Merge schedutil governor updates for v4.10.

15 files changed, 103 insertions, 132 deletions

diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 1188bc849ee3..a39629206864 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -194,6 +194,8 @@
 #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
 
 #define X86_FEATURE_INTEL_PT    ( 7*32+15) /* Intel Processor Trace */
+#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
+#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index c0c0b265e88e..b63a31be1218 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -98,6 +98,15 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
                         *type = INSN_FP_SETUP;
                 break;
 
+        case 0x8d:
+                if (insn.rex_prefix.bytes &&
+                    insn.rex_prefix.bytes[0] == 0x48 &&
+                    insn.modrm.nbytes && insn.modrm.bytes[0] == 0x2c &&
+                    insn.sib.nbytes && insn.sib.bytes[0] == 0x24)
+                        /* lea %(rsp), %rbp */
+                        *type = INSN_FP_SETUP;
+                break;
+
         case 0x90:
                 *type = INSN_NOP;
                 break;
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index 143b6cdd7f06..e8a1f699058a 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -97,6 +97,19 @@ static struct instruction *next_insn_same_sec(struct objtool_file *file,
         return next;
 }
 
+static bool gcov_enabled(struct objtool_file *file)
+{
+        struct section *sec;
+        struct symbol *sym;
+
+        list_for_each_entry(sec, &file->elf->sections, list)
+                list_for_each_entry(sym, &sec->symbol_list, list)
+                        if (!strncmp(sym->name, "__gcov_.", 8))
+                                return true;
+
+        return false;
+}
+
 #define for_each_insn(file, insn)                                       \
         list_for_each_entry(insn, &file->insn_list, list)
 
@@ -713,6 +726,7 @@ static struct rela *find_switch_table(struct objtool_file *file,
                                       struct instruction *insn)
 {
         struct rela *text_rela, *rodata_rela;
+        struct instruction *orig_insn = insn;
 
         text_rela = find_rela_by_dest_range(insn->sec, insn->offset, insn->len);
         if (text_rela && text_rela->sym == file->rodata->sym) {
@@ -733,10 +747,16 @@ static struct rela *find_switch_table(struct objtool_file *file,
 
         /* case 3 */
         func_for_each_insn_continue_reverse(file, func, insn) {
-                if (insn->type == INSN_JUMP_UNCONDITIONAL ||
-                    insn->type == INSN_JUMP_DYNAMIC)
+                if (insn->type == INSN_JUMP_DYNAMIC)
                         break;
 
+                /* allow small jumps within the range */
+                if (insn->type == INSN_JUMP_UNCONDITIONAL &&
+                    insn->jump_dest &&
+                    (insn->jump_dest->offset <= insn->offset ||
+                     insn->jump_dest->offset > orig_insn->offset))
+                    break;
+
                 text_rela = find_rela_by_dest_range(insn->sec, insn->offset,
                                                     insn->len);
                 if (text_rela && text_rela->sym == file->rodata->sym)
@@ -1034,34 +1054,6 @@ static int validate_branch(struct objtool_file *file,
         return 0;
 }
 
-static bool is_gcov_insn(struct instruction *insn)
-{
-        struct rela *rela;
-        struct section *sec;
-        struct symbol *sym;
-        unsigned long offset;
-
-        rela = find_rela_by_dest_range(insn->sec, insn->offset, insn->len);
-        if (!rela)
-                return false;
-
-        if (rela->sym->type != STT_SECTION)
-                return false;
-
-        sec = rela->sym->sec;
-        offset = rela->addend + insn->offset + insn->len - rela->offset;
-
-        list_for_each_entry(sym, &sec->symbol_list, list) {
-                if (sym->type != STT_OBJECT)
-                        continue;
-
-                if (offset >= sym->offset && offset < sym->offset + sym->len)
-                        return (!memcmp(sym->name, "__gcov0.", 8));
-        }
-
-        return false;
-}
-
 static bool is_kasan_insn(struct instruction *insn)
 {
         return (insn->type == INSN_CALL &&
@@ -1083,9 +1075,6 @@ static bool ignore_unreachable_insn(struct symbol *func,
         if (insn->type == INSN_NOP)
                 return true;
 
-        if (is_gcov_insn(insn))
-                return true;
-
         /*
          * Check if this (or a subsequent) instruction is related to
          * CONFIG_UBSAN or CONFIG_KASAN.
@@ -1146,6 +1135,19 @@ static int validate_functions(struct objtool_file *file)
                                     ignore_unreachable_insn(func, insn))
                                         continue;
 
+                                /*
+                                 * gcov produces a lot of unreachable
+                                 * instructions.  If we get an unreachable
+                                 * warning and the file has gcov enabled, just
+                                 * ignore it, and all other such warnings for
+                                 * the file.
+                                 */
+                                if (!file->ignore_unreachables &&
+                                    gcov_enabled(file)) {
+                                        file->ignore_unreachables = true;
+                                        continue;
+                                }
+
                                 WARN_FUNC("function has unreachable instruction", insn->sec, insn->offset);
                                 warnings++;
                         }
diff --git a/tools/perf/jvmti/Makefile b/tools/perf/jvmti/Makefile
index 5ce61a1bda9c..df14e6b67b63 100644
--- a/tools/perf/jvmti/Makefile
+++ b/tools/perf/jvmti/Makefile
@@ -36,7 +36,7 @@ SOLIBEXT=so
 # The following works at least on fedora 23, you may need the next
 # line for other distros.
 ifneq (,$(wildcard /usr/sbin/update-java-alternatives))
-JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | cut -d ' ' -f 3)
+JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | awk '{print $$3}')
 else
   ifneq (,$(wildcard /usr/sbin/alternatives))
     JDIR=$(shell alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g')
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index fb8e42c7507a..4ffff7be9299 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -601,7 +601,8 @@ int hist_browser__run(struct hist_browser *browser, const char *help)
                         u64 nr_entries;
                         hbt->timer(hbt->arg);
 
-                        if (hist_browser__has_filter(browser))
+                        if (hist_browser__has_filter(browser) ||
+                            symbol_conf.report_hierarchy)
                                 hist_browser__update_nr_entries(browser);
 
                         nr_entries = hist_browser__nr_entries(browser);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 85dd0db0a127..2f3eded54b0c 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1895,7 +1895,6 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse
         if (ph->needs_swap)
                 nr = bswap_32(nr);
 
-        ph->env.nr_numa_nodes = nr;
         nodes = zalloc(sizeof(*nodes) * nr);
         if (!nodes)
                 return -ENOMEM;
@@ -1932,6 +1931,7 @@ static int process_numa_topology(struct perf_file_section *section __maybe_unuse
 
                 free(str);
         }
+        ph->env.nr_numa_nodes = nr;
         ph->env.numa_nodes = nodes;
         return 0;
 
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 9f43fda2570f..660fca05bc93 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -136,8 +136,8 @@ do {							\
 group           [^,{}/]*[{][^}]*[}][^,{}/]*
 event_pmu       [^,{}/]+[/][^/]*[/][^,{}/]*
 event           [^,{}/]+
-bpf_object      .*\.(o|bpf)
-bpf_source      .*\.c
+bpf_object      [^,{}]+\.(o|bpf)
+bpf_source      [^,{}]+\.c
 
 num_dec         [0-9]+
 num_hex         0x[a-fA-F0-9]+
diff --git a/tools/power/cpupower/utils/cpufreq-set.c b/tools/power/cpupower/utils/cpufreq-set.c
index b4bf76971dc9..1eef0aed6423 100644
--- a/tools/power/cpupower/utils/cpufreq-set.c
+++ b/tools/power/cpupower/utils/cpufreq-set.c
@@ -296,7 +296,7 @@ int cmd_freq_set(int argc, char **argv)
                         struct cpufreq_affected_cpus *cpus;
 
                         if (!bitmask_isbitset(cpus_chosen, cpu) ||
-                            cpupower_is_cpu_online(cpu))
+                            cpupower_is_cpu_online(cpu) != 1)
                                 continue;
 
                         cpus = cpufreq_get_related_cpus(cpu);
@@ -316,10 +316,7 @@ int cmd_freq_set(int argc, char **argv)
              cpu <= bitmask_last(cpus_chosen); cpu++) {
 
                 if (!bitmask_isbitset(cpus_chosen, cpu) ||
-                    cpupower_is_cpu_online(cpu))
-                        continue;
-
-                if (cpupower_is_cpu_online(cpu) != 1)
+                    cpupower_is_cpu_online(cpu) != 1)
                         continue;
 
                 printf(_("Setting cpu: %d\n"), cpu);
diff --git a/tools/virtio/ringtest/Makefile b/tools/virtio/ringtest/Makefile
index 877a8a4721b6..c012edbdb13b 100644
--- a/tools/virtio/ringtest/Makefile
+++ b/tools/virtio/ringtest/Makefile
@@ -3,8 +3,8 @@ all:
 all: ring virtio_ring_0_9 virtio_ring_poll virtio_ring_inorder ptr_ring noring
 
 CFLAGS += -Wall
-CFLAGS += -pthread -O2 -ggdb
-LDFLAGS += -pthread -O2 -ggdb
+CFLAGS += -pthread -O2 -ggdb -flto -fwhole-program
+LDFLAGS += -pthread -O2 -ggdb -flto -fwhole-program
 
 main.o: main.c main.h
 ring.o: ring.c main.h
diff --git a/tools/virtio/ringtest/main.c b/tools/virtio/ringtest/main.c
index 147abb452a6c..f31353fac541 100644
--- a/tools/virtio/ringtest/main.c
+++ b/tools/virtio/ringtest/main.c
@@ -96,7 +96,13 @@ void set_affinity(const char *arg)
         assert(!ret);
 }
 
-static void run_guest(void)
+void poll_used(void)
+{
+        while (used_empty())
+                busy_wait();
+}
+
+static void __attribute__((__flatten__)) run_guest(void)
 {
         int completed_before;
         int completed = 0;
@@ -141,7 +147,7 @@ static void run_guest(void)
                 assert(completed <= bufs);
                 assert(started <= bufs);
                 if (do_sleep) {
-                        if (enable_call())
+                        if (used_empty() && enable_call())
                                 wait_for_call();
                 } else {
                         poll_used();
@@ -149,7 +155,13 @@ static void run_guest(void)
         }
 }
 
-static void run_host(void)
+void poll_avail(void)
+{
+        while (avail_empty())
+                busy_wait();
+}
+
+static void __attribute__((__flatten__)) run_host(void)
 {
         int completed_before;
         int completed = 0;
@@ -160,7 +172,7 @@ static void run_host(void)
 
         for (;;) {
                 if (do_sleep) {
-                        if (enable_kick())
+                        if (avail_empty() && enable_kick())
                                 wait_for_kick();
                 } else {
                         poll_avail();
diff --git a/tools/virtio/ringtest/main.h b/tools/virtio/ringtest/main.h
index 16917acb0ade..34e63cc4c572 100644
--- a/tools/virtio/ringtest/main.h
+++ b/tools/virtio/ringtest/main.h
@@ -56,15 +56,15 @@ void alloc_ring(void);
 int add_inbuf(unsigned, void *, void *);
 void *get_buf(unsigned *, void **);
 void disable_call();
+bool used_empty();
 bool enable_call();
 void kick_available();
-void poll_used();
 /* host side */
 void disable_kick();
+bool avail_empty();
 bool enable_kick();
 bool use_buf(unsigned *, void **);
 void call_used();
-void poll_avail();
 
 /* implemented by main */
 extern bool do_sleep;
diff --git a/tools/virtio/ringtest/noring.c b/tools/virtio/ringtest/noring.c
index eda2f4824130..b8d1c1daac7c 100644
--- a/tools/virtio/ringtest/noring.c
+++ b/tools/virtio/ringtest/noring.c
@@ -24,8 +24,9 @@ void *get_buf(unsigned *lenp, void **bufp)
         return "Buffer";
 }
 
-void poll_used(void)
+bool used_empty()
 {
+        return false;
 }
 
 void disable_call()
@@ -54,8 +55,9 @@ bool enable_kick()
         assert(0);
 }
 
-void poll_avail(void)
+bool avail_empty()
 {
+        return false;
 }
 
 bool use_buf(unsigned *lenp, void **bufp)
diff --git a/tools/virtio/ringtest/ptr_ring.c b/tools/virtio/ringtest/ptr_ring.c
index bd2ad1d3b7a9..635b07b4fdd3 100644
--- a/tools/virtio/ringtest/ptr_ring.c
+++ b/tools/virtio/ringtest/ptr_ring.c
@@ -133,18 +133,9 @@ void *get_buf(unsigned *lenp, void **bufp)
         return datap;
 }
 
-void poll_used(void)
+bool used_empty()
 {
-        void *b;
-
-        do {
-                if (tailcnt == headcnt || __ptr_ring_full(&array)) {
-                        b = NULL;
-                        barrier();
-                } else {
-                        b = "Buffer\n";
-                }
-        } while (!b);
+        return (tailcnt == headcnt || __ptr_ring_full(&array));
 }
 
 void disable_call()
@@ -173,14 +164,9 @@ bool enable_kick()
         assert(0);
 }
 
-void poll_avail(void)
+bool avail_empty()
 {
-        void *b;
-
-        do {
-                barrier();
-                b = __ptr_ring_peek(&array);
-        } while (!b);
+        return !__ptr_ring_peek(&array);
 }
 
 bool use_buf(unsigned *lenp, void **bufp)
diff --git a/tools/virtio/ringtest/ring.c b/tools/virtio/ringtest/ring.c
index c25c8d248b6b..747c5dd47be8 100644
--- a/tools/virtio/ringtest/ring.c
+++ b/tools/virtio/ringtest/ring.c
@@ -163,12 +163,11 @@ void *get_buf(unsigned *lenp, void **bufp)
         return datap;
 }
 
-void poll_used(void)
+bool used_empty()
 {
         unsigned head = (ring_size - 1) & guest.last_used_idx;
 
-        while (ring[head].flags & DESC_HW)
-                busy_wait();
+        return (ring[head].flags & DESC_HW);
 }
 
 void disable_call()
@@ -180,13 +179,11 @@ void disable_call()
 
 bool enable_call()
 {
-        unsigned head = (ring_size - 1) & guest.last_used_idx;
-
         event->call_index = guest.last_used_idx;
         /* Flush call index write */
         /* Barrier D (for pairing) */
         smp_mb();
-        return ring[head].flags & DESC_HW;
+        return used_empty();
 }
 
 void kick_available(void)
@@ -213,20 +210,17 @@ void disable_kick()
 
 bool enable_kick()
 {
-        unsigned head = (ring_size - 1) & host.used_idx;
-
         event->kick_index = host.used_idx;
         /* Barrier C (for pairing) */
         smp_mb();
-        return !(ring[head].flags & DESC_HW);
+        return avail_empty();
 }
 
-void poll_avail(void)
+bool avail_empty()
 {
         unsigned head = (ring_size - 1) & host.used_idx;
 
-        while (!(ring[head].flags & DESC_HW))
-                busy_wait();
+        return !(ring[head].flags & DESC_HW);
 }
 
 bool use_buf(unsigned *lenp, void **bufp)
diff --git a/tools/virtio/ringtest/virtio_ring_0_9.c b/tools/virtio/ringtest/virtio_ring_0_9.c
index 761866212aac..bbc3043b2fb1 100644
--- a/tools/virtio/ringtest/virtio_ring_0_9.c
+++ b/tools/virtio/ringtest/virtio_ring_0_9.c
@@ -194,24 +194,16 @@ void *get_buf(unsigned *lenp, void **bufp)
         return datap;
 }
 
-void poll_used(void)
+bool used_empty()
 {
+        unsigned short last_used_idx = guest.last_used_idx;
 #ifdef RING_POLL
-        unsigned head = (ring_size - 1) & guest.last_used_idx;
+        unsigned short head = last_used_idx & (ring_size - 1);
+        unsigned index = ring.used->ring[head].id;
 
-        for (;;) {
-                unsigned index = ring.used->ring[head].id;
-
-                if ((index ^ guest.last_used_idx ^ 0x8000) & ~(ring_size - 1))
-                        busy_wait();
-                else
-                        break;
-        }
+        return (index ^ last_used_idx ^ 0x8000) & ~(ring_size - 1);
 #else
-        unsigned head = guest.last_used_idx;
-
-        while (ring.used->idx == head)
-                busy_wait();
+        return ring.used->idx == last_used_idx;
 #endif
 }
 
@@ -224,22 +216,11 @@ void disable_call()
 
 bool enable_call()
 {
-        unsigned short last_used_idx;
-
-        vring_used_event(&ring) = (last_used_idx = guest.last_used_idx);
+        vring_used_event(&ring) = guest.last_used_idx;
         /* Flush call index write */
         /* Barrier D (for pairing) */
         smp_mb();
-#ifdef RING_POLL
-        {
-                unsigned short head = last_used_idx & (ring_size - 1);
-                unsigned index = ring.used->ring[head].id;
-
-                return (index ^ last_used_idx ^ 0x8000) & ~(ring_size - 1);
-        }
-#else
-        return ring.used->idx == last_used_idx;
-#endif
+        return used_empty();
 }
 
 void kick_available(void)
@@ -266,36 +247,21 @@ void disable_kick()
 
 bool enable_kick()
 {
-        unsigned head = host.used_idx;
-
-        vring_avail_event(&ring) = head;
+        vring_avail_event(&ring) = host.used_idx;
         /* Barrier C (for pairing) */
         smp_mb();
-#ifdef RING_POLL
-        {
-                unsigned index = ring.avail->ring[head & (ring_size - 1)];
-
-                return (index ^ head ^ 0x8000) & ~(ring_size - 1);
-        }
-#else
-        return head == ring.avail->idx;
-#endif
+        return avail_empty();
 }
 
-void poll_avail(void)
+bool avail_empty()
 {
         unsigned head = host.used_idx;
 #ifdef RING_POLL
-        for (;;) {
-                unsigned index = ring.avail->ring[head & (ring_size - 1)];
-                if ((index ^ head ^ 0x8000) & ~(ring_size - 1))
-                        busy_wait();
-                else
-                        break;
-        }
+        unsigned index = ring.avail->ring[head & (ring_size - 1)];
+
+        return ((index ^ head ^ 0x8000) & ~(ring_size - 1));
 #else
-        while (ring.avail->idx == head)
-                busy_wait();
+        return head == ring.avail->idx;
 #endif
 }