All of lore.kernel.org
 help / color / mirror / Atom feed
From: Eric Dumazet <edumazet@google.com>
To: Noah Goldstein <goldstein.w.n@gmail.com>
Cc: Johannes Berg <johannes@sipsolutions.net>,
	alexanderduyck@fb.com, kbuild-all@lists.01.org,
	open list <linux-kernel@vger.kernel.org>,
	linux-um@lists.infradead.org, lkp@intel.com,
	peterz@infradead.org, X86 ML <x86@kernel.org>
Subject: Re: [tip:x86/core 1/1] arch/x86/um/../lib/csum-partial_64.c:98:12: error: implicit declaration of function 'load_unaligned_zeropad'
Date: Wed, 24 Nov 2021 22:32:21 -0800	[thread overview]
Message-ID: <CANn89iLYHkyaLawrZJYuRETx63c0QWQ0kLGysPbGpWj2+C5Jfw@mail.gmail.com> (raw)
In-Reply-To: <CAFUsyfLz89DrkvTwDTDqNCHVbBzk1QgEKu0+PuwBoF=Y6me7cQ@mail.gmail.com>

On Wed, Nov 24, 2021 at 9:09 PM Noah Goldstein <goldstein.w.n@gmail.com> wrote:
>
>
>
> Although I see slightly worse performance with aligned `buff`  in
> the branch-free approach. Imagine if non-aligned `buff` is that
> uncommon might be better to speculate past the work of `ror`.

Yes, no clear win here removing the conditional (same cost really),
although using a ror32() is removing the from32to16() helper and get
rid of one folding.

I will formally submit this change, thanks !

diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c
index 1eb8f2d11f7c785be624eba315fe9ca7989fd56d..cf4bd3ef66e56c681b3435d43011ece78438376d
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.
@@ -41,6 +31,7 @@ __wsum csum_partial(const void *buff, int len, __wsum sum)
        if (unlikely(odd)) {
                if (unlikely(len == 0))
                        return sum;
+               temp64 = ror32((__force u32)sum, 8);
                temp64 += (*(unsigned char *)buff << 8);
                len--;
                buff++;
@@ -129,10 +120,8 @@ __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);
-       }
+       if (unlikely(odd))
+               result = ror32(result, 8);
        return (__force __wsum)result;
 }
 EXPORT_SYMBOL(csum_partial);

WARNING: multiple messages have this Message-ID (diff)
From: Eric Dumazet <edumazet@google.com>
To: kbuild-all@lists.01.org
Subject: Re: [tip:x86/core 1/1] arch/x86/um/../lib/csum-partial_64.c:98:12: error: implicit declaration of function 'load_unaligned_zeropad'
Date: Wed, 24 Nov 2021 22:32:21 -0800	[thread overview]
Message-ID: <CANn89iLYHkyaLawrZJYuRETx63c0QWQ0kLGysPbGpWj2+C5Jfw@mail.gmail.com> (raw)
In-Reply-To: <CAFUsyfLz89DrkvTwDTDqNCHVbBzk1QgEKu0+PuwBoF=Y6me7cQ@mail.gmail.com>

[-- Attachment #1: Type: text/plain, Size: 1989 bytes --]

On Wed, Nov 24, 2021 at 9:09 PM Noah Goldstein <goldstein.w.n@gmail.com> wrote:
>
>
>
> Although I see slightly worse performance with aligned `buff`  in
> the branch-free approach. Imagine if non-aligned `buff` is that
> uncommon might be better to speculate past the work of `ror`.

Yes, no clear win here removing the conditional (same cost really),
although using a ror32() is removing the from32to16() helper and get
rid of one folding.

I will formally submit this change, thanks !

diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c
index 1eb8f2d11f7c785be624eba315fe9ca7989fd56d..cf4bd3ef66e56c681b3435d43011ece78438376d
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.
@@ -41,6 +31,7 @@ __wsum csum_partial(const void *buff, int len, __wsum sum)
        if (unlikely(odd)) {
                if (unlikely(len == 0))
                        return sum;
+               temp64 = ror32((__force u32)sum, 8);
                temp64 += (*(unsigned char *)buff << 8);
                len--;
                buff++;
@@ -129,10 +120,8 @@ __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);
-       }
+       if (unlikely(odd))
+               result = ror32(result, 8);
        return (__force __wsum)result;
 }
 EXPORT_SYMBOL(csum_partial);

WARNING: multiple messages have this Message-ID (diff)
From: Eric Dumazet <edumazet@google.com>
To: Noah Goldstein <goldstein.w.n@gmail.com>
Cc: Johannes Berg <johannes@sipsolutions.net>,
	alexanderduyck@fb.com, kbuild-all@lists.01.org,
	open list <linux-kernel@vger.kernel.org>,
	linux-um@lists.infradead.org, lkp@intel.com,
	peterz@infradead.org, X86 ML <x86@kernel.org>
Subject: Re: [tip:x86/core 1/1] arch/x86/um/../lib/csum-partial_64.c:98:12: error: implicit declaration of function 'load_unaligned_zeropad'
Date: Wed, 24 Nov 2021 22:32:21 -0800	[thread overview]
Message-ID: <CANn89iLYHkyaLawrZJYuRETx63c0QWQ0kLGysPbGpWj2+C5Jfw@mail.gmail.com> (raw)
In-Reply-To: <CAFUsyfLz89DrkvTwDTDqNCHVbBzk1QgEKu0+PuwBoF=Y6me7cQ@mail.gmail.com>

On Wed, Nov 24, 2021 at 9:09 PM Noah Goldstein <goldstein.w.n@gmail.com> wrote:
>
>
>
> Although I see slightly worse performance with aligned `buff`  in
> the branch-free approach. Imagine if non-aligned `buff` is that
> uncommon might be better to speculate past the work of `ror`.

Yes, no clear win here removing the conditional (same cost really),
although using a ror32() is removing the from32to16() helper and get
rid of one folding.

I will formally submit this change, thanks !

diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c
index 1eb8f2d11f7c785be624eba315fe9ca7989fd56d..cf4bd3ef66e56c681b3435d43011ece78438376d
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.
@@ -41,6 +31,7 @@ __wsum csum_partial(const void *buff, int len, __wsum sum)
        if (unlikely(odd)) {
                if (unlikely(len == 0))
                        return sum;
+               temp64 = ror32((__force u32)sum, 8);
                temp64 += (*(unsigned char *)buff << 8);
                len--;
                buff++;
@@ -129,10 +120,8 @@ __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);
-       }
+       if (unlikely(odd))
+               result = ror32(result, 8);
        return (__force __wsum)result;
 }
 EXPORT_SYMBOL(csum_partial);

_______________________________________________
linux-um mailing list
linux-um@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-um


  reply	other threads:[~2021-11-25  6:35 UTC|newest]

Thread overview: 75+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-11-17 18:45 [tip:x86/core 1/1] arch/x86/um/../lib/csum-partial_64.c:98:12: error: implicit declaration of function 'load_unaligned_zeropad' kernel test robot
2021-11-17 18:45 ` kernel test robot
2021-11-17 18:55 ` Eric Dumazet
2021-11-17 18:55   ` Eric Dumazet
2021-11-17 19:40   ` Eric Dumazet
2021-11-17 19:40     ` Eric Dumazet
2021-11-18 16:00     ` Peter Zijlstra
2021-11-18 16:00       ` Peter Zijlstra
2021-11-18 16:00       ` Peter Zijlstra
2021-11-18 16:26       ` Johannes Berg
2021-11-18 16:26         ` Johannes Berg
2021-11-18 16:26         ` Johannes Berg
2021-11-18 16:57         ` Eric Dumazet
2021-11-18 16:57           ` Eric Dumazet
2021-11-18 16:57           ` Eric Dumazet
2021-11-18 17:02           ` Eric Dumazet
2021-11-18 17:02             ` Eric Dumazet
2021-11-18 17:02             ` Eric Dumazet
2021-11-25  1:58           ` Noah Goldstein
2021-11-25  1:58             ` Noah Goldstein
2021-11-25  1:58             ` Noah Goldstein
2021-11-25  2:56             ` Eric Dumazet
2021-11-25  2:56               ` Eric Dumazet
2021-11-25  2:56               ` Eric Dumazet
2021-11-25  3:41               ` Noah Goldstein
2021-11-25  3:41                 ` Noah Goldstein
2021-11-25  3:41                 ` Noah Goldstein
2021-11-25  4:00                 ` Eric Dumazet
2021-11-25  4:00                   ` Eric Dumazet
2021-11-25  4:00                   ` Eric Dumazet
2021-11-25  4:08                   ` Eric Dumazet
2021-11-25  4:08                     ` Eric Dumazet
2021-11-25  4:08                     ` Eric Dumazet
2021-11-25  4:20                     ` Eric Dumazet
2021-11-25  4:20                       ` Eric Dumazet
2021-11-25  4:20                       ` Eric Dumazet
2021-11-25  4:56                       ` Noah Goldstein
2021-11-25  4:56                         ` Noah Goldstein
2021-11-25  4:56                         ` Noah Goldstein
2021-11-25  5:09                         ` Noah Goldstein
2021-11-25  5:09                           ` Noah Goldstein
2021-11-25  5:09                           ` Noah Goldstein
2021-11-25  6:32                           ` Eric Dumazet [this message]
2021-11-25  6:32                             ` Eric Dumazet
2021-11-25  6:32                             ` Eric Dumazet
2021-11-25  6:45                             ` Eric Dumazet
2021-11-25  6:45                               ` Eric Dumazet
2021-11-25  6:45                               ` Eric Dumazet
2021-11-25  6:49                               ` Noah Goldstein
2021-11-25  6:49                                 ` Noah Goldstein
2021-11-25  6:49                                 ` Noah Goldstein
2021-11-25  6:47                             ` Noah Goldstein
2021-11-25  6:47                               ` Noah Goldstein
2021-11-25  6:47                               ` Noah Goldstein
2021-11-26 17:18                   ` David Laight
2021-11-26 17:18                     ` David Laight
2021-11-26 17:18                     ` David Laight
2021-11-26 18:09                     ` Eric Dumazet
2021-11-26 18:09                       ` Eric Dumazet
2021-11-26 18:09                       ` Eric Dumazet
2021-11-26 22:41                       ` David Laight
2021-11-26 22:41                         ` David Laight
2021-11-26 22:41                         ` David Laight
2021-11-26 23:04                         ` Noah Goldstein
2021-11-26 23:04                           ` Noah Goldstein
2021-11-26 23:04                           ` Noah Goldstein
2021-11-28 18:30                           ` David Laight
2021-11-28 18:30                             ` David Laight
2021-11-28 18:30                             ` David Laight
2021-12-29  6:00       ` Al Viro
2021-12-29  6:00         ` Al Viro
2021-12-29  6:00         ` Al Viro
2022-01-31  2:29         ` Al Viro
2022-01-31  2:29           ` Al Viro
2022-01-31  2:29           ` Al Viro

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=CANn89iLYHkyaLawrZJYuRETx63c0QWQ0kLGysPbGpWj2+C5Jfw@mail.gmail.com \
    --to=edumazet@google.com \
    --cc=alexanderduyck@fb.com \
    --cc=goldstein.w.n@gmail.com \
    --cc=johannes@sipsolutions.net \
    --cc=kbuild-all@lists.01.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-um@lists.infradead.org \
    --cc=lkp@intel.com \
    --cc=peterz@infradead.org \
    --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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.