37 files changed, 413 insertions, 103 deletions

diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index f209ea151dca..3051f86a9b5f 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -87,9 +87,11 @@ struct kvm_regs {
 /* Supported VGICv3 address types  */
 #define KVM_VGIC_V3_ADDR_TYPE_DIST      2
 #define KVM_VGIC_V3_ADDR_TYPE_REDIST    3
+#define KVM_VGIC_ITS_ADDR_TYPE          4
 
 #define KVM_VGIC_V3_DIST_SIZE           SZ_64K
 #define KVM_VGIC_V3_REDIST_SIZE         (2 * SZ_64K)
+#define KVM_VGIC_V3_ITS_SIZE            (2 * SZ_64K)
 
 #define KVM_ARM_VCPU_POWER_OFF          0 /* CPU is started in OFF state */
 #define KVM_ARM_VCPU_EL1_32BIT          1 /* CPU running a 32bit VM */
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 3b8e99ef9d58..a2ffec4139ad 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -93,6 +93,47 @@ struct kvm_s390_vm_cpu_machine {
         __u64 fac_list[256];
 };
 
+#define KVM_S390_VM_CPU_PROCESSOR_FEAT  2
+#define KVM_S390_VM_CPU_MACHINE_FEAT    3
+
+#define KVM_S390_VM_CPU_FEAT_NR_BITS    1024
+#define KVM_S390_VM_CPU_FEAT_ESOP       0
+#define KVM_S390_VM_CPU_FEAT_SIEF2      1
+#define KVM_S390_VM_CPU_FEAT_64BSCAO    2
+#define KVM_S390_VM_CPU_FEAT_SIIF       3
+#define KVM_S390_VM_CPU_FEAT_GPERE      4
+#define KVM_S390_VM_CPU_FEAT_GSLS       5
+#define KVM_S390_VM_CPU_FEAT_IB         6
+#define KVM_S390_VM_CPU_FEAT_CEI        7
+#define KVM_S390_VM_CPU_FEAT_IBS        8
+#define KVM_S390_VM_CPU_FEAT_SKEY       9
+#define KVM_S390_VM_CPU_FEAT_CMMA       10
+#define KVM_S390_VM_CPU_FEAT_PFMFI      11
+#define KVM_S390_VM_CPU_FEAT_SIGPIF     12
+struct kvm_s390_vm_cpu_feat {
+        __u64 feat[16];
+};
+
+#define KVM_S390_VM_CPU_PROCESSOR_SUBFUNC       4
+#define KVM_S390_VM_CPU_MACHINE_SUBFUNC         5
+/* for "test bit" instructions MSB 0 bit ordering, for "query" raw blocks */
+struct kvm_s390_vm_cpu_subfunc {
+        __u8 plo[32];           /* always */
+        __u8 ptff[16];          /* with TOD-clock steering */
+        __u8 kmac[16];          /* with MSA */
+        __u8 kmc[16];           /* with MSA */
+        __u8 km[16];            /* with MSA */
+        __u8 kimd[16];          /* with MSA */
+        __u8 klmd[16];          /* with MSA */
+        __u8 pckmo[16];         /* with MSA3 */
+        __u8 kmctr[16];         /* with MSA4 */
+        __u8 kmf[16];           /* with MSA4 */
+        __u8 kmo[16];           /* with MSA4 */
+        __u8 pcc[16];           /* with MSA4 */
+        __u8 ppno[16];          /* with MSA5 */
+        __u8 reserved[1824];
+};
+
 /* kvm attributes for crypto */
 #define KVM_S390_VM_CRYPTO_ENABLE_AES_KW        0
 #define KVM_S390_VM_CRYPTO_ENABLE_DEA_KW        1
diff --git a/tools/arch/s390/include/uapi/asm/sie.h b/tools/arch/s390/include/uapi/asm/sie.h
index 8fb5d4a6dd25..3ac634368939 100644
--- a/tools/arch/s390/include/uapi/asm/sie.h
+++ b/tools/arch/s390/include/uapi/asm/sie.h
@@ -140,6 +140,7 @@
         exit_code_ipa0(0xB2, 0x4c, "TAR"),      \
         exit_code_ipa0(0xB2, 0x50, "CSP"),      \
         exit_code_ipa0(0xB2, 0x54, "MVPG"),     \
+        exit_code_ipa0(0xB2, 0x56, "STHYI"),    \
         exit_code_ipa0(0xB2, 0x58, "BSG"),      \
         exit_code_ipa0(0xB2, 0x5a, "BSA"),      \
         exit_code_ipa0(0xB2, 0x5f, "CHSC"),     \
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 4a413485f9eb..92a8308b96f6 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -225,7 +225,6 @@
 #define X86_FEATURE_RDSEED      ( 9*32+18) /* The RDSEED instruction */
 #define X86_FEATURE_ADX         ( 9*32+19) /* The ADCX and ADOX instructions */
 #define X86_FEATURE_SMAP        ( 9*32+20) /* Supervisor Mode Access Prevention */
-#define X86_FEATURE_PCOMMIT     ( 9*32+22) /* PCOMMIT instruction */
 #define X86_FEATURE_CLFLUSHOPT  ( 9*32+23) /* CLFLUSHOPT instruction */
 #define X86_FEATURE_CLWB        ( 9*32+24) /* CLWB instruction */
 #define X86_FEATURE_AVX512PF    ( 9*32+26) /* AVX-512 Prefetch */
@@ -301,10 +300,6 @@
 #define X86_BUG_FXSAVE_LEAK     X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
 #define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
 #define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
-#define X86_BUG_NULL_SEG        X86_BUG(9) /* Nulling a selector preserves the base */
-#define X86_BUG_SWAPGS_FENCE    X86_BUG(10) /* SWAPGS without input dep on GS */
-
-
 #ifdef CONFIG_X86_32
 /*
  * 64-bit kernels don't use X86_BUG_ESPFIX.  Make the define conditional
@@ -312,5 +307,7 @@
  */
 #define X86_BUG_ESPFIX          X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */
 #endif
-
+#define X86_BUG_NULL_SEG        X86_BUG(10) /* Nulling a selector preserves the base */
+#define X86_BUG_SWAPGS_FENCE    X86_BUG(11) /* SWAPGS without input dep on GS */
+#define X86_BUG_MONITOR         X86_BUG(12) /* IPI required to wake up remote CPU */
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 911e9358ceb1..85599ad4d024 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -56,5 +56,7 @@
 #define DISABLED_MASK14 0
 #define DISABLED_MASK15 0
 #define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE)
+#define DISABLED_MASK17 0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
 
 #endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h
index 4916144e3c42..fac9a5c0abe9 100644
--- a/tools/arch/x86/include/asm/required-features.h
+++ b/tools/arch/x86/include/asm/required-features.h
@@ -99,5 +99,7 @@
 #define REQUIRED_MASK14 0
 #define REQUIRED_MASK15 0
 #define REQUIRED_MASK16 0
+#define REQUIRED_MASK17 0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
 
 #endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index 5b15d94a33f8..37fee272618f 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -78,7 +78,6 @@
 #define EXIT_REASON_PML_FULL            62
 #define EXIT_REASON_XSAVES              63
 #define EXIT_REASON_XRSTORS             64
-#define EXIT_REASON_PCOMMIT             65
 
 #define VMX_EXIT_REASONS \
         { EXIT_REASON_EXCEPTION_NMI,         "EXCEPTION_NMI" }, \
@@ -127,8 +126,7 @@
         { EXIT_REASON_INVVPID,               "INVVPID" }, \
         { EXIT_REASON_INVPCID,               "INVPCID" }, \
         { EXIT_REASON_XSAVES,                "XSAVES" }, \
-        { EXIT_REASON_XRSTORS,               "XRSTORS" }, \
-        { EXIT_REASON_PCOMMIT,               "PCOMMIT" }
+        { EXIT_REASON_XRSTORS,               "XRSTORS" }
 
 #define VMX_ABORT_SAVE_GUEST_MSR_FAIL        1
 #define VMX_ABORT_LOAD_HOST_MSR_FAIL         4
diff --git a/tools/gpio/gpio-event-mon.c b/tools/gpio/gpio-event-mon.c
index 448ed96b3b4f..1c14c2595158 100644
--- a/tools/gpio/gpio-event-mon.c
+++ b/tools/gpio/gpio-event-mon.c
@@ -1,5 +1,5 @@
 /*
- * gpio-hammer - example swiss army knife to shake GPIO lines on a system
+ * gpio-event-mon - monitor GPIO line events from userspace
  *
  * Copyright (C) 2016 Linus Walleij
  *
diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h
index b96879477311..f436d2420a18 100644
--- a/tools/include/linux/string.h
+++ b/tools/include/linux/string.h
@@ -8,7 +8,11 @@ void *memdup(const void *src, size_t len);
 
 int strtobool(const char *s, bool *res);
 
-#ifdef __GLIBC__
+/*
+ * glibc based builds needs the extern while uClibc doesn't.
+ * However uClibc headers also define __GLIBC__ hence the hack below
+ */
+#if defined(__GLIBC__) && !defined(__UCLIBC__)
 extern size_t strlcpy(char *dest, const char *src, size_t size);
 #endif
 
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 406459b935a2..da218fec6056 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -84,6 +84,7 @@ enum bpf_map_type {
         BPF_MAP_TYPE_PERCPU_HASH,
         BPF_MAP_TYPE_PERCPU_ARRAY,
         BPF_MAP_TYPE_STACK_TRACE,
+        BPF_MAP_TYPE_CGROUP_ARRAY,
 };
 
 enum bpf_prog_type {
@@ -93,6 +94,7 @@ enum bpf_prog_type {
         BPF_PROG_TYPE_SCHED_CLS,
         BPF_PROG_TYPE_SCHED_ACT,
         BPF_PROG_TYPE_TRACEPOINT,
+        BPF_PROG_TYPE_XDP,
 };
 
 #define BPF_PSEUDO_MAP_FD       1
@@ -313,6 +315,66 @@ enum bpf_func_id {
          */
         BPF_FUNC_skb_get_tunnel_opt,
         BPF_FUNC_skb_set_tunnel_opt,
+
+        /**
+         * bpf_skb_change_proto(skb, proto, flags)
+         * Change protocol of the skb. Currently supported is
+         * v4 -> v6, v6 -> v4 transitions. The helper will also
+         * resize the skb. eBPF program is expected to fill the
+         * new headers via skb_store_bytes and lX_csum_replace.
+         * @skb: pointer to skb
+         * @proto: new skb->protocol type
+         * @flags: reserved
+         * Return: 0 on success or negative error
+         */
+        BPF_FUNC_skb_change_proto,
+
+        /**
+         * bpf_skb_change_type(skb, type)
+         * Change packet type of skb.
+         * @skb: pointer to skb
+         * @type: new skb->pkt_type type
+         * Return: 0 on success or negative error
+         */
+        BPF_FUNC_skb_change_type,
+
+        /**
+         * bpf_skb_in_cgroup(skb, map, index) - Check cgroup2 membership of skb
+         * @skb: pointer to skb
+         * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
+         * @index: index of the cgroup in the bpf_map
+         * Return:
+         *   == 0 skb failed the cgroup2 descendant test
+         *   == 1 skb succeeded the cgroup2 descendant test
+         *    < 0 error
+         */
+        BPF_FUNC_skb_in_cgroup,
+
+        /**
+         * bpf_get_hash_recalc(skb)
+         * Retrieve and possibly recalculate skb->hash.
+         * @skb: pointer to skb
+         * Return: hash
+         */
+        BPF_FUNC_get_hash_recalc,
+
+        /**
+         * u64 bpf_get_current_task(void)
+         * Returns current task_struct
+         * Return: current
+         */
+        BPF_FUNC_get_current_task,
+
+        /**
+         * bpf_probe_write_user(void *dst, void *src, int len)
+         * safely attempt to write to a location
+         * @dst: destination address in userspace
+         * @src: source address on stack
+         * @len: number of bytes to copy
+         * Return: 0 on success or negative error
+         */
+        BPF_FUNC_probe_write_user,
+
         __BPF_FUNC_MAX_ID,
 };
 
@@ -347,9 +409,11 @@ enum bpf_func_id {
 #define BPF_F_ZERO_CSUM_TX              (1ULL << 1)
 #define BPF_F_DONT_FRAGMENT             (1ULL << 2)
 
-/* BPF_FUNC_perf_event_output flags. */
+/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */
 #define BPF_F_INDEX_MASK                0xffffffffULL
 #define BPF_F_CURRENT_CPU               BPF_F_INDEX_MASK
+/* BPF_FUNC_perf_event_output for sk_buff input context. */
+#define BPF_F_CTXLEN_MASK               (0xfffffULL << 32)
 
 /* user accessible mirror of in-kernel sk_buff.
  * new fields can only be added to the end of this structure
@@ -386,4 +450,24 @@ struct bpf_tunnel_key {
         __u32 tunnel_label;
 };
 
+/* User return codes for XDP prog type.
+ * A valid XDP program must return one of these defined values. All other
+ * return codes are reserved for future use. Unknown return codes will result
+ * in packet drop.
+ */
+enum xdp_action {
+        XDP_ABORTED = 0,
+        XDP_DROP,
+        XDP_PASS,
+        XDP_TX,
+};
+
+/* user accessible metadata for XDP packet hook
+ * new fields must be added to the end of this structure
+ */
+struct xdp_md {
+        __u32 data;
+        __u32 data_end;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 736da44596e4..b303bcdd8ed1 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -176,10 +176,18 @@ Each probe argument follows below syntax.
 
 '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. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type.
+'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), 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.
 
+TYPES
+-----
+Basic types (u8/u16/u32/u64/s8/s16/s32/s64) are integer types. Prefix 's' and 'u' means those types are signed and unsigned respectively. Traced arguments are shown in decimal (signed) or hex (unsigned). You can also use 's' or 'u' to specify only signedness and leave its size auto-detected by perf probe.
+String type is a special type, which fetches a "null-terminated" string from kernel space. This means it will fail and store NULL if the string container has been paged out. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type.
+Bitfield is another special type, which takes 3 parameters, bit-width, bit-offset, and container-size (usually 32). The syntax is;
+
+ b<bit-width>@<bit-offset>/<container-size>
+
 LINE SYNTAX
 -----------
 Line range is described by following syntax.
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 1f6c70594f0f..053bbbd84ece 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -116,8 +116,8 @@ OPTIONS
 --fields::
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
-        srcline, period, iregs, brstack, brstacksym, flags.
-        Field list can be prepended with the type, trace, sw or hw,
+        srcline, period, iregs, brstack, brstacksym, flags, bpf-output,
+        callindent. Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -F sw:comm,tid,time,ip,sym  and -F trace:time,cpu,trace
 
diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c
index c6d0f91731a1..35745a733100 100644
--- a/tools/perf/arch/powerpc/util/sym-handling.c
+++ b/tools/perf/arch/powerpc/util/sym-handling.c
@@ -54,10 +54,6 @@ int arch__compare_symbol_names(const char *namea, const char *nameb)
 #endif
 
 #if defined(_CALL_ELF) && _CALL_ELF == 2
-bool arch__prefers_symtab(void)
-{
-        return true;
-}
 
 #ifdef HAVE_LIBELF_SUPPORT
 void arch__sym_update(struct symbol *s, GElf_Sym *sym)
@@ -100,4 +96,29 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev,
                         tev->point.offset += lep_offset;
         }
 }
+
+#ifdef HAVE_LIBELF_SUPPORT
+void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
+                                           int ntevs)
+{
+        struct probe_trace_event *tev;
+        struct map *map;
+        struct symbol *sym = NULL;
+        struct rb_node *tmp;
+        int i = 0;
+
+        map = get_target_map(pev->target, pev->uprobes);
+        if (!map || map__load(map, NULL) < 0)
+                return;
+
+        for (i = 0; i < ntevs; i++) {
+                tev = &pev->tevs[i];
+                map__for_each_symbol(map, sym, tmp) {
+                        if (map->unmap_ip(map, sym->start) == tev->point.address)
+                                arch__fix_tev_from_maps(pev, tev, map, sym);
+                }
+        }
+}
+#endif /* HAVE_LIBELF_SUPPORT */
+
 #endif
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index fb51457ba338..a2412e9d883b 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -501,7 +501,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
         struct intel_pt_recording *ptr =
                         container_of(itr, struct intel_pt_recording, itr);
         struct perf_pmu *intel_pt_pmu = ptr->intel_pt_pmu;
-        bool have_timing_info;
+        bool have_timing_info, need_immediate = false;
         struct perf_evsel *evsel, *intel_pt_evsel = NULL;
         const struct cpu_map *cpus = evlist->cpus;
         bool privileged = geteuid() == 0 || perf_event_paranoid() < 0;
@@ -655,6 +655,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
                                 ptr->have_sched_switch = 3;
                         } else {
                                 opts->record_switch_events = true;
+                                need_immediate = true;
                                 if (cpu_wide)
                                         ptr->have_sched_switch = 3;
                                 else
@@ -700,6 +701,9 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
                 tracking_evsel->attr.freq = 0;
                 tracking_evsel->attr.sample_period = 1;
 
+                if (need_immediate)
+                        tracking_evsel->immediate = true;
+
                 /* In per-cpu case, always need the time of mmap events etc */
                 if (!cpu_map__empty(cpus)) {
                         perf_evsel__set_sample_bit(tracking_evsel, TIME);
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index d608a2c9e48c..d1ce29be560e 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -88,6 +88,9 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
         if (mem->operation & MEM_OPERATION_LOAD)
                 perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true;
 
+        if (mem->operation & MEM_OPERATION_STORE)
+                perf_mem_events[PERF_MEM_EVENTS__STORE].record = true;
+
         if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record)
                 rec_argv[i++] = "-W";
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 971ff91b16cb..c859e59dfe3e 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -371,14 +371,16 @@ static int perf_session__check_output_opt(struct perf_session *session)
 
         if (!no_callchain) {
                 bool use_callchain = false;
+                bool not_pipe = false;
 
                 evlist__for_each_entry(session->evlist, evsel) {
+                        not_pipe = true;
                         if (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
                                 use_callchain = true;
                                 break;
                         }
                 }
-                if (!use_callchain)
+                if (not_pipe && !use_callchain)
                         symbol_conf.use_callchain = false;
         }
 
@@ -1690,8 +1692,13 @@ static int list_available_scripts(const struct option *opt __maybe_unused,
         snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path());
 
         scripts_dir = opendir(scripts_path);
-        if (!scripts_dir)
-                return -1;
+        if (!scripts_dir) {
+                fprintf(stdout,
+                        "open(%s) failed.\n"
+                        "Check \"PERF_EXEC_PATH\" env to set scripts dir.\n",
+                        scripts_path);
+                exit(-1);
+        }
 
         for_each_lang(scripts_path, scripts_dir, lang_dirent) {
                 snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
@@ -2116,7 +2123,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
                      "Valid types: hw,sw,trace,raw. "
                      "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
                      "addr,symoff,period,iregs,brstack,brstacksym,flags,"
-                     "callindent", parse_output_fields),
+                     "bpf-output,callindent", parse_output_fields),
         OPT_BOOLEAN('a', "all-cpus", &system_wide,
                     "system-wide collection from all CPUs"),
         OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 0c16d20d7e32..3c7452b39f57 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -331,7 +331,7 @@ static int read_counter(struct perf_evsel *counter)
         return 0;
 }
 
-static void read_counters(bool close_counters)
+static void read_counters(void)
 {
         struct perf_evsel *counter;
 
@@ -341,11 +341,6 @@ static void read_counters(bool close_counters)
 
                 if (perf_stat_process_counter(&stat_config, counter))
                         pr_warning("failed to process counter %s\n", counter->name);
-
-                if (close_counters) {
-                        perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
-                                             thread_map__nr(evsel_list->threads));
-                }
         }
 }
 
@@ -353,7 +348,7 @@ static void process_interval(void)
 {
         struct timespec ts, rs;
 
-        read_counters(false);
+        read_counters();
 
         clock_gettime(CLOCK_MONOTONIC, &ts);
         diff_timespec(&rs, &ts, &ref_time);
@@ -380,6 +375,17 @@ static void enable_counters(void)
                 perf_evlist__enable(evsel_list);
 }
 
+static void disable_counters(void)
+{
+        /*
+         * If we don't have tracee (attaching to task or cpu), counters may
+         * still be running. To get accurate group ratios, we must stop groups
+         * from counting before reading their constituent counters.
+         */
+        if (!target__none(&target))
+                perf_evlist__disable(evsel_list);
+}
+
 static volatile int workload_exec_errno;
 
 /*
@@ -657,11 +663,20 @@ try_again:
                 }
         }
 
+        disable_counters();
+
         t1 = rdclock();
 
         update_stats(&walltime_nsecs_stats, t1 - t0);
 
-        read_counters(true);
+        /*
+         * Closing a group leader splits the group, and as we only disable
+         * group leaders, results in remaining events becoming enabled. To
+         * avoid arbitrary skew, we must read all counters before closing any
+         * group leaders.
+         */
+        read_counters();
+        perf_evlist__close(evsel_list);
 
         return WEXITSTATUS(status);
 }
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index d9b80ef881cd..21fd573106ed 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -507,17 +507,17 @@ static int __perf_evsel__hw_cache_name(u64 config, char *bf, size_t size)
         u8 op, result, type = (config >>  0) & 0xff;
         const char *err = "unknown-ext-hardware-cache-type";
 
-        if (type > PERF_COUNT_HW_CACHE_MAX)
+        if (type >= PERF_COUNT_HW_CACHE_MAX)
                 goto out_err;
 
         op = (config >>  8) & 0xff;
         err = "unknown-ext-hardware-cache-op";
-        if (op > PERF_COUNT_HW_CACHE_OP_MAX)
+        if (op >= PERF_COUNT_HW_CACHE_OP_MAX)
                 goto out_err;
 
         result = (config >> 16) & 0xff;
         err = "unknown-ext-hardware-cache-result";
-        if (result > PERF_COUNT_HW_CACHE_RESULT_MAX)
+        if (result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
                 goto out_err;
 
         err = "invalid-cache";
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 9c8f15da86ce..8ff6c6a61291 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -123,8 +123,6 @@ struct intel_pt_decoder {
         bool have_calc_cyc_to_tsc;
         int exec_mode;
         unsigned int insn_bytes;
-        uint64_t sign_bit;
-        uint64_t sign_bits;
         uint64_t period;
         enum intel_pt_period_type period_type;
         uint64_t tot_insn_cnt;
@@ -191,9 +189,6 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params)
         decoder->data               = params->data;
         decoder->return_compression = params->return_compression;
 
-        decoder->sign_bit           = (uint64_t)1 << 47;
-        decoder->sign_bits          = ~(((uint64_t)1 << 48) - 1);
-
         decoder->period             = params->period;
         decoder->period_type        = params->period_type;
 
@@ -362,21 +357,30 @@ int intel_pt__strerror(int code, char *buf, size_t buflen)
         return 0;
 }
 
-static uint64_t intel_pt_calc_ip(struct intel_pt_decoder *decoder,
-                                 const struct intel_pt_pkt *packet,
+static uint64_t intel_pt_calc_ip(const struct intel_pt_pkt *packet,
                                  uint64_t last_ip)
 {
         uint64_t ip;
 
         switch (packet->count) {
-        case 2:
+        case 1:
                 ip = (last_ip & (uint64_t)0xffffffffffff0000ULL) |
                      packet->payload;
                 break;
-        case 4:
+        case 2:
                 ip = (last_ip & (uint64_t)0xffffffff00000000ULL) |
                      packet->payload;
                 break;
+        case 3:
+                ip = packet->payload;
+                /* Sign-extend 6-byte ip */
+                if (ip & (uint64_t)0x800000000000ULL)
+                        ip |= (uint64_t)0xffff000000000000ULL;
+                break;
+        case 4:
+                ip = (last_ip & (uint64_t)0xffff000000000000ULL) |
+                     packet->payload;
+                break;
         case 6:
                 ip = packet->payload;
                 break;
@@ -384,16 +388,12 @@ static uint64_t intel_pt_calc_ip(struct intel_pt_decoder *decoder,
                 return 0;
         }
 
-        if (ip & decoder->sign_bit)
-                return ip | decoder->sign_bits;
-
         return ip;
 }
 
 static inline void intel_pt_set_last_ip(struct intel_pt_decoder *decoder)
 {
-        decoder->last_ip = intel_pt_calc_ip(decoder, &decoder->packet,
-                                            decoder->last_ip);
+        decoder->last_ip = intel_pt_calc_ip(&decoder->packet, decoder->last_ip);
 }
 
 static inline void intel_pt_set_ip(struct intel_pt_decoder *decoder)
@@ -1657,6 +1657,12 @@ next:
         }
 }
 
+static inline bool intel_pt_have_ip(struct intel_pt_decoder *decoder)
+{
+        return decoder->last_ip || decoder->packet.count == 0 ||
+               decoder->packet.count == 3 || decoder->packet.count == 6;
+}
+
 /* Walk PSB+ packets to get in sync. */
 static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
 {
@@ -1677,8 +1683,7 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
 
                 case INTEL_PT_FUP:
                         decoder->pge = true;
-                        if (decoder->last_ip || decoder->packet.count == 6 ||
-                            decoder->packet.count == 0) {
+                        if (intel_pt_have_ip(decoder)) {
                                 uint64_t current_ip = decoder->ip;
 
                                 intel_pt_set_ip(decoder);
@@ -1767,8 +1772,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
                 case INTEL_PT_TIP_PGE:
                 case INTEL_PT_TIP:
                         decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD;
-                        if (decoder->last_ip || decoder->packet.count == 6 ||
-                            decoder->packet.count == 0)
+                        if (intel_pt_have_ip(decoder))
                                 intel_pt_set_ip(decoder);
                         if (decoder->ip)
                                 return 0;
@@ -1776,9 +1780,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
 
                 case INTEL_PT_FUP:
                         if (decoder->overflow) {
-                                if (decoder->last_ip ||
-                                    decoder->packet.count == 6 ||
-                                    decoder->packet.count == 0)
+                                if (intel_pt_have_ip(decoder))
                                         intel_pt_set_ip(decoder);
                                 if (decoder->ip)
                                         return 0;
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
index b1257c816310..4f7b32020487 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
@@ -292,36 +292,46 @@ static int intel_pt_get_ip(enum intel_pt_pkt_type type, unsigned int byte,
                            const unsigned char *buf, size_t len,
                            struct intel_pt_pkt *packet)
 {
-        switch (byte >> 5) {
+        int ip_len;
+
+        packet->count = byte >> 5;
+
+        switch (packet->count) {
         case 0:
-                packet->count = 0;
+                ip_len = 0;
                 break;
         case 1:
                 if (len < 3)
                         return INTEL_PT_NEED_MORE_BYTES;
-                packet->count = 2;
+                ip_len = 2;
                 packet->payload = le16_to_cpu(*(uint16_t *)(buf + 1));
                 break;
         case 2:
                 if (len < 5)
                         return INTEL_PT_NEED_MORE_BYTES;
-                packet->count = 4;
+                ip_len = 4;
                 packet->payload = le32_to_cpu(*(uint32_t *)(buf + 1));
                 break;
         case 3:
-        case 6:
+        case 4:
                 if (len < 7)
                         return INTEL_PT_NEED_MORE_BYTES;
-                packet->count = 6;
+                ip_len = 6;
                 memcpy_le64(&packet->payload, buf + 1, 6);
                 break;
+        case 6:
+                if (len < 9)
+                        return INTEL_PT_NEED_MORE_BYTES;
+                ip_len = 8;
+                packet->payload = le64_to_cpu(*(uint64_t *)(buf + 1));
+                break;
         default:
                 return INTEL_PT_BAD_PACKET;
         }
 
         packet->type = type;
 
-        return packet->count + 1;
+        return ip_len + 1;
 }
 
 static int intel_pt_get_mode(const unsigned char *buf, size_t len,
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index 9f3305f6b6d5..95f0884aae02 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -1,3 +1,4 @@
+#include <sys/sysmacros.h>
 #include <sys/types.h>
 #include <stdio.h>
 #include <stdlib.h>
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 953dc1ab2ed7..28733962cd80 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -170,15 +170,17 @@ static struct map *kernel_get_module_map(const char *module)
                 module = "kernel";
 
         for (pos = maps__first(maps); pos; pos = map__next(pos)) {
+                /* short_name is "[module]" */
                 if (strncmp(pos->dso->short_name + 1, module,
-                            pos->dso->short_name_len - 2) == 0) {
+                            pos->dso->short_name_len - 2) == 0 &&
+                    module[pos->dso->short_name_len - 2] == '\0') {
                         return pos;
                 }
         }
         return NULL;
 }
 
-static struct map *get_target_map(const char *target, bool user)
+struct map *get_target_map(const char *target, bool user)
 {
         /* Init maps of given executable or kernel */
         if (user)
@@ -385,7 +387,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo,
                 if (uprobes)
                         address = sym->start;
                 else
-                        address = map->unmap_ip(map, sym->start);
+                        address = map->unmap_ip(map, sym->start) - map->reloc;
                 break;
         }
         if (!address) {
@@ -664,22 +666,14 @@ static int add_module_to_probe_trace_events(struct probe_trace_event *tevs,
         return ret;
 }
 
-/* Post processing the probe events */
-static int post_process_probe_trace_events(struct probe_trace_event *tevs,
-                                           int ntevs, const char *module,
-                                           bool uprobe)
+static int
+post_process_kernel_probe_trace_events(struct probe_trace_event *tevs,
+                                       int ntevs)
 {
         struct ref_reloc_sym *reloc_sym;
         char *tmp;
         int i, skipped = 0;
 
-        if (uprobe)
-                return add_exec_to_probe_trace_events(tevs, ntevs, module);
-
-        /* Note that currently ref_reloc_sym based probe is not for drivers */
-        if (module)
-                return add_module_to_probe_trace_events(tevs, ntevs, module);
-
         reloc_sym = kernel_get_ref_reloc_sym();
         if (!reloc_sym) {
                 pr_warning("Relocated base symbol is not found!\n");
@@ -711,6 +705,34 @@ static int post_process_probe_trace_events(struct probe_trace_event *tevs,
         return skipped;
 }
 
+void __weak
+arch__post_process_probe_trace_events(struct perf_probe_event *pev __maybe_unused,
+                                      int ntevs __maybe_unused)
+{
+}
+
+/* Post processing the probe events */
+static int post_process_probe_trace_events(struct perf_probe_event *pev,
+                                           struct probe_trace_event *tevs,
+                                           int ntevs, const char *module,
+                                           bool uprobe)
+{
+        int ret;
+
+        if (uprobe)
+                ret = add_exec_to_probe_trace_events(tevs, ntevs, module);
+        else if (module)
+                /* Currently ref_reloc_sym based probe is not for drivers */
+                ret = add_module_to_probe_trace_events(tevs, ntevs, module);
+        else
+                ret = post_process_kernel_probe_trace_events(tevs, ntevs);
+
+        if (ret >= 0)
+                arch__post_process_probe_trace_events(pev, ntevs);
+
+        return ret;
+}
+
 /* Try to find perf_probe_event with debuginfo */
 static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
                                           struct probe_trace_event **tevs)
@@ -749,7 +771,7 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 
         if (ntevs > 0) {        /* Succeeded to find trace events */
                 pr_debug("Found %d probe_trace_events.\n", ntevs);
-                ret = post_process_probe_trace_events(*tevs, ntevs,
+                ret = post_process_probe_trace_events(pev, *tevs, ntevs,
                                                 pev->target, pev->uprobes);
                 if (ret < 0 || ret == ntevs) {
                         clear_probe_trace_events(*tevs, ntevs);
@@ -2936,8 +2958,6 @@ errout:
         return err;
 }
 
-bool __weak arch__prefers_symtab(void) { return false; }
-
 /* Concatinate two arrays */
 static void *memcat(void *a, size_t sz_a, void *b, size_t sz_b)
 {
@@ -3158,12 +3178,6 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev,
         if (ret > 0 || pev->sdt)        /* SDT can be found only in the cache */
                 return ret == 0 ? -ENOENT : ret; /* Found in probe cache */
 
-        if (arch__prefers_symtab() && !perf_probe_event_need_dwarf(pev)) {
-                ret = find_probe_trace_events_from_map(pev, tevs);
-                if (ret > 0)
-                        return ret; /* Found in symbol table */
-        }
-
         /* Convert perf_probe_event with debuginfo */
         ret = try_to_find_probe_trace_events(pev, tevs);
         if (ret != 0)
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index e18ea9fe6385..f4f45db77c1c 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -158,7 +158,6 @@ int show_line_range(struct line_range *lr, const char *module, bool user);
 int show_available_vars(struct perf_probe_event *pevs, int npevs,
                         struct strfilter *filter);
 int show_available_funcs(const char *module, struct strfilter *filter, bool user);
-bool arch__prefers_symtab(void);
 void arch__fix_tev_from_maps(struct perf_probe_event *pev,
                              struct probe_trace_event *tev, struct map *map,
                              struct symbol *sym);
@@ -173,4 +172,9 @@ int e_snprintf(char *str, size_t size, const char *format, ...)
 int copy_to_probe_trace_arg(struct probe_trace_arg *tvar,
                             struct perf_probe_arg *pvar);
 
+struct map *get_target_map(const char *target, bool user);
+
+void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
+                                           int ntevs);
+
 #endif /*_PROBE_EVENT_H */
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 9aed9c332da6..9c3b9ed5b3c3 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -133,7 +133,7 @@ int probe_file__open_both(int *kfd, int *ufd, int flag)
 /* Get raw string list of current kprobe_events  or uprobe_events */
 struct strlist *probe_file__get_rawlist(int fd)
 {
-        int ret, idx;
+        int ret, idx, fddup;
         FILE *fp;
         char buf[MAX_CMDLEN];
         char *p;
@@ -143,8 +143,17 @@ struct strlist *probe_file__get_rawlist(int fd)
                 return NULL;
 
         sl = strlist__new(NULL, NULL);
+        if (sl == NULL)
+                return NULL;
+
+        fddup = dup(fd);
+        if (fddup < 0)
+                goto out_free_sl;
+
+        fp = fdopen(fddup, "r");
+        if (!fp)
+                goto out_close_fddup;
 
-        fp = fdopen(dup(fd), "r");
         while (!feof(fp)) {
                 p = fgets(buf, MAX_CMDLEN, fp);
                 if (!p)
@@ -156,13 +165,21 @@ struct strlist *probe_file__get_rawlist(int fd)
                 ret = strlist__add(sl, buf);
                 if (ret < 0) {
                         pr_debug("strlist__add failed (%d)\n", ret);
-                        strlist__delete(sl);
-                        return NULL;
+                        goto out_close_fp;
                 }
         }
         fclose(fp);
 
         return sl;
+
+out_close_fp:
+        fclose(fp);
+        goto out_free_sl;
+out_close_fddup:
+        close(fddup);
+out_free_sl:
+        strlist__delete(sl);
+        return NULL;
 }
 
 static struct strlist *__probe_file__get_namelist(int fd, bool include_group)
@@ -447,12 +464,17 @@ static int probe_cache__load(struct probe_cache *pcache)
 {
         struct probe_cache_entry *entry = NULL;
         char buf[MAX_CMDLEN], *p;
-        int ret = 0;
+        int ret = 0, fddup;
         FILE *fp;
 
-        fp = fdopen(dup(pcache->fd), "r");
-        if (!fp)
+        fddup = dup(pcache->fd);
+        if (fddup < 0)
+                return -errno;
+        fp = fdopen(fddup, "r");
+        if (!fp) {
+                close(fddup);
                 return -EINVAL;
+        }
 
         while (!feof(fp)) {
                 if (!fgets(buf, MAX_CMDLEN, fp))
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index f2d9ff064e2d..5c290c682afe 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -297,10 +297,13 @@ static int convert_variable_type(Dwarf_Die *vr_die,
         char sbuf[STRERR_BUFSIZE];
         int bsize, boffs, total;
         int ret;
+        char sign;
 
         /* TODO: check all types */
-        if (cast && strcmp(cast, "string") != 0) {
+        if (cast && strcmp(cast, "string") != 0 &&
+            strcmp(cast, "s") != 0 && strcmp(cast, "u") != 0) {
                 /* Non string type is OK */
+                /* and respect signedness cast */
                 tvar->type = strdup(cast);
                 return (tvar->type == NULL) ? -ENOMEM : 0;
         }
@@ -361,6 +364,13 @@ static int convert_variable_type(Dwarf_Die *vr_die,
                 return (tvar->type == NULL) ? -ENOMEM : 0;
         }
 
+        if (cast && (strcmp(cast, "u") == 0))
+                sign = 'u';
+        else if (cast && (strcmp(cast, "s") == 0))
+                sign = 's';
+        else
+                sign = die_is_signed_type(&type) ? 's' : 'u';
+
         ret = dwarf_bytesize(&type);
         if (ret <= 0)
                 /* No size ... try to use default type */
@@ -373,8 +383,7 @@ static int convert_variable_type(Dwarf_Die *vr_die,
                         dwarf_diename(&type), MAX_BASIC_TYPE_BITS);
                 ret = MAX_BASIC_TYPE_BITS;
         }
-        ret = snprintf(buf, 16, "%c%d",
-                       die_is_signed_type(&type) ? 's' : 'u', ret);
+        ret = snprintf(buf, 16, "%c%d", sign, ret);
 
 formatted:
         if (ret < 0 || ret >= 16) {
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 947d21f38398..3d3cb8392c86 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -588,7 +588,11 @@ static char *get_trace_output(struct hist_entry *he)
         } else {
                 pevent_event_info(&seq, evsel->tp_format, &rec);
         }
-        return seq.buffer;
+        /*
+         * Trim the buffer, it starts at 4KB and we're not going to
+         * add anything more to this buffer.
+         */
+        return realloc(seq.buffer, seq.len + 1);
 }
 
 static int64_t
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index a34321e9b44d..a811c13a74d6 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -837,7 +837,8 @@ int dso__load_sym(struct dso *dso, struct map *map,
         sec = syms_ss->symtab;
         shdr = syms_ss->symshdr;
 
-        if (elf_section_by_name(elf, &ehdr, &tshdr, ".text", NULL))
+        if (elf_section_by_name(runtime_ss->elf, &runtime_ss->ehdr, &tshdr,
+                                ".text", NULL))
                 dso->text_offset = tshdr.sh_addr - tshdr.sh_offset;
 
         if (runtime_ss->opdsec)
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index cf5e250bc78e..783a53fb7a4e 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -66,7 +66,7 @@ static int entry(u64 ip, struct unwind_info *ui)
         if (__report_module(&al, ip, ui))
                 return -1;
 
-        e->ip  = ip;
+        e->ip  = al.addr;
         e->map = al.map;
         e->sym = al.sym;
 
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 97c0f8fc5561..20c2e5743903 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -542,7 +542,7 @@ static int entry(u64 ip, struct thread *thread,
         thread__find_addr_location(thread, PERF_RECORD_MISC_USER,
                                    MAP__FUNCTION, ip, &al);
 
-        e.ip = ip;
+        e.ip = al.addr;
         e.map = al.map;
         e.sym = al.sym;
 
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 5404efa578a3..dd48f421844c 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -13,6 +13,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
+#include <linux/workqueue.h>
 #include <linux/libnvdimm.h>
 #include <linux/vmalloc.h>
 #include <linux/device.h>
@@ -1474,6 +1475,7 @@ static int nfit_test_probe(struct platform_device *pdev)
         if (nfit_test->setup != nfit_test0_setup)
                 return 0;
 
+        flush_work(&acpi_desc->work);
         nfit_test->setup_hotplug = 1;
         nfit_test->setup(nfit_test);
 
diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile
index 3c40c9d0e6c7..1cc6d64c39b7 100644
--- a/tools/testing/selftests/powerpc/Makefile
+++ b/tools/testing/selftests/powerpc/Makefile
@@ -8,7 +8,7 @@ ifeq ($(ARCH),powerpc)
 
 GIT_VERSION = $(shell git describe --always --long --dirty || echo "unknown")
 
-CFLAGS := -Wall -O2 -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CURDIR) $(CFLAGS)
+CFLAGS := -std=gnu99 -Wall -O2 -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CURDIR) $(CFLAGS)
 
 export CFLAGS
 
diff --git a/tools/virtio/linux/dma-mapping.h b/tools/virtio/linux/dma-mapping.h
index 4f93af89ae16..18601f6689b9 100644
--- a/tools/virtio/linux/dma-mapping.h
+++ b/tools/virtio/linux/dma-mapping.h
@@ -14,4 +14,20 @@ enum dma_data_direction {
         DMA_NONE = 3,
 };
 
+#define dma_alloc_coherent(d, s, hp, f) ({ \
+        void *__dma_alloc_coherent_p = kmalloc((s), (f)); \
+        *(hp) = (unsigned long)__dma_alloc_coherent_p; \
+        __dma_alloc_coherent_p; \
+})
+
+#define dma_free_coherent(d, s, p, h) kfree(p)
+
+#define dma_map_page(d, p, o, s, dir) (page_to_phys(p) + (o))
+
+#define dma_map_single(d, p, s, dir) (virt_to_phys(p))
+#define dma_mapping_error(...) (0)
+
+#define dma_unmap_single(...) do { } while (0)
+#define dma_unmap_page(...) do { } while (0)
+
 #endif
diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h
index 033849948215..d9554fc3f340 100644
--- a/tools/virtio/linux/kernel.h
+++ b/tools/virtio/linux/kernel.h
@@ -20,7 +20,9 @@
 
 #define PAGE_SIZE getpagesize()
 #define PAGE_MASK (~(PAGE_SIZE-1))
+#define PAGE_ALIGN(x) ((x + PAGE_SIZE - 1) & PAGE_MASK)
 
+typedef unsigned long long phys_addr_t;
 typedef unsigned long long dma_addr_t;
 typedef size_t __kernel_size_t;
 typedef unsigned int __wsum;
@@ -57,6 +59,11 @@ static inline void *kzalloc(size_t s, gfp_t gfp)
         return p;
 }
 
+static inline void *alloc_pages_exact(size_t s, gfp_t gfp)
+{
+        return kmalloc(s, gfp);
+}
+
 static inline void kfree(void *p)
 {
         if (p >= __kfree_ignore_start && p < __kfree_ignore_end)
@@ -64,6 +71,11 @@ static inline void kfree(void *p)
         free(p);
 }
 
+static inline void free_pages_exact(void *p, size_t s)
+{
+        kfree(p);
+}
+
 static inline void *krealloc(void *p, size_t s, gfp_t gfp)
 {
         return realloc(p, s);
@@ -105,6 +117,8 @@ static inline void free_page(unsigned long addr)
 #define dev_err(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__)
 #define dev_warn(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__)
 
+#define WARN_ON_ONCE(cond) ((cond) && fprintf (stderr, "WARNING\n"))
+
 #define min(x, y) ({                            \
         typeof(x) _min1 = (x);                  \
         typeof(y) _min2 = (y);                  \
diff --git a/tools/virtio/linux/slab.h b/tools/virtio/linux/slab.h
index 81baeac8ae40..7e1c1197d439 100644
--- a/tools/virtio/linux/slab.h
+++ b/tools/virtio/linux/slab.h
@@ -1,2 +1,6 @@
 #ifndef LINUX_SLAB_H
+#define GFP_KERNEL 0
+#define GFP_ATOMIC 0
+#define __GFP_NOWARN 0
+#define __GFP_ZERO 0
 #endif
diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h
index ee125e714053..9377c8b4ac16 100644
--- a/tools/virtio/linux/virtio.h
+++ b/tools/virtio/linux/virtio.h
@@ -3,8 +3,12 @@
 #include <linux/scatterlist.h>
 #include <linux/kernel.h>
 
+struct device {
+        void *parent;
+};
+
 struct virtio_device {
-        void *dev;
+        struct device dev;
         u64 features;
 };
 
diff --git a/tools/virtio/linux/virtio_config.h b/tools/virtio/linux/virtio_config.h
index 57a6964a1e35..9ba11815e0a1 100644
--- a/tools/virtio/linux/virtio_config.h
+++ b/tools/virtio/linux/virtio_config.h
@@ -40,6 +40,19 @@ static inline void __virtio_clear_bit(struct virtio_device *vdev,
 #define virtio_has_feature(dev, feature) \
         (__virtio_test_bit((dev), feature))
 
+/**
+ * virtio_has_iommu_quirk - determine whether this device has the iommu quirk
+ * @vdev: the device
+ */
+static inline bool virtio_has_iommu_quirk(const struct virtio_device *vdev)
+{
+        /*
+         * Note the reverse polarity of the quirk feature (compared to most
+         * other features), this is for compatibility with legacy systems.
+         */
+        return !virtio_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM);
+}
+
 static inline bool virtio_is_little_endian(struct virtio_device *vdev)
 {
         return virtio_has_feature(vdev, VIRTIO_F_VERSION_1) ||
diff --git a/tools/virtio/ringtest/ptr_ring.c b/tools/virtio/ringtest/ptr_ring.c
index 68e4f9f0da3a..bd2ad1d3b7a9 100644
--- a/tools/virtio/ringtest/ptr_ring.c
+++ b/tools/virtio/ringtest/ptr_ring.c
@@ -13,6 +13,7 @@
 #define cache_line_size() SMP_CACHE_BYTES
 #define ____cacheline_aligned_in_smp __attribute__ ((aligned (SMP_CACHE_BYTES)))
 #define unlikely(x)    (__builtin_expect(!!(x), 0))
+#define likely(x)    (__builtin_expect(!!(x), 1))
 #define ALIGN(x, a) (((x) + (a) - 1) / (a) * (a))
 typedef pthread_spinlock_t  spinlock_t;