the default subarch is the one whose full name is just the base arch
name, with no suffixes. normally, either the asm in the default
subarch is suitable for all subarch variants, or separate asm is
mandatory for each variant. however, in the case of asm which is
purely for optimization purposes, it's possible to have asm that only
works (or only performs well) on the default subarch, and not any othe
the other variants. thus, I have added a mechanism to give a name to
the default variant, for example "armel" for the default,
little-endian arm. further such default-subarch names can be added in
the future as needed.
a mips signal mask contains 128 bits, enough for signals 1 through
128. however, the exit status obtained from the wait-family functions
only has room for values up to 127. reportedly signal 128 was causing
kernelspace bugs, so it was removed from the kernel recently; even
without that issue, however, it was impossible to support it correctly
in userspace.
at the same time, the bug was masked on musl by SIGRTMAX incorrectly
yielding 64 on mips, rather than the "correct" value of 128. now that
the _NSIG issue is fixed, SIGRTMAX can be fixed at the same time,
exposing the full range of signals for application use.
note that the (nonstandardized) libc _NSIG value is actually one
greater than the max signal number, and also one greater than the
kernel headers' idea of _NSIG. this is the reason for the discrepency
with the recent kernel changes. since reducing _NSIG by one brought it
down from 129 to 128, rather than from 128 to 127, _NSIG/8, used
widely in the musl sources, is unchanged.
mips has signal numbers up to 127 (formerly, up to 128, but the last
one never worked right and caused kernel panic when used), so 127 in
the "signal number" field of the wait status is insufficient for
determining that the process was stopped. in addition, a nonzero value
in the upper bits must be present, indicating the signal number which
caused the process to be stopped.
details on this issue can be seen in the email with message id
CAAG0J9-d4BfEhbQovFqUAJ3QoOuXScrpsY1y95PrEPxA5DWedQ@mail.gmail.com on
the linux-mips mailing list, archived at:
http://www.linux-mips.org/archives/linux-mips/2013-06/msg00552.html
and in the associated thread about fixing the mips kernel bug.
commit 4a96b948687166da26a6c327e6c6733ad2336c5c fixed the
corresponding issue in uClibc, but introduced a multiple-evaluation
issue for the WIFSTOPPED macro.
for the most part, none of these issues affected pure musl systems,
since musl has up until now (incorrectly) defined SIGRTMAX as 64 on
all archs, even mips. however, interpreting status of non-musl
programs on mips may have caused problems. with this change, the full
range of signal numbers can be made available on mips.
this first commit just includes the CPU_* and sched_* interfaces, not
the pthread_* interfaces, which may be added later. simple
sanity-check testing has been done for the basic interfaces, but most
of the macros have not yet been tested.
the idea here is to avoid advertising signals that don't exist and to
make these functions safe to call (e.g. from within other parts of the
implementation) on fake sigset_t objects which do not have the HURD
padding.
the trick here is that sigaction can track for us which signals have
ever had a signal handler set for them, and only those signals need to
be considered for reset. this tracking mask may have false positives,
since it is impossible to remove bits from it without race conditions.
false negatives are not possible since the mask is updated with atomic
operations prior to making the sigaction syscall.
implementation-internal signals are set to SIG_IGN rather than SIG_DFL
so that a signal raised in the parent (e.g. calling pthread_cancel on
the thread executing pthread_spawn) does not have any chance make it
to the child, where it would cause spurious termination by signal.
this change reduces the minimum/typical number of syscalls in the
child from around 70 to 4 (including execve). this should greatly
improve the performance of posix_spawn and other interfaces which use
it (popen and system).
to facilitate these changes, sigismember is also changed to return 0
rather than -1 for invalid signals, and to return the actual status of
implementation-internal signals. POSIX allows but does not require an
error on invalid signal numbers, and in fact returning an error tends
to confuse applications which wrongly assume the return value of
sigismember is boolean.
the child process's stack may be insufficient size to support a signal
frame, and there is no reason these signal handlers should run in the
child anyway.
there are several reasons for this. some of them are related to race
conditions that arise since fork is required to be async-signal-safe:
if fork or pthread_create is called from a signal handler after the
fork syscall has returned but before the subsequent userspace code has
finished, inconsistent state could result. also, there seem to be
kernel and/or strace bugs related to arrival of signals during fork,
at least on some versions, and simply blocking signals eliminates the
possibility of such bugs.
this commit does not add versioning support; it merely fixes incorrect
lookups of symbols in libraries that contain versioned symbols.
previously, the version information was completely ignored, and
empirically this seems to have resulted in the oldest version being
chosen, but I am uncertain if that behavior was even reliable.
the new behavior being introduced is to completely ignore symbols
which are marked "hidden" (this seems to be the confusing nomenclature
for non-current-version) when versioning is present. this should solve
all problems related to libraries with symbol versioning as long as
all binaries involved are up-to-date (compatible with the
latest-version symbols), and it's the needed behavior for dlsym under
all circumstances.
at this point, it is just the common base charset equivalent to
Windows CP 950, with no further extensions. HKSCS and possibly other
supersets will be added later. other aliases may need to be added too.
the (obsolete) standard allows either 0 or 1 for the decimal point
location in this case, but since the number of zero digits returned in
the output string (in this implementation) is one more than the number
of digits the caller requested, it makes sense for the decimal point
to be logically "after" the first digit. in a sense, this change goes
with the previous commit which fixed the value of the decimal point
location for non-zero inputs.
these functions are obsolete and have no modern standard. the text in
SUSv2 is highly ambiguous, specifying that "negative means to the left
of the returned digits", which suggested to me that 0 would mean to
the right of the first digit. however, this does not agree with
historic practice, and the Linux man pages are more clear, specifying
that a negative value means "that the decimal point is to the left of
the start of the string" (in which case, 0 would mean the start of the
string, in accordance with historic practice).
like for other character sets, stateful iso-2022 form is not supported
yet but everything else should work. all charset aliases are treated
the same, as Windows codepage 949, because reportedly the EUC-KR
charset name is in widespread (mis?)usage in email and on the web for
data which actually uses the extended characters outside the standard
93x94 grid. this could easily be changed if desired.
the principle of this converter for handling the giant bulk of rare
Hangul syllables outside of the standard KS X 1001 93x94 grid is the
same as the GB18030 converter's treatment of non-explicitly-coded
Unicode codepoints: sequences in the extension range are mapped to an
integer index N, and the converter explicitly computes the Nth Hangul
syllable not explicitly encoded in the character map. empirically,
this requires at most 7 passes over the grid. this approach reduces
the table size required for Korean legacy encodings from roughly 44k
to 17k and should have minimal performance impact on real-world text
conversions since the "slow" characters are rare. where it does have
impact, the cost is merely a large constant time factor.
unblocking it in the pthread_once init function is not sufficient,
since multiple threads, some of them with the signal blocked, could
already exist before this is called; timers started from such threads
would be non-functional.
this is needed for reused threads in the SIGEV_THREAD timer
notification system, and could be reused elsewhere in the future if
needed, though it should be refactored for such use.
for static linking, __init_tls.c is simply modified to export the TLS
info in a structure with external linkage, rather than using statics.
this perhaps makes the code more clear, since the statics were poorly
named for statics. the new __reset_tls.c is only linked if it is used.
for dynamic linking, the code is in dynlink.c. sharing code with
__copy_tls is not practical since __reset_tls must also re-zero
thread-local bss.
1. the thread result field was reused for storing a kernel timer id,
but would be overwritten if the application code exited or cancelled
the thread.
2. low pointer values were used as the indicator that the timer id is
a kernel timer id rather than a thread id. this is not portable, as
mmap may return low pointers on some conditions. instead, use the fact
that pointers must be aligned and kernel timer ids must be
non-negative to map pointers into the negative integer space.
3. signals were not blocked until after the timer thread started, so a
race condition could allow a signal handler to run in the timer thread
when it's not supposed to exist. this is mainly problematic if the
calling thread was the only thread where the signal was unblocked and
the signal handler assumes it runs in that thread.
this is another case of the kernel syscall failing to support flags
where it needs to, leading to horrible workarounds in userspace. this
time the workaround requires changing uid/gid, and that's not safe to
do in the current process. in the worst case, kernel resource limits
might prevent recovering the original values, and then there would be
no way to safely return. so, use the safe but horribly inefficient
alternative: forking. clone is used instead of fork to suppress
signals from the child.
fortunately this worst-case code is only needed when effective and
real ids mismatch, which mainly happens in suid programs.
it turns out Linux is buggy for faccessat, just like fchmodat: the
kernel does not actually take a flags argument. so we're going to have
to emulate it there.
patch by nsz. the actual object the caller has storing the tree root
has type void *, so accessing it as struct node * is not valid.
instead, simply access the value, move it to a temporary of the
appropriate type and work from there, then move the result back.
check in configure to be polite (failing early if we're going to fail)
and in vfprintf.c since that is the point at which a mismatching type
would be extremely dangerous.
on newer kernels, fchdir and fstat work anyway. this same fix should
be applied to any other syscalls that are similarly affected.
with this change, the current definitions of O_SEARCH and O_EXEC as
O_PATH are mostly conforming to POSIX requirements. the main remaining
issue is that O_NOFOLLOW has different semantics.
I intend to add more Linux workarounds that depend on using these
pathnames, and some of them will be in "syscall" functions that, from
an anti-bloat standpoint, should not depend on the whole snprintf
framework.
previously, the AT_SYMLINK_NOFOLLOW flag was ignored, giving
dangerously incorrect behavior -- the target of the symlink had its
modes changed to the modes (usually 0777) intended for the symlink).
this issue was amplified by the fact that musl provides lchmod, as a
wrapper for fchmodat, which some archival programs take as a sign that
symlink modes are supported and thus attempt to use.
emulating AT_SYMLINK_NOFOLLOW was a difficult problem, and I
originally believed it could not be solved, at least not without
depending on kernels newer than 3.5.x or so where O_PATH works halfway
well. however, it turns out that accessing O_PATH file descriptors via
their pseudo-symlink entries in /proc/self/fd works much better than
trying to use the fd directly, and works even on older kernels.
moreover, the kernel has permanently pegged these references to the
inode obtained by the O_PATH open, so there should not be race
conditions with the file being moved, deleted, replaced, etc.
this is the modern way, and the only way that makes any sense. glibc
has this complicated mechanism with RPATH and RUNPATH that controls
whether RPATH is processed before or after LD_LIBRARY_PATH, presumably
to support legacy binaries, but there is no compelling reason to
support this, and better behavior is obtained by just fixing the
search order.
previously, errno could be meaningless when the caller wrote it to the
dlerror string or stderr. try to make it meaningful. also, fix
incorrect check for over-long program headers and instead actually
support them by allocating memory if needed.
the access function cannot be used to check for existence, because it
operates using real uid/gid rather than effective to determine
accessibility; this matters for the non-final path components.
instead, use stat. failure of stat is success if only the final
component is missing (ENOENT) and otherwise is failure.
the concept of both versions is the same; they differ only in details.
for long runs, they use "rep movsl" or "rep movsq", and for small
runs, they use a trick, writing from both ends towards the middle,
that reduces the number of branches needed. in addition, if memset is
called multiple times with the same length, all branches will be
predicted; there are no loops.
for larger runs, there are likely faster approaches than "rep", at
least on some cpu models. for 32-bit, it's unlikely that there is any
faster approach that does not require non-baseline instructions; doing
anything fancier would require inspecting cpu capabilities. for
64-bit, there may very well be faster versions that work on all
models; further optimization could be explored in the future.
with these changes, memset is anywhere between 50% faster and 6 times
faster, depending on the cpu model and the length and alignment of the
destination buffer.
the original motivation for this patch was that qemu (and possibly
other syscall emulators) nop out madvise, resulting in an infinite
loop. however, there is another benefit to this change: madvise may
actually undo an explicit madvise the application intended for its
stack, whereas the mremap operation is a true nop. the logic here is
that mremap must fail if it cannot resize the mapping in-place, and
the caller knows that it cannot resize in-place because it knows the
next page of virtual memory is already occupied.
one of the arguments to memcmp may be shorter than the length l-3, and
memcmp is under no obligation not to access past the first byte that
differs. instead use strncmp which conveys the correct semantics. the
performance difference is negligible here and since the code is only
use for shared libc, both functions are already linked anyway.
the dev/inode for the main app and the dynamic linker ("interpreter")
are not available, so the subsequent checks don't work. in general we
don't want to make exact string matches to existing libraries prevent
loading new ones, since this breaks loading upgraded modules in
module-loading systems. so instead, special-case it.
the motivation for this fix is that calling dlopen on the names
returned by dl_iterate_phdr or walking the link map (obtained by
dlinfo) seem to be the only methods available to an application to
actually get a list of open dso handles.
reject elf files which are not ET_EXEC/ET_DYN type as bad exec format,
and reject ET_EXEC files when they cannot be loaded at the correct
address, since they are not relocatable at runtime. the main practical
benefit of this is to make dlopen of the main program fail rather than
producing an unsafe-to-use handle.
Rich Felker
rofl0r