mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
To: Andy Shevchenko <andriy.shevchenko@linux.intel.com>,
	linux-kernel@vger.kernel.org,
	Andrew Morton <akpm@linux-foundation.org>,
	Kees Cook <keescook@chromium.org>
Cc: "Jason A. Donenfeld" <Jason@zx2c4.com>
Subject: [PATCH v3 2/2] minmax: clamp more efficiently by avoiding extra comparison
Date: Mon, 26 Sep 2022 15:34:35 +0200	[thread overview]
Message-ID: <20220926133435.1333846-2-Jason@zx2c4.com> (raw)
In-Reply-To: <20220926133435.1333846-1-Jason@zx2c4.com>

Currently the clamp algorithm does:

    if (val > hi)
        val = hi;
    if (val < lo)
        val = lo;

But since hi > lo by definition, this can be made more efficient with:

    if (val > hi)
        val = hi;
    else if (val < lo)
        val = lo;

So fix up the clamp and clamp_t functions to do this, adding the same
argument checking as for min and min_t.

For simple cases, code generation on x86_64 and aarch64 stay about the
same:

    before:
            cmp     edi, edx
            mov     eax, esi
            cmova   edi, edx
            cmp     edi, esi
            cmovnb  eax, edi
            ret
    after:
            cmp     edi, esi
            mov     eax, edx
            cmovnb  esi, edi
            cmp     edi, edx
            cmovb   eax, esi
            ret

    before:
            cmp     w0, w2
            csel    w8, w0, w2, lo
            cmp     w8, w1
            csel    w0, w8, w1, hi
            ret
    after:
            cmp     w0, w1
            csel    w8, w0, w1, hi
            cmp     w0, w2
            csel    w0, w8, w2, lo
            ret

On MIPS64, however, code generation improves, by removing arithmetic in
the second branch:

    before:
            sltu    $3,$6,$4
            bne     $3,$0,.L2
            move    $2,$6

            move    $2,$4
    .L2:
            sltu    $3,$2,$5
            bnel    $3,$0,.L7
            move    $2,$5

    .L7:
            jr      $31
            nop
    after:
            sltu    $3,$4,$6
            beq     $3,$0,.L13
            move    $2,$6

            sltu    $3,$4,$5
            bne     $3,$0,.L12
            move    $2,$4

    .L13:
            jr      $31
            nop

    .L12:
            jr      $31
            move    $2,$5

For more complex cases with surrounding code, the effects are a bit
more complicated. For example, consider this simplified version of
timestamp_truncate() from fs/inode.c on x86_64:

    struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode)
    {
        struct super_block *sb = inode->i_sb;
        unsigned int gran = sb->s_time_gran;

        t.tv_sec = clamp(t.tv_sec, sb->s_time_min, sb->s_time_max);
        if (t.tv_sec == sb->s_time_max || t.tv_sec == sb->s_time_min)
            t.tv_nsec = 0;
        return t;
    }

    before:
            mov     r8, rdx
            mov     rdx, rsi
            mov     rcx, QWORD PTR [r8]
            mov     rax, QWORD PTR [rcx+8]
            mov     rcx, QWORD PTR [rcx+16]
            cmp     rax, rdi
            mov     r8, rcx
            cmovge  rdi, rax
            cmp     rdi, rcx
            cmovle  r8, rdi
            cmp     rax, r8
            je      .L4
            cmp     rdi, rcx
            jge     .L4
            mov     rax, r8
            ret
    .L4:
            xor     edx, edx
            mov     rax, r8
            ret

    after:
            mov     rax, QWORD PTR [rdx]
            mov     rdx, QWORD PTR [rax+8]
            mov     rax, QWORD PTR [rax+16]
            cmp     rax, rdi
            jg      .L6
            mov     r8, rax
            xor     edx, edx
    .L2:
            mov     rax, r8
            ret
    .L6:
            cmp     rdx, rdi
            mov     r8, rdi
            cmovge  r8, rdx
            cmp     rax, r8
            je      .L4
            xor     eax, eax
            cmp     rdx, rdi
            cmovl   rax, rsi
            mov     rdx, rax
            mov     rax, r8
            ret
    .L4:
            xor     edx, edx
            jmp     .L2

In this case, we actually gain a branch, unfortunately, because the
compiler's replacement axioms no longer as cleanly apply.

So all and all, this change is a bit of a mixed bag.

Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
---
 include/linux/minmax.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/minmax.h b/include/linux/minmax.h
index 293a66ad7830..9e7cc5319676 100644
--- a/include/linux/minmax.h
+++ b/include/linux/minmax.h
@@ -38,7 +38,7 @@
 		__cmp_once(x, y, __UNIQUE_ID(__x), __UNIQUE_ID(__y), op))
 
 #define __clamp(val, lo, hi)							\
-	__cmp(__cmp(val, lo, >), hi, <)
+	((val) >= (hi) ? (hi) : ((val) <= (lo) ? (lo) : (val)))
 
 #define __clamp_once(val, lo, hi, unique_val, unique_lo, unique_hi) ({		\
 		typeof(val) unique_val = (val);					\
-- 
2.37.3


  reply	other threads:[~2022-09-26 15:03 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-09-23 10:06 [PATCH] " Jason A. Donenfeld
2022-09-23 10:35 ` Andy Shevchenko
2022-09-23 10:40   ` Jason A. Donenfeld
2022-09-23 10:48     ` Jason A. Donenfeld
2022-09-23 15:12       ` Andy Shevchenko
2022-09-23 15:13         ` Jason A. Donenfeld
2022-09-23 15:40           ` [PATCH v2] " Jason A. Donenfeld
2022-09-23 16:41             ` Kees Cook
2022-09-23 16:42               ` Jason A. Donenfeld
2022-09-23 16:53               ` Andy Shevchenko
2022-09-23 16:54                 ` Jason A. Donenfeld
2022-09-23 19:47             ` Kees Cook
2022-09-23 22:54             ` Andrew Morton
2022-09-24  0:02               ` Kees Cook
2022-09-24 10:37               ` Jason A. Donenfeld
2022-09-25 16:29                 ` Andrew Morton
2022-09-26 10:00                 ` Andy Shevchenko
2022-09-26 12:23                   ` Jason A. Donenfeld
2022-09-26 13:34                     ` [PATCH v3 1/2] minmax: sanity check constant bounds when clamping Jason A. Donenfeld
2022-09-26 13:34                       ` Jason A. Donenfeld [this message]
2022-09-26 18:30                         ` [PATCH v3 2/2] minmax: clamp more efficiently by avoiding extra comparison Kees Cook
2022-09-26 21:33                           ` Jason A. Donenfeld
2022-09-26 13:46                       ` [PATCH v3 1/2] minmax: sanity check constant bounds when clamping Andy Shevchenko
2022-09-26 18:26                       ` Kees Cook
2022-10-04 13:41                         ` Jason A. Donenfeld
2022-10-04 14:39                           ` Kees Cook
2022-10-04 15:01                             ` Jason A. Donenfeld
2022-09-26 18:30                     ` [PATCH v2] minmax: clamp more efficiently by avoiding extra comparison Kees Cook
2022-09-23 15:10     ` [PATCH] " Andy Shevchenko
2022-09-23 15:11       ` Jason A. Donenfeld

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=20220926133435.1333846-2-Jason@zx2c4.com \
    --to=jason@zx2c4.com \
    --cc=akpm@linux-foundation.org \
    --cc=andriy.shevchenko@linux.intel.com \
    --cc=keescook@chromium.org \
    --cc=linux-kernel@vger.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

all inboxes | Powered by JetHome®