| Age | Commit message (Collapse) | Author |
|---|
|
|
|
|
|
|
|
> Very interesting. Do you have any suggestions for how
> we could fix our powerpc shared library loader
Removing those instr. comes with a very big performance
penalty. To flush the dcache you will have read up to 8KB
dummy data and to invalidate the icache you will have to
execute up to 16KB nops. I don't know of any other way from
user space.
hmm, actually I think it will work reliable to perform a
store to the same page(s) as the dcbst/icbi will act on. That
way you will make the DTLB Error happen(if any) prior to the
dcbst/icbi. The worst thing that can happen then is a regular
DTLB Miss and that works for dcbst/icbi.
You will have to lookout for if dcbst/icbi crosses a page
boundary. Then you will have to perform a store to both
pages.
Jocke
# And again later writes:
Hi again
I think I know what the problem is. The
PPC_DCBST;PPC_SYNC;PPC_ICBI;PPC_ISYNC sequence is executed
even if no modification has been done i some cases:
_dl_linux_resolver(), the last else has no store for insns[0].
these is a insns[1] = OPCODE_B(delta - 4) that
does not have a PPC_DCBST.
_dl_do_lazy_reloc(), for R_PPC_NONE there is no store.
for R_PPC_JMP_SLOT there is a
insns[1] = OPCODE_B(delta)that does not
have a PPC_DCBST.
_dl_do_reloc(), for R_PPC_COPY there is no store.
for R_PPC_JMP_SLOT there is a
reloc_addr[1] = OPCODE_B(delta) that does not
have a PPC_DCBST.
_dl_init_got(), I THINK that the
PPC_DCBST(plt);
PPC_DCBST(plt+4);
PPC_DCBST(plt+8);
PPC_SYNC;
PPC_ICBI(plt);
PPC_ICBI(plt+4);
PPC_ICBI(plt+8);
PPC_ISYNC;
is off a bit. The address range does not match the sum
of the plt[] and tramp[] address range.
Jocke
# And then later added the comment:
I think that the tramp[] part should be included in the
PPC_DCBST/PPC_ICBI sequence. Then you have to add entries for
plt+12 and plt+16. If the tramp[] part should be excluded,
then all is well.
Jocke
|
|
showed up while running the latest LTP testsuite.
-Erik
|
|
|
|
broke the install target
|
|
|
|
|
|
around...
|
|
|
|
|
|
contained a digit. Also adjust a comment.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Dear Erik,
We downloded uClibc lattest version from the CVS. Still there are some
minor problems with extra/Configs/Config.e1
You have actually set ARCH_HAS_C_SYMBOL_PREFIX to NO which is not
correct for our architecture. Please apply the patch that will fix the
problem.
Best Regards,
- George
P.S. Patch also removes some irritating comments we have added in the past.
|
|
|
|
|
|
things like mmx/3dnow/etc. These are not inline, and will therefore not be as
fast as modifying the headers to use inlines (and cannot therefore do tricky
things when dealing with const memory). But they should (I hope!) be faster
than their generic equivalents....
More importantly, these should provide a good example for others to follow when
adding arch specific optimizations.
-Erik
|
|
|
|
|
|
|
|
|
|
static version. This will need further work later on, but should do the job for
the time being,
|
|
|
|
need to be fixed properly. I tried, but I was unable to build a cross
toolchain for each of these (using stock binutils and gcc) so it is someone
else's problem to fix them now.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
places....
|
|
I've noticed a few people have posted over the last year about problems
compiling programs that use vfork when pthreads are involved. Some
detective work turned up that ptfork.c aliases vfork to fork and then tries
to call the original fork as __libc_fork. This patch removes the aliasing
when there is no MMU present, and uses the same call semantics to call
__libc_vfork. I then added a symbol to the m68k vfork.S to allow vfork to
be called as __libc_vfork.
The same bug exists in the uClibc CVS, and with a possible tweak this patch
should go through there as well.
Obviously, all other platforms need __libc_vfork as a workable means to call
vfork in order for this to work for them.
Let me know if there are any problems with this patch.
Art Shipkowski
Videon Central Software Engineer
(814)235-1111 x307
|
|
endian cris architecture.
|
|
|
|
|
|
|
