Merge tag 'perf-urgent-for-mingo-5.3-20190708-2' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/urgent fixes from Arnaldo Carvalho de Melo:

core:

  Arnaldo Carvalho de Melo:

  - Allow references to thread objects after__machine_exit(), fixing a bug with
    'perf sched lat' where that happens, i.e. after perf_session__delete() we
    still have references to threads that were in a linked list whose head was
    freed in perf_session__delete(), causing a segfault, fix it.

  Jiri Olsa:

  - Do not rely on errno values for precise_ip fallback, fixing the default
    use case for 'perf record' on some AMD servers, when no events are specified
    and we try to use "cycles:P", i.e. with the maximum precision level.

BPF:

  Song Liu:

  - Assign proper ff->ph in perf_event__synthesize_features(), fixing a bug
    when using pipe mode, i.e.  'perf record -o -'.

tools headers:

  Arnaldo Carvalho de Melo:

  - Sync kvm headers with the kernel sources

perf tests:

  Seeteena Thoufeek:

  - Fix record+probe_libc_inet_pton.sh for powerpc64, where without the
    debuginfo package for the 'ping' utility we can't resolve its symbols,
    so admit getting "[unknown]" for that backtrace line.

perf python:

  Arnaldo Carvalho de Melo:

  - Remove -fstack-protector-strong if clang doesn't have it, fixing the build
    with clang on fedora:30, oracleline:7, centos:7.

perf jvmti:

  Jiri Olsa:

  - Address gcc string overflow warning for strncpy()

build:

  Arnaldo Carvalho de Melo:

  - Check if gettid() is available before providing helper, as recent
    versions of glibc started to provide gettid().

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

8 files changed, 90 insertions, 30 deletions

diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 7b7ac0f6cec9..d819a3e8b552 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -260,6 +260,13 @@ struct kvm_vcpu_events {
          KVM_REG_SIZE_U256 |                                            \
          ((i) & (KVM_ARM64_SVE_MAX_SLICES - 1)))
 
+/*
+ * Register values for KVM_REG_ARM64_SVE_ZREG(), KVM_REG_ARM64_SVE_PREG() and
+ * KVM_REG_ARM64_SVE_FFR() are represented in memory in an endianness-
+ * invariant layout which differs from the layout used for the FPSIMD
+ * V-registers on big-endian systems: see sigcontext.h for more explanation.
+ */
+
 #define KVM_ARM64_SVE_VQ_MIN __SVE_VQ_MIN
 #define KVM_ARM64_SVE_VQ_MAX __SVE_VQ_MAX
 
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 75f27ee2c263..998c2cc08363 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -239,12 +239,14 @@
 #define X86_FEATURE_BMI1                ( 9*32+ 3) /* 1st group bit manipulation extensions */
 #define X86_FEATURE_HLE                 ( 9*32+ 4) /* Hardware Lock Elision */
 #define X86_FEATURE_AVX2                ( 9*32+ 5) /* AVX2 instructions */
+#define X86_FEATURE_FDP_EXCPTN_ONLY     ( 9*32+ 6) /* "" FPU data pointer updated only on x87 exceptions */
 #define X86_FEATURE_SMEP                ( 9*32+ 7) /* Supervisor Mode Execution Protection */
 #define X86_FEATURE_BMI2                ( 9*32+ 8) /* 2nd group bit manipulation extensions */
 #define X86_FEATURE_ERMS                ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB instructions */
 #define X86_FEATURE_INVPCID             ( 9*32+10) /* Invalidate Processor Context ID */
 #define X86_FEATURE_RTM                 ( 9*32+11) /* Restricted Transactional Memory */
 #define X86_FEATURE_CQM                 ( 9*32+12) /* Cache QoS Monitoring */
+#define X86_FEATURE_ZERO_FCS_FDS        ( 9*32+13) /* "" Zero out FPU CS and FPU DS */
 #define X86_FEATURE_MPX                 ( 9*32+14) /* Memory Protection Extension */
 #define X86_FEATURE_RDT_A               ( 9*32+15) /* Resource Director Technology Allocation */
 #define X86_FEATURE_AVX512F             ( 9*32+16) /* AVX-512 Foundation */
@@ -269,13 +271,19 @@
 #define X86_FEATURE_XGETBV1             (10*32+ 2) /* XGETBV with ECX = 1 instruction */
 #define X86_FEATURE_XSAVES              (10*32+ 3) /* XSAVES/XRSTORS instructions */
 
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (EDX), word 11 */
-#define X86_FEATURE_CQM_LLC             (11*32+ 1) /* LLC QoS if 1 */
+/*
+ * Extended auxiliary flags: Linux defined - for features scattered in various
+ * CPUID levels like 0xf, etc.
+ *
+ * Reuse free bits when adding new feature flags!
+ */
+#define X86_FEATURE_CQM_LLC             (11*32+ 0) /* LLC QoS if 1 */
+#define X86_FEATURE_CQM_OCCUP_LLC       (11*32+ 1) /* LLC occupancy monitoring */
+#define X86_FEATURE_CQM_MBM_TOTAL       (11*32+ 2) /* LLC Total MBM monitoring */
+#define X86_FEATURE_CQM_MBM_LOCAL       (11*32+ 3) /* LLC Local MBM monitoring */
 
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (EDX), word 12 */
-#define X86_FEATURE_CQM_OCCUP_LLC       (12*32+ 0) /* LLC occupancy monitoring */
-#define X86_FEATURE_CQM_MBM_TOTAL       (12*32+ 1) /* LLC Total MBM monitoring */
-#define X86_FEATURE_CQM_MBM_LOCAL       (12*32+ 2) /* LLC Local MBM monitoring */
+/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
+#define X86_FEATURE_AVX512_BF16         (12*32+ 5) /* AVX512 BFLOAT16 instructions */
 
 /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
 #define X86_FEATURE_CLZERO              (13*32+ 0) /* CLZERO instruction */
@@ -322,6 +330,7 @@
 #define X86_FEATURE_UMIP                (16*32+ 2) /* User Mode Instruction Protection */
 #define X86_FEATURE_PKU                 (16*32+ 3) /* Protection Keys for Userspace */
 #define X86_FEATURE_OSPKE               (16*32+ 4) /* OS Protection Keys Enable */
+#define X86_FEATURE_WAITPKG             (16*32+ 5) /* UMONITOR/UMWAIT/TPAUSE Instructions */
 #define X86_FEATURE_AVX512_VBMI2        (16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */
 #define X86_FEATURE_GFNI                (16*32+ 8) /* Galois Field New Instructions */
 #define X86_FEATURE_VAES                (16*32+ 9) /* Vector AES */
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 24a8cd229df6..d6ab5b4d15e5 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -383,6 +383,9 @@ struct kvm_sync_regs {
 #define KVM_X86_QUIRK_LAPIC_MMIO_HOLE   (1 << 2)
 #define KVM_X86_QUIRK_OUT_7E_INC_RIP    (1 << 3)
 
+#define KVM_STATE_NESTED_FORMAT_VMX     0
+#define KVM_STATE_NESTED_FORMAT_SVM     1       /* unused */
+
 #define KVM_STATE_NESTED_GUEST_MODE     0x00000001
 #define KVM_STATE_NESTED_RUN_PENDING    0x00000002
 #define KVM_STATE_NESTED_EVMCS          0x00000004
@@ -390,7 +393,14 @@ struct kvm_sync_regs {
 #define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001
 #define KVM_STATE_NESTED_SMM_VMXON      0x00000002
 
-struct kvm_vmx_nested_state {
+#define KVM_STATE_NESTED_VMX_VMCS_SIZE  0x1000
+
+struct kvm_vmx_nested_state_data {
+        __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
+        __u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
+};
+
+struct kvm_vmx_nested_state_hdr {
         __u64 vmxon_pa;
         __u64 vmcs12_pa;
 
@@ -401,24 +411,25 @@ struct kvm_vmx_nested_state {
 
 /* for KVM_CAP_NESTED_STATE */
 struct kvm_nested_state {
-        /* KVM_STATE_* flags */
         __u16 flags;
-
-        /* 0 for VMX, 1 for SVM.  */
         __u16 format;
-
-        /* 128 for SVM, 128 + VMCS size for VMX.  */
         __u32 size;
 
         union {
-                /* VMXON, VMCS */
-                struct kvm_vmx_nested_state vmx;
+                struct kvm_vmx_nested_state_hdr vmx;
 
                 /* Pad the header to 128 bytes.  */
                 __u8 pad[120];
-        };
+        } hdr;
 
-        __u8 data[0];
+        /*
+         * Define data region as 0 bytes to preserve backwards-compatability
+         * to old definition of kvm_nested_state in order to avoid changing
+         * KVM_{GET,PUT}_NESTED_STATE ioctl values.
+         */
+        union {
+                struct kvm_vmx_nested_state_data vmx[0];
+        } data;
 };
 
 #endif /* _ASM_X86_KVM_H */
diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index 9b7632ff70aa..f12a4e217968 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -45,7 +45,7 @@ trace_libc_inet_pton_backtrace() {
                 eventattr='max-stack=4'
                 echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
                 echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
-                echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
+                echo ".*(\+0x[[:xdigit:]]+|\[unknown\])[[:space:]]\(.*/bin/ping.*\)$" >> $expected
                 ;;
         *)
                 eventattr='max-stack=3'
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 5ab31a4a658d..7fb4ae82f34c 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1800,14 +1800,8 @@ static int perf_event_open(struct perf_evsel *evsel,
                 if (fd >= 0)
                         break;
 
-                /*
-                 * Do quick precise_ip fallback if:
-                 *  - there is precise_ip set in perf_event_attr
-                 *  - maximum precise is requested
-                 *  - sys_perf_event_open failed with ENOTSUP error,
-                 *    which is associated with wrong precise_ip
-                 */
-                if (!precise_ip || !evsel->precise_max || (errno != ENOTSUP))
+                /* Do not try less precise if not requested. */
+                if (!evsel->precise_max)
                         break;
 
                 /*
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index bf26dc85eaaa..6a93ff5d8db5 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3683,6 +3683,7 @@ int perf_event__synthesize_features(struct perf_tool *tool,
                 return -ENOMEM;
 
         ff.size = sz - sz_hdr;
+        ff.ph = &session->header;
 
         for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) {
                 if (!feat_ops[feat].synthesize) {
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 1b3d7265bca9..147ed85ea2bc 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -210,6 +210,18 @@ void machine__exit(struct machine *machine)
 
         for (i = 0; i < THREADS__TABLE_SIZE; i++) {
                 struct threads *threads = &machine->threads[i];
+                struct thread *thread, *n;
+                /*
+                 * Forget about the dead, at this point whatever threads were
+                 * left in the dead lists better have a reference count taken
+                 * by who is using them, and then, when they drop those references
+                 * and it finally hits zero, thread__put() will check and see that
+                 * its not in the dead threads list and will not try to remove it
+                 * from there, just calling thread__delete() straight away.
+                 */
+                list_for_each_entry_safe(thread, n, &threads->dead, node)
+                        list_del_init(&thread->node);
+
                 exit_rwsem(&threads->lock);
         }
 }
@@ -1759,9 +1771,11 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th,
         if (threads->last_match == th)
                 threads__set_last_match(threads, NULL);
 
-        BUG_ON(refcount_read(&th->refcnt) == 0);
         if (lock)
                 down_write(&threads->lock);
+
+        BUG_ON(refcount_read(&th->refcnt) == 0);
+
         rb_erase_cached(&th->rb_node, &threads->entries);
         RB_CLEAR_NODE(&th->rb_node);
         --threads->nr;
@@ -1771,9 +1785,16 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th,
          * will be called and we will remove it from the dead_threads list.
          */
         list_add_tail(&th->node, &threads->dead);
+
+        /*
+         * We need to do the put here because if this is the last refcount,
+         * then we will be touching the threads->dead head when removing the
+         * thread.
+         */
+        thread__put(th);
+
         if (lock)
                 up_write(&threads->lock);
-        thread__put(th);
 }
 
 void machine__remove_thread(struct machine *machine, struct thread *th)
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index aab7807d445f..3e29a4e8b5e6 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -125,10 +125,27 @@ void thread__put(struct thread *thread)
 {
         if (thread && refcount_dec_and_test(&thread->refcnt)) {
                 /*
-                 * Remove it from the dead_threads list, as last reference
-                 * is gone.
+                 * Remove it from the dead threads list, as last reference is
+                 * gone, if it is in a dead threads list.
+                 *
+                 * We may not be there anymore if say, the machine where it was
+                 * stored was already deleted, so we already removed it from
+                 * the dead threads and some other piece of code still keeps a
+                 * reference.
+                 *
+                 * This is what 'perf sched' does and finally drops it in
+                 * perf_sched__lat(), where it calls perf_sched__read_events(),
+                 * that processes the events by creating a session and deleting
+                 * it, which ends up destroying the list heads for the dead
+                 * threads, but before it does that it removes all threads from
+                 * it using list_del_init().
+                 *
+                 * So we need to check here if it is in a dead threads list and
+                 * if so, remove it before finally deleting the thread, to avoid
+                 * an use after free situation.
                  */
-                list_del_init(&thread->node);
+                if (!list_empty(&thread->node))
+                        list_del_init(&thread->node);
                 thread__delete(thread);
         }
 }