Merge tag 'perf-core-for-mingo-4.21-20190103' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

perf c2c:

  Jiri Olsa:

  - Change the default coalesce setup to from '--coalesce pid,iaddr' to just '--coalesce iaddr'.

  - Increase the HITM ratio limit for displayed cachelines.

perf script:

  Andi Kleen:

  - Fix LBR skid dump problems in brstackinsn.

perf trace:

  Arnaldo Carvalho de Melo:

  - Check if the raw_syscalls:sys_{enter,exit} are setup before setting tp filter.

  - Do not hardcode the size of the tracepoint common_ fields.

  - Beautify USBDEFFS_ ioctl commands.

  Colin Ian King:

  - Use correct SECCOMP prefix spelling, "SECOMP_*" -> "SECCOMP_*".

perf python:

  Jiri Olsa:

  - Do not force closing original perf descriptor in evlist.get_pollfd().

tools misc:

  Jiri Olsa:

  - Allow overriding CFLAGS and LDFLAGS.

perf build:

  Stanislav Fomichev:

  - Don't unconditionally link the libbfd feature test to -liberty and -lz

thread-stack:

  Adrian Hunter:

  - Fix processing for the idle task, having a stack per cpu.

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

27 files changed, 620 insertions, 166 deletions

diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index d47b8f73e2e7..5467c6bf9ceb 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -82,8 +82,8 @@ FEATURE_TESTS_EXTRA :=                  \
          cplus-demangle                 \
          hello                          \
          libbabeltrace                  \
-         liberty                        \
-         liberty-z                      \
+         libbfd-liberty                 \
+         libbfd-liberty-z               \
          libunwind-debug-frame          \
          libunwind-debug-frame-arm      \
          libunwind-debug-frame-aarch64  \
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 2dbcc0d00f52..7ceb4441b627 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -17,8 +17,8 @@ FILES=                                          \
          test-libbfd.bin                        \
          test-disassembler-four-args.bin        \
          test-reallocarray.bin			\
-         test-liberty.bin                       \
-         test-liberty-z.bin                     \
+         test-libbfd-liberty.bin                \
+         test-libbfd-liberty-z.bin              \
          test-cplus-demangle.bin                \
          test-libelf.bin                        \
          test-libelf-getphdrnum.bin             \
@@ -210,7 +210,7 @@ $(OUTPUT)test-libpython-version.bin:
 	$(BUILD)
 
 $(OUTPUT)test-libbfd.bin:
-	$(BUILD) -DPACKAGE='"perf"' -lbfd -lz -liberty -ldl
+	$(BUILD) -DPACKAGE='"perf"' -lbfd -ldl
 
 $(OUTPUT)test-disassembler-four-args.bin:
 	$(BUILD) -DPACKAGE='"perf"' -lbfd -lopcodes
@@ -218,10 +218,10 @@ $(OUTPUT)test-disassembler-four-args.bin:
 $(OUTPUT)test-reallocarray.bin:
 	$(BUILD)
 
-$(OUTPUT)test-liberty.bin:
+$(OUTPUT)test-libbfd-liberty.bin:
 	$(CC) $(CFLAGS) -Wall -Werror -o $@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty
 
-$(OUTPUT)test-liberty-z.bin:
+$(OUTPUT)test-libbfd-liberty-z.bin:
 	$(CC) $(CFLAGS) -Wall -Werror -o $@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty -lz
 
 $(OUTPUT)test-cplus-demangle.bin:
diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile
index 240eda014b37..6ecdd1067826 100644
--- a/tools/gpio/Makefile
+++ b/tools/gpio/Makefile
@@ -12,7 +12,7 @@ endif
 # (this improves performance and avoids hard-to-debug behaviour);
 MAKEFLAGS += -r
 
-CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include
+override CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include
 
 ALL_TARGETS := lsgpio gpio-hammer gpio-event-mon
 ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS))
diff --git a/tools/include/uapi/linux/usbdevice_fs.h b/tools/include/uapi/linux/usbdevice_fs.h
new file mode 100644
index 000000000000..964e87217be4
--- /dev/null
+++ b/tools/include/uapi/linux/usbdevice_fs.h
@@ -0,0 +1,201 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*****************************************************************************/
+
+/*
+ *	usbdevice_fs.h  --  USB device file system.
+ *
+ *	Copyright (C) 2000
+ *          Thomas Sailer (sailer@ife.ee.ethz.ch)
+ *
+ *	This program is free software; you can redistribute it and/or modify
+ *	it under the terms of the GNU General Public License as published by
+ *	the Free Software Foundation; either version 2 of the License, or
+ *	(at your option) any later version.
+ *
+ *	This program is distributed in the hope that it will be useful,
+ *	but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *	MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *	GNU General Public License for more details.
+ *
+ *	You should have received a copy of the GNU General Public License
+ *	along with this program; if not, write to the Free Software
+ *	Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ *  History:
+ *   0.1  04.01.2000  Created
+ */
+
+/*****************************************************************************/
+
+#ifndef _UAPI_LINUX_USBDEVICE_FS_H
+#define _UAPI_LINUX_USBDEVICE_FS_H
+
+#include <linux/types.h>
+#include <linux/magic.h>
+
+/* --------------------------------------------------------------------- */
+
+/* usbdevfs ioctl codes */
+
+struct usbdevfs_ctrltransfer {
+	__u8 bRequestType;
+	__u8 bRequest;
+	__u16 wValue;
+	__u16 wIndex;
+	__u16 wLength;
+	__u32 timeout;  /* in milliseconds */
+ 	void __user *data;
+};
+
+struct usbdevfs_bulktransfer {
+	unsigned int ep;
+	unsigned int len;
+	unsigned int timeout; /* in milliseconds */
+	void __user *data;
+};
+
+struct usbdevfs_setinterface {
+	unsigned int interface;
+	unsigned int altsetting;
+};
+
+struct usbdevfs_disconnectsignal {
+	unsigned int signr;
+	void __user *context;
+};
+
+#define USBDEVFS_MAXDRIVERNAME 255
+
+struct usbdevfs_getdriver {
+	unsigned int interface;
+	char driver[USBDEVFS_MAXDRIVERNAME + 1];
+};
+
+struct usbdevfs_connectinfo {
+	unsigned int devnum;
+	unsigned char slow;
+};
+
+#define USBDEVFS_URB_SHORT_NOT_OK	0x01
+#define USBDEVFS_URB_ISO_ASAP		0x02
+#define USBDEVFS_URB_BULK_CONTINUATION	0x04
+#define USBDEVFS_URB_NO_FSBR		0x20	/* Not used */
+#define USBDEVFS_URB_ZERO_PACKET	0x40
+#define USBDEVFS_URB_NO_INTERRUPT	0x80
+
+#define USBDEVFS_URB_TYPE_ISO		   0
+#define USBDEVFS_URB_TYPE_INTERRUPT	   1
+#define USBDEVFS_URB_TYPE_CONTROL	   2
+#define USBDEVFS_URB_TYPE_BULK		   3
+
+struct usbdevfs_iso_packet_desc {
+	unsigned int length;
+	unsigned int actual_length;
+	unsigned int status;
+};
+
+struct usbdevfs_urb {
+	unsigned char type;
+	unsigned char endpoint;
+	int status;
+	unsigned int flags;
+	void __user *buffer;
+	int buffer_length;
+	int actual_length;
+	int start_frame;
+	union {
+		int number_of_packets;	/* Only used for isoc urbs */
+		unsigned int stream_id;	/* Only used with bulk streams */
+	};
+	int error_count;
+	unsigned int signr;	/* signal to be sent on completion,
+				  or 0 if none should be sent. */
+	void __user *usercontext;
+	struct usbdevfs_iso_packet_desc iso_frame_desc[0];
+};
+
+/* ioctls for talking directly to drivers */
+struct usbdevfs_ioctl {
+	int	ifno;		/* interface 0..N ; negative numbers reserved */
+	int	ioctl_code;	/* MUST encode size + direction of data so the
+				 * macros in <asm/ioctl.h> give correct values */
+	void __user *data;	/* param buffer (in, or out) */
+};
+
+/* You can do most things with hubs just through control messages,
+ * except find out what device connects to what port. */
+struct usbdevfs_hub_portinfo {
+	char nports;		/* number of downstream ports in this hub */
+	char port [127];	/* e.g. port 3 connects to device 27 */
+};
+
+/* System and bus capability flags */
+#define USBDEVFS_CAP_ZERO_PACKET		0x01
+#define USBDEVFS_CAP_BULK_CONTINUATION		0x02
+#define USBDEVFS_CAP_NO_PACKET_SIZE_LIM		0x04
+#define USBDEVFS_CAP_BULK_SCATTER_GATHER	0x08
+#define USBDEVFS_CAP_REAP_AFTER_DISCONNECT	0x10
+#define USBDEVFS_CAP_MMAP			0x20
+#define USBDEVFS_CAP_DROP_PRIVILEGES		0x40
+
+/* USBDEVFS_DISCONNECT_CLAIM flags & struct */
+
+/* disconnect-and-claim if the driver matches the driver field */
+#define USBDEVFS_DISCONNECT_CLAIM_IF_DRIVER	0x01
+/* disconnect-and-claim except when the driver matches the driver field */
+#define USBDEVFS_DISCONNECT_CLAIM_EXCEPT_DRIVER	0x02
+
+struct usbdevfs_disconnect_claim {
+	unsigned int interface;
+	unsigned int flags;
+	char driver[USBDEVFS_MAXDRIVERNAME + 1];
+};
+
+struct usbdevfs_streams {
+	unsigned int num_streams; /* Not used by USBDEVFS_FREE_STREAMS */
+	unsigned int num_eps;
+	unsigned char eps[0];
+};
+
+/*
+ * USB_SPEED_* values returned by USBDEVFS_GET_SPEED are defined in
+ * linux/usb/ch9.h
+ */
+
+#define USBDEVFS_CONTROL           _IOWR('U', 0, struct usbdevfs_ctrltransfer)
+#define USBDEVFS_CONTROL32           _IOWR('U', 0, struct usbdevfs_ctrltransfer32)
+#define USBDEVFS_BULK              _IOWR('U', 2, struct usbdevfs_bulktransfer)
+#define USBDEVFS_BULK32              _IOWR('U', 2, struct usbdevfs_bulktransfer32)
+#define USBDEVFS_RESETEP           _IOR('U', 3, unsigned int)
+#define USBDEVFS_SETINTERFACE      _IOR('U', 4, struct usbdevfs_setinterface)
+#define USBDEVFS_SETCONFIGURATION  _IOR('U', 5, unsigned int)
+#define USBDEVFS_GETDRIVER         _IOW('U', 8, struct usbdevfs_getdriver)
+#define USBDEVFS_SUBMITURB         _IOR('U', 10, struct usbdevfs_urb)
+#define USBDEVFS_SUBMITURB32       _IOR('U', 10, struct usbdevfs_urb32)
+#define USBDEVFS_DISCARDURB        _IO('U', 11)
+#define USBDEVFS_REAPURB           _IOW('U', 12, void *)
+#define USBDEVFS_REAPURB32         _IOW('U', 12, __u32)
+#define USBDEVFS_REAPURBNDELAY     _IOW('U', 13, void *)
+#define USBDEVFS_REAPURBNDELAY32   _IOW('U', 13, __u32)
+#define USBDEVFS_DISCSIGNAL        _IOR('U', 14, struct usbdevfs_disconnectsignal)
+#define USBDEVFS_DISCSIGNAL32      _IOR('U', 14, struct usbdevfs_disconnectsignal32)
+#define USBDEVFS_CLAIMINTERFACE    _IOR('U', 15, unsigned int)
+#define USBDEVFS_RELEASEINTERFACE  _IOR('U', 16, unsigned int)
+#define USBDEVFS_CONNECTINFO       _IOW('U', 17, struct usbdevfs_connectinfo)
+#define USBDEVFS_IOCTL             _IOWR('U', 18, struct usbdevfs_ioctl)
+#define USBDEVFS_IOCTL32           _IOWR('U', 18, struct usbdevfs_ioctl32)
+#define USBDEVFS_HUB_PORTINFO      _IOR('U', 19, struct usbdevfs_hub_portinfo)
+#define USBDEVFS_RESET             _IO('U', 20)
+#define USBDEVFS_CLEAR_HALT        _IOR('U', 21, unsigned int)
+#define USBDEVFS_DISCONNECT        _IO('U', 22)
+#define USBDEVFS_CONNECT           _IO('U', 23)
+#define USBDEVFS_CLAIM_PORT        _IOR('U', 24, unsigned int)
+#define USBDEVFS_RELEASE_PORT      _IOR('U', 25, unsigned int)
+#define USBDEVFS_GET_CAPABILITIES  _IOR('U', 26, __u32)
+#define USBDEVFS_DISCONNECT_CLAIM  _IOR('U', 27, struct usbdevfs_disconnect_claim)
+#define USBDEVFS_ALLOC_STREAMS     _IOR('U', 28, struct usbdevfs_streams)
+#define USBDEVFS_FREE_STREAMS      _IOR('U', 29, struct usbdevfs_streams)
+#define USBDEVFS_DROP_PRIVILEGES   _IOW('U', 30, __u32)
+#define USBDEVFS_GET_SPEED         _IO('U', 31)
+
+#endif /* _UAPI_LINUX_USBDEVICE_FS_H */
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 07c1857c3d7a..b441c88cafa1 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -702,18 +702,20 @@ endif
 
 ifeq ($(feature-libbfd), 1)
   EXTLIBS += -lbfd
+else
+  # we are on a system that requires -liberty and (maybe) -lz
+  # to link against -lbfd; test each case individually here
 
   # call all detections now so we get correct
   # status in VF output
-  $(call feature_check,liberty)
-  $(call feature_check,liberty-z)
-  $(call feature_check,cplus-demangle)
+  $(call feature_check,libbfd-liberty)
+  $(call feature_check,libbfd-liberty-z)
 
-  ifeq ($(feature-liberty), 1)
-    EXTLIBS += -liberty
+  ifeq ($(feature-libbfd-liberty), 1)
+    EXTLIBS += -lbfd -liberty
   else
-    ifeq ($(feature-liberty-z), 1)
-      EXTLIBS += -liberty -lz
+    ifeq ($(feature-libbfd-liberty-z), 1)
+      EXTLIBS += -lbfd -liberty -lz
     endif
   endif
 endif
@@ -723,24 +725,24 @@ ifdef NO_DEMANGLE
 else
   ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
     EXTLIBS += -liberty
-    CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT
   else
-    ifneq ($(feature-libbfd), 1)
-      ifneq ($(feature-liberty), 1)
-        ifneq ($(feature-liberty-z), 1)
-          # we dont have neither HAVE_CPLUS_DEMANGLE_SUPPORT
-          # or any of 'bfd iberty z' trinity
-          ifeq ($(feature-cplus-demangle), 1)
-            EXTLIBS += -liberty
-            CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT
-          else
-            msg := $(warning No bfd.h/libbfd found, please install binutils-dev[el]/zlib-static/libiberty-dev to gain symbol demangling)
-            CFLAGS += -DNO_DEMANGLE
-          endif
-        endif
+    ifeq ($(filter -liberty,$(EXTLIBS)),)
+      $(call feature_check,cplus-demangle)
+
+      # we dont have neither HAVE_CPLUS_DEMANGLE_SUPPORT
+      # or any of 'bfd iberty z' trinity
+      ifeq ($(feature-cplus-demangle), 1)
+        EXTLIBS += -liberty
+      else
+        msg := $(warning No bfd.h/libbfd found, please install binutils-dev[el]/zlib-static/libiberty-dev to gain symbol demangling)
+        CFLAGS += -DNO_DEMANGLE
       endif
     endif
   endif
+
+  ifneq ($(filter -liberty,$(EXTLIBS)),)
+    CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT
+  endif
 endif
 
 ifneq ($(filter -lbfd,$(EXTLIBS)),)
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index bd23e3f30895..ff29c3372ec3 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -497,6 +497,12 @@ prctl_option_tbl := $(srctree)/tools/perf/trace/beauty/prctl_option.sh
 $(prctl_option_array): $(prctl_hdr_dir)/prctl.h $(prctl_option_tbl)
 	$(Q)$(SHELL) '$(prctl_option_tbl)' $(prctl_hdr_dir) > $@
 
+usbdevfs_ioctl_array := $(beauty_ioctl_outdir)/usbdevfs_ioctl_array.c
+usbdevfs_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/usbdevfs_ioctl.sh
+
+$(usbdevfs_ioctl_array): $(linux_uapi_dir)/usbdevice_fs.h $(usbdevfs_ioctl_tbl)
+	$(Q)$(SHELL) '$(usbdevfs_ioctl_tbl)' $(linux_uapi_dir) > $@
+
 x86_arch_prctl_code_array := $(beauty_outdir)/x86_arch_prctl_code_array.c
 x86_arch_prctl_code_tbl := $(srctree)/tools/perf/trace/beauty/x86_arch_prctl.sh
 
@@ -624,6 +630,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
 	$(mount_flags_array) \
 	$(perf_ioctl_array) \
 	$(prctl_option_array) \
+	$(usbdevfs_ioctl_array) \
 	$(x86_arch_prctl_code_array) \
 	$(rename_flags_array) \
 	$(arch_errno_name_array)
@@ -923,6 +930,7 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
 		$(OUTPUT)$(vhost_virtio_ioctl_array) \
 		$(OUTPUT)$(perf_ioctl_array) \
 		$(OUTPUT)$(prctl_option_array) \
+		$(OUTPUT)$(usbdevfs_ioctl_array) \
 		$(OUTPUT)$(x86_arch_prctl_code_array) \
 		$(OUTPUT)$(rename_flags_array) \
 		$(OUTPUT)$(arch_errno_name_array)
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index f3aa9d02a5ab..d340d2e42776 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -68,7 +68,7 @@ struct c2c_hist_entry {
 	struct hist_entry	he;
 };
 
-static char const *coalesce_default = "pid,iaddr";
+static char const *coalesce_default = "iaddr";
 
 struct perf_c2c {
 	struct perf_tool	tool;
@@ -1878,7 +1878,7 @@ static int c2c_hists__reinit(struct c2c_hists *c2c_hists,
 	return hpp_list__parse(&c2c_hists->list, output, sort);
 }
 
-#define DISPLAY_LINE_LIMIT  0.0005
+#define DISPLAY_LINE_LIMIT  0.001
 
 static bool he__display(struct hist_entry *he, struct c2c_stats *stats)
 {
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 3728b50e52e2..d079f36d342d 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1073,9 +1073,18 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 
 	/*
 	 * Print final block upto sample
+	 *
+	 * Due to pipeline delays the LBRs might be missing a branch
+	 * or two, which can result in very large or negative blocks
+	 * between final branch and sample. When this happens just
+	 * continue walking after the last TO until we hit a branch.
 	 */
 	start = br->entries[0].to;
 	end = sample->ip;
+	if (end < start) {
+		/* Missing jump. Scan 128 bytes for the next branch */
+		end = start + 128;
+	}
 	len = grab_bb(buffer, start, end, machine, thread, &x.is64bit, &x.cpumode, true);
 	printed += ip__fprintf_sym(start, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
 	if (len <= 0) {
@@ -1084,7 +1093,6 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 			      machine, thread, &x.is64bit, &x.cpumode, false);
 		if (len <= 0)
 			goto out;
-
 		printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", sample->ip,
 			dump_insn(&x, sample->ip, buffer, len, NULL));
 		if (PRINT_FIELD(SRCCODE))
@@ -1096,6 +1104,13 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 				   dump_insn(&x, start + off, buffer + off, len - off, &ilen));
 		if (ilen == 0)
 			break;
+		if (arch_is_branch(buffer + off, len - off, x.is64bit) && start + off != sample->ip) {
+			/*
+			 * Hit a missing branch. Just stop.
+			 */
+			printed += fprintf(fp, "\t... not reaching sample ...\n");
+			break;
+		}
 		if (PRINT_FIELD(SRCCODE))
 			print_srccode(thread, x.cpumode, start + off);
 	}
@@ -1167,7 +1182,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
 					   struct addr_location *al, FILE *fp)
 {
 	struct perf_event_attr *attr = &evsel->attr;
-	size_t depth = thread_stack__depth(thread);
+	size_t depth = thread_stack__depth(thread, sample->cpu);
 	const char *name = NULL;
 	static int spacing;
 	int len = 0;
@@ -1701,7 +1716,7 @@ static bool show_event(struct perf_sample *sample,
 		       struct thread *thread,
 		       struct addr_location *al)
 {
-	int depth = thread_stack__depth(thread);
+	int depth = thread_stack__depth(thread, sample->cpu);
 
 	if (!symbol_conf.graph_function)
 		return true;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index ebde59e61133..adbf28183560 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -60,6 +60,7 @@
 #include <linux/stringify.h>
 #include <linux/time64.h>
 #include <fcntl.h>
+#include <sys/sysmacros.h>
 
 #include "sane_ctype.h"
 
@@ -112,8 +113,9 @@ struct trace {
 	} stats;
 	unsigned int		max_stack;
 	unsigned int		min_stack;
-	bool			sort_events;
+	int			raw_augmented_syscalls_args_size;
 	bool			raw_augmented_syscalls;
+	bool			sort_events;
 	bool			not_ev_qualifier;
 	bool			live;
 	bool			full_time;
@@ -283,12 +285,17 @@ out_delete:
 	return -ENOENT;
 }
 
-static int perf_evsel__init_augmented_syscall_tp(struct perf_evsel *evsel)
+static int perf_evsel__init_augmented_syscall_tp(struct perf_evsel *evsel, struct perf_evsel *tp)
 {
 	struct syscall_tp *sc = evsel->priv = malloc(sizeof(struct syscall_tp));
 
-	if (evsel->priv != NULL) {       /* field, sizeof_field, offsetof_field */
-		if (__tp_field__init_uint(&sc->id, sizeof(long), sizeof(long long), evsel->needs_swap))
+	if (evsel->priv != NULL) {
+		struct tep_format_field *syscall_id = perf_evsel__field(tp, "id");
+		if (syscall_id == NULL)
+			syscall_id = perf_evsel__field(tp, "__syscall_nr");
+		if (syscall_id == NULL)
+			goto out_delete;
+		if (__tp_field__init_uint(&sc->id, syscall_id->size, syscall_id->offset, evsel->needs_swap))
 			goto out_delete;
 
 		return 0;
@@ -974,9 +981,9 @@ struct thread_trace {
 		char	      *name;
 	} filename;
 	struct {
-		int	  max;
-		char	  **table;
-	} paths;
+		int	      max;
+		struct file   *table;
+	} files;
 
 	struct intlist *syscall_stats;
 };
@@ -986,7 +993,7 @@ static struct thread_trace *thread_trace__new(void)
 	struct thread_trace *ttrace =  zalloc(sizeof(struct thread_trace));
 
 	if (ttrace)
-		ttrace->paths.max = -1;
+		ttrace->files.max = -1;
 
 	ttrace->syscall_stats = intlist__new(NULL);
 
@@ -1030,30 +1037,48 @@ void syscall_arg__set_ret_scnprintf(struct syscall_arg *arg,
 
 static const size_t trace__entry_str_size = 2048;
 
-static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname)
+static struct file *thread_trace__files_entry(struct thread_trace *ttrace, int fd)
 {
-	struct thread_trace *ttrace = thread__priv(thread);
-
-	if (fd > ttrace->paths.max) {
-		char **npath = realloc(ttrace->paths.table, (fd + 1) * sizeof(char *));
+	if (fd > ttrace->files.max) {
+		struct file *nfiles = realloc(ttrace->files.table, (fd + 1) * sizeof(struct file));
 
-		if (npath == NULL)
-			return -1;
+		if (nfiles == NULL)
+			return NULL;
 
-		if (ttrace->paths.max != -1) {
-			memset(npath + ttrace->paths.max + 1, 0,
-			       (fd - ttrace->paths.max) * sizeof(char *));
+		if (ttrace->files.max != -1) {
+			memset(nfiles + ttrace->files.max + 1, 0,
+			       (fd - ttrace->files.max) * sizeof(struct file));
 		} else {
-			memset(npath, 0, (fd + 1) * sizeof(char *));
+			memset(nfiles, 0, (fd + 1) * sizeof(struct file));
 		}
 
-		ttrace->paths.table = npath;
-		ttrace->paths.max   = fd;
+		ttrace->files.table = nfiles;
+		ttrace->files.max   = fd;
 	}
 
-	ttrace->paths.table[fd] = strdup(pathname);
+	return ttrace->files.table + fd;
+}
 
-	return ttrace->paths.table[fd] != NULL ? 0 : -1;
+struct file *thread__files_entry(struct thread *thread, int fd)
+{
+	return thread_trace__files_entry(thread__priv(thread), fd);
+}
+
+static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname)
+{
+	struct thread_trace *ttrace = thread__priv(thread);
+	struct file *file = thread_trace__files_entry(ttrace, fd);
+
+	if (file != NULL) {
+		struct stat st;
+		if (stat(pathname, &st) == 0)
+			file->dev_maj = major(st.st_rdev);
+		file->pathname = strdup(pathname);
+		if (file->pathname)
+			return 0;
+	}
+
+	return -1;
 }
 
 static int thread__read_fd_path(struct thread *thread, int fd)
@@ -1093,7 +1118,7 @@ static const char *thread__fd_path(struct thread *thread, int fd,
 	if (fd < 0)
 		return NULL;
 
-	if ((fd > ttrace->paths.max || ttrace->paths.table[fd] == NULL)) {
+	if ((fd > ttrace->files.max || ttrace->files.table[fd].pathname == NULL)) {
 		if (!trace->live)
 			return NULL;
 		++trace->stats.proc_getname;
@@ -1101,7 +1126,7 @@ static const char *thread__fd_path(struct thread *thread, int fd,
 			return NULL;
 	}
 
-	return ttrace->paths.table[fd];
+	return ttrace->files.table[fd].pathname;
 }
 
 size_t syscall_arg__scnprintf_fd(char *bf, size_t size, struct syscall_arg *arg)
@@ -1140,8 +1165,8 @@ static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size,
 	size_t printed = syscall_arg__scnprintf_fd(bf, size, arg);
 	struct thread_trace *ttrace = thread__priv(arg->thread);
 
-	if (ttrace && fd >= 0 && fd <= ttrace->paths.max)
-		zfree(&ttrace->paths.table[fd]);
+	if (ttrace && fd >= 0 && fd <= ttrace->files.max)
+		zfree(&ttrace->files.table[fd].pathname);
 
 	return printed;
 }
@@ -1768,16 +1793,16 @@ static int trace__fprintf_sample(struct trace *trace, struct perf_evsel *evsel,
 	return printed;
 }
 
-static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size, bool raw_augmented)
+static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size, int raw_augmented_args_size)
 {
 	void *augmented_args = NULL;
 	/*
 	 * For now with BPF raw_augmented we hook into raw_syscalls:sys_enter
-	 * and there we get all 6 syscall args plus the tracepoint common
-	 * fields (sizeof(long)) and the syscall_nr (another long). So we check
-	 * if that is the case and if so don't look after the sc->args_size,
-	 * but always after the full raw_syscalls:sys_enter payload, which is
-	 * fixed.
+	 * and there we get all 6 syscall args plus the tracepoint common fields
+	 * that gets calculated at the start and the syscall_nr (another long).
+	 * So we check if that is the case and if so don't look after the
+	 * sc->args_size but always after the full raw_syscalls:sys_enter payload,
+	 * which is fixed.
 	 *
 	 * We'll revisit this later to pass s->args_size to the BPF augmenter
 	 * (now tools/perf/examples/bpf/augmented_raw_syscalls.c, so that it
@@ -1785,7 +1810,7 @@ static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sam
 	 * use syscalls:sys_enter_NAME, so that we reduce the kernel/userspace
 	 * traffic to just what is needed for each syscall.
 	 */
-	int args_size = raw_augmented ? (8 * (int)sizeof(long)) : sc->args_size;
+	int args_size = raw_augmented_args_size ?: sc->args_size;
 
 	*augmented_args_size = sample->raw_size - args_size;
 	if (*augmented_args_size > 0)
@@ -1839,7 +1864,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	 * here and avoid using augmented syscalls when the evsel is the raw_syscalls one.
 	 */
 	if (evsel != trace->syscalls.events.sys_enter)
-		augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls);
+		augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls_args_size);
 	ttrace->entry_time = sample->time;
 	msg = ttrace->entry_str;
 	printed += scnprintf(msg + printed, trace__entry_str_size - printed, "%s(", sc->name);
@@ -1897,7 +1922,7 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evse
 		goto out_put;
 
 	args = perf_evsel__sc_tp_ptr(evsel, args, sample);
-	augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls);
+	augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls_args_size);
 	syscall__scnprintf_args(sc, msg, sizeof(msg), args, augmented_args, augmented_args_size, trace, thread);
 	fprintf(trace->output, "%s", msg);
 	err = 0;
@@ -2686,7 +2711,9 @@ static int trace__set_ev_qualifier_filter(struct trace *trace)
 {
 	if (trace->syscalls.map)
 		return trace__set_ev_qualifier_bpf_filter(trace);
-	return trace__set_ev_qualifier_tp_filter(trace);
+	if (trace->syscalls.events.sys_enter)
+		return trace__set_ev_qualifier_tp_filter(trace);
+	return 0;
 }
 
 static int bpf_map__set_filter_pids(struct bpf_map *map __maybe_unused,
@@ -3812,13 +3839,6 @@ int cmd_trace(int argc, const char **argv)
 	 * syscall.
 	 */
 	if (trace.syscalls.events.augmented) {
-		evsel = trace.syscalls.events.augmented;
-
-		if (perf_evsel__init_augmented_syscall_tp(evsel) ||
-		    perf_evsel__init_augmented_syscall_tp_args(evsel))
-			goto out;
-		evsel->handler = trace__sys_enter;
-
 		evlist__for_each_entry(trace.evlist, evsel) {
 			bool raw_syscalls_sys_exit = strcmp(perf_evsel__name(evsel), "raw_syscalls:sys_exit") == 0;
 
@@ -3827,9 +3847,41 @@ int cmd_trace(int argc, const char **argv)
 				goto init_augmented_syscall_tp;
 			}
 
+			if (strcmp(perf_evsel__name(evsel), "raw_syscalls:sys_enter") == 0) {
+				struct perf_evsel *augmented = trace.syscalls.events.augmented;
+				if (perf_evsel__init_augmented_syscall_tp(augmented, evsel) ||
+				    perf_evsel__init_augmented_syscall_tp_args(augmented))
+					goto out;
+				augmented->handler = trace__sys_enter;
+			}
+
 			if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_")) {
+				struct syscall_tp *sc;
 init_augmented_syscall_tp:
-				perf_evsel__init_augmented_syscall_tp(evsel);
+				if (perf_evsel__init_augmented_syscall_tp(evsel, evsel))
+					goto out;
+				sc = evsel->priv;
+				/*
+				 * For now with BPF raw_augmented we hook into
+				 * raw_syscalls:sys_enter and there we get all
+				 * 6 syscall args plus the tracepoint common
+				 * fields and the syscall_nr (another long).
+				 * So we check if that is the case and if so
+				 * don't look after the sc->args_size but
+				 * always after the full raw_syscalls:sys_enter
+				 * payload, which is fixed.
+				 *
+				 * We'll revisit this later to pass
+				 * s->args_size to the BPF augmenter (now
+				 * tools/perf/examples/bpf/augmented_raw_syscalls.c,
+				 * so that it copies only what we need for each
+				 * syscall, like what happens when we use
+				 * syscalls:sys_enter_NAME, so that we reduce
+				 * the kernel/userspace traffic to just what is
+				 * needed for each syscall.
+				 */
+				if (trace.raw_augmented_syscalls)
+					trace.raw_augmented_syscalls_args_size = (6 + 1) * sizeof(long) + sc->id.offset;
 				perf_evsel__init_augmented_syscall_tp_ret(evsel);
 				evsel->handler = trace__sys_exit;
 			}
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 8e811ea0cf85..6cb98f8570a2 100755
--- a/