Merge tag 'perf-tools-fixes-for-v6.0-2022-08-13' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull more perf tool updates from Arnaldo Carvalho de Melo:

 - 'perf c2c' now supports ARM64, adjust its output to cope with
   differences with what is in x86_64. Now go find false sharing on
   ARM64 (at least Neoverse) as well!

 - Refactor the JSON processing, making the output more compact and thus
   reducing the size of the resulting perf binary

 - Improvements for 'perf offcpu' profiling, including tracking child
   processes

 - Update Intel JSON metrics and events files for broadwellde,
   broadwellx, cascadelakex, haswellx, icelakex, ivytown, jaketown,
   knightslanding, sapphirerapids, skylakex and snowridgex

 - Add 'perf stat' JSON output and a 'perf test' entry for it

 - Ignore memfd and anonymous mmap events if jitdump present

 - Refactor 'perf test' shell tests allowing subdirs

 - Fix an error handling path in 'parse_perf_probe_command()'

 - Fixes for the guest Intel PT tracing patchkit in the 1st batch of
   this merge window

 - Print debuginfod queries if -v option is used, to explain delays in
   processing when debuginfo servers are enabled to fetch DSOs with
   richer symbol tables

 - Improve error message for 'perf record -p not_existing_pid'

 - Fix openssl and libbpf feature detection

 - Add PMU pai_crypto event description for IBM z16 on 'perf list'

 - Fix typos and duplicated words on comments in various places

* tag 'perf-tools-fixes-for-v6.0-2022-08-13' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (81 commits)
  perf test: Refactor shell tests allowing subdirs
  perf vendor events: Update events for snowridgex
  perf vendor events: Update events and metrics for skylakex
  perf vendor events: Update metrics for sapphirerapids
  perf vendor events: Update events for knightslanding
  perf vendor events: Update metrics for jaketown
  perf vendor events: Update metrics for ivytown
  perf vendor events: Update events and metrics for icelakex
  perf vendor events: Update events and metrics for haswellx
  perf vendor events: Update events and metrics for cascadelakex
  perf vendor events: Update events and metrics for broadwellx
  perf vendor events: Update metrics for broadwellde
  perf jevents: Fold strings optimization
  perf jevents: Compress the pmu_events_table
  perf metrics: Copy entire pmu_event in find metric
  perf pmu-events: Hide the pmu_events
  perf pmu-events: Don't assume pmu_event is an array
  perf pmu-events: Move test events/metrics to JSON
  perf test: Use full metric resolution
  perf pmu-events: Hide pmu_events_map
  ...

Author: torvalds

tools/bpf/bpftool/Makefile

@@ -93,9 +93,11 @@ INSTALL ?= install
 RM ?= rm -f
 
 FEATURE_USER = .bpftool
-FEATURE_TESTS = libbfd disassembler-four-args disassembler-init-styled libcap \
+FEATURE_TESTS = libbfd libbfd-liberty libbfd-liberty-z \
+	disassembler-four-args disassembler-init-styled libcap \
 	clang-bpf-co-re
-FEATURE_DISPLAY = libbfd libcap clang-bpf-co-re
+FEATURE_DISPLAY = libbfd libbfd-liberty libbfd-liberty-z \
+	libcap clang-bpf-co-re
 
 check_feat := 1
 NON_CHECK_FEAT_TARGETS := clean uninstall doc doc-clean doc-install doc-uninstall

tools/build/feature/Makefile

@@ -90,14 +90,16 @@ all: $(FILES)
 
 __BUILD = $(CC) $(CFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.c,$(@F)) $(LDFLAGS)
   BUILD = $(__BUILD) > $(@:.bin=.make.output) 2>&1
+  BUILD_BFD = $(BUILD) -DPACKAGE='"perf"' -lbfd -ldl
+  BUILD_ALL = $(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lzstd -lcap
 
 __BUILDXX = $(CXX) $(CXXFLAGS) -MD -Wall -Werror -o $@ $(patsubst %.bin,%.cpp,$(@F)) $(LDFLAGS)
   BUILDXX = $(__BUILDXX) > $(@:.bin=.make.output) 2>&1
 
 ###############################
 
 $(OUTPUT)test-all.bin:
-	$(BUILD) -fstack-protector-all -O2 -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -lslang $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz -llzma -lzstd -lcap
+	$(BUILD_ALL) || $(BUILD_ALL) -lopcodes -liberty
 
 $(OUTPUT)test-hello.bin:
 	$(BUILD)
@@ -241,16 +243,18 @@ $(OUTPUT)test-libpython.bin:
 	$(BUILD) $(FLAGS_PYTHON_EMBED)
 
 $(OUTPUT)test-libbfd.bin:
-	$(BUILD) -DPACKAGE='"perf"' -lbfd -ldl
+	$(BUILD_BFD)
 
 $(OUTPUT)test-libbfd-buildid.bin:
-	$(BUILD) -DPACKAGE='"perf"' -lbfd -ldl
+	$(BUILD_BFD) || $(BUILD_BFD) -liberty || $(BUILD_BFD) -liberty -lz
 
 $(OUTPUT)test-disassembler-four-args.bin:
-	$(BUILD) -DPACKAGE='"perf"' -lbfd -lopcodes
+	$(BUILD_BFD) -lopcodes || $(BUILD_BFD) -lopcodes -liberty || \
+	$(BUILD_BFD) -lopcodes -liberty -lz
 
 $(OUTPUT)test-disassembler-init-styled.bin:
-	$(BUILD) -DPACKAGE='"perf"' -lbfd -lopcodes
+	$(BUILD_BFD) -lopcodes || $(BUILD_BFD) -lopcodes -liberty || \
+	$(BUILD_BFD) -lopcodes -liberty -lz
 
 $(OUTPUT)test-reallocarray.bin:
 	$(BUILD)

tools/build/feature/test-libcrypto.c

@@ -1,22 +1,23 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <openssl/evp.h>
 #include <openssl/sha.h>
 #include <openssl/md5.h>
 
-/*
- * The MD5_* API have been deprecated since OpenSSL 3.0, which causes the
- * feature test to fail silently. This is a workaround.
- */
-#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
-
 int main(void)
 {
-	MD5_CTX context;
+	EVP_MD_CTX *mdctx;
 	unsigned char md[MD5_DIGEST_LENGTH + SHA_DIGEST_LENGTH];
 	unsigned char dat[] = "12345";
+	unsigned int digest_len;
+
+	mdctx = EVP_MD_CTX_new();
+	if (!mdctx)
+		return 0;
 
-	MD5_Init(&context);
-	MD5_Update(&context, &dat[0], sizeof(dat));
-	MD5_Final(&md[0], &context);
+	EVP_DigestInit_ex(mdctx, EVP_md5(), NULL);
+	EVP_DigestUpdate(mdctx, &dat[0], sizeof(dat));
+	EVP_DigestFinal_ex(mdctx, &md[0], &digest_len);
+	EVP_MD_CTX_free(mdctx);
 
 	SHA1(&dat[0], sizeof(dat), &md[0]);
 

tools/include/uapi/linux/perf_event.h

@@ -1310,7 +1310,7 @@ union perf_mem_data_src {
 #define PERF_MEM_SNOOP_SHIFT	19
 
 #define PERF_MEM_SNOOPX_FWD	0x01 /* forward */
-/* 1 free */
+#define PERF_MEM_SNOOPX_PEER	0x02 /* xfer from peer */
 #define PERF_MEM_SNOOPX_SHIFT  38
 
 /* locked instruction */

tools/perf/Documentation/guest-files.txt

@@ -0,0 +1,16 @@
+include::guestmount.txt[]
+
+--guestkallsyms=<path>::
+	Guest OS /proc/kallsyms file copy. perf reads it to get guest
+	kernel symbols. Users copy it out from guest OS.
+
+--guestmodules=<path>::
+	Guest OS /proc/modules file copy. perf reads it to get guest
+	kernel module information. Users copy it out from guest OS.
+
+--guestvmlinux=<path>::
+	Guest OS kernel vmlinux.
+
+--guest-code::
+	Indicate that guest code can be found in the hypervisor process,
+	which is a common case for KVM test programs.

tools/perf/Documentation/guestmount.txt

@@ -0,0 +1,11 @@
+--guestmount=<path>::
+	Guest OS root file system mount directory. Users mount guest OS
+	root directories under <path> by a specific filesystem access method,
+	typically, sshfs.
+	For example, start 2 guest OS, one's pid is 8888 and the other's is 9999:
+[verse]
+	$ mkdir \~/guestmount
+	$ cd \~/guestmount
+	$ sshfs -o allow_other,direct_io -p 5551 localhost:/ 8888/
+	$ sshfs -o allow_other,direct_io -p 5552 localhost:/ 9999/
+	$ perf {GMEXAMPLECMD} --guestmount=~/guestmount {GMEXAMPLESUBCMD}

tools/perf/Documentation/perf-c2c.txt

@@ -109,7 +109,9 @@ REPORT OPTIONS
 
 -d::
 --display::
-	Switch to HITM type (rmt, lcl) to display and sort on. Total HITMs as default.
+	Switch to HITM type (rmt, lcl) or peer snooping type (peer) to display
+	and sort on. Total HITMs (tot) as default, except Arm64 uses peer mode
+	as default.
 
 --stitch-lbr::
 	Show callgraph with stitched LBRs, which may have more complete
@@ -174,12 +176,18 @@ For each cacheline in the 1) list we display following data:
   Cacheline
   - cacheline address (hex number)
 
-  Rmt/Lcl Hitm
+  Rmt/Lcl Hitm (Display with HITM types)
   - cacheline percentage of all Remote/Local HITM accesses
 
-  LLC Load Hitm - Total, LclHitm, RmtHitm
+  Peer Snoop (Display with peer type)
+  - cacheline percentage of all peer accesses
+
+  LLC Load Hitm - Total, LclHitm, RmtHitm (For display with HITM types)
   - count of Total/Local/Remote load HITMs
 
+  Load Peer - Total, Local, Remote (For display with peer type)
+  - count of Total/Local/Remote load from peer cache or DRAM
+
   Total records
   - sum of all cachelines accesses
 
@@ -201,16 +209,21 @@ For each cacheline in the 1) list we display following data:
   - count of LLC load accesses, includes LLC hits and LLC HITMs
 
   RMT Load Hit - RmtHit, RmtHitm
-  - count of remote load accesses, includes remote hits and remote HITMs
+  - count of remote load accesses, includes remote hits and remote HITMs;
+    on Arm neoverse cores, RmtHit is used to account remote accesses,
+    includes remote DRAM or any upward cache level in remote node
 
   Load Dram - Lcl, Rmt
   - count of local and remote DRAM accesses
 
 For each offset in the 2) list we display following data:
 
-  HITM - Rmt, Lcl
+  HITM - Rmt, Lcl (Display with HITM types)
   - % of Remote/Local HITM accesses for given offset within cacheline
 
+  Peer Snoop - Rmt, Lcl (Display with peer type)
+  - % of Remote/Local peer accesses for given offset within cacheline
+
   Store Refs - L1 Hit, L1 Miss, N/A
   - % of store accesses that hit L1, missed L1 and N/A (no available) memory
     level for given offset within cacheline
@@ -227,9 +240,12 @@ For each offset in the 2) list we display following data:
   Code address
   - code address responsible for the accesses
 
-  cycles - rmt hitm, lcl hitm, load
+  cycles - rmt hitm, lcl hitm, load (Display with HITM types)
     - sum of cycles for given accesses - Remote/Local HITM and generic load
 
+  cycles - rmt peer, lcl peer, load (Display with peer type)
+    - sum of cycles for given accesses - Remote/Local peer load and generic load
+
   cpu cnt
     - number of cpus that participated on the access
 
@@ -251,7 +267,8 @@ The 'Node' field displays nodes that accesses given cacheline
 offset. Its output comes in 3 flavors:
   - node IDs separated by ','
   - node IDs with stats for each ID, in following format:
-      Node{cpus %hitms %stores}
+      Node{cpus %hitms %stores} (Display with HITM types)
+      Node{cpus %peers %stores} (Display with peer type)
   - node IDs with list of affected CPUs in following format:
       Node{cpu list}
 

tools/perf/Documentation/perf-inject.txt

@@ -102,6 +102,10 @@ include::itrace.txt[]
 	should be used, and also --buildid-all and --switch-events may be
 	useful.
 
+:GMEXAMPLECMD: inject
+:GMEXAMPLESUBCMD:
+include::guestmount.txt[]
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1],

tools/perf/Documentation/perf-kvm.txt

@@ -77,26 +77,11 @@ OPTIONS
         Collect host side performance profile.
 --guest::
         Collect guest side performance profile.
---guestmount=<path>::
-	Guest os root file system mount directory. Users mounts guest os
-        root directories under <path> by a specific filesystem access method,
-	typically, sshfs. For example, start 2 guest os. The one's pid is 8888
-	and the other's is 9999.
-        #mkdir ~/guestmount; cd ~/guestmount
-        #sshfs -o allow_other,direct_io -p 5551 localhost:/ 8888/
-        #sshfs -o allow_other,direct_io -p 5552 localhost:/ 9999/
-        #perf kvm --host --guest --guestmount=~/guestmount top
---guestkallsyms=<path>::
-        Guest os /proc/kallsyms file copy. 'perf' kvm' reads it to get guest
-	kernel symbols. Users copy it out from guest os.
---guestmodules=<path>::
-	Guest os /proc/modules file copy. 'perf' kvm' reads it to get guest
-	kernel module information. Users copy it out from guest os.
---guestvmlinux=<path>::
-	Guest os kernel vmlinux.
---guest-code::
-	Indicate that guest code can be found in the hypervisor process,
-	which is a common case for KVM test programs.
+
+:GMEXAMPLECMD: kvm --host --guest
+:GMEXAMPLESUBCMD: top
+include::guest-files.txt[]
+
 -v::
 --verbose::
 	Be more verbose (show counter open errors, etc).

tools/perf/Documentation/perf-script.txt

@@ -228,7 +228,7 @@ OPTIONS
 	Instruction Trace decoding.
 
 	The machine_pid and vcpu fields are derived from data resulting from using
-	perf insert to insert a perf.data file recorded inside a virtual machine into
+	perf inject to insert a perf.data file recorded inside a virtual machine into
 	a perf.data file recorded on the host at the same time.
 
 	Finally, a user may not set fields to none for all event types.
@@ -507,9 +507,9 @@ include::itrace.txt[]
 	The known limitations include exception handing such as
 	setjmp/longjmp will have calls/returns not match.
 
---guest-code::
-	Indicate that guest code can be found in the hypervisor process,
-	which is a common case for KVM test programs.
+:GMEXAMPLECMD: script
+:GMEXAMPLESUBCMD:
+include::guest-files.txt[]
 
 SEE ALSO
 --------