Merge branch 'linus' into x86/asm, to pick up fixes before applying new changes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

18 files changed, 186 insertions, 100 deletions

diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 2975632d51e2..c8fe6d177119 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -41,6 +41,7 @@ FEATURE_TESTS ?=			\
         libelf-getphdrnum               \
         libelf-mmap                     \
         libnuma                         \
+        numa_num_possible_cpus          \
         libperl                         \
         libpython                       \
         libpython-version               \
@@ -51,7 +52,8 @@ FEATURE_TESTS ?=			\
         timerfd                         \
         libdw-dwarf-unwind              \
         zlib                            \
-        lzma
+        lzma                            \
+        get_cpuid
 
 FEATURE_DISPLAY ?=                      \
         dwarf                           \
@@ -61,13 +63,15 @@ FEATURE_DISPLAY ?=			\
         libbfd                          \
         libelf                          \
         libnuma                         \
+        numa_num_possible_cpus          \
         libperl                         \
         libpython                       \
         libslang                        \
         libunwind                       \
         libdw-dwarf-unwind              \
         zlib                            \
-        lzma
+        lzma                            \
+        get_cpuid
 
 # Set FEATURE_CHECK_(C|LD)FLAGS-all for all FEATURE_TESTS features.
 # If in the future we need per-feature checks/flags for features not
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 74ca42093d70..e43a2971bf56 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -19,6 +19,7 @@ FILES=					\
         test-libelf-getphdrnum.bin      \
         test-libelf-mmap.bin            \
         test-libnuma.bin                \
+        test-numa_num_possible_cpus.bin \
         test-libperl.bin                \
         test-libpython.bin              \
         test-libpython-version.bin      \
@@ -34,7 +35,8 @@ FILES=					\
         test-compile-x32.bin            \
         test-zlib.bin                   \
         test-lzma.bin                   \
-        test-bpf.bin
+        test-bpf.bin                    \
+        test-get_cpuid.bin
 
 CC := $(CROSS_COMPILE)gcc -MD
 PKG_CONFIG := $(CROSS_COMPILE)pkg-config
@@ -87,6 +89,9 @@ test-libelf-getphdrnum.bin:
 test-libnuma.bin:
         $(BUILD) -lnuma
 
+test-numa_num_possible_cpus.bin:
+        $(BUILD) -lnuma
+
 test-libunwind.bin:
         $(BUILD) -lelf
 
@@ -162,6 +167,9 @@ test-zlib.bin:
 test-lzma.bin:
         $(BUILD) -llzma
 
+test-get_cpuid.bin:
+        $(BUILD)
+
 test-bpf.bin:
         $(BUILD)
 
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 84689a67814a..33cf6f20bd4e 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -77,6 +77,10 @@
 # include "test-libnuma.c"
 #undef main
 
+#define main main_test_numa_num_possible_cpus
+# include "test-numa_num_possible_cpus.c"
+#undef main
+
 #define main main_test_timerfd
 # include "test-timerfd.c"
 #undef main
@@ -117,6 +121,10 @@
 # include "test-lzma.c"
 #undef main
 
+#define main main_test_get_cpuid
+# include "test-get_cpuid.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
         main_test_libpython();
@@ -136,6 +144,7 @@ int main(int argc, char *argv[])
         main_test_libbfd();
         main_test_backtrace();
         main_test_libnuma();
+        main_test_numa_num_possible_cpus();
         main_test_timerfd();
         main_test_stackprotector_all();
         main_test_libdw_dwarf_unwind();
@@ -143,6 +152,7 @@ int main(int argc, char *argv[])
         main_test_zlib();
         main_test_pthread_attr_setaffinity_np();
         main_test_lzma();
+        main_test_get_cpuid();
 
         return 0;
 }
diff --git a/tools/build/feature/test-get_cpuid.c b/tools/build/feature/test-get_cpuid.c
new file mode 100644
index 000000000000..d7a2c407130d
--- /dev/null
+++ b/tools/build/feature/test-get_cpuid.c
@@ -0,0 +1,7 @@
+#include <cpuid.h>
+
+int main(void)
+{
+        unsigned int eax = 0, ebx = 0, ecx = 0, edx = 0;
+        return __get_cpuid(0x15, &eax, &ebx, &ecx, &edx);
+}
diff --git a/tools/build/feature/test-numa_num_possible_cpus.c b/tools/build/feature/test-numa_num_possible_cpus.c
new file mode 100644
index 000000000000..2606e94b0659
--- /dev/null
+++ b/tools/build/feature/test-numa_num_possible_cpus.c
@@ -0,0 +1,6 @@
+#include <numa.h>
+
+int main(void)
+{
+        return numa_num_possible_cpus();
+}
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 4d885934b919..cf42b090477b 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -3795,7 +3795,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
         struct format_field *field;
         struct printk_map *printk;
         long long val, fval;
-        unsigned long addr;
+        unsigned long long addr;
         char *str;
         unsigned char *hex;
         int print;
@@ -3828,13 +3828,30 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
                  */
                 if (!(field->flags & FIELD_IS_ARRAY) &&
                     field->size == pevent->long_size) {
-                        addr = *(unsigned long *)(data + field->offset);
+
+                        /* Handle heterogeneous recording and processing
+                         * architectures
+                         *
+                         * CASE I:
+                         * Traces recorded on 32-bit devices (32-bit
+                         * addressing) and processed on 64-bit devices:
+                         * In this case, only 32 bits should be read.
+                         *
+                         * CASE II:
+                         * Traces recorded on 64 bit devices and processed
+                         * on 32-bit devices:
+                         * In this case, 64 bits must be read.
+                         */
+                        addr = (pevent->long_size == 8) ?
+                                *(unsigned long long *)(data + field->offset) :
+                                (unsigned long long)*(unsigned int *)(data + field->offset);
+
                         /* Check if it matches a print format */
                         printk = find_printk(pevent, addr);
                         if (printk)
                                 trace_seq_puts(s, printk->printk);
                         else
-                                trace_seq_printf(s, "%lx", addr);
+                                trace_seq_printf(s, "%llx", addr);
                         break;
                 }
                 str = malloc(len + 1);
diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
index 4a0501d7a3b4..c94c9de3173e 100644
--- a/tools/perf/Documentation/intel-pt.txt
+++ b/tools/perf/Documentation/intel-pt.txt
@@ -364,21 +364,6 @@ cyc_thresh	Specifies how frequently CYC packets are produced - see cyc
 
                 CYC packets are not requested by default.
 
-no_force_psb    This is a driver option and is not in the IA32_RTIT_CTL MSR.
-
-                It stops the driver resetting the byte count to zero whenever
-                enabling the trace (for example on context switches) which in
-                turn results in no PSB being forced.  However some processors
-                will produce a PSB anyway.
-
-                In any case, there is still a PSB when the trace is enabled for
-                the first time.
-
-                no_force_psb can be used to slightly decrease the trace size but
-                may make it harder for the decoder to recover from errors.
-
-                no_force_psb is not selected by default.
-
 
 new snapshot option
 -------------------
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 827557fc7511..38a08539f4bf 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -573,9 +573,14 @@ ifndef NO_LIBNUMA
     msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numactl-devel/libnuma-devel/libnuma-dev);
     NO_LIBNUMA := 1
   else
-    CFLAGS += -DHAVE_LIBNUMA_SUPPORT
-    EXTLIBS += -lnuma
-    $(call detected,CONFIG_NUMA)
+    ifeq ($(feature-numa_num_possible_cpus), 0)
+      msg := $(warning Old numa library found, disables 'perf bench numa mem' benchmark, please install numactl-devel/libnuma-devel/libnuma-dev >= 2.0.8);
+      NO_LIBNUMA := 1
+    else
+      CFLAGS += -DHAVE_LIBNUMA_SUPPORT
+      EXTLIBS += -lnuma
+      $(call detected,CONFIG_NUMA)
+    endif
   endif
 endif
 
@@ -621,8 +626,13 @@ ifdef LIBBABELTRACE
 endif
 
 ifndef NO_AUXTRACE
-  $(call detected,CONFIG_AUXTRACE)
-  CFLAGS += -DHAVE_AUXTRACE_SUPPORT
+  ifeq ($(feature-get_cpuid), 0)
+    msg := $(warning Your gcc lacks the __get_cpuid() builtin, disables support for auxtrace/Intel PT, please install a newer gcc);
+    NO_AUXTRACE := 1
+  else
+    $(call detected,CONFIG_AUXTRACE)
+    CFLAGS += -DHAVE_AUXTRACE_SUPPORT
+  endif
 endif
 
 # Among the variables below, these:
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index eb5f18b75402..c6f9af78f6f5 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -270,12 +270,13 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso)
         int ret = 0;
 
         if (module) {
-                list_for_each_entry(dso, &host_machine->dsos.head, node) {
-                        if (!dso->kernel)
-                                continue;
-                        if (strncmp(dso->short_name + 1, module,
-                                    dso->short_name_len - 2) == 0)
-                                goto found;
+                char module_name[128];
+
+                snprintf(module_name, sizeof(module_name), "[%s]", module);
+                map = map_groups__find_by_name(&host_machine->kmaps, MAP__FUNCTION, module_name);
+                if (map) {
+                        dso = map->dso;
+                        goto found;
                 }
                 pr_debug("Failed to find module %s.\n", module);
                 return -ENOENT;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 8a4537ee9bc3..fc3f7c922f99 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1580,7 +1580,10 @@ static int __perf_session__process_events(struct perf_session *session,
         file_offset = page_offset;
         head = data_offset - page_offset;
 
-        if (data_size && (data_offset + data_size < file_size))
+        if (data_size == 0)
+                goto out;
+
+        if (data_offset + data_size < file_size)
                 file_size = data_offset + data_size;
 
         ui_progress__init(&prog, file_size, "Processing events...");
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 415c359de465..2d065d065b67 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -196,7 +196,8 @@ static void zero_per_pkg(struct perf_evsel *counter)
                 memset(counter->per_pkg_mask, 0, MAX_NR_CPUS);
 }
 
-static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip)
+static int check_per_pkg(struct perf_evsel *counter,
+                         struct perf_counts_values *vals, int cpu, bool *skip)
 {
         unsigned long *mask = counter->per_pkg_mask;
         struct cpu_map *cpus = perf_evsel__cpus(counter);
@@ -218,6 +219,17 @@ static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip)
                 counter->per_pkg_mask = mask;
         }
 
+        /*
+         * we do not consider an event that has not run as a good
+         * instance to mark a package as used (skip=1). Otherwise
+         * we may run into a situation where the first CPU in a package
+         * is not running anything, yet the second is, and this function
+         * would mark the package as used after the first CPU and would
+         * not read the values from the second CPU.
+         */
+        if (!(vals->run && vals->ena))
+                return 0;
+
         s = cpu_map__get_socket(cpus, cpu);
         if (s < 0)
                 return -1;
@@ -235,7 +247,7 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel
         static struct perf_counts_values zero;
         bool skip = false;
 
-        if (check_per_pkg(evsel, cpu, &skip)) {
+        if (check_per_pkg(evsel, count, cpu, &skip)) {
                 pr_err("failed to read per-pkg counter\n");
                 return -1;
         }
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 53bb5f59ec58..475d88d0a1c9 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -38,7 +38,7 @@ static inline char *bfd_demangle(void __maybe_unused *v,
 #endif
 
 #ifndef HAVE_ELF_GETPHDRNUM_SUPPORT
-int elf_getphdrnum(Elf *elf, size_t *dst)
+static int elf_getphdrnum(Elf *elf, size_t *dst)
 {
         GElf_Ehdr gehdr;
         GElf_Ehdr *ehdr;
@@ -1271,8 +1271,6 @@ out_close:
 static int kcore__init(struct kcore *kcore, char *filename, int elfclass,
                        bool temp)
 {
-        GElf_Ehdr *ehdr;
-
         kcore->elfclass = elfclass;
 
         if (temp)
@@ -1289,9 +1287,7 @@ static int kcore__init(struct kcore *kcore, char *filename, int elfclass,
         if (!gelf_newehdr(kcore->elf, elfclass))
                 goto out_end;
 
-        ehdr = gelf_getehdr(kcore->elf, &kcore->ehdr);
-        if (!ehdr)
-                goto out_end;
+        memset(&kcore->ehdr, 0, sizeof(GElf_Ehdr));
 
         return 0;
 
@@ -1348,23 +1344,18 @@ static int kcore__copy_hdr(struct kcore *from, struct kcore *to, size_t count)
 static int kcore__add_phdr(struct kcore *kcore, int idx, off_t offset,
                            u64 addr, u64 len)
 {
-        GElf_Phdr gphdr;
-        GElf_Phdr *phdr;
-
-        phdr = gelf_getphdr(kcore->elf, idx, &gphdr);
-        if (!phdr)
-                return -1;
-
-        phdr->p_type    = PT_LOAD;
-        phdr->p_flags   = PF_R | PF_W | PF_X;
-        phdr->p_offset  = offset;
-        phdr->p_vaddr   = addr;
-        phdr->p_paddr   = 0;
-        phdr->p_filesz  = len;
-        phdr->p_memsz   = len;
-        phdr->p_align   = page_size;
-
-        if (!gelf_update_phdr(kcore->elf, idx, phdr))
+        GElf_Phdr phdr = {
+                .p_type         = PT_LOAD,
+                .p_flags        = PF_R | PF_W | PF_X,
+                .p_offset       = offset,
+                .p_vaddr        = addr,
+                .p_paddr        = 0,
+                .p_filesz       = len,
+                .p_memsz        = len,
+                .p_align        = page_size,
+        };
+
+        if (!gelf_update_phdr(kcore->elf, idx, &phdr))
                 return -1;
 
         return 0;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 7acafb3c5592..c2cd9bf2348b 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -709,7 +709,7 @@ bool find_process(const char *name)
 
         dir = opendir(procfs__mountpoint());
         if (!dir)
-                return -1;
+                return false;
 
         /* Walk through the directory. */
         while (ret && (d = readdir(dir)) != NULL) {
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 9655cb49c7cb..bde0ef1a63df 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -71,8 +71,11 @@ unsigned int extra_msr_offset32;
 unsigned int extra_msr_offset64;
 unsigned int extra_delta_offset32;
 unsigned int extra_delta_offset64;
+unsigned int aperf_mperf_multiplier = 1;
 int do_smi;
 double bclk;
+double base_hz;
+double tsc_tweak = 1.0;
 unsigned int show_pkg;
 unsigned int show_core;
 unsigned int show_cpu;
@@ -502,7 +505,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
         /* %Busy */
         if (has_aperf) {
                 if (!skip_c0)
-                        outp += sprintf(outp, "%8.2f", 100.0 * t->mperf/t->tsc);
+                        outp += sprintf(outp, "%8.2f", 100.0 * t->mperf/t->tsc/tsc_tweak);
                 else
                         outp += sprintf(outp, "********");
         }
@@ -510,7 +513,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
         /* Bzy_MHz */
         if (has_aperf)
                 outp += sprintf(outp, "%8.0f",
-                        1.0 * t->tsc / units * t->aperf / t->mperf / interval_float);
+                        1.0 * t->tsc * tsc_tweak / units * t->aperf / t->mperf / interval_float);
 
         /* TSC_MHz */
         outp += sprintf(outp, "%8.0f", 1.0 * t->tsc/units/interval_float);
@@ -984,6 +987,8 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
                         return -3;
                 if (get_msr(cpu, MSR_IA32_MPERF, &t->mperf))
                         return -4;
+                t->aperf = t->aperf * aperf_mperf_multiplier;
+                t->mperf = t->mperf * aperf_mperf_multiplier;
         }
 
         if (do_smi) {
@@ -1149,6 +1154,19 @@ int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV,
 int amt_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 
+
+static void
+calculate_tsc_tweak()
+{
+        unsigned long long msr;
+        unsigned int base_ratio;
+
+        get_msr(base_cpu, MSR_NHM_PLATFORM_INFO, &msr);
+        base_ratio = (msr >> 8) & 0xFF;
+        base_hz = base_ratio * bclk * 1000000;
+        tsc_tweak = base_hz / tsc_hz;
+}
+
 static void
 dump_nhm_platform_info(void)
 {
@@ -1926,8 +1944,6 @@ int has_config_tdp(unsigned int family, unsigned int model)
 
         switch (model) {
         case 0x3A:      /* IVB */
-        case 0x3E:      /* IVB Xeon */
-
         case 0x3C:      /* HSW */
         case 0x3F:      /* HSX */
         case 0x45:      /* HSW */
@@ -2543,6 +2559,13 @@ int is_knl(unsigned int family, unsigned int model)
         return 0;
 }
 
+unsigned int get_aperf_mperf_multiplier(unsigned int family, unsigned int model)
+{
+        if (is_knl(family, model))
+                return 1024;
+        return 1;
+}
+
 #define SLM_BCLK_FREQS 5
 double slm_freq_table[SLM_BCLK_FREQS] = { 83.3, 100.0, 133.3, 116.7, 80.0};
 
@@ -2744,6 +2767,9 @@ void process_cpuid()
                 }
         }
 
+        if (has_aperf)
+                aperf_mperf_multiplier = get_aperf_mperf_multiplier(family, model);
+
         do_nhm_platform_info = do_nhm_cstates = do_smi = probe_nhm_msrs(family, model);
         do_snb_cstates = has_snb_msrs(family, model);
         do_pc2 = do_snb_cstates && (pkg_cstate_limit >= PCL__2);
@@ -2762,6 +2788,9 @@ void process_cpuid()
         if (debug)
                 dump_cstate_pstate_config_info();
 
+        if (has_skl_msrs(family, model))
+                calculate_tsc_tweak();
+
         return;
 }
 
@@ -3090,7 +3119,7 @@ int get_and_dump_counters(void)
 }
 
 void print_version() {
-        fprintf(stderr, "turbostat version 4.7 17-June, 2015"
+        fprintf(stderr, "turbostat version 4.8 26-Sep, 2015"
                 " - Len Brown <lenb@kernel.org>\n");
 }
 
diff --git a/tools/testing/selftests/membarrier/Makefile b/tools/testing/selftests/membarrier/Makefile
index 877a50355d7f..a1a97085847d 100644
--- a/tools/testing/selftests/membarrier/Makefile
+++ b/tools/testing/selftests/membarrier/Makefile
@@ -1,11 +1,10 @@
 CFLAGS += -g -I../../../../usr/include/
 
-all:
-        $(CC) $(CFLAGS) membarrier_test.c -o membarrier_test
-
 TEST_PROGS := membarrier_test
 
+all: $(TEST_PROGS)
+
 include ../lib.mk
 
 clean:
-        $(RM) membarrier_test
+        $(RM) $(TEST_PROGS)
diff --git a/tools/testing/selftests/membarrier/membarrier_test.c b/tools/testing/selftests/membarrier/membarrier_test.c
index dde312508007..535f0fef4d0b 100644
--- a/tools/testing/selftests/membarrier/membarrier_test.c
+++ b/tools/testing/selftests/membarrier/membarrier_test.c
@@ -1,9 +1,6 @@
 #define _GNU_SOURCE
-#define __EXPORTED_HEADERS__
-
 #include <linux/membarrier.h>
-#include <asm-generic/unistd.h>
-#include <sys/syscall.h>
+#include <syscall.h>
 #include <stdio.h>
 #include <errno.h>
 #include <string.h>
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index d36fab7d8ebd..3c53cac15de1 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -1,6 +1,6 @@
 # Makefile for vm selftests
 
-CFLAGS = -Wall
+CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS)
 BINARIES = compaction_test
 BINARIES += hugepage-mmap
 BINARIES += hugepage-shm
@@ -12,8 +12,11 @@ BINARIES += userfaultfd
 all: $(BINARIES)
 %: %.c
         $(CC) $(CFLAGS) -o $@ $^ -lrt
-userfaultfd: userfaultfd.c
-        $(CC) $(CFLAGS) -O2 -o $@ $^ -lpthread
+userfaultfd: userfaultfd.c ../../../../usr/include/linux/kernel.h
+        $(CC) $(CFLAGS) -O2 -o $@ $< -lpthread
+
+../../../../usr/include/linux/kernel.h:
+        make -C ../../../.. headers_install
 
 TEST_PROGS := run_vmtests
 TEST_FILES := $(BINARIES)
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index 7c1d958857d2..d77ed41b2094 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -64,19 +64,9 @@
 #include <sys/syscall.h>
 #include <sys/ioctl.h>
 #include <pthread.h>
-#include "../../../../include/uapi/linux/userfaultfd.h"
-
-#ifdef __x86_64__
-#define __NR_userfaultfd 323
-#elif defined(__i386__)
-#define __NR_userfaultfd 374
-#elif defined(__powewrpc__)
-#define __NR_userfaultfd 364
-#elif defined(__s390__)
-#define __NR_userfaultfd 355
-#else
-#error "missing __NR_userfaultfd definition"
-#endif
+#include <linux/userfaultfd.h>
+
+#ifdef __NR_userfaultfd
 
 static unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size;
 
@@ -432,7 +422,7 @@ static int userfaultfd_stress(void)
         struct uffdio_register uffdio_register;
         struct uffdio_api uffdio_api;
         unsigned long cpu;
-        int uffd_flags;
+        int uffd_flags, err;
         unsigned long userfaults[nr_cpus];
 
         if (posix_memalign(&area, page_size, nr_pages * page_size)) {
@@ -475,6 +465,14 @@ static int userfaultfd_stress(void)
                 *area_mutex(area_src, nr) = (pthread_mutex_t)
                         PTHREAD_MUTEX_INITIALIZER;
                 count_verify[nr] = *area_count(area_src, nr) = 1;
+                /*
+                 * In the transition between 255 to 256, powerpc will
+                 * read out of order in my_bcmp and see both bytes as
+                 * zero, so leave a placeholder below always non-zero
+                 * after the count, to avoid my_bcmp to trigger false
+                 * positives.
+                 */
+                *(area_count(area_src, nr) + 1) = 1;
         }
 
         pipefd = malloc(sizeof(int) * nr_cpus * 2);
@@ -501,6 +499,7 @@ static int userfaultfd_stress(void)
         pthread_attr_init(&attr);
         pthread_attr_setstacksize(&attr, 16*1024*1024);
 
+        err = 0;
         while (bounces--) {
                 unsigned long expected_ioctls;
 
@@ -581,20 +580,13 @@ static int userfaultfd_stress(void)
                 /* verification */
                 if (bounces & BOUNCE_VERIFY) {
                         for (nr = 0; nr < nr_pages; nr++) {
-                                if (my_bcmp(area_dst,
-                                            area_dst + nr * page_size,
-                                            sizeof(pthread_mutex_t))) {
-                                        fprintf(stderr,
-                                                "error mutex 2 %lu\n",
-                                                nr);
-                                        bounces = 0;
-                                }
                                 if (*area_count(area_dst, nr) != count_verify[nr]) {
                                         fprintf(stderr,
                                                 "error area_count %Lu %Lu %lu\n",
                                                 *area_count(area_src, nr),
                                                 count_verify[nr],
                                                 nr);
+                                        err = 1;
                                         bounces = 0;
                                 }
                         }
@@ -611,7 +603,7 @@ static int userfaultfd_stress(void)
                 printf("\n");
         }
 
-        return 0;
+        return err;
 }
 
 int main(int argc, char **argv)
@@ -620,8 +612,8 @@ int main(int argc, char **argv)
                 fprintf(stderr, "Usage: <MiB> <bounces>\n"), exit(1);
         nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
         page_size = sysconf(_SC_PAGE_SIZE);
-        if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) >
-            page_size)
+        if ((unsigned long) area_count(NULL, 0) + sizeof(unsigned long long) * 2
+            > page_size)
                 fprintf(stderr, "Impossible to run this test\n"), exit(2);
         nr_pages_per_cpu = atol(argv[1]) * 1024*1024 / page_size /
                 nr_cpus;
@@ -639,3 +631,15 @@ int main(int argc, char **argv)
                nr_pages, nr_pages_per_cpu);
         return userfaultfd_stress();
 }
+
+#else /* __NR_userfaultfd */
+
+#warning "missing __NR_userfaultfd definition"
+
+int main(void)
+{
+        printf("skip: Skipping userfaultfd test (missing __NR_userfaultfd)\n");
+        return 0;
+}
+
+#endif /* __NR_userfaultfd */