linux-kernel - [PATCH v5 3/7] crypto: SHA1 multibuffer crypto opportunistic flush

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-ID: <1406066975.2970.805.camel@schen9-DESK>
Date:	Tue, 22 Jul 2014 15:09:35 -0700
From:	Tim Chen <tim.c.chen@...ux.intel.com>
To:	Herbert Xu <herbert@...dor.apana.org.au>,
	"H. Peter Anvin" <hpa@...or.com>,
	"David S.Miller" <davem@...emloft.net>,
	Peter Zijlstra <peterz@...radead.org>,
	Ingo Molnar <mingo@...nel.org>
Cc:	Chandramouli Narayanan <mouli@...ux.intel.com>,
	Vinodh Gopal <vinodh.gopal@...el.com>,
	James Guilford <james.guilford@...el.com>,
	Wajdi Feghali <wajdi.k.feghali@...el.com>,
	Tim Chen <tim.c.chen@...ux.intel.com>,
	Jussi Kivilinna <jussi.kivilinna@....fi>,
	Thomas Gleixner <tglx@...utronix.de>,
	Tadeusz Struk <tadeusz.struk@...el.com>, tkhai@...dex.ru,
	linux-crypto@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: [PATCH v5 3/7] crypto: SHA1 multibuffer crypto opportunistic flush

The crypto daemon can take advantage of available cpu
cycles to flush any unfinished jobs if it is the
only task running on the cpu, and there are no more crypto
jobs to process.

Signed-off-by: Tim Chen <tim.c.chen@...ux.intel.com>
---
 crypto/mcryptd.c | 39 ++++++++++++++++++++++++++++++++++++---
 1 file changed, 36 insertions(+), 3 deletions(-)

diff --git a/crypto/mcryptd.c b/crypto/mcryptd.c
index 622d6b4..dbc20d1 100644
--- a/crypto/mcryptd.c
+++ b/crypto/mcryptd.c
@@ -116,9 +116,40 @@ static int mcryptd_enqueue_request(struct mcryptd_queue *queue,
 	return err;
 }
 
-/* Called in workqueue context, do one real cryption work (via
+/*
+ * Try to opportunisticlly flush the partially completed jobs if
+ * crypto daemon is the only task running.
+ */
+static void mcryptd_opportunistic_flush(void)
+{
+	struct mcryptd_flush_list *flist;
+	struct mcryptd_alg_cstate *cstate;
+
+	flist = per_cpu_ptr(mcryptd_flist, smp_processor_id());
+	while (single_task_running()) {
+		mutex_lock(&flist->lock);
+		if (list_empty(&flist->list)) {
+			mutex_unlock(&flist->lock);
+			return;
+		}
+		cstate = list_entry(flist->list.next,
+				struct mcryptd_alg_cstate, flush_list);
+		if (!cstate->flusher_engaged) {
+			mutex_unlock(&flist->lock);
+			return;
+		}
+		list_del(&cstate->flush_list);
+		cstate->flusher_engaged = false;
+		mutex_unlock(&flist->lock);
+		cstate->alg_state->flusher(cstate);
+	}
+}
+
+/*
+ * Called in workqueue context, do one real cryption work (via
  * req->complete) and reschedule itself if there are more work to
- * do. */
+ * do.
+ */
 static void mcryptd_queue_worker(struct work_struct *work)
 {
 	struct mcryptd_cpu_queue *cpu_queue;
@@ -144,8 +175,10 @@ static void mcryptd_queue_worker(struct work_struct *work)
 		preempt_enable();
 		local_bh_enable();
 
-		if (!req)
+		if (!req) {
+			mcryptd_opportunistic_flush();
 			return;
+		}
 
 		if (backlog)
 			backlog->complete(backlog, -EINPROGRESS);
-- 
1.7.11.7



--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/