public inbox for glibc-cvs@sourceware.org
help / color / mirror / Atom feed
From: H.J. Lu <hjl@sourceware.org>
To: glibc-cvs@sourceware.org
Subject: [glibc] x86: Check minimum/maximum of non_temporal_threshold [BZ #29953]
Date: Tue,  3 Jan 2023 21:58:27 +0000 (GMT)	[thread overview]
Message-ID: <20230103215827.4FEE43858404@sourceware.org> (raw)

https://sourceware.org/git/gitweb.cgi?p=glibc.git;h=48b74865c63840b288bd85b4d8743533b73b339b

commit 48b74865c63840b288bd85b4d8743533b73b339b
Author: H.J. Lu <hjl.tools@gmail.com>
Date:   Tue Jan 3 13:06:48 2023 -0800

    x86: Check minimum/maximum of non_temporal_threshold [BZ #29953]
    
    The minimum non_temporal_threshold is 0x4040.  non_temporal_threshold may
    be set to less than the minimum value when the shared cache size isn't
    available (e.g., in an emulator) or by the tunable.  Add checks for
    minimum and maximum of non_temporal_threshold.
    
    This fixes BZ #29953.

Diff:
---
 sysdeps/x86/dl-cacheinfo.h | 25 ++++++++++++++++---------
 1 file changed, 16 insertions(+), 9 deletions(-)

diff --git a/sysdeps/x86/dl-cacheinfo.h b/sysdeps/x86/dl-cacheinfo.h
index e9f3382108..637b5a022d 100644
--- a/sysdeps/x86/dl-cacheinfo.h
+++ b/sysdeps/x86/dl-cacheinfo.h
@@ -861,6 +861,18 @@ dl_init_cacheinfo (struct cpu_features *cpu_features)
      share of the cache, it has a substantial risk of negatively
      impacting the performance of other threads running on the chip. */
   unsigned long int non_temporal_threshold = shared * 3 / 4;
+  /* SIZE_MAX >> 4 because memmove-vec-unaligned-erms right-shifts the value of
+     'x86_non_temporal_threshold' by `LOG_4X_MEMCPY_THRESH` (4) and it is best
+     if that operation cannot overflow. Minimum of 0x4040 (16448) because the
+     L(large_memset_4x) loops need 64-byte to cache align and enough space for
+     at least 1 iteration of 4x PAGE_SIZE unrolled loop.  Both values are
+     reflected in the manual.  */
+  unsigned long int maximum_non_temporal_threshold = SIZE_MAX >> 4;
+  unsigned long int minimum_non_temporal_threshold = 0x4040;
+  if (non_temporal_threshold < minimum_non_temporal_threshold)
+    non_temporal_threshold = minimum_non_temporal_threshold;
+  else if (non_temporal_threshold > maximum_non_temporal_threshold)
+    non_temporal_threshold = maximum_non_temporal_threshold;
 
 #if HAVE_TUNABLES
   /* NB: The REP MOVSB threshold must be greater than VEC_SIZE * 8.  */
@@ -915,8 +927,8 @@ dl_init_cacheinfo (struct cpu_features *cpu_features)
     shared = tunable_size;
 
   tunable_size = TUNABLE_GET (x86_non_temporal_threshold, long int, NULL);
-  /* NB: Ignore the default value 0.  */
-  if (tunable_size != 0)
+  if (tunable_size > minimum_non_temporal_threshold
+      && tunable_size <= maximum_non_temporal_threshold)
     non_temporal_threshold = tunable_size;
 
   tunable_size = TUNABLE_GET (x86_rep_movsb_threshold, long int, NULL);
@@ -931,14 +943,9 @@ dl_init_cacheinfo (struct cpu_features *cpu_features)
 
   TUNABLE_SET_WITH_BOUNDS (x86_data_cache_size, data, 0, SIZE_MAX);
   TUNABLE_SET_WITH_BOUNDS (x86_shared_cache_size, shared, 0, SIZE_MAX);
-  /* SIZE_MAX >> 4 because memmove-vec-unaligned-erms right-shifts the value of
-     'x86_non_temporal_threshold' by `LOG_4X_MEMCPY_THRESH` (4) and it is best
-     if that operation cannot overflow. Minimum of 0x4040 (16448) because the
-     L(large_memset_4x) loops need 64-byte to cache align and enough space for
-     at least 1 iteration of 4x PAGE_SIZE unrolled loop.  Both values are
-     reflected in the manual.  */
   TUNABLE_SET_WITH_BOUNDS (x86_non_temporal_threshold, non_temporal_threshold,
-			   0x4040, SIZE_MAX >> 4);
+			   minimum_non_temporal_threshold,
+			   maximum_non_temporal_threshold);
   TUNABLE_SET_WITH_BOUNDS (x86_rep_movsb_threshold, rep_movsb_threshold,
 			   minimum_rep_movsb_threshold, SIZE_MAX);
   TUNABLE_SET_WITH_BOUNDS (x86_rep_stosb_threshold, rep_stosb_threshold, 1,

                 reply	other threads:[~2023-01-03 21:58 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

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=20230103215827.4FEE43858404@sourceware.org \
    --to=hjl@sourceware.org \
    --cc=glibc-cvs@sourceware.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 read-only IMAP folder(s) and NNTP newsgroup(s).