Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/…

…linux/kernel/git/tip/tip

Pull more perf updates from Ingo Molnar:
 "The only kernel change is comment typo fixes.

  The rest is mostly tooling fixes, but also new vendor event additions
  and updates, a bigger libperf/libtraceevent library and a header files
  reorganization that came in a bit late"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (108 commits)
  perf unwind: Fix libunwind build failure on i386 systems
  perf parser: Remove needless include directives
  perf build: Add detection of java-11-openjdk-devel package
  perf jvmti: Include JVMTI support for s390
  perf vendor events: Remove P8 HW events which are not supported
  perf evlist: Fix access of freed id arrays
  perf stat: Fix free memory access / memory leaks in metrics
  perf tools: Replace needless mmap.h with what is needed, event.h
  perf evsel: Move config terms to a separate header
  perf evlist: Remove unused perf_evlist__fprintf() method
  perf evsel: Introduce evsel_fprintf.h
  perf evsel: Remove need for symbol_conf in evsel_fprintf.c
  perf copyfile: Move copyfile routines to separate files
  libperf: Add perf_evlist__poll() function
  libperf: Add perf_evlist__add_pollfd() function
  libperf: Add perf_evlist__alloc_pollfd() function
  libperf: Add libperf_init() call to the tests
  libperf: Merge libperf_set_print() into libperf_init()
  libperf: Add libperf dependency for tests targets
  libperf: Use sys/types.h to get ssize_t, not unistd.h
  ...

kernel/events/core.c

@@ -2239,7 +2239,7 @@ static void __perf_event_disable(struct perf_event *event,
  *
  * If event->ctx is a cloned context, callers must make sure that
  * every task struct that event->ctx->task could possibly point to
- * remains valid.  This condition is satisifed when called through
+ * remains valid.  This condition is satisfied when called through
  * perf_event_for_each_child or perf_event_for_each because they
  * hold the top-level event's child_mutex, so any descendant that
  * goes to exit will block in perf_event_exit_event().
@@ -6054,7 +6054,7 @@ static void perf_sample_regs_intr(struct perf_regs *regs_intr,
  * Get remaining task size from user stack pointer.
  *
  * It'd be better to take stack vma map and limit this more
- * precisly, but there's no way to get it safely under interrupt,
+ * precisely, but there's no way to get it safely under interrupt,
  * so using TASK_SIZE as limit.
  */
 static u64 perf_ustack_task_size(struct pt_regs *regs)
@@ -6616,7 +6616,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 
 	if (sample_type & PERF_SAMPLE_STACK_USER) {
 		/*
-		 * Either we need PERF_SAMPLE_STACK_USER bit to be allways
+		 * Either we need PERF_SAMPLE_STACK_USER bit to be always
 		 * processed as the last one or have additional check added
 		 * in case new sample type is added, because we could eat
 		 * up the rest of the sample size.

tools/arch/x86/include/asm/cpufeatures.h

@@ -231,6 +231,8 @@
 #define X86_FEATURE_VMMCALL		( 8*32+15) /* Prefer VMMCALL to VMCALL */
 #define X86_FEATURE_XENPV		( 8*32+16) /* "" Xen paravirtual guest */
 #define X86_FEATURE_EPT_AD		( 8*32+17) /* Intel Extended Page Table access-dirty bit */
+#define X86_FEATURE_VMCALL		( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */
+#define X86_FEATURE_VMW_VMMCALL		( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
 #define X86_FEATURE_FSGSBASE		( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
@@ -354,6 +356,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */
 #define X86_FEATURE_MD_CLEAR		(18*32+10) /* VERW clears CPU buffers */
 #define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */

tools/arch/x86/include/uapi/asm/unistd.h

@@ -3,7 +3,7 @@
 #define _UAPI_ASM_X86_UNISTD_H
 
 /* x32 syscall flag bit */
-#define __X32_SYSCALL_BIT	0x40000000
+#define __X32_SYSCALL_BIT	0x40000000UL
 
 #ifndef __KERNEL__
 # ifdef __i386__

tools/include/asm/bug.h

@@ -3,6 +3,7 @@
 #define _TOOLS_ASM_BUG_H
 
 #include <linux/compiler.h>
+#include <stdio.h>
 
 #define __WARN_printf(arg...)	do { fprintf(stderr, arg); } while (0)
 

tools/include/uapi/asm-generic/unistd.h

@@ -569,7 +569,7 @@ __SYSCALL(__NR_semget, sys_semget)
 __SC_COMP(__NR_semctl, sys_semctl, compat_sys_semctl)
 #if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_semtimedop 192
-__SC_COMP(__NR_semtimedop, sys_semtimedop, sys_semtimedop_time32)
+__SC_3264(__NR_semtimedop, sys_semtimedop_time32, sys_semtimedop)
 #endif
 #define __NR_semop 193
 __SYSCALL(__NR_semop, sys_semop)

tools/include/uapi/linux/prctl.h

@@ -181,7 +181,7 @@ struct prctl_mm_map {
 #define PR_GET_THP_DISABLE	42
 
 /*
- * Tell the kernel to start/stop helping userspace manage bounds tables.
+ * No longer implemented, but left here to ensure the numbers stay reserved:
  */
 #define PR_MPX_ENABLE_MANAGEMENT  43
 #define PR_MPX_DISABLE_MANAGEMENT 44
@@ -229,4 +229,9 @@ struct prctl_mm_map {
 # define PR_PAC_APDBKEY			(1UL << 3)
 # define PR_PAC_APGAKEY			(1UL << 4)
 
+/* Tagged user address controls for arm64 */
+#define PR_SET_TAGGED_ADDR_CTRL		55
+#define PR_GET_TAGGED_ADDR_CTRL		56
+# define PR_TAGGED_ADDR_ENABLE		(1UL << 0)
+
 #endif /* _LINUX_PRCTL_H */

tools/lib/traceevent/Build

@@ -6,14 +6,3 @@ libtraceevent-y += parse-utils.o
 libtraceevent-y += kbuffer-parse.o
 libtraceevent-y += tep_strerror.o
 libtraceevent-y += event-parse-api.o
-
-plugin_jbd2-y         += plugin_jbd2.o
-plugin_hrtimer-y      += plugin_hrtimer.o
-plugin_kmem-y         += plugin_kmem.o
-plugin_kvm-y          += plugin_kvm.o
-plugin_mac80211-y     += plugin_mac80211.o
-plugin_sched_switch-y += plugin_sched_switch.o
-plugin_function-y     += plugin_function.o
-plugin_xen-y          += plugin_xen.o
-plugin_scsi-y         += plugin_scsi.o
-plugin_cfg80211-y     += plugin_cfg80211.o

tools/lib/traceevent/Documentation/libtraceevent-event_print.txt

@@ -0,0 +1,130 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_print_event - Writes event information into a trace sequence.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+*#include <trace-seq.h>*
+
+void *tep_print_event*(struct tep_handle pass:[*]_tep_, struct trace_seqpass:[*]_s_, struct tep_record pass:[*]_record_, const char pass:[*]_fmt_, _..._)
+--
+
+DESCRIPTION
+-----------
+
+The _tep_print_event()_ function parses the event information of the given
+_record_ and writes it into the trace sequence _s_, according to the format
+string _fmt_. The desired information is specified after the format string.
+The _fmt_ is printf-like format string, following arguments are supported:
+[verse]
+--
+	TEP_PRINT_PID, "%d"  - PID of the event.
+	TEP_PRINT_CPU, "%d"  - Event CPU.
+	TEP_PRINT_COMM, "%s" - Event command string.
+	TEP_PRINT_NAME, "%s" - Event name.
+	TEP_PRINT_LATENCY, "%s" - Latency of the event. It prints 4 or more
+			fields - interrupt state, scheduling state,
+			current context, and preemption count.
+			Field 1 is the interrupt enabled state:
+				d : Interrupts are disabled
+				. : Interrupts are enabled
+				X : The architecture does not support this
+				    information
+			Field 2 is the "need resched" state.
+				N : The task is set to call the scheduler when
+				    possible, as another higher priority task
+				    may need to be scheduled in.
+				. : The task is not set to call the scheduler.
+			Field 3 is the context state.
+				. : Normal context
+				s : Soft interrupt context
+				h : Hard interrupt context
+				H : Hard interrupt context which triggered
+				    during soft interrupt context.
+				z : NMI context
+				Z : NMI context which triggered during hard
+				    interrupt context
+			Field 4 is the preemption count.
+				. : The preempt count is zero.
+			On preemptible kernels (where the task can be scheduled
+			out in arbitrary locations while in kernel context), the
+			preempt count, when non zero, will prevent the kernel
+			from scheduling out the current task. The preempt count
+			number is displayed when it is not zero.
+			Depending on the kernel, it may show other fields
+			(lock depth, or migration disabled, which are unique to
+			specialized kernels).
+	TEP_PRINT_TIME, %d - event time stamp. A divisor and precision can be
+			specified as part of this format string:
+			"%precision.divisord". Example:
+			"%3.1000d" - divide the time by 1000 and print the first
+			3 digits before the dot. Thus, the time stamp
+			"123456000" will be printed as "123.456"
+	TEP_PRINT_INFO, "%s" - event information.
+	TEP_PRINT_INFO_RAW, "%s" - event information, in raw format.
+
+--
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+#include <trace-seq.h>
+...
+struct trace_seq seq;
+trace_seq_init(&seq);
+struct tep_handle *tep = tep_alloc();
+...
+void print_my_event(struct tep_record *record)
+{
+	trace_seq_reset(&seq);
+	tep_print_event(tep, s, record, "%16s-%-5d [%03d] %s %6.1000d %s %s",
+			TEP_PRINT_COMM, TEP_PRINT_PID, TEP_PRINT_CPU,
+			TEP_PRINT_LATENCY, TEP_PRINT_TIME, TEP_PRINT_NAME,
+			TEP_PRINT_INFO);
+}
+...
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+	Header file to include in order to have access to the library APIs.
+*trace-seq.h*
+	Header file to include in order to have access to trace sequences related APIs.
+	Trace sequences are used to allow a function to call several other functions
+	to create a string of data to use.
+*-ltraceevent*
+	Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <[email protected]>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <[email protected]>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to  <[email protected]>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git

tools/lib/traceevent/Documentation/libtraceevent-func_apis.txt

@@ -59,12 +59,12 @@ parser context.
 
 The _tep_register_function()_ function registers a function name mapped to an
 address and (optional) module. This mapping is used in case the function tracer
-or events have "%pF" or "%pS" parameter in its format string. It is common to
-pass in the kallsyms function names with their corresponding addresses with this
+or events have "%pS" parameter in its format string. It is common to pass in
+the kallsyms function names with their corresponding addresses with this
 function. The _tep_ argument is the trace event parser context. The _name_ is
-the name of the function, the string is copied internally. The _addr_ is
-the start address of the function. The _mod_ is the kernel module
-the function may be in (NULL for none).
+the name of the function, the string is copied internally. The _addr_ is the
+start address of the function. The _mod_ is the kernel module the function may
+be in (NULL for none).
 
 The _tep_register_print_string()_ function  registers a string by the address
 it was stored in the kernel. Some strings internal to the kernel with static

tools/lib/traceevent/Documentation/libtraceevent-handle.txt

@@ -3,7 +3,7 @@ libtraceevent(3)
 
 NAME
 ----
-tep_alloc, tep_free,tep_ref, tep_unref,tep_ref_get - Create, destroy, manage
+tep_alloc, tep_free,tep_ref, tep_unref,tep_get_ref - Create, destroy, manage
 references of trace event parser context.
 
 SYNOPSIS
@@ -16,7 +16,7 @@ struct tep_handle pass:[*]*tep_alloc*(void);
 void *tep_free*(struct tep_handle pass:[*]_tep_);
 void *tep_ref*(struct tep_handle pass:[*]_tep_);
 void *tep_unref*(struct tep_handle pass:[*]_tep_);
-int *tep_ref_get*(struct tep_handle pass:[*]_tep_);
+int *tep_get_ref*(struct tep_handle pass:[*]_tep_);
 --
 
 DESCRIPTION
@@ -57,9 +57,9 @@ EXAMPLE
 ...
 struct tep_handle *tep = tep_alloc();
 ...
-int ref = tep_ref_get(tep);
+int ref = tep_get_ref(tep);
 tep_ref(tep);
-if ( (ref+1) != tep_ref_get(tep)) {
+if ( (ref+1) != tep_get_ref(tep)) {
 	/* Something wrong happened, the counter is not incremented by 1 */
 }
 tep_unref(tep);

tools/lib/traceevent/Documentation/libtraceevent-plugins.txt

@@ -0,0 +1,99 @@
+libtraceevent(3)
+================
+
+NAME
+----
+tep_load_plugins, tep_unload_plugins - Load / unload traceevent plugins.
+
+SYNOPSIS
+--------
+[verse]
+--
+*#include <event-parse.h>*
+
+struct tep_plugin_list pass:[*]*tep_load_plugins*(struct tep_handle pass:[*]_tep_);
+void *tep_unload_plugins*(struct tep_plugin_list pass:[*]_plugin_list_, struct tep_handle pass:[*]_tep_);
+--
+
+DESCRIPTION
+-----------
+The _tep_load_plugins()_ function loads all plugins, located in the plugin
+directories. The _tep_ argument is trace event parser context.
+The plugin directories are :
+[verse]
+--
+	- System's plugin directory, defined at the library compile time. It
+	  depends on the library installation prefix and usually is
+	  _(install_preffix)/lib/traceevent/plugins_
+	- Directory, defined by the environment variable _TRACEEVENT_PLUGIN_DIR_
+	- User's plugin directory, located at _~/.local/lib/traceevent/plugins_
+--
+Loading of plugins can be controlled by the _tep_flags_, using the
+_tep_set_flag()_ API:
+[verse]
+--
+	_TEP_DISABLE_SYS_PLUGINS_	- do not load plugins, located in
+					the system's plugin directory.
+	_TEP_DISABLE_PLUGINS_		- do not load any plugins.
+--
+The _tep_set_flag()_ API needs to be called before _tep_load_plugins()_, if
+loading of all plugins is not the desired case.
+
+The _tep_unload_plugins()_ function unloads the plugins, previously loaded by
+_tep_load_plugins()_. The _tep_ argument is trace event parser context. The
+_plugin_list_ is the list of loaded plugins, returned by
+the _tep_load_plugins()_ function.
+
+RETURN VALUE
+------------
+The _tep_load_plugins()_ function returns a list of successfully loaded plugins,
+or NULL in case no plugins are loaded.
+
+EXAMPLE
+-------
+[source,c]
+--
+#include <event-parse.h>
+...
+struct tep_handle *tep = tep_alloc();
+...
+struct tep_plugin_list *plugins = tep_load_plugins(tep);
+if (plugins == NULL) {
+	/* no plugins are loaded */
+}
+...
+tep_unload_plugins(plugins, tep);
+--
+
+FILES
+-----
+[verse]
+--
+*event-parse.h*
+	Header file to include in order to have access to the library APIs.
+*-ltraceevent*
+	Linker switch to add when building a program that uses the library.
+--
+
+SEE ALSO
+--------
+_libtraceevent(3)_, _trace-cmd(1)_, _tep_set_flag(3)_
+
+AUTHOR
+------
+[verse]
+--
+*Steven Rostedt* <[email protected]>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <[email protected]>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to  <[email protected]>
+
+LICENSE
+-------
+libtraceevent is Free Software licensed under the GNU LGPL 2.1
+
+RESOURCES
+---------
+https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git