Netdev Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Luis Chamberlain <mcgrof@kernel.org>
To: gregkh@linuxfoundation.org, tj@kernel.org, shuah@kernel.org,
	akpm@linux-foundation.org, rafael@kernel.org,
	davem@davemloft.net, kuba@kernel.org, ast@kernel.org,
	andriin@fb.com, daniel@iogearbox.net, atenart@kernel.org,
	alobakin@pm.me, weiwan@google.com, ap420073@gmail.com
Cc: jeyu@kernel.org, ngupta@vflare.org,
	sergey.senozhatsky.work@gmail.com, minchan@kernel.org,
	mcgrof@kernel.org, axboe@kernel.dk, mbenes@suse.com,
	jpoimboe@redhat.com, tglx@linutronix.de, keescook@chromium.org,
	jikos@kernel.org, rostedt@goodmis.org, peterz@infradead.org,
	linux-block@vger.kernel.org, netdev@vger.kernel.org,
	linux-kselftest@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH v2 3/4] test_sysfs: add support to use kernfs failure injection
Date: Fri,  2 Jul 2021 17:46:31 -0700	[thread overview]
Message-ID: <20210703004632.621662-4-mcgrof@kernel.org> (raw)
In-Reply-To: <20210703004632.621662-1-mcgrof@kernel.org>

This extends test_sysfs with support for using the failure injection
wait completion and knobs to force a few race conditions which
demonstrates that kernfs active reference protection is sufficient
for kobject / device protection at higher layers.

This adds 4 new tests which tries to remove the device attribute
store operation in 4 different situations:

  1) at the start of kernfs_kernfs_fop_write_iter()
  2) before the of->mutex is held in kernfs_kernfs_fop_write_iter()
  3) after the of->mutex is held in kernfs_kernfs_fop_write_iter()
  4) after the kernfs node active reference is taken

A write fails in call cases.

No null dereferences are reproduced, even though this has been observed
in some complex testing cases [0]. If this issue really exists we should
have enough tools on the sysfs_test toolbox now to try to reproduce
this easily without having to poke around other drivers.

[0] https://lkml.kernel.org/r/20210623215007.862787-1-mcgrof@kernel.org

Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
 lib/Kconfig.debug                      |   3 +
 lib/test_sysfs.c                       |  31 +++++
 tools/testing/selftests/sysfs/config   |   3 +
 tools/testing/selftests/sysfs/sysfs.sh | 174 +++++++++++++++++++++++++
 4 files changed, 211 insertions(+)

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 7dbfbfbd3cfc..717bc367a9db 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2373,6 +2373,9 @@ config TEST_SYSCTL
 config TEST_SYSFS
 	tristate "sysfs test driver"
 	depends on SYSFS
+	select FAULT_INJECTION
+	select FAULT_INJECTION_DEBUG_FS
+	select FAIL_KERNFS_KNOBS
 	help
 	  This builds the "test_sysfs" module. This driver enables to test the
 	  sysfs file system safely without affecting production knobs which
diff --git a/lib/test_sysfs.c b/lib/test_sysfs.c
index bf43016d40b5..f27ec0eab747 100644
--- a/lib/test_sysfs.c
+++ b/lib/test_sysfs.c
@@ -38,6 +38,11 @@
 #include <linux/rtnetlink.h>
 #include <linux/genhd.h>
 #include <linux/blkdev.h>
+#include <linux/kernfs.h>
+
+#ifdef CONFIG_FAIL_KERNFS_KNOBS
+MODULE_IMPORT_NS(KERNFS_DEBUG_PRIVATE);
+#endif
 
 static bool enable_lock;
 module_param(enable_lock, bool_enable_only, 0644);
@@ -82,6 +87,13 @@ static bool enable_verbose_rmmod;
 module_param(enable_verbose_rmmod, bool_enable_only, 0644);
 MODULE_PARM_DESC(enable_verbose_rmmod, "enable verbose print messages on rmmod");
 
+#ifdef CONFIG_FAIL_KERNFS_KNOBS
+static bool enable_completion_on_rmmod;
+module_param(enable_completion_on_rmmod, bool_enable_only, 0644);
+MODULE_PARM_DESC(enable_completion_on_rmmod,
+		 "enable sending a kernfs completion on rmmod");
+#endif
+
 static int sysfs_test_major;
 
 /**
@@ -289,6 +301,12 @@ static ssize_t config_show(struct device *dev,
 			"enable_verbose_writes:\t%s\n",
 			enable_verbose_writes ? "true" : "false");
 
+#ifdef CONFIG_FAIL_KERNFS_KNOBS
+	len += snprintf(buf+len, PAGE_SIZE - len,
+			"enable_completion_on_rmmod:\t%s\n",
+			enable_completion_on_rmmod ? "true" : "false");
+#endif
+
 	test_dev_config_unlock(test_dev);
 
 	return len;
@@ -926,10 +944,23 @@ static int __init test_sysfs_init(void)
 }
 module_init(test_sysfs_init);
 
+#ifdef CONFIG_FAIL_KERNFS_KNOBS
+/* The goal is to race our device removal with a pending kernfs -> store call */
+static void test_sysfs_kernfs_send_completion_rmmod(void)
+{
+	if (!enable_completion_on_rmmod)
+		return;
+	complete(&kernfs_debug_wait_completion);
+}
+#else
+static inline void test_sysfs_kernfs_send_completion_rmmod(void) {}
+#endif
+
 static void __exit test_sysfs_exit(void)
 {
 	if (enable_debugfs)
 		debugfs_remove(debugfs_dir);
+	test_sysfs_kernfs_send_completion_rmmod();
 	if (delay_rmmod_ms)
 		msleep(delay_rmmod_ms);
 	unregister_test_dev_sysfs(first_test_dev);
diff --git a/tools/testing/selftests/sysfs/config b/tools/testing/selftests/sysfs/config
index 9196f452ecd5..2876a229f95b 100644
--- a/tools/testing/selftests/sysfs/config
+++ b/tools/testing/selftests/sysfs/config
@@ -1,2 +1,5 @@
 CONFIG_SYSFS=m
 CONFIG_TEST_SYSFS=m
+CONFIG_FAULT_INJECTION=y
+CONFIG_FAULT_INJECTION_DEBUG_FS=y
+CONFIG_FAIL_KERNFS_KNOBS=y
diff --git a/tools/testing/selftests/sysfs/sysfs.sh b/tools/testing/selftests/sysfs/sysfs.sh
index 681b27579f6f..f27ea61e0e95 100755
--- a/tools/testing/selftests/sysfs/sysfs.sh
+++ b/tools/testing/selftests/sysfs/sysfs.sh
@@ -62,6 +62,10 @@ ALL_TESTS="$ALL_TESTS 0025:1:1:test_dev_y:block"
 ALL_TESTS="$ALL_TESTS 0026:1:1:test_dev_y:block"
 ALL_TESTS="$ALL_TESTS 0027:1:0:test_dev_x:block" # deadlock test
 ALL_TESTS="$ALL_TESTS 0028:1:0:test_dev_x:block" # deadlock test with rntl_lock
+ALL_TESTS="$ALL_TESTS 0029:1:1:test_dev_x:block" # kernfs race removal of store
+ALL_TESTS="$ALL_TESTS 0030:1:1:test_dev_x:block" # kernfs race removal before mutex
+ALL_TESTS="$ALL_TESTS 0031:1:1:test_dev_x:block" # kernfs race removal after mutex
+ALL_TESTS="$ALL_TESTS 0032:1:1:test_dev_x:block" # kernfs race removal after active
 
 allow_user_defaults()
 {
@@ -92,6 +96,9 @@ allow_user_defaults()
 	if [ -z $SYSFS_DEBUGFS_DIR ]; then
 		SYSFS_DEBUGFS_DIR="/sys/kernel/debug/test_sysfs"
 	fi
+	if [ -z $KERNFS_DEBUGFS_DIR ]; then
+		KERNFS_DEBUGFS_DIR="/sys/kernel/debug/kernfs"
+	fi
 	if [ -z $PAGE_SIZE ]; then
 		PAGE_SIZE=$(getconf PAGESIZE)
 	fi
@@ -167,6 +174,14 @@ modprobe_reset_enable_rtnl_lock_on_rmmod()
 	unset FIRST_MODPROBE_ARGS
 }
 
+modprobe_reset_enable_completion()
+{
+	FIRST_MODPROBE_ARGS="enable_completion_on_rmmod=1 enable_verbose_writes=1"
+	FIRST_MODPROBE_ARGS="$FIRST_MODPROBE_ARGS enable_verbose_rmmod=1 delay_rmmod_ms=0"
+	modprobe_reset
+	unset FIRST_MODPROBE_ARGS
+}
+
 load_req_mod()
 {
 	modprobe_reset
@@ -197,6 +212,63 @@ debugfs_reset_first_test_dev_ignore_errors()
 	echo -n "1" >"$SYSFS_DEBUGFS_DIR"/reset_first_test_dev
 }
 
+debugfs_kernfs_kernfs_fop_write_iter_exists()
+{
+	KNOB_DIR="${KERNFS_DEBUGFS_DIR}/config_fail_kernfs_fop_write_iter"
+	if [[ ! -d $KNOB_DIR ]]; then
+		echo "kernfs debugfs does not exist $KNOB_DIR"
+		return 0;
+	fi
+	KNOB_DEBUGFS="${KERNFS_DEBUGFS_DIR}/fail_kernfs_fop_write_iter"
+	if [[ ! -d $KNOB_DEBUGFS ]]; then
+		echo -n "kernfs debugfs for coniguring fail_kernfs_fop_write_iter "
+		echo "does not exist $KNOB_DIR"
+		return 0;
+	fi
+	return 1
+}
+
+debugfs_kernfs_kernfs_fop_write_iter_set_fail_once()
+{
+	KNOB_DEBUGFS="${KERNFS_DEBUGFS_DIR}/fail_kernfs_fop_write_iter"
+	echo 1 > $KNOB_DEBUGFS/interval
+	echo 100 > $KNOB_DEBUGFS/probability
+	echo 0 > $KNOB_DEBUGFS/space
+	# Disable verbose messages on the kernel ring buffer which may
+	# confuse developers with a kernel panic.
+	echo 0 > $KNOB_DEBUGFS/verbose
+
+	# Fail only once
+	echo 1 > $KNOB_DEBUGFS/times
+}
+
+debugfs_kernfs_kernfs_fop_write_iter_set_fail_never()
+{
+	KNOB_DEBUGFS="${KERNFS_DEBUGFS_DIR}/fail_kernfs_fop_write_iter"
+	echo 0 > $KNOB_DEBUGFS/times
+}
+
+debugfs_kernfs_set_wait_ms()
+{
+	SLEEP_AFTER_WAIT_MS="${KERNFS_DEBUGFS_DIR}/sleep_after_wait_ms"
+	echo $1 > $SLEEP_AFTER_WAIT_MS
+}
+
+debugfs_kernfs_disable_wait_kernfs_fop_write_iter()
+{
+	ENABLE_WAIT_KNOB="${KERNFS_DEBUGFS_DIR}/config_fail_kernfs_fop_write_iter/wait_"
+	for KNOB in ${ENABLE_WAIT_KNOB}*; do
+		echo 0 > $KNOB
+	done
+}
+
+debugfs_kernfs_enable_wait_kernfs_fop_write_iter()
+{
+	ENABLE_WAIT_KNOB="${KERNFS_DEBUGFS_DIR}/config_fail_kernfs_fop_write_iter/wait_$1"
+	echo -n "1" > $ENABLE_WAIT_KNOB
+	return $?
+}
+
 set_orig()
 {
 	if [[ ! -z $TARGET ]] && [[ ! -z $ORIG ]]; then
@@ -972,6 +1044,104 @@ sysfs_test_0028()
 	fi
 }
 
+sysfs_race_kernfs_kernfs_fop_write_iter()
+{
+	TARGET="${DIR}/$(get_test_target $1)"
+	WAIT_AT=$2
+	EXPECT_WRITE_RETURNS=$3
+	MSDELAY=$4
+
+	modprobe_reset_enable_completion
+	ORIG=$(cat "${TARGET}")
+	TEST_STR=$(( $ORIG + 1 ))
+
+	echo -n "Test racing removal of sysfs store op with kernfs $WAIT_AT ... "
+
+	if debugfs_kernfs_kernfs_fop_write_iter_exists; then
+		echo -n "skipping test as CONFIG_FAIL_KERNFS_KNOBS "
+		echo " or CONFIG_FAULT_INJECTION_DEBUG_FS is disabled"
+		return $ksft_skip
+	fi
+
+	# Allow for failing the kernfs_kernfs_fop_write_iter call once,
+	# we'll provide exact context shortly afterwards.
+	debugfs_kernfs_kernfs_fop_write_iter_set_fail_once
+
+	# First disable all waits
+	debugfs_kernfs_disable_wait_kernfs_fop_write_iter
+
+	# Enable a wait_for_completion(&kernfs_debug_wait_completion) at the
+	# specified location inside the kernfs_fop_write_iter() routine
+	debugfs_kernfs_enable_wait_kernfs_fop_write_iter $WAIT_AT
+
+	# Configure kernfs so that after its wait_for_completion() it
+	# will msleep() this amount of time and schedule(). We figure this
+	# will be sufficient time to allow for our module removal to complete.
+	debugfs_kernfs_set_wait_ms $MSDELAY
+
+	# Now we trigger a kernfs write op, which will run kernfs_fop_write_iter,
+	# but will wait until our driver sends a respective completion
+	set_test_ignore_errors &
+	write_pid=$!
+
+	# At this point kernfs_fop_write_iter() hasn't run our op, its
+	# waiting for our completion at the specified time $WAIT_AT.
+	# We now remove our module which will send a
+	# complete(&kernfs_debug_wait_completion) right before we deregister
+	# our device and the sysfs device attributes are removed.
+	#
+	# After the completion is sent, the test_sysfs driver races with
+	# kernfs to do the device deregistration with the kernfs msleep
+	# and schedule(). This should mean we've forced trying to remove the
+	# module prior to allowing kernfs to run our store operation. If the
+	# race did happen we'll panic with a null dereference on the store op.
+	#
+	# If no race happens we should see no write operation triggered.
+	modprobe -r $TEST_DRIVER > /dev/null 2>&1
+
+	debugfs_kernfs_kernfs_fop_write_iter_set_fail_never
+
+	wait $write_pid
+	if [[ $? -eq $EXPECT_WRITE_RETURNS ]]; then
+		echo "ok"
+	else
+		echo "FAIL" >&2
+	fi
+}
+
+sysfs_test_0029()
+{
+	for delay in 0 2 4 8 16 32 64 128 246 512 1024; do
+		echo "Using delay-after-completion: $delay"
+		sysfs_race_kernfs_kernfs_fop_write_iter 0029 at_start 1 $delay
+	done
+}
+
+sysfs_test_0030()
+{
+	for delay in 0 2 4 8 16 32 64 128 246 512 1024; do
+		echo "Using delay-after-completion: $delay"
+		sysfs_race_kernfs_kernfs_fop_write_iter 0030 before_mutex 1 $delay
+	done
+}
+
+sysfs_test_0031()
+{
+	for delay in 0 2 4 8 16 32 64 128 246 512 1024; do
+		echo "Using delay-after-completion: $delay"
+		sysfs_race_kernfs_kernfs_fop_write_iter 0031 after_mutex 1 $delay
+	done
+}
+
+# Even if we get the active reference the write fails
+sysfs_test_0032()
+{
+	for delay in 0 2 4 8 16 32 64 128 246 512 1024; do
+		echo "Using delay-after-completion: $delay"
+		sysfs_race_kernfs_kernfs_fop_write_iter 0032 after_active 1 $delay
+	done
+}
+
 test_gen_desc()
 {
 	echo -n "$1 x $(get_test_count $1)"
@@ -1013,6 +1183,10 @@ list_tests()
 	echo "$(test_gen_desc 0026) - block test writing y larger delay and resetting device"
 	echo "$(test_gen_desc 0027) - test rmmod deadlock while writing x ... "
 	echo "$(test_gen_desc 0028) - test rmmod deadlock using rtnl_lock while writing x ..."
+	echo "$(test_gen_desc 0029) - racing removal of store op with kernfs at start"
+	echo "$(test_gen_desc 0030) - racing removal of store op with kernfs before mutex"
+	echo "$(test_gen_desc 0031) - racing removal of store op with kernfs after mutex"
+	echo "$(test_gen_desc 0032) - racing removal of store op with kernfs after active"
 }
 
 usage()
-- 
2.27.0


  parent reply	other threads:[~2021-07-03  0:47 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-03  0:46 [PATCH v2 0/4] selftests: add a new test driver for sysfs Luis Chamberlain
2021-07-03  0:46 ` [PATCH v2 1/4] selftests: add tests_sysfs module Luis Chamberlain
2021-07-21 11:32   ` Greg KH
2021-07-22 22:34     ` Luis Chamberlain
2021-07-23 10:38       ` Greg KH
2021-07-23 17:32         ` Luis Chamberlain
2021-07-03  0:46 ` [PATCH v2 2/4] kernfs: add initial failure injection support Luis Chamberlain
2021-07-03  0:46 ` Luis Chamberlain [this message]
2021-07-03  0:46 ` [PATCH v2 4/4] test_sysfs: demonstrate deadlock fix Luis Chamberlain
2021-07-03  4:49   ` Greg KH
2021-07-03 17:28     ` Luis Chamberlain
2021-07-21 11:33       ` Greg KH
2021-07-22 22:36         ` Luis Chamberlain

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210703004632.621662-4-mcgrof@kernel.org \
    --to=mcgrof@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=alobakin@pm.me \
    --cc=andriin@fb.com \
    --cc=ap420073@gmail.com \
    --cc=ast@kernel.org \
    --cc=atenart@kernel.org \
    --cc=axboe@kernel.dk \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=gregkh@linuxfoundation.org \
    --cc=jeyu@kernel.org \
    --cc=jikos@kernel.org \
    --cc=jpoimboe@redhat.com \
    --cc=keescook@chromium.org \
    --cc=kuba@kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=mbenes@suse.com \
    --cc=minchan@kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=ngupta@vflare.org \
    --cc=peterz@infradead.org \
    --cc=rafael@kernel.org \
    --cc=rostedt@goodmis.org \
    --cc=sergey.senozhatsky.work@gmail.com \
    --cc=shuah@kernel.org \
    --cc=tglx@linutronix.de \
    --cc=tj@kernel.org \
    --cc=weiwan@google.com \
    --subject='Re: [PATCH v2 3/4] test_sysfs: add support to use kernfs failure injection' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).