mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Andrew Morton <akpm@osdl.org>
To: davidm@hpl.hp.com
Cc: davidm@napali.hpl.hp.com, mpm@selenic.com, linux-kernel@vger.kernel.org
Subject: Re: Fw: potential /dev/urandom scalability improvement
Date: Thu, 25 Mar 2004 18:00:14 -0800	[thread overview]
Message-ID: <20040325180014.29e40b65.akpm@osdl.org> (raw)
In-Reply-To: <16483.35656.864787.827149@napali.hpl.hp.com>

David Mosberger <davidm@napali.hpl.hp.com> wrote:
>
> The
>  patch below is updated to go on top of your patch and gives about the
>  same performance as I reported yesterday.  For now, I defined an
>  inline prefetch_range().  If and when all architectures get updated to
>  define this directly, we can simply remove prefetch_range() from the
>  driver.

We may as well stick prefetch_range() in prefetch.h.

And Matt's patch series is not a thing I want to take on board at present,
so let's stick with the straight scalability patch for now.

I moved the prefetch_range() call to outside the spinlock.  Does that make
sense?

 25-akpm/drivers/char/random.c    |   51 ++++++++++++++++++++++++++-------------
 25-akpm/include/linux/prefetch.h |   11 ++++++++
 2 files changed, 46 insertions(+), 16 deletions(-)

diff -puN drivers/char/random.c~urandom-scalability-fix drivers/char/random.c
--- 25/drivers/char/random.c~urandom-scalability-fix	2004-03-25 17:53:57.498675480 -0800
+++ 25-akpm/drivers/char/random.c	2004-03-25 17:57:39.795881168 -0800
@@ -490,12 +490,15 @@ static inline __u32 int_ln_12bits(__u32 
  **********************************************************************/
 
 struct entropy_store {
+	/* mostly-read data: */
+	struct poolinfo poolinfo;
+	__u32		*pool;
+
+	/* read-write data: */
+	spinlock_t lock ____cacheline_aligned;
 	unsigned	add_ptr;
 	int		entropy_count;
 	int		input_rotate;
-	struct poolinfo poolinfo;
-	__u32		*pool;
-	spinlock_t lock;
 };
 
 /*
@@ -571,38 +574,54 @@ static void add_entropy_words(struct ent
 	static __u32 const twist_table[8] = {
 		         0, 0x3b6e20c8, 0x76dc4190, 0x4db26158,
 		0xedb88320, 0xd6d6a3e8, 0x9b64c2b0, 0xa00ae278 };
-	unsigned i;
-	int new_rotate;
+	unsigned long i, add_ptr, tap1, tap2, tap3, tap4, tap5;
+	int new_rotate, input_rotate;
 	int wordmask = r->poolinfo.poolwords - 1;
-	__u32 w;
+	__u32 w, next_w;
 	unsigned long flags;
 
+	/* Taps are constant, so we can load them without holding r->lock.  */
+	tap1 = r->poolinfo.tap1;
+	tap2 = r->poolinfo.tap2;
+	tap3 = r->poolinfo.tap3;
+	tap4 = r->poolinfo.tap4;
+	tap5 = r->poolinfo.tap5;
+	next_w = *in++;
+
+	prefetch_range(r->pool, wordmask);
 	spin_lock_irqsave(&r->lock, flags);
+	input_rotate = r->input_rotate;
+	add_ptr = r->add_ptr;
 
 	while (nwords--) {
-		w = rotate_left(r->input_rotate, *in++);
-		i = r->add_ptr = (r->add_ptr - 1) & wordmask;
+		w = rotate_left(input_rotate, next_w);
+		if (nwords > 0)
+			next_w = *in++;
+		i = add_ptr = (add_ptr - 1) & wordmask;
 		/*
 		 * Normally, we add 7 bits of rotation to the pool.
 		 * At the beginning of the pool, add an extra 7 bits
 		 * rotation, so that successive passes spread the
 		 * input bits across the pool evenly.
 		 */
-		new_rotate = r->input_rotate + 14;
+		new_rotate = input_rotate + 14;
 		if (i)
-			new_rotate = r->input_rotate + 7;
-		r->input_rotate = new_rotate & 31;
+			new_rotate = input_rotate + 7;
+		input_rotate = new_rotate & 31;
 
 		/* XOR in the various taps */
-		w ^= r->pool[(i + r->poolinfo.tap1) & wordmask];
-		w ^= r->pool[(i + r->poolinfo.tap2) & wordmask];
-		w ^= r->pool[(i + r->poolinfo.tap3) & wordmask];
-		w ^= r->pool[(i + r->poolinfo.tap4) & wordmask];
-		w ^= r->pool[(i + r->poolinfo.tap5) & wordmask];
+		w ^= r->pool[(i + tap1) & wordmask];
+		w ^= r->pool[(i + tap2) & wordmask];
+		w ^= r->pool[(i + tap3) & wordmask];
+		w ^= r->pool[(i + tap4) & wordmask];
+		w ^= r->pool[(i + tap5) & wordmask];
 		w ^= r->pool[i];
 		r->pool[i] = (w >> 3) ^ twist_table[w & 7];
 	}
 
+	r->input_rotate = input_rotate;
+	r->add_ptr = add_ptr;
+
 	spin_unlock_irqrestore(&r->lock, flags);
 }
 
diff -puN include/linux/prefetch.h~urandom-scalability-fix include/linux/prefetch.h
--- 25/include/linux/prefetch.h~urandom-scalability-fix	2004-03-25 17:54:27.279148160 -0800
+++ 25-akpm/include/linux/prefetch.h	2004-03-25 17:55:34.456935584 -0800
@@ -54,4 +54,15 @@ static inline void prefetchw(const void 
 #define PREFETCH_STRIDE (4*L1_CACHE_BYTES)
 #endif
 
+static inline void prefetch_range(void *addr, size_t len)
+{
+#ifdef ARCH_HAS_PREFETCH
+	char *cp;
+	char *end = addr + len;
+
+	for (cp = addr; cp < end; cp += PREFETCH_STRIDE)
+		prefetch(cp);
+#endif
+}
+
 #endif

_


  reply	other threads:[~2004-03-26  2:01 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20040325141923.7080c6f0.akpm@osdl.org>
2004-03-25 22:47 ` Matt Mackall
2004-03-26  1:45   ` David Mosberger
2004-03-26  2:00     ` Andrew Morton [this message]
2004-03-26  2:10       ` David Mosberger
2004-03-26  4:07       ` Matt Mackall
2004-03-26  4:19       ` Matt Mackall
2004-03-26  4:51         ` David Mosberger
2004-03-26  5:15           ` Matt Mackall
2004-03-26  5:24             ` David Mosberger
2004-03-26 11:06       ` Dave Jones
2004-03-26 18:08         ` David Mosberger
2004-03-26 18:23           ` Dave Jones
2004-03-26 21:31             ` David Mosberger
2004-03-26 18:49           ` Andrew Morton
2004-03-26 20:25             ` David Mosberger
2004-03-26 20:33               ` Andrew Morton
2004-03-26 20:45                 ` Arjan van de Ven
2004-03-26 21:17                   ` Andrew Morton
2004-03-27  7:44                     ` Arjan van de Ven
2004-03-26 21:12                 ` David Mosberger
     [not found] <1DLZM-8aK-67@gated-at.bofh.it>
     [not found] ` <1DLZM-8aK-65@gated-at.bofh.it>
     [not found]   ` <1DOE1-20o-17@gated-at.bofh.it>
     [not found]     ` <1DOXn-2k7-5@gated-at.bofh.it>
     [not found]       ` <1DXxI-Z7-39@gated-at.bofh.it>
     [not found]         ` <1E467-6KK-17@gated-at.bofh.it>
     [not found]           ` <1E4IT-7f3-21@gated-at.bofh.it>
2004-03-27  1:29             ` Andi Kleen
2004-03-27 15:48               ` Matt Mackall

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=20040325180014.29e40b65.akpm@osdl.org \
    --to=akpm@osdl.org \
    --cc=davidm@hpl.hp.com \
    --cc=davidm@napali.hpl.hp.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mpm@selenic.com \
    /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®