md *xdp, struct ctl_value *cval,
               struct real_definition *dst, __u32 pkt_bytes)
 {
 
-        __u32 ip_suffix = __builtin_bswap16(pckt->flow.port16[0]);
+        __u32 ip_suffix = bpf_ntohs(pckt->flow.port16[0]);
         struct eth_hdr *new_eth;
         struct eth_hdr *old_eth;
         __u16 *next_iph_u16;
@@ -352,7 +353,7 @@ bool encap_v4(struct xdp_md *xdp, struct ctl_value *cval,
         iph->protocol = IPPROTO_IPIP;
         iph->check = 0;
         iph->tos = 1;
-        iph->tot_len = __builtin_bswap16(pkt_bytes + sizeof(struct iphdr));
+        iph->tot_len = bpf_htons(pkt_bytes + sizeof(struct iphdr));
         /* don't update iph->daddr, since it will overwrite old eth_proto
          * and multiple iterations of bpf_prog_run() will fail
          */
@@ -639,7 +640,7 @@ static int process_l3_headers_v6(struct packet_description *pckt,
         iph_len = sizeof(struct ipv6hdr);
         *protocol = ip6h->nexthdr;
         pckt->flow.proto = *protocol;
-        *pkt_bytes = __builtin_bswap16(ip6h->payload_len);
+        *pkt_bytes = bpf_ntohs(ip6h->payload_len);
         off += iph_len;
         if (*protocol == 45) {
                 return XDP_DROP;
@@ -671,7 +672,7 @@ static int process_l3_headers_v4(struct packet_description *pckt,
                 return XDP_DROP;
         *protocol = iph->protocol;
         pckt->flow.proto = *protocol;
-        *pkt_bytes = __builtin_bswap16(iph->tot_len);
+        *pkt_bytes = bpf_ntohs(iph->tot_len);
         off += 20;
         if (iph->frag_off & 65343)
                 return XDP_DROP;
@@ -808,10 +809,10 @@ int balancer_ingress(struct xdp_md *ctx)
         nh_off = sizeof(struct eth_hdr);
         if (data + nh_off > data_end)
                 return XDP_DROP;
-        eth_proto = eth->eth_proto;
-        if (eth_proto == 8)
+        eth_proto = bpf_ntohs(eth->eth_proto);
+        if (eth_proto == ETH_P_IP)
                 return process_packet(data, nh_off, data_end, 0, ctx);
-        else if (eth_proto == 56710)
+        else if (eth_proto == ETH_P_IPV6)
                 return process_packet(data, nh_off, data_end, 1, ctx);
         else
                 return XDP_DROP;
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 8351cb5f4a20..3d617e806054 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -3417,6 +3417,94 @@ static struct btf_raw_test raw_tests[] = {
         .value_type_id = 1,
         .max_entries = 4,
 },
+/*
+ * typedef int arr_t[16];
+ * struct s {
+ *      arr_t *a;
+ * };
+ */
+{
+        .descr = "struct->ptr->typedef->array->int size resolution",
+        .raw_types = {
+                BTF_STRUCT_ENC(NAME_TBD, 1, 8),                 /* [1] */
+                BTF_MEMBER_ENC(NAME_TBD, 2, 0),
+                BTF_PTR_ENC(3),                                 /* [2] */
+                BTF_TYPEDEF_ENC(NAME_TBD, 4),                   /* [3] */
+                BTF_TYPE_ARRAY_ENC(5, 5, 16),                   /* [4] */
+                BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [5] */
+                BTF_END_RAW,
+        },
+        BTF_STR_SEC("\0s\0a\0arr_t"),
+        .map_type = BPF_MAP_TYPE_ARRAY,
+        .map_name = "ptr_mod_chain_size_resolve_map",
+        .key_size = sizeof(int),
+        .value_size = sizeof(int) * 16,
+        .key_type_id = 5 /* int */,
+        .value_type_id = 3 /* arr_t */,
+        .max_entries = 4,
+},
+/*
+ * typedef int arr_t[16][8][4];
+ * struct s {
+ *      arr_t *a;
+ * };
+ */
+{
+        .descr = "struct->ptr->typedef->multi-array->int size resolution",
+        .raw_types = {
+                BTF_STRUCT_ENC(NAME_TBD, 1, 8),                 /* [1] */
+                BTF_MEMBER_ENC(NAME_TBD, 2, 0),
+                BTF_PTR_ENC(3),                                 /* [2] */
+                BTF_TYPEDEF_ENC(NAME_TBD, 4),                   /* [3] */
+                BTF_TYPE_ARRAY_ENC(5, 7, 16),                   /* [4] */
+                BTF_TYPE_ARRAY_ENC(6, 7, 8),                    /* [5] */
+                BTF_TYPE_ARRAY_ENC(7, 7, 4),                    /* [6] */
+                BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [7] */
+                BTF_END_RAW,
+        },
+        BTF_STR_SEC("\0s\0a\0arr_t"),
+        .map_type = BPF_MAP_TYPE_ARRAY,
+        .map_name = "multi_arr_size_resolve_map",
+        .key_size = sizeof(int),
+        .value_size = sizeof(int) * 16 * 8 * 4,
+        .key_type_id = 7 /* int */,
+        .value_type_id = 3 /* arr_t */,
+        .max_entries = 4,
+},
+/*
+ * typedef int int_t;
+ * typedef int_t arr3_t[4];
+ * typedef arr3_t arr2_t[8];
+ * typedef arr2_t arr1_t[16];
+ * struct s {
+ *      arr1_t *a;
+ * };
+ */
+{
+        .descr = "typedef/multi-arr mix size resolution",
+        .raw_types = {
+                BTF_STRUCT_ENC(NAME_TBD, 1, 8),                 /* [1] */
+                BTF_MEMBER_ENC(NAME_TBD, 2, 0),
+                BTF_PTR_ENC(3),                                 /* [2] */
+                BTF_TYPEDEF_ENC(NAME_TBD, 4),                   /* [3] */
+                BTF_TYPE_ARRAY_ENC(5, 10, 16),                  /* [4] */
+                BTF_TYPEDEF_ENC(NAME_TBD, 6),                   /* [5] */
+                BTF_TYPE_ARRAY_ENC(7, 10, 8),                   /* [6] */
+                BTF_TYPEDEF_ENC(NAME_TBD, 8),                   /* [7] */
+                BTF_TYPE_ARRAY_ENC(9, 10, 4),                   /* [8] */
+                BTF_TYPEDEF_ENC(NAME_TBD, 10),                  /* [9] */
+                BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [10] */
+                BTF_END_RAW,
+        },
+        BTF_STR_SEC("\0s\0a\0arr1_t\0arr2_t\0arr3_t\0int_t"),
+        .map_type = BPF_MAP_TYPE_ARRAY,
+        .map_name = "typedef_arra_mix_size_resolve_map",
+        .key_size = sizeof(int),
+        .value_size = sizeof(int) * 16 * 8 * 4,
+        .key_type_id = 10 /* int */,
+        .value_type_id = 3 /* arr_t */,
+        .max_entries = 4,
+},
 
 }; /* struct btf_raw_test raw_tests[] */
 
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index f095e1d4c657..49e0f7d85643 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -92,3 +92,11 @@ int compare_map_keys(int map1_fd, int map2_fd);
 int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len);
 int extract_build_id(char *build_id, size_t size);
 void *spin_lock_thread(void *arg);
+
+#ifdef __x86_64__
+#define SYS_NANOSLEEP_KPROBE_NAME "__x64_sys_nanosleep"
+#elif defined(__s390x__)
+#define SYS_NANOSLEEP_KPROBE_NAME "__s390x_sys_nanosleep"
+#else
+#define SYS_NANOSLEEP_KPROBE_NAME "sys_nanosleep"
+#endif
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index b0773291012a..84135d5f4b35 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -86,7 +86,7 @@ struct bpf_test {
         int fixup_sk_storage_map[MAX_FIXUPS];
         const char *errstr;
         const char *errstr_unpriv;
-        uint32_t retval, retval_unpriv, insn_processed;
+        uint32_t insn_processed;
         int prog_len;
         enum {
                 UNDEF,
@@ -95,16 +95,20 @@ struct bpf_test {
         } result, result_unpriv;
         enum bpf_prog_type prog_type;
         uint8_t flags;
-        __u8 data[TEST_DATA_LEN];
         void (*fill_helper)(struct bpf_test *self);
         uint8_t runs;
-        struct {
-                uint32_t retval, retval_unpriv;
-                union {
-                        __u8 data[TEST_DATA_LEN];
-                        __u64 data64[TEST_DATA_LEN / 8];
-                };
-        } retvals[MAX_TEST_RUNS];
+#define bpf_testdata_struct_t                                   \
+        struct {                                                \
+                uint32_t retval, retval_unpriv;                 \
+                union {                                         \
+                        __u8 data[TEST_DATA_LEN];               \
+                        __u64 data64[TEST_DATA_LEN / 8];        \
+                };                                              \
+        }
+        union {
+                bpf_testdata_struct_t;
+                bpf_testdata_struct_t retvals[MAX_TEST_RUNS];
+        };
         enum bpf_attach_type expected_attach_type;
 };
 
@@ -949,17 +953,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
                 uint32_t expected_val;
                 int i;
 
-                if (!test->runs) {
-                        expected_val = unpriv && test->retval_unpriv ?
-                                test->retval_unpriv : test->retval;
-
-                        err = do_prog_test_run(fd_prog, unpriv, expected_val,
-                                               test->data, sizeof(test->data));
-                        if (err)
-                                run_errs++;
-                        else
-                                run_successes++;
-                }
+                if (!test->runs)
+                        test->runs = 1;
 
                 for (i = 0; i < test->runs; i++) {
                         if (unpriv && test->retvals[i].retval_unpriv)
diff --git a/tools/testing/selftests/bpf/verifier/array_access.c b/tools/testing/selftests/bpf/verifier/array_access.c
index bcb83196e459..f3c33e128709 100644
--- a/tools/testing/selftests/bpf/verifier/array_access.c
+++ b/tools/testing/selftests/bpf/verifier/array_access.c
@@ -226,7 +226,7 @@
         BPF_LD_MAP_FD(BPF_REG_1, 0),
         BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
         BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
+        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0),
         BPF_EXIT_INSN(),
         },
         .fixup_map_array_ro = { 3 },
diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
index c3de1a2c9dc5..a53d99cebd9f 100644
--- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
+++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
@@ -183,7 +183,7 @@
         BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
         BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
         BPF_EXIT_INSN(),
-        BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+        BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
         BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 3),
         BPF_MOV64_IMM(BPF_REG_2, 0),
         BPF_MOV64_IMM(BPF_REG_3, 0x100000),
diff --git a/tools/testing/selftests/bpf/verifier/wide_access.c b/tools/testing/selftests/bpf/verifier/wide_access.c
new file mode 100644
index 000000000000..ccade9312d21
--- /dev/null
+++ b/tools/testing/selftests/bpf/verifier/wide_access.c
@@ -0,0 +1,73 @@
+#define BPF_SOCK_ADDR_STORE(field, off, res, err) \
+{ \
+        "wide store to bpf_sock_addr." #field "[" #off "]", \
+        .insns = { \
+        BPF_MOV64_IMM(BPF_REG_0, 1), \
+        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, \
+                    offsetof(struct bpf_sock_addr, field[off])), \
+        BPF_EXIT_INSN(), \
+        }, \
+        .result = res, \
+        .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, \
+        .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, \
+        .errstr = err, \
+}
+
+/* user_ip6[0] is u64 aligned */
+BPF_SOCK_ADDR_STORE(user_ip6, 0, ACCEPT,
+                    NULL),
+BPF_SOCK_ADDR_STORE(user_ip6, 1, REJECT,
+                    "invalid bpf_context access off=12 size=8"),
+BPF_SOCK_ADDR_STORE(user_ip6, 2, ACCEPT,
+                    NULL),
+BPF_SOCK_ADDR_STORE(user_ip6, 3, REJECT,
+                    "invalid bpf_context access off=20 size=8"),
+
+/* msg_src_ip6[0] is _not_ u64 aligned */
+BPF_SOCK_ADDR_STORE(msg_src_ip6, 0, REJECT,
+                    "invalid bpf_context access off=44 size=8"),
+BPF_SOCK_ADDR_STORE(msg_src_ip6, 1, ACCEPT,
+                    NULL),
+BPF_SOCK_ADDR_STORE(msg_src_ip6, 2, REJECT,
+                    "invalid bpf_context access off=52 size=8"),
+BPF_SOCK_ADDR_STORE(msg_src_ip6, 3, REJECT,
+                    "invalid bpf_context access off=56 size=8"),
+
+#undef BPF_SOCK_ADDR_STORE
+
+#define BPF_SOCK_ADDR_LOAD(field, off, res, err) \
+{ \
+        "wide load from bpf_sock_addr." #field "[" #off "]", \
+        .insns = { \
+        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, \
+                    offsetof(struct bpf_sock_addr, field[off])), \
+        BPF_MOV64_IMM(BPF_REG_0, 1), \
+        BPF_EXIT_INSN(), \
+        }, \
+        .result = res, \
+        .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, \
+        .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, \
+        .errstr = err, \
+}
+
+/* user_ip6[0] is u64 aligned */
+BPF_SOCK_ADDR_LOAD(user_ip6, 0, ACCEPT,
+                   NULL),
+BPF_SOCK_ADDR_LOAD(user_ip6, 1, REJECT,
+                   "invalid bpf_context access off=12 size=8"),
+BPF_SOCK_ADDR_LOAD(user_ip6, 2, ACCEPT,
+                   NULL),
+BPF_SOCK_ADDR_LOAD(user_ip6, 3, REJECT,
+                   "invalid bpf_context access off=20 size=8"),
+
+/* msg_src_ip6[0] is _not_ u64 aligned */
+BPF_SOCK_ADDR_LOAD(msg_src_ip6, 0, REJECT,
+                   "invalid bpf_context access off=44 size=8"),
+BPF_SOCK_ADDR_LOAD(msg_src_ip6, 1, ACCEPT,
+                   NULL),
+BPF_SOCK_ADDR_LOAD(msg_src_ip6, 2, REJECT,
+                   "invalid bpf_context access off=52 size=8"),
+BPF_SOCK_ADDR_LOAD(msg_src_ip6, 3, REJECT,
+                   "invalid bpf_context access off=56 size=8"),
+
+#undef BPF_SOCK_ADDR_LOAD
diff --git a/tools/testing/selftests/bpf/verifier/wide_store.c b/tools/testing/selftests/bpf/verifier/wide_store.c
deleted file mode 100644
index 8fe99602ded4..000000000000
--- a/tools/testing/selftests/bpf/verifier/wide_store.c
+++ /dev/null
@@ -1,36 +0,0 @@
-#define BPF_SOCK_ADDR(field, off, res, err) \
-{ \
-        "wide store to bpf_sock_addr." #field "[" #off "]", \
-        .insns = { \
-        BPF_MOV64_IMM(BPF_REG_0, 1), \
-        BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, \
-                    offsetof(struct bpf_sock_addr, field[off])), \
-        BPF_EXIT_INSN(), \
-        }, \
-        .result = res, \
-        .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, \
-        .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, \
-        .errstr = err, \
-}
-
-/* user_ip6[0] is u64 aligned */
-BPF_SOCK_ADDR(user_ip6, 0, ACCEPT,
-              NULL),
-BPF_SOCK_ADDR(user_ip6, 1, REJECT,
-              "invalid bpf_context access off=12 size=8"),
-BPF_SOCK_ADDR(user_ip6, 2, ACCEPT,
-              NULL),
-BPF_SOCK_ADDR(user_ip6, 3, REJECT,
-              "invalid bpf_context access off=20 size=8"),
-
-/* msg_src_ip6[0] is _not_ u64 aligned */
-BPF_SOCK_ADDR(msg_src_ip6, 0, REJECT,
-              "invalid bpf_context access off=44 size=8"),
-BPF_SOCK_ADDR(msg_src_ip6, 1, ACCEPT,
-              NULL),
-BPF_SOCK_ADDR(msg_src_ip6, 2, REJECT,
-              "invalid bpf_context access off=52 size=8"),
-BPF_SOCK_ADDR(msg_src_ip6, 3, REJECT,
-              "invalid bpf_context access off=56 size=8"),
-
-#undef BPF_SOCK_ADDR
diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest
index 6d5e9e87c4b7..063ecb290a5a 100755
--- a/tools/testing/selftests/ftrace/ftracetest
+++ b/tools/testing/selftests/ftrace/ftracetest
@@ -23,9 +23,15 @@ echo "		            If <dir> is -, all logs output in console only"
 exit $1
 }
 
+# default error
+err_ret=1
+
+# kselftest skip code is 4
+err_skip=4
+
 errexit() { # message
   echo "Error: $1" 1>&2
-  exit 1
+  exit $err_ret
 }
 
 # Ensuring user privilege
@@ -116,11 +122,31 @@ parse_opts() { # opts
 }
 
 # Parameters
-DEBUGFS_DIR=`grep debugfs /proc/mounts | cut -f2 -d' ' | head -1`
-if [ -z "$DEBUGFS_DIR" ]; then
-    TRACING_DIR=`grep tracefs /proc/mounts | cut -f2 -d' ' | head -1`
-else
-    TRACING_DIR=$DEBUGFS_DIR/tracing
+TRACING_DIR=`grep tracefs /proc/mounts | cut -f2 -d' ' | head -1`
+if [ -z "$TRACING_DIR" ]; then
+    DEBUGFS_DIR=`grep debugfs /proc/mounts | cut -f2 -d' ' | head -1`
+    if [ -z "$DEBUGFS_DIR" ]; then
+        # If tracefs exists, then so does /sys/kernel/tracing
+        if [ -d "/sys/kernel/tracing" ]; then
+            mount -t tracefs nodev /sys/kernel/tracing ||
+              errexit "Failed to mount /sys/kernel/tracing"
+            TRACING_DIR="/sys/kernel/tracing"
+        # If debugfs exists, then so does /sys/kernel/debug
+        elif [ -d "/sys/kernel/debug" ]; then
+            mount -t debugfs nodev /sys/kernel/debug ||
+              errexit "Failed to mount /sys/kernel/debug"
+            TRACING_DIR="/sys/kernel/debug/tracing"
+        else
+            err_ret=$err_skip
+            errexit "debugfs and tracefs are not configured in this kernel"
+        fi
+    else
+        TRACING_DIR="$DEBUGFS_DIR/tracing"
+    fi
+fi
+if [ ! -d "$TRACING_DIR" ]; then
+    err_ret=$err_skip
+    errexit "ftrace is not configured in this kernel"
 fi
 
 TOP_DIR=`absdir $0`
diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions
index 779ec11f61bd..1d96c5f7e402 100644
--- a/tools/testing/selftests/ftrace/test.d/functions
+++ b/tools/testing/selftests/ftrace/test.d/functions
@@ -91,8 +91,8 @@ initialize_ftrace() { # Reset ftrace to initial-state
     reset_events_filter
     reset_ftrace_filter
     disable_events
-    echo > set_event_pid        # event tracer is always on
-    echo > set_ftrace_pid
+    [ -f set_event_pid ] && echo > set_event_pid
+    [ -f set_ftrace_pid ] && echo > set_ftrace_pid
     [ -f set_ftrace_filter ] && echo | tee set_ftrace_*
     [ -f set_graph_function ] && echo | tee set_graph_*
     [ -f stack_trace_filter ] && echo > stack_trace_filter
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_user.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_user.tc
new file mode 100644
index 000000000000..0f60087583d8
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_user.tc
@@ -0,0 +1,32 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Kprobe event user-memory access
+
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
+grep -q '\$arg<N>' README || exit_unresolved # depends on arch
+grep -A10 "fetcharg:" README | grep -q 'ustring' || exit_unsupported
+grep -A10 "fetcharg:" README | grep -q '\[u\]<offset>' || exit_unsupported
+
+:;: "user-memory access syntax and ustring working on user memory";:
+echo 'p:myevent do_sys_open path=+0($arg2):ustring path2=+u0($arg2):string' \
+        > kprobe_events
+
+grep myevent kprobe_events | \
+        grep -q 'path=+0($arg2):ustring path2=+u0($arg2):string'
+echo 1 > events/kprobes/myevent/enable
+echo > /dev/null
+echo 0 > events/kprobes/myevent/enable
+
+grep myevent trace | grep -q 'path="/dev/null" path2="/dev/null"'
+
+:;: "user-memory access syntax and ustring not working with kernel memory";:
+echo 'p:myevent vfs_symlink path=+0($arg3):ustring path2=+u0($arg3):string' \
+        > kprobe_events
+echo 1 > events/kprobes/myevent/enable
+ln -s foo $TMPDIR/bar
+echo 0 > events/kprobes/myevent/enable
+
+grep myevent trace | grep -q 'path=(fault) path2=(fault)'
+
+exit 0
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 9457aaeae092..4465fc2dae14 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -9,12 +9,13 @@ ret=0
 ksft_skip=4
 
 # all tests in this script. Can be overridden with -t option
-TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw"
+TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter"
 
 VERBOSE=0
 PAUSE_ON_FAIL=no
 PAUSE=no
 IP="ip -netns ns1"
+NS_EXEC="ip netns exec ns1"
 
 log_test()
 {
@@ -433,6 +434,37 @@ fib_carrier_test()
         fib_carrier_unicast_test
 }
 
+fib_rp_filter_test()
+{
+        echo
+        echo "IPv4 rp_filter tests"
+
+        setup
+
+        set -e
+        $IP link set dev lo address 52:54:00:6a:c7:5e
+        $IP link set dummy0 address 52:54:00:6a:c7:5e
+        $IP link add dummy1 type dummy
+        $IP link set dummy1 address 52:54:00:6a:c7:5e
+        $IP link set dev dummy1 up
+        $NS_EXEC sysctl -qw net.ipv4.conf.all.rp_filter=1
+        $NS_EXEC sysctl -qw net.ipv4.conf.all.accept_local=1
+        $NS_EXEC sysctl -qw net.ipv4.conf.all.route_localnet=1
+
+        $NS_EXEC tc qd add dev dummy1 parent root handle 1: fq_codel
+        $NS_EXEC tc filter add dev dummy1 parent 1: protocol arp basic action mirred egress redirect dev lo
+        $NS_EXEC tc filter add dev dummy1 parent 1: protocol ip basic action mirred egress redirect dev lo
+        set +e
+
+        run_cmd "ip netns exec ns1 ping -I dummy1 -w1 -c1 198.51.100.1"
+        log_test $? 0 "rp_filter passes local packets"
+
+        run_cmd "ip netns exec ns1 ping -I dummy1 -w1 -c1 127.0.0.1"
+        log_test $? 0 "rp_filter passes loopback packets"
+
+        cleanup
+}
+
 ################################################################################
 # Tests on nexthop spec
 
@@ -1557,6 +1589,7 @@ do
         fib_unreg_test|unregister)      fib_unreg_test;;
         fib_down_test|down)             fib_down_test;;
         fib_carrier_test|carrier)       fib_carrier_test;;
+        fib_rp_filter_test|rp_filter)   fib_rp_filter_test;;
         fib_nexthop_test|nexthop)       fib_nexthop_test;;
         ipv6_route_test|ipv6_rt)        ipv6_route_test;;
         ipv4_route_test|ipv4_rt)        ipv4_route_test;;
diff --git a/tools/testing/selftests/ntb/ntb_test.sh b/tools/testing/selftests/ntb/ntb_test.sh
index 8a20e03d4cb7..9c60337317c6 100755
--- a/tools/testing/selftests/ntb/ntb_test.sh
+++ b/tools/testing/selftests/ntb/ntb_test.sh
@@ -78,10 +78,10 @@ set -e
 
 function _modprobe()
 {
-        modprobe "$@"
+        modprobe "$@" || return 1
 
         if [[ "$REMOTE_HOST" != "" ]]; then
-                ssh "$REMOTE_HOST" modprobe "$@"
+                ssh "$REMOTE_HOST" modprobe "$@" || return 1
         fi
 }
 
@@ -442,6 +442,30 @@ function pingpong_test()
         echo "  Passed"
 }
 
+function msi_test()
+{
+        LOC=$1
+        REM=$2
+
+        write_file 1 $LOC/ready
+
+        echo "Running MSI interrupt tests on: $(subdirname $LOC) / $(subdirname $REM)"
+
+        CNT=$(read_file "$LOC/count")
+        for ((i = 0; i < $CNT; i++)); do
+                START=$(read_file $REM/../irq${i}_occurrences)
+                write_file $i $LOC/trigger
+                END=$(read_file $REM/../irq${i}_occurrences)
+
+                if [[ $(($END - $START)) != 1 ]]; then
+                        echo "MSI did not trigger the interrupt on the remote side!" >&2
+                        exit 1
+                fi
+        done
+
+        echo "  Passed"
+}
+
 function perf_test()
 {
         USE_DMA=$1
@@ -520,6 +544,29 @@ function ntb_pingpong_tests()
         _modprobe -r ntb_pingpong
 }
 
+function ntb_msi_tests()
+{
+        LOCAL_MSI="$DEBUGFS/ntb_msi_test/$LOCAL_DEV"
+        REMOTE_MSI="$REMOTE_HOST:$DEBUGFS/ntb_msi_test/$REMOTE_DEV"
+
+        echo "Starting ntb_msi_test tests..."
+
+        if ! _modprobe ntb_msi_test 2> /dev/null; then
+                echo "  Not doing MSI tests seeing the module is not available."
+                return
+        fi
+
+        port_test $LOCAL_MSI $REMOTE_MSI
+
+        LOCAL_PEER="$LOCAL_MSI/peer$LOCAL_PIDX"
+        REMOTE_PEER="$REMOTE_MSI/peer$REMOTE_PIDX"
+
+        msi_test $LOCAL_PEER $REMOTE_PEER
+        msi_test $REMOTE_PEER $LOCAL_PEER
+
+        _modprobe -r ntb_msi_test
+}
+
 function ntb_perf_tests()
 {
         LOCAL_PERF="$DEBUGFS/ntb_perf/$LOCAL_DEV"
@@ -541,6 +588,7 @@ function cleanup()
         _modprobe -r ntb_perf 2> /dev/null
         _modprobe -r ntb_pingpong 2> /dev/null
         _modprobe -r ntb_transport 2> /dev/null
+        _modprobe -r ntb_msi_test 2> /dev/null
         set -e
 }
 
@@ -577,5 +625,7 @@ ntb_tool_tests
 echo
 ntb_pingpong_tests
 echo
+ntb_msi_tests
+echo
 ntb_perf_tests
 echo
diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore
index d503b8764a8e..7101ffd08d66 100644
--- a/tools/testing/selftests/powerpc/mm/.gitignore
+++ b/tools/testing/selftests/powerpc/mm/.gitignore
@@ -4,4 +4,4 @@ tempfile
 prot_sao
 segv_errors
 wild_bctr
-large_vm_fork_separation
\ No newline at end of file
+large_vm_fork_separation
diff --git a/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h b/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h
index d2c0a911f55e..2b488b78c4f2 100644
--- a/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h
+++ b/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _PPC_ASM_H
-#define __PPC_ASM_H
+#define _PPC_ASM_H
 #include <ppc-asm.h>
 
 #ifndef r1
diff --git a/tools/testing/selftests/powerpc/tm/tm-vmxcopy.c b/tools/testing/selftests/powerpc/tm/tm-vmxcopy.c
index 147c6dc4eb0b..c1e788a6df47 100644
--- a/tools/testing/selftests/powerpc/tm/tm-vmxcopy.c
+++ b/tools/testing/selftests/powerpc/tm/tm-vmxcopy.c
@@ -79,7 +79,7 @@ int test_vmxcopy()
 
                 "5:;"
                 "stxvd2x 40,0,%[vecoutptr];"
-                : [res]"=r"(aborted)
+                : [res]"=&r"(aborted)
                 : [vecinptr]"r"(&vecin),
                   [vecoutptr]"r"(&vecout),
                   [map]"r"(a)
diff --git a/tools/testing/selftests/powerpc/vphn/Makefile b/tools/testing/selftests/powerpc/vphn/Makefile
index 18b885da01bd..cf65cbf33085 100644
--- a/tools/testing/selftests/powerpc/vphn/Makefile
+++ b/tools/testing/selftests/powerpc/vphn/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 TEST_GEN_PROGS := test-vphn
 
-CFLAGS += -m64
+CFLAGS += -m64 -I$(CURDIR)
 
 top_srcdir = ../../../../..
 include ../../lib.mk
diff --git a/tools/testing/selftests/powerpc/vphn/asm/lppaca.h b/tools/testing/selftests/powerpc/vphn/asm/lppaca.h
new file mode 120000
index 000000000000..942b1d00999c
--- /dev/null
+++ b/tools/testing/selftests/powerpc/vphn/asm/lppaca.h
@@ -0,0 +1 @@
+../../../../../../arch/powerpc/include/asm/lppaca.h
\ No newline at end of file
diff --git a/tools/testing/selftests/powerpc/vphn/vphn.c b/tools/testing/selftests/powerpc/vphn/vphn.c
index 1d1f5f2be3b2..5b5fbddccabd 120000
--- a/tools/testing/selftests/powerpc/vphn/vphn.c
+++ b/tools/testing/selftests/powerpc/vphn/vphn.c
@@ -1 +1 @@
-../../../../../arch/powerpc/mm/book3s64/vphn.c
\ No newline at end of file
+../../../../../arch/powerpc/platforms/pseries/vphn.c
\ No newline at end of file
diff --git a/tools/testing/selftests/powerpc/vphn/vphn.h b/tools/testing/selftests/powerpc/vphn/vphn.h
deleted file mode 120000
index 45fe160f8288..000000000000
--- a/tools/testing/selftests/powerpc/vphn/vphn.h
+++ /dev/null
@@ -1 +0,0 @@
-../../../../../arch/powerpc/mm/book3s64/vphn.h
\ No newline at end of file
diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selftests/proc/.gitignore
index 444ad39d3700..66fab4c58ed4 100644
--- a/tools/testing/selftests/proc/.gitignore
+++ b/tools/testing/selftests/proc/.gitignore
@@ -12,4 +12,5 @@
 /read
 /self
 /setns-dcache
+/setns-sysvipc
 /thread-self
diff --git a/tools/testing/selftests/proc/Makefile b/tools/testing/selftests/proc/Makefile
index 9f09fcd09ea3..a8ed0f684829 100644
--- a/tools/testing/selftests/proc/Makefile
+++ b/tools/testing/selftests/proc/Makefile
@@ -17,6 +17,7 @@ TEST_GEN_PROGS += proc-uptime-002
 TEST_GEN_PROGS += read
 TEST_GEN_PROGS += self
 TEST_GEN_PROGS += setns-dcache
+TEST_GEN_PROGS += setns-sysvipc
 TEST_GEN_PROGS += thread-self
 
 include ../lib.mk
diff --git a/tools/testing/selftests/proc/proc-pid-vm.c b/tools/testing/selftests/proc/proc-pid-vm.c
index 853aa164a401..18a3bde8bc96 100644
--- a/tools/testing/selftests/proc/proc-pid-vm.c
+++ b/tools/testing/selftests/proc/proc-pid-vm.c
@@ -215,6 +215,11 @@ static const char str_vsyscall[] =
 "ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0                  [vsyscall]\n";
 
 #ifdef __x86_64__
+static void sigaction_SIGSEGV(int _, siginfo_t *__, void *___)
+{
+        _exit(1);
+}
+
 /*
  * vsyscall page can't be unmapped, probe it with memory load.
  */
@@ -231,11 +236,19 @@ static void vsyscall(void)
         if (pid == 0) {
                 struct rlimit rlim = {0, 0};
                 (void)setrlimit(RLIMIT_CORE, &rlim);
+
+                /* Hide "segfault at ffffffffff600000" messages. */
+                struct sigaction act;
+                memset(&act, 0, sizeof(struct sigaction));
+                act.sa_flags = SA_SIGINFO;
+                act.sa_sigaction = sigaction_SIGSEGV;
+                (void)sigaction(SIGSEGV, &act, NULL);
+
                 *(volatile int *)0xffffffffff600000UL;
                 exit(0);
         }
-        wait(&wstatus);
-        if (WIFEXITED(wstatus)) {
+        waitpid(pid, &wstatus, 0);
+        if (WIFEXITED(wstatus) && WEXITSTATUS(wstatus) == 0) {
                 g_vsyscall = true;
         }
 }
diff --git a/tools/testing/selftests/proc/setns-sysvipc.c b/tools/testing/selftests/proc/setns-sysvipc.c
new file mode 100644
index 000000000000..903890c5e587
--- /dev/null
+++ b/tools/testing/selftests/proc/setns-sysvipc.c
@@ -0,0 +1,133 @@
+/*
+ * Copyright © 2019 Alexey Dobriyan <adobriyan@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+/*
+ * Test that setns(CLONE_NEWIPC) points to new /proc/sysvipc content even
+ * if old one is in dcache.
+ */
+#undef NDEBUG
+#include <assert.h>
+#include <errno.h>
+#include <stdio.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <sys/ipc.h>
+#include <sys/shm.h>
+
+static pid_t pid = -1;
+
+static void f(void)
+{
+        if (pid > 0) {
+                kill(pid, SIGTERM);
+        }
+}
+
+int main(void)
+{
+        int fd[2];
+        char _ = 0;
+        int nsfd;
+
+        atexit(f);
+
+        /* Check for priviledges and syscall availability straight away. */
+        if (unshare(CLONE_NEWIPC) == -1) {
+                if (errno == ENOSYS || errno == EPERM) {
+                        return 4;
+                }
+                return 1;
+        }
+        /* Distinguisher between two otherwise empty IPC namespaces. */
+        if (shmget(IPC_PRIVATE, 1, IPC_CREAT) == -1) {
+                return 1;
+        }
+
+        if (pipe(fd) == -1) {
+                return 1;
+        }
+
+        pid = fork();
+        if (pid == -1) {
+                return 1;
+        }
+
+        if (pid == 0) {
+                if (unshare(CLONE_NEWIPC) == -1) {
+                        return 1;
+                }
+
+                if (write(fd[1], &_, 1) != 1) {
+                        return 1;
+                }
+
+                pause();
+
+                return 0;
+        }
+
+        if (read(fd[0], &_, 1) != 1) {
+                return 1;
+        }
+
+        {
+                char buf[64];
+                snprintf(buf, sizeof(buf), "/proc/%u/ns/ipc", pid);
+                nsfd = open(buf, O_RDONLY);
+                if (nsfd == -1) {
+                        return 1;
+                }
+        }
+
+        /* Reliably pin dentry into dcache. */
+        (void)open("/proc/sysvipc/shm", O_RDONLY);
+
+        if (setns(nsfd, CLONE_NEWIPC) == -1) {
+                return 1;
+        }
+
+        kill(pid, SIGTERM);
+        pid = 0;
+
+        {
+                char buf[4096];
+                ssize_t rv;
+                int fd;
+
+                fd = open("/proc/sysvipc/shm", O_RDONLY);
+                if (fd == -1) {
+                        return 1;
+                }
+
+#define S32 "       key      shmid perms       size  cpid  lpid nattch   uid   gid  cuid  cgid      atime      dtime      ctime        rss       swap\n"
+#define S64 "       key      shmid perms                  size  cpid  lpid nattch   uid   gid  cuid  cgid      atime      dtime      ctime                   rss                  swap\n"
+                rv = read(fd, buf, sizeof(buf));
+                if (rv == strlen(S32)) {
+                        assert(memcmp(buf, S32, strlen(S32)) == 0);
+                } else if (rv == strlen(S64)) {
+                        assert(memcmp(buf, S64, strlen(S64)) == 0);
+                } else {
+                        assert(0);
+                }
+        }
+
+        return 0;
+}
diff --git a/tools/testing/selftests/ptrace/.gitignore b/tools/testing/selftests/ptrace/.gitignore
index b3e59d41fd82..cfcc49a7def7 100644
--- a/tools/testing/selftests/ptrace/.gitignore
+++ b/tools/testing/selftests/ptrace/.gitignore
@@ -1 +1,2 @@
+get_syscall_info
 peeksiginfo
diff --git a/tools/testing/selftests/ptrace/Makefile b/tools/testing/selftests/ptrace/Makefile
index cb21c76a18ca..c0b7f89f0930 100644
--- a/tools/testing/selftests/ptrace/Makefile
+++ b/tools/testing/selftests/ptrace/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 CFLAGS += -iquote../../../../include/uapi -Wall
 
-TEST_GEN_PROGS := peeksiginfo
+TEST_GEN_PROGS := get_syscall_info peeksiginfo
 
 include ../lib.mk
diff --git a/tools/testing/selftests/ptrace/get_syscall_info.c b/tools/testing/selftests/ptrace/get_syscall_info.c
new file mode 100644
index 000000000000..5bcd1c7b5be6
--- /dev/null
+++ b/tools/testing/selftests/ptrace/get_syscall_info.c
@@ -0,0 +1,271 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (c) 2018 Dmitry V. Levin <ldv@altlinux.org>
+ * All rights reserved.
+ *
+ * Check whether PTRACE_GET_SYSCALL_INFO semantics implemented in the kernel
+ * matches userspace expectations.
+ */
+
+#include "../kselftest_harness.h"
+#include <err.h>
+#include <signal.h>
+#include <asm/unistd.h>
+#include "linux/ptrace.h"
+
+static int
+kill_tracee(pid_t pid)
+{
+        if (!pid)
+                return 0;
+
+        int saved_errno = errno;
+
+        int rc = kill(pid, SIGKILL);
+
+        errno = saved_errno;
+        return rc;
+}
+
+static long
+sys_ptrace(int request, pid_t pid, unsigned long addr, unsigned long data)
+{
+        return syscall(__NR_ptrace, request, pid, addr, data);
+}
+
+#define LOG_KILL_TRACEE(fmt, ...)                               \
+        do {                                                    \
+                kill_tracee(pid);                               \
+                TH_LOG("wait #%d: " fmt,                        \
+                       ptrace_stop, ##__VA_ARGS__);             \
+        } while (0)
+
+TEST(get_syscall_info)
+{
+        static const unsigned long args[][7] = {
+                /* a sequence of architecture-agnostic syscalls */
+                {
+                        __NR_chdir,
+                        (unsigned long) "",
+                        0xbad1fed1,
+                        0xbad2fed2,
+                        0xbad3fed3,
+                        0xbad4fed4,
+                        0xbad5fed5
+                },
+                {
+                        __NR_gettid,
+                        0xcaf0bea0,
+                        0xcaf1bea1,
+                        0xcaf2bea2,
+                        0xcaf3bea3,
+                        0xcaf4bea4,
+                        0xcaf5bea5
+                },
+                {
+                        __NR_exit_group,
+                        0,
+                        0xfac1c0d1,
+                        0xfac2c0d2,
+                        0xfac3c0d3,
+                        0xfac4c0d4,
+                        0xfac5c0d5
+                }
+        };
+        const unsigned long *exp_args;
+
+        pid_t pid = fork();
+
+        ASSERT_LE(0, pid) {
+                TH_LOG("fork: %m");
+        }
+
+        if (pid == 0) {
+                /* get the pid before PTRACE_TRACEME */
+                pid = getpid();
+                ASSERT_EQ(0, sys_ptrace(PTRACE_TRACEME, 0, 0, 0)) {
+                        TH_LOG("PTRACE_TRACEME: %m");
+                }
+                ASSERT_EQ(0, kill(pid, SIGSTOP)) {
+                        /* cannot happen */
+                        TH_LOG("kill SIGSTOP: %m");
+                }
+                for (unsigned int i = 0; i < ARRAY_SIZE(args); ++i) {
+                        syscall(args[i][0],
+                                args[i][1], args[i][2], args[i][3],
+                                args[i][4], args[i][5], args[i][6]);
+                }
+                /* unreachable */
+                _exit(1);
+        }
+
+        const struct {
+                unsigned int is_error;
+                int rval;
+        } *exp_param, exit_param[] = {
+                { 1, -ENOENT }, /* chdir */
+                { 0, pid }      /* gettid */
+        };
+
+        unsigned int ptrace_stop;
+
+        for (ptrace_stop = 0; ; ++ptrace_stop) {
+                struct ptrace_syscall_info info = {
+                        .op = 0xff      /* invalid PTRACE_SYSCALL_INFO_* op */
+                };
+                const size_t size = sizeof(info);
+                const int expected_none_size =
+                        (void *) &info.entry - (void *) &info;
+                const int expected_entry_size =
+                        (void *) &info.entry.args[6] - (void *) &info;
+                const int expected_exit_size =
+                        (void *) (&info.exit.is_error + 1) -
+                        (void *) &info;
+                int status;
+                long rc;
+
+                ASSERT_EQ(pid, wait(&status)) {
+                        /* cannot happen */
+                        LOG_KILL_TRACEE("wait: %m");
+                }
+                if (WIFEXITED(status)) {
+                        pid = 0;        /* the tracee is no more */
+                        ASSERT_EQ(0, WEXITSTATUS(status));
+                        break;
+                }
+                ASSERT_FALSE(WIFSIGNALED(status)) {
+                        pid = 0;        /* the tracee is no more */
+                        LOG_KILL_TRACEE("unexpected signal %u",
+                                        WTERMSIG(status));
+                }
+                ASSERT_TRUE(WIFSTOPPED(status)) {
+                        /* cannot happen */
+                        LOG_KILL_TRACEE("unexpected wait status %#x", status);
+                }
+
+                switch (WSTOPSIG(status)) {
+                case SIGSTOP:
+                        ASSERT_EQ(0, ptrace_stop) {
+                                LOG_KILL_TRACEE("unexpected signal stop");
+                        }
+                        ASSERT_EQ(0, sys_ptrace(PTRACE_SETOPTIONS, pid, 0,
+                                                PTRACE_O_TRACESYSGOOD)) {
+                                LOG_KILL_TRACEE("PTRACE_SETOPTIONS: %m");
+                        }
+                        ASSERT_LT(0, (rc = sys_ptrace(PTRACE_GET_SYSCALL_INFO,
+                                                      pid, size,
+                                                      (unsigned long) &info))) {
+                                LOG_KILL_TRACEE("PTRACE_GET_SYSCALL_INFO: %m");
+                        }
+                        ASSERT_EQ(expected_none_size, rc) {
+                                LOG_KILL_TRACEE("signal stop mismatch");
+                        }
+                        ASSERT_EQ(PTRACE_SYSCALL_INFO_NONE, info.op) {
+                                LOG_KILL_TRACEE("signal stop mismatch");
+                        }
+                        ASSERT_TRUE(info.arch) {
+                                LOG_KILL_TRACEE("signal stop mismatch");
+                        }
+                        ASSERT_TRUE(info.instruction_pointer) {
+                                LOG_KILL_TRACEE("signal stop mismatch");
+                        }
+                        ASSERT_TRUE(info.stack_pointer) {
+                                LOG_KILL_TRACEE("signal stop mismatch");
+                        }
+                        break;
+
+                case SIGTRAP | 0x80:
+                        ASSERT_LT(0, (rc = sys_ptrace(PTRACE_GET_SYSCALL_INFO,
+                                                      pid, size,
+                                                      (unsigned long) &info))) {
+                                LOG_KILL_TRACEE("PTRACE_GET_SYSCALL_INFO: %m");
+                        }
+                        switch (ptrace_stop) {
+                        case 1: /* entering chdir */
+                        case 3: /* entering gettid */
+                        case 5: /* entering exit_group */
+                                exp_args = args[ptrace_stop / 2];
+                                ASSERT_EQ(expected_entry_size, rc) {
+                                        LOG_KILL_TRACEE("entry stop mismatch");
+                                }
+                                ASSERT_EQ(PTRACE_SYSCALL_INFO_ENTRY, info.op) {
+                                        LOG_KILL_TRACEE("entry stop mismatch");
+                                }
+                                ASSERT_TRUE(info.arch) {
+                                        LOG_KILL_TRACEE("entry stop mismatch");
+                                }
+                                ASSERT_TRUE(info.instruction_pointer) {
+                                        LOG_KILL_TRACEE("entry stop mismatch");
+                                }
+                                ASSERT_TRUE(info.stack_pointer) {
+                                        LOG_KILL_TRACEE("entry stop mismatch");
+                                }
+                                ASSERT_EQ(exp_args[0], info.entry.nr) {
+                                        LOG_KILL_TRACEE("entry stop mismatch");
+                                }
+                                ASSERT_EQ(exp_args[1], info.entry.args[0]) {
+                                        LOG_KILL_TRACEE("entry stop mismatch");
+                                }
+                                ASSERT_EQ(exp_args[2], info.entry.args[1]) {
+                                        LOG_KILL_TRACEE("entry stop mismatch");
+                                }
+                                ASSERT_EQ(exp_args[3], info.entry.args[2]) {
+                                        LOG_KILL_TRACEE("entry stop mismatch");
+                                }
+                                ASSERT_EQ(exp_args[4], info.entry.args[3]) {
+                                        LOG_KILL_TRACEE("entry stop mismatch");
+                                }
+                                ASSERT_EQ(exp_args[5], info.entry.args[4]) {
+                                        LOG_KILL_TRACEE("entry stop mismatch");
+                                }
+                                ASSERT_EQ(exp_args[6], info.entry.args[5]) {
+                                        LOG_KILL_TRACEE("entry stop mismatch");
+                                }
+                                break;
+                        case 2: /* exiting chdir */
+                        case 4: /* exiting gettid */
+                                exp_param = &exit_param[ptrace_stop / 2 - 1];
+                                ASSERT_EQ(expected_exit_size, rc) {
+                                        LOG_KILL_TRACEE("exit stop mismatch");
+                                }
+                                ASSERT_EQ(PTRACE_SYSCALL_INFO_EXIT, info.op) {
+                                        LOG_KILL_TRACEE("exit stop mismatch");
+                                }
+                                ASSERT_TRUE(info.arch) {
+                                        LOG_KILL_TRACEE("exit stop mismatch");
+                                }
+                                ASSERT_TRUE(info.instruction_pointer) {
+                                        LOG_KILL_TRACEE("exit stop mismatch");
+                                }
+                                ASSERT_TRUE(info.stack_pointer) {
+                                        LOG_KILL_TRACEE("exit stop mismatch");
+                                }
+                                ASSERT_EQ(exp_param->is_error,
+                                          info.exit.is_error) {
+                                        LOG_KILL_TRACEE("exit stop mismatch");
+                                }
+                                ASSERT_EQ(exp_param->rval, info.exit.rval) {
+                                        LOG_KILL_TRACEE("exit stop mismatch");
+                                }
+                                break;
+                        default:
+                                LOG_KILL_TRACEE("unexpected syscall stop");
+                                abort();
+                        }
+                        break;
+
+                default:
+                        LOG_KILL_TRACEE("unexpected stop signal %#x",
+                                        WSTOPSIG(status));
+                        abort();
+                }
+
+                ASSERT_EQ(0, sys_ptrace(PTRACE_SYSCALL, pid, 0, 0)) {
+                        LOG_KILL_TRACEE("PTRACE_SYSCALL: %m");
+                }
+        }
+
+        ASSERT_EQ(ARRAY_SIZE(args) * 2, ptrace_stop);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/safesetid/safesetid-test.c b/tools/testing/selftests/safesetid/safesetid-test.c
index 892c8e8b1b8b..8f40c6ecdad1 100644
--- a/tools/testing/selftests/safesetid/safesetid-test.c
+++ b/tools/testing/selftests/safesetid/safesetid-test.c
@@ -142,23 +142,19 @@ static void ensure_securityfs_mounted(void)
 
 static void write_policies(void)
 {
+        static char *policy_str =
+                "1:2\n"
+                "1:3\n"
+                "2:2\n"
+                "3:3\n";
         ssize_t written;
         int fd;
 
         fd = open(add_whitelist_policy_file, O_WRONLY);
         if (fd < 0)
                 die("cant open add_whitelist_policy file\n");
-        written = write(fd, "1:2", strlen("1:2"));
-        if (written != strlen("1:2")) {
-                if (written >= 0) {
-                        die("short write to %s\n", add_whitelist_policy_file);
-                } else {
-                        die("write to %s failed: %s\n",
-                                add_whitelist_policy_file, strerror(errno));
-                }
-        }
-        written = write(fd, "1:3", strlen("1:3"));
-        if (written != strlen("1:3")) {
+        written = write(fd, policy_str, strlen(policy_str));
+        if (written != strlen(policy_str)) {
                 if (written >= 0) {
                         die("short write to %s\n", add_whitelist_policy_file);
                 } else {
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index dc66fe852768..6ef7f16c4cf5 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -1775,13 +1775,18 @@ void tracer_ptrace(struct __test_metadata *_metadata, pid_t tracee,
         unsigned long msg;
         static bool entry;
 
-        /* Make sure we got an empty message. */
+        /*
+         * The traditional way to tell PTRACE_SYSCALL entry/exit
+         * is by counting.
+         */
+        entry = !entry;
+
+        /* Make sure we got an appropriate message. */
         ret = ptrace(PTRACE_GETEVENTMSG, tracee, NULL, &msg);
         EXPECT_EQ(0, ret);
-        EXPECT_EQ(0, msg);
+        EXPECT_EQ(entry ? PTRACE_EVENTMSG_SYSCALL_ENTRY
+                        : PTRACE_EVENTMSG_SYSCALL_EXIT, msg);
 
-        /* The only way to tell PTRACE_SYSCALL entry/exit is by counting. */
-        entry = !entry;
         if (!entry)
                 return;
 
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
index 45e7e89928a5..bf5ebf59c2d4 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
@@ -70,6 +70,123 @@
         "teardown": []
     },
     {
+        "id": "d4cd",
+        "name": "Add skbedit action with valid mark and mask",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit mark 1/0xaabb",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*: skbedit  mark 1/0xaabb",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "baa7",
+        "name": "Add skbedit action with valid mark and 32-bit maximum mask",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit mark 1/0xffffffff",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*: skbedit  mark 1/0xffffffff",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
+        "id": "62a5",
+        "name": "Add skbedit action with valid mark and mask exceeding 32-bit maximum",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit mark 1/0xaabbccddeeff112233",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*: skbedit  mark 1/0xaabbccddeeff112233",
+        "matchCount": "0",
+        "teardown": []
+    },
+    {
+        "id": "bc15",
+        "name": "Add skbedit action with valid mark and mask with invalid format",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action skbedit mark 1/-1234",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*: skbedit  mark 1/-1234",
+        "matchCount": "0",
+        "teardown": []
+    },
+    {
+        "id": "57c2",
+        "name": "Replace skbedit action with new mask",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action skbedit mark 1/0x11223344 index 1"
+        ],
+        "cmdUnderTest": "$TC actions replace action skbedit mark 1/0xaabb index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*: skbedit  mark 1/0xaabb",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
+    },
+    {
         "id": "081d",
         "name": "Add skbedit action with priority",
         "category": [
diff --git a/tools/testing/selftests/x86/fsgsbase.c b/tools/testing/selftests/x86/fsgsbase.c
index 5ab4c60c100e..15a329da59fa 100644
--- a/tools/testing/selftests/x86/fsgsbase.c
+++ b/tools/testing/selftests/x86/fsgsbase.c
@@ -489,25 +489,11 @@ static void test_ptrace_write_gsbase(void)
                  * selector value is changed or not by the GSBASE write in
                  * a ptracer.
                  */
-                if (gs != *shared_scratch) {
-                        nerrs++;
-                        printf("[FAIL]\tGS changed to %lx\n", gs);
-
-                        /*
-                         * On older kernels, poking a nonzero value into the
-                         * base would zero the selector.  On newer kernels,
-                         * this behavior has changed -- poking the base
-                         * changes only the base and, if FSGSBASE is not
-                         * available, this may have no effect.
-                         */
-                        if (gs == 0)
-                                printf("\tNote: this is expected behavior on older kernels.\n");
-                } else if (have_fsgsbase && (base != 0xFF)) {
-                        nerrs++;
-                        printf("[FAIL]\tGSBASE changed to %lx\n", base);
+                if (gs == 0 && base == 0xFF) {
+                        printf("[OK]\tGS was reset as expected\n");
                 } else {
-                        printf("[OK]\tGS remained 0x%hx%s", *shared_scratch, have_fsgsbase ? " and GSBASE changed to 0xFF" : "");
-                        printf("\n");
+                        nerrs++;
+                        printf("[FAIL]\tGS=0x%lx, GSBASE=0x%lx (should be 0, 0xFF)\n", gs, base);
                 }
         }
 
diff --git a/tools/testing/selftests/zram/README b/tools/testing/selftests/zram/README
index 7972cc512408..110b34834a6f 100644
--- a/tools/testing/selftests/zram/README
+++ b/tools/testing/selftests/zram/README
@@ -37,4 +37,4 @@ Commands required for testing:
  - mkfs/ mkfs.ext4
 
 For more information please refer:
-kernel-source-tree/Documentation/blockdev/zram.txt
+kernel-source-tree/Documentation/admin-guide/blockdev/zram.rst