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.

(cherry picked from commit 48b74865c63840b288bd85b4d8743533b73b339b)

diff --git a/NEWS b/NEWS
index 87ab465c5e6a511ca0113a991a77cdf39a8edd7a..6fe6a997e5225c8d9c63d3ae041be18dc61eccf4 100644 (file)
--- a/NEWS
+++ b/NEWS
@@ -137,6 +137,7 @@ The following bugs are resolved with this release:
   [29771] Restore IPC_64 support in sysvipc *ctl functions
   [29776] elf/tst-tlsopt-powerpc fails when compiled with -mcpu=power10
   [29951] time: Set daylight to 1 for matching DST/offset change
+  [29953] x86: Check minimum/maximum of non_temporal_threshold
   [30053] time: strftime %s returns -1 after 2038 on 32 bits systems
 
 \f

diff --git a/sysdeps/x86/dl-cacheinfo.h b/sysdeps/x86/dl-cacheinfo.h
index 8f85f70858413ebe8826b7dd052b9310ced9a78b..87f995b071300c22831dd9190202dfd0679432a4 100644 (file)
--- 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,