From 9308f2f9e7f055cf3934645ec622bb5259dc1c14 Mon Sep 17 00:00:00 2001
From: "Luis R. Rodriguez" <mcgrof@kernel.org>
Date: Wed, 12 Jul 2017 14:33:43 -0700
Subject: test_sysctl: add dedicated proc sysctl test driver

The existing tools/testing/selftests/sysctl/ tests include two test
cases, but these use existing production kernel sysctl interfaces.  We
want to expand test coverage but we can't just be looking for random
safe production values to poke at, that's just insane!

Instead just dedicate a test driver for debugging purposes and port the
existing scripts to use it.  This will make it easier for further tests
to be added.

Subsequent patches will extend our test coverage for sysctl.

The stress test driver uses a new license (GPL on Linux, copyleft-next
outside of Linux).  Linus was fine with this [0] and later due to Ted's
and Alans's request ironed out an "or" language clause to use [1] which
is already present upstream.

[0] https://lkml.kernel.org/r/CA+55aFyhxcvD+q7tp+-yrSFDKfR0mOHgyEAe=f_94aKLsOu0Og@mail.gmail.com
[1] https://lkml.kernel.org/r/1495234558.7848.122.camel@linux.intel.com

Link: http://lkml.kernel.org/r/20170630224431.17374-2-mcgrof@kernel.org
Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/sysctl/config           | 1 +
 tools/testing/selftests/sysctl/run_numerictests | 4 ++--
 tools/testing/selftests/sysctl/run_stringtests  | 4 ++--
 3 files changed, 5 insertions(+), 4 deletions(-)
 create mode 100644 tools/testing/selftests/sysctl/config

(limited to 'tools')

diff --git a/tools/testing/selftests/sysctl/config b/tools/testing/selftests/sysctl/config
new file mode 100644
index 000000000000..6ca14800d755
--- /dev/null
+++ b/tools/testing/selftests/sysctl/config
@@ -0,0 +1 @@
+CONFIG_TEST_SYSCTL=y
diff --git a/tools/testing/selftests/sysctl/run_numerictests b/tools/testing/selftests/sysctl/run_numerictests
index e6e76c93d948..c375ce0f4c15 100755
--- a/tools/testing/selftests/sysctl/run_numerictests
+++ b/tools/testing/selftests/sysctl/run_numerictests
@@ -1,7 +1,7 @@
 #!/bin/sh
 
-SYSCTL="/proc/sys"
-TARGET="${SYSCTL}/vm/swappiness"
+SYSCTL="/proc/sys/debug/test_sysctl/"
+TARGET="${SYSCTL}/int_0001"
 ORIG=$(cat "${TARGET}")
 TEST_STR=$(( $ORIG + 1 ))
 
diff --git a/tools/testing/selftests/sysctl/run_stringtests b/tools/testing/selftests/sysctl/run_stringtests
index 857ec667fb02..a6f2618afeaa 100755
--- a/tools/testing/selftests/sysctl/run_stringtests
+++ b/tools/testing/selftests/sysctl/run_stringtests
@@ -1,7 +1,7 @@
 #!/bin/sh
 
-SYSCTL="/proc/sys"
-TARGET="${SYSCTL}/kernel/domainname"
+SYSCTL="/proc/sys/debug/test_sysctl/"
+TARGET="${SYSCTL}/string_0001"
 ORIG=$(cat "${TARGET}")
 TEST_STR="Testing sysctl"
 
-- 
cgit v1.2.3-59-g8ed1b


From 64b671204afd71591e774e7237b7c862ac5bbd97 Mon Sep 17 00:00:00 2001
From: "Luis R. Rodriguez" <mcgrof@kernel.org>
Date: Wed, 12 Jul 2017 14:33:46 -0700
Subject: test_sysctl: add generic script to expand on tests

This adds a generic script to let us more easily add more tests cases.
Since we really have only two types of tests cases just fold them into
the one file.  Each test unit is now identified into its separate
function:

    # ./sysctl.sh -l
  Test ID list:

  TEST_ID x NUM_TEST
  TEST_ID:   Test ID
  NUM_TESTS: Number of recommended times to run the test

  0001 x 1 - tests proc_dointvec_minmax()
  0002 x 1 - tests proc_dostring()

For now we start off with what we had before, and run only each test
once.  We can now watch a test case until it fails:

  ./sysctl.sh -w 0002

We can also run a test case x number of times, say we want to run a test
case 100 times:

  ./sysctl.sh -c 0001 100

To run a test case only once, for example:

  ./sysctl.sh -s 0002

The default settings are specified at the top of sysctl.sh.

Link: http://lkml.kernel.org/r/20170630224431.17374-3-mcgrof@kernel.org
Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/sysctl/Makefile         |   3 +-
 tools/testing/selftests/sysctl/common_tests     | 131 -------
 tools/testing/selftests/sysctl/run_numerictests |  10 -
 tools/testing/selftests/sysctl/run_stringtests  |  77 ----
 tools/testing/selftests/sysctl/sysctl.sh        | 494 ++++++++++++++++++++++++
 5 files changed, 495 insertions(+), 220 deletions(-)
 delete mode 100644 tools/testing/selftests/sysctl/common_tests
 delete mode 100755 tools/testing/selftests/sysctl/run_numerictests
 delete mode 100755 tools/testing/selftests/sysctl/run_stringtests
 create mode 100644 tools/testing/selftests/sysctl/sysctl.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/sysctl/Makefile b/tools/testing/selftests/sysctl/Makefile
index b3c33e071f10..95c320b354e8 100644
--- a/tools/testing/selftests/sysctl/Makefile
+++ b/tools/testing/selftests/sysctl/Makefile
@@ -4,8 +4,7 @@
 # No binaries, but make sure arg-less "make" doesn't trigger "run_tests".
 all:
 
-TEST_PROGS := run_numerictests run_stringtests
-TEST_FILES := common_tests
+TEST_PROGS := sysctl.sh
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/sysctl/common_tests b/tools/testing/selftests/sysctl/common_tests
deleted file mode 100644
index b6862322962f..000000000000
--- a/tools/testing/selftests/sysctl/common_tests
+++ /dev/null
@@ -1,131 +0,0 @@
-#!/bin/sh
-
-TEST_FILE=$(mktemp)
-
-echo "== Testing sysctl behavior against ${TARGET} =="
-
-set_orig()
-{
-	echo "${ORIG}" > "${TARGET}"
-}
-
-set_test()
-{
-	echo "${TEST_STR}" > "${TARGET}"
-}
-
-verify()
-{
-	local seen
-	seen=$(cat "$1")
-	if [ "${seen}" != "${TEST_STR}" ]; then
-		return 1
-	fi
-	return 0
-}
-
-exit_test()
-{
-	if [ ! -z ${old_strict} ]; then
-		echo ${old_strict} > ${WRITES_STRICT}
-	fi
-	exit $rc
-}
-
-trap 'set_orig; rm -f "${TEST_FILE}"' EXIT
-
-rc=0
-
-echo -n "Writing test file ... "
-echo "${TEST_STR}" > "${TEST_FILE}"
-if ! verify "${TEST_FILE}"; then
-	echo "FAIL" >&2
-	exit 1
-else
-	echo "ok"
-fi
-
-echo -n "Checking sysctl is not set to test value ... "
-if verify "${TARGET}"; then
-	echo "FAIL" >&2
-	exit 1
-else
-	echo "ok"
-fi
-
-echo -n "Writing sysctl from shell ... "
-set_test
-if ! verify "${TARGET}"; then
-	echo "FAIL" >&2
-	exit 1
-else
-	echo "ok"
-fi
-
-echo -n "Resetting sysctl to original value ... "
-set_orig
-if verify "${TARGET}"; then
-	echo "FAIL" >&2
-	exit 1
-else
-	echo "ok"
-fi
-
-echo -n "Checking write strict setting ... "
-WRITES_STRICT="${SYSCTL}/kernel/sysctl_writes_strict"
-if [ ! -e ${WRITES_STRICT} ]; then
-	echo "FAIL, but skip in case of old kernel" >&2
-else
-	old_strict=$(cat ${WRITES_STRICT})
-	if [ "$old_strict" = "1" ]; then
-		echo "ok"
-	else
-		echo "FAIL, strict value is 0 but force to 1 to continue" >&2
-		echo "1" > ${WRITES_STRICT}
-	fi
-fi
-
-# Now that we've validated the sanity of "set_test" and "set_orig",
-# we can use those functions to set starting states before running
-# specific behavioral tests.
-
-echo -n "Writing entire sysctl in single write ... "
-set_orig
-dd if="${TEST_FILE}" of="${TARGET}" bs=4096 2>/dev/null
-if ! verify "${TARGET}"; then
-	echo "FAIL" >&2
-	rc=1
-else
-	echo "ok"
-fi
-
-echo -n "Writing middle of sysctl after synchronized seek ... "
-set_test
-dd if="${TEST_FILE}" of="${TARGET}" bs=1 seek=1 skip=1 2>/dev/null
-if ! verify "${TARGET}"; then
-	echo "FAIL" >&2
-	rc=1
-else
-	echo "ok"
-fi
-
-echo -n "Writing beyond end of sysctl ... "
-set_orig
-dd if="${TEST_FILE}" of="${TARGET}" bs=20 seek=2 2>/dev/null
-if verify "${TARGET}"; then
-        echo "FAIL" >&2
-        rc=1
-else
-        echo "ok"
-fi
-
-echo -n "Writing sysctl with multiple long writes ... "
-set_orig
-(perl -e 'print "A" x 50;'; echo "${TEST_STR}") | \
-	dd of="${TARGET}" bs=50 2>/dev/null
-if verify "${TARGET}"; then
-	echo "FAIL" >&2
-	rc=1
-else
-	echo "ok"
-fi
diff --git a/tools/testing/selftests/sysctl/run_numerictests b/tools/testing/selftests/sysctl/run_numerictests
deleted file mode 100755
index c375ce0f4c15..000000000000
--- a/tools/testing/selftests/sysctl/run_numerictests
+++ /dev/null
@@ -1,10 +0,0 @@
-#!/bin/sh
-
-SYSCTL="/proc/sys/debug/test_sysctl/"
-TARGET="${SYSCTL}/int_0001"
-ORIG=$(cat "${TARGET}")
-TEST_STR=$(( $ORIG + 1 ))
-
-. ./common_tests
-
-exit_test
diff --git a/tools/testing/selftests/sysctl/run_stringtests b/tools/testing/selftests/sysctl/run_stringtests
deleted file mode 100755
index a6f2618afeaa..000000000000
--- a/tools/testing/selftests/sysctl/run_stringtests
+++ /dev/null
@@ -1,77 +0,0 @@
-#!/bin/sh
-
-SYSCTL="/proc/sys/debug/test_sysctl/"
-TARGET="${SYSCTL}/string_0001"
-ORIG=$(cat "${TARGET}")
-TEST_STR="Testing sysctl"
-
-. ./common_tests
-
-# Only string sysctls support seeking/appending.
-MAXLEN=65
-
-echo -n "Writing entire sysctl in short writes ... "
-set_orig
-dd if="${TEST_FILE}" of="${TARGET}" bs=1 2>/dev/null
-if ! verify "${TARGET}"; then
-	echo "FAIL" >&2
-	rc=1
-else
-	echo "ok"
-fi
-
-echo -n "Writing middle of sysctl after unsynchronized seek ... "
-set_test
-dd if="${TEST_FILE}" of="${TARGET}" bs=1 seek=1 2>/dev/null
-if verify "${TARGET}"; then
-	echo "FAIL" >&2
-	rc=1
-else
-	echo "ok"
-fi
-
-echo -n "Checking sysctl maxlen is at least $MAXLEN ... "
-set_orig
-perl -e 'print "A" x ('"${MAXLEN}"'-2), "B";' | \
-	dd of="${TARGET}" bs="${MAXLEN}" 2>/dev/null
-if ! grep -q B "${TARGET}"; then
-	echo "FAIL" >&2
-	rc=1
-else
-	echo "ok"
-fi
-
-echo -n "Checking sysctl keeps original string on overflow append ... "
-set_orig
-perl -e 'print "A" x ('"${MAXLEN}"'-1), "B";' | \
-	dd of="${TARGET}" bs=$(( MAXLEN - 1 )) 2>/dev/null
-if grep -q B "${TARGET}"; then
-	echo "FAIL" >&2
-	rc=1
-else
-	echo "ok"
-fi
-
-echo -n "Checking sysctl stays NULL terminated on write ... "
-set_orig
-perl -e 'print "A" x ('"${MAXLEN}"'-1), "B";' | \
-	dd of="${TARGET}" bs="${MAXLEN}" 2>/dev/null
-if grep -q B "${TARGET}"; then
-	echo "FAIL" >&2
-	rc=1
-else
-	echo "ok"
-fi
-
-echo -n "Checking sysctl stays NULL terminated on overwrite ... "
-set_orig
-perl -e 'print "A" x ('"${MAXLEN}"'-1), "BB";' | \
-	dd of="${TARGET}" bs=$(( $MAXLEN + 1 )) 2>/dev/null
-if grep -q B "${TARGET}"; then
-	echo "FAIL" >&2
-	rc=1
-else
-	echo "ok"
-fi
-
-exit_test
diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh
new file mode 100644
index 000000000000..cbe1345d7c1d
--- /dev/null
+++ b/tools/testing/selftests/sysctl/sysctl.sh
@@ -0,0 +1,494 @@
+#!/bin/bash
+# Copyright (C) 2017 Luis R. Rodriguez <mcgrof@kernel.org>
+#
+# 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; or, when distributed separately from the Linux kernel or
+# when incorporated into other software packages, subject to the following
+# license:
+#
+# This program is free software; you can redistribute it and/or modify it
+# under the terms of copyleft-next (version 0.3.1 or later) as published
+# at http://copyleft-next.org/.
+
+# This performs a series tests against the proc sysctl interface.
+
+TEST_NAME="sysctl"
+TEST_DRIVER="test_${TEST_NAME}"
+TEST_DIR=$(dirname $0)
+TEST_FILE=$(mktemp)
+
+# This represents
+#
+# TEST_ID:TEST_COUNT:ENABLED
+#
+# TEST_ID: is the test id number
+# TEST_COUNT: number of times we should run the test
+# ENABLED: 1 if enabled, 0 otherwise
+#
+# Once these are enabled please leave them as-is. Write your own test,
+# we have tons of space.
+ALL_TESTS="0001:1:1"
+ALL_TESTS="$ALL_TESTS 0002:1:1"
+
+test_modprobe()
+{
+       if [ ! -d $DIR ]; then
+               echo "$0: $DIR not present" >&2
+               echo "You must have the following enabled in your kernel:" >&2
+               cat $TEST_DIR/config >&2
+               exit 1
+       fi
+}
+
+function allow_user_defaults()
+{
+	if [ -z $DIR ]; then
+		DIR="/sys/module/test_sysctl/"
+	fi
+	if [ -z $DEFAULT_NUM_TESTS ]; then
+		DEFAULT_NUM_TESTS=50
+	fi
+	if [ -z $SYSCTL ]; then
+		SYSCTL="/proc/sys/debug/test_sysctl"
+	fi
+	if [ -z $PROD_SYSCTL ]; then
+		PROD_SYSCTL="/proc/sys"
+	fi
+	if [ -z $WRITES_STRICT ]; then
+		WRITES_STRICT="${PROD_SYSCTL}/kernel/sysctl_writes_strict"
+	fi
+}
+
+function check_production_sysctl_writes_strict()
+{
+	echo -n "Checking production write strict setting ... "
+	if [ ! -e ${WRITES_STRICT} ]; then
+		echo "FAIL, but skip in case of old kernel" >&2
+	else
+		old_strict=$(cat ${WRITES_STRICT})
+		if [ "$old_strict" = "1" ]; then
+			echo "ok"
+		else
+			echo "FAIL, strict value is 0 but force to 1 to continue" >&2
+			echo "1" > ${WRITES_STRICT}
+		fi
+	fi
+}
+
+test_reqs()
+{
+	uid=$(id -u)
+	if [ $uid -ne 0 ]; then
+		echo $msg must be run as root >&2
+		exit 0
+	fi
+
+	if ! which perl 2> /dev/null > /dev/null; then
+		echo "$0: You need perl installed"
+		exit 1
+	fi
+}
+
+function load_req_mod()
+{
+	trap "test_modprobe" EXIT
+
+	if [ ! -d $DIR ]; then
+		modprobe $TEST_DRIVER
+		if [ $? -ne 0 ]; then
+			exit
+		fi
+	fi
+}
+
+set_orig()
+{
+	if [ ! -z $TARGET ]; then
+		echo "${ORIG}" > "${TARGET}"
+	fi
+}
+
+set_test()
+{
+	echo "${TEST_STR}" > "${TARGET}"
+}
+
+verify()
+{
+	local seen
+	seen=$(cat "$1")
+	if [ "${seen}" != "${TEST_STR}" ]; then
+		return 1
+	fi
+	return 0
+}
+
+test_rc()
+{
+	if [[ $rc != 0 ]]; then
+		echo "Failed test, return value: $rc" >&2
+		exit $rc
+	fi
+}
+
+test_finish()
+{
+	set_orig
+	rm -f "${TEST_FILE}"
+
+	if [ ! -z ${old_strict} ]; then
+		echo ${old_strict} > ${WRITES_STRICT}
+	fi
+	exit $rc
+}
+
+run_numerictests()
+{
+	echo "== Testing sysctl behavior against ${TARGET} =="
+
+	rc=0
+
+	echo -n "Writing test file ... "
+	echo "${TEST_STR}" > "${TEST_FILE}"
+	if ! verify "${TEST_FILE}"; then
+		echo "FAIL" >&2
+		exit 1
+	else
+		echo "ok"
+	fi
+
+	echo -n "Checking sysctl is not set to test value ... "
+	if verify "${TARGET}"; then
+		echo "FAIL" >&2
+		exit 1
+	else
+		echo "ok"
+	fi
+
+	echo -n "Writing sysctl from shell ... "
+	set_test
+	if ! verify "${TARGET}"; then
+		echo "FAIL" >&2
+		exit 1
+	else
+		echo "ok"
+	fi
+
+	echo -n "Resetting sysctl to original value ... "
+	set_orig
+	if verify "${TARGET}"; then
+		echo "FAIL" >&2
+		exit 1
+	else
+		echo "ok"
+	fi
+
+	# Now that we've validated the sanity of "set_test" and "set_orig",
+	# we can use those functions to set starting states before running
+	# specific behavioral tests.
+
+	echo -n "Writing entire sysctl in single write ... "
+	set_orig
+	dd if="${TEST_FILE}" of="${TARGET}" bs=4096 2>/dev/null
+	if ! verify "${TARGET}"; then
+		echo "FAIL" >&2
+		rc=1
+	else
+		echo "ok"
+	fi
+
+	echo -n "Writing middle of sysctl after synchronized seek ... "
+	set_test
+	dd if="${TEST_FILE}" of="${TARGET}" bs=1 seek=1 skip=1 2>/dev/null
+	if ! verify "${TARGET}"; then
+		echo "FAIL" >&2
+		rc=1
+	else
+		echo "ok"
+	fi
+
+	echo -n "Writing beyond end of sysctl ... "
+	set_orig
+	dd if="${TEST_FILE}" of="${TARGET}" bs=20 seek=2 2>/dev/null
+	if verify "${TARGET}"; then
+		echo "FAIL" >&2
+		rc=1
+	else
+		echo "ok"
+	fi
+
+	echo -n "Writing sysctl with multiple long writes ... "
+	set_orig
+	(perl -e 'print "A" x 50;'; echo "${TEST_STR}") | \
+		dd of="${TARGET}" bs=50 2>/dev/null
+	if verify "${TARGET}"; then
+		echo "FAIL" >&2
+		rc=1
+	else
+		echo "ok"
+	fi
+
+	test_rc
+}
+
+run_stringtests()
+{
+	echo -n "Writing entire sysctl in short writes ... "
+	set_orig
+	dd if="${TEST_FILE}" of="${TARGET}" bs=1 2>/dev/null
+	if ! verify "${TARGET}"; then
+		echo "FAIL" >&2
+		rc=1
+	else
+		echo "ok"
+	fi
+
+	echo -n "Writing middle of sysctl after unsynchronized seek ... "
+	set_test
+	dd if="${TEST_FILE}" of="${TARGET}" bs=1 seek=1 2>/dev/null
+	if verify "${TARGET}"; then
+		echo "FAIL" >&2
+		rc=1
+	else
+		echo "ok"
+	fi
+
+	echo -n "Checking sysctl maxlen is at least $MAXLEN ... "
+	set_orig
+	perl -e 'print "A" x ('"${MAXLEN}"'-2), "B";' | \
+		dd of="${TARGET}" bs="${MAXLEN}" 2>/dev/null
+	if ! grep -q B "${TARGET}"; then
+		echo "FAIL" >&2
+		rc=1
+	else
+		echo "ok"
+	fi
+
+	echo -n "Checking sysctl keeps original string on overflow append ... "
+	set_orig
+	perl -e 'print "A" x ('"${MAXLEN}"'-1), "B";' | \
+		dd of="${TARGET}" bs=$(( MAXLEN - 1 )) 2>/dev/null
+	if grep -q B "${TARGET}"; then
+		echo "FAIL" >&2
+		rc=1
+	else
+		echo "ok"
+	fi
+
+	echo -n "Checking sysctl stays NULL terminated on write ... "
+	set_orig
+	perl -e 'print "A" x ('"${MAXLEN}"'-1), "B";' | \
+		dd of="${TARGET}" bs="${MAXLEN}" 2>/dev/null
+	if grep -q B "${TARGET}"; then
+		echo "FAIL" >&2
+		rc=1
+	else
+		echo "ok"
+	fi
+
+	echo -n "Checking sysctl stays NULL terminated on overwrite ... "
+	set_orig
+	perl -e 'print "A" x ('"${MAXLEN}"'-1), "BB";' | \
+		dd of="${TARGET}" bs=$(( $MAXLEN + 1 )) 2>/dev/null
+	if grep -q B "${TARGET}"; then
+		echo "FAIL" >&2
+		rc=1
+	else
+		echo "ok"
+	fi
+
+	test_rc
+}
+
+sysctl_test_0001()
+{
+	TARGET="${SYSCTL}/int_0001"
+	ORIG=$(cat "${TARGET}")
+	TEST_STR=$(( $ORIG + 1 ))
+
+	run_numerictests
+}
+
+sysctl_test_0002()
+{
+	TARGET="${SYSCTL}/string_0001"
+	ORIG=$(cat "${TARGET}")
+	TEST_STR="Testing sysctl"
+	# Only string sysctls support seeking/appending.
+	MAXLEN=65
+
+	run_numerictests
+	run_stringtests
+}
+
+list_tests()
+{
+	echo "Test ID list:"
+	echo
+	echo "TEST_ID x NUM_TEST"
+	echo "TEST_ID:   Test ID"
+	echo "NUM_TESTS: Number of recommended times to run the test"
+	echo
+	echo "0001 x $(get_test_count 0001) - tests proc_dointvec_minmax()"
+	echo "0002 x $(get_test_count 0002) - tests proc_dostring()"
+}
+
+test_reqs
+
+usage()
+{
+	NUM_TESTS=$(grep -o ' ' <<<"$ALL_TESTS" | grep -c .)
+	let NUM_TESTS=$NUM_TESTS+1
+	MAX_TEST=$(printf "%04d\n" $NUM_TESTS)
+	echo "Usage: $0 [ -t <4-number-digit> ] | [ -w <4-number-digit> ] |"
+	echo "		 [ -s <4-number-digit> ] | [ -c <4-number-digit> <test- count>"
+	echo "           [ all ] [ -h | --help ] [ -l ]"
+	echo ""
+	echo "Valid tests: 0001-$MAX_TEST"
+	echo ""
+	echo "    all     Runs all tests (default)"
+	echo "    -t      Run test ID the number amount of times is recommended"
+	echo "    -w      Watch test ID run until it runs into an error"
+	echo "    -c      Run test ID once"
+	echo "    -s      Run test ID x test-count number of times"
+	echo "    -l      List all test ID list"
+	echo " -h|--help  Help"
+	echo
+	echo "If an error every occurs execution will immediately terminate."
+	echo "If you are adding a new test try using -w <test-ID> first to"
+	echo "make sure the test passes a series of tests."
+	echo
+	echo Example uses:
+	echo
+	echo "$TEST_NAME.sh            -- executes all tests"
+	echo "$TEST_NAME.sh -t 0002    -- Executes test ID 0002 number of times is recomended"
+	echo "$TEST_NAME.sh -w 0002    -- Watch test ID 0002 run until an error occurs"
+	echo "$TEST_NAME.sh -s 0002    -- Run test ID 0002 once"
+	echo "$TEST_NAME.sh -c 0002 3  -- Run test ID 0002 three times"
+	echo
+	list_tests
+	exit 1
+}
+
+function test_num()
+{
+	re='^[0-9]+$'
+	if ! [[ $1 =~ $re ]]; then
+		usage
+	fi
+}
+
+function get_test_count()
+{
+	test_num $1
+	TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}')
+	LAST_TWO=${TEST_DATA#*:*}
+	echo ${LAST_TWO%:*}
+}
+
+function get_test_enabled()
+{
+	test_num $1
+	TEST_DATA=$(echo $ALL_TESTS | awk '{print $'$1'}')
+	echo ${TEST_DATA#*:*:}
+}
+
+function run_all_tests()
+{
+	for i in $ALL_TESTS ; do
+		TEST_ID=${i%:*:*}
+		ENABLED=$(get_test_enabled $TEST_ID)
+		TEST_COUNT=$(get_test_count $TEST_ID)
+		if [[ $ENABLED -eq "1" ]]; then
+			test_case $TEST_ID $TEST_COUNT
+		fi
+	done
+}
+
+function watch_log()
+{
+	if [ $# -ne 3 ]; then
+		clear
+	fi
+	date
+	echo "Running test: $2 - run #$1"
+}
+
+function watch_case()
+{
+	i=0
+	while [ 1 ]; do
+
+		if [ $# -eq 1 ]; then
+			test_num $1
+			watch_log $i ${TEST_NAME}_test_$1
+			${TEST_NAME}_test_$1
+		else
+			watch_log $i all
+			run_all_tests
+		fi
+		let i=$i+1
+	done
+}
+
+function test_case()
+{
+	NUM_TESTS=$DEFAULT_NUM_TESTS
+	if [ $# -eq 2 ]; then
+		NUM_TESTS=$2
+	fi
+
+	i=0
+	while [ $i -lt $NUM_TESTS ]; do
+		test_num $1
+		watch_log $i ${TEST_NAME}_test_$1 noclear
+		RUN_TEST=${TEST_NAME}_test_$1
+		$RUN_TEST
+		let i=$i+1
+	done
+}
+
+function parse_args()
+{
+	if [ $# -eq 0 ]; then
+		run_all_tests
+	else
+		if [[ "$1" = "all" ]]; then
+			run_all_tests
+		elif [[ "$1" = "-w" ]]; then
+			shift
+			watch_case $@
+		elif [[ "$1" = "-t" ]]; then
+			shift
+			test_num $1
+			test_case $1 $(get_test_count $1)
+		elif [[ "$1" = "-c" ]]; then
+			shift
+			test_num $1
+			test_num $2
+			test_case $1 $2
+		elif [[ "$1" = "-s" ]]; then
+			shift
+			test_case $1 1
+		elif [[ "$1" = "-l" ]]; then
+			list_tests
+		elif [[ "$1" = "-h" || "$1" = "--help" ]]; then
+			usage
+		else
+			usage
+		fi
+	fi
+}
+
+test_reqs
+allow_user_defaults
+check_production_sysctl_writes_strict
+load_req_mod
+
+trap "test_finish" EXIT
+
+parse_args $@
+
+exit 0
-- 
cgit v1.2.3-59-g8ed1b


From 1c0357c846452add7c2c863ec372010e3d2ca943 Mon Sep 17 00:00:00 2001
From: "Luis R. Rodriguez" <mcgrof@kernel.org>
Date: Wed, 12 Jul 2017 14:33:49 -0700
Subject: test_sysctl: test against PAGE_SIZE for int

Add the following tests to ensure we do not regress:

  o Test using a buffer full of space (PAGE_SIZE-1) followed by a
    single digit works

  o Test using a buffer full of spaces (PAGE_SIZE or over) will fail

As tests increase instead of unloading the module and reloading it we
can just do a shell reset_vals() with a reset to values we know are set
at init on the driver.

Link: http://lkml.kernel.org/r/20170630224431.17374-4-mcgrof@kernel.org
Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/sysctl/sysctl.sh | 66 ++++++++++++++++++++++++++++++++
 1 file changed, 66 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh
index cbe1345d7c1d..6ec807576f7c 100644
--- a/tools/testing/selftests/sysctl/sysctl.sh
+++ b/tools/testing/selftests/sysctl/sysctl.sh
@@ -75,6 +75,13 @@ function check_production_sysctl_writes_strict()
 			echo "1" > ${WRITES_STRICT}
 		fi
 	fi
+
+	if [ -z $PAGE_SIZE ]; then
+		PAGE_SIZE=$(getconf PAGESIZE)
+	fi
+	if [ -z $MAX_DIGITS ]; then
+		MAX_DIGITS=$(($PAGE_SIZE/8))
+	fi
 }
 
 test_reqs()
@@ -89,6 +96,10 @@ test_reqs()
 		echo "$0: You need perl installed"
 		exit 1
 	fi
+	if ! which getconf 2> /dev/null > /dev/null; then
+		echo "$0: You need getconf installed"
+		exit 1
+	fi
 }
 
 function load_req_mod()
@@ -103,6 +114,23 @@ function load_req_mod()
 	fi
 }
 
+reset_vals()
+{
+	VAL=""
+	TRIGGER=$(basename ${TARGET})
+	case "$TRIGGER" in
+		int_0001)
+			VAL="60"
+			;;
+		string_0001)
+			VAL="(none)"
+			;;
+		*)
+			;;
+	esac
+	echo -n $VAL > $TARGET
+}
+
 set_orig()
 {
 	if [ ! -z $TARGET ]; then
@@ -229,7 +257,42 @@ run_numerictests()
 	else
 		echo "ok"
 	fi
+	test_rc
+}
+
+# Your test must accept digits 3 and 4 to use this
+run_limit_digit()
+{
+	echo -n "Checking ignoring spaces up to PAGE_SIZE works on write ..."
+	reset_vals
 
+	LIMIT=$((MAX_DIGITS -1))
+	TEST_STR="3"
+	(perl -e 'print " " x '$LIMIT';'; echo "${TEST_STR}") | \
+		dd of="${TARGET}" 2>/dev/null
+
+	if ! verify "${TARGET}"; then
+		echo "FAIL" >&2
+		rc=1
+	else
+		echo "ok"
+	fi
+	test_rc
+
+	echo -n "Checking passing PAGE_SIZE of spaces fails on write ..."
+	reset_vals
+
+	LIMIT=$((MAX_DIGITS))
+	TEST_STR="4"
+	(perl -e 'print " " x '$LIMIT';'; echo "${TEST_STR}") | \
+		dd of="${TARGET}" 2>/dev/null
+
+	if verify "${TARGET}"; then
+		echo "FAIL" >&2
+		rc=1
+	else
+		echo "ok"
+	fi
 	test_rc
 }
 
@@ -305,15 +368,18 @@ run_stringtests()
 sysctl_test_0001()
 {
 	TARGET="${SYSCTL}/int_0001"
+	reset_vals
 	ORIG=$(cat "${TARGET}")
 	TEST_STR=$(( $ORIG + 1 ))
 
 	run_numerictests
+	run_limit_digit
 }
 
 sysctl_test_0002()
 {
 	TARGET="${SYSCTL}/string_0001"
+	reset_vals
 	ORIG=$(cat "${TARGET}")
 	TEST_STR="Testing sysctl"
 	# Only string sysctls support seeking/appending.
-- 
cgit v1.2.3-59-g8ed1b


From eb965eda1cabf26e62afc07a06cdf2fd5aaa2906 Mon Sep 17 00:00:00 2001
From: "Luis R. Rodriguez" <mcgrof@kernel.org>
Date: Wed, 12 Jul 2017 14:33:52 -0700
Subject: test_sysctl: add simple proc_dointvec() case

Test against a simple proc_dointvec() case.  While at it, add a test
against INT_MAX.  Make sure INT_MAX works, and INT_MAX+1 will fail.
Also test negative values work.

Link: http://lkml.kernel.org/r/20170630224431.17374-5-mcgrof@kernel.org
Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 lib/test_sysctl.c                        | 11 ++++++
 tools/testing/selftests/sysctl/sysctl.sh | 62 ++++++++++++++++++++++++++++++++
 2 files changed, 73 insertions(+)

(limited to 'tools')

diff --git a/lib/test_sysctl.c b/lib/test_sysctl.c
index b2163bfb6eb2..1472e1ae4931 100644
--- a/lib/test_sysctl.c
+++ b/lib/test_sysctl.c
@@ -41,11 +41,15 @@ static int i_one_hundred = 100;
 
 struct test_sysctl_data {
 	int int_0001;
+	int int_0002;
+
 	char string_0001[65];
 };
 
 static struct test_sysctl_data test_data = {
 	.int_0001 = 60,
+	.int_0002 = 1,
+
 	.string_0001 = "(none)",
 };
 
@@ -60,6 +64,13 @@ static struct ctl_table test_table[] = {
 		.extra1		= &i_zero,
 		.extra2         = &i_one_hundred,
 	},
+	{
+		.procname	= "int_0002",
+		.data		= &test_data.int_0002,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 	{
 		.procname	= "string_0001",
 		.data		= &test_data.string_0001,
diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh
index 6ec807576f7c..7ba3fa2bbd54 100644
--- a/tools/testing/selftests/sysctl/sysctl.sh
+++ b/tools/testing/selftests/sysctl/sysctl.sh
@@ -31,6 +31,7 @@ TEST_FILE=$(mktemp)
 # we have tons of space.
 ALL_TESTS="0001:1:1"
 ALL_TESTS="$ALL_TESTS 0002:1:1"
+ALL_TESTS="$ALL_TESTS 0003:1:1"
 
 test_modprobe()
 {
@@ -82,6 +83,9 @@ function check_production_sysctl_writes_strict()
 	if [ -z $MAX_DIGITS ]; then
 		MAX_DIGITS=$(($PAGE_SIZE/8))
 	fi
+	if [ -z $INT_MAX ]; then
+		INT_MAX=$(getconf INT_MAX)
+	fi
 }
 
 test_reqs()
@@ -122,6 +126,9 @@ reset_vals()
 		int_0001)
 			VAL="60"
 			;;
+		int_0002)
+			VAL="1"
+			;;
 		string_0001)
 			VAL="(none)"
 			;;
@@ -296,6 +303,48 @@ run_limit_digit()
 	test_rc
 }
 
+# You are using an int
+run_limit_digit_int()
+{
+	echo -n "Testing INT_MAX works ..."
+	reset_vals
+	TEST_STR="$INT_MAX"
+	echo -n $TEST_STR > $TARGET
+
+	if ! verify "${TARGET}"; then
+		echo "FAIL" >&2
+		rc=1
+	else
+		echo "ok"
+	fi
+	test_rc
+
+	echo -n "Testing INT_MAX + 1 will fail as expected..."
+	reset_vals
+	let TEST_STR=$INT_MAX+1
+	echo -n $TEST_STR > $TARGET 2> /dev/null
+
+	if verify "${TARGET}"; then
+		echo "FAIL" >&2
+		rc=1
+	else
+		echo "ok"
+	fi
+	test_rc
+
+	echo -n "Testing negative values will work as expected..."
+	reset_vals
+	TEST_STR="-3"
+	echo -n $TEST_STR > $TARGET 2> /dev/null
+	if ! verify "${TARGET}"; then
+		echo "FAIL" >&2
+		rc=1
+	else
+		echo "ok"
+	fi
+	test_rc
+}
+
 run_stringtests()
 {
 	echo -n "Writing entire sysctl in short writes ... "
@@ -389,6 +438,18 @@ sysctl_test_0002()
 	run_stringtests
 }
 
+sysctl_test_0003()
+{
+	TARGET="${SYSCTL}/int_0002"
+	reset_vals
+	ORIG=$(cat "${TARGET}")
+	TEST_STR=$(( $ORIG + 1 ))
+
+	run_numerictests
+	run_limit_digit
+	run_limit_digit_int
+}
+
 list_tests()
 {
 	echo "Test ID list:"
@@ -399,6 +460,7 @@ list_tests()
 	echo
 	echo "0001 x $(get_test_count 0001) - tests proc_dointvec_minmax()"
 	echo "0002 x $(get_test_count 0002) - tests proc_dostring()"
+	echo "0003 x $(get_test_count 0003) - tests proc_dointvec()"
 }
 
 test_reqs
-- 
cgit v1.2.3-59-g8ed1b


From 2920fad3a5d394b66011c7f35c7b05278354055e Mon Sep 17 00:00:00 2001
From: "Luis R. Rodriguez" <mcgrof@kernel.org>
Date: Wed, 12 Jul 2017 14:33:55 -0700
Subject: test_sysctl: add simple proc_douintvec() case

Test against a simple proc_douintvec() case.  While at it, add a test
against UINT_MAX.  Make sure UINT_MAX works, and UINT_MAX+1 will fail
and that negative values are not accepted.

Link: http://lkml.kernel.org/r/20170630224431.17374-6-mcgrof@kernel.org
Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 lib/test_sysctl.c                        | 11 ++++++
 tools/testing/selftests/sysctl/sysctl.sh | 63 ++++++++++++++++++++++++++++++++
 2 files changed, 74 insertions(+)

(limited to 'tools')

diff --git a/lib/test_sysctl.c b/lib/test_sysctl.c
index 1472e1ae4931..53db3513ab08 100644
--- a/lib/test_sysctl.c
+++ b/lib/test_sysctl.c
@@ -43,6 +43,8 @@ struct test_sysctl_data {
 	int int_0001;
 	int int_0002;
 
+	unsigned int uint_0001;
+
 	char string_0001[65];
 };
 
@@ -50,6 +52,8 @@ static struct test_sysctl_data test_data = {
 	.int_0001 = 60,
 	.int_0002 = 1,
 
+	.uint_0001 = 314,
+
 	.string_0001 = "(none)",
 };
 
@@ -71,6 +75,13 @@ static struct ctl_table test_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "uint_0001",
+		.data		= &test_data.uint_0001,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_douintvec,
+	},
 	{
 		.procname	= "string_0001",
 		.data		= &test_data.string_0001,
diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh
index 7ba3fa2bbd54..abeef675a884 100644
--- a/tools/testing/selftests/sysctl/sysctl.sh
+++ b/tools/testing/selftests/sysctl/sysctl.sh
@@ -32,6 +32,7 @@ TEST_FILE=$(mktemp)
 ALL_TESTS="0001:1:1"
 ALL_TESTS="$ALL_TESTS 0002:1:1"
 ALL_TESTS="$ALL_TESTS 0003:1:1"
+ALL_TESTS="$ALL_TESTS 0004:1:1"
 
 test_modprobe()
 {
@@ -86,6 +87,9 @@ function check_production_sysctl_writes_strict()
 	if [ -z $INT_MAX ]; then
 		INT_MAX=$(getconf INT_MAX)
 	fi
+	if [ -z $UINT_MAX ]; then
+		UINT_MAX=$(getconf UINT_MAX)
+	fi
 }
 
 test_reqs()
@@ -129,6 +133,9 @@ reset_vals()
 		int_0002)
 			VAL="1"
 			;;
+		uint_0001)
+			VAL="314"
+			;;
 		string_0001)
 			VAL="(none)"
 			;;
@@ -345,6 +352,49 @@ run_limit_digit_int()
 	test_rc
 }
 
+# You are using an unsigned int
+run_limit_digit_uint()
+{
+	echo -n "Testing UINT_MAX works ..."
+	reset_vals
+	TEST_STR="$UINT_MAX"
+	echo -n $TEST_STR > $TARGET
+
+	if ! verify "${TARGET}"; then
+		echo "FAIL" >&2
+		rc=1
+	else
+		echo "ok"
+	fi
+	test_rc
+
+	echo -n "Testing UINT_MAX + 1 will fail as expected..."
+	reset_vals
+	TEST_STR=$(($UINT_MAX+1))
+	echo -n $TEST_STR > $TARGET 2> /dev/null
+
+	if verify "${TARGET}"; then
+		echo "FAIL" >&2
+		rc=1
+	else
+		echo "ok"
+	fi
+	test_rc
+
+	echo -n "Testing negative values will not work as expected ..."
+	reset_vals
+	TEST_STR="-3"
+	echo -n $TEST_STR > $TARGET 2> /dev/null
+
+	if verify "${TARGET}"; then
+		echo "FAIL" >&2
+		rc=1
+	else
+		echo "ok"
+	fi
+	test_rc
+}
+
 run_stringtests()
 {
 	echo -n "Writing entire sysctl in short writes ... "
@@ -450,6 +500,18 @@ sysctl_test_0003()
 	run_limit_digit_int
 }
 
+sysctl_test_0004()
+{
+	TARGET="${SYSCTL}/uint_0001"
+	reset_vals
+	ORIG=$(cat "${TARGET}")
+	TEST_STR=$(( $ORIG + 1 ))
+
+	run_numerictests
+	run_limit_digit
+	run_limit_digit_uint
+}
+
 list_tests()
 {
 	echo "Test ID list:"
@@ -461,6 +523,7 @@ list_tests()
 	echo "0001 x $(get_test_count 0001) - tests proc_dointvec_minmax()"
 	echo "0002 x $(get_test_count 0002) - tests proc_dostring()"
 	echo "0003 x $(get_test_count 0003) - tests proc_dointvec()"
+	echo "0004 x $(get_test_count 0004) - tests proc_douintvec()"
 }
 
 test_reqs
-- 
cgit v1.2.3-59-g8ed1b


From 7c43a657a4beadeb6d2fe1a00732261e313a807f Mon Sep 17 00:00:00 2001
From: "Luis R. Rodriguez" <mcgrof@kernel.org>
Date: Wed, 12 Jul 2017 14:33:58 -0700
Subject: test_sysctl: test against int proc_dointvec() array support

Add a few initial respective tests for an array:

  o Echoing values separated by spaces works
  o Echoing only first elements will set first elements
  o Confirm PAGE_SIZE limit still applies even if an array is used

Link: http://lkml.kernel.org/r/20170630224431.17374-7-mcgrof@kernel.org
Signed-off-by: Luis R. Rodriguez <mcgrof@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 lib/test_sysctl.c                        | 13 +++++
 tools/testing/selftests/sysctl/sysctl.sh | 89 ++++++++++++++++++++++++++++++++
 2 files changed, 102 insertions(+)

(limited to 'tools')

diff --git a/lib/test_sysctl.c b/lib/test_sysctl.c
index 53db3513ab08..3dd801c1c85b 100644
--- a/lib/test_sysctl.c
+++ b/lib/test_sysctl.c
@@ -42,6 +42,7 @@ static int i_one_hundred = 100;
 struct test_sysctl_data {
 	int int_0001;
 	int int_0002;
+	int int_0003[4];
 
 	unsigned int uint_0001;
 
@@ -52,6 +53,11 @@ static struct test_sysctl_data test_data = {
 	.int_0001 = 60,
 	.int_0002 = 1,
 
+	.int_0003[0] = 0,
+	.int_0003[1] = 1,
+	.int_0003[2] = 2,
+	.int_0003[3] = 3,
+
 	.uint_0001 = 314,
 
 	.string_0001 = "(none)",
@@ -75,6 +81,13 @@ static struct ctl_table test_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "int_0003",
+		.data		= &test_data.int_0003,
+		.maxlen		= sizeof(test_data.int_0003),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 	{
 		.procname	= "uint_0001",
 		.data		= &test_data.uint_0001,
diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh
index abeef675a884..ec232c3cfcaa 100644
--- a/tools/testing/selftests/sysctl/sysctl.sh
+++ b/tools/testing/selftests/sysctl/sysctl.sh
@@ -33,6 +33,7 @@ ALL_TESTS="0001:1:1"
 ALL_TESTS="$ALL_TESTS 0002:1:1"
 ALL_TESTS="$ALL_TESTS 0003:1:1"
 ALL_TESTS="$ALL_TESTS 0004:1:1"
+ALL_TESTS="$ALL_TESTS 0005:3:1"
 
 test_modprobe()
 {
@@ -108,6 +109,10 @@ test_reqs()
 		echo "$0: You need getconf installed"
 		exit 1
 	fi
+	if ! which diff 2> /dev/null > /dev/null; then
+		echo "$0: You need diff installed"
+		exit 1
+	fi
 }
 
 function load_req_mod()
@@ -167,6 +172,12 @@ verify()
 	return 0
 }
 
+verify_diff_w()
+{
+	echo "$TEST_STR" | diff -q -w -u - $1
+	return $?
+}
+
 test_rc()
 {
 	if [[ $rc != 0 ]]; then
@@ -352,6 +363,74 @@ run_limit_digit_int()
 	test_rc
 }
 
+# You used an int array
+run_limit_digit_int_array()
+{
+	echo -n "Testing array works as expected ... "
+	TEST_STR="4 3 2 1"
+	echo -n $TEST_STR > $TARGET
+
+	if ! verify_diff_w "${TARGET}"; then
+		echo "FAIL" >&2
+		rc=1
+	else
+		echo "ok"
+	fi
+	test_rc
+
+	echo -n "Testing skipping trailing array elements works ... "
+	# Do not reset_vals, carry on the values from the last test.
+	# If we only echo in two digits the last two are left intact
+	TEST_STR="100 101"
+	echo -n $TEST_STR > $TARGET
+	# After we echo in, to help diff we need to set on TEST_STR what
+	# we expect the result to be.
+	TEST_STR="100 101 2 1"
+
+	if ! verify_diff_w "${TARGET}"; then
+		echo "FAIL" >&2
+		rc=1
+	else
+		echo "ok"
+	fi
+	test_rc
+
+	echo -n "Testing PAGE_SIZE limit on array works ... "
+	# Do not reset_vals, carry on the values from the last test.
+	# Even if you use an int array, you are still restricted to
+	# MAX_DIGITS, this is a known limitation. Test limit works.
+	LIMIT=$((MAX_DIGITS -1))
+	TEST_STR="9"
+	(perl -e 'print " " x '$LIMIT';'; echo "${TEST_STR}") | \
+		dd of="${TARGET}" 2>/dev/null
+
+	TEST_STR="9 101 2 1"
+	if ! verify_diff_w "${TARGET}"; then
+		echo "FAIL" >&2
+		rc=1
+	else
+		echo "ok"
+	fi
+	test_rc
+
+	echo -n "Testing exceeding PAGE_SIZE limit fails as expected ... "
+	# Do not reset_vals, carry on the values from the last test.
+	# Now go over limit.
+	LIMIT=$((MAX_DIGITS))
+	TEST_STR="7"
+	(perl -e 'print " " x '$LIMIT';'; echo "${TEST_STR}") | \
+		dd of="${TARGET}" 2>/dev/null
+
+	TEST_STR="7 101 2 1"
+	if verify_diff_w "${TARGET}"; then
+		echo "FAIL" >&2
+		rc=1
+	else
+		echo "ok"
+	fi
+	test_rc
+}
+
 # You are using an unsigned int
 run_limit_digit_uint()
 {
@@ -512,6 +591,15 @@ sysctl_test_0004()
 	run_limit_digit_uint
 }
 
+sysctl_test_0005()
+{
+	TARGET="${SYSCTL}/int_0003"
+	reset_vals
+	ORIG=$(cat "${TARGET}")
+
+	run_limit_digit_int_array
+}
+
 list_tests()
 {
 	echo "Test ID list:"
@@ -524,6 +612,7 @@ list_tests()
 	echo "0002 x $(get_test_count 0002) - tests proc_dostring()"
 	echo "0003 x $(get_test_count 0003) - tests proc_dointvec()"
 	echo "0004 x $(get_test_count 0004) - tests proc_douintvec()"
+	echo "0005 x $(get_test_count 0005) - tests proc_douintvec() array"
 }
 
 test_reqs
-- 
cgit v1.2.3-59-g8ed1b


From dcda9b04713c3f6ff0875652924844fae28286ea Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.com>
Date: Wed, 12 Jul 2017 14:36:45 -0700
Subject: mm, tree wide: replace __GFP_REPEAT by __GFP_RETRY_MAYFAIL with more
 useful semantic

__GFP_REPEAT was designed to allow retry-but-eventually-fail semantic to
the page allocator.  This has been true but only for allocations
requests larger than PAGE_ALLOC_COSTLY_ORDER.  It has been always
ignored for smaller sizes.  This is a bit unfortunate because there is
no way to express the same semantic for those requests and they are
considered too important to fail so they might end up looping in the
page allocator for ever, similarly to GFP_NOFAIL requests.

Now that the whole tree has been cleaned up and accidental or misled
usage of __GFP_REPEAT flag has been removed for !costly requests we can
give the original flag a better name and more importantly a more useful
semantic.  Let's rename it to __GFP_RETRY_MAYFAIL which tells the user
that the allocator would try really hard but there is no promise of a
success.  This will work independent of the order and overrides the
default allocator behavior.  Page allocator users have several levels of
guarantee vs.  cost options (take GFP_KERNEL as an example)

 - GFP_KERNEL & ~__GFP_RECLAIM - optimistic allocation without _any_
   attempt to free memory at all. The most light weight mode which even
   doesn't kick the background reclaim. Should be used carefully because
   it might deplete the memory and the next user might hit the more
   aggressive reclaim

 - GFP_KERNEL & ~__GFP_DIRECT_RECLAIM (or GFP_NOWAIT)- optimistic
   allocation without any attempt to free memory from the current
   context but can wake kswapd to reclaim memory if the zone is below
   the low watermark. Can be used from either atomic contexts or when
   the request is a performance optimization and there is another
   fallback for a slow path.

 - (GFP_KERNEL|__GFP_HIGH) & ~__GFP_DIRECT_RECLAIM (aka GFP_ATOMIC) -
   non sleeping allocation with an expensive fallback so it can access
   some portion of memory reserves. Usually used from interrupt/bh
   context with an expensive slow path fallback.

 - GFP_KERNEL - both background and direct reclaim are allowed and the
   _default_ page allocator behavior is used. That means that !costly
   allocation requests are basically nofail but there is no guarantee of
   that behavior so failures have to be checked properly by callers
   (e.g. OOM killer victim is allowed to fail currently).

 - GFP_KERNEL | __GFP_NORETRY - overrides the default allocator behavior
   and all allocation requests fail early rather than cause disruptive
   reclaim (one round of reclaim in this implementation). The OOM killer
   is not invoked.

 - GFP_KERNEL | __GFP_RETRY_MAYFAIL - overrides the default allocator
   behavior and all allocation requests try really hard. The request
   will fail if the reclaim cannot make any progress. The OOM killer
   won't be triggered.

 - GFP_KERNEL | __GFP_NOFAIL - overrides the default allocator behavior
   and all allocation requests will loop endlessly until they succeed.
   This might be really dangerous especially for larger orders.

Existing users of __GFP_REPEAT are changed to __GFP_RETRY_MAYFAIL
because they already had their semantic.  No new users are added.
__alloc_pages_slowpath is changed to bail out for __GFP_RETRY_MAYFAIL if
there is no progress and we have already passed the OOM point.

This means that all the reclaim opportunities have been exhausted except
the most disruptive one (the OOM killer) and a user defined fallback
behavior is more sensible than keep retrying in the page allocator.

[akpm@linux-foundation.org: fix arch/sparc/kernel/mdesc.c]
[mhocko@suse.com: semantic fix]
  Link: http://lkml.kernel.org/r/20170626123847.GM11534@dhcp22.suse.cz
[mhocko@kernel.org: address other thing spotted by Vlastimil]
  Link: http://lkml.kernel.org/r/20170626124233.GN11534@dhcp22.suse.cz
Link: http://lkml.kernel.org/r/20170623085345.11304-3-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Alex Belits <alex.belits@cavium.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Darrick J. Wong <darrick.wong@oracle.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: NeilBrown <neilb@suse.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/DMA-ISA-LPC.txt                |  2 +-
 arch/powerpc/include/asm/book3s/64/pgalloc.h |  2 +-
 arch/powerpc/kvm/book3s_64_mmu_hv.c          |  2 +-
 arch/sparc/kernel/mdesc.c                    |  2 +-
 drivers/mmc/host/wbsd.c                      |  2 +-
 drivers/s390/char/vmcp.c                     |  2 +-
 drivers/target/target_core_transport.c       |  2 +-
 drivers/vhost/net.c                          |  2 +-
 drivers/vhost/scsi.c                         |  2 +-
 drivers/vhost/vsock.c                        |  2 +-
 include/linux/gfp.h                          | 56 +++++++++++++++++++++-------
 include/linux/slab.h                         |  3 +-
 include/trace/events/mmflags.h               |  2 +-
 mm/hugetlb.c                                 |  4 +-
 mm/internal.h                                |  2 +-
 mm/page_alloc.c                              | 14 +++++--
 mm/sparse-vmemmap.c                          |  4 +-
 mm/util.c                                    |  6 +--
 mm/vmalloc.c                                 |  2 +-
 mm/vmscan.c                                  |  8 ++--
 net/core/dev.c                               |  6 +--
 net/core/skbuff.c                            |  2 +-
 net/sched/sch_fq.c                           |  2 +-
 tools/perf/builtin-kmem.c                    |  2 +-
 24 files changed, 86 insertions(+), 47 deletions(-)

(limited to 'tools')

diff --git a/Documentation/DMA-ISA-LPC.txt b/Documentation/DMA-ISA-LPC.txt
index c41331398752..7a065ac4a9d1 100644
--- a/Documentation/DMA-ISA-LPC.txt
+++ b/Documentation/DMA-ISA-LPC.txt
@@ -42,7 +42,7 @@ requirements you pass the flag GFP_DMA to kmalloc.
 
 Unfortunately the memory available for ISA DMA is scarce so unless you
 allocate the memory during boot-up it's a good idea to also pass
-__GFP_REPEAT and __GFP_NOWARN to make the allocator try a bit harder.
+__GFP_RETRY_MAYFAIL and __GFP_NOWARN to make the allocator try a bit harder.
 
 (This scarcity also means that you should allocate the buffer as
 early as possible and not release it until the driver is unloaded.)
diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h
index 20b1485ff1e8..e2329db9d6f4 100644
--- a/arch/powerpc/include/asm/book3s/64/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h
@@ -56,7 +56,7 @@ static inline pgd_t *radix__pgd_alloc(struct mm_struct *mm)
 	return (pgd_t *)__get_free_page(pgtable_gfp_flags(mm, PGALLOC_GFP));
 #else
 	struct page *page;
-	page = alloc_pages(pgtable_gfp_flags(mm, PGALLOC_GFP | __GFP_REPEAT),
+	page = alloc_pages(pgtable_gfp_flags(mm, PGALLOC_GFP | __GFP_RETRY_MAYFAIL),
 				4);
 	if (!page)
 		return NULL;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 710e491206ed..8cb0190e2a73 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -93,7 +93,7 @@ int kvmppc_allocate_hpt(struct kvm_hpt_info *info, u32 order)
 	}
 
 	if (!hpt)
-		hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT
+		hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_RETRY_MAYFAIL
 				       |__GFP_NOWARN, order - PAGE_SHIFT);
 
 	if (!hpt)
diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
index e4b4e790bf89..fa466ce45bc9 100644
--- a/arch/sparc/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
@@ -205,7 +205,7 @@ static struct mdesc_handle *mdesc_kmalloc(unsigned int mdesc_size)
 	handle_size = (sizeof(struct mdesc_handle) -
 		       sizeof(struct mdesc_hdr) +
 		       mdesc_size);
-	base = kmalloc(handle_size + 15, GFP_KERNEL | __GFP_REPEAT);
+	base = kmalloc(handle_size + 15, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 	if (!base)
 		return NULL;
 
diff --git a/drivers/mmc/host/wbsd.c b/drivers/mmc/host/wbsd.c
index e15a9733fcfd..9668616faf16 100644
--- a/drivers/mmc/host/wbsd.c
+++ b/drivers/mmc/host/wbsd.c
@@ -1386,7 +1386,7 @@ static void wbsd_request_dma(struct wbsd_host *host, int dma)
 	 * order for ISA to be able to DMA to it.
 	 */
 	host->dma_buffer = kmalloc(WBSD_DMA_SIZE,
-		GFP_NOIO | GFP_DMA | __GFP_REPEAT | __GFP_NOWARN);
+		GFP_NOIO | GFP_DMA | __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
 	if (!host->dma_buffer)
 		goto free;
 
diff --git a/drivers/s390/char/vmcp.c b/drivers/s390/char/vmcp.c
index 65f5a794f26d..98749fa817da 100644
--- a/drivers/s390/char/vmcp.c
+++ b/drivers/s390/char/vmcp.c
@@ -98,7 +98,7 @@ vmcp_write(struct file *file, const char __user *buff, size_t count,
 	}
 	if (!session->response)
 		session->response = (char *)__get_free_pages(GFP_KERNEL
-						| __GFP_REPEAT | GFP_DMA,
+						| __GFP_RETRY_MAYFAIL | GFP_DMA,
 						get_order(session->bufsize));
 	if (!session->response) {
 		mutex_unlock(&session->mutex);
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index f1b3a46bdcaf..1bdc10651bcd 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -252,7 +252,7 @@ int transport_alloc_session_tags(struct se_session *se_sess,
 	int rc;
 
 	se_sess->sess_cmd_map = kzalloc(tag_num * tag_size,
-					GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+					GFP_KERNEL | __GFP_NOWARN | __GFP_RETRY_MAYFAIL);
 	if (!se_sess->sess_cmd_map) {
 		se_sess->sess_cmd_map = vzalloc(tag_num * tag_size);
 		if (!se_sess->sess_cmd_map) {
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index e3d7ea1288c6..06d044862e58 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -897,7 +897,7 @@ static int vhost_net_open(struct inode *inode, struct file *f)
 	struct sk_buff **queue;
 	int i;
 
-	n = kvmalloc(sizeof *n, GFP_KERNEL | __GFP_REPEAT);
+	n = kvmalloc(sizeof *n, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 	if (!n)
 		return -ENOMEM;
 	vqs = kmalloc(VHOST_NET_VQ_MAX * sizeof(*vqs), GFP_KERNEL);
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index fd6c8b66f06f..ff02a942c4d5 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1404,7 +1404,7 @@ static int vhost_scsi_open(struct inode *inode, struct file *f)
 	struct vhost_virtqueue **vqs;
 	int r = -ENOMEM, i;
 
-	vs = kzalloc(sizeof(*vs), GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+	vs = kzalloc(sizeof(*vs), GFP_KERNEL | __GFP_NOWARN | __GFP_RETRY_MAYFAIL);
 	if (!vs) {
 		vs = vzalloc(sizeof(*vs));
 		if (!vs)
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 3f63e03de8e8..c9de9c41aa97 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -508,7 +508,7 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
 	/* This struct is large and allocation could fail, fall back to vmalloc
 	 * if there is no other way.
 	 */
-	vsock = kvmalloc(sizeof(*vsock), GFP_KERNEL | __GFP_REPEAT);
+	vsock = kvmalloc(sizeof(*vsock), GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 	if (!vsock)
 		return -ENOMEM;
 
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 4c6656f1fee7..bcfb9f7c46f5 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -25,7 +25,7 @@ struct vm_area_struct;
 #define ___GFP_FS		0x80u
 #define ___GFP_COLD		0x100u
 #define ___GFP_NOWARN		0x200u
-#define ___GFP_REPEAT		0x400u
+#define ___GFP_RETRY_MAYFAIL	0x400u
 #define ___GFP_NOFAIL		0x800u
 #define ___GFP_NORETRY		0x1000u
 #define ___GFP_MEMALLOC		0x2000u
@@ -136,26 +136,56 @@ struct vm_area_struct;
  *
  * __GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim.
  *
- * __GFP_REPEAT: Try hard to allocate the memory, but the allocation attempt
- *   _might_ fail.  This depends upon the particular VM implementation.
+ * The default allocator behavior depends on the request size. We have a concept
+ * of so called costly allocations (with order > PAGE_ALLOC_COSTLY_ORDER).
+ * !costly allocations are too essential to fail so they are implicitly
+ * non-failing by default (with some exceptions like OOM victims might fail so
+ * the caller still has to check for failures) while costly requests try to be
+ * not disruptive and back off even without invoking the OOM killer.
+ * The following three modifiers might be used to override some of these
+ * implicit rules
+ *
+ * __GFP_NORETRY: The VM implementation will try only very lightweight
+ *   memory direct reclaim to get some memory under memory pressure (thus
+ *   it can sleep). It will avoid disruptive actions like OOM killer. The
+ *   caller must handle the failure which is quite likely to happen under
+ *   heavy memory pressure. The flag is suitable when failure can easily be
+ *   handled at small cost, such as reduced throughput
+ *
+ * __GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim
+ *   procedures that have previously failed if there is some indication
+ *   that progress has been made else where.  It can wait for other
+ *   tasks to attempt high level approaches to freeing memory such as
+ *   compaction (which removes fragmentation) and page-out.
+ *   There is still a definite limit to the number of retries, but it is
+ *   a larger limit than with __GFP_NORETRY.
+ *   Allocations with this flag may fail, but only when there is
+ *   genuinely little unused memory. While these allocations do not
+ *   directly trigger the OOM killer, their failure indicates that
+ *   the system is likely to need to use the OOM killer soon.  The
+ *   caller must handle failure, but can reasonably do so by failing
+ *   a higher-level request, or completing it only in a much less
+ *   efficient manner.
+ *   If the allocation does fail, and the caller is in a position to
+ *   free some non-essential memory, doing so could benefit the system
+ *   as a whole.
  *
  * __GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller
- *   cannot handle allocation failures. New users should be evaluated carefully
- *   (and the flag should be used only when there is no reasonable failure
- *   policy) but it is definitely preferable to use the flag rather than
- *   opencode endless loop around allocator.
- *
- * __GFP_NORETRY: The VM implementation must not retry indefinitely and will
- *   return NULL when direct reclaim and memory compaction have failed to allow
- *   the allocation to succeed.  The OOM killer is not called with the current
- *   implementation.
+ *   cannot handle allocation failures. The allocation could block
+ *   indefinitely but will never return with failure. Testing for
+ *   failure is pointless.
+ *   New users should be evaluated carefully (and the flag should be
+ *   used only when there is no reasonable failure policy) but it is
+ *   definitely preferable to use the flag rather than opencode endless
+ *   loop around allocator.
+ *   Using this flag for costly allocations is _highly_ discouraged.
  */
 #define __GFP_IO	((__force gfp_t)___GFP_IO)
 #define __GFP_FS	((__force gfp_t)___GFP_FS)
 #define __GFP_DIRECT_RECLAIM	((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */
 #define __GFP_KSWAPD_RECLAIM	((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */
 #define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM))
-#define __GFP_REPEAT	((__force gfp_t)___GFP_REPEAT)
+#define __GFP_RETRY_MAYFAIL	((__force gfp_t)___GFP_RETRY_MAYFAIL)
 #define __GFP_NOFAIL	((__force gfp_t)___GFP_NOFAIL)
 #define __GFP_NORETRY	((__force gfp_t)___GFP_NORETRY)
 
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 04a7f7993e67..41473df6dfb0 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -471,7 +471,8 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags)
  *
  * %__GFP_NOWARN - If allocation fails, don't issue any warnings.
  *
- * %__GFP_REPEAT - If allocation fails initially, try once more before failing.
+ * %__GFP_RETRY_MAYFAIL - Try really hard to succeed the allocation but fail
+ *   eventually.
  *
  * There are other flags available as well, but these are not intended
  * for general use, and so are not documented here. For a full list of
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 10e3663a75a6..8e50d01c645f 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -34,7 +34,7 @@
 	{(unsigned long)__GFP_FS,		"__GFP_FS"},		\
 	{(unsigned long)__GFP_COLD,		"__GFP_COLD"},		\
 	{(unsigned long)__GFP_NOWARN,		"__GFP_NOWARN"},	\
-	{(unsigned long)__GFP_REPEAT,		"__GFP_REPEAT"},	\
+	{(unsigned long)__GFP_RETRY_MAYFAIL,	"__GFP_RETRY_MAYFAIL"},	\
 	{(unsigned long)__GFP_NOFAIL,		"__GFP_NOFAIL"},	\
 	{(unsigned long)__GFP_NORETRY,		"__GFP_NORETRY"},	\
 	{(unsigned long)__GFP_COMP,		"__GFP_COMP"},		\
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 1e516520433d..bc48ee783dd9 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1384,7 +1384,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
 
 	page = __alloc_pages_node(nid,
 		htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE|
-						__GFP_REPEAT|__GFP_NOWARN,
+						__GFP_RETRY_MAYFAIL|__GFP_NOWARN,
 		huge_page_order(h));
 	if (page) {
 		prep_new_huge_page(h, page, nid);
@@ -1525,7 +1525,7 @@ static struct page *__hugetlb_alloc_buddy_huge_page(struct hstate *h,
 {
 	int order = huge_page_order(h);
 
-	gfp_mask |= __GFP_COMP|__GFP_REPEAT|__GFP_NOWARN;
+	gfp_mask |= __GFP_COMP|__GFP_RETRY_MAYFAIL|__GFP_NOWARN;
 	if (nid == NUMA_NO_NODE)
 		nid = numa_mem_id();
 	return __alloc_pages_nodemask(gfp_mask, order, nid, nmask);
diff --git a/mm/internal.h b/mm/internal.h
index 0e4f558412fb..24d88f084705 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -23,7 +23,7 @@
  * hints such as HIGHMEM usage.
  */
 #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\
-			__GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\
+			__GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\
 			__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\
 			__GFP_ATOMIC)
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 64b7d82a9b1a..6d30e914afb6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3284,6 +3284,14 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	/* The OOM killer will not help higher order allocs */
 	if (order > PAGE_ALLOC_COSTLY_ORDER)
 		goto out;
+	/*
+	 * We have already exhausted all our reclaim opportunities without any
+	 * success so it is time to admit defeat. We will skip the OOM killer
+	 * because it is very likely that the caller has a more reasonable
+	 * fallback than shooting a random task.
+	 */
+	if (gfp_mask & __GFP_RETRY_MAYFAIL)
+		goto out;
 	/* The OOM killer does not needlessly kill tasks for lowmem */
 	if (ac->high_zoneidx < ZONE_NORMAL)
 		goto out;
@@ -3413,7 +3421,7 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags,
 	}
 
 	/*
-	 * !costly requests are much more important than __GFP_REPEAT
+	 * !costly requests are much more important than __GFP_RETRY_MAYFAIL
 	 * costly ones because they are de facto nofail and invoke OOM
 	 * killer to move on while costly can fail and users are ready
 	 * to cope with that. 1/4 retries is rather arbitrary but we
@@ -3920,9 +3928,9 @@ retry:
 
 	/*
 	 * Do not retry costly high order allocations unless they are
-	 * __GFP_REPEAT
+	 * __GFP_RETRY_MAYFAIL
 	 */
-	if (costly_order && !(gfp_mask & __GFP_REPEAT))
+	if (costly_order && !(gfp_mask & __GFP_RETRY_MAYFAIL))
 		goto nopage;
 
 	if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags,
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index a56c3989f773..c50b1a14d55e 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -56,11 +56,11 @@ void * __meminit vmemmap_alloc_block(unsigned long size, int node)
 
 		if (node_state(node, N_HIGH_MEMORY))
 			page = alloc_pages_node(
-				node, GFP_KERNEL | __GFP_ZERO | __GFP_REPEAT,
+				node, GFP_KERNEL | __GFP_ZERO | __GFP_RETRY_MAYFAIL,
 				get_order(size));
 		else
 			page = alloc_pages(
-				GFP_KERNEL | __GFP_ZERO | __GFP_REPEAT,
+				GFP_KERNEL | __GFP_ZERO | __GFP_RETRY_MAYFAIL,
 				get_order(size));
 		if (page)
 			return page_address(page);
diff --git a/mm/util.c b/mm/util.c
index 26be6407abd7..6520f2d4a226 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -339,7 +339,7 @@ EXPORT_SYMBOL(vm_mmap);
  * Uses kmalloc to get the memory but if the allocation fails then falls back
  * to the vmalloc allocator. Use kvfree for freeing the memory.
  *
- * Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported. __GFP_REPEAT
+ * Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported. __GFP_RETRY_MAYFAIL
  * is supported only for large (>32kB) allocations, and it should be used only if
  * kmalloc is preferable to the vmalloc fallback, due to visible performance drawbacks.
  *
@@ -367,11 +367,11 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node)
 		kmalloc_flags |= __GFP_NOWARN;
 
 		/*
-		 * We have to override __GFP_REPEAT by __GFP_NORETRY for !costly
+		 * We have to override __GFP_RETRY_MAYFAIL by __GFP_NORETRY for !costly
 		 * requests because there is no other way to tell the allocator
 		 * that we want to fail rather than retry endlessly.
 		 */
-		if (!(kmalloc_flags & __GFP_REPEAT) ||
+		if (!(kmalloc_flags & __GFP_RETRY_MAYFAIL) ||
 				(size <= PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
 			kmalloc_flags |= __GFP_NORETRY;
 	}
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 6016ab079e2b..8698c1c86c4d 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1795,7 +1795,7 @@ fail:
  *	allocator with @gfp_mask flags.  Map them into contiguous
  *	kernel virtual space, using a pagetable protection of @prot.
  *
- *	Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_REPEAT
+ *	Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_RETRY_MAYFAIL
  *	and __GFP_NOFAIL are not supported
  *
  *	Any use of gfp flags outside of GFP_KERNEL should be consulted
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e9210f825219..a1af041930a6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2506,18 +2506,18 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat,
 		return false;
 
 	/* Consider stopping depending on scan and reclaim activity */
-	if (sc->gfp_mask & __GFP_REPEAT) {
+	if (sc->gfp_mask & __GFP_RETRY_MAYFAIL) {
 		/*
-		 * For __GFP_REPEAT allocations, stop reclaiming if the
+		 * For __GFP_RETRY_MAYFAIL allocations, stop reclaiming if the
 		 * full LRU list has been scanned and we are still failing
 		 * to reclaim pages. This full LRU scan is potentially
-		 * expensive but a __GFP_REPEAT caller really wants to succeed
+		 * expensive but a __GFP_RETRY_MAYFAIL caller really wants to succeed
 		 */
 		if (!nr_reclaimed && !nr_scanned)
 			return false;
 	} else {
 		/*
-		 * For non-__GFP_REPEAT allocations which can presumably
+		 * For non-__GFP_RETRY_MAYFAIL allocations which can presumably
 		 * fail without consequence, stop if we failed to reclaim
 		 * any pages from the last SWAP_CLUSTER_MAX number of
 		 * pages that were scanned. This will return to the
diff --git a/net/core/dev.c b/net/core/dev.c
index 02440518dd69..8515f8fe0460 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7384,7 +7384,7 @@ static int netif_alloc_rx_queues(struct net_device *dev)
 
 	BUG_ON(count < 1);
 
-	rx = kvzalloc(sz, GFP_KERNEL | __GFP_REPEAT);
+	rx = kvzalloc(sz, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 	if (!rx)
 		return -ENOMEM;
 
@@ -7424,7 +7424,7 @@ static int netif_alloc_netdev_queues(struct net_device *dev)
 	if (count < 1 || count > 0xffff)
 		return -EINVAL;
 
-	tx = kvzalloc(sz, GFP_KERNEL | __GFP_REPEAT);
+	tx = kvzalloc(sz, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 	if (!tx)
 		return -ENOMEM;
 
@@ -7965,7 +7965,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	/* ensure 32-byte alignment of whole construct */
 	alloc_size += NETDEV_ALIGN - 1;
 
-	p = kvzalloc(alloc_size, GFP_KERNEL | __GFP_REPEAT);
+	p = kvzalloc(alloc_size, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 	if (!p)
 		return NULL;
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 8b11341ed69a..f990eb8b30a9 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4747,7 +4747,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
 
 	gfp_head = gfp_mask;
 	if (gfp_head & __GFP_DIRECT_RECLAIM)
-		gfp_head |= __GFP_REPEAT;
+		gfp_head |= __GFP_RETRY_MAYFAIL;
 
 	*errcode = -ENOBUFS;
 	skb = alloc_skb(header_len, gfp_head);
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 147fde73a0f5..263d16e3219e 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -648,7 +648,7 @@ static int fq_resize(struct Qdisc *sch, u32 log)
 		return 0;
 
 	/* If XPS was setup, we can allocate memory on right NUMA node */
-	array = kvmalloc_node(sizeof(struct rb_root) << log, GFP_KERNEL | __GFP_REPEAT,
+	array = kvmalloc_node(sizeof(struct rb_root) << log, GFP_KERNEL | __GFP_RETRY_MAYFAIL,
 			      netdev_queue_numa_node_read(sch->dev_queue));
 	if (!array)
 		return -ENOMEM;
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 0a8a1c45af87..a1497c516d85 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -643,7 +643,7 @@ static const struct {
 	{ "__GFP_FS",			"F" },
 	{ "__GFP_COLD",			"CO" },
 	{ "__GFP_NOWARN",		"NWR" },
-	{ "__GFP_REPEAT",		"R" },
+	{ "__GFP_RETRY_MAYFAIL",	"R" },
 	{ "__GFP_NOFAIL",		"NF" },
 	{ "__GFP_NORETRY",		"NR" },
 	{ "__GFP_COMP",			"C" },
-- 
cgit v1.2.3-59-g8ed1b