For now this builds the C version, for completeness, so
that e.g. lang/ocaml can be configured & built. However,
googling reveals that powerpc does have a "fused multiply add"
instruction, ref.
https://www.ibm.com/docs/en/aix/7.1?topic=set-fmadd-fma-floating-multiply-add-instruction
so this could probably be taken advantage of for a more
optimized version.
to __cerror so if the ptrace syscall fails we can call __cerror again with
the correct %r19 value.
Do this even though the call of __cerror doesn't go via the PLT because
__cerror calls __errno which does.
Analysis and fix from Tom Lane in
port-hppa/56864: hppa: ptrace(2) dumps core when returning an error
I changed the location of where %r19 is stored on the stack to follow the
ABI.
Patch from chs@. Comment explaining the story by me. This patch may
not be optimal -- maybe it would be better in pthread__init, or
better for rtld to call _lwp_unpark after _lwp_park in the contened
case -- but we've tested this version and it's annoying to reproduce,
so let's take this version and worry about testing improvements
later.
This was introduced two years ago when the getrandom/getentropy API
question was still open, and removed because the discussion was
ongoing. Now getentropy is more widely adopted and soon to be in
POSIX. So reintroduce the symbol into libc since we'll be keeping it
anyway. Discussion of details of the semantics, as interpreted by
NetBSD, is ongoing, but the symbol needs to get in before the
netbsd-10 branch. The draft POSIX text is
(https://www.opengroup.org/austin/docs/austin_1110.pdf):
SYNOPSIS
#include <unistd.h>
int getentropy(void *buffer, size_t length);
DESCRIPTION
The getentropy() function shall write length bytes of data
starting at the location pointed to by buffer. The output
shall be unpredictable high quality random data, generated by
a cryptographically secure pseudo-random number
generator. The maximum permitted value for the length
argument is given by the {GETENTROPY_MAX} symbolic constant
defined in <limits.h>.
RETURN VALUES
Upon successful completion, getentropy() shall return 0;
otherwise, -1 shall be retunred and errno set to indicate the
error.
ERRORS
The getentropy() function shall fail if:
[EINVAL] The value of length is greater than
{GETENTROPY_MAX}.
The getentropy() function may fail if:
[ENOSYS] The system does not provide the necessary
source of entropy.
RATIONALE
The getentropy() function is not a cancellation point.
Minor changes from the previous introduction of getentropy into libc:
- Return EINVAL, not EIO, on buflen > 256.
- Define GETENTROPY_MAX in limits.h.
The declaration of getentropy in unistd.h and definition of
GETENTROPY_MAX in limits.h are currently conditional on
_NETBSD_SOURCE. When the next revision of POSIX is finalized, we can
expose them also under _POSIX_C_SOURCE > 20yymmL as usual -- and this
can be done as a pullup without breaking existing compiled programs.
strictly-aligned versions of memcmp(3), bcopy(3), memcpy(3), and
memmove(3).
This is used for 403 by ld.so.conf with machdep.no_unaligned variable.
With this library, unaligned memory accesses are significantly reduced
for 403 (from several hundreds to few tens per sec under heavy load);
only ld.elf_so (typically few times per fork) and statically-linked
binaries do such access.
with strictly-aligned versions.
Now all 32-bit powerpc ports share the same libc binary.
This change together with the preceding similar change in libkern slightly
improve performance for DHT (ibm4xx/405GP) and RB800 (MPC8533E).
See changes in bytebench scores:
- DHT https://gist.github.com/rokuyama/301063355de9733bea515b84ef574c0a
- RB800 https://gist.github.com/rokuyama/60ad665d367d6d110b79ec44707f39ff
Improvements may be negligible, but this does not cause performance
regressions at least.
This hack was for 403, but unaligned memory access is now emulated by
kernel. This should result in serious performance regression for 403.
We will provide strictly-aligned versions by ld.so.conf.
Seen on netbsd-9 built xscreensaver running on a current system.
Whatever triggered this should also be fixed, but in the meantime
we can improve the behaviour from "Segmentation Fault"
PR toolchain/56771
Fix profiling on CPUs that do not support unaligned memory access;
Allocate objects (referenced from struct gmonparam) with proper
alignments.
For monstartup(), objects are allocated on heap. Break is not
guaranteed to be aligned at all, unlike stack pointer.
For _m_gmon_alloc(), objects are allocated on anonymous memory.
p->tos is not aligned properly in general.
This fixes quasi-random crashes for *_profile tests, at least on
SH-4 and PowerPC 403 [1]. Also, no regression is observed for
others as far as I can see.
This change does not cause any ABI breakage, as long as application
uses proper pointers; use p->tos instead of evil pointer arithmetic
like (struct tostruct *)((char *)p->froms + p->fromssize) [2].
[1] Timeout should be increased for some tests. "pic" variants
still fail as expected. Dynamically-linked binaries also crash in
rtld for SH-4, but this seems different problem...
[2] This example did not work even before, since the order of
froms[] and tos[] is reversed depending on which of monstartup() or
_m_gmon_alloc() is used for allocation.
wiz