linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Andi Kleen <andi@firstfloor.org>
To: tytso@mit.edu
Cc: linux-kernel@vger.kernel.org, Andi Kleen <ak@linux.intel.com>
Subject: [PATCH 2/3] random: Make input to output pool balancing per cpu
Date: Tue,  6 Oct 2015 15:05:39 -0700	[thread overview]
Message-ID: <1444169140-4938-2-git-send-email-andi@firstfloor.org> (raw)
In-Reply-To: <1444169140-4938-1-git-send-email-andi@firstfloor.org>

From: Andi Kleen <ak@linux.intel.com>

The load balancing from input pool to output pools was
essentially unlocked. Before it didn't matter much because
there were only two choices (blocking and non blocking).

But now with the distributed non blocking pools we have
a lot more pools, and unlocked access of the counters
may systematically deprive some nodes from their deserved
entropy.

Turn the round-robin state into per CPU variables
to avoid any possibility of races. This code already
runs with preemption disabled.

v2: Check for non initialized pools.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 drivers/char/random.c | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c
index e7e02c0..a395f783 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -774,15 +774,20 @@ retry:
 		if (entropy_bits > random_write_wakeup_bits &&
 		    r->initialized &&
 		    r->entropy_total >= 2*random_read_wakeup_bits) {
-			static struct entropy_store *last = &blocking_pool;
-			static int next_pool = -1;
-			struct entropy_store *other = &blocking_pool;
+			static DEFINE_PER_CPU(struct entropy_store *, lastp) =
+				&blocking_pool;
+			static DEFINE_PER_CPU(int, next_pool);
+			struct entropy_store *other = &blocking_pool, *last;
+			int np;
 
 			/* -1: use blocking pool, 0<=max_node: node nb pool */
-			if (next_pool > -1)
-				other = nonblocking_node_pool[next_pool];
-			if (++next_pool >= num_possible_nodes())
-				next_pool = -1;
+			np = __this_cpu_read(next_pool);
+			if (np > -1 && nonblocking_node_pool)
+				other = nonblocking_node_pool[np];
+			if (++np >= num_possible_nodes())
+				np = -1;
+			__this_cpu_write(next_pool, np);
+			last = __this_cpu_read(lastp);
 			if (other->entropy_count <=
 			    3 * other->poolinfo->poolfracbits / 4)
 				last = other;
@@ -791,6 +796,7 @@ retry:
 				schedule_work(&last->push_work);
 				r->entropy_total = 0;
 			}
+			__this_cpu_write(lastp, last);
 		}
 	}
 }
-- 
2.4.3


  reply	other threads:[~2015-10-06 22:05 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-10-06 22:05 [PATCH 1/3] Make /dev/urandom scalable Andi Kleen
2015-10-06 22:05 ` Andi Kleen [this message]
2015-10-06 22:18   ` [PATCH 2/3] random: Make input to output pool balancing per cpu kbuild test robot
2015-10-06 22:05 ` [PATCH 3/3] random: Add pool name to urandom_read trace point Andi Kleen
  -- strict thread matches above, loose matches on Subject: below --
2016-03-01  5:17 [PATCH 1/3] Make /dev/urandom scalable Andi Kleen
2016-03-01  5:17 ` [PATCH 2/3] random: Make input to output pool balancing per cpu Andi Kleen
2016-02-10 23:01 Scalable random patchkit revisited Andi Kleen
2016-02-10 23:01 ` [PATCH 2/3] random: Make input to output pool balancing per cpu Andi Kleen
2016-02-10 23:21   ` kbuild test robot
2016-02-10 23:36   ` kbuild test robot
2015-09-24 17:19 Updated scalable urandom patchkit Andi Kleen
2015-09-24 17:19 ` [PATCH 2/3] random: Make input to output pool balancing per cpu Andi Kleen
2015-09-22 23:16 [PATCH 1/3] Make /dev/urandom scalable Andi Kleen
2015-09-22 23:16 ` [PATCH 2/3] random: Make input to output pool balancing per cpu Andi Kleen

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=1444169140-4938-2-git-send-email-andi@firstfloor.org \
    --to=andi@firstfloor.org \
    --cc=ak@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=tytso@mit.edu \
    /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;
as well as URLs for NNTP newsgroup(s).