From: "Theodore Ts'o" <tytso@mit.edu>
To: Linux Kernel Developers List <linux-kernel@vger.kernel.org>
Cc: smueller@chronox.de, herbert@gondor.apana.org.au,
andi@firstfloor.org, sandyinchina@gmail.com,
cryptography@lakedaemon.net, jsd@av8n.com, hpa@zytor.com,
linux-crypto@vger.kernel.org, "Theodore Ts'o" <tytso@mit.edu>
Subject: [PATCH 2/4] random: make /dev/urandom scalable for silly userspace programs
Date: Wed, 4 May 2016 15:25:49 -0400 [thread overview]
Message-ID: <1462389951-29439-3-git-send-email-tytso@mit.edu> (raw)
In-Reply-To: <1462389951-29439-1-git-send-email-tytso@mit.edu>
On a system with a 4 socket (NUMA) system where a large number of
application threads were all trying to read from /dev/urandom, this
can result in the system spending 80% of its time contending on the
global urandom spinlock. The application should have used its own
PRNG, but let's try to help it from running, lemming-like, straight
over the locking cliff.
Reported-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
drivers/char/random.c | 67 +++++++++++++++++++++++++++++++++++++++++++++++----
1 file changed, 62 insertions(+), 5 deletions(-)
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 91d5c2a..b970db6 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -749,6 +749,17 @@ struct crng_state primary_crng = {
};
static DECLARE_WAIT_QUEUE_HEAD(crng_init_wait);
+#ifdef CONFIG_NUMA
+/*
+ * Hack to deal with crazy userspace progams when they are all trying
+ * to access /dev/urandom in parallel. The programs are almost
+ * certainly doing something terribly wrong, but we'll work around
+ * their brain damage.
+ */
+static struct crng_state **crng_node_pool __read_mostly;
+#endif
+
+
static void _initialize_crng(struct crng_state *crng)
{
int i;
@@ -764,11 +775,13 @@ static void _initialize_crng(struct crng_state *crng)
crng->init_time = jiffies - CRNG_RESEED_INTERVAL;
}
+#ifdef CONFIG_NUMA
static void initialize_crng(struct crng_state *crng)
{
_initialize_crng(crng);
spin_lock_init(&crng->lock);
}
+#endif
static int crng_fast_load(__u32 pool[4])
{
@@ -823,19 +836,23 @@ out:
return ret;
}
+static inline void maybe_reseed_primary_crng(void)
+{
+ if (crng_init > 2 &&
+ time_after(jiffies, primary_crng.init_time + CRNG_RESEED_INTERVAL))
+ crng_reseed(&input_pool);
+}
+
static inline void crng_wait_ready(void)
{
wait_event_interruptible(crng_init_wait, crng_ready());
}
-static void extract_crng(__u8 out[CHACHA20_BLOCK_SIZE])
+static void _extract_crng(struct crng_state *crng,
+ __u8 out[CHACHA20_BLOCK_SIZE])
{
unsigned long v, flags;
- struct crng_state *crng = &primary_crng;
- if (crng_init > 2 &&
- time_after(jiffies, crng->init_time + CRNG_RESEED_INTERVAL))
- crng_reseed(&input_pool);
spin_lock_irqsave(&crng->lock, flags);
if (arch_get_random_long(&v))
crng->state[14] ^= v;
@@ -845,6 +862,30 @@ static void extract_crng(__u8 out[CHACHA20_BLOCK_SIZE])
spin_unlock_irqrestore(&crng->lock, flags);
}
+static void extract_crng(__u8 out[CHACHA20_BLOCK_SIZE])
+{
+#ifndef CONFIG_NUMA
+ maybe_reseed_primary_crng();
+ _extract_crng(&primary_crng, out);
+#else
+ int node_id = numa_node_id();
+ struct crng_state *crng = crng_node_pool[node_id];
+
+ if (time_after(jiffies, crng->init_time + CRNG_RESEED_INTERVAL)) {
+ unsigned long flags;
+
+ maybe_reseed_primary_crng();
+ _extract_crng(&primary_crng, out);
+ spin_lock_irqsave(&crng->lock, flags);
+ memcpy(&crng->state[4], out, CHACHA20_KEY_SIZE);
+ crng->state[15] = node_id;
+ crng->init_time = jiffies;
+ spin_unlock_irqrestore(&crng->lock, flags);
+ }
+ _extract_crng(crng, out);
+#endif
+}
+
static ssize_t extract_crng_user(void __user *buf, size_t nbytes)
{
ssize_t ret = 0, i;
@@ -1549,6 +1590,22 @@ static void init_std_data(struct entropy_store *r)
*/
static int rand_initialize(void)
{
+#ifdef CONFIG_NUMA
+ int i;
+ int num_nodes = num_possible_nodes();
+ struct crng_state *crng;
+
+ crng_node_pool = kmalloc(num_nodes * sizeof(void *),
+ GFP_KERNEL|__GFP_NOFAIL);
+
+ for (i=0; i < num_nodes; i++) {
+ crng = kmalloc(sizeof(struct crng_state),
+ GFP_KERNEL | __GFP_NOFAIL);
+ initialize_crng(crng);
+ crng_node_pool[i] = crng;
+
+ }
+#endif
init_std_data(&input_pool);
init_std_data(&blocking_pool);
_initialize_crng(&primary_crng);
--
2.5.0
next prev parent reply other threads:[~2016-05-04 19:26 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-05-04 19:25 [PATCH -v2 0/4] random: replace urandom pool with a CRNG Theodore Ts'o
2016-05-04 19:25 ` [PATCH 1/4] random: replace non-blocking pool with a Chacha20-based CRNG Theodore Ts'o
2016-05-04 20:28 ` Stephan Mueller
2016-05-05 1:10 ` Theodore Ts'o
2016-05-05 12:49 ` Theodore Ts'o
2016-05-04 19:25 ` Theodore Ts'o [this message]
2016-05-04 19:25 ` [PATCH 3/4] random: add interrupt callback to VMBus IRQ handler Theodore Ts'o
2016-05-04 19:25 ` [PATCH 4/4] random: add backtracking protection to the CRNG Theodore Ts'o
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=1462389951-29439-3-git-send-email-tytso@mit.edu \
--to=tytso@mit.edu \
--cc=andi@firstfloor.org \
--cc=cryptography@lakedaemon.net \
--cc=herbert@gondor.apana.org.au \
--cc=hpa@zytor.com \
--cc=jsd@av8n.com \
--cc=linux-crypto@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=sandyinchina@gmail.com \
--cc=smueller@chronox.de \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®