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* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to  <linux-trace-devel@vger.kernel.org>
+
+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
+or events have "%pS" parameter in its format string. It is common to pass in
-pass in the kallsyms function names with their corresponding addresses with this
+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 name of the function, the string is copied internally. The _addr_ is the
-the start address of the function. The _mod_ is the kernel module
+start address of the function. The _mod_ is the kernel module the function may
-the function may be in (NULL for none).
+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* <rostedt@goodmis.org>, author of *libtraceevent*.
+*Tzvetomir Stoyanov* <tz.stoyanov@gmail.com>, author of this man page.
+--
+REPORTING BUGS
+--------------
+Report bugs to  <linux-trace-devel@vger.kernel.org>
+
+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.txt

@@ -16,7 +16,7 @@ Management of tep handler data structure and access of its members:
 	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_);
 	void *tep_set_flag*(struct tep_handle pass:[*]_tep_, enum tep_flag _flag_);
 	void *tep_clear_flag*(struct tep_handle pass:[*]_tep_, enum tep_flag _flag_);
 	bool *tep_test_flag*(struct tep_handle pass:[*]_tep_, enum tep_flag _flags_);
@@ -26,15 +26,12 @@ Management of tep handler data structure and access of its members:
 	void *tep_set_long_size*(struct tep_handle pass:[*]_tep_, int _long_size_);
 	int *tep_get_page_size*(struct tep_handle pass:[*]_tep_);
 	void *tep_set_page_size*(struct tep_handle pass:[*]_tep_, int _page_size_);
-	bool *tep_is_latency_format*(struct tep_handle pass:[*]_tep_);
-	void *tep_set_latency_format*(struct tep_handle pass:[*]_tep_, int _lat_);
 	int *tep_get_header_page_size*(struct tep_handle pass:[*]_tep_);
 	int *tep_get_header_timestamp_size*(struct tep_handle pass:[*]_tep_);
 	bool *tep_is_old_format*(struct tep_handle pass:[*]_tep_);
 	int *tep_strerror*(struct tep_handle pass:[*]_tep_, enum tep_errno _errnum_, char pass:[*]_buf_, size_t _buflen_);
 
 Register / unregister APIs:
-	int *tep_register_trace_clock*(struct tep_handle pass:[*]_tep_, const char pass:[*]_trace_clock_);
 	int *tep_register_function*(struct tep_handle pass:[*]_tep_, char pass:[*]_name_, unsigned long long _addr_, char pass:[*]_mod_);
 	int *tep_register_event_handler*(struct tep_handle pass:[*]_tep_, int _id_, const char pass:[*]_sys_name_, const char pass:[*]_event_name_, tep_event_handler_func _func_, void pass:[*]_context_);
 	int *tep_unregister_event_handler*(struct tep_handle pass:[*]tep, int id, const char pass:[*]sys_name, const char pass:[*]event_name, tep_event_handler_func func, void pass:[*]_context_);
@@ -57,14 +54,7 @@ Event related APIs:
 	int *tep_get_events_count*(struct tep_handle pass:[*]_tep_);
 	struct tep_event pass:[*]pass:[*]*tep_list_events*(struct tep_handle pass:[*]_tep_, enum tep_event_sort_type _sort_type_);
 	struct tep_event pass:[*]pass:[*]*tep_list_events_copy*(struct tep_handle pass:[*]_tep_, enum tep_event_sort_type _sort_type_);
-
+	void *tep_print_event*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_record pass:[*]_record_, const char pass:[*]_fmt_, _..._);
-Event printing:
-	void *tep_print_event*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_record pass:[*]_record_, bool _use_trace_clock_);
-	void *tep_print_event_data*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, struct tep_record pass:[*]_record_);
-	void *tep_event_info*(struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, struct tep_record pass:[*]_record_);
-	void *tep_print_event_task*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, struct tep_record pass:[*]_record_);
-	void *tep_print_event_time*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_event pass:[*]_event_, struct tep_record pass:[*]record, bool _use_trace_clock_);
-	void *tep_set_print_raw*(struct tep_handle pass:[*]_tep_, int _print_raw_);
 
 Event finding:
 	struct tep_event pass:[*]*tep_find_event*(struct tep_handle pass:[*]_tep_, int _id_);
@@ -116,7 +106,6 @@ Filter management:
 	int *tep_filter_compare*(struct tep_event_filter pass:[*]_filter1_, struct tep_event_filter pass:[*]_filter2_);
 
 Parsing various data from the records:
-	void *tep_data_latency_format*(struct tep_handle pass:[*]_tep_, struct trace_seq pass:[*]_s_, struct tep_record pass:[*]_record_);
 	int *tep_data_type*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_);
 	int *tep_data_pid*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_);
 	int *tep_data_preempt_count*(struct tep_handle pass:[*]_tep_, struct tep_record pass:[*]_rec_);

tools/lib/traceevent/Makefile

@@ -58,30 +58,6 @@ export man_dir man_dir_SQ INSTALL
 export DESTDIR DESTDIR_SQ
 export EVENT_PARSE_VERSION
 
-set_plugin_dir := 1
-
-# Set plugin_dir to preffered global plugin location
-# If we install under $HOME directory we go under
-# $(HOME)/.local/lib/traceevent/plugins
-#
-# We dont set PLUGIN_DIR in case we install under $HOME
-# directory, because by default the code looks under:
-# $(HOME)/.local/lib/traceevent/plugins by default.
-#
-ifeq ($(plugin_dir),)
-ifeq ($(prefix),$(HOME))
-override plugin_dir = $(HOME)/.local/lib/traceevent/plugins
-set_plugin_dir := 0
-else
-override plugin_dir = $(libdir)/traceevent/plugins
-endif
-endif
-
-ifeq ($(set_plugin_dir),1)
-PLUGIN_DIR = -DPLUGIN_DIR="$(plugin_dir)"
-PLUGIN_DIR_SQ = '$(subst ','\'',$(PLUGIN_DIR))'
-endif
-
 include ../../scripts/Makefile.include
 
 # copy a bit from Linux kbuild
@@ -105,7 +81,6 @@ export prefix libdir src obj
 # Shell quotes
 libdir_SQ = $(subst ','\'',$(libdir))
 libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
-plugin_dir_SQ = $(subst ','\'',$(plugin_dir))
 
 CONFIG_INCLUDES = 
 CONFIG_LIBS	=
@@ -151,29 +126,14 @@ MAKEOVERRIDES=
 export srctree OUTPUT CC LD CFLAGS V
 build := -f $(srctree)/tools/build/Makefile.build dir=. obj
 
-PLUGINS  = plugin_jbd2.so
-PLUGINS += plugin_hrtimer.so
-PLUGINS += plugin_kmem.so
-PLUGINS += plugin_kvm.so
-PLUGINS += plugin_mac80211.so
-PLUGINS += plugin_sched_switch.so
-PLUGINS += plugin_function.so
-PLUGINS += plugin_xen.so
-PLUGINS += plugin_scsi.so
-PLUGINS += plugin_cfg80211.so
-
-PLUGINS    := $(addprefix $(OUTPUT),$(PLUGINS))
-PLUGINS_IN := $(PLUGINS:.so=-in.o)
-
 TE_IN      := $(OUTPUT)libtraceevent-in.o
 LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET))
-DYNAMIC_LIST_FILE := $(OUTPUT)libtraceevent-dynamic-list
 
-CMD_TARGETS = $(LIB_TARGET) $(PLUGINS) $(DYNAMIC_LIST_FILE)
+CMD_TARGETS = $(LIB_TARGET)
 
 TARGETS = $(CMD_TARGETS)
 
-all: all_cmd
+all: all_cmd plugins
 
 all_cmd: $(CMD_TARGETS)
 
@@ -188,17 +148,6 @@ $(OUTPUT)libtraceevent.so.$(EVENT_PARSE_VERSION): $(TE_IN)
 $(OUTPUT)libtraceevent.a: $(TE_IN)
 	$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
 
-$(OUTPUT)libtraceevent-dynamic-list: $(PLUGINS)
-	$(QUIET_GEN)$(call do_generate_dynamic_list_file, $(PLUGINS), $@)
-
-plugins: $(PLUGINS)
-
-__plugin_obj = $(notdir $@)
-  plugin_obj = $(__plugin_obj:-in.o=)
-
-$(PLUGINS_IN): force
-	$(Q)$(MAKE) $(build)=$(plugin_obj)
-
 $(OUTPUT)%.so: $(OUTPUT)%-in.o
 	$(QUIET_LINK)$(CC) $(CFLAGS) -shared $(LDFLAGS) -nostartfiles -o $@ $^
 
@@ -258,25 +207,6 @@ define do_install
 	$(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2'
 endef
 
-define do_install_plugins
-	for plugin in $1; do				\
-	  $(call do_install,$$plugin,$(plugin_dir_SQ));	\
-	done
-endef
-
-define do_generate_dynamic_list_file
-	symbol_type=`$(NM) -u -D $1 | awk 'NF>1 {print $$1}' | \
-	xargs echo "U w W" | tr 'w ' 'W\n' | sort -u | xargs echo`;\
-	if [ "$$symbol_type" = "U W" ];then				\
-		(echo '{';						\
-		$(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\
-		echo '};';						\
-		) > $2;							\
-	else								\
-		(echo Either missing one of [$1] or bad version of $(NM)) 1>&2;\
-	fi
-endef
-
 PKG_CONFIG_FILE = libtraceevent.pc
 define do_install_pkgconfig_file
 	if [ -n "${pkgconfig_dir}" ]; then 					\
@@ -296,10 +226,6 @@ install_lib: all_cmd install_plugins install_headers install_pkgconfig
 		$(call do_install_mkdir,$(libdir_SQ)); \
 		cp -fpR $(LIB_INSTALL) $(DESTDIR)$(libdir_SQ)
 
-install_plugins: $(PLUGINS)
-	$(call QUIET_INSTALL, trace_plugins) \
-		$(call do_install_plugins, $(PLUGINS))
-
 install_pkgconfig:
 	$(call QUIET_INSTALL, $(PKG_CONFIG_FILE)) \
 		$(call do_install_pkgconfig_file,$(prefix))
@@ -313,7 +239,7 @@ install_headers:
 
 install: install_lib
 
-clean:
+clean: clean_plugins
 	$(call QUIET_CLEAN, libtraceevent) \
 		$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d .*.cmd; \
 		$(RM) TRACEEVENT-CFLAGS tags TAGS; \
@@ -351,7 +277,19 @@ help:
 	@echo '  doc-install         - install the man pages'
 	@echo '  doc-uninstall       - uninstall the man pages'
 	@echo''
-PHONY += force plugins
+
+PHONY += plugins
+plugins:
+	$(call descend,plugins)
+
+PHONY += install_plugins
+install_plugins:
+	$(call descend,plugins,install)
+
+PHONY += clean_plugins
+clean_plugins:
+	$(call descend,plugins,clean)
+
 force:
 
 # Declare the contents of the .PHONY variable as phony.  We keep that

tools/lib/traceevent/event-parse.c

@@ -4367,10 +4367,20 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s
 					switch (*ptr) {
 					case 's':
 					case 'S':
-					case 'f':
-					case 'F':
 					case 'x':
 						break;
+					case 'f':
+					case 'F':
+						/*
+						 * Pre-5.5 kernels use %pf and
+						 * %pF for printing symbols
+						 * while kernels since 5.5 use
+						 * %pfw for fwnodes. So check
+						 * %p[fF] isn't followed by 'w'.
+						 */
+						if (ptr[1] != 'w')
+							break;
+						/* fall through */
 					default:
 						/*
 						 * Older kernels do not process
@@ -4487,12 +4497,12 @@ get_bprint_format(void *data, int size __maybe_unused,
 
 	printk = find_printk(tep, addr);
 	if (!printk) {
-		if (asprintf(&format, "%%pf: (NO FORMAT FOUND at %llx)\n", addr) < 0)
+		if (asprintf(&format, "%%ps: (NO FORMAT FOUND at %llx)\n", addr) < 0)
 			return NULL;
 		return format;
 	}
 
-	if (asprintf(&format, "%s: %s", "%pf", printk->printk) < 0)
+	if (asprintf(&format, "%s: %s", "%ps", printk->printk) < 0)
 		return NULL;
 
 	return format;
@@ -5517,8 +5527,10 @@ static void print_event_time(struct tep_handle *tep, struct trace_seq *s,
 	if (divstr && isdigit(*(divstr + 1)))
 		div = atoi(divstr + 1);
 	time = record->ts;
-	if (div)
+	if (div) {
+		time += div / 2;
 		time /= div;
+	}
 	pr = prec;
 	while (pr--)
 		p10 *= 10;

tools/lib/traceevent/event-parse.h

@@ -441,6 +441,8 @@ int tep_register_print_string(struct tep_handle *tep, const char *fmt,
 			      unsigned long long addr);
 bool tep_is_pid_registered(struct tep_handle *tep, int pid);
 
+struct tep_event *tep_get_event(struct tep_handle *tep, int index);
+
 #define TEP_PRINT_INFO		"INFO"
 #define TEP_PRINT_INFO_RAW	"INFO_RAW"
 #define TEP_PRINT_COMM		"COMM"

tools/lib/traceevent/plugins/Build

@@ -0,0 +1,10 @@
+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/plugins/Makefile

@@ -0,0 +1,222 @@
+# SPDX-License-Identifier: GPL-2.0
+
+#MAKEFLAGS += --no-print-directory
+
+
+# Makefiles suck: This macro sets a default value of $(2) for the
+# variable named by $(1), unless the variable has been set by
+# environment or command line. This is necessary for CC and AR
+# because make sets default values, so the simpler ?= approach
+# won't work as expected.
+define allow-override
+  $(if $(or $(findstring environment,$(origin $(1))),\
+            $(findstring command line,$(origin $(1)))),,\
+    $(eval $(1) = $(2)))
+endef
+
+# Allow setting CC and AR, or setting CROSS_COMPILE as a prefix.
+$(call allow-override,CC,$(CROSS_COMPILE)gcc)
+$(call allow-override,AR,$(CROSS_COMPILE)ar)
+$(call allow-override,NM,$(CROSS_COMPILE)nm)
+$(call allow-override,PKG_CONFIG,pkg-config)
+
+EXT = -std=gnu99
+INSTALL = install
+
+# Use DESTDIR for installing into a different root directory.
+# This is useful for building a package. The program will be
+# installed in this directory as if it was the root directory.
+# Then the build tool can move it later.
+DESTDIR ?=
+DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
+
+LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
+ifeq ($(LP64), 1)
+  libdir_relative = lib64
+else
+  libdir_relative = lib
+endif
+
+prefix ?= /usr/local
+libdir = $(prefix)/$(libdir_relative)
+
+set_plugin_dir := 1
+
+# Set plugin_dir to preffered global plugin location
+# If we install under $HOME directory we go under
+# $(HOME)/.local/lib/traceevent/plugins
+#
+# We dont set PLUGIN_DIR in case we install under $HOME
+# directory, because by default the code looks under:
+# $(HOME)/.local/lib/traceevent/plugins by default.
+#
+ifeq ($(plugin_dir),)
+ifeq ($(prefix),$(HOME))
+override plugin_dir = $(HOME)/.local/lib/traceevent/plugins
+set_plugin_dir := 0
+else
+override plugin_dir = $(libdir)/traceevent/plugins
+endif
+endif
+
+ifeq ($(set_plugin_dir),1)
+PLUGIN_DIR = -DPLUGIN_DIR="$(plugin_dir)"
+PLUGIN_DIR_SQ = '$(subst ','\'',$(PLUGIN_DIR))'
+endif
+
+include ../../../scripts/Makefile.include
+
+# copy a bit from Linux kbuild
+
+ifeq ("$(origin V)", "command line")
+  VERBOSE = $(V)
+endif
+ifndef VERBOSE
+  VERBOSE = 0
+endif
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+#$(info Determined 'srctree' to be $(srctree))
+endif
+
+export prefix libdir src obj
+
+# Shell quotes
+plugin_dir_SQ = $(subst ','\'',$(plugin_dir))
+
+CONFIG_INCLUDES =
+CONFIG_LIBS    =
+CONFIG_FLAGS   =
+
+OBJ            = $@
+N              =
+
+INCLUDES = -I. -I.. -I $(srctree)/tools/include $(CONFIG_INCLUDES)
+
+# Set compile option CFLAGS
+ifdef EXTRA_CFLAGS
+  CFLAGS := $(EXTRA_CFLAGS)
+else
+  CFLAGS := -g -Wall
+endif
+
+# Append required CFLAGS
+override CFLAGS += -fPIC
+override CFLAGS += $(CONFIG_FLAGS) $(INCLUDES) $(PLUGIN_DIR_SQ)
+override CFLAGS += $(udis86-flags) -D_GNU_SOURCE
+
+ifeq ($(VERBOSE),1)
+  Q =
+else
+  Q = @
+endif
+
+# Disable command line variables (CFLAGS) override from top
+# level Makefile (perf), otherwise build Makefile will get
+# the same command line setup.
+MAKEOVERRIDES=
+
+export srctree OUTPUT CC LD CFLAGS V
+
+build := -f $(srctree)/tools/build/Makefile.build dir=. obj
+
+DYNAMIC_LIST_FILE := $(OUTPUT)libtraceevent-dynamic-list
+
+PLUGINS  = plugin_jbd2.so
+PLUGINS += plugin_hrtimer.so
+PLUGINS += plugin_kmem.so
+PLUGINS += plugin_kvm.so
+PLUGINS += plugin_mac80211.so
+PLUGINS += plugin_sched_switch.so
+PLUGINS += plugin_function.so
+PLUGINS += plugin_xen.so
+PLUGINS += plugin_scsi.so
+PLUGINS += plugin_cfg80211.so
+
+PLUGINS    := $(addprefix $(OUTPUT),$(PLUGINS))
+PLUGINS_IN := $(PLUGINS:.so=-in.o)
+
+plugins: $(PLUGINS) $(DYNAMIC_LIST_FILE)
+
+__plugin_obj = $(notdir $@)
+  plugin_obj = $(__plugin_obj:-in.o=)
+
+$(PLUGINS_IN): force
+	$(Q)$(MAKE) $(build)=$(plugin_obj)
+
+$(OUTPUT)libtraceevent-dynamic-list: $(PLUGINS)
+	$(QUIET_GEN)$(call do_generate_dynamic_list_file, $(PLUGINS), $@)
+
+$(OUTPUT)%.so: $(OUTPUT)%-in.o
+	$(QUIET_LINK)$(CC) $(CFLAGS) -shared $(LDFLAGS) -nostartfiles -o $@ $^
+
+define update_dir
+  (echo $1 > $@.tmp;                           \
+   if [ -r $@ ] && cmp -s $@ $@.tmp; then      \
+     rm -f $@.tmp;                             \
+   else                                                \
+     echo '  UPDATE                 $@';       \
+     mv -f $@.tmp $@;                          \
+   fi);
+endef
+
+tags:	force
+	$(RM) tags
+	find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px \
+	--regex-c++='/_PE\(([^,)]*).*/TEP_ERRNO__\1/'
+
+TAGS:	force
+	$(RM) TAGS
+	find . -name '*.[ch]' | xargs etags \
+	--regex='/_PE(\([^,)]*\).*/TEP_ERRNO__\1/'
+
+define do_install_mkdir
+	if [ ! -d '$(DESTDIR_SQ)$1' ]; then             \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1'; \
+	fi
+endef
+
+define do_install
+	$(call do_install_mkdir,$2);                    \
+	$(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2'
+endef
+
+define do_install_plugins
+       for plugin in $1; do                            \
+         $(call do_install,$$plugin,$(plugin_dir_SQ)); \
+       done
+endef
+
+define do_generate_dynamic_list_file
+	symbol_type=`$(NM) -u -D $1 | awk 'NF>1 {print $$1}' | \
+	xargs echo "U w W" | tr 'w ' 'W\n' | sort -u | xargs echo`;\
+	if [ "$$symbol_type" = "U W" ];then				\
+		(echo '{';                                              \
+		$(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\
+		echo '};';                                              \
+		) > $2;                                                 \
+	else                                                            \
+		(echo Either missing one of [$1] or bad version of $(NM)) 1>&2;\
+		fi
+endef
+
+install: $(PLUGINS)
+	$(call QUIET_INSTALL, trace_plugins) \
+	$(call do_install_plugins, $(PLUGINS))
+
+clean:
+	$(call QUIET_CLEAN, trace_plugins) \
+		$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d .*.cmd; \
+		$(RM) $(OUTPUT)libtraceevent-dynamic-list \
+		$(RM) TRACEEVENT-CFLAGS tags TAGS;
+
+PHONY += force plugins
+force:
+
+# Declare the contents of the .PHONY variable as phony.  We keep that
+# information in a variable so we can use it in if_changed and friends.
+.PHONY: $(PHONY)

tools/perf/Makefile.config

@@ -924,7 +924,7 @@ ifndef NO_JVMTI
     JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | awk '{print $$3}')
   else
     ifneq (,$(wildcard /usr/sbin/alternatives))
-      JDIR=$(shell /usr/sbin/alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g')
+      JDIR=$(shell /usr/sbin/alternatives --display java | tail -1 | cut -d' ' -f 5 | sed -e 's%/jre/bin/java.%%g' -e 's%/bin/java.%%g')
     endif
   endif
   ifndef JDIR

tools/perf/Makefile.perf

@@ -292,7 +292,7 @@ endif
 LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
 export LIBTRACEEVENT
 
-LIBTRACEEVENT_DYNAMIC_LIST = $(TE_PATH)libtraceevent-dynamic-list
+LIBTRACEEVENT_DYNAMIC_LIST = $(TE_PATH)plugins/libtraceevent-dynamic-list
 
 #
 # The static build has no dynsym table, so this does not work for
@@ -567,7 +567,7 @@ all: shell_compatibility_test $(ALL_PROGRAMS) $(LANG_BINDINGS) $(OTHER_PROGRAMS)
 # Create python binding output directory if not already present
 _dummy := $(shell [ -d '$(OUTPUT)python' ] || mkdir -p '$(OUTPUT)python')
 
-$(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST)
+$(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST) $(LIBPERF)
 	$(QUIET_GEN)LDSHARED="$(CC) -pthread -shared" \
         CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS)' \
 	  $(PYTHON_WORD) util/setup.py \
@@ -737,7 +737,7 @@ libtraceevent_plugins: FORCE
 	$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) plugins
 
 $(LIBTRACEEVENT_DYNAMIC_LIST): libtraceevent_plugins
-	$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent-dynamic-list
+	$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)plugins/libtraceevent-dynamic-list
 
 $(LIBTRACEEVENT)-clean:
 	$(call QUIET_CLEAN, libtraceevent)

tools/perf/arch/arm/util/cs-etm.c

@@ -23,9 +23,10 @@
 #include "../../util/event.h"
 #include "../../util/evlist.h"
 #include "../../util/evsel.h"
+#include "../../util/evsel_config.h"
 #include "../../util/pmu.h"
 #include "../../util/cs-etm.h"
-#include "../../util/util.h"
+#include <internal/lib.h> // page_size
 #include "../../util/session.h"
 
 #include <errno.h>
@@ -416,7 +417,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 		if (err)
 			goto out;
 
-		tracking_evsel = perf_evlist__last(evlist);
+		tracking_evsel = evlist__last(evlist);
 		perf_evlist__set_tracking_event(evlist, tracking_evsel);
 
 		tracking_evsel->core.attr.freq = 0;
@@ -648,7 +649,7 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
 	if (priv_size != cs_etm_info_priv_size(itr, session->evlist))
 		return -EINVAL;
 
-	if (!session->evlist->nr_mmaps)
+	if (!session->evlist->core.nr_mmaps)
 		return -EINVAL;
 
 	/* If the cpu_map is empty all online CPUs are involved */

tools/perf/arch/arm64/util/arm-spe.c

@@ -16,7 +16,7 @@
 #include "../../util/evsel.h"
 #include "../../util/evlist.h"
 #include "../../util/session.h"
-#include "../../util/util.h"
+#include <internal/lib.h> // page_size
 #include "../../util/pmu.h"
 #include "../../util/debug.h"
 #include "../../util/auxtrace.h"
@@ -51,7 +51,7 @@ static int arm_spe_info_fill(struct auxtrace_record *itr,
 	if (priv_size != ARM_SPE_AUXTRACE_PRIV_SIZE)
 		return -EINVAL;
 
-	if (!session->evlist->nr_mmaps)
+	if (!session->evlist->core.nr_mmaps)
 		return -EINVAL;
 
 	auxtrace_info->type = PERF_AUXTRACE_ARM_SPE;
@@ -129,7 +129,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	if (err)
 		return err;
 
-	tracking_evsel = perf_evlist__last(evlist);
+	tracking_evsel = evlist__last(evlist);
 	perf_evlist__set_tracking_event(evlist, tracking_evsel);
 
 	tracking_evsel->core.attr.freq = 0;

tools/perf/arch/arm64/util/dwarf-regs.c

@@ -11,7 +11,6 @@
 #include <dwarf-regs.h>
 #include <linux/ptrace.h> /* for struct user_pt_regs */
 #include <linux/stringify.h>
-#include "util.h"
 
 struct pt_regs_dwarfnum {
 	const char *name;

tools/perf/arch/arm64/util/header.c

@@ -1,5 +1,7 @@
 #include <stdio.h>
 #include <stdlib.h>
+#include <perf/cpumap.h>
+#include <internal/cpumap.h>
 #include <api/fs/fs.h>
 #include "debug.h"
 #include "header.h"
@@ -29,7 +31,7 @@ char *get_cpuid_str(struct perf_pmu *pmu)
 
 	/* read midr from list of cpus mapped to this pmu */
 	cpus = perf_cpu_map__get(pmu->cpus);
-	for (cpu = 0; cpu < cpus->nr; cpu++) {
+	for (cpu = 0; cpu < perf_cpu_map__nr(cpus); cpu++) {
 		scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR,
 				sysfs, cpus->map[cpu]);
 

tools/perf/arch/arm64/util/unwind-libunwind.c

@@ -5,8 +5,8 @@
 #include <libunwind.h>
 #include "perf_regs.h"
 #include "../../util/unwind.h"
-#include "../../util/debug.h"
 #endif
+#include "../../util/debug.h"
 
 int LIBUNWIND__ARCH_REG_ID(int regnum)
 {

tools/perf/arch/powerpc/util/dwarf-regs.c

@@ -12,7 +12,6 @@
 #include <linux/ptrace.h>
 #include <linux/kernel.h>
 #include <linux/stringify.h>
-#include "util.h"
 
 struct pt_regs_dwarfnum {
 	const char *name;

tools/perf/arch/powerpc/util/header.c

@@ -6,7 +6,6 @@
 #include <string.h>
 #include <linux/stringify.h>
 #include "header.h"
-#include "util.h"
 
 #define mfspr(rn)       ({unsigned long rval; \
 			 asm volatile("mfspr %0," __stringify(rn) \

tools/perf/arch/powerpc/util/kvm-stat.c

@@ -5,9 +5,11 @@
 #include "util/debug.h"
 #include "util/evsel.h"
 #include "util/evlist.h"
+#include "util/pmu.h"
 
 #include "book3s_hv_exits.h"
 #include "book3s_hcalls.h"
+#include <subcmd/parse-options.h>
 
 #define NR_TPS 4
 
@@ -172,3 +174,46 @@ int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid __maybe_unused)
 
 	return ret;
 }
+
+/*
+ * Incase of powerpc architecture, pmu registers are programmable
+ * by guest kernel. So monitoring guest via host may not provide
+ * valid samples with default 'cycles' event. It is better to use
+ * 'trace_imc/trace_cycles' event for guest profiling, since it
+ * can track the guest instruction pointer in the trace-record.
+ *
+ * Function to parse the arguments and return appropriate values.
+ */
+int kvm_add_default_arch_event(int *argc, const char **argv)
+{
+	const char **tmp;
+	bool event = false;
+	int i, j = *argc;
+
+	const struct option event_options[] = {
+		OPT_BOOLEAN('e', "event", &event, NULL),
+		OPT_END()
+	};
+
+	tmp = calloc(j + 1, sizeof(char *));
+	if (!tmp)
+		return -EINVAL;
+
+	for (i = 0; i < j; i++)
+		tmp[i] = argv[i];
+
+	parse_options(j, tmp, event_options, NULL, PARSE_OPT_KEEP_UNKNOWN);
+	if (!event) {
+		if (pmu_have_event("trace_imc", "trace_cycles")) {
+			argv[j++] = strdup("-e");
+			argv[j++] = strdup("trace_imc/trace_cycles/");
+			*argc += 2;
+		} else {
+			free(tmp);
+			return -EINVAL;
+		}
+	}
+
+	free(tmp);
+	return 0;
+}

tools/perf/arch/powerpc/util/skip-callchain-idx.c

@@ -13,6 +13,7 @@
 #include "util/callchain.h"
 #include "util/debug.h"
 #include "util/dso.h"
+#include "util/event.h" // struct ip_callchain
 #include "util/map.h"
 #include "util/symbol.h"
 

tools/perf/arch/powerpc/util/sym-handling.c

@@ -4,7 +4,6 @@
  * Copyright (C) 2015 Naveen N. Rao, IBM Corporation
  */
 
-#include "debug.h"
 #include "dso.h"
 #include "symbol.h"
 #include "map.h"

tools/perf/arch/s390/Makefile

@@ -4,6 +4,7 @@ PERF_HAVE_DWARF_REGS := 1
 endif
 HAVE_KVM_STAT_SUPPORT := 1
 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
+PERF_HAVE_JITDUMP := 1
 
 #
 # Syscall table generation for perf

tools/perf/arch/s390/util/auxtrace.c

@@ -1,4 +1,5 @@
 #include <stdbool.h>
+#include <stdlib.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/bitops.h>

tools/perf/arch/s390/util/machine.c

@@ -2,7 +2,7 @@
 #include <unistd.h>
 #include <stdio.h>
 #include <string.h>
-#include "util.h"
+#include <internal/lib.h> // page_size
 #include "machine.h"
 #include "api/fs/fs.h"
 #include "debug.h"

tools/perf/arch/x86/tests/intel-cqm.c

@@ -5,7 +5,7 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "arch-tests.h"
-#include "util.h"
+#include <internal/lib.h> // page_size
 
 #include <signal.h>
 #include <sys/mman.h>
@@ -63,9 +63,9 @@ int test__intel_cqm_count_nmi_context(struct test *test __maybe_unused, int subt
 		goto out;
 	}
 
-	evsel = perf_evlist__first(evlist);
+	evsel = evlist__first(evlist);
 	if (!evsel) {
-		pr_debug("perf_evlist__first failed\n");
+		pr_debug("evlist__first failed\n");
 		goto out;
 	}
 

tools/perf/arch/x86/tests/perf-time-to-tsc.c

@@ -15,9 +15,9 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "thread_map.h"
-#include "cpumap.h"
 #include "record.h"
 #include "tsc.h"
+#include "util/mmap.h"
 #include "tests/tests.h"
 
 #include "arch-tests.h"
@@ -66,7 +66,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 	union perf_event *event;
 	u64 test_tsc, comm1_tsc, comm2_tsc;
 	u64 test_time, comm1_time = 0, comm2_time = 0;
-	struct perf_mmap *md;
+	struct mmap *md;
 
 	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	CHECK_NOT_NULL__(threads);
@@ -83,7 +83,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 
 	perf_evlist__config(evlist, &opts, NULL);
 
-	evsel = perf_evlist__first(evlist);
+	evsel = evlist__first(evlist);
 
 	evsel->core.attr.comm = 1;
 	evsel->core.attr.disabled = 1;
@@ -91,9 +91,9 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 
 	CHECK__(evlist__open(evlist));
 
-	CHECK__(perf_evlist__mmap(evlist, UINT_MAX));
+	CHECK__(evlist__mmap(evlist, UINT_MAX));
 
-	pc = evlist->mmap[0].base;
+	pc = evlist->mmap[0].core.base;
 	ret = perf_read_tsc_conversion(pc, &tc);
 	if (ret) {
 		if (ret == -EOPNOTSUPP) {
@@ -115,7 +115,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 
 	evlist__disable(evlist);
 
-	for (i = 0; i < evlist->nr_mmaps; i++) {
+	for (i = 0; i < evlist->core.nr_mmaps; i++) {
 		md = &evlist->mmap[i];
 		if (perf_mmap__read_init(md) < 0)
 			continue;

tools/perf/arch/x86/tests/rdpmc.c

@@ -13,7 +13,7 @@
 #include "tests/tests.h"
 #include "cloexec.h"
 #include "event.h"
-#include "util.h"
+#include <internal/lib.h> // page_size
 #include "arch-tests.h"
 
 static u64 rdpmc(unsigned int counter)

tools/perf/arch/x86/util/archinsn.c

@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "../../../../arch/x86/include/asm/insn.h"
 #include "archinsn.h"
+#include "event.h"
 #include "machine.h"
 #include "thread.h"
 #include "symbol.h"

tools/perf/arch/x86/util/event.c

@@ -3,6 +3,8 @@
 #include <linux/string.h>
 #include <linux/zalloc.h>
 
+#include "../../util/event.h"
+#include "../../util/synthetic-events.h"
 #include "../../util/machine.h"
 #include "../../util/tool.h"
 #include "../../util/map.h"

tools/perf/arch/x86/util/intel-bts.c

@@ -15,6 +15,7 @@
 #include "../../util/event.h"
 #include "../../util/evsel.h"
 #include "../../util/evlist.h"
+#include "../../util/mmap.h"
 #include "../../util/session.h"
 #include "../../util/pmu.h"
 #include "../../util/debug.h"
@@ -22,7 +23,7 @@
 #include "../../util/tsc.h"
 #include "../../util/auxtrace.h"
 #include "../../util/intel-bts.h"
-#include "../../util/util.h"
+#include <internal/lib.h> // page_size
 
 #define KiB(x) ((x) * 1024)
 #define MiB(x) ((x) * 1024 * 1024)
@@ -74,10 +75,10 @@ static int intel_bts_info_fill(struct auxtrace_record *itr,
 	if (priv_size != INTEL_BTS_AUXTRACE_PRIV_SIZE)
 		return -EINVAL;
 
-	if (!session->evlist->nr_mmaps)
+	if (!session->evlist->core.nr_mmaps)
 		return -EINVAL;
 
-	pc = session->evlist->mmap[0].base;
+	pc = session->evlist->mmap[0].core.base;
 	if (pc) {
 		err = perf_read_tsc_conversion(pc, &tc);
 		if (err) {
@@ -230,7 +231,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr,
 		if (err)
 			return err;
 
-		tracking_evsel = perf_evlist__last(evlist);
+		tracking_evsel = evlist__last(evlist);
 
 		perf_evlist__set_tracking_event(evlist, tracking_evsel);
 

tools/perf/arch/x86/util/intel-pt.c

@@ -18,6 +18,7 @@
 #include "../../util/evlist.h"
 #include "../../util/evsel.h"
 #include "../../util/cpumap.h"
+#include "../../util/mmap.h"
 #include <subcmd/parse-options.h>
 #include "../../util/parse-events.h"
 #include "../../util/pmu.h"
@@ -26,7 +27,7 @@
 #include "../../util/record.h"
 #include "../../util/target.h"
 #include "../../util/tsc.h"
-#include "../../util/util.h"
+#include <internal/lib.h> // page_size
 #include "../../util/intel-pt.h"
 
 #define KiB(x) ((x) * 1024)
@@ -351,10 +352,10 @@ static int intel_pt_info_fill(struct auxtrace_record *itr,
 	filter = intel_pt_find_filter(session->evlist, ptr->intel_pt_pmu);
 	filter_str_len = filter ? strlen(filter) : 0;
 
-	if (!session->evlist->nr_mmaps)
+	if (!session->evlist->core.nr_mmaps)
 		return -EINVAL;
 
-	pc = session->evlist->mmap[0].base;
+	pc = session->evlist->mmap[0].core.base;
 	if (pc) {
 		err = perf_read_tsc_conversion(pc, &tc);
 		if (err) {
@@ -416,12 +417,12 @@ static int intel_pt_track_switches(struct evlist *evlist)
 		return err;
 	}
 
-	evsel = perf_evlist__last(evlist);
+	evsel = evlist__last(evlist);
 
 	perf_evsel__set_sample_bit(evsel, CPU);
 	perf_evsel__set_sample_bit(evsel, TIME);
 
-	evsel->system_wide = true;
+	evsel->core.system_wide = true;
 	evsel->no_aux_samples = true;
 	evsel->immediate = true;
 
@@ -716,13 +717,13 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 				if (err)
 					return err;
 
-				switch_evsel = perf_evlist__last(evlist);
+				switch_evsel = evlist__last(evlist);
 
 				switch_evsel->core.attr.freq = 0;
 				switch_evsel->core.attr.sample_period = 1;
 				switch_evsel->core.attr.context_switch = 1;
 
-				switch_evsel->system_wide = true;
+				switch_evsel->core.system_wide = true;
 				switch_evsel->no_aux_samples = true;
 				switch_evsel->immediate = true;
 
@@ -774,7 +775,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 		if (err)
 			return err;
 
-		tracking_evsel = perf_evlist__last(evlist);
+		tracking_evsel = evlist__last(evlist);
 
 		perf_evlist__set_tracking_event(evlist, tracking_evsel);
 

tools/perf/arch/x86/util/machine.c

@@ -1,9 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/types.h>
 #include <linux/string.h>
+#include <limits.h>
 #include <stdlib.h>
 
-#include "../../util/util.h"
+#include <internal/lib.h> // page_size
 #include "../../util/machine.h"
 #include "../../util/map.h"
 #include "../../util/symbol.h"

tools/perf/arch/x86/util/tsc.c

@@ -8,6 +8,8 @@
 #include <linux/types.h>
 #include <asm/barrier.h>
 #include "../../../util/debug.h"
+#include "../../../util/event.h"
+#include "../../../util/synthetic-events.h"
 #include "../../../util/tsc.h"
 
 int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,

tools/perf/arch/x86/util/unwind-libunwind.c

@@ -1,11 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <errno.h>
+#include "../../util/debug.h"
 #ifndef REMOTE_UNWIND_LIBUNWIND
 #include <libunwind.h>
 #include "perf_regs.h"
 #include "../../util/unwind.h"
-#include "../../util/debug.h"
 #endif
 
 #ifdef HAVE_ARCH_X86_64_SUPPORT

tools/perf/bench/epoll-ctl.c

@@ -21,12 +21,12 @@
 #include <sys/resource.h>
 #include <sys/epoll.h>
 #include <sys/eventfd.h>
+#include <internal/cpumap.h>
 #include <perf/cpumap.h>
 
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
 #include "bench.h"
-#include "cpumap.h"
 
 #include <err.h>
 

tools/perf/bench/epoll-wait.c

@@ -76,12 +76,12 @@
 #include <sys/epoll.h>
 #include <sys/eventfd.h>
 #include <sys/types.h>
+#include <internal/cpumap.h>
 #include <perf/cpumap.h>
 
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
 #include "bench.h"
-#include "cpumap.h"
 
 #include <err.h>
 

tools/perf/bench/futex-hash.c

@@ -20,13 +20,13 @@
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
 #include <sys/time.h>
+#include <internal/cpumap.h>
 #include <perf/cpumap.h>
 
 #include "../util/stat.h"
 #include <subcmd/parse-options.h>
 #include "bench.h"
 #include "futex.h"
-#include "cpumap.h"
 
 #include <err.h>
 

tools/perf/bench/futex-lock-pi.c

@@ -14,10 +14,10 @@
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
 #include <errno.h>
+#include <internal/cpumap.h>
 #include <perf/cpumap.h>
 #include "bench.h"
 #include "futex.h"
-#include "cpumap.h"
 
 #include <err.h>
 #include <stdlib.h>

tools/perf/bench/futex-requeue.c

@@ -20,10 +20,10 @@
 #include <linux/kernel.h>
 #include <linux/time64.h>
 #include <errno.h>
+#include <internal/cpumap.h>
 #include <perf/cpumap.h>
 #include "bench.h"
 #include "futex.h"
-#include "cpumap.h"
 
 #include <err.h>
 #include <stdlib.h>

tools/perf/bench/futex-wake-parallel.c

@@ -29,7 +29,8 @@ int bench_futex_wake_parallel(int argc __maybe_unused, const char **argv __maybe
 #include <linux/time64.h>
 #include <errno.h>
 #include "futex.h"
-#include "cpumap.h"
+#include <internal/cpumap.h>
+#include <perf/cpumap.h>
 
 #include <err.h>
 #include <stdlib.h>

tools/perf/bench/futex-wake.c

@@ -20,10 +20,10 @@
 #include <linux/kernel.h>
 #include <linux/time64.h>
 #include <errno.h>
+#include <internal/cpumap.h>
 #include <perf/cpumap.h>
 #include "bench.h"
 #include "futex.h"
-#include "cpumap.h"
 
 #include <err.h>
 #include <stdlib.h>

tools/perf/bench/numa.c

@@ -9,7 +9,6 @@
 /* For the CLR_() macros */
 #include <pthread.h>
 
-#include "../builtin.h"
 #include <subcmd/parse-options.h>
 #include "../util/cloexec.h"
 

tools/perf/bench/sched-messaging.c

@@ -10,9 +10,7 @@
  *
  */
 
-#include "../util/util.h"
 #include <subcmd/parse-options.h>
-#include "../builtin.h"
 #include "bench.h"
 
 /* Test groups of 20 processes spraying to 20 receivers */

tools/perf/bench/sched-pipe.c

@@ -9,9 +9,7 @@
  *  http://people.redhat.com/mingo/cfs-scheduler/tools/pipe-test-1m.c
  * Ported to perf by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
  */
-#include "../util/util.h"
 #include <subcmd/parse-options.h>
-#include "../builtin.h"
 #include "bench.h"
 
 #include <unistd.h>

tools/perf/builtin-annotate.c

@@ -27,6 +27,7 @@
 #include "util/sort.h"
 #include "util/hist.h"
 #include "util/dso.h"
+#include "util/machine.h"
 #include "util/map.h"
 #include "util/session.h"
 #include "util/tool.h"
@@ -39,6 +40,7 @@
 #include <dlfcn.h>
 #include <errno.h>
 #include <linux/bitmap.h>
+#include <linux/err.h>
 
 struct perf_annotate {
 	struct perf_tool tool;
@@ -583,8 +585,8 @@ int cmd_annotate(int argc, const char **argv)
 	data.path = input_name;
 
 	annotate.session = perf_session__new(&data, false, &annotate.tool);
-	if (annotate.session == NULL)
+	if (IS_ERR(annotate.session))
-		return -1;
+		return PTR_ERR(annotate.session);
 
 	annotate.has_br_stack = perf_header__has_feat(&annotate.session->header,
 						      HEADER_BRANCH_STACK);

tools/perf/builtin-buildid-cache.c

@@ -28,6 +28,7 @@
 #include "util/util.h"
 #include "util/probe-file.h"
 #include <linux/string.h>
+#include <linux/err.h>
 
 static int build_id_cache__kcore_buildid(const char *proc_dir, char *sbuildid)
 {
@@ -422,8 +423,8 @@ int cmd_buildid_cache(int argc, const char **argv)
 		data.force = force;
 
 		session = perf_session__new(&data, false, NULL);
-		if (session == NULL)
+		if (IS_ERR(session))
-			return -1;
+			return PTR_ERR(session);
 	}
 
 	if (symbol__init(session ? &session->header.env : NULL) < 0)

tools/perf/builtin-buildid-list.c

@@ -18,6 +18,7 @@
 #include "util/symbol.h"
 #include "util/data.h"
 #include <errno.h>
+#include <linux/err.h>
 
 static int sysfs__fprintf_build_id(FILE *fp)
 {
@@ -65,8 +66,8 @@ static int perf_session__list_build_ids(bool force, bool with_hits)
 		goto out;
 
 	session = perf_session__new(&data, false, &build_id__mark_dso_hit_ops);
-	if (session == NULL)
+	if (IS_ERR(session))
-		return -1;
+		return PTR_ERR(session);
 
 	/*
 	 * We take all buildids when the file contains AUX area tracing data

tools/perf/builtin-c2c.c

@@ -13,6 +13,7 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <linux/compiler.h>
+#include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/stringify.h>
 #include <linux/zalloc.h>
@@ -20,6 +21,7 @@
 #include <sys/param.h>
 #include "debug.h"
 #include "builtin.h"
+#include <perf/cpumap.h>
 #include <subcmd/pager.h>
 #include <subcmd/parse-options.h>
 #include "map_symbol.h"
@@ -2780,8 +2782,9 @@ static int perf_c2c__report(int argc, const char **argv)
 	}
 
 	session = perf_session__new(&data, 0, &c2c.tool);
-	if (session == NULL) {
+	if (IS_ERR(session)) {
-		pr_debug("No memory for session\n");
+		err = PTR_ERR(session);
+		pr_debug("Error creating perf session\n");
 		goto out;
 	}
 

tools/perf/builtin-config.c

@@ -9,7 +9,6 @@
 
 #include "util/cache.h"
 #include <subcmd/parse-options.h>
-#include "util/util.h"
 #include "util/debug.h"
 #include "util/config.h"
 #include <linux/string.h>

tools/perf/builtin-diff.c

@@ -23,6 +23,7 @@
 #include "util/time-utils.h"
 #include "util/annotate.h"
 #include "util/map.h"
+#include <linux/err.h>
 #include <linux/zalloc.h>
 #include <subcmd/pager.h>
 #include <subcmd/parse-options.h>
@@ -1153,9 +1154,9 @@ static int check_file_brstack(void)
 
 	data__for_each_file(i, d) {
 		d->session = perf_session__new(&d->data, false, &pdiff.tool);
-		if (!d->session) {
+		if (IS_ERR(d->session)) {
 			pr_err("Failed to open %s\n", d->data.path);
-			return -1;
+			return PTR_ERR(d->session);
 		}
 
 		has_br_stack = perf_header__has_feat(&d->session->header,
@@ -1185,9 +1186,9 @@ static int __cmd_diff(void)
 
 	data__for_each_file(i, d) {
 		d->session = perf_session__new(&d->data, false, &pdiff.tool);
-		if (!d->session) {
+		if (IS_ERR(d->session)) {
+			ret = PTR_ERR(d->session);
 			pr_err("Failed to open %s\n", d->data.path);
-			ret = -1;
 			goto out_delete;
 		}
 

tools/perf/builtin-evlist.c

@@ -5,18 +5,18 @@
  */
 #include "builtin.h"
 
-#include "util/util.h"
-
 #include <linux/list.h>
 
 #include "perf.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
+#include "util/evsel_fprintf.h"
 #include "util/parse-events.h"
 #include <subcmd/parse-options.h>
 #include "util/session.h"
 #include "util/data.h"
 #include "util/debug.h"
+#include <linux/err.h>
 
 static int __cmd_evlist(const char *file_name, struct perf_attr_details *details)
 {
@@ -30,8 +30,8 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details
 	bool has_tracepoint = false;
 
 	session = perf_session__new(&data, 0, NULL);
-	if (session == NULL)
+	if (IS_ERR(session))
-		return -1;
+		return PTR_ERR(session);
 
 	evlist__for_each_entry(session->evlist, pos) {
 		perf_evsel__fprintf(pos, details, stdout);

tools/perf/builtin-inject.c

@@ -21,7 +21,9 @@
 #include "util/auxtrace.h"
 #include "util/jit.h"
 #include "util/symbol.h"
+#include "util/synthetic-events.h"
 #include "util/thread.h"
+#include <linux/err.h>
 
 #include <subcmd/parse-options.h>
 
@@ -834,8 +836,8 @@ int cmd_inject(int argc, const char **argv)
 
 	data.path = inject.input_name;
 	inject.session = perf_session__new(&data, true, &inject.tool);
-	if (inject.session == NULL)
+	if (IS_ERR(inject.session))
-		return -1;
+		return PTR_ERR(inject.session);
 
 	if (zstd_init(&(inject.session->zstd_data), 0) < 0)
 		pr_warning("Decompression initialization failed.\n");

tools/perf/builtin-kmem.c

@@ -14,6 +14,7 @@
 #include "util/tool.h"
 #include "util/callchain.h"
 #include "util/time-utils.h"
+#include <linux/err.h>
 
 #include <subcmd/pager.h>
 #include <subcmd/parse-options.h>
@@ -1956,8 +1957,8 @@ int cmd_kmem(int argc, const char **argv)
 	data.path = input_name;
 
 	kmem_session = session = perf_session__new(&data, false, &perf_kmem);
-	if (session == NULL)
+	if (IS_ERR(session))
-		return -1;
+		return PTR_ERR(session);
 
 	ret = -1;
 

tools/perf/builtin-kvm.c

@@ -5,6 +5,7 @@
 #include "util/build-id.h"
 #include "util/evsel.h"
 #include "util/evlist.h"
+#include "util/mmap.h"
 #include "util/term.h"
 #include "util/symbol.h"
 #include "util/thread.h"
@@ -17,9 +18,11 @@
 #include "util/debug.h"
 #include "util/tool.h"
 #include "util/stat.h"
+#include "util/synthetic-events.h"
 #include "util/top.h"
 #include "util/data.h"
 #include "util/ordered-events.h"
+#include "util/kvm-stat.h"
 #include "ui/ui.h"
 
 #include <sys/prctl.h>
@@ -31,6 +34,7 @@
 #include <sys/stat.h>
 #include <fcntl.h>
 
+#include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/time64.h>
@@ -58,7 +62,6 @@ static const char *get_filename_for_perf_kvm(void)
 }
 
 #ifdef HAVE_KVM_STAT_SUPPORT
-#include "util/kvm-stat.h"
 
 void exit_event_get_key(struct evsel *evsel,
 			struct perf_sample *sample,
@@ -748,7 +751,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 {
 	struct evlist *evlist = kvm->evlist;
 	union perf_event *event;
-	struct perf_mmap *md;
+	struct mmap *md;
 	u64 timestamp;
 	s64 n = 0;
 	int err;
@@ -799,7 +802,7 @@ static int perf_kvm__mmap_read(struct perf_kvm_stat *kvm)
 	s64 n, ntotal = 0;
 	u64 flush_time = ULLONG_MAX, mmap_time;
 
-	for (i = 0; i < kvm->evlist->nr_mmaps; i++) {
+	for (i = 0; i < kvm->evlist->core.nr_mmaps; i++) {
 		n = perf_kvm__mmap_read_idx(kvm, i, &mmap_time);
 		if (n < 0)
 			return -1;
@@ -964,10 +967,10 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm)
 		goto out;
 	}
 
-	if (perf_evlist__add_pollfd(kvm->evlist, kvm->timerfd) < 0)
+	if (evlist__add_pollfd(kvm->evlist, kvm->timerfd) < 0)
 		goto out;
 
-	nr_stdin = perf_evlist__add_pollfd(kvm->evlist, fileno(stdin));
+	nr_stdin = evlist__add_pollfd(kvm->evlist, fileno(stdin));
 	if (nr_stdin < 0)
 		goto out;
 
@@ -978,7 +981,7 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm)
 	evlist__enable(kvm->evlist);
 
 	while (!done) {
-		struct fdarray *fda = &kvm->evlist->pollfd;
+		struct fdarray *fda = &kvm->evlist->core.pollfd;
 		int rc;
 
 		rc = perf_kvm__mmap_read(kvm);
@@ -1058,7 +1061,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
 		goto out;
 	}
 
-	if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages) < 0) {
+	if (evlist__mmap(evlist, kvm->opts.mmap_pages) < 0) {
 		ui__error("Failed to mmap the events: %s\n",
 			  str_error_r(errno, sbuf, sizeof(sbuf)));
 		evlist__close(evlist);
@@ -1090,9 +1093,9 @@ static int read_events(struct perf_kvm_stat *kvm)
 
 	kvm->tool = eops;
 	kvm->session = perf_session__new(&file, false, &kvm->tool);
-	if (!kvm->session) {
+	if (IS_ERR(kvm->session)) {
 		pr_err("Initializing perf session failed\n");
-		return -1;
+		return PTR_ERR(kvm->session);
 	}
 
 	symbol__init(&kvm->session->header.env);
@@ -1445,8 +1448,8 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	 * perf session
 	 */
 	kvm->session = perf_session__new(&data, false, &kvm->tool);
-	if (kvm->session == NULL) {
+	if (IS_ERR(kvm->session)) {
-		err = -1;
+		err = PTR_ERR(kvm->session);
 		goto out;
 	}
 	kvm->session->evlist = kvm->evlist;
@@ -1513,11 +1516,21 @@ perf_stat:
 }
 #endif /* HAVE_KVM_STAT_SUPPORT */
 
+int __weak kvm_add_default_arch_event(int *argc __maybe_unused,
+					const char **argv __maybe_unused)
+{
+	return 0;
+}
+
 static int __cmd_record(const char *file_name, int argc, const char **argv)
 {
-	int rec_argc, i = 0, j;
+	int rec_argc, i = 0, j, ret;
 	const char **rec_argv;
 
+	ret = kvm_add_default_arch_event(&argc, argv);
+	if (ret)
+		return -EINVAL;
+
 	rec_argc = argc + 2;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 	rec_argv[i++] = strdup("record");

tools/perf/builtin-list.c

@@ -81,9 +81,9 @@ int cmd_list(int argc, const char **argv)
 						long_desc_flag, details_flag);
 		else if (strcmp(argv[i], "sdt") == 0)
 			print_sdt_events(NULL, NULL, raw_dump);
-		else if (strcmp(argv[i], "metric") == 0)
+		else if (strcmp(argv[i], "metric") == 0 || strcmp(argv[i], "metrics") == 0)
 			metricgroup__print(true, false, NULL, raw_dump, details_flag);
-		else if (strcmp(argv[i], "metricgroup") == 0)
+		else if (strcmp(argv[i], "metricgroup") == 0 || strcmp(argv[i], "metricgroups") == 0)
 			metricgroup__print(false, true, NULL, raw_dump, details_flag);
 		else if ((sep = strchr(argv[i], ':')) != NULL) {
 			int sep_idx;

tools/perf/builtin-lock.c

@@ -30,6 +30,7 @@
 #include <linux/hash.h>
 #include <linux/kernel.h>
 #include <linux/zalloc.h>
+#include <linux/err.h>
 
 static struct perf_session *session;
 
@@ -872,9 +873,9 @@ static int __cmd_report(bool display_info)
 	};
 
 	session = perf_session__new(&data, false, &eops);
-	if (!session) {
+	if (IS_ERR(session)) {
 		pr_err("Initializing perf session failed\n");
-		return -1;
+		return PTR_ERR(session);
 	}
 
 	symbol__init(&session->header.env);

tools/perf/builtin-mem.c

@@ -17,6 +17,7 @@
 #include "util/dso.h"
 #include "util/map.h"
 #include "util/symbol.h"
+#include <linux/err.h>
 
 #define MEM_OPERATION_LOAD	0x1
 #define MEM_OPERATION_STORE	0x2
@@ -249,8 +250,8 @@ static int report_raw_events(struct perf_mem *mem)
 	struct perf_session *session = perf_session__new(&data, false,
 							 &mem->tool);
 
-	if (session == NULL)
+	if (IS_ERR(session))
-		return -1;
+		return PTR_ERR(session);
 
 	if (mem->cpu_list) {
 		ret = perf_session__cpu_bitmap(session, mem->cpu_list,

tools/perf/builtin-record.c

@@ -20,6 +20,7 @@
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/debug.h"
+#include "util/mmap.h"
 #include "util/target.h"
 #include "util/session.h"
 #include "util/tool.h"
@@ -38,6 +39,7 @@
 #include "util/trigger.h"
 #include "util/perf-hooks.h"
 #include "util/cpu-set-sched.h"
+#include "util/synthetic-events.h"
 #include "util/time-utils.h"
 #include "util/units.h"
 #include "util/bpf-event.h"
@@ -53,6 +55,7 @@
 #include <signal.h>
 #include <sys/mman.h>
 #include <sys/wait.h>
+#include <linux/err.h>
 #include <linux/string.h>
 #include <linux/time64.h>
 #include <linux/zalloc.h>
@@ -117,7 +120,7 @@ static bool switch_output_time(struct record *rec)
 	       trigger_is_ready(&switch_output_trigger);
 }
 
-static int record__write(struct record *rec, struct perf_mmap *map __maybe_unused,
+static int record__write(struct record *rec, struct mmap *map __maybe_unused,
 			 void *bf, size_t size)
 {
 	struct perf_data_file *file = &rec->session->data->file;
@@ -166,7 +169,7 @@ static int record__aio_write(struct aiocb *cblock, int trace_fd,
 	return rc;
 }
 
-static int record__aio_complete(struct perf_mmap *md, struct aiocb *cblock)
+static int record__aio_complete(struct mmap *md, struct aiocb *cblock)
 {
 	void *rem_buf;
 	off_t rem_off;
@@ -212,7 +215,7 @@ static int record__aio_complete(struct perf_mmap *md, struct aiocb *cblock)
 	return rc;
 }
 
-static int record__aio_sync(struct perf_mmap *md, bool sync_all)
+static int record__aio_sync(struct mmap *md, bool sync_all)
 {
 	struct aiocb **aiocb = md->aio.aiocb;
 	struct aiocb *cblocks = md->aio.cblocks;
@@ -253,12 +256,12 @@ struct record_aio {
 	size_t		size;
 };
 
-static int record__aio_pushfn(struct perf_mmap *map, void *to, void *buf, size_t size)
+static int record__aio_pushfn(struct mmap *map, void *to, void *buf, size_t size)
 {
 	struct record_aio *aio = to;
 
 	/*
-	 * map->base data pointed by buf is copied into free map->aio.data[] buffer
+	 * map->core.base data pointed by buf is copied into free map->aio.data[] buffer
 	 * to release space in the kernel buffer as fast as possible, calling
 	 * perf_mmap__consume() from perf_mmap__push() function.
 	 *
@@ -298,7 +301,7 @@ static int record__aio_pushfn(struct perf_mmap *map, void *to, void *buf, size_t
 	return size;
 }
 
-static int record__aio_push(struct record *rec, struct perf_mmap *map, off_t *off)
+static int record__aio_push(struct record *rec, struct mmap *map, off_t *off)
 {
 	int ret, idx;
 	int trace_fd = rec->session->data->file.fd;
@@ -349,15 +352,15 @@ static void record__aio_mmap_read_sync(struct record *rec)
 {
 	int i;
 	struct evlist *evlist = rec->evlist;
-	struct perf_mmap *maps = evlist->mmap;
+	struct mmap *maps = evlist->mmap;
 
 	if (!record__aio_enabled(rec))
 		return;
 
-	for (i = 0; i < evlist->nr_mmaps; i++) {
+	for (i = 0; i < evlist->core.nr_mmaps; i++) {
-		struct perf_mmap *map = &maps[i];
+		struct mmap *map = &maps[i];
 
-		if (map->base)
+		if (map->core.base)
 			record__aio_sync(map, true);
 	}
 }
@@ -385,7 +388,7 @@ static int record__aio_parse(const struct option *opt,
 #else /* HAVE_AIO_SUPPORT */
 static int nr_cblocks_max = 0;
 
-static int record__aio_push(struct record *rec __maybe_unused, struct perf_mmap *map __maybe_unused,
+static int record__aio_push(struct record *rec __maybe_unused, struct mmap *map __maybe_unused,
 			    off_t *off __maybe_unused)
 {
 	return -1;
@@ -437,7 +440,7 @@ static int record__mmap_flush_parse(const struct option *opt,
 	if (!opts->mmap_flush)
 		opts->mmap_flush = MMAP_FLUSH_DEFAULT;
 
-	flush_max = perf_evlist__mmap_size(opts->mmap_pages);
+	flush_max = evlist__mmap_size(opts->mmap_pages);
 	flush_max /= 4;
 	if (opts->mmap_flush > flush_max)
 		opts->mmap_flush = flush_max;
@@ -480,7 +483,7 @@ static int process_synthesized_event(struct perf_tool *tool,
 	return record__write(rec, NULL, event, event->header.size);
 }
 
-static int record__pushfn(struct perf_mmap *map, void *to, void *bf, size_t size)
+static int record__pushfn(struct mmap *map, void *to, void *bf, size_t size)
 {
 	struct record *rec = to;
 
@@ -525,7 +528,7 @@ static void record__sig_exit(void)
 #ifdef HAVE_AUXTRACE_SUPPORT
 
 static int record__process_auxtrace(struct perf_tool *tool,
-				    struct perf_mmap *map,
+				    struct mmap *map,
 				    union perf_event *event, void *data1,
 				    size_t len1, void *data2, size_t len2)
 {
@@ -563,7 +566,7 @@ static int record__process_auxtrace(struct perf_tool *tool,
 }
 
 static int record__auxtrace_mmap_read(struct record *rec,
-				      struct perf_mmap *map)
+				      struct mmap *map)
 {
 	int ret;
 
@@ -579,7 +582,7 @@ static int record__auxtrace_mmap_read(struct record *rec,
 }
 
 static int record__auxtrace_mmap_read_snapshot(struct record *rec,
-					       struct perf_mmap *map)
+					       struct mmap *map)
 {
 	int ret;
 
@@ -600,8 +603,8 @@ static int record__auxtrace_read_snapshot_all(struct record *rec)
 	int i;
 	int rc = 0;
 
-	for (i = 0; i < rec->evlist->nr_mmaps; i++) {
+	for (i = 0; i < rec->evlist->core.nr_mmaps; i++) {
-		struct perf_mmap *map = &rec->evlist->mmap[i];
+		struct mmap *map = &rec->evlist->mmap[i];
 
 		if (!map->auxtrace_mmap.base)
 			continue;
@@ -666,7 +669,7 @@ static int record__auxtrace_init(struct record *rec)
 
 static inline
 int record__auxtrace_mmap_read(struct record *rec __maybe_unused,
-			       struct perf_mmap *map __maybe_unused)
+			       struct mmap *map __maybe_unused)
 {
 	return 0;
 }
@@ -705,7 +708,7 @@ static int record__mmap_evlist(struct record *rec,
 	if (opts->affinity != PERF_AFFINITY_SYS)
 		cpu__setup_cpunode_map();
 
-	if (perf_evlist__mmap_ex(evlist, opts->mmap_pages,
+	if (evlist__mmap_ex(evlist, opts->mmap_pages,
 				 opts->auxtrace_mmap_pages,
 				 opts->auxtrace_snapshot_mode,
 				 opts->nr_cblocks, opts->affinity,
@@ -753,9 +756,9 @@ static int record__open(struct record *rec)
 		if (perf_evlist__add_dummy(evlist))
 			return -ENOMEM;
 
-		pos = perf_evlist__first(evlist);
+		pos = evlist__first(evlist);
 		pos->tracking = 0;
-		pos = perf_evlist__last(evlist);
+		pos = evlist__last(evlist);
 		pos->tracking = 1;
 		pos->core.attr.enable_on_exec = 1;
 	}
@@ -786,6 +789,17 @@ try_again:
 		pos->supported = true;
 	}
 
+	if (symbol_conf.kptr_restrict && !perf_evlist__exclude_kernel(evlist)) {
+		pr_warning(
+"WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
+"check /proc/sys/kernel/kptr_restrict and /proc/sys/kernel/perf_event_paranoid.\n\n"
+"Samples in kernel functions may not be resolved if a suitable vmlinux\n"
+"file is not found in the buildid cache or in the vmlinux path.\n\n"
+"Samples in kernel modules won't be resolved at all.\n\n"
+"If some relocation was applied (e.g. kexec) symbols may be misresolved\n"
+"even with a suitable vmlinux or kallsyms file.\n\n");
+	}
+
 	if (perf_evlist__apply_filters(evlist, &pos)) {
 		pr_err("failed to set filter \"%s\" on event %s with %d (%s)\n",
 			pos->filter, perf_evsel__name(pos), errno,
@@ -888,7 +902,7 @@ static struct perf_event_header finished_round_event = {
 	.type = PERF_RECORD_FINISHED_ROUND,
 };
 
-static void record__adjust_affinity(struct record *rec, struct perf_mmap *map)
+static void record__adjust_affinity(struct record *rec, struct mmap *map)
 {
 	if (rec->opts.affinity != PERF_AFFINITY_SYS &&
 	    !CPU_EQUAL(&rec->affinity_mask, &map->affinity_mask)) {
@@ -935,7 +949,7 @@ static int record__mmap_read_evlist(struct record *rec, struct evlist *evlist,
 	u64 bytes_written = rec->bytes_written;
 	int i;
 	int rc = 0;
-	struct perf_mmap *maps;
+	struct mmap *maps;
 	int trace_fd = rec->data.file.fd;
 	off_t off = 0;
 
@@ -952,20 +966,20 @@ static int record__mmap_read_evlist(struct record *rec, struct evlist *evlist,
 	if (record__aio_enabled(rec))
 		off = record__aio_get_pos(trace_fd);
 
-	for (i = 0; i < evlist->nr_mmaps; i++) {
+	for (i = 0; i < evlist->core.nr_mmaps; i++) {
 		u64 flush = 0;
-		struct perf_mmap *map = &maps[i];
+		struct mmap *map = &maps[i];
 
-		if (map->base) {
+		if (map->core.base) {
 			record__adjust_affinity(rec, map);
 			if (synch) {
-				flush = map->flush;
+				flush = map->core.flush;
-				map->flush = 1;
+				map->core.flush = 1;
 			}
 			if (!record__aio_enabled(rec)) {
 				if (perf_mmap__push(map, rec, record__pushfn) < 0) {
 					if (synch)
-						map->flush = flush;
+						map->core.flush = flush;
 					rc = -1;
 					goto out;
 				}
@@ -973,13 +987,13 @@ static int record__mmap_read_evlist(struct record *rec, struct evlist *evlist,
 				if (record__aio_push(rec, map, &off) < 0) {
 					record__aio_set_pos(trace_fd, off);
 					if (synch)
-						map->flush = flush;
+						map->core.flush = flush;
 					rc = -1;
 					goto out;
 				}
 			}
 			if (synch)
-				map->flush = flush;
+				map->core.flush = flush;
 		}
 
 		if (map->auxtrace_mmap.base && !rec->opts.auxtrace_snapshot_mode &&
@@ -1180,23 +1194,14 @@ static void workload_exec_failed_signal(int signo __maybe_unused,
 static void snapshot_sig_handler(int sig);
 static void alarm_sig_handler(int sig);
 
-int __weak
-perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused,
-			    struct perf_tool *tool __maybe_unused,
-			    perf_event__handler_t process __maybe_unused,
-			    struct machine *machine __maybe_unused)
-{
-	return 0;
-}
-
 static const struct perf_event_mmap_page *
 perf_evlist__pick_pc(struct evlist *evlist)
 {
 	if (evlist) {
-		if (evlist->mmap && evlist->mmap[0].base)
+		if (evlist->mmap && evlist->mmap[0].core.base)
-			return evlist->mmap[0].base;
+			return evlist->mmap[0].core.base;
-		if (evlist->overwrite_mmap && evlist->overwrite_mmap[0].base)
+		if (evlist->overwrite_mmap && evlist->overwrite_mmap[0].core.base)
-			return evlist->overwrite_mmap[0].base;
+			return evlist->overwrite_mmap[0].core.base;
 	}
 	return NULL;
 }
@@ -1362,9 +1367,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	}
 
 	session = perf_session__new(data, false, tool);
-	if (session == NULL) {
+	if (IS_ERR(session)) {
 		pr_err("Perf session creation failed.\n");
-		return -1;
+		return PTR_ERR(session);
 	}
 
 	fd = perf_data__fd(data);
@@ -1407,7 +1412,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		err = -1;
 		goto out_child;
 	}
-	session->header.env.comp_mmap_len = session->evlist->mmap_len;
+	session->header.env.comp_mmap_len = session->evlist->core.mmap_len;
 
 	err = bpf__apply_obj_config();
 	if (err) {
@@ -1610,7 +1615,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		if (hits == rec->samples) {
 			if (done || draining)
 				break;
-			err = perf_evlist__poll(rec->evlist, -1);
+			err = evlist__poll(rec->evlist, -1);
 			/*
 			 * Propagate error, only if there's any. Ignore positive
 			 * number of returned events and interrupt error.
@@ -1619,7 +1624,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 				err = 0;
 			waking++;
 
-			if (perf_evlist__filter_pollfd(rec->evlist, POLLERR | POLLHUP) == 0)
+			if (evlist__filter_pollfd(rec->evlist, POLLERR | POLLHUP) == 0)
 				draining = true;
 		}
 
@@ -1976,7 +1981,7 @@ out_free:
 
 static void switch_output_size_warn(struct record *rec)
 {
-	u64 wakeup_size = perf_evlist__mmap_size(rec->opts.mmap_pages);
+	u64 wakeup_size = evlist__mmap_size(rec->opts.mmap_pages);
 	struct switch_output *s = &rec->switch_output;
 
 	wakeup_size /= 2;
@@ -2371,16 +2376,6 @@ int cmd_record(int argc, const char **argv)
 
 	err = -ENOMEM;
 
-	if (symbol_conf.kptr_restrict && !perf_evlist__exclude_kernel(rec->evlist))
-		pr_warning(
-"WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
-"check /proc/sys/kernel/kptr_restrict and /proc/sys/kernel/perf_event_paranoid.\n\n"
-"Samples in kernel functions may not be resolved if a suitable vmlinux\n"
-"file is not found in the buildid cache or in the vmlinux path.\n\n"
-"Samples in kernel modules won't be resolved at all.\n\n"
-"If some relocation was applied (e.g. kexec) symbols may be misresolved\n"
-"even with a suitable vmlinux or kallsyms file.\n\n");
-
 	if (rec->no_buildid_cache || rec->no_buildid) {
 		disable_buildid_cache();
 	} else if (rec->switch_output.enabled) {

tools/perf/builtin-report.c

@@ -48,7 +48,7 @@
 #include "util/auxtrace.h"
 #include "util/units.h"
 #include "util/branch.h"
-#include "util/util.h"
+#include "util/util.h" // perf_tip()
 #include "ui/ui.h"
 #include "ui/progress.h"
 
@@ -1269,8 +1269,8 @@ int cmd_report(int argc, const char **argv)
 
 repeat:
 	session = perf_session__new(&data, false, &report.tool);
-	if (session == NULL)
+	if (IS_ERR(session))
-		return -1;
+		return PTR_ERR(session);
 
 	ret = evswitch__init(&report.evswitch, session->evlist, stderr);
 	if (ret)

tools/perf/builtin-sched.c

@@ -3,8 +3,10 @@
 #include "perf.h"
 #include "perf-sys.h"
 
+#include "util/cpumap.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
+#include "util/evsel_fprintf.h"
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/header.h"
@@ -23,6 +25,7 @@
 #include "util/trace-event.h"
 
 #include "util/debug.h"
+#include "util/event.h"
 
 #include <linux/kernel.h>
 #include <linux/log2.h>
@@ -36,7 +39,9 @@
 #include <pthread.h>
 #include <math.h>
 #include <api/fs/fs.h>
+#include <perf/cpumap.h>
 #include <linux/time64.h>
+#include <linux/err.h>
 
 #include <linux/ctype.h>
 
@@ -1794,9 +1799,9 @@ static int perf_sched__read_events(struct perf_sched *sched)
 	int rc = -1;
 
 	session = perf_session__new(&data, false, &sched->tool);
-	if (session == NULL) {
+	if (IS_ERR(session)) {
-		pr_debug("No Memory for session\n");
+		pr_debug("Error creating perf session");
-		return -1;
+		return PTR_ERR(session);
 	}
 
 	symbol__init(&session->header.env);
@@ -2051,7 +2056,7 @@ static void timehist_print_sample(struct perf_sched *sched,
 			    EVSEL__PRINT_SYM | EVSEL__PRINT_ONELINE |
 			    EVSEL__PRINT_CALLCHAIN_ARROW |
 			    EVSEL__PRINT_SKIP_IGNORED,
-			    &callchain_cursor, stdout);
+			    &callchain_cursor, symbol_conf.bt_stop_list,  stdout);
 
 out:
 	printf("\n");
@@ -2986,8 +2991,8 @@ static int perf_sched__timehist(struct perf_sched *sched)
 	symbol_conf.use_callchain = sched->show_callchain;
 
 	session = perf_session__new(&data, false, &sched->tool);
-	if (session == NULL)
+	if (IS_ERR(session))
-		return -ENOMEM;
+		return PTR_ERR(session);
 
 	evlist = session->evlist;
 

tools/perf/builtin-script.c

@@ -17,6 +17,7 @@
 #include "util/trace-event.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
+#include "util/evsel_fprintf.h"
 #include "util/evswitch.h"
 #include "util/sort.h"
 #include "util/data.h"
@@ -52,6 +53,7 @@
 #include <unistd.h>
 #include <subcmd/pager.h>
 #include <perf/evlist.h>
+#include <linux/err.h>
 #include "util/record.h"
 #include "util/util.h"
 #include "perf.h"
@@ -1324,7 +1326,8 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample,
 		} else
 			printed += fprintf(fp, "\n");
 
-		printed += sample__fprintf_sym(sample, al, 0, print_opts, cursor, fp);
+		printed += sample__fprintf_sym(sample, al, 0, print_opts, cursor,
+					       symbol_conf.bt_stop_list, fp);
 	}
 
 	/* print branch_to information */
@@ -1866,7 +1869,8 @@ static void process_event(struct perf_script *script,
 			cursor = &callchain_cursor;
 
 		fputc(cursor ? '\n' : ' ', fp);
-		sample__fprintf_sym(sample, al, 0, output[type].print_ip_opts, cursor, fp);
+		sample__fprintf_sym(sample, al, 0, output[type].print_ip_opts, cursor,
+				    symbol_conf.bt_stop_list, fp);
 	}
 
 	if (PRINT_FIELD(IREGS))
@@ -1915,7 +1919,7 @@ static void __process_stat(struct evsel *counter, u64 tstamp)
 	int cpu, thread;
 	static int header_printed;
 
-	if (counter->system_wide)
+	if (counter->core.system_wide)
 		nthreads = 1;
 
 	if (!header_printed) {
@@ -2042,7 +2046,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 		return err;
 
 	evlist = *pevlist;
-	evsel = perf_evlist__last(*pevlist);
+	evsel = evlist__last(*pevlist);
 
 	if (!evsel->priv) {
 		if (scr->per_event_dump) {
@@ -3083,8 +3087,8 @@ int find_scripts(char **scripts_array, char **scripts_path_array, int num,
 	int i = 0;
 
 	session = perf_session__new(&data, false, NULL);
-	if (!session)
+	if (IS_ERR(session))
-		return -1;
+		return PTR_ERR(session);
 
 	snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path());
 
@@ -3754,8 +3758,8 @@ int cmd_script(int argc, const char **argv)
 	}
 
 	session = perf_session__new(&data, false, &script.tool);
-	if (session == NULL)
+	if (IS_ERR(session))
-		return -1;
+		return PTR_ERR(session);
 
 	if (header || header_only) {
 		script.tool.show_feat_hdr = SHOW_FEAT_HEADER;

tools/perf/builtin-stat.c

@@ -61,6 +61,7 @@
 #include "util/tool.h"
 #include "util/string2.h"
 #include "util/metricgroup.h"
+#include "util/synthetic-events.h"
 #include "util/target.h"
 #include "util/time-utils.h"
 #include "util/top.h"
@@ -82,6 +83,7 @@
 #include <unistd.h>
 #include <sys/time.h>
 #include <sys/resource.h>
+#include <linux/err.h>
 
 #include <linux/ctype.h>
 #include <perf/evlist.h>
@@ -233,7 +235,7 @@ static int write_stat_round_event(u64 tm, u64 type)
 #define WRITE_STAT_ROUND_EVENT(time, interval) \
 	write_stat_round_event(time, PERF_STAT_ROUND_TYPE__ ## interval)
 
-#define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
+#define SID(e, x, y) xyarray__entry(e->core.sample_id, x, y)
 
 static int
 perf_evsel__write_stat_event(struct evsel *counter, u32 cpu, u32 thread,
@@ -276,7 +278,7 @@ static int read_counter(struct evsel *counter, struct timespec *rs)
 	if (!counter->supported)
 		return -ENOENT;
 
-	if (counter->system_wide)
+	if (counter->core.system_wide)
 		nthreads = 1;
 
 	for (thread = 0; thread < nthreads; thread++) {
@@ -540,7 +542,7 @@ try_again:
 		if (err < 0)
 			return err;
 
-		err = perf_stat_synthesize_config(&stat_config, NULL, evsel_list,
+		err = perf_event__synthesize_stat_events(&stat_config, NULL, evsel_list,
 							 process_synthesized_event, is_pipe);
 		if (err < 0)
 			return err;
@@ -822,18 +824,6 @@ static int perf_stat__get_core(struct perf_stat_config *config __maybe_unused,
 	return cpu_map__get_core(map, cpu, NULL);
 }
 
-static int cpu_map__get_max(struct perf_cpu_map *map)
-{
-	int i, max = -1;
-
-	for (i = 0; i < map->nr; i++) {
-		if (map->map[i] > max)
-			max = map->map[i];
-	}
-
-	return max;
-}
-
 static int perf_stat__get_aggr(struct perf_stat_config *config,
 			       aggr_get_id_t get_id, struct perf_cpu_map *map, int idx)
 {
@@ -928,7 +918,7 @@ static int perf_stat_init_aggr_mode(void)
 	 * taking the highest cpu number to be the size of
 	 * the aggregation translate cpumap.
 	 */
-	nr = cpu_map__get_max(evsel_list->core.cpus);
+	nr = perf_cpu_map__max(evsel_list->core.cpus);
 	stat_config.cpus_aggr_map = perf_cpu_map__empty_new(nr + 1);
 	return stat_config.cpus_aggr_map ? 0 : -ENOMEM;
 }
@@ -1447,9 +1437,9 @@ static int __cmd_record(int argc, const char **argv)
 	}
 
 	session = perf_session__new(data, false, NULL);
-	if (session == NULL) {
+	if (IS_ERR(session)) {
-		pr_err("Perf session creation failed.\n");
+		pr_err("Perf session creation failed\n");
-		return -1;
+		return PTR_ERR(session);
 	}
 
 	init_features(session);
@@ -1646,8 +1636,8 @@ static int __cmd_report(int argc, const char **argv)
 	perf_stat.data.mode = PERF_DATA_MODE_READ;
 
 	session = perf_session__new(&perf_stat.data, false, &perf_stat.tool);
-	if (session == NULL)
+	if (IS_ERR(session))
-		return -1;
+		return PTR_ERR(session);
 
 	perf_stat.session  = session;
 	stat_config.output = stderr;
@@ -1681,7 +1671,7 @@ static void setup_system_wide(int forks)
 		struct evsel *counter;
 
 		evlist__for_each_entry(evsel_list, counter) {
-			if (!counter->system_wide)
+			if (!counter->core.system_wide)
 				return;
 		}
 
@@ -1963,8 +1953,11 @@ int cmd_stat(int argc, const char **argv)
 			fprintf(output, "[ perf stat: executing run #%d ... ]\n",
 				run_idx + 1);
 
+		if (run_idx != 0)
+			perf_evlist__reset_prev_raw_counts(evsel_list);
+
 		status = run_perf_stat(argc, argv, run_idx);
-		if (forever && status != -1) {
+		if (forever && status != -1 && !interval) {
 			print_counters(NULL, argc, argv);
 			perf_stat__reset_stats();
 		}

tools/perf/builtin-timechart.c

@@ -35,6 +35,7 @@
 #include "util/tool.h"
 #include "util/data.h"
 #include "util/debug.h"
+#include <linux/err.h>
 
 #ifdef LACKS_OPEN_MEMSTREAM_PROTOTYPE
 FILE *open_memstream(char **ptr, size_t *sizeloc);
@@ -1601,8 +1602,8 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name)
 							 &tchart->tool);
 	int ret = -EINVAL;
 
-	if (session == NULL)
+	if (IS_ERR(session))
-		return -1;
+		return PTR_ERR(session);
 
 	symbol__init(&session->header.env);
 

tools/perf/builtin-top.c

@@ -27,11 +27,14 @@
 #include "util/dso.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
+#include "util/evsel_config.h"
 #include "util/event.h"
 #include "util/machine.h"
 #include "util/map.h"
+#include "util/mmap.h"
 #include "util/session.h"
 #include "util/symbol.h"
+#include "util/synthetic-events.h"
 #include "util/top.h"
 #include "util/util.h"
 #include <linux/rbtree.h>
@@ -76,6 +79,7 @@
 #include <linux/stringify.h>
 #include <linux/time64.h>
 #include <linux/types.h>
+#include <linux/err.h>
 
 #include <linux/ctype.h>
 
@@ -528,7 +532,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 				prompt_integer(&counter, "Enter details event counter");
 
 				if (counter >= top->evlist->core.nr_entries) {
-					top->sym_evsel = perf_evlist__first(top->evlist);
+					top->sym_evsel = evlist__first(top->evlist);
 					fprintf(stderr, "Sorry, no such event, using %s.\n", perf_evsel__name(top->sym_evsel));
 					sleep(1);
 					break;
@@ -537,7 +541,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 					if (top->sym_evsel->idx == counter)
 						break;
 			} else
-				top->sym_evsel = perf_evlist__first(top->evlist);
+				top->sym_evsel = evlist__first(top->evlist);
 			break;
 		case 'f':
 			prompt_integer(&top->count_filter, "Enter display event count filter");
@@ -861,7 +865,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 {
 	struct record_opts *opts = &top->record_opts;
 	struct evlist *evlist = top->evlist;
-	struct perf_mmap *md;
+	struct mmap *md;
 	union perf_event *event;
 
 	md = opts->overwrite ? &evlist->overwrite_mmap[idx] : &evlist->mmap[idx];
@@ -901,7 +905,7 @@ static void perf_top__mmap_read(struct perf_top *top)
 	if (overwrite)
 		perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_DATA_PENDING);
 
-	for (i = 0; i < top->evlist->nr_mmaps; i++)
+	for (i = 0; i < top->evlist->core.nr_mmaps; i++)
 		perf_top__mmap_read_idx(top, i);
 
 	if (overwrite) {
@@ -959,7 +963,7 @@ static int perf_top__overwrite_check(struct perf_top *top)
 		/* has term for current event */
 		if ((overwrite < 0) && (set >= 0)) {
 			/* if it's first event, set overwrite */
-			if (evsel == perf_evlist__first(evlist))
+			if (evsel == evlist__first(evlist))
 				overwrite = set;
 			else
 				return -1;
@@ -983,7 +987,7 @@ static int perf_top_overwrite_fallback(struct perf_top *top,
 		return 0;
 
 	/* only fall back when first event fails */
-	if (evsel != perf_evlist__first(evlist))
+	if (evsel != evlist__first(evlist))
 		return 0;
 
 	evlist__for_each_entry(evlist, counter)
@@ -1040,7 +1044,7 @@ try_again:
 		}
 	}
 
-	if (perf_evlist__mmap(evlist, opts->mmap_pages) < 0) {
+	if (evlist__mmap(evlist, opts->mmap_pages) < 0) {
 		ui__error("Failed to mmap with %d (%s)\n",
 			    errno, str_error_r(errno, msg, sizeof(msg)));
 		goto out_err;
@@ -1304,7 +1308,7 @@ static int __cmd_top(struct perf_top *top)
 	}
 
 	/* Wait for a minimal set of events before starting the snapshot */
-	perf_evlist__poll(top->evlist, 100);
+	evlist__poll(top->evlist, 100);
 
 	perf_top__mmap_read(top);
 
@@ -1314,7 +1318,7 @@ static int __cmd_top(struct perf_top *top)
 		perf_top__mmap_read(top);
 
 		if (opts->overwrite || (hits == top->samples))
-			ret = perf_evlist__poll(top->evlist, 100);
+			ret = evlist__poll(top->evlist, 100);
 
 		if (resize) {
 			perf_top__resize(top);
@@ -1641,7 +1645,7 @@ int cmd_top(int argc, const char **argv)
 		goto out_delete_evlist;
 	}
 
-	top.sym_evsel = perf_evlist__first(top.evlist);
+	top.sym_evsel = evlist__first(top.evlist);
 
 	if (!callchain_param.enabled) {
 		symbol_conf.cumulate_callchain = false;
@@ -1671,8 +1675,8 @@ int cmd_top(int argc, const char **argv)
 	}
 
 	top.session = perf_session__new(NULL, false, NULL);
-	if (top.session == NULL) {
+	if (IS_ERR(top.session)) {
-		status = -1;
+		status = PTR_ERR(top.session);
 		goto out_delete_evlist;
 	}
 

tools/perf/builtin-trace.c

@@ -28,8 +28,12 @@
 #include "util/dso.h"
 #include "util/env.h"
 #include "util/event.h"
+#include "util/evsel.h"
+#include "util/evsel_fprintf.h"
+#include "util/synthetic-events.h"
 #include "util/evlist.h"
 #include "util/evswitch.h"
+#include "util/mmap.h"
 #include <subcmd/pager.h>
 #include <subcmd/exec-cmd.h>
 #include "util/machine.h"
@@ -2074,7 +2078,7 @@ static int trace__fprintf_callchain(struct trace *trace, struct perf_sample *sam
 				        EVSEL__PRINT_DSO |
 				        EVSEL__PRINT_UNKNOWN_AS_ADDR;
 
-	return sample__fprintf_callchain(sample, 38, print_opts, &callchain_cursor, trace->output);
+	return sample__fprintf_callchain(sample, 38, print_opts, &callchain_cursor, symbol_conf.bt_stop_list, trace->output);
 }
 
 static const char *errno_to_name(struct evsel *evsel, int err)
@@ -3408,7 +3412,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (trace->dump.map)
 		bpf_map__fprintf(trace->dump.map, trace->output);
 
-	err = perf_evlist__mmap(evlist, trace->opts.mmap_pages);
+	err = evlist__mmap(evlist, trace->opts.mmap_pages);
 	if (err < 0)
 		goto out_error_mmap;
 
@@ -3425,7 +3429,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 
 	trace->multiple_threads = perf_thread_map__pid(evlist->core.threads, 0) == -1 ||
 				  evlist->core.threads->nr > 1 ||
-				  perf_evlist__first(evlist)->core.attr.inherit;
+				  evlist__first(evlist)->core.attr.inherit;
 
 	/*
 	 * Now that we already used evsel->core.attr to ask the kernel to setup the
@@ -3441,9 +3445,9 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 again:
 	before = trace->nr_events;
 
-	for (i = 0; i < evlist->nr_mmaps; i++) {
+	for (i = 0; i < evlist->core.nr_mmaps; i++) {
 		union perf_event *event;
-		struct perf_mmap *md;
+		struct mmap *md;
 
 		md = &evlist->mmap[i];
 		if (perf_mmap__read_init(md) < 0)
@@ -3472,8 +3476,8 @@ again:
 	if (trace->nr_events == before) {
 		int timeout = done ? 100 : -1;
 
-		if (!draining && perf_evlist__poll(evlist, timeout) > 0) {
+		if (!draining && evlist__poll(evlist, timeout) > 0) {
-			if (perf_evlist__filter_pollfd(evlist, POLLERR | POLLHUP | POLLNVAL) == 0)
+			if (evlist__filter_pollfd(evlist, POLLERR | POLLHUP | POLLNVAL) == 0)
 				draining = true;
 
 			goto again;
@@ -3584,8 +3588,8 @@ static int trace__replay(struct trace *trace)
 	trace->multiple_threads = true;
 
 	session = perf_session__new(&data, false, &trace->tool);
-	if (session == NULL)
+	if (IS_ERR(session))
-		return -1;
+		return PTR_ERR(session);
 
 	if (trace->opts.target.pid)
 		symbol_conf.pid_list_str = strdup(trace->opts.target.pid);

tools/perf/jvmti/Build

@@ -1,8 +1,17 @@
 jvmti-y += libjvmti.o
 jvmti-y += jvmti_agent.o
 
+# For strlcpy
+jvmti-y += libstring.o
+
 CFLAGS_jvmti         = -fPIC -DPIC -I$(JDIR)/include -I$(JDIR)/include/linux
 CFLAGS_REMOVE_jvmti  = -Wmissing-declarations
 CFLAGS_REMOVE_jvmti += -Wstrict-prototypes
 CFLAGS_REMOVE_jvmti += -Wextra
 CFLAGS_REMOVE_jvmti += -Wwrite-strings
+
+CFLAGS_libstring.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
+
+$(OUTPUT)jvmti/libstring.o: ../lib/string.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)

tools/perf/lib/Makefile

@@ -59,7 +59,13 @@ else
   CFLAGS := -g -Wall
 endif
 
-INCLUDES = -I$(srctree)/tools/perf/lib/include -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(SRCARCH)/include/ -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi -I$(srctree)/tools/include/uapi
+INCLUDES = \
+-I$(srctree)/tools/perf/lib/include \
+-I$(srctree)/tools/lib/ \
+-I$(srctree)/tools/include \
+-I$(srctree)/tools/arch/$(SRCARCH)/include/ \
+-I$(srctree)/tools/arch/$(SRCARCH)/include/uapi \
+-I$(srctree)/tools/include/uapi
 
 # Append required CFLAGS
 override CFLAGS += $(EXTRA_WARNINGS)
@@ -88,13 +94,34 @@ LIBPERF_PC := $(OUTPUT)libperf.pc
 
 LIBPERF_ALL := $(LIBPERF_A) $(OUTPUT)libperf.so*
 
+LIB_DIR := $(srctree)/tools/lib/api/
+
+ifneq ($(OUTPUT),)
+ifneq ($(subdir),)
+  API_PATH=$(OUTPUT)/../lib/api/
+else
+  API_PATH=$(OUTPUT)
+endif
+else
+  API_PATH=$(LIB_DIR)
+endif
+
+LIBAPI = $(API_PATH)libapi.a
+
+$(LIBAPI): FORCE
+	$(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) $(OUTPUT)libapi.a
+
+$(LIBAPI)-clean:
+	$(call QUIET_CLEAN, libapi)
+	$(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null
+
 $(LIBPERF_IN): FORCE
 	$(Q)$(MAKE) $(build)=libperf
 
 $(LIBPERF_A): $(LIBPERF_IN)
 	$(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIBPERF_IN)
 
-$(LIBPERF_SO): $(LIBPERF_IN)
+$(LIBPERF_SO): $(LIBPERF_IN) $(LIBAPI)
 	$(QUIET_LINK)$(CC) --shared -Wl,-soname,libperf.so \
                                     -Wl,--version-script=$(VERSION_SCRIPT) $^ -o $@
 	@ln -sf $(@F) $(OUTPUT)libperf.so
@@ -106,12 +133,12 @@ libs: $(LIBPERF_A) $(LIBPERF_SO) $(LIBPERF_PC)
 all: fixdep
 	$(Q)$(MAKE) libs
 
-clean:
+clean: $(LIBAPI)-clean
 	$(call QUIET_CLEAN, libperf) $(RM) $(LIBPERF_A) \
                 *.o *~ *.a *.so *.so.$(VERSION) *.so.$(LIBPERF_VERSION) .*.d .*.cmd LIBPERF-CFLAGS $(LIBPERF_PC)
 	$(Q)$(MAKE) -C tests clean
 
-tests:
+tests: libs
 	$(Q)$(MAKE) -C tests
 	$(Q)$(MAKE) -C tests run
 
@@ -146,6 +173,7 @@ install_headers:
 		$(call do_install,include/perf/threadmap.h,$(prefix)/include/perf,644); \
 		$(call do_install,include/perf/evlist.h,$(prefix)/include/perf,644); \
 		$(call do_install,include/perf/evsel.h,$(prefix)/include/perf,644);
+		$(call do_install,include/perf/event.h,$(prefix)/include/perf,644);
 
 install_pkgconfig: $(LIBPERF_PC)
 	$(call QUIET_INSTALL, $(LIBPERF_PC)) \

tools/perf/lib/core.c

@@ -4,7 +4,9 @@
 
 #include <stdio.h>
 #include <stdarg.h>
+#include <unistd.h>
 #include <perf/core.h>
+#include <internal/lib.h>
 #include "internal.h"
 
 static int __base_pr(enum libperf_print_level level, const char *format,
@@ -15,11 +17,6 @@ static int __base_pr(enum libperf_print_level level, const char *format,
 
 static libperf_print_fn_t __libperf_pr = __base_pr;
 
-void libperf_set_print(libperf_print_fn_t fn)
-{
-	__libperf_pr = fn;
-}
-
 __printf(2, 3)
 void libperf_print(enum libperf_print_level level, const char *format, ...)
 {
@@ -32,3 +29,9 @@ void libperf_print(enum libperf_print_level level, const char *format, ...)
 	__libperf_pr(level, format, args);
 	va_end(args);
 }
+
+void libperf_init(libperf_print_fn_t fn)
+{
+	page_size = sysconf(_SC_PAGE_SIZE);
+	__libperf_pr = fn;
+}

tools/perf/lib/cpumap.c

@@ -260,3 +260,15 @@ int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu)
 
 	return -1;
 }
+
+int perf_cpu_map__max(struct perf_cpu_map *map)
+{
+	int i, max = -1;
+
+	for (i = 0; i < map->nr; i++) {
+		if (map->map[i] > max)
+			max = map->map[i];
+	}
+
+	return max;
+}

tools/perf/lib/evlist.c

@@ -1,16 +1,30 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <perf/evlist.h>
 #include <perf/evsel.h>
+#include <linux/bitops.h>
 #include <linux/list.h>
+#include <linux/hash.h>
+#include <sys/ioctl.h>
 #include <internal/evlist.h>
 #include <internal/evsel.h>
+#include <internal/xyarray.h>
 #include <linux/zalloc.h>
 #include <stdlib.h>
+#include <errno.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <signal.h>
+#include <poll.h>
 #include <perf/cpumap.h>
 #include <perf/threadmap.h>
+#include <api/fd/array.h>
 
 void perf_evlist__init(struct perf_evlist *evlist)
 {
+	int i;
+
+	for (i = 0; i < PERF_EVLIST__HLIST_SIZE; ++i)
+		INIT_HLIST_HEAD(&evlist->heads[i]);
 	INIT_LIST_HEAD(&evlist->entries);
 	evlist->nr_entries = 0;
 }
@@ -157,3 +171,113 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 	perf_evlist__for_each_entry(evlist, evsel)
 		perf_evsel__disable(evsel);
 }
+
+u64 perf_evlist__read_format(struct perf_evlist *evlist)
+{
+	struct perf_evsel *first = perf_evlist__first(evlist);
+
+	return first->attr.read_format;
+}
+
+#define SID(e, x, y) xyarray__entry(e->sample_id, x, y)
+
+static void perf_evlist__id_hash(struct perf_evlist *evlist,
+				 struct perf_evsel *evsel,
+				 int cpu, int thread, u64 id)
+{
+	int hash;
+	struct perf_sample_id *sid = SID(evsel, cpu, thread);
+
+	sid->id = id;
+	sid->evsel = evsel;
+	hash = hash_64(sid->id, PERF_EVLIST__HLIST_BITS);
+	hlist_add_head(&sid->node, &evlist->heads[hash]);
+}
+
+void perf_evlist__id_add(struct perf_evlist *evlist,
+			 struct perf_evsel *evsel,
+			 int cpu, int thread, u64 id)
+{
+	perf_evlist__id_hash(evlist, evsel, cpu, thread, id);
+	evsel->id[evsel->ids++] = id;
+}
+
+int perf_evlist__id_add_fd(struct perf_evlist *evlist,
+			   struct perf_evsel *evsel,
+			   int cpu, int thread, int fd)
+{
+	u64 read_data[4] = { 0, };
+	int id_idx = 1; /* The first entry is the counter value */
+	u64 id;
+	int ret;
+
+	ret = ioctl(fd, PERF_EVENT_IOC_ID, &id);
+	if (!ret)
+		goto add;
+
+	if (errno != ENOTTY)
+		return -1;
+
+	/* Legacy way to get event id.. All hail to old kernels! */
+
+	/*
+	 * This way does not work with group format read, so bail
+	 * out in that case.
+	 */
+	if (perf_evlist__read_format(evlist) & PERF_FORMAT_GROUP)
+		return -1;
+
+	if (!(evsel->attr.read_format & PERF_FORMAT_ID) ||
+	    read(fd, &read_data, sizeof(read_data)) == -1)
+		return -1;
+
+	if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+		++id_idx;
+	if (evsel->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+		++id_idx;
+
+	id = read_data[id_idx];
+
+add:
+	perf_evlist__id_add(evlist, evsel, cpu, thread, id);
+	return 0;
+}
+
+int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
+{
+	int nr_cpus = perf_cpu_map__nr(evlist->cpus);
+	int nr_threads = perf_thread_map__nr(evlist->threads);
+	int nfds = 0;
+	struct perf_evsel *evsel;
+
+	perf_evlist__for_each_entry(evlist, evsel) {
+		if (evsel->system_wide)
+			nfds += nr_cpus;
+		else
+			nfds += nr_cpus * nr_threads;
+	}
+
+	if (fdarray__available_entries(&evlist->pollfd) < nfds &&
+	    fdarray__grow(&evlist->pollfd, nfds) < 0)
+		return -ENOMEM;
+
+	return 0;
+}
+
+int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd,
+			    void *ptr, short revent)
+{
+	int pos = fdarray__add(&evlist->pollfd, fd, revent | POLLERR | POLLHUP);
+
+	if (pos >= 0) {
+		evlist->pollfd.priv[pos].ptr = ptr;
+		fcntl(fd, F_SETFL, O_NONBLOCK);
+	}
+
+	return pos;
+}
+
+int perf_evlist__poll(struct perf_evlist *evlist, int timeout)
+{
+	return fdarray__poll(&evlist->pollfd, timeout);
+}

tools/perf/lib/evsel.c

@@ -230,3 +230,33 @@ struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel)
 {
 	return &evsel->attr;
 }
+
+int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
+{
+	if (ncpus == 0 || nthreads == 0)
+		return 0;
+
+	if (evsel->system_wide)
+		nthreads = 1;
+
+	evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id));
+	if (evsel->sample_id == NULL)
+		return -ENOMEM;
+
+	evsel->id = zalloc(ncpus * nthreads * sizeof(u64));
+	if (evsel->id == NULL) {
+		xyarray__delete(evsel->sample_id);
+		evsel->sample_id = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+void perf_evsel__free_id(struct perf_evsel *evsel)
+{
+	xyarray__delete(evsel->sample_id);
+	evsel->sample_id = NULL;
+	zfree(&evsel->id);
+	evsel->ids = 0;
+}

tools/perf/lib/include/internal/evlist.h

@@ -3,6 +3,11 @@
 #define __LIBPERF_INTERNAL_EVLIST_H
 
 #include <linux/list.h>
+#include <api/fd/array.h>
+#include <internal/evsel.h>
+
+#define PERF_EVLIST__HLIST_BITS 8
+#define PERF_EVLIST__HLIST_SIZE (1 << PERF_EVLIST__HLIST_BITS)
 
 struct perf_cpu_map;
 struct perf_thread_map;
@@ -13,8 +18,16 @@ struct perf_evlist {
 	bool			 has_user_cpus;
 	struct perf_cpu_map	*cpus;
 	struct perf_thread_map	*threads;
+	int			 nr_mmaps;
+	size_t			 mmap_len;
+	struct fdarray		 pollfd;
+	struct hlist_head	 heads[PERF_EVLIST__HLIST_SIZE];
 };
 
+int perf_evlist__alloc_pollfd(struct perf_evlist *evlist);
+int perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd,
+			    void *ptr, short revent);
+
 /**
  * __perf_evlist__for_each_entry - iterate thru all the evsels
  * @list: list_head instance to iterate
@@ -47,4 +60,24 @@ struct perf_evlist {
 #define perf_evlist__for_each_entry_reverse(evlist, evsel) \
 	__perf_evlist__for_each_entry_reverse(&(evlist)->entries, evsel)
 
+static inline struct perf_evsel *perf_evlist__first(struct perf_evlist *evlist)
+{
+	return list_entry(evlist->entries.next, struct perf_evsel, node);
+}
+
+static inline struct perf_evsel *perf_evlist__last(struct perf_evlist *evlist)
+{
+	return list_entry(evlist->entries.prev, struct perf_evsel, node);
+}
+
+u64 perf_evlist__read_format(struct perf_evlist *evlist);
+
+void perf_evlist__id_add(struct perf_evlist *evlist,
+			 struct perf_evsel *evsel,
+			 int cpu, int thread, u64 id);
+
+int perf_evlist__id_add_fd(struct perf_evlist *evlist,
+			   struct perf_evsel *evsel,
+			   int cpu, int thread, int fd);
+
 #endif /* __LIBPERF_INTERNAL_EVLIST_H */

tools/perf/lib/include/internal/evsel.h

@@ -4,9 +4,35 @@
 
 #include <linux/types.h>
 #include <linux/perf_event.h>
+#include <stdbool.h>
+#include <sys/types.h>
 
 struct perf_cpu_map;
 struct perf_thread_map;
+struct xyarray;
+
+/*
+ * Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there are
+ * more than one entry in the evlist.
+ */
+struct perf_sample_id {
+	struct hlist_node	 node;
+	u64			 id;
+	struct perf_evsel	*evsel;
+       /*
+	* 'idx' will be used for AUX area sampling. A sample will have AUX area
+	* data that will be queued for decoding, where there are separate
+	* queues for each CPU (per-cpu tracing) or task (per-thread tracing).
+	* The sample ID can be used to lookup 'idx' which is effectively the
+	* queue number.
+	*/
+	int			 idx;
+	int			 cpu;
+	pid_t			 tid;
+
+	/* Holds total ID period value for PERF_SAMPLE_READ processing. */
+	u64			 period;
+};
 
 struct perf_evsel {
 	struct list_head	 node;
@@ -15,9 +41,13 @@ struct perf_evsel {
 	struct perf_cpu_map	*own_cpus;
 	struct perf_thread_map	*threads;
 	struct xyarray		*fd;
+	struct xyarray		*sample_id;
+	u64			*id;
+	u32			 ids;
 
 	/* parse modifier helper */
 	int			 nr_members;
+	bool			 system_wide;
 };
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
@@ -26,4 +56,7 @@ void perf_evsel__free_fd(struct perf_evsel *evsel);
 int perf_evsel__read_size(struct perf_evsel *evsel);
 int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter);
 
+int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
+void perf_evsel__free_id(struct perf_evsel *evsel);
+
 #endif /* __LIBPERF_INTERNAL_EVSEL_H */

tools/perf/lib/include/internal/lib.h

@@ -2,7 +2,9 @@
 #ifndef __LIBPERF_INTERNAL_LIB_H
 #define __LIBPERF_INTERNAL_LIB_H
 
-#include <unistd.h>
+#include <sys/types.h>
+
+extern unsigned int page_size;
 
 ssize_t readn(int fd, void *buf, size_t n);
 ssize_t writen(int fd, const void *buf, size_t n);

tools/perf/lib/include/internal/mmap.h

@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LIBPERF_INTERNAL_MMAP_H
+#define __LIBPERF_INTERNAL_MMAP_H
+
+#include <linux/compiler.h>
+#include <linux/refcount.h>
+#include <linux/types.h>
+#include <stdbool.h>
+
+/* perf sample has 16 bits size limit */
+#define PERF_SAMPLE_MAX_SIZE (1 << 16)
+
+/**
+ * struct perf_mmap - perf's ring buffer mmap details
+ *
+ * @refcnt - e.g. code using PERF_EVENT_IOC_SET_OUTPUT to share this
+ */
+struct perf_mmap {
+	void		*base;
+	int		 mask;
+	int		 fd;
+	int		 cpu;
+	refcount_t	 refcnt;
+	u64		 prev;
+	u64		 start;
+	u64		 end;
+	bool		 overwrite;
+	u64		 flush;
+	char		 event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8);
+};
+
+#endif /* __LIBPERF_INTERNAL_MMAP_H */

tools/perf/lib/include/perf/core.h

@@ -17,6 +17,6 @@ enum libperf_print_level {
 typedef int (*libperf_print_fn_t)(enum libperf_print_level level,
 				  const char *, va_list ap);
 
-LIBPERF_API void libperf_set_print(libperf_print_fn_t fn);
+LIBPERF_API void libperf_init(libperf_print_fn_t fn);
 
 #endif /* __LIBPERF_CORE_H */

tools/perf/lib/include/perf/cpumap.h

@@ -16,6 +16,7 @@ LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map);
 LIBPERF_API int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
 LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
 LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map);
+LIBPERF_API int perf_cpu_map__max(struct perf_cpu_map *map);
 
 #define perf_cpu_map__for_each_cpu(cpu, idx, cpus)		\
 	for ((idx) = 0, (cpu) = perf_cpu_map__cpu(cpus, idx);	\

tools/perf/lib/include/perf/evlist.h

@@ -31,5 +31,6 @@ LIBPERF_API void perf_evlist__disable(struct perf_evlist *evlist);
 LIBPERF_API void perf_evlist__set_maps(struct perf_evlist *evlist,
 				       struct perf_cpu_map *cpus,
 				       struct perf_thread_map *threads);
+LIBPERF_API int perf_evlist__poll(struct perf_evlist *evlist, int timeout);
 
 #endif /* __LIBPERF_EVLIST_H */

tools/perf/lib/lib.c

@@ -5,6 +5,8 @@
 #include <linux/kernel.h>
 #include <internal/lib.h>
 
+unsigned int page_size;
+
 static ssize_t ion(bool is_read, int fd, void *buf, size_t n)
 {
 	void *buf_start = buf;

tools/perf/lib/libperf.map

@@ -1,6 +1,6 @@
 LIBPERF_0.0.1 {
 	global:
-		libperf_set_print;
+		libperf_init;
 		perf_cpu_map__dummy_new;
 		perf_cpu_map__get;
 		perf_cpu_map__put;
@@ -9,6 +9,7 @@ LIBPERF_0.0.1 {
 		perf_cpu_map__nr;
 		perf_cpu_map__cpu;
 		perf_cpu_map__empty;
+		perf_cpu_map__max;
 		perf_thread_map__new_dummy;
 		perf_thread_map__set_pid;
 		perf_thread_map__comm;
@@ -38,6 +39,7 @@ LIBPERF_0.0.1 {
 		perf_evlist__remove;
 		perf_evlist__next;
 		perf_evlist__set_maps;
+		perf_evlist__poll;
 	local:
 		*;
 };

tools/perf/lib/tests/test-cpumap.c

@@ -1,13 +1,23 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <stdarg.h>
+#include <stdio.h>
 #include <perf/cpumap.h>
 #include <internal/tests.h>
 
+static int libperf_print(enum libperf_print_level level,
+			 const char *fmt, va_list ap)
+{
+	return vfprintf(stderr, fmt, ap);
+}
+
 int main(int argc, char **argv)
 {
 	struct perf_cpu_map *cpus;
 
 	__T_START;
 
+	libperf_init(libperf_print);
+
 	cpus = perf_cpu_map__dummy_new();
 	if (!cpus)
 		return -1;

tools/perf/lib/tests/test-evlist.c

@@ -1,4 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <stdarg.h>
 #include <linux/perf_event.h>
 #include <perf/cpumap.h>
 #include <perf/threadmap.h>
@@ -6,6 +8,12 @@
 #include <perf/evsel.h>
 #include <internal/tests.h>
 
+static int libperf_print(enum libperf_print_level level,
+			 const char *fmt, va_list ap)
+{
+	return vfprintf(stderr, fmt, ap);
+}
+
 static int test_stat_cpu(void)
 {
 	struct perf_cpu_map *cpus;
@@ -177,6 +185,8 @@ int main(int argc, char **argv)
 {
 	__T_START;
 
+	libperf_init(libperf_print);
+
 	test_stat_cpu();
 	test_stat_thread();
 	test_stat_thread_enable();