diff options
Diffstat (limited to 'tools/testing/selftests')
83 files changed, 3128 insertions, 322 deletions
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index d10f95ce2ea4..45f145c6f843 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -2,8 +2,10 @@ TARGETS = breakpoints TARGETS += cpu-hotplug TARGETS += efivarfs TARGETS += kcmp +TARGETS += memfd TARGETS += memory-hotplug TARGETS += mqueue +TARGETS += mount TARGETS += net TARGETS += ptrace TARGETS += timers @@ -12,6 +14,7 @@ TARGETS += powerpc TARGETS += user TARGETS += sysctl TARGETS += firmware +TARGETS += ftrace TARGETS_HOTPLUG = cpu-hotplug TARGETS_HOTPLUG += memory-hotplug diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile new file mode 100644 index 000000000000..76cc9f156267 --- /dev/null +++ b/tools/testing/selftests/ftrace/Makefile @@ -0,0 +1,7 @@ +all: + +run_tests: + @/bin/sh ./ftracetest || echo "ftrace selftests: [FAIL]" + +clean: + rm -rf logs/* diff --git a/tools/testing/selftests/ftrace/README b/tools/testing/selftests/ftrace/README new file mode 100644 index 000000000000..182e76fa4b82 --- /dev/null +++ b/tools/testing/selftests/ftrace/README @@ -0,0 +1,82 @@ +Linux Ftrace Testcases + +This is a collection of testcases for ftrace tracing feature in the Linux +kernel. Since ftrace exports interfaces via the debugfs, we just need +shell scripts for testing. Feel free to add new test cases. + +Running the ftrace testcases +============================ + +At first, you need to be the root user to run this script. +To run all testcases: + + $ sudo ./ftracetest + +To run specific testcases: + + # ./ftracetest test.d/basic3.tc + +Or you can also run testcases under given directory: + + # ./ftracetest test.d/kprobe/ + +Contributing new testcases +========================== + +Copy test.d/template to your testcase (whose filename must have *.tc +extension) and rewrite the test description line. + + * The working directory of the script is <debugfs>/tracing/. + + * Take care with side effects as the tests are run with root privilege. + + * The tests should not run for a long period of time (more than 1 min.) + These are to be unit tests. + + * You can add a directory for your testcases under test.d/ if needed. + + * The test cases should run on dash (busybox shell) for testing on + minimal cross-build environments. + + * Note that the tests are run with "set -e" (errexit) option. If any + command fails, the test will be terminated immediately. + + * The tests can return some result codes instead of pass or fail by + using exit_unresolved, exit_untested, exit_unsupported and exit_xfail. + +Result code +=========== + +Ftracetest supports following result codes. + + * PASS: The test succeeded as expected. The test which exits with 0 is + counted as passed test. + + * FAIL: The test failed, but was expected to succeed. The test which exits + with !0 is counted as failed test. + + * UNRESOLVED: The test produced unclear or intermidiate results. + for example, the test was interrupted + or the test depends on a previous test, which failed. + or the test was set up incorrectly + The test which is in above situation, must call exit_unresolved. + + * UNTESTED: The test was not run, currently just a placeholder. + In this case, the test must call exit_untested. + + * UNSUPPORTED: The test failed because of lack of feature. + In this case, the test must call exit_unsupported. + + * XFAIL: The test failed, and was expected to fail. + To return XFAIL, call exit_xfail from the test. + +There are some sample test scripts for result code under samples/. +You can also run samples as below: + + # ./ftracetest samples/ + +TODO +==== + + * Fancy colored output :) + diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest new file mode 100755 index 000000000000..515247601df4 --- /dev/null +++ b/tools/testing/selftests/ftrace/ftracetest @@ -0,0 +1,253 @@ +#!/bin/sh + +# ftracetest - Ftrace test shell scripts +# +# Copyright (C) Hitachi Ltd., 2014 +# Written by Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> +# +# Released under the terms of the GPL v2. + +usage() { # errno [message] +[ "$2" ] && echo $2 +echo "Usage: ftracetest [options] [testcase(s)] [testcase-directory(s)]" +echo " Options:" +echo " -h|--help Show help message" +echo " -k|--keep Keep passed test logs" +echo " -d|--debug Debug mode (trace all shell commands)" +exit $1 +} + +errexit() { # message + echo "Error: $1" 1>&2 + exit 1 +} + +# Ensuring user privilege +if [ `id -u` -ne 0 ]; then + errexit "this must be run by root user" +fi + +# Utilities +absdir() { # file_path + (cd `dirname $1`; pwd) +} + +abspath() { + echo `absdir $1`/`basename $1` +} + +find_testcases() { #directory + echo `find $1 -name \*.tc` +} + +parse_opts() { # opts + local OPT_TEST_CASES= + local OPT_TEST_DIR= + + while [ "$1" ]; do + case "$1" in + --help|-h) + usage 0 + ;; + --keep|-k) + KEEP_LOG=1 + shift 1 + ;; + --debug|-d) + DEBUG=1 + shift 1 + ;; + *.tc) + if [ -f "$1" ]; then + OPT_TEST_CASES="$OPT_TEST_CASES `abspath $1`" + shift 1 + else + usage 1 "$1 is not a testcase" + fi + ;; + *) + if [ -d "$1" ]; then + OPT_TEST_DIR=`abspath $1` + OPT_TEST_CASES="$OPT_TEST_CASES `find_testcases $OPT_TEST_DIR`" + shift 1 + else + usage 1 "Invalid option ($1)" + fi + ;; + esac + done + if [ "$OPT_TEST_CASES" ]; then + TEST_CASES=$OPT_TEST_CASES + fi +} + +# Parameters +DEBUGFS_DIR=`grep debugfs /proc/mounts | cut -f2 -d' ' | head -1` +TRACING_DIR=$DEBUGFS_DIR/tracing +TOP_DIR=`absdir $0` +TEST_DIR=$TOP_DIR/test.d +TEST_CASES=`find_testcases $TEST_DIR` +LOG_DIR=$TOP_DIR/logs/`date +%Y%m%d-%H%M%S`/ +KEEP_LOG=0 +DEBUG=0 +# Parse command-line options +parse_opts $* + +[ $DEBUG -ne 0 ] && set -x + +# Verify parameters +if [ -z "$DEBUGFS_DIR" -o ! -d "$TRACING_DIR" ]; then + errexit "No ftrace directory found" +fi + +# Preparing logs +LOG_FILE=$LOG_DIR/ftracetest.log +mkdir -p $LOG_DIR || errexit "Failed to make a log directory: $LOG_DIR" +date > $LOG_FILE +prlog() { # messages + echo "$@" | tee -a $LOG_FILE +} +catlog() { #file + cat $1 | tee -a $LOG_FILE +} +prlog "=== Ftrace unit tests ===" + + +# Testcase management +# Test result codes - Dejagnu extended code +PASS=0 # The test succeeded. +FAIL=1 # The test failed, but was expected to succeed. +UNRESOLVED=2 # The test produced indeterminate results. (e.g. interrupted) +UNTESTED=3 # The test was not run, currently just a placeholder. +UNSUPPORTED=4 # The test failed because of lack of feature. +XFAIL=5 # The test failed, and was expected to fail. + +# Accumulations +PASSED_CASES= +FAILED_CASES= +UNRESOLVED_CASES= +UNTESTED_CASES= +UNSUPPORTED_CASES= +XFAILED_CASES= +UNDEFINED_CASES= +TOTAL_RESULT=0 + +CASENO=0 +testcase() { # testfile + CASENO=$((CASENO+1)) + prlog -n "[$CASENO]"`grep "^#[ \t]*description:" $1 | cut -f2 -d:` +} + +eval_result() { # retval sigval + local retval=$2 + if [ $2 -eq 0 ]; then + test $1 -ne 0 && retval=$FAIL + fi + case $retval in + $PASS) + prlog " [PASS]" + PASSED_CASES="$PASSED_CASES $CASENO" + return 0 + ;; + $FAIL) + prlog " [FAIL]" + FAILED_CASES="$FAILED_CASES $CASENO" + return 1 # this is a bug. + ;; + $UNRESOLVED) + prlog " [UNRESOLVED]" + UNRESOLVED_CASES="$UNRESOLVED_CASES $CASENO" + return 1 # this is a kind of bug.. something happened. + ;; + $UNTESTED) + prlog " [UNTESTED]" + UNTESTED_CASES="$UNTESTED_CASES $CASENO" + return 0 + ;; + $UNSUPPORTED) + prlog " [UNSUPPORTED]" + UNSUPPORTED_CASES="$UNSUPPORTED_CASES $CASENO" + return 1 # this is not a bug, but the result should be reported. + ;; + $XFAIL) + prlog " [XFAIL]" + XFAILED_CASES="$XFAILED_CASES $CASENO" + return 0 + ;; + *) + prlog " [UNDEFINED]" + UNDEFINED_CASES="$UNDEFINED_CASES $CASENO" + return 1 # this must be a test bug + ;; + esac +} + +# Signal handling for result codes +SIG_RESULT= +SIG_BASE=36 # Use realtime signals +SIG_PID=$$ + +SIG_UNRESOLVED=$((SIG_BASE + UNRESOLVED)) +exit_unresolved () { + kill -s $SIG_UNRESOLVED $SIG_PID + exit 0 +} +trap 'SIG_RESULT=$UNRESOLVED' $SIG_UNRESOLVED + +SIG_UNTESTED=$((SIG_BASE + UNTESTED)) +exit_untested () { + kill -s $SIG_UNTESTED $SIG_PID + exit 0 +} +trap 'SIG_RESULT=$UNTESTED' $SIG_UNTESTED + +SIG_UNSUPPORTED=$((SIG_BASE + UNSUPPORTED)) +exit_unsupported () { + kill -s $SIG_UNSUPPORTED $SIG_PID + exit 0 +} +trap 'SIG_RESULT=$UNSUPPORTED' $SIG_UNSUPPORTED + +SIG_XFAIL=$((SIG_BASE + XFAIL)) +exit_xfail () { + kill -s $SIG_XFAIL $SIG_PID + exit 0 +} +trap 'SIG_RESULT=$XFAIL' $SIG_XFAIL + +# Run one test case +run_test() { # testfile + local testname=`basename $1` + local testlog=`mktemp --tmpdir=$LOG_DIR ${testname}-XXXXXX.log` + testcase $1 + echo "execute: "$1 > $testlog + SIG_RESULT=0 + # setup PID and PPID, $$ is not updated. + (cd $TRACING_DIR; read PID _ < /proc/self/stat ; + set -e; set -x; . $1) >> $testlog 2>&1 + eval_result $? $SIG_RESULT + if [ $? -eq 0 ]; then + # Remove test log if the test was done as it was expected. + [ $KEEP_LOG -eq 0 ] && rm $testlog + else + catlog $testlog + TOTAL_RESULT=1 + fi +} + +# Main loop +for t in $TEST_CASES; do + run_test $t +done + +prlog "" +prlog "# of passed: " `echo $PASSED_CASES | wc -w` +prlog "# of failed: " `echo $FAILED_CASES | wc -w` +prlog "# of unresolved: " `echo $UNRESOLVED_CASES | wc -w` +prlog "# of untested: " `echo $UNTESTED_CASES | wc -w` +prlog "# of unsupported: " `echo $UNSUPPORTED_CASES | wc -w` +prlog "# of xfailed: " `echo $XFAILED_CASES | wc -w` +prlog "# of undefined(test bug): " `echo $UNDEFINED_CASES | wc -w` + +# if no error, return 0 +exit $TOTAL_RESULT diff --git a/tools/testing/selftests/ftrace/samples/fail.tc b/tools/testing/selftests/ftrace/samples/fail.tc new file mode 100644 index 000000000000..15e35b956e05 --- /dev/null +++ b/tools/testing/selftests/ftrace/samples/fail.tc @@ -0,0 +1,4 @@ +#!/bin/sh +# description: failure-case example +cat non-exist-file +echo "this is not executed" diff --git a/tools/testing/selftests/ftrace/samples/pass.tc b/tools/testing/selftests/ftrace/samples/pass.tc new file mode 100644 index 000000000000..d01549370041 --- /dev/null +++ b/tools/testing/selftests/ftrace/samples/pass.tc @@ -0,0 +1,3 @@ +#!/bin/sh +# description: pass-case example +return 0 diff --git a/tools/testing/selftests/ftrace/samples/unresolved.tc b/tools/testing/selftests/ftrace/samples/unresolved.tc new file mode 100644 index 000000000000..41e99d3358d1 --- /dev/null +++ b/tools/testing/selftests/ftrace/samples/unresolved.tc @@ -0,0 +1,4 @@ +#!/bin/sh +# description: unresolved-case example +trap exit_unresolved INT +kill -INT $PID diff --git a/tools/testing/selftests/ftrace/samples/unsupported.tc b/tools/testing/selftests/ftrace/samples/unsupported.tc new file mode 100644 index 000000000000..45910ff13328 --- /dev/null +++ b/tools/testing/selftests/ftrace/samples/unsupported.tc @@ -0,0 +1,3 @@ +#!/bin/sh +# description: unsupported-case example +exit_unsupported diff --git a/tools/testing/selftests/ftrace/samples/untested.tc b/tools/testing/selftests/ftrace/samples/untested.tc new file mode 100644 index 000000000000..35a45946ec60 --- /dev/null +++ b/tools/testing/selftests/ftrace/samples/untested.tc @@ -0,0 +1,3 @@ +#!/bin/sh +# description: untested-case example +exit_untested diff --git a/tools/testing/selftests/ftrace/samples/xfail.tc b/tools/testing/selftests/ftrace/samples/xfail.tc new file mode 100644 index 000000000000..9dd395323259 --- /dev/null +++ b/tools/testing/selftests/ftrace/samples/xfail.tc @@ -0,0 +1,3 @@ +#!/bin/sh +# description: xfail-case example +cat non-exist-file || exit_xfail diff --git a/tools/testing/selftests/ftrace/test.d/00basic/basic1.tc b/tools/testing/selftests/ftrace/test.d/00basic/basic1.tc new file mode 100644 index 000000000000..9980ff14ae44 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/00basic/basic1.tc @@ -0,0 +1,3 @@ +#!/bin/sh +# description: Basic trace file check +test -f README -a -f trace -a -f tracing_on -a -f trace_pipe diff --git a/tools/testing/selftests/ftrace/test.d/00basic/basic2.tc b/tools/testing/selftests/ftrace/test.d/00basic/basic2.tc new file mode 100644 index 000000000000..bf9a7b037924 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/00basic/basic2.tc @@ -0,0 +1,7 @@ +#!/bin/sh +# description: Basic test for tracers +test -f available_tracers +for t in `cat available_tracers`; do + echo $t > current_tracer +done +echo nop > current_tracer diff --git a/tools/testing/selftests/ftrace/test.d/00basic/basic3.tc b/tools/testing/selftests/ftrace/test.d/00basic/basic3.tc new file mode 100644 index 000000000000..bde6625d9785 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/00basic/basic3.tc @@ -0,0 +1,8 @@ +#!/bin/sh +# description: Basic trace clock test +test -f trace_clock +for c in `cat trace_clock | tr -d \[\]`; do + echo $c > trace_clock + grep '\['$c'\]' trace_clock +done +echo local > trace_clock diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc new file mode 100644 index 000000000000..1b8b665ab2b3 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/add_and_remove.tc @@ -0,0 +1,11 @@ +#!/bin/sh +# description: Kprobe dynamic event - adding and removing + +[ -f kprobe_events ] || exit_unsupported # this is configurable + +echo 0 > events/enable +echo > kprobe_events +echo p:myevent do_fork > kprobe_events +grep myevent kprobe_events +test -d events/kprobes/myevent +echo > kprobe_events diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc new file mode 100644 index 000000000000..b55c84003587 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/busy_check.tc @@ -0,0 +1,13 @@ +#!/bin/sh +# description: Kprobe dynamic event - busy event check + +[ -f kprobe_events ] || exit_unsupported + +echo 0 > events/enable +echo > kprobe_events +echo p:myevent do_fork > kprobe_events +test -d events/kprobes/myevent +echo 1 > events/kprobes/myevent/enable +echo > kprobe_events && exit 1 # this must fail +echo 0 > events/kprobes/myevent/enable +echo > kprobe_events # this must succeed diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc new file mode 100644 index 000000000000..a603d3f8db7b --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args.tc @@ -0,0 +1,16 @@ +#!/bin/sh +# description: Kprobe dynamic event with arguments + +[ -f kprobe_events ] || exit_unsupported # this is configurable + +echo 0 > events/enable +echo > kprobe_events +echo 'p:testprobe do_fork $stack $stack0 +0($stack)' > kprobe_events +grep testprobe kprobe_events +test -d events/kprobes/testprobe +echo 1 > events/kprobes/testprobe/enable +( echo "forked") +echo 0 > events/kprobes/testprobe/enable +echo "-:testprobe" >> kprobe_events +test -d events/kprobes/testprobe && exit 1 || exit 0 + diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc new file mode 100644 index 000000000000..283c29e7f7c4 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kretprobe_args.tc @@ -0,0 +1,15 @@ +#!/bin/sh +# description: Kretprobe dynamic event with arguments + +[ -f kprobe_events ] || exit_unsupported # this is configurable + +echo 0 > events/enable +echo > kprobe_events +echo 'r:testprobe2 do_fork $retval' > kprobe_events +grep testprobe2 kprobe_events +test -d events/kprobes/testprobe2 +echo 1 > events/kprobes/testprobe2/enable +( echo "forked") +echo 0 > events/kprobes/testprobe2/enable +echo '-:testprobe2' >> kprobe_events +test -d events/kprobes/testprobe2 && exit 1 || exit 0 diff --git a/tools/testing/selftests/ftrace/test.d/template b/tools/testing/selftests/ftrace/test.d/template new file mode 100644 index 000000000000..5448f7abad5f --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/template @@ -0,0 +1,9 @@ +#!/bin/sh +# description: %HERE DESCRIBE WHAT THIS DOES% +# you have to add ".tc" extention for your testcase file +# Note that all tests are run with "errexit" option. + +exit 0 # Return 0 if the test is passed, otherwise return !0 +# If the test could not run because of lack of feature, call exit_unsupported +# If the test returned unclear results, call exit_unresolved +# If the test is a dummy, or a placeholder, call exit_untested diff --git a/tools/testing/selftests/ipc/Makefile b/tools/testing/selftests/ipc/Makefile index 5386fd7c43ae..74bbefdeaf4c 100644 --- a/tools/testing/selftests/ipc/Makefile +++ b/tools/testing/selftests/ipc/Makefile @@ -1,18 +1,18 @@ uname_M := $(shell uname -m 2>/dev/null || echo not) ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/) ifeq ($(ARCH),i386) - ARCH := X86 + ARCH := x86 CFLAGS := -DCONFIG_X86_32 -D__i386__ endif ifeq ($(ARCH),x86_64) - ARCH := X86 + ARCH := x86 CFLAGS := -DCONFIG_X86_64 -D__x86_64__ endif CFLAGS += -I../../../../usr/include/ all: -ifeq ($(ARCH),X86) +ifeq ($(ARCH),x86) gcc $(CFLAGS) msgque.c -o msgque_test else echo "Not an x86 target, can't build msgque selftest" diff --git a/tools/testing/selftests/kcmp/Makefile b/tools/testing/selftests/kcmp/Makefile index d7d6bbeeff2f..8aabd82db9e4 100644 --- a/tools/testing/selftests/kcmp/Makefile +++ b/tools/testing/selftests/kcmp/Makefile @@ -1,11 +1,11 @@ uname_M := $(shell uname -m 2>/dev/null || echo not) ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/) ifeq ($(ARCH),i386) - ARCH := X86 + ARCH := x86 CFLAGS := -DCONFIG_X86_32 -D__i386__ endif ifeq ($(ARCH),x86_64) - ARCH := X86 + ARCH := x86 CFLAGS := -DCONFIG_X86_64 -D__x86_64__ endif @@ -15,7 +15,7 @@ CFLAGS += -I../../../../usr/include/ CFLAGS += -I../../../../arch/x86/include/ all: -ifeq ($(ARCH),X86) +ifeq ($(ARCH),x86) gcc $(CFLAGS) kcmp_test.c -o kcmp_test else echo "Not an x86 target, can't build kcmp selftest" diff --git a/tools/testing/selftests/memfd/.gitignore b/tools/testing/selftests/memfd/.gitignore new file mode 100644 index 000000000000..afe87c40ac80 --- /dev/null +++ b/tools/testing/selftests/memfd/.gitignore @@ -0,0 +1,4 @@ +fuse_mnt +fuse_test +memfd_test +memfd-test-file diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile new file mode 100644 index 000000000000..b80cd10d53ba --- /dev/null +++ b/tools/testing/selftests/memfd/Makefile @@ -0,0 +1,20 @@ +CFLAGS += -D_FILE_OFFSET_BITS=64 +CFLAGS += -I../../../../include/uapi/ +CFLAGS += -I../../../../include/ + +all: + gcc $(CFLAGS) memfd_test.c -o memfd_test + +run_tests: all + gcc $(CFLAGS) memfd_test.c -o memfd_test + @./memfd_test || echo "memfd_test: [FAIL]" + +build_fuse: + gcc $(CFLAGS) fuse_mnt.c `pkg-config fuse --cflags --libs` -o fuse_mnt + gcc $(CFLAGS) fuse_test.c -o fuse_test + +run_fuse: build_fuse + @./run_fuse_test.sh || echo "fuse_test: [FAIL]" + +clean: + $(RM) memfd_test fuse_test diff --git a/tools/testing/selftests/memfd/fuse_mnt.c b/tools/testing/selftests/memfd/fuse_mnt.c new file mode 100644 index 000000000000..feacf1280fcd --- /dev/null +++ b/tools/testing/selftests/memfd/fuse_mnt.c @@ -0,0 +1,110 @@ +/* + * memfd test file-system + * This file uses FUSE to create a dummy file-system with only one file /memfd. + * This file is read-only and takes 1s per read. + * + * This file-system is used by the memfd test-cases to force the kernel to pin + * pages during reads(). Due to the 1s delay of this file-system, this is a + * nice way to test race-conditions against get_user_pages() in the kernel. + * + * We use direct_io==1 to force the kernel to use direct-IO for this + * file-system. + */ + +#define FUSE_USE_VERSION 26 + +#include <fuse.h> +#include <stdio.h> +#include <string.h> +#include <errno.h> +#include <fcntl.h> +#include <unistd.h> + +static const char memfd_content[] = "memfd-example-content"; +static const char memfd_path[] = "/memfd"; + +static int memfd_getattr(const char *path, struct stat *st) +{ + memset(st, 0, sizeof(*st)); + + if (!strcmp(path, "/")) { + st->st_mode = S_IFDIR | 0755; + st->st_nlink = 2; + } else if (!strcmp(path, memfd_path)) { + st->st_mode = S_IFREG | 0444; + st->st_nlink = 1; + st->st_size = strlen(memfd_content); + } else { + return -ENOENT; + } + + return 0; +} + +static int memfd_readdir(const char *path, + void *buf, + fuse_fill_dir_t filler, + off_t offset, + struct fuse_file_info *fi) +{ + if (strcmp(path, "/")) + return -ENOENT; + + filler(buf, ".", NULL, 0); + filler(buf, "..", NULL, 0); + filler(buf, memfd_path + 1, NULL, 0); + + return 0; +} + +static int memfd_open(const char *path, struct fuse_file_info *fi) +{ + if (strcmp(path, memfd_path)) + return -ENOENT; + + if ((fi->flags & 3) != O_RDONLY) + return -EACCES; + + /* force direct-IO */ + fi->direct_io = 1; + + return 0; +} + +static int memfd_read(const char *path, + char *buf, + size_t size, + off_t offset, + struct fuse_file_info *fi) +{ + size_t len; + + if (strcmp(path, memfd_path) != 0) + return -ENOENT; + + sleep(1); + + len = strlen(memfd_content); + if (offset < len) { + if (offset + size > len) + size = len - offset; + + memcpy(buf, memfd_content + offset, size); + } else { + size = 0; + } + + return size; +} + +static struct fuse_operations memfd_ops = { + .getattr = memfd_getattr, + .readdir = memfd_readdir, + .open = memfd_open, + .read = memfd_read, +}; + +int main(int argc, char *argv[]) +{ + return fuse_main(argc, argv, &memfd_ops, NULL); +} diff --git a/tools/testing/selftests/memfd/fuse_test.c b/tools/testing/selftests/memfd/fuse_test.c new file mode 100644 index 000000000000..67908b18f035 --- /dev/null +++ b/tools/testing/selftests/memfd/fuse_test.c @@ -0,0 +1,311 @@ +/* + * memfd GUP test-case + * This tests memfd interactions with get_user_pages(). We require the + * fuse_mnt.c program to provide a fake direct-IO FUSE mount-point for us. This + * file-system delays _all_ reads by 1s and forces direct-IO. This means, any + * read() on files in that file-system will pin the receive-buffer pages for at + * least 1s via get_user_pages(). + * + * We use this trick to race ADD_SEALS against a write on a memfd object. The + * ADD_SEALS must fail if the memfd pages are still pinned. Note that we use + * the read() syscall with our memory-mapped memfd object as receive buffer to + * force the kernel to write into our memfd object. + */ + +#define _GNU_SOURCE +#define __EXPORTED_HEADERS__ + +#include <errno.h> +#include <inttypes.h> +#include <limits.h> +#include <linux/falloc.h> +#include <linux/fcntl.h> +#include <linux/memfd.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <signal.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/stat.h> +#include <sys/syscall.h> +#include <sys/wait.h> +#include <unistd.h> + +#define MFD_DEF_SIZE 8192 +#define STACK_SIZE 65535 + +static int sys_memfd_create(const char *name, + unsigned int flags) +{ + return syscall(__NR_memfd_create, name, flags); +} + +static int mfd_assert_new(const char *name, loff_t sz, unsigned int flags) +{ + int r, fd; + + fd = sys_memfd_create(name, flags); + if (fd < 0) { + printf("memfd_create(\"%s\", %u) failed: %m\n", + name, flags); + abort(); + } + + r = ftruncate(fd, sz); + if (r < 0) { + printf("ftruncate(%llu) failed: %m\n", (unsigned long long)sz); + abort(); + } + + return fd; +} + +static __u64 mfd_assert_get_seals(int fd) +{ + long r; + + r = fcntl(fd, F_GET_SEALS); + if (r < 0) { + printf("GET_SEALS(%d) failed: %m\n", fd); + abort(); + } + + return r; +} + +static void mfd_assert_has_seals(int fd, __u64 seals) +{ + __u64 s; + + s = mfd_assert_get_seals(fd); + if (s != seals) { + printf("%llu != %llu = GET_SEALS(%d)\n", + (unsigned long long)seals, (unsigned long long)s, fd); + abort(); + } +} + +static void mfd_assert_add_seals(int fd, __u64 seals) +{ + long r; + __u64 s; + + s = mfd_assert_get_seals(fd); + r = fcntl(fd, F_ADD_SEALS, seals); + if (r < 0) { + printf("ADD_SEALS(%d, %llu -> %llu) failed: %m\n", + fd, (unsigned long long)s, (unsigned long long)seals); + abort(); + } +} + +static int mfd_busy_add_seals(int fd, __u64 seals) +{ + long r; + __u64 s; + + r = fcntl(fd, F_GET_SEALS); + if (r < 0) + s = 0; + else + s = r; + + r = fcntl(fd, F_ADD_SEALS, seals); + if (r < 0 && errno != EBUSY) { + printf("ADD_SEALS(%d, %llu -> %llu) didn't fail as expected with EBUSY: %m\n", + fd, (unsigned long long)s, (unsigned long long)seals); + abort(); + } + + return r; +} + +static void *mfd_assert_mmap_shared(int fd) +{ + void *p; + + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_READ | PROT_WRITE, + MAP_SHARED, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + + return p; +} + +static void *mfd_assert_mmap_private(int fd) +{ + void *p; + + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_READ | PROT_WRITE, + MAP_PRIVATE, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + + return p; +} + +static int global_mfd = -1; +static void *global_p = NULL; + +static int sealing_thread_fn(void *arg) +{ + int sig, r; + + /* + * This thread first waits 200ms so any pending operation in the parent + * is correctly started. After that, it tries to seal @global_mfd as + * SEAL_WRITE. This _must_ fail as the parent thread has a read() into + * that memory mapped object still ongoing. + * We then wait one more second and try sealing again. This time it + * must succeed as there shouldn't be anyone else pinning the pages. + */ + + /* wait 200ms for FUSE-request to be active */ + usleep(200000); + + /* unmount mapping before sealing to avoid i_mmap_writable failures */ + munmap(global_p, MFD_DEF_SIZE); + + /* Try sealing the global file; expect EBUSY or success. Current + * kernels will never succeed, but in the future, kernels might + * implement page-replacements or other fancy ways to avoid racing + * writes. */ + r = mfd_busy_add_seals(global_mfd, F_SEAL_WRITE); + if (r >= 0) { + printf("HURRAY! This kernel fixed GUP races!\n"); + } else { + /* wait 1s more so the FUSE-request is done */ + sleep(1); + + /* try sealing the global file again */ + mfd_assert_add_seals(global_mfd, F_SEAL_WRITE); + } + + return 0; +} + +static pid_t spawn_sealing_thread(void) +{ + uint8_t *stack; + pid_t pid; + + stack = malloc(STACK_SIZE); + if (!stack) { + printf("malloc(STACK_SIZE) failed: %m\n"); + abort(); + } + + pid = clone(sealing_thread_fn, + stack + STACK_SIZE, + SIGCHLD | CLONE_FILES | CLONE_FS | CLONE_VM, + NULL); + if (pid < 0) { + printf("clone() failed: %m\n"); + abort(); + } + + return pid; +} + +static void join_sealing_thread(pid_t pid) +{ + waitpid(pid, NULL, 0); +} + +int main(int argc, char **argv) +{ + static const char zero[MFD_DEF_SIZE]; + int fd, mfd, r; + void *p; + int was_sealed; + pid_t pid; + + if (argc < 2) { + printf("error: please pass path to file in fuse_mnt mount-point\n"); + abort(); + } + + /* open FUSE memfd file for GUP testing */ + printf("opening: %s\n", argv[1]); + fd = open(argv[1], O_RDONLY | O_CLOEXEC); + if (fd < 0) { + printf("cannot open(\"%s\"): %m\n", argv[1]); + abort(); + } + + /* create new memfd-object */ + mfd = mfd_assert_new("kern_memfd_fuse", + MFD_DEF_SIZE, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + + /* mmap memfd-object for writing */ + p = mfd_assert_mmap_shared(mfd); + + /* pass mfd+mapping to a separate sealing-thread which tries to seal + * the memfd objects with SEAL_WRITE while we write into it */ + global_mfd = mfd; + global_p = p; + pid = spawn_sealing_thread(); + + /* Use read() on the FUSE file to read into our memory-mapped memfd + * object. This races the other thread which tries to seal the + * memfd-object. + * If @fd is on the memfd-fake-FUSE-FS, the read() is delayed by 1s. + * This guarantees that the receive-buffer is pinned for 1s until the + * data is written into it. The racing ADD_SEALS should thus fail as + * the pages are still pinned. */ + r = read(fd, p, MFD_DEF_SIZE); + if (r < 0) { + printf("read() failed: %m\n"); + abort(); + } else if (!r) { + printf("unexpected EOF on read()\n"); + abort(); + } + + was_sealed = mfd_assert_get_seals(mfd) & F_SEAL_WRITE; + + /* Wait for sealing-thread to finish and verify that it + * successfully sealed the file after the second try. */ + join_sealing_thread(pid); + mfd_assert_has_seals(mfd, F_SEAL_WRITE); + + /* *IF* the memfd-object was sealed at the time our read() returned, + * then the kernel did a page-replacement or canceled the read() (or + * whatever magic it did..). In that case, the memfd object is still + * all zero. + * In case the memfd-object was *not* sealed, the read() was successfull + * and the memfd object must *not* be all zero. + * Note that in real scenarios, there might be a mixture of both, but + * in this test-cases, we have explicit 200ms delays which should be + * enough to avoid any in-flight writes. */ + + p = mfd_assert_mmap_private(mfd); + if (was_sealed && memcmp(p, zero, MFD_DEF_SIZE)) { + printf("memfd sealed during read() but data not discarded\n"); + abort(); + } else if (!was_sealed && !memcmp(p, zero, MFD_DEF_SIZE)) { + printf("memfd sealed after read() but data discarded\n"); + abort(); + } + + close(mfd); + close(fd); + + printf("fuse: DONE\n"); + + return 0; +} diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c new file mode 100644 index 000000000000..0b9eafb7ab7b --- /dev/null +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -0,0 +1,911 @@ +#define _GNU_SOURCE +#define __EXPORTED_HEADERS__ + +#include <errno.h> +#include <inttypes.h> +#include <limits.h> +#include <linux/falloc.h> +#include <linux/fcntl.h> +#include <linux/memfd.h> +#include <sched.h> +#include <stdio.h> +#include <stdlib.h> +#include <signal.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/stat.h> +#include <sys/syscall.h> +#include <unistd.h> + +#define MFD_DEF_SIZE 8192 +#define STACK_SIZE 65535 + +static int sys_memfd_create(const char *name, + unsigned int flags) +{ + return syscall(__NR_memfd_create, name, flags); +} + +static int mfd_assert_new(const char *name, loff_t sz, unsigned int flags) +{ + int r, fd; + + fd = sys_memfd_create(name, flags); + if (fd < 0) { + printf("memfd_create(\"%s\", %u) failed: %m\n", + name, flags); + abort(); + } + + r = ftruncate(fd, sz); + if (r < 0) { + printf("ftruncate(%llu) failed: %m\n", (unsigned long long)sz); + abort(); + } + + return fd; +} + +static void mfd_fail_new(const char *name, unsigned int flags) +{ + int r; + + r = sys_memfd_create(name, flags); + if (r >= 0) { + printf("memfd_create(\"%s\", %u) succeeded, but failure expected\n", + name, flags); + close(r); + abort(); + } +} + +static unsigned int mfd_assert_get_seals(int fd) +{ + int r; + + r = fcntl(fd, F_GET_SEALS); + if (r < 0) { + printf("GET_SEALS(%d) failed: %m\n", fd); + abort(); + } + + return (unsigned int)r; +} + +static void mfd_assert_has_seals(int fd, unsigned int seals) +{ + unsigned int s; + + s = mfd_assert_get_seals(fd); + if (s != seals) { + printf("%u != %u = GET_SEALS(%d)\n", seals, s, fd); + abort(); + } +} + +static void mfd_assert_add_seals(int fd, unsigned int seals) +{ + int r; + unsigned int s; + + s = mfd_assert_get_seals(fd); + r = fcntl(fd, F_ADD_SEALS, seals); + if (r < 0) { + printf("ADD_SEALS(%d, %u -> %u) failed: %m\n", fd, s, seals); + abort(); + } +} + +static void mfd_fail_add_seals(int fd, unsigned int seals) +{ + int r; + unsigned int s; + + r = fcntl(fd, F_GET_SEALS); + if (r < 0) + s = 0; + else + s = (unsigned int)r; + + r = fcntl(fd, F_ADD_SEALS, seals); + if (r >= 0) { + printf("ADD_SEALS(%d, %u -> %u) didn't fail as expected\n", + fd, s, seals); + abort(); + } +} + +static void mfd_assert_size(int fd, size_t size) +{ + struct stat st; + int r; + + r = fstat(fd, &st); + if (r < 0) { + printf("fstat(%d) failed: %m\n", fd); + abort(); + } else if (st.st_size != size) { + printf("wrong file size %lld, but expected %lld\n", + (long long)st.st_size, (long long)size); + abort(); + } +} + +static int mfd_assert_dup(int fd) +{ + int r; + + r = dup(fd); + if (r < 0) { + printf("dup(%d) failed: %m\n", fd); + abort(); + } + + return r; +} + +static void *mfd_assert_mmap_shared(int fd) +{ + void *p; + + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_READ | PROT_WRITE, + MAP_SHARED, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + + return p; +} + +static void *mfd_assert_mmap_private(int fd) +{ + void *p; + + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_READ, + MAP_PRIVATE, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + + return p; +} + +static int mfd_assert_open(int fd, int flags, mode_t mode) +{ + char buf[512]; + int r; + + sprintf(buf, "/proc/self/fd/%d", fd); + r = open(buf, flags, mode); + if (r < 0) { + printf("open(%s) failed: %m\n", buf); + abort(); + } + + return r; +} + +static void mfd_fail_open(int fd, int flags, mode_t mode) +{ + char buf[512]; + int r; + + sprintf(buf, "/proc/self/fd/%d", fd); + r = open(buf, flags, mode); + if (r >= 0) { + printf("open(%s) didn't fail as expected\n", buf); + abort(); + } +} + +static void mfd_assert_read(int fd) +{ + char buf[16]; + void *p; + ssize_t l; + + l = read(fd, buf, sizeof(buf)); + if (l != sizeof(buf)) { + printf("read() failed: %m\n"); + abort(); + } + + /* verify PROT_READ *is* allowed */ + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_READ, + MAP_PRIVATE, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + munmap(p, MFD_DEF_SIZE); + + /* verify MAP_PRIVATE is *always* allowed (even writable) */ + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_READ | PROT_WRITE, + MAP_PRIVATE, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + munmap(p, MFD_DEF_SIZE); +} + +static void mfd_assert_write(int fd) +{ + ssize_t l; + void *p; + int r; + + /* verify write() succeeds */ + l = write(fd, "\0\0\0\0", 4); + if (l != 4) { + printf("write() failed: %m\n"); + abort(); + } + + /* verify PROT_READ | PROT_WRITE is allowed */ + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_READ | PROT_WRITE, + MAP_SHARED, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + *(char *)p = 0; + munmap(p, MFD_DEF_SIZE); + + /* verify PROT_WRITE is allowed */ + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_WRITE, + MAP_SHARED, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + *(char *)p = 0; + munmap(p, MFD_DEF_SIZE); + + /* verify PROT_READ with MAP_SHARED is allowed and a following + * mprotect(PROT_WRITE) allows writing */ + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_READ, + MAP_SHARED, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + + r = mprotect(p, MFD_DEF_SIZE, PROT_READ | PROT_WRITE); + if (r < 0) { + printf("mprotect() failed: %m\n"); + abort(); + } + + *(char *)p = 0; + munmap(p, MFD_DEF_SIZE); + + /* verify PUNCH_HOLE works */ + r = fallocate(fd, + FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, + 0, + MFD_DEF_SIZE); + if (r < 0) { + printf("fallocate(PUNCH_HOLE) failed: %m\n"); + abort(); + } +} + +static void mfd_fail_write(int fd) +{ + ssize_t l; + void *p; + int r; + + /* verify write() fails */ + l = write(fd, "data", 4); + if (l != -EPERM) { + printf("expected EPERM on write(), but got %d: %m\n", (int)l); + abort(); + } + + /* verify PROT_READ | PROT_WRITE is not allowed */ + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_READ | PROT_WRITE, + MAP_SHARED, + fd, + 0); + if (p != MAP_FAILED) { + printf("mmap() didn't fail as expected\n"); + abort(); + } + + /* verify PROT_WRITE is not allowed */ + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_WRITE, + MAP_SHARED, + fd, + 0); + if (p != MAP_FAILED) { + printf("mmap() didn't fail as expected\n"); + abort(); + } + + /* Verify PROT_READ with MAP_SHARED with a following mprotect is not + * allowed. Note that for r/w the kernel already prevents the mmap. */ + p = mmap(NULL, + MFD_DEF_SIZE, + PROT_READ, + MAP_SHARED, + fd, + 0); + if (p != MAP_FAILED) { + r = mprotect(p, MFD_DEF_SIZE, PROT_READ | PROT_WRITE); + if (r >= 0) { + printf("mmap()+mprotect() didn't fail as expected\n"); + abort(); + } + } + + /* verify PUNCH_HOLE fails */ + r = fallocate(fd, + FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, + 0, + MFD_DEF_SIZE); + if (r >= 0) { + printf("fallocate(PUNCH_HOLE) didn't fail as expected\n"); + abort(); + } +} + +static void mfd_assert_shrink(int fd) +{ + int r, fd2; + + r = ftruncate(fd, MFD_DEF_SIZE / 2); + if (r < 0) { + printf("ftruncate(SHRINK) failed: %m\n"); + abort(); + } + + mfd_assert_size(fd, MFD_DEF_SIZE / 2); + + fd2 = mfd_assert_open(fd, + O_RDWR | O_CREAT | O_TRUNC, + S_IRUSR | S_IWUSR); + close(fd2); + + mfd_assert_size(fd, 0); +} + +static void mfd_fail_shrink(int fd) +{ + int r; + + r = ftruncate(fd, MFD_DEF_SIZE / 2); + if (r >= 0) { + printf("ftruncate(SHRINK) didn't fail as expected\n"); + abort(); + } + + mfd_fail_open(fd, + O_RDWR | O_CREAT | O_TRUNC, + S_IRUSR | S_IWUSR); +} + +static void mfd_assert_grow(int fd) +{ + int r; + + r = ftruncate(fd, MFD_DEF_SIZE * 2); + if (r < 0) { + printf("ftruncate(GROW) failed: %m\n"); + abort(); + } + + mfd_assert_size(fd, MFD_DEF_SIZE * 2); + + r = fallocate(fd, + 0, + 0, + MFD_DEF_SIZE * 4); + if (r < 0) { + printf("fallocate(ALLOC) failed: %m\n"); + abort(); + } + + mfd_assert_size(fd, MFD_DEF_SIZE * 4); +} + +static void mfd_fail_grow(int fd) +{ + int r; + + r = ftruncate(fd, MFD_DEF_SIZE * 2); + if (r >= 0) { + printf("ftruncate(GROW) didn't fail as expected\n"); + abort(); + } + + r = fallocate(fd, + 0, + 0, + MFD_DEF_SIZE * 4); + if (r >= 0) { + printf("fallocate(ALLOC) didn't fail as expected\n"); + abort(); + } +} + +static void mfd_assert_grow_write(int fd) +{ + static char buf[MFD_DEF_SIZE * 8]; + ssize_t l; + + l = pwrite(fd, buf, sizeof(buf), 0); + if (l != sizeof(buf)) { + printf("pwrite() failed: %m\n"); + abort(); + } + + mfd_assert_size(fd, MFD_DEF_SIZE * 8); +} + +static void mfd_fail_grow_write(int fd) +{ + static char buf[MFD_DEF_SIZE * 8]; + ssize_t l; + + l = pwrite(fd, buf, sizeof(buf), 0); + if (l == sizeof(buf)) { + printf("pwrite() didn't fail as expected\n"); + abort(); + } +} + +static int idle_thread_fn(void *arg) +{ + sigset_t set; + int sig; + + /* dummy waiter; SIGTERM terminates us anyway */ + sigemptyset(&set); + sigaddset(&set, SIGTERM); + sigwait(&set, &sig); + + return 0; +} + +static pid_t spawn_idle_thread(unsigned int flags) +{ + uint8_t *stack; + pid_t pid; + + stack = malloc(STACK_SIZE); + if (!stack) { + printf("malloc(STACK_SIZE) failed: %m\n"); + abort(); + } + + pid = clone(idle_thread_fn, + stack + STACK_SIZE, + SIGCHLD | flags, + NULL); + if (pid < 0) { + printf("clone() failed: %m\n"); + abort(); + } + + return pid; +} + +static void join_idle_thread(pid_t pid) +{ + kill(pid, SIGTERM); + waitpid(pid, NULL, 0); +} + +/* + * Test memfd_create() syscall + * Verify syscall-argument validation, including name checks, flag validation + * and more. + */ +static void test_create(void) +{ + char buf[2048]; + int fd; + + /* test NULL name */ + mfd_fail_new(NULL, 0); + + /* test over-long name (not zero-terminated) */ + memset(buf, 0xff, sizeof(buf)); + mfd_fail_new(buf, 0); + + /* test over-long zero-terminated name */ + memset(buf, 0xff, sizeof(buf)); + buf[sizeof(buf) - 1] = 0; + mfd_fail_new(buf, 0); + + /* verify "" is a valid name */ + fd = mfd_assert_new("", 0, 0); + close(fd); + + /* verify invalid O_* open flags */ + mfd_fail_new("", 0x0100); + mfd_fail_new("", ~MFD_CLOEXEC); + mfd_fail_new("", ~MFD_ALLOW_SEALING); + mfd_fail_new("", ~0); + mfd_fail_new("", 0x80000000U); + + /* verify MFD_CLOEXEC is allowed */ + fd = mfd_assert_new("", 0, MFD_CLOEXEC); + close(fd); + + /* verify MFD_ALLOW_SEALING is allowed */ + fd = mfd_assert_new("", 0, MFD_ALLOW_SEALING); + close(fd); + + /* verify MFD_ALLOW_SEALING | MFD_CLOEXEC is allowed */ + fd = mfd_assert_new("", 0, MFD_ALLOW_SEALING | MFD_CLOEXEC); + close(fd); +} + +/* + * Test basic sealing + * A very basic sealing test to see whether setting/retrieving seals works. + */ +static void test_basic(void) +{ + int fd; + + fd = mfd_assert_new("kern_memfd_basic", + MFD_DEF_SIZE, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + + /* add basic seals */ + mfd_assert_has_seals(fd, 0); + mfd_assert_add_seals(fd, F_SEAL_SHRINK | + F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_SHRINK | + F_SEAL_WRITE); + + /* add them again */ + mfd_assert_add_seals(fd, F_SEAL_SHRINK | + F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_SHRINK | + F_SEAL_WRITE); + + /* add more seals and seal against sealing */ + mfd_assert_add_seals(fd, F_SEAL_GROW | F_SEAL_SEAL); + mfd_assert_has_seals(fd, F_SEAL_SHRINK | + F_SEAL_GROW | + F_SEAL_WRITE | + F_SEAL_SEAL); + + /* verify that sealing no longer works */ + mfd_fail_add_seals(fd, F_SEAL_GROW); + mfd_fail_add_seals(fd, 0); + + close(fd); + + /* verify sealing does not work without MFD_ALLOW_SEALING */ + fd = mfd_assert_new("kern_memfd_basic", + MFD_DEF_SIZE, + MFD_CLOEXEC); + mfd_assert_has_seals(fd, F_SEAL_SEAL); + mfd_fail_add_seals(fd, F_SEAL_SHRINK | + F_SEAL_GROW | + F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_SEAL); + close(fd); +} + +/* + * Test SEAL_WRITE + * Test whether SEAL_WRITE actually prevents modifications. + */ +static void test_seal_write(void) +{ + int fd; + + fd = mfd_assert_new("kern_memfd_seal_write", + MFD_DEF_SIZE, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + mfd_assert_has_seals(fd, 0); + mfd_assert_add_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_WRITE); + + mfd_assert_read(fd); + mfd_fail_write(fd); + mfd_assert_shrink(fd); + mfd_assert_grow(fd); + mfd_fail_grow_write(fd); + + close(fd); +} + +/* + * Test SEAL_SHRINK + * Test whether SEAL_SHRINK actually prevents shrinking + */ +static void test_seal_shrink(void) +{ + int fd; + + fd = mfd_assert_new("kern_memfd_seal_shrink", + MFD_DEF_SIZE, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + mfd_assert_has_seals(fd, 0); + mfd_assert_add_seals(fd, F_SEAL_SHRINK); + mfd_assert_has_seals(fd, F_SEAL_SHRINK); + + mfd_assert_read(fd); + mfd_assert_write(fd); + mfd_fail_shrink(fd); + mfd_assert_grow(fd); + mfd_assert_grow_write(fd); + + close(fd); +} + +/* + * Test SEAL_GROW + * Test whether SEAL_GROW actually prevents growing + */ +static void test_seal_grow(void) +{ + int fd; + + fd = mfd_assert_new("kern_memfd_seal_grow", + MFD_DEF_SIZE, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + mfd_assert_has_seals(fd, 0); + mfd_assert_add_seals(fd, F_SEAL_GROW); + mfd_assert_has_seals(fd, F_SEAL_GROW); + + mfd_assert_read(fd); + mfd_assert_write(fd); + mfd_assert_shrink(fd); + mfd_fail_grow(fd); + mfd_fail_grow_write(fd); + + close(fd); +} + +/* + * Test SEAL_SHRINK | SEAL_GROW + * Test whether SEAL_SHRINK | SEAL_GROW actually prevents resizing + */ +static void test_seal_resize(void) +{ + int fd; + + fd = mfd_assert_new("kern_memfd_seal_resize", + MFD_DEF_SIZE, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + mfd_assert_has_seals(fd, 0); + mfd_assert_add_seals(fd, F_SEAL_SHRINK | F_SEAL_GROW); + mfd_assert_has_seals(fd, F_SEAL_SHRINK | F_SEAL_GROW); + + mfd_assert_read(fd); + mfd_assert_write(fd); + mfd_fail_shrink(fd); + mfd_fail_grow(fd); + mfd_fail_grow_write(fd); + + close(fd); +} + +/* + * Test sharing via dup() + * Test that seals are shared between dupped FDs and they're all equal. + */ +static void test_share_dup(void) +{ + int fd, fd2; + + fd = mfd_assert_new("kern_memfd_share_dup", + MFD_DEF_SIZE, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + mfd_assert_has_seals(fd, 0); + + fd2 = mfd_assert_dup(fd); + mfd_assert_has_seals(fd2, 0); + + mfd_assert_add_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd2, F_SEAL_WRITE); + + mfd_assert_add_seals(fd2, F_SEAL_SHRINK); + mfd_assert_has_seals(fd, F_SEAL_WRITE | F_SEAL_SHRINK); + mfd_assert_has_seals(fd2, F_SEAL_WRITE | F_SEAL_SHRINK); + + mfd_assert_add_seals(fd, F_SEAL_SEAL); + mfd_assert_has_seals(fd, F_SEAL_WRITE | F_SEAL_SHRINK | F_SEAL_SEAL); + mfd_assert_has_seals(fd2, F_SEAL_WRITE | F_SEAL_SHRINK | F_SEAL_SEAL); + + mfd_fail_add_seals(fd, F_SEAL_GROW); + mfd_fail_add_seals(fd2, F_SEAL_GROW); + mfd_fail_add_seals(fd, F_SEAL_SEAL); + mfd_fail_add_seals(fd2, F_SEAL_SEAL); + + close(fd2); + + mfd_fail_add_seals(fd, F_SEAL_GROW); + close(fd); +} + +/* + * Test sealing with active mmap()s + * Modifying seals is only allowed if no other mmap() refs exist. + */ +static void test_share_mmap(void) +{ + int fd; + void *p; + + fd = mfd_assert_new("kern_memfd_share_mmap", + MFD_DEF_SIZE, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + mfd_assert_has_seals(fd, 0); + + /* shared/writable ref prevents sealing WRITE, but allows others */ + p = mfd_assert_mmap_shared(fd); + mfd_fail_add_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd, 0); + mfd_assert_add_seals(fd, F_SEAL_SHRINK); + mfd_assert_has_seals(fd, F_SEAL_SHRINK); + munmap(p, MFD_DEF_SIZE); + + /* readable ref allows sealing */ + p = mfd_assert_mmap_private(fd); + mfd_assert_add_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_WRITE | F_SEAL_SHRINK); + munmap(p, MFD_DEF_SIZE); + + close(fd); +} + +/* + * Test sealing with open(/proc/self/fd/%d) + * Via /proc we can get access to a separate file-context for the same memfd. + * This is *not* like dup(), but like a real separate open(). Make sure the + * semantics are as expected and we correctly check for RDONLY / WRONLY / RDWR. + */ +static void test_share_open(void) +{ + int fd, fd2; + + fd = mfd_assert_new("kern_memfd_share_open", + MFD_DEF_SIZE, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + mfd_assert_has_seals(fd, 0); + + fd2 = mfd_assert_open(fd, O_RDWR, 0); + mfd_assert_add_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd2, F_SEAL_WRITE); + + mfd_assert_add_seals(fd2, F_SEAL_SHRINK); + mfd_assert_has_seals(fd, F_SEAL_WRITE | F_SEAL_SHRINK); + mfd_assert_has_seals(fd2, F_SEAL_WRITE | F_SEAL_SHRINK); + + close(fd); + fd = mfd_assert_open(fd2, O_RDONLY, 0); + + mfd_fail_add_seals(fd, F_SEAL_SEAL); + mfd_assert_has_seals(fd, F_SEAL_WRITE | F_SEAL_SHRINK); + mfd_assert_has_seals(fd2, F_SEAL_WRITE | F_SEAL_SHRINK); + + close(fd2); + fd2 = mfd_assert_open(fd, O_RDWR, 0); + + mfd_assert_add_seals(fd2, F_SEAL_SEAL); + mfd_assert_has_seals(fd, F_SEAL_WRITE | F_SEAL_SHRINK | F_SEAL_SEAL); + mfd_assert_has_seals(fd2, F_SEAL_WRITE | F_SEAL_SHRINK | F_SEAL_SEAL); + + close(fd2); + close(fd); +} + +/* + * Test sharing via fork() + * Test whether seal-modifications work as expected with forked childs. + */ +static void test_share_fork(void) +{ + int fd; + pid_t pid; + + fd = mfd_assert_new("kern_memfd_share_fork", + MFD_DEF_SIZE, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + mfd_assert_has_seals(fd, 0); + + pid = spawn_idle_thread(0); + mfd_assert_add_seals(fd, F_SEAL_SEAL); + mfd_assert_has_seals(fd, F_SEAL_SEAL); + + mfd_fail_add_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_SEAL); + + join_idle_thread(pid); + + mfd_fail_add_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_SEAL); + + close(fd); +} + +int main(int argc, char **argv) +{ + pid_t pid; + + printf("memfd: CREATE\n"); + test_create(); + printf("memfd: BASIC\n"); + test_basic(); + + printf("memfd: SEAL-WRITE\n"); + test_seal_write(); + printf("memfd: SEAL-SHRINK\n"); + test_seal_shrink(); + printf("memfd: SEAL-GROW\n"); + test_seal_grow(); + printf("memfd: SEAL-RESIZE\n"); + test_seal_resize(); + + printf("memfd: SHARE-DUP\n"); + test_share_dup(); + printf("memfd: SHARE-MMAP\n"); + test_share_mmap(); + printf("memfd: SHARE-OPEN\n"); + test_share_open(); + printf("memfd: SHARE-FORK\n"); + test_share_fork(); + + /* Run test-suite in a multi-threaded environment with a shared + * file-table. */ + pid = spawn_idle_thread(CLONE_FILES | CLONE_FS | CLONE_VM); + printf("memfd: SHARE-DUP (shared file-table)\n"); + test_share_dup(); + printf("memfd: SHARE-MMAP (shared file-table)\n"); + test_share_mmap(); + printf("memfd: SHARE-OPEN (shared file-table)\n"); + test_share_open(); + printf("memfd: SHARE-FORK (shared file-table)\n"); + test_share_fork(); + join_idle_thread(pid); + + printf("memfd: DONE\n"); + + return 0; +} diff --git a/tools/testing/selftests/memfd/run_fuse_test.sh b/tools/testing/selftests/memfd/run_fuse_test.sh new file mode 100644 index 000000000000..69b930e1e041 --- /dev/null +++ b/tools/testing/selftests/memfd/run_fuse_test.sh @@ -0,0 +1,14 @@ +#!/bin/sh + +if test -d "./mnt" ; then + fusermount -u ./mnt + rmdir ./mnt +fi + +set -e + +mkdir mnt +./fuse_mnt ./mnt +./fuse_test ./mnt/memfd +fusermount -u ./mnt +rmdir ./mnt diff --git a/tools/testing/selftests/mount/Makefile b/tools/testing/selftests/mount/Makefile new file mode 100644 index 000000000000..337d853c2b72 --- /dev/null +++ b/tools/testing/selftests/mount/Makefile @@ -0,0 +1,17 @@ +# Makefile for mount selftests. + +all: unprivileged-remount-test + +unprivileged-remount-test: unprivileged-remount-test.c + gcc -Wall -O2 unprivileged-remount-test.c -o unprivileged-remount-test + +# Allow specific tests to be selected. +test_unprivileged_remount: unprivileged-remount-test + @if [ -f /proc/self/uid_map ] ; then ./unprivileged-remount-test ; fi + +run_tests: all test_unprivileged_remount + +clean: + rm -f unprivileged-remount-test + +.PHONY: all test_unprivileged_remount diff --git a/tools/testing/selftests/mount/unprivileged-remount-test.c b/tools/testing/selftests/mount/unprivileged-remount-test.c new file mode 100644 index 000000000000..1b3ff2fda4d0 --- /dev/null +++ b/tools/testing/selftests/mount/unprivileged-remount-test.c @@ -0,0 +1,242 @@ +#define _GNU_SOURCE +#include <sched.h> +#include <stdio.h> +#include <errno.h> +#include <string.h> +#include <sys/types.h> +#include <sys/mount.h> +#include <sys/wait.h> +#include <stdlib.h> +#include <unistd.h> +#include <fcntl.h> +#include <grp.h> +#include <stdbool.h> +#include <stdarg.h> + +#ifndef CLONE_NEWNS +# define CLONE_NEWNS 0x00020000 +#endif +#ifndef CLONE_NEWUTS +# define CLONE_NEWUTS 0x04000000 +#endif +#ifndef CLONE_NEWIPC +# define CLONE_NEWIPC 0x08000000 +#endif +#ifndef CLONE_NEWNET +# define CLONE_NEWNET 0x40000000 +#endif +#ifndef CLONE_NEWUSER +# define CLONE_NEWUSER 0x10000000 +#endif +#ifndef CLONE_NEWPID +# define CLONE_NEWPID 0x20000000 +#endif + +#ifndef MS_RELATIME +#define MS_RELATIME (1 << 21) +#endif +#ifndef MS_STRICTATIME +#define MS_STRICTATIME (1 << 24) +#endif + +static void die(char *fmt, ...) +{ + va_list ap; + va_start(ap, fmt); + vfprintf(stderr, fmt, ap); + va_end(ap); + exit(EXIT_FAILURE); +} + +static void write_file(char *filename, char *fmt, ...) +{ + char buf[4096]; + int fd; + ssize_t written; + int buf_len; + va_list ap; + + va_start(ap, fmt); + buf_len = vsnprintf(buf, sizeof(buf), fmt, ap); + va_end(ap); + if (buf_len < 0) { + die("vsnprintf failed: %s\n", + strerror(errno)); + } + if (buf_len >= sizeof(buf)) { + die("vsnprintf output truncated\n"); + } + + fd = open(filename, O_WRONLY); + if (fd < 0) { + die("open of %s failed: %s\n", + filename, strerror(errno)); + } + written = write(fd, buf, buf_len); + if (written != buf_len) { + if (written >= 0) { + die("short write to %s\n", filename); + } else { + die("write to %s failed: %s\n", + filename, strerror(errno)); + } + } + if (close(fd) != 0) { + die("close of %s failed: %s\n", + filename, strerror(errno)); + } +} + +static void create_and_enter_userns(void) +{ + uid_t uid; + gid_t gid; + + uid = getuid(); + gid = getgid(); + + if (unshare(CLONE_NEWUSER) !=0) { + die("unshare(CLONE_NEWUSER) failed: %s\n", + strerror(errno)); + } + + write_file("/proc/self/uid_map", "0 %d 1", uid); + write_file("/proc/self/gid_map", "0 %d 1", gid); + + if (setgroups(0, NULL) != 0) { + die("setgroups failed: %s\n", + strerror(errno)); + } + if (setgid(0) != 0) { + die ("setgid(0) failed %s\n", + strerror(errno)); + } + if (setuid(0) != 0) { + die("setuid(0) failed %s\n", + strerror(errno)); + } +} + +static +bool test_unpriv_remount(int mount_flags, int remount_flags, int invalid_flags) +{ + pid_t child; + + child = fork(); + if (child == -1) { + die("fork failed: %s\n", + strerror(errno)); + } + if (child != 0) { /* parent */ + pid_t pid; + int status; + pid = waitpid(child, &status, 0); + if (pid == -1) { + die("waitpid failed: %s\n", + strerror(errno)); + } + if (pid != child) { + die("waited for %d got %d\n", + child, pid); + } + if (!WIFEXITED(status)) { + die("child did not terminate cleanly\n"); + } + return WEXITSTATUS(status) == EXIT_SUCCESS ? true : false; + } + + create_and_enter_userns(); + if (unshare(CLONE_NEWNS) != 0) { + die("unshare(CLONE_NEWNS) failed: %s\n", + strerror(errno)); + } + + if (mount("testing", "/tmp", "ramfs", mount_flags, NULL) != 0) { + die("mount of /tmp failed: %s\n", + strerror(errno)); + } + + create_and_enter_userns(); + + if (unshare(CLONE_NEWNS) != 0) { + die("unshare(CLONE_NEWNS) failed: %s\n", + strerror(errno)); + } + + if (mount("/tmp", "/tmp", "none", + MS_REMOUNT | MS_BIND | remount_flags, NULL) != 0) { + /* system("cat /proc/self/mounts"); */ + die("remount of /tmp failed: %s\n", + strerror(errno)); + } + + if (mount("/tmp", "/tmp", "none", + MS_REMOUNT | MS_BIND | invalid_flags, NULL) == 0) { + /* system("cat /proc/self/mounts"); */ + die("remount of /tmp with invalid flags " + "succeeded unexpectedly\n"); + } + exit(EXIT_SUCCESS); +} + +static bool test_unpriv_remount_simple(int mount_flags) +{ + return test_unpriv_remount(mount_flags, mount_flags, 0); +} + +static bool test_unpriv_remount_atime(int mount_flags, int invalid_flags) +{ + return test_unpriv_remount(mount_flags, mount_flags, invalid_flags); +} + +int main(int argc, char **argv) +{ + if (!test_unpriv_remount_simple(MS_RDONLY|MS_NODEV)) { + die("MS_RDONLY malfunctions\n"); + } + if (!test_unpriv_remount_simple(MS_NODEV)) { + die("MS_NODEV malfunctions\n"); + } + if (!test_unpriv_remount_simple(MS_NOSUID|MS_NODEV)) { + die("MS_NOSUID malfunctions\n"); + } + if (!test_unpriv_remount_simple(MS_NOEXEC|MS_NODEV)) { + die("MS_NOEXEC malfunctions\n"); + } + if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODEV, + MS_NOATIME|MS_NODEV)) + { + die("MS_RELATIME malfunctions\n"); + } + if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODEV, + MS_NOATIME|MS_NODEV)) + { + die("MS_STRICTATIME malfunctions\n"); + } + if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODEV, + MS_STRICTATIME|MS_NODEV)) + { + die("MS_RELATIME malfunctions\n"); + } + if (!test_unpriv_remount_atime(MS_RELATIME|MS_NODIRATIME|MS_NODEV, + MS_NOATIME|MS_NODEV)) + { + die("MS_RELATIME malfunctions\n"); + } + if (!test_unpriv_remount_atime(MS_STRICTATIME|MS_NODIRATIME|MS_NODEV, + MS_NOATIME|MS_NODEV)) + { + die("MS_RELATIME malfunctions\n"); + } + if (!test_unpriv_remount_atime(MS_NOATIME|MS_NODIRATIME|MS_NODEV, + MS_STRICTATIME|MS_NODEV)) + { + die("MS_RELATIME malfunctions\n"); + } + if (!test_unpriv_remount(MS_STRICTATIME|MS_NODEV, MS_NODEV, + MS_NOATIME|MS_NODEV)) + { + die("Default atime malfunctions\n"); + } + return EXIT_SUCCESS; +} diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c index 57b9c2b7c4ff..6f6733331d95 100644 --- a/tools/testing/selftests/net/psock_fanout.c +++ b/tools/testing/selftests/net/psock_fanout.c @@ -128,7 +128,7 @@ static int sock_fanout_read_ring(int fd, void *ring) struct tpacket2_hdr *header = ring; int count = 0; - while (header->tp_status & TP_STATUS_USER && count < RING_NUM_FRAMES) { + while (count < RING_NUM_FRAMES && header->tp_status & TP_STATUS_USER) { count++; header = ring + (count * getpagesize()); } diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile index 54833a791a44..f6ff90a76bd7 100644 --- a/tools/testing/selftests/powerpc/Makefile +++ b/tools/testing/selftests/powerpc/Makefile @@ -13,14 +13,14 @@ CFLAGS := -Wall -O2 -flto -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CUR export CC CFLAGS -TARGETS = pmu copyloops mm tm +TARGETS = pmu copyloops mm tm primitives endif -all: - @for TARGET in $(TARGETS); do \ - $(MAKE) -C $$TARGET all; \ - done; +all: $(TARGETS) + +$(TARGETS): + $(MAKE) -k -C $@ all run_tests: all @for TARGET in $(TARGETS); do \ @@ -36,4 +36,4 @@ clean: tags: find . -name '*.c' -o -name '*.h' | xargs ctags -.PHONY: all run_tests clean tags +.PHONY: all run_tests clean tags $(TARGETS) diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile index b9ff0db42c79..c9f4263906a5 100644 --- a/tools/testing/selftests/powerpc/pmu/Makefile +++ b/tools/testing/selftests/powerpc/pmu/Makefile @@ -1,10 +1,12 @@ noarg: $(MAKE) -C ../ -PROGS := count_instructions -EXTRA_SOURCES := ../harness.c event.c +PROGS := count_instructions l3_bank_test per_event_excludes +EXTRA_SOURCES := ../harness.c event.c lib.c -all: $(PROGS) sub_all +SUB_TARGETS = ebb + +all: $(PROGS) $(SUB_TARGETS) $(PROGS): $(EXTRA_SOURCES) @@ -20,13 +22,8 @@ run_tests: all sub_run_tests clean: sub_clean rm -f $(PROGS) loop.o - -SUB_TARGETS = ebb - -sub_all: - @for TARGET in $(SUB_TARGETS); do \ - $(MAKE) -C $$TARGET all; \ - done; +$(SUB_TARGETS): + $(MAKE) -k -C $@ all sub_run_tests: all @for TARGET in $(SUB_TARGETS); do \ @@ -38,4 +35,4 @@ sub_clean: $(MAKE) -C $$TARGET clean; \ done; -.PHONY: all run_tests clean sub_all sub_run_tests sub_clean +.PHONY: all run_tests clean sub_run_tests sub_clean $(SUB_TARGETS) diff --git a/tools/testing/selftests/powerpc/pmu/count_instructions.c b/tools/testing/selftests/powerpc/pmu/count_instructions.c index 312b4f0fd27c..4622117b24c0 100644 --- a/tools/testing/selftests/powerpc/pmu/count_instructions.c +++ b/tools/testing/selftests/powerpc/pmu/count_instructions.c @@ -12,6 +12,7 @@ #include "event.h" #include "utils.h" +#include "lib.h" extern void thirty_two_instruction_loop(u64 loops); @@ -90,7 +91,7 @@ static u64 determine_overhead(struct event *events) return overhead; } -static int count_instructions(void) +static int test_body(void) { struct event events[2]; u64 overhead; @@ -111,17 +112,23 @@ static int count_instructions(void) overhead = determine_overhead(events); printf("Overhead of null loop: %llu instructions\n", overhead); - /* Run for 1M instructions */ - FAIL_IF(do_count_loop(events, 0x100000, overhead, true)); + /* Run for 1Mi instructions */ + FAIL_IF(do_count_loop(events, 1000000, overhead, true)); + + /* Run for 10Mi instructions */ + FAIL_IF(do_count_loop(events, 10000000, overhead, true)); + + /* Run for 100Mi instructions */ + FAIL_IF(do_count_loop(events, 100000000, overhead, true)); - /* Run for 10M instructions */ - FAIL_IF(do_count_loop(events, 0xa00000, overhead, true)); + /* Run for 1Bi instructions */ + FAIL_IF(do_count_loop(events, 1000000000, overhead, true)); - /* Run for 100M instructions */ - FAIL_IF(do_count_loop(events, 0x6400000, overhead, true)); + /* Run for 16Bi instructions */ + FAIL_IF(do_count_loop(events, 16000000000, overhead, true)); - /* Run for 1G instructions */ - FAIL_IF(do_count_loop(events, 0x40000000, overhead, true)); + /* Run for 64Bi instructions */ + FAIL_IF(do_count_loop(events, 64000000000, overhead, true)); event_close(&events[0]); event_close(&events[1]); @@ -129,6 +136,11 @@ static int count_instructions(void) return 0; } +static int count_instructions(void) +{ + return eat_cpu(test_body); +} + int main(void) { return test_harness(count_instructions, "count_instructions"); diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile index edbba2affc2c..3dc4332698cb 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile +++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile @@ -13,11 +13,12 @@ PROGS := reg_access_test event_attributes_test cycles_test \ close_clears_pmcc_test instruction_count_test \ fork_cleanup_test ebb_on_child_test \ ebb_on_willing_child_test back_to_back_ebbs_test \ - lost_exception_test no_handler_test + lost_exception_test no_handler_test \ + cycles_with_mmcr2_test all: $(PROGS) -$(PROGS): ../../harness.c ../event.c ../lib.c ebb.c ebb_handler.S trace.c +$(PROGS): ../../harness.c ../event.c ../lib.c ebb.c ebb_handler.S trace.c busy_loop.S instruction_count_test: ../loop.S diff --git a/tools/testing/selftests/powerpc/pmu/ebb/busy_loop.S b/tools/testing/selftests/powerpc/pmu/ebb/busy_loop.S new file mode 100644 index 000000000000..c7e4093f1cd3 --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/ebb/busy_loop.S @@ -0,0 +1,271 @@ +/* + * Copyright 2014, Michael Ellerman, IBM Corp. + * Licensed under GPLv2. + */ + +#include <ppc-asm.h> + + .text + +FUNC_START(core_busy_loop) + stdu %r1, -168(%r1) + std r14, 160(%r1) + std r15, 152(%r1) + std r16, 144(%r1) + std r17, 136(%r1) + std r18, 128(%r1) + std r19, 120(%r1) + std r20, 112(%r1) + std r21, 104(%r1) + std r22, 96(%r1) + std r23, 88(%r1) + std r24, 80(%r1) + std r25, 72(%r1) + std r26, 64(%r1) + std r27, 56(%r1) + std r28, 48(%r1) + std r29, 40(%r1) + std r30, 32(%r1) + std r31, 24(%r1) + + li r3, 0x3030 + std r3, -96(%r1) + li r4, 0x4040 + std r4, -104(%r1) + li r5, 0x5050 + std r5, -112(%r1) + li r6, 0x6060 + std r6, -120(%r1) + li r7, 0x7070 + std r7, -128(%r1) + li r8, 0x0808 + std r8, -136(%r1) + li r9, 0x0909 + std r9, -144(%r1) + li r10, 0x1010 + std r10, -152(%r1) + li r11, 0x1111 + std r11, -160(%r1) + li r14, 0x1414 + std r14, -168(%r1) + li r15, 0x1515 + std r15, -176(%r1) + li r16, 0x1616 + std r16, -184(%r1) + li r17, 0x1717 + std r17, -192(%r1) + li r18, 0x1818 + std r18, -200(%r1) + li r19, 0x1919 + std r19, -208(%r1) + li r20, 0x2020 + std r20, -216(%r1) + li r21, 0x2121 + std r21, -224(%r1) + li r22, 0x2222 + std r22, -232(%r1) + li r23, 0x2323 + std r23, -240(%r1) + li r24, 0x2424 + std r24, -248(%r1) + li r25, 0x2525 + std r25, -256(%r1) + li r26, 0x2626 + std r26, -264(%r1) + li r27, 0x2727 + std r27, -272(%r1) + li r28, 0x2828 + std r28, -280(%r1) + li r29, 0x2929 + std r29, -288(%r1) + li r30, 0x3030 + li r31, 0x3131 + + li r3, 0 +0: addi r3, r3, 1 + cmpwi r3, 100 + blt 0b + + /* Return 1 (fail) unless we get through all the checks */ + li r3, 1 + + /* Check none of our registers have been corrupted */ + cmpwi r4, 0x4040 + bne 1f + cmpwi r5, 0x5050 + bne 1f + cmpwi r6, 0x6060 + bne 1f + cmpwi r7, 0x7070 + bne 1f + cmpwi r8, 0x0808 + bne 1f + cmpwi r9, 0x0909 + bne 1f + cmpwi r10, 0x1010 + bne 1f + cmpwi r11, 0x1111 + bne 1f + cmpwi r14, 0x1414 + bne 1f + cmpwi r15, 0x1515 + bne 1f + cmpwi r16, 0x1616 + bne 1f + cmpwi r17, 0x1717 + bne 1f + cmpwi r18, 0x1818 + bne 1f + cmpwi r19, 0x1919 + bne 1f + cmpwi r20, 0x2020 + bne 1f + cmpwi r21, 0x2121 + bne 1f + cmpwi r22, 0x2222 + bne 1f + cmpwi r23, 0x2323 + bne 1f + cmpwi r24, 0x2424 + bne 1f + cmpwi r25, 0x2525 + bne 1f + cmpwi r26, 0x2626 + bne 1f + cmpwi r27, 0x2727 + bne 1f + cmpwi r28, 0x2828 + bne 1f + cmpwi r29, 0x2929 + bne 1f + cmpwi r30, 0x3030 + bne 1f + cmpwi r31, 0x3131 + bne 1f + + /* Load junk into all our registers before we reload them from the stack. */ + li r3, 0xde + li r4, 0xad + li r5, 0xbe + li r6, 0xef + li r7, 0xde + li r8, 0xad + li r9, 0xbe + li r10, 0xef + li r11, 0xde + li r14, 0xad + li r15, 0xbe + li r16, 0xef + li r17, 0xde + li r18, 0xad + li r19, 0xbe + li r20, 0xef + li r21, 0xde + li r22, 0xad + li r23, 0xbe + li r24, 0xef + li r25, 0xde + li r26, 0xad + li r27, 0xbe + li r28, 0xef + li r29, 0xdd + + ld r3, -96(%r1) + cmpwi r3, 0x3030 + bne 1f + ld r4, -104(%r1) + cmpwi r4, 0x4040 + bne 1f + ld r5, -112(%r1) + cmpwi r5, 0x5050 + bne 1f + ld r6, -120(%r1) + cmpwi r6, 0x6060 + bne 1f + ld r7, -128(%r1) + cmpwi r7, 0x7070 + bne 1f + ld r8, -136(%r1) + cmpwi r8, 0x0808 + bne 1f + ld r9, -144(%r1) + cmpwi r9, 0x0909 + bne 1f + ld r10, -152(%r1) + cmpwi r10, 0x1010 + bne 1f + ld r11, -160(%r1) + cmpwi r11, 0x1111 + bne 1f + ld r14, -168(%r1) + cmpwi r14, 0x1414 + bne 1f + ld r15, -176(%r1) + cmpwi r15, 0x1515 + bne 1f + ld r16, -184(%r1) + cmpwi r16, 0x1616 + bne 1f + ld r17, -192(%r1) + cmpwi r17, 0x1717 + bne 1f + ld r18, -200(%r1) + cmpwi r18, 0x1818 + bne 1f + ld r19, -208(%r1) + cmpwi r19, 0x1919 + bne 1f + ld r20, -216(%r1) + cmpwi r20, 0x2020 + bne 1f + ld r21, -224(%r1) + cmpwi r21, 0x2121 + bne 1f + ld r22, -232(%r1) + cmpwi r22, 0x2222 + bne 1f + ld r23, -240(%r1) + cmpwi r23, 0x2323 + bne 1f + ld r24, -248(%r1) + cmpwi r24, 0x2424 + bne 1f + ld r25, -256(%r1) + cmpwi r25, 0x2525 + bne 1f + ld r26, -264(%r1) + cmpwi r26, 0x2626 + bne 1f + ld r27, -272(%r1) + cmpwi r27, 0x2727 + bne 1f + ld r28, -280(%r1) + cmpwi r28, 0x2828 + bne 1f + ld r29, -288(%r1) + cmpwi r29, 0x2929 + bne 1f + + /* Load 0 (success) to return */ + li r3, 0 + +1: ld r14, 160(%r1) + ld r15, 152(%r1) + ld r16, 144(%r1) + ld r17, 136(%r1) + ld r18, 128(%r1) + ld r19, 120(%r1) + ld r20, 112(%r1) + ld r21, 104(%r1) + ld r22, 96(%r1) + ld r23, 88(%r1) + ld r24, 80(%r1) + ld r25, 72(%r1) + ld r26, 64(%r1) + ld r27, 56(%r1) + ld r28, 48(%r1) + ld r29, 40(%r1) + ld r30, 32(%r1) + ld r31, 24(%r1) + addi %r1, %r1, 168 + blr diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c new file mode 100644 index 000000000000..d43029b0800c --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c @@ -0,0 +1,91 @@ +/* + * Copyright 2014, Michael Ellerman, IBM Corp. + * Licensed under GPLv2. + */ + +#include <stdio.h> +#include <stdlib.h> +#include <stdbool.h> + +#include "ebb.h" + + +/* + * Test of counting cycles while manipulating the user accessible bits in MMCR2. + */ + +/* We use two values because the first freezes PMC1 and so we would get no EBBs */ +#define MMCR2_EXPECTED_1 0x4020100804020000UL /* (FC1P|FC2P|FC3P|FC4P|FC5P|FC6P) */ +#define MMCR2_EXPECTED_2 0x0020100804020000UL /* ( FC2P|FC3P|FC4P|FC5P|FC6P) */ + + +int cycles_with_mmcr2(void) +{ + struct event event; + uint64_t val, expected[2], actual; + int i; + bool bad_mmcr2; + + event_init_named(&event, 0x1001e, "cycles"); + event_leader_ebb_init(&event); + + event.attr.exclude_kernel = 1; + event.attr.exclude_hv = 1; + event.attr.exclude_idle = 1; + + FAIL_IF(event_open(&event)); + + ebb_enable_pmc_counting(1); + setup_ebb_handler(standard_ebb_callee); + ebb_global_enable(); + + FAIL_IF(ebb_event_enable(&event)); + + mtspr(SPRN_PMC1, pmc_sample_period(sample_period)); + + /* XXX Set of MMCR2 must be after enable */ + expected[0] = MMCR2_EXPECTED_1; + expected[1] = MMCR2_EXPECTED_2; + i = 0; + bad_mmcr2 = false; + + /* Make sure we loop until we take at least one EBB */ + while ((ebb_state.stats.ebb_count < 20 && !bad_mmcr2) || + ebb_state.stats.ebb_count < 1) + { + mtspr(SPRN_MMCR2, expected[i % 2]); + + FAIL_IF(core_busy_loop()); + + val = mfspr(SPRN_MMCR2); + if (val != expected[i % 2]) { + bad_mmcr2 = true; + actual = val; + } + + i++; + } + + ebb_global_disable(); + ebb_freeze_pmcs(); + + count_pmc(1, sample_period); + + dump_ebb_state(); + + event_close(&event); + + FAIL_IF(ebb_state.stats.ebb_count == 0); + + if (bad_mmcr2) + printf("Bad MMCR2 value seen is 0x%lx\n", actual); + + FAIL_IF(bad_mmcr2); + + return 0; +} + +int main(void) +{ + return test_harness(cycles_with_mmcr2, "cycles_with_mmcr2"); +} diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c index 1b46be94b64c..d7a72ce696b5 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c +++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c @@ -224,6 +224,7 @@ void dump_ebb_hw_state(void) printf("HW state:\n" \ "MMCR0 0x%016x %s\n" \ + "MMCR2 0x%016lx\n" \ "EBBHR 0x%016lx\n" \ "BESCR 0x%016llx %s\n" \ "PMC1 0x%016lx\n" \ @@ -233,10 +234,11 @@ void dump_ebb_hw_state(void) "PMC5 0x%016lx\n" \ "PMC6 0x%016lx\n" \ "SIAR 0x%016lx\n", - mmcr0, decode_mmcr0(mmcr0), mfspr(SPRN_EBBHR), bescr, - decode_bescr(bescr), mfspr(SPRN_PMC1), mfspr(SPRN_PMC2), - mfspr(SPRN_PMC3), mfspr(SPRN_PMC4), mfspr(SPRN_PMC5), - mfspr(SPRN_PMC6), mfspr(SPRN_SIAR)); + mmcr0, decode_mmcr0(mmcr0), mfspr(SPRN_MMCR2), + mfspr(SPRN_EBBHR), bescr, decode_bescr(bescr), + mfspr(SPRN_PMC1), mfspr(SPRN_PMC2), mfspr(SPRN_PMC3), + mfspr(SPRN_PMC4), mfspr(SPRN_PMC5), mfspr(SPRN_PMC6), + mfspr(SPRN_SIAR)); } void dump_ebb_state(void) @@ -335,257 +337,6 @@ void event_leader_ebb_init(struct event *e) e->attr.pinned = 1; } -int core_busy_loop(void) -{ - int rc; - - asm volatile ( - "li 3, 0x3030\n" - "std 3, -96(1)\n" - "li 4, 0x4040\n" - "std 4, -104(1)\n" - "li 5, 0x5050\n" - "std 5, -112(1)\n" - "li 6, 0x6060\n" - "std 6, -120(1)\n" - "li 7, 0x7070\n" - "std 7, -128(1)\n" - "li 8, 0x0808\n" - "std 8, -136(1)\n" - "li 9, 0x0909\n" - "std 9, -144(1)\n" - "li 10, 0x1010\n" - "std 10, -152(1)\n" - "li 11, 0x1111\n" - "std 11, -160(1)\n" - "li 14, 0x1414\n" - "std 14, -168(1)\n" - "li 15, 0x1515\n" - "std 15, -176(1)\n" - "li 16, 0x1616\n" - "std 16, -184(1)\n" - "li 17, 0x1717\n" - "std 17, -192(1)\n" - "li 18, 0x1818\n" - "std 18, -200(1)\n" - "li 19, 0x1919\n" - "std 19, -208(1)\n" - "li 20, 0x2020\n" - "std 20, -216(1)\n" - "li 21, 0x2121\n" - "std 21, -224(1)\n" - "li 22, 0x2222\n" - "std 22, -232(1)\n" - "li 23, 0x2323\n" - "std 23, -240(1)\n" - "li 24, 0x2424\n" - "std 24, -248(1)\n" - "li 25, 0x2525\n" - "std 25, -256(1)\n" - "li 26, 0x2626\n" - "std 26, -264(1)\n" - "li 27, 0x2727\n" - "std 27, -272(1)\n" - "li 28, 0x2828\n" - "std 28, -280(1)\n" - "li 29, 0x2929\n" - "std 29, -288(1)\n" - "li 30, 0x3030\n" - "li 31, 0x3131\n" - - "li 3, 0\n" - "0: " - "addi 3, 3, 1\n" - "cmpwi 3, 100\n" - "blt 0b\n" - - /* Return 1 (fail) unless we get through all the checks */ - "li 0, 1\n" - - /* Check none of our registers have been corrupted */ - "cmpwi 4, 0x4040\n" - "bne 1f\n" - "cmpwi 5, 0x5050\n" - "bne 1f\n" - "cmpwi 6, 0x6060\n" - "bne 1f\n" - "cmpwi 7, 0x7070\n" - "bne 1f\n" - "cmpwi 8, 0x0808\n" - "bne 1f\n" - "cmpwi 9, 0x0909\n" - "bne 1f\n" - "cmpwi 10, 0x1010\n" - "bne 1f\n" - "cmpwi 11, 0x1111\n" - "bne 1f\n" - "cmpwi 14, 0x1414\n" - "bne 1f\n" - "cmpwi 15, 0x1515\n" - "bne 1f\n" - "cmpwi 16, 0x1616\n" - "bne 1f\n" - "cmpwi 17, 0x1717\n" - "bne 1f\n" - "cmpwi 18, 0x1818\n" - "bne 1f\n" - "cmpwi 19, 0x1919\n" - "bne 1f\n" - "cmpwi 20, 0x2020\n" - "bne 1f\n" - "cmpwi 21, 0x2121\n" - "bne 1f\n" - "cmpwi 22, 0x2222\n" - "bne 1f\n" - "cmpwi 23, 0x2323\n" - "bne 1f\n" - "cmpwi 24, 0x2424\n" - "bne 1f\n" - "cmpwi 25, 0x2525\n" - "bne 1f\n" - "cmpwi 26, 0x2626\n" - "bne 1f\n" - "cmpwi 27, 0x2727\n" - "bne 1f\n" - "cmpwi 28, 0x2828\n" - "bne 1f\n" - "cmpwi 29, 0x2929\n" - "bne 1f\n" - "cmpwi 30, 0x3030\n" - "bne 1f\n" - "cmpwi 31, 0x3131\n" - "bne 1f\n" - - /* Load junk into all our registers before we reload them from the stack. */ - "li 3, 0xde\n" - "li 4, 0xad\n" - "li 5, 0xbe\n" - "li 6, 0xef\n" - "li 7, 0xde\n" - "li 8, 0xad\n" - "li 9, 0xbe\n" - "li 10, 0xef\n" - "li 11, 0xde\n" - "li 14, 0xad\n" - "li 15, 0xbe\n" - "li 16, 0xef\n" - "li 17, 0xde\n" - "li 18, 0xad\n" - "li 19, 0xbe\n" - "li 20, 0xef\n" - "li 21, 0xde\n" - "li 22, 0xad\n" - "li 23, 0xbe\n" - "li 24, 0xef\n" - "li 25, 0xde\n" - "li 26, 0xad\n" - "li 27, 0xbe\n" - "li 28, 0xef\n" - "li 29, 0xdd\n" - - "ld 3, -96(1)\n" - "cmpwi 3, 0x3030\n" - "bne 1f\n" - "ld 4, -104(1)\n" - "cmpwi 4, 0x4040\n" - "bne 1f\n" - "ld 5, -112(1)\n" - "cmpwi 5, 0x5050\n" - "bne 1f\n" - "ld 6, -120(1)\n" - "cmpwi 6, 0x6060\n" - "bne 1f\n" - "ld 7, -128(1)\n" - "cmpwi 7, 0x7070\n" - "bne 1f\n" - "ld 8, -136(1)\n" - "cmpwi 8, 0x0808\n" - "bne 1f\n" - "ld 9, -144(1)\n" - "cmpwi 9, 0x0909\n" - "bne 1f\n" - "ld 10, -152(1)\n" - "cmpwi 10, 0x1010\n" - "bne 1f\n" - "ld 11, -160(1)\n" - "cmpwi 11, 0x1111\n" - "bne 1f\n" - "ld 14, -168(1)\n" - "cmpwi 14, 0x1414\n" - "bne 1f\n" - "ld 15, -176(1)\n" - "cmpwi 15, 0x1515\n" - "bne 1f\n" - "ld 16, -184(1)\n" - "cmpwi 16, 0x1616\n" - "bne 1f\n" - "ld 17, -192(1)\n" - "cmpwi 17, 0x1717\n" - "bne 1f\n" - "ld 18, -200(1)\n" - "cmpwi 18, 0x1818\n" - "bne 1f\n" - "ld 19, -208(1)\n" - "cmpwi 19, 0x1919\n" - "bne 1f\n" - "ld 20, -216(1)\n" - "cmpwi 20, 0x2020\n" - "bne 1f\n" - "ld 21, -224(1)\n" - "cmpwi 21, 0x2121\n" - "bne 1f\n" - "ld 22, -232(1)\n" - "cmpwi 22, 0x2222\n" - "bne 1f\n" - "ld 23, -240(1)\n" - "cmpwi 23, 0x2323\n" - "bne 1f\n" - "ld 24, -248(1)\n" - "cmpwi 24, 0x2424\n" - "bne 1f\n" - "ld 25, -256(1)\n" - "cmpwi 25, 0x2525\n" - "bne 1f\n" - "ld 26, -264(1)\n" - "cmpwi 26, 0x2626\n" - "bne 1f\n" - "ld 27, -272(1)\n" - "cmpwi 27, 0x2727\n" - "bne 1f\n" - "ld 28, -280(1)\n" - "cmpwi 28, 0x2828\n" - "bne 1f\n" - "ld 29, -288(1)\n" - "cmpwi 29, 0x2929\n" - "bne 1f\n" - - /* Load 0 (success) to return */ - "li 0, 0\n" - - "1: mr %0, 0\n" - - : "=r" (rc) - : /* no inputs */ - : "3", "4", "5", "6", "7", "8", "9", "10", "11", "14", - "15", "16", "17", "18", "19", "20", "21", "22", "23", - "24", "25", "26", "27", "28", "29", "30", "31", - "memory" - ); - - return rc; -} - -int core_busy_loop_with_freeze(void) -{ - int rc; - - mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) & ~MMCR0_FC); - rc = core_busy_loop(); - mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) | MMCR0_FC); - - return rc; -} - int ebb_child(union pipe read_pipe, union pipe write_pipe) { struct event event; diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb.h b/tools/testing/selftests/powerpc/pmu/ebb/ebb.h index e62bde05bf78..e44eee5d97ca 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/ebb.h +++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.h @@ -70,7 +70,6 @@ int ebb_check_mmcr0(void); extern u64 sample_period; int core_busy_loop(void); -int core_busy_loop_with_freeze(void); int ebb_child(union pipe read_pipe, union pipe write_pipe); int catch_sigill(void (*func)(void)); void write_pmc1(void); diff --git a/tools/testing/selftests/powerpc/pmu/l3_bank_test.c b/tools/testing/selftests/powerpc/pmu/l3_bank_test.c new file mode 100644 index 000000000000..77472f31441e --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/l3_bank_test.c @@ -0,0 +1,48 @@ +/* + * Copyright 2014, Michael Ellerman, IBM Corp. + * Licensed under GPLv2. + */ + +#include <stdio.h> +#include <stdlib.h> + +#include "event.h" +#include "utils.h" + +#define MALLOC_SIZE (0x10000 * 10) /* Ought to be enough .. */ + +/* + * Tests that the L3 bank handling is correct. We fixed it in commit e9aaac1. + */ +static int l3_bank_test(void) +{ + struct event event; + char *p; + int i; + + p = malloc(MALLOC_SIZE); + FAIL_IF(!p); + + event_init(&event, 0x84918F); + + FAIL_IF(event_open(&event)); + + for (i = 0; i < MALLOC_SIZE; i += 0x10000) + p[i] = i; + + event_read(&event); + event_report(&event); + + FAIL_IF(event.result.running == 0); + FAIL_IF(event.result.enabled == 0); + + event_close(&event); + free(p); + + return 0; +} + +int main(void) +{ + return test_harness(l3_bank_test, "l3_bank_test"); +} diff --git a/tools/testing/selftests/powerpc/pmu/lib.c b/tools/testing/selftests/powerpc/pmu/lib.c index 0f6a4731d546..9768dea37bf3 100644 --- a/tools/testing/selftests/powerpc/pmu/lib.c +++ b/tools/testing/selftests/powerpc/pmu/lib.c @@ -5,10 +5,15 @@ #define _GNU_SOURCE /* For CPU_ZERO etc. */ +#include <elf.h> #include <errno.h> +#include <fcntl.h> +#include <link.h> #include <sched.h> #include <setjmp.h> #include <stdlib.h> +#include <sys/stat.h> +#include <sys/types.h> #include <sys/wait.h> #include "utils.h" @@ -177,8 +182,8 @@ struct addr_range libc, vdso; int parse_proc_maps(void) { + unsigned long start, end; char execute, name[128]; - uint64_t start, end; FILE *f; int rc; @@ -250,3 +255,46 @@ out_close: out: return rc; } + +static char auxv[4096]; + +void *get_auxv_entry(int type) +{ + ElfW(auxv_t) *p; + void *result; + ssize_t num; + int fd; + + fd = open("/proc/self/auxv", O_RDONLY); + if (fd == -1) { + perror("open"); + return NULL; + } + + result = NULL; + + num = read(fd, auxv, sizeof(auxv)); + if (num < 0) { + perror("read"); + goto out; + } + + if (num > sizeof(auxv)) { + printf("Overflowed auxv buffer\n"); + goto out; + } + + p = (ElfW(auxv_t) *)auxv; + + while (p->a_type != AT_NULL) { + if (p->a_type == type) { + result = (void *)p->a_un.a_val; + break; + } + + p++; + } +out: + close(fd); + return result; +} diff --git a/tools/testing/selftests/powerpc/pmu/lib.h b/tools/testing/selftests/powerpc/pmu/lib.h index ca5d72ae3be6..0f0339c8a6f6 100644 --- a/tools/testing/selftests/powerpc/pmu/lib.h +++ b/tools/testing/selftests/powerpc/pmu/lib.h @@ -29,6 +29,7 @@ extern int notify_parent(union pipe write_pipe); extern int notify_parent_of_error(union pipe write_pipe); extern pid_t eat_cpu(int (test_function)(void)); extern bool require_paranoia_below(int level); +extern void *get_auxv_entry(int type); struct addr_range { uint64_t first, last; diff --git a/tools/testing/selftests/powerpc/pmu/per_event_excludes.c b/tools/testing/selftests/powerpc/pmu/per_event_excludes.c new file mode 100644 index 000000000000..fddbbc9cae2f --- /dev/null +++ b/tools/testing/selftests/powerpc/pmu/per_event_excludes.c @@ -0,0 +1,114 @@ +/* + * Copyright 2014, Michael Ellerman, IBM Corp. + * Licensed under GPLv2. + */ + +#define _GNU_SOURCE + +#include <elf.h> +#include <limits.h> +#include <stdio.h> +#include <stdbool.h> +#include <string.h> +#include <sys/prctl.h> + +#include "event.h" +#include "lib.h" +#include "utils.h" + +/* + * Test that per-event excludes work. + */ + +static int per_event_excludes(void) +{ + struct event *e, events[4]; + char *platform; + int i; + + platform = (char *)get_auxv_entry(AT_BASE_PLATFORM); + FAIL_IF(!platform); + SKIP_IF(strcmp(platform, "power8") != 0); + + /* + * We need to create the events disabled, otherwise the running/enabled + * counts don't match up. + */ + e = &events[0]; + event_init_opts(e, PERF_COUNT_HW_INSTRUCTIONS, + PERF_TYPE_HARDWARE, "instructions"); + e->attr.disabled = 1; + + e = &events[1]; + event_init_opts(e, PERF_COUNT_HW_INSTRUCTIONS, + PERF_TYPE_HARDWARE, "instructions(k)"); + e->attr.disabled = 1; + e->attr.exclude_user = 1; + e->attr.exclude_hv = 1; + + e = &events[2]; + event_init_opts(e, PERF_COUNT_HW_INSTRUCTIONS, + PERF_TYPE_HARDWARE, "instructions(h)"); + e->attr.disabled = 1; + e->attr.exclude_user = 1; + e->attr.exclude_kernel = 1; + + e = &events[3]; + event_init_opts(e, PERF_COUNT_HW_INSTRUCTIONS, + PERF_TYPE_HARDWARE, "instructions(u)"); + e->attr.disabled = 1; + e->attr.exclude_hv = 1; + e->attr.exclude_kernel = 1; + + FAIL_IF(event_open(&events[0])); + + /* + * The open here will fail if we don't have per event exclude support, + * because the second event has an incompatible set of exclude settings + * and we're asking for the events to be in a group. + */ + for (i = 1; i < 4; i++) + FAIL_IF(event_open_with_group(&events[i], events[0].fd)); + + /* + * Even though the above will fail without per-event excludes we keep + * testing in order to be thorough. + */ + prctl(PR_TASK_PERF_EVENTS_ENABLE); + + /* Spin for a while */ + for (i = 0; i < INT_MAX; i++) + asm volatile("" : : : "memory"); + + prctl(PR_TASK_PERF_EVENTS_DISABLE); + + for (i = 0; i < 4; i++) { + FAIL_IF(event_read(&events[i])); + event_report(&events[i]); + } + + /* + * We should see that all events have enabled == running. That + * shows that they were all on the PMU at once. + */ + for (i = 0; i < 4; i++) + FAIL_IF(events[i].result.running != events[i].result.enabled); + + /* + * We can also check that the result for instructions is >= all the + * other counts. That's because it is counting all instructions while + * the others are counting a subset. + */ + for (i = 1; i < 4; i++) + FAIL_IF(events[0].result.value < events[i].result.value); + + for (i = 0; i < 4; i++) + event_close(&events[i]); + + return 0; +} + +int main(void) +{ + return test_harness(per_event_excludes, "per_event_excludes"); +} diff --git a/tools/testing/selftests/powerpc/primitives/Makefile b/tools/testing/selftests/powerpc/primitives/Makefile new file mode 100644 index 000000000000..ea737ca01732 --- /dev/null +++ b/tools/testing/selftests/powerpc/primitives/Makefile @@ -0,0 +1,17 @@ +CFLAGS += -I$(CURDIR) + +PROGS := load_unaligned_zeropad + +all: $(PROGS) + +$(PROGS): ../harness.c + +run_tests: all + @-for PROG in $(PROGS); do \ + ./$$PROG; \ + done; + +clean: + rm -f $(PROGS) *.o + +.PHONY: all run_tests clean diff --git a/tools/testing/selftests/powerpc/primitives/asm/asm-compat.h b/tools/testing/selftests/powerpc/primitives/asm/asm-compat.h new file mode 120000 index 000000000000..b14255e15a25 --- /dev/null +++ b/tools/testing/selftests/powerpc/primitives/asm/asm-compat.h @@ -0,0 +1 @@ +../.././../../../../arch/powerpc/include/asm/asm-compat.h
\ No newline at end of file diff --git a/tools/testing/selftests/powerpc/primitives/asm/ppc-opcode.h b/tools/testing/selftests/powerpc/primitives/asm/ppc-opcode.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/testing/selftests/powerpc/primitives/asm/ppc-opcode.h diff --git a/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c b/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c new file mode 100644 index 000000000000..d1b647509596 --- /dev/null +++ b/tools/testing/selftests/powerpc/primitives/load_unaligned_zeropad.c @@ -0,0 +1,147 @@ +/* + * Userspace test harness for load_unaligned_zeropad. Creates two + * pages and uses mprotect to prevent access to the second page and + * a SEGV handler that walks the exception tables and runs the fixup + * routine. + * + * The results are compared against a normal load that is that is + * performed while access to the second page is enabled via mprotect. + * + * Copyright (C) 2014 Anton Blanchard <anton@au.ibm.com>, IBM + * + * 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. + */ + +#include <stdlib.h> +#include <string.h> +#include <stdio.h> +#include <stdbool.h> +#include <signal.h> +#include <unistd.h> +#include <sys/mman.h> + +#define FIXUP_SECTION ".ex_fixup" + +#include "word-at-a-time.h" + +#include "utils.h" + + +static int page_size; +static char *mem_region; + +static int protect_region(void) +{ + if (mprotect(mem_region + page_size, page_size, PROT_NONE)) { + perror("mprotect"); + return 1; + } + + return 0; +} + +static int unprotect_region(void) +{ + if (mprotect(mem_region + page_size, page_size, PROT_READ|PROT_WRITE)) { + perror("mprotect"); + return 1; + } + + return 0; +} + +extern char __start___ex_table[]; +extern char __stop___ex_table[]; + +#if defined(__powerpc64__) +#define UCONTEXT_NIA(UC) (UC)->uc_mcontext.gp_regs[PT_NIP] +#elif defined(__powerpc__) +#define UCONTEXT_NIA(UC) (UC)->uc_mcontext.uc_regs->gregs[PT_NIP] +#else +#error implement UCONTEXT_NIA +#endif + +static int segv_error; + +static void segv_handler(int signr, siginfo_t *info, void *ptr) +{ + ucontext_t *uc = (ucontext_t *)ptr; + unsigned long addr = (unsigned long)info->si_addr; + unsigned long *ip = &UCONTEXT_NIA(uc); + unsigned long *ex_p = (unsigned long *)__start___ex_table; + + while (ex_p < (unsigned long *)__stop___ex_table) { + unsigned long insn, fixup; + + insn = *ex_p++; + fixup = *ex_p++; + + if (insn == *ip) { + *ip = fixup; + return; + } + } + + printf("No exception table match for NIA %lx ADDR %lx\n", *ip, addr); + segv_error++; +} + +static void setup_segv_handler(void) +{ + struct sigaction action; + + memset(&action, 0, sizeof(action)); + action.sa_sigaction = segv_handler; + action.sa_flags = SA_SIGINFO; + sigaction(SIGSEGV, &action, NULL); +} + +static int do_one_test(char *p, int page_offset) +{ + unsigned long should; + unsigned long got; + + FAIL_IF(unprotect_region()); + should = *(unsigned long *)p; + FAIL_IF(protect_region()); + + got = load_unaligned_zeropad(p); + + if (should != got) + printf("offset %u load_unaligned_zeropad returned 0x%lx, should be 0x%lx\n", page_offset, got, should); + + return 0; +} + +static int test_body(void) +{ + unsigned long i; + + page_size = getpagesize(); + mem_region = mmap(NULL, page_size * 2, PROT_READ|PROT_WRITE, + MAP_PRIVATE|MAP_ANONYMOUS, -1, 0); + + FAIL_IF(mem_region == MAP_FAILED); + + for (i = 0; i < page_size; i++) + mem_region[i] = i; + + memset(mem_region+page_size, 0, page_size); + + setup_segv_handler(); + + for (i = 0; i < page_size; i++) + FAIL_IF(do_one_test(mem_region+i, i)); + + FAIL_IF(segv_error); + + return 0; +} + +int main(void) +{ + return test_harness(test_body, "load_unaligned_zeropad"); +} diff --git a/tools/testing/selftests/powerpc/primitives/word-at-a-time.h b/tools/testing/selftests/powerpc/primitives/word-at-a-time.h new file mode 120000 index 000000000000..eb74401b591f --- /dev/null +++ b/tools/testing/selftests/powerpc/primitives/word-at-a-time.h @@ -0,0 +1 @@ +../../../../../arch/powerpc/include/asm/word-at-a-time.h
\ No newline at end of file diff --git a/tools/testing/selftests/ptrace/peeksiginfo.c b/tools/testing/selftests/ptrace/peeksiginfo.c index d46558b1f58d..c34cd8ac8aaa 100644 --- a/tools/testing/selftests/ptrace/peeksiginfo.c +++ b/tools/testing/selftests/ptrace/peeksiginfo.c @@ -31,6 +31,10 @@ static int sys_ptrace(int request, pid_t pid, void *addr, void *data) #define TEST_SICODE_PRIV -1 #define TEST_SICODE_SHARE -2 +#ifndef PAGE_SIZE +#define PAGE_SIZE sysconf(_SC_PAGESIZE) +#endif + #define err(fmt, ...) \ fprintf(stderr, \ "Error (%s:%d): " fmt, \ diff --git a/tools/testing/selftests/rcutorture/bin/config2frag.sh b/tools/testing/selftests/rcutorture/bin/config2frag.sh index 9f9ffcd427d3..56f51ae13d73 100644..100755 --- a/tools/testing/selftests/rcutorture/bin/config2frag.sh +++ b/tools/testing/selftests/rcutorture/bin/config2frag.sh @@ -1,5 +1,5 @@ -#!/bin/sh -# Usage: sh config2frag.sh < .config > configfrag +#!/bin/bash +# Usage: config2frag.sh < .config > configfrag # # Converts the "# CONFIG_XXX is not set" to "CONFIG_XXX=n" so that the # resulting file becomes a legitimate Kconfig fragment. diff --git a/tools/testing/selftests/rcutorture/bin/configcheck.sh b/tools/testing/selftests/rcutorture/bin/configcheck.sh index d686537dd55c..eee31e261bf7 100755 --- a/tools/testing/selftests/rcutorture/bin/configcheck.sh +++ b/tools/testing/selftests/rcutorture/bin/configcheck.sh @@ -1,5 +1,5 @@ -#!/bin/sh -# Usage: sh configcheck.sh .config .config-template +#!/bin/bash +# Usage: configcheck.sh .config .config-template # # 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 diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh index 9c3f3d39b934..15f1a17ca96e 100755 --- a/tools/testing/selftests/rcutorture/bin/configinit.sh +++ b/tools/testing/selftests/rcutorture/bin/configinit.sh @@ -1,6 +1,6 @@ -#!/bin/sh +#!/bin/bash # -# sh configinit.sh config-spec-file [ build output dir ] +# Usage: configinit.sh config-spec-file [ build output dir ] # # Create a .config file from the spec file. Run from the kernel source tree. # Exits with 0 if all went well, with 1 if all went well but the config diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh index d01b865bb100..b325470c01b3 100644 --- a/tools/testing/selftests/rcutorture/bin/functions.sh +++ b/tools/testing/selftests/rcutorture/bin/functions.sh @@ -64,6 +64,26 @@ configfrag_boot_params () { fi } +# configfrag_boot_cpus bootparam-string config-fragment-file config-cpus +# +# Decreases number of CPUs based on any maxcpus= boot parameters specified. +configfrag_boot_cpus () { + local bootargs="`configfrag_boot_params "$1" "$2"`" + local maxcpus + if echo "${bootargs}" | grep -q 'maxcpus=[0-9]' + then + maxcpus="`echo "${bootargs}" | sed -e 's/^.*maxcpus=\([0-9]*\).*$/\1/'`" + if test "$3" -gt "$maxcpus" + then + echo $maxcpus + else + echo $3 + fi + else + echo $3 + fi +} + # configfrag_hotplug_cpu config-fragment-file # # Returns 1 if the config fragment specifies hotplug CPU. diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh index 7c1e56b46de4..00cb0db2643d 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh @@ -2,7 +2,7 @@ # # Build a kvm-ready Linux kernel from the tree in the current directory. # -# Usage: sh kvm-build.sh config-template build-dir more-configs +# Usage: kvm-build.sh config-template build-dir more-configs # # 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 diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh index 7f1ff1a8fc4b..43f764098e50 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh @@ -2,7 +2,7 @@ # # Analyze a given results directory for locktorture progress. # -# Usage: sh kvm-recheck-lock.sh resdir +# Usage: kvm-recheck-lock.sh resdir # # 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 diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh index 307c4b95f325..d6cc07fc137f 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh @@ -2,7 +2,7 @@ # # Analyze a given results directory for rcutorture progress. # -# Usage: sh kvm-recheck-rcu.sh resdir +# Usage: kvm-recheck-rcu.sh resdir # # 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 diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh index 3f6c9b78d177..4f5b20f367a9 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh @@ -4,7 +4,7 @@ # check the build and console output for errors. Given a directory # containing results directories, this recursively checks them all. # -# Usage: sh kvm-recheck.sh resdir ... +# Usage: kvm-recheck.sh resdir ... # # 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 diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index 0f69dcbf9def..f6b2b4771b78 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -6,7 +6,7 @@ # Execute this in the source tree. Do not run it as a background task # because qemu does not seem to like that much. # -# Usage: sh kvm-test-1-run.sh config builddir resdir minutes qemu-args boot_args +# Usage: kvm-test-1-run.sh config builddir resdir minutes qemu-args boot_args # # qemu-args defaults to "-nographic", along with arguments specifying the # number of CPUs and other options generated from @@ -140,6 +140,7 @@ fi # Generate -smp qemu argument. qemu_args="-nographic $qemu_args" cpu_count=`configNR_CPUS.sh $config_template` +cpu_count=`configfrag_boot_cpus "$boot_args" "$config_template" "$cpu_count"` vcpus=`identify_qemu_vcpus` if test $cpu_count -gt $vcpus then @@ -214,7 +215,7 @@ then fi if test $kruntime -ge $((seconds + grace)) then - echo "!!! Hang at $kruntime vs. $seconds seconds" >> $resdir/Warnings 2>&1 + echo "!!! PID $qemu_pid hung at $kruntime vs. $seconds seconds" >> $resdir/Warnings 2>&1 kill -KILL $qemu_pid break fi diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index 589e9c38413b..e527dc952eb0 100644..100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -7,7 +7,7 @@ # Edit the definitions below to set the locations of the various directories, # as well as the test duration. # -# Usage: sh kvm.sh [ options ] +# Usage: kvm.sh [ options ] # # 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 @@ -188,7 +188,9 @@ for CF in $configs do if test -f "$CONFIGFRAG/$kversion/$CF" then - echo $CF `configNR_CPUS.sh $CONFIGFRAG/$kversion/$CF` >> $T/cfgcpu + cpu_count=`configNR_CPUS.sh $CONFIGFRAG/$kversion/$CF` + cpu_count=`configfrag_boot_cpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$kversion/$CF" "$cpu_count"` + echo $CF $cpu_count >> $T/cfgcpu else echo "The --configs file $CF does not exist, terminating." exit 1 diff --git a/tools/testing/selftests/rcutorture/bin/parse-build.sh b/tools/testing/selftests/rcutorture/bin/parse-build.sh index 543230951c38..499d1e598e42 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-build.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-build.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # # Check the build output from an rcutorture run for goodness. # The "file" is a pathname on the local system, and "title" is @@ -6,8 +6,7 @@ # # The file must contain kernel build output. # -# Usage: -# sh parse-build.sh file title +# Usage: parse-build.sh file title # # 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 diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh index 4185d4cab32e..f962ba4cf68b 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-console.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh @@ -1,11 +1,10 @@ -#!/bin/sh +#!/bin/bash # # Check the console output from an rcutorture run for oopses. # The "file" is a pathname on the local system, and "title" is # a text string for error-message purposes. # -# Usage: -# sh parse-console.sh file title +# Usage: parse-console.sh file title # # 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 @@ -33,6 +32,10 @@ title="$2" . functions.sh +if grep -Pq '\x00' < $file +then + print_warning Console output contains nul bytes, old qemu still running? +fi egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $T if test -s $T then diff --git a/tools/testing/selftests/rcutorture/bin/parse-torture.sh b/tools/testing/selftests/rcutorture/bin/parse-torture.sh index 3455560ab4e4..e3c5f0705696 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-torture.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-torture.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # # Check the console output from a torture run for goodness. # The "file" is a pathname on the local system, and "title" is @@ -7,8 +7,7 @@ # The file must contain torture output, but can be interspersed # with other dmesg text, as in console-log output. # -# Usage: -# sh parse-torture.sh file title +# Usage: parse-torture.sh file title # # 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 diff --git a/tools/testing/selftests/rcutorture/configs/lock/CFLIST b/tools/testing/selftests/rcutorture/configs/lock/CFLIST index a061b22d1892..6910b7370761 100644 --- a/tools/testing/selftests/rcutorture/configs/lock/CFLIST +++ b/tools/testing/selftests/rcutorture/configs/lock/CFLIST @@ -1 +1,4 @@ LOCK01 +LOCK02 +LOCK03 +LOCK04
\ No newline at end of file diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK02 b/tools/testing/selftests/rcutorture/configs/lock/LOCK02 new file mode 100644 index 000000000000..1d1da1477fc3 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK02 @@ -0,0 +1,6 @@ +CONFIG_SMP=y +CONFIG_NR_CPUS=4 +CONFIG_HOTPLUG_CPU=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK02.boot b/tools/testing/selftests/rcutorture/configs/lock/LOCK02.boot new file mode 100644 index 000000000000..5aa44b4f1b51 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK02.boot @@ -0,0 +1 @@ +locktorture.torture_type=mutex_lock diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK03 b/tools/testing/selftests/rcutorture/configs/lock/LOCK03 new file mode 100644 index 000000000000..1d1da1477fc3 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK03 @@ -0,0 +1,6 @@ +CONFIG_SMP=y +CONFIG_NR_CPUS=4 +CONFIG_HOTPLUG_CPU=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK03.boot b/tools/testing/selftests/rcutorture/configs/lock/LOCK03.boot new file mode 100644 index 000000000000..a67bbe0245c9 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK03.boot @@ -0,0 +1 @@ +locktorture.torture_type=rwsem_lock diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK04 b/tools/testing/selftests/rcutorture/configs/lock/LOCK04 new file mode 100644 index 000000000000..1d1da1477fc3 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK04 @@ -0,0 +1,6 @@ +CONFIG_SMP=y +CONFIG_NR_CPUS=4 +CONFIG_HOTPLUG_CPU=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK04.boot b/tools/testing/selftests/rcutorture/configs/lock/LOCK04.boot new file mode 100644 index 000000000000..48c04fe47fb4 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK04.boot @@ -0,0 +1 @@ +locktorture.torture_type=rw_lock diff --git a/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh index 9746ea1cd6c7..252aae618984 100644 --- a/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh +++ b/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh @@ -38,6 +38,6 @@ per_version_boot_params () { echo $1 `locktorture_param_onoff "$1" "$2"` \ locktorture.stat_interval=15 \ locktorture.shutdown_secs=$3 \ - locktorture.locktorture_runnable=1 \ + locktorture.torture_runnable=1 \ locktorture.verbose=1 } diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST index cd3d29cb0a47..a3a1a05a2b5c 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/CFLIST +++ b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST @@ -11,3 +11,6 @@ SRCU-N SRCU-P TINY01 TINY02 +TASKS01 +TASKS02 +TASKS03 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 new file mode 100644 index 000000000000..97f0a0b27ef7 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 @@ -0,0 +1,9 @@ +CONFIG_SMP=y +CONFIG_NR_CPUS=2 +CONFIG_HOTPLUG_CPU=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y +CONFIG_DEBUG_LOCK_ALLOC=y +CONFIG_PROVE_RCU=y +CONFIG_TASKS_RCU=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01.boot b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01.boot new file mode 100644 index 000000000000..cd2a188eeb6d --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01.boot @@ -0,0 +1 @@ +rcutorture.torture_type=tasks diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 new file mode 100644 index 000000000000..696d2ea74d13 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 @@ -0,0 +1,5 @@ +CONFIG_SMP=n +CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=n +CONFIG_TASKS_RCU=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot new file mode 100644 index 000000000000..cd2a188eeb6d --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot @@ -0,0 +1 @@ +rcutorture.torture_type=tasks diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 new file mode 100644 index 000000000000..9c60da5b5d1d --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 @@ -0,0 +1,13 @@ +CONFIG_SMP=y +CONFIG_NR_CPUS=2 +CONFIG_HOTPLUG_CPU=n +CONFIG_SUSPEND=n +CONFIG_HIBERNATION=n +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y +CONFIG_TASKS_RCU=y +CONFIG_HZ_PERIODIC=n +CONFIG_NO_HZ_IDLE=n +CONFIG_NO_HZ_FULL=y +CONFIG_NO_HZ_FULL_ALL=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03.boot b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03.boot new file mode 100644 index 000000000000..cd2a188eeb6d --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03.boot @@ -0,0 +1 @@ +rcutorture.torture_type=tasks diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 index 063b7079c621..38e3895759dd 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01 @@ -1,5 +1,4 @@ CONFIG_SMP=y -CONFIG_NR_CPUS=8 CONFIG_PREEMPT_NONE=n CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=y @@ -10,8 +9,7 @@ CONFIG_NO_HZ_FULL=n CONFIG_RCU_FAST_NO_HZ=y CONFIG_RCU_TRACE=y CONFIG_HOTPLUG_CPU=y -CONFIG_RCU_FANOUT=8 -CONFIG_RCU_FANOUT_EXACT=n +CONFIG_MAXSMP=y CONFIG_RCU_NOCB_CPU=y CONFIG_RCU_NOCB_CPU_ZERO=y CONFIG_DEBUG_LOCK_ALLOC=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot index 0fc8a3428938..adc3abc82fb8 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot @@ -1 +1 @@ -rcutorture.torture_type=rcu_bh +rcutorture.torture_type=rcu_bh maxcpus=8 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 index ab6225506909..8f1017666aa7 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07 @@ -1,5 +1,6 @@ CONFIG_SMP=y CONFIG_NR_CPUS=16 +CONFIG_CPUMASK_OFFSTACK=y CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n @@ -7,7 +8,7 @@ CONFIG_PREEMPT=n CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=n CONFIG_NO_HZ_FULL=y -CONFIG_NO_HZ_FULL_ALL=y +CONFIG_NO_HZ_FULL_ALL=n CONFIG_NO_HZ_FULL_SYSIDLE=y CONFIG_RCU_FAST_NO_HZ=n CONFIG_RCU_TRACE=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot new file mode 100644 index 000000000000..d44609937503 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07.boot @@ -0,0 +1 @@ +nohz_full=2-9 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh index 8977d8d31b19..ffb85ed786fa 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh +++ b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh @@ -51,7 +51,7 @@ per_version_boot_params () { `rcutorture_param_n_barrier_cbs "$1"` \ rcutorture.stat_interval=15 \ rcutorture.shutdown_secs=$3 \ - rcutorture.rcutorture_runnable=1 \ + rcutorture.torture_runnable=1 \ rcutorture.test_no_idle_hz=1 \ rcutorture.verbose=1 } diff --git a/tools/testing/selftests/rcutorture/doc/initrd.txt b/tools/testing/selftests/rcutorture/doc/initrd.txt index 49d134c25c04..4170e714f044 100644 --- a/tools/testing/selftests/rcutorture/doc/initrd.txt +++ b/tools/testing/selftests/rcutorture/doc/initrd.txt @@ -6,6 +6,7 @@ this case. There are probably much better ways of doing this. That said, here are the commands: ------------------------------------------------------------------------ +cd tools/testing/selftests/rcutorture zcat /initrd.img > /tmp/initrd.img.zcat mkdir initrd cd initrd diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 3f94e1afd6cf..4c4b1f631ecf 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -3,6 +3,7 @@ CC = $(CROSS_COMPILE)gcc CFLAGS = -Wall BINARIES = hugepage-mmap hugepage-shm map_hugetlb thuge-gen hugetlbfstest +BINARIES += transhuge-stress all: $(BINARIES) %: %.c diff --git a/tools/testing/selftests/vm/transhuge-stress.c b/tools/testing/selftests/vm/transhuge-stress.c new file mode 100644 index 000000000000..fd7f1b4a96f9 --- /dev/null +++ b/tools/testing/selftests/vm/transhuge-stress.c @@ -0,0 +1,144 @@ +/* + * Stress test for transparent huge pages, memory compaction and migration. + * + * Authors: Konstantin Khlebnikov <koct9i@gmail.com> + * + * This is free and unencumbered software released into the public domain. + */ + +#include <stdlib.h> +#include <stdio.h> +#include <stdint.h> +#include <err.h> +#include <time.h> +#include <unistd.h> +#include <fcntl.h> +#include <string.h> +#include <sys/mman.h> + +#define PAGE_SHIFT 12 +#define HPAGE_SHIFT 21 + +#define PAGE_SIZE (1 << PAGE_SHIFT) +#define HPAGE_SIZE (1 << HPAGE_SHIFT) + +#define PAGEMAP_PRESENT(ent) (((ent) & (1ull << 63)) != 0) +#define PAGEMAP_PFN(ent) ((ent) & ((1ull << 55) - 1)) + +int pagemap_fd; + +int64_t allocate_transhuge(void *ptr) +{ + uint64_t ent[2]; + + /* drop pmd */ + if (mmap(ptr, HPAGE_SIZE, PROT_READ | PROT_WRITE, + MAP_FIXED | MAP_ANONYMOUS | + MAP_NORESERVE | MAP_PRIVATE, -1, 0) != ptr) + errx(2, "mmap transhuge"); + + if (madvise(ptr, HPAGE_SIZE, MADV_HUGEPAGE)) + err(2, "MADV_HUGEPAGE"); + + /* allocate transparent huge page */ + *(volatile void **)ptr = ptr; + + if (pread(pagemap_fd, ent, sizeof(ent), + (uintptr_t)ptr >> (PAGE_SHIFT - 3)) != sizeof(ent)) + err(2, "read pagemap"); + + if (PAGEMAP_PRESENT(ent[0]) && PAGEMAP_PRESENT(ent[1]) && + PAGEMAP_PFN(ent[0]) + 1 == PAGEMAP_PFN(ent[1]) && + !(PAGEMAP_PFN(ent[0]) & ((1 << (HPAGE_SHIFT - PAGE_SHIFT)) - 1))) + return PAGEMAP_PFN(ent[0]); + + return -1; +} + +int main(int argc, char **argv) +{ + size_t ram, len; + void *ptr, *p; + struct timespec a, b; + double s; + uint8_t *map; + size_t map_len; + + ram = sysconf(_SC_PHYS_PAGES); + if (ram > SIZE_MAX / sysconf(_SC_PAGESIZE) / 4) + ram = SIZE_MAX / 4; + else + ram *= sysconf(_SC_PAGESIZE); + + if (argc == 1) + len = ram; + else if (!strcmp(argv[1], "-h")) + errx(1, "usage: %s [size in MiB]", argv[0]); + else + len = atoll(argv[1]) << 20; + + warnx("allocate %zd transhuge pages, using %zd MiB virtual memory" + " and %zd MiB of ram", len >> HPAGE_SHIFT, len >> 20, + len >> (20 + HPAGE_SHIFT - PAGE_SHIFT - 1)); + + pagemap_fd = open("/proc/self/pagemap", O_RDONLY); + if (pagemap_fd < 0) + err(2, "open pagemap"); + + len -= len % HPAGE_SIZE; + ptr = mmap(NULL, len + HPAGE_SIZE, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE, -1, 0); + if (ptr == MAP_FAILED) + err(2, "initial mmap"); + ptr += HPAGE_SIZE - (uintptr_t)ptr % HPAGE_SIZE; + + if (madvise(ptr, len, MADV_HUGEPAGE)) + err(2, "MADV_HUGEPAGE"); + + map_len = ram >> (HPAGE_SHIFT - 1); + map = malloc(map_len); + if (!map) + errx(2, "map malloc"); + + while (1) { + int nr_succeed = 0, nr_failed = 0, nr_pages = 0; + + memset(map, 0, map_len); + + clock_gettime(CLOCK_MONOTONIC, &a); + for (p = ptr; p < ptr + len; p += HPAGE_SIZE) { + int64_t pfn; + + pfn = allocate_transhuge(p); + + if (pfn < 0) { + nr_failed++; + } else { + size_t idx = pfn >> (HPAGE_SHIFT - PAGE_SHIFT); + + nr_succeed++; + if (idx >= map_len) { + map = realloc(map, idx + 1); + if (!map) + errx(2, "map realloc"); + memset(map + map_len, 0, idx + 1 - map_len); + map_len = idx + 1; + } + if (!map[idx]) + nr_pages++; + map[idx] = 1; + } + + /* split transhuge page, keep last page */ + if (madvise(p, HPAGE_SIZE - PAGE_SIZE, MADV_DONTNEED)) + err(2, "MADV_DONTNEED"); + } + clock_gettime(CLOCK_MONOTONIC, &b); + s = b.tv_sec - a.tv_sec + (b.tv_nsec - a.tv_nsec) / 1000000000.; + + warnx("%.3f s/loop, %.3f ms/page, %10.3f MiB/s\t" + "%4d succeed, %4d failed, %4d different pages", + s, s * 1000 / (len >> HPAGE_SHIFT), len / s / (1 << 20), + nr_succeed, nr_failed, nr_pages); + } +} |