netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: David Laight <David.Laight@ACULAB.COM>
To: 'Eric Dumazet' <edumazet@google.com>,
	Peter Zijlstra <peterz@infradead.org>
Cc: "'tglx@linutronix.de'" <tglx@linutronix.de>,
	"'mingo@redhat.com'" <mingo@redhat.com>,
	'Borislav Petkov' <bp@alien8.de>,
	"'dave.hansen@linux.intel.com'" <dave.hansen@linux.intel.com>,
	'X86 ML' <x86@kernel.org>, "'hpa@zytor.com'" <hpa@zytor.com>,
	"'alexanderduyck@fb.com'" <alexanderduyck@fb.com>,
	'open list' <linux-kernel@vger.kernel.org>,
	'netdev' <netdev@vger.kernel.org>,
	"'Noah Goldstein'" <goldstein.w.n@gmail.com>
Subject: [PATCH v2] x86/lib: Remove the special case for odd-aligned buffers in csum-partial_64.c
Date: Thu, 6 Jan 2022 14:45:41 +0000	[thread overview]
Message-ID: <e2864e9c5d794c79aa7ee7de4abbfc6d@AcuMS.aculab.com> (raw)

There is no need to special case the very unusual odd-aligned buffers.
They are no worse than 4n+2 aligned buffers.

Signed-off-by: David Laight <david.laight@aculab.com>
Acked-by: Eric Dumazet
---

resend - v1 seems to have got lost :-)

v2: Also delete from32to16()
    Add acked-by from Eric (he sent one at some point)
    Fix possible whitespace error in the last hunk.

The penalty for any misaligned access seems to be minimal.
On an i7-7700 misaligned buffers add 2 or 3 clocks (in 115) to a 512 byte
  checksum.
That is less than 1 clock for each cache line!
That is just measuring the main loop with an lfence prior to rdpmc to
read PERF_COUNT_HW_CPU_CYCLES.

 arch/x86/lib/csum-partial_64.c | 28 ++--------------------------
 1 file changed, 2 insertions(+), 26 deletions(-)

diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c
index 1f8a8f895173..061b1ed74d6a 100644
--- a/arch/x86/lib/csum-partial_64.c
+++ b/arch/x86/lib/csum-partial_64.c
@@ -11,16 +11,6 @@
 #include <asm/checksum.h>
 #include <asm/word-at-a-time.h>
 
-static inline unsigned short from32to16(unsigned a) 
-{
-	unsigned short b = a >> 16; 
-	asm("addw %w2,%w0\n\t"
-	    "adcw $0,%w0\n" 
-	    : "=r" (b)
-	    : "0" (b), "r" (a));
-	return b;
-}
-
 /*
  * Do a checksum on an arbitrary memory area.
  * Returns a 32bit checksum.
@@ -30,22 +20,12 @@ static inline unsigned short from32to16(unsigned a)
  *
  * Still, with CHECKSUM_COMPLETE this is called to compute
  * checksums on IPv6 headers (40 bytes) and other small parts.
- * it's best to have buff aligned on a 64-bit boundary
+ * The penalty for misaligned buff is negligable.
  */
 __wsum csum_partial(const void *buff, int len, __wsum sum)
 {
 	u64 temp64 = (__force u64)sum;
-	unsigned odd, result;
-
-	odd = 1 & (unsigned long) buff;
-	if (unlikely(odd)) {
-		if (unlikely(len == 0))
-			return sum;
-		temp64 = ror32((__force u32)sum, 8);
-		temp64 += (*(unsigned char *)buff << 8);
-		len--;
-		buff++;
-	}
+	unsigned result;
 
 	while (unlikely(len >= 64)) {
 		asm("addq 0*8(%[src]),%[res]\n\t"
@@ -130,10 +110,6 @@ __wsum csum_partial(const void *buff, int len, __wsum sum)
 #endif
 	}
 	result = add32_with_carry(temp64 >> 32, temp64 & 0xffffffff);
-	if (unlikely(odd)) {
-		result = from32to16(result);
-		result = ((result >> 8) & 0xff) | ((result & 0xff) << 8);
-	}
 	return (__force __wsum)result;
 }
 EXPORT_SYMBOL(csum_partial);
-- 
2.17.1

-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)

             reply	other threads:[~2022-01-06 14:45 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-01-06 14:45 David Laight [this message]
2022-01-10 11:49 ` [PATCH v2] x86/lib: Remove the special case for odd-aligned buffers in csum-partial_64.c David Laight

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=e2864e9c5d794c79aa7ee7de4abbfc6d@AcuMS.aculab.com \
    --to=david.laight@aculab.com \
    --cc=alexanderduyck@fb.com \
    --cc=bp@alien8.de \
    --cc=dave.hansen@linux.intel.com \
    --cc=edumazet@google.com \
    --cc=goldstein.w.n@gmail.com \
    --cc=hpa@zytor.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=x86@kernel.org \
    /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).