[PATCH v4 3/3] kmod: throttle kmod thread limit

[Luis R. Rodriguez]

If we reach the limit of modprobe_limit threads running the next
request_module() call will fail. The original reason for adding
a kill was to do away with possible issues with in old circumstances
which would create a recursive series of request_module() calls.

We can do better than just be super aggressive and reject calls
once we've reached the limit by simply making pending callers wait
until the threshold has been reduced, and then throttling them in,
one by one.

This throttling enables requests over the kmod concurrent limit to
be processed once a pending request completes. Only the first item
queued up to wait is woken up. The assumption here is once a task
is woken it will have no other option to also kick the queue to check
if there are more pending tasks -- regardless of whether or not it
was successful.

By throttling and processing only max kmod concurrent tasks we ensure
we avoid unexpected fatal request_module() calls, and we keep memory
consumption on module loading to a minimum.

With x86_64 qemu, with 4 cores, 4 GiB of RAM it takes the following run
time to run both tests:

time ./kmod.sh -t 0008
real    0m16.366s
user    0m0.883s
sys     0m8.916s

time ./kmod.sh -t 0009
real    0m50.803s
user    0m0.791s
sys     0m9.852s

Reviewed-by: Petr Mladek <pmladek@xxxxxxxx>
Signed-off-by: Luis R. Rodriguez <mcgrof@xxxxxxxxxx>
---
 kernel/kmod.c                        | 16 +++++++---------
 tools/testing/selftests/kmod/kmod.sh | 24 ++----------------------
 2 files changed, 9 insertions(+), 31 deletions(-)

diff --git a/kernel/kmod.c b/kernel/kmod.c
index ff68198fe83b..6d016c5d97c8 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -68,6 +68,7 @@ static DECLARE_RWSEM(umhelper_sem);
  */
 #define MAX_KMOD_CONCURRENT 50
 static atomic_t kmod_concurrent_max = ATOMIC_INIT(MAX_KMOD_CONCURRENT);
+static DECLARE_WAIT_QUEUE_HEAD(kmod_wq);
 
 /*
 	modprobe_path is set via /proc/sys.
@@ -140,7 +141,6 @@ int __request_module(bool wait, const char *fmt, ...)
 	va_list args;
 	char module_name[MODULE_NAME_LEN];
 	int ret;
-	static int kmod_loop_msg;
 
 	/*
 	 * We don't allow synchronous module loading from async.  Module
@@ -164,14 +164,11 @@ int __request_module(bool wait, const char *fmt, ...)
 		return ret;
 
 	if (atomic_dec_if_positive(&kmod_concurrent_max) < 0) {
-		/* We may be blaming an innocent here, but unlikely */
-		if (kmod_loop_msg < 5) {
-			printk(KERN_ERR
-			       "request_module: runaway loop modprobe %s\n",
-			       module_name);
-			kmod_loop_msg++;
-		}
-		return -ENOMEM;
+		pr_warn_ratelimited("request_module: kmod_concurrent_max (%u) close to 0 (max_modprobes: %u), for module %s, throttling...",
+				    atomic_read(&kmod_concurrent_max),
+				    MAX_KMOD_CONCURRENT, module_name);
+		wait_event_interruptible(kmod_wq,
+					 atomic_dec_if_positive(&kmod_concurrent_max) >= 0);
 	}
 
 	trace_module_request(module_name, wait, _RET_IP_);
@@ -179,6 +176,7 @@ int __request_module(bool wait, const char *fmt, ...)
 	ret = call_modprobe(module_name, wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC);
 
 	atomic_inc(&kmod_concurrent_max);
+	wake_up(&kmod_wq);
 
 	return ret;
 }
diff --git a/tools/testing/selftests/kmod/kmod.sh b/tools/testing/selftests/kmod/kmod.sh
index 10196a62ed09..8cecae9a8bca 100755
--- a/tools/testing/selftests/kmod/kmod.sh
+++ b/tools/testing/selftests/kmod/kmod.sh
@@ -59,28 +59,8 @@ ALL_TESTS="$ALL_TESTS 0004:1:1"
 ALL_TESTS="$ALL_TESTS 0005:10:1"
 ALL_TESTS="$ALL_TESTS 0006:10:1"
 ALL_TESTS="$ALL_TESTS 0007:5:1"
-
-# Disabled tests:
-#
-# 0008 x 150 -  multithreaded - push kmod_concurrent over max_modprobes for request_module()"
-# Current best-effort failure interpretation:
-# Enough module requests get loaded in place fast enough to reach over the
-# max_modprobes limit and trigger a failure -- before we're even able to
-# start processing pending requests.
-ALL_TESTS="$ALL_TESTS 0008:150:0"
-
-# 0009 x 150 - multithreaded - push kmod_concurrent over max_modprobes for get_fs_type()"
-# Current best-effort failure interpretation:
-#
-# get_fs_type() requests modules using aliases as such the optimization in
-# place today to look for already loaded modules will not take effect and
-# we end up requesting a new module to load, this bumps the kmod_concurrent,
-# and in certain circumstances can lead to pushing the kmod_concurrent over
-# the max_modprobe limit.
-#
-# This test fails much easier than test 0008 since the alias optimizations
-# are not in place.
-ALL_TESTS="$ALL_TESTS 0009:150:0"
+ALL_TESTS="$ALL_TESTS 0008:150:1"
+ALL_TESTS="$ALL_TESTS 0009:150:1"
 
 test_modprobe()
 {
-- 
2.11.0