This is the mail archive of the libc-alpha@sourceware.org mailing list for the glibc project.
| Index Nav: | [Date Index] [Subject Index] [Author Index] [Thread Index] | |
|---|---|---|
| Message Nav: | [Date Prev] [Date Next] | [Thread Prev] [Thread Next] |
| Other format: | [Raw text] | |
On 05/22/2018 04:12 PM, Andreas Schwab wrote:
On Mai 22 2018, Florian Weimer <fweimer@redhat.com> wrote:My test machine had an L2 cache size of 1 MiB.Then you should be safe, a 64K mempcpy is enough to trigger it.
Our memcpy has:
L(512bytesormore):
#ifdef SHARED_CACHE_SIZE_HALF
mov $SHARED_CACHE_SIZE_HALF, %r8
#else
mov __x86_64_shared_cache_size_half(%rip), %r8
#endif
cmp %r8, %rdx
jae L(preloop_large)
cmp $1024, %rdx
ja L(1024bytesormore)
And with the original reproducer, we wouldn't hit preloop_large, where
the bug is.
Thanks, Florian
| Index Nav: | [Date Index] [Subject Index] [Author Index] [Thread Index] | |
|---|---|---|
| Message Nav: | [Date Prev] [Date Next] | [Thread Prev] [Thread Next] |