perf tools fixes for v5.19: 5th batch

- Fix addresses for bss symbols, describing variables used in resolving data
   access in tools such as 'perf c2c' and 'perf mem'.
 
 - Skip symbols if SHF_ALLOC flag is not set, a technique used for
   listing deprecated symbols, its addresses are zeros, so not useful.
 
 - Remove undefined behavior from bpf_perf_object__next() when
   dealing with an empty bpf_objects_list list.
 
 - Make a ARM CoreSight disasm script work with both python2 and python3.
 
 - Sync x86's cpufeatures header with with the kernel sources.
 
 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQR2GiIUctdOfX2qHhGyPKLppCJ+JwUCYuQG9QAKCRCyPKLppCJ+
 JxtPAP9KlHo6mrPNtjly6jLJ0VvbS2NoJAg8gY1oIJBx68jE2QD+KRAZ7g6XaUuo
 4c0BGm41QFyCIrUCDHMJhGJGI6g7NwI=
 =ktD4
 -----END PGP SIGNATURE-----

Merge tag 'perf-tools-fixes-for-v5.19-2022-07-29' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Fix addresses for bss symbols, describing variables used in resolving
   data access in tools such as 'perf c2c' and 'perf mem'.

 - Skip symbols if SHF_ALLOC flag is not set, a technique used for
   listing deprecated symbols, its addresses are zeros, so not useful.

 - Remove undefined behavior from bpf_perf_object__next() when dealing
   with an empty bpf_objects_list list.

 - Make a ARM CoreSight disasm script work with both python2 and
   python3.

 - Sync x86's cpufeatures header with with the kernel sources.

* tag 'perf-tools-fixes-for-v5.19-2022-07-29' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf bpf: Remove undefined behavior from bpf_perf_object__next()
  perf symbol: Skip symbols if SHF_ALLOC flag is not set
  perf symbol: Correct address for bss symbols
  perf scripts python: Let script to be python2 compliant
  tools headers cpufeatures: Sync with the kernel sources

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

@@ -302,6 +302,7 @@
 #define X86_FEATURE_RETPOLINE_LFENCE	(11*32+13) /* "" Use LFENCE for Spectre variant 2 */
 #define X86_FEATURE_RETHUNK		(11*32+14) /* "" Use REturn THUNK */
 #define X86_FEATURE_UNRET		(11*32+15) /* "" AMD BTB untrain return */
+#define X86_FEATURE_USE_IBPB_FW		(11*32+16) /* "" Use IBPB during runtime firmware calls */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */

tools/perf/scripts/python/arm-cs-trace-disasm.py

@@ -61,7 +61,7 @@ def get_optional(perf_dict, field):
 
 def get_offset(perf_dict, field):
 	if field in perf_dict:
-		return f"+0x{perf_dict[field]:x}"
+		return "+%#x" % perf_dict[field]
 	return ""
 
 def get_dso_file_path(dso_name, dso_build_id):
@@ -76,7 +76,7 @@ def get_dso_file_path(dso_name, dso_build_id):
 	else:
 		append = "/elf"
 
-	dso_path = f"{os.environ['PERF_BUILDID_DIR']}/{dso_name}/{dso_build_id}{append}"
+	dso_path = os.environ['PERF_BUILDID_DIR'] + "/" + dso_name + "/" + dso_build_id + append;
 	# Replace duplicate slash chars to single slash char
 	dso_path = dso_path.replace('//', '/', 1)
 	return dso_path
@@ -94,8 +94,8 @@ def read_disam(dso_fname, dso_start, start_addr, stop_addr):
 		start_addr = start_addr - dso_start;
 		stop_addr = stop_addr - dso_start;
 		disasm = [ options.objdump_name, "-d", "-z",
-			   f"--start-address=0x{start_addr:x}",
-			   f"--stop-address=0x{stop_addr:x}" ]
+			   "--start-address="+format(start_addr,"#x"),
+			   "--stop-address="+format(stop_addr,"#x") ]
 		disasm += [ dso_fname ]
 		disasm_output = check_output(disasm).decode('utf-8').split('\n')
 		disasm_cache[addr_range] = disasm_output
@@ -109,12 +109,14 @@ def print_disam(dso_fname, dso_start, start_addr, stop_addr):
 			m = disasm_re.search(line)
 			if m is None:
 				continue
-		print(f"\t{line}")
+		print("\t" + line)
 
 def print_sample(sample):
-	print(f"Sample = {{ cpu: {sample['cpu']:04} addr: 0x{sample['addr']:016x} " \
-	      f"phys_addr: 0x{sample['phys_addr']:016x} ip: 0x{sample['ip']:016x} " \
-	      f"pid: {sample['pid']} tid: {sample['tid']} period: {sample['period']} time: {sample['time']} }}")
+	print("Sample = { cpu: %04d addr: 0x%016x phys_addr: 0x%016x ip: 0x%016x " \
+	      "pid: %d tid: %d period: %d time: %d }" % \
+	      (sample['cpu'], sample['addr'], sample['phys_addr'], \
+	       sample['ip'], sample['pid'], sample['tid'], \
+	       sample['period'], sample['time']))
 
 def trace_begin():
 	print('ARM CoreSight Trace Data Assembler Dump')
@@ -131,7 +133,7 @@ def common_start_str(comm, sample):
 	cpu = sample["cpu"]
 	pid = sample["pid"]
 	tid = sample["tid"]
-	return f"{comm:>16} {pid:>5}/{tid:<5} [{cpu:04}] {sec:9}.{ns:09}  "
+	return "%16s %5u/%-5u [%04u] %9u.%09u  " % (comm, pid, tid, cpu, sec, ns)
 
 # This code is copied from intel-pt-events.py for printing source code
 # line and symbols.
@@ -171,7 +173,7 @@ def print_srccode(comm, param_dict, sample, symbol, dso):
 	glb_line_number = line_number
 	glb_source_file_name = source_file_name
 
-	print(f"{start_str}{src_str}")
+	print(start_str, src_str)
 
 def process_event(param_dict):
 	global cache_size
@@ -188,7 +190,7 @@ def process_event(param_dict):
 	symbol = get_optional(param_dict, "symbol")
 
 	if (options.verbose == True):
-		print(f"Event type: {name}")
+		print("Event type: %s" % name)
 		print_sample(sample)
 
 	# If cannot find dso so cannot dump assembler, bail out
@@ -197,7 +199,7 @@ def process_event(param_dict):
 
 	# Validate dso start and end addresses
 	if ((dso_start == '[unknown]') or (dso_end == '[unknown]')):
-		print(f"Failed to find valid dso map for dso {dso}")
+		print("Failed to find valid dso map for dso %s" % dso)
 		return
 
 	if (name[0:12] == "instructions"):
@@ -244,15 +246,15 @@ def process_event(param_dict):
 
 	# Handle CS_ETM_TRACE_ON packet if start_addr=0 and stop_addr=4
 	if (start_addr == 0 and stop_addr == 4):
-		print(f"CPU{cpu}: CS_ETM_TRACE_ON packet is inserted")
+		print("CPU%d: CS_ETM_TRACE_ON packet is inserted" % cpu)
 		return
 
 	if (start_addr < int(dso_start) or start_addr > int(dso_end)):
-		print(f"Start address 0x{start_addr:x} is out of range [ 0x{dso_start:x} .. 0x{dso_end:x} ] for dso {dso}")
+		print("Start address 0x%x is out of range [ 0x%x .. 0x%x ] for dso %s" % (start_addr, int(dso_start), int(dso_end), dso))
 		return
 
 	if (stop_addr < int(dso_start) or stop_addr > int(dso_end)):
-		print(f"Stop address 0x{stop_addr:x} is out of range [ 0x{dso_start:x} .. 0x{dso_end:x} ] for dso {dso}")
+		print("Stop address 0x%x is out of range [ 0x%x .. 0x%x ] for dso %s" % (stop_addr, int(dso_start), int(dso_end), dso))
 		return
 
 	if (options.objdump_name != None):
@@ -267,6 +269,6 @@ def process_event(param_dict):
 		if path.exists(dso_fname):
 			print_disam(dso_fname, dso_vm_start, start_addr, stop_addr)
 		else:
-			print(f"Failed to find dso {dso} for address range [ 0x{start_addr:x} .. 0x{stop_addr:x} ]")
+			print("Failed to find dso %s for address range [ 0x%x .. 0x%x ]" % (dso, start_addr, stop_addr))
 
 	print_srccode(comm, param_dict, sample, symbol, dso)

tools/perf/util/bpf-loader.c

@@ -63,20 +63,16 @@ static struct hashmap *bpf_map_hash;
 static struct bpf_perf_object *
 bpf_perf_object__next(struct bpf_perf_object *prev)
 {
-	struct bpf_perf_object *next;
+	if (!prev) {
+		if (list_empty(&bpf_objects_list))
+			return NULL;
 
-	if (!prev)
-		next = list_first_entry(&bpf_objects_list,
-					struct bpf_perf_object,
-					list);
-	else
-		next = list_next_entry(prev, list);
-
-	/* Empty list is noticed here so don't need checking on entry. */
-	if (&next->list == &bpf_objects_list)
+		return list_first_entry(&bpf_objects_list, struct bpf_perf_object, list);
+	}
+	if (list_is_last(&prev->list, &bpf_objects_list))
 		return NULL;
 
-	return next;
+	return list_next_entry(prev, list);
 }
 
 #define bpf_perf_object__for_each(perf_obj, tmp)	\

tools/perf/util/symbol-elf.c

@@ -233,6 +233,33 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
 	return NULL;
 }
 
+static int elf_read_program_header(Elf *elf, u64 vaddr, GElf_Phdr *phdr)
+{
+	size_t i, phdrnum;
+	u64 sz;
+
+	if (elf_getphdrnum(elf, &phdrnum))
+		return -1;
+
+	for (i = 0; i < phdrnum; i++) {
+		if (gelf_getphdr(elf, i, phdr) == NULL)
+			return -1;
+
+		if (phdr->p_type != PT_LOAD)
+			continue;
+
+		sz = max(phdr->p_memsz, phdr->p_filesz);
+		if (!sz)
+			continue;
+
+		if (vaddr >= phdr->p_vaddr && (vaddr < phdr->p_vaddr + sz))
+			return 0;
+	}
+
+	/* Not found any valid program header */
+	return -1;
+}
+
 static bool want_demangle(bool is_kernel_sym)
 {
 	return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
@@ -1209,6 +1236,7 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 					sym.st_value);
 			used_opd = true;
 		}
+
 		/*
 		 * When loading symbols in a data mapping, ABS symbols (which
 		 * has a value of SHN_ABS in its st_shndx) failed at
@@ -1227,6 +1255,17 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 
 		gelf_getshdr(sec, &shdr);
 
+		/*
+		 * If the attribute bit SHF_ALLOC is not set, the section
+		 * doesn't occupy memory during process execution.
+		 * E.g. ".gnu.warning.*" section is used by linker to generate
+		 * warnings when calling deprecated functions, the symbols in
+		 * the section aren't loaded to memory during process execution,
+		 * so skip them.
+		 */
+		if (!(shdr.sh_flags & SHF_ALLOC))
+			continue;
+
 		secstrs = secstrs_sym;
 
 		/*
@@ -1262,11 +1301,20 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 				goto out_elf_end;
 		} else if ((used_opd && runtime_ss->adjust_symbols) ||
 			   (!used_opd && syms_ss->adjust_symbols)) {
+			GElf_Phdr phdr;
+
+			if (elf_read_program_header(syms_ss->elf,
+						    (u64)sym.st_value, &phdr)) {
+				pr_warning("%s: failed to find program header for "
+					   "symbol: %s st_value: %#" PRIx64 "\n",
+					   __func__, elf_name, (u64)sym.st_value);
+				continue;
+			}
 			pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " "
-				  "sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n", __func__,
-				  (u64)sym.st_value, (u64)shdr.sh_addr,
-				  (u64)shdr.sh_offset);
-			sym.st_value -= shdr.sh_addr - shdr.sh_offset;
+				  "p_vaddr: %#" PRIx64 " p_offset: %#" PRIx64 "\n",
+				  __func__, (u64)sym.st_value, (u64)phdr.p_vaddr,
+				  (u64)phdr.p_offset);
+			sym.st_value -= phdr.p_vaddr - phdr.p_offset;
 		}
 
 		demangled = demangle_sym(dso, kmodule, elf_name);