this is something of a tradeoff, as now set*id() functions, rather
than pthread_create, are what pull in the code overhead for dealing
with linux's refusal to implement proper POSIX thread-vs-process
semantics. my motivations are:
1. it's cleaner this way, especially cleaner to optimize out the
rsyscall locking overhead from pthread_create when it's not needed.
2. it's expected that only a tiny number of core system programs will
ever use set*id() functions, whereas many programs may want to use
threads, and making thread overhead tiny is an incentive for "light"
programs to try threads.
since timer_create is no longer allocating a structure for the timer_t
and simply using the kernel timer id, it was impossible to specify the
timer_t as the argument to the signal handler. the solution is to pass
the null sigevent pointer on to the kernel, rather than filling it in
userspace, so that the kernel does the right thing. however, that
precludes the clever timerid-versus-threadid encoding we were doing.
instead, just assume timerids are below 1M and thread pointers are
above 1M. (in perspective: timerids are sequentially allocated and
seem limited to 32k, and thread pointers are at roughly 3G.)
with these small changes, libc functions which need to call functions
which are cancellation points, but which themselves must not be
cancellation points, can use the CANCELPT_INHIBIT and CANCELPT_RESUME
macros to temporarily inhibit all cancellation.
note that unlike the originals, these do not print the program
name/argv[0] because we have not saved it anywhere. this could be
changed in __libc_start_main if desired.
this could actually cause rare crashes in the case where a short
string is located at the end of a page and the following page is not
readable, and in fact this was seen in gcc compiling certain files.
the bug appeared only with requests roughly 2*sizeof(size_t) to
4*sizeof(size_t) bytes smaller than a multiple of the page size, and
only for requests large enough to be serviced by mmap instead of the
normal heap. it was only ever observed on 64-bit machines but
presumably could also affect 32-bit (albeit with a smaller window of
opportunity).
since vfprintf will provide a temporary buffer in the case where the
target FILE has a zero buffer size, don't bother setting up a real
buffer for vdprintf. this also allows us to skip the call to fflush
since we know everything will be written out before vfprintf returns.
this change makes it so most calls to fprintf(stderr, ...) will result
in a single writev syscall, as opposed to roughly 2*N syscalls (and
possibly more) where N is the number of format specifiers. in
principle we could use a much larger buffer, but it's best not to
increase the stack requirements too much. most messages are under 80
chars.
0e10000000000000000000000000000000 was setting ERANGE
exponent char e/p was considered part of the match even if not
followed by a valid decimal value
"1e +10" was parsed as "1e+10"
hex digits were misinterpreted as 0..5 instead of 10..15
the problem: there is a (single-instruction) race condition window
between a thread flagging itself dead and decrementing itself from the
thread count. if it receives the rsyscall signal at this exact moment,
the rsyscall caller will never succeed in signalling enough flags to
succeed, and will deadlock forever. in previous versions of musl, the
about-to-terminate thread masked all signals prior to decrementing
the thread count, but this cost a whole syscall just to account for
extremely rare races.
the solution is a huge hack: rather than blocking in the signal
handler if the thread is dead, modify the signal mask of the saved
context and return in order to prevent further signal handling by the
dead thread. this allows the dead thread to continue decrementing the
thread count (if it had not yet done so) and exiting, even while the
live part of the program blocks for rsyscall.
for some inexplicable reason, linux allows the sender of realtime
signals to spoof its identity. permission checks for sending signals
should limit the impact to same-user processes, but just to be safe,
we avoid trusting the siginfo structure and instead simply examine the
program state to see if we're in the middle of a legitimate rsyscall.
if init_malloc returns positive (successful first init), malloc will
retry getting a chunk from the free bins rather than expanding the
heap again. also pass init_malloc a hint for the size of the initial
allocation.
we want to keep atomically updated fields (locks and thread count) and
really anything writable far away from frequently-needed function
pointers. stuff some rarely-needed function pointers in between to
pad, hopefully up to a cache line boundary.
Rich Felker