replacement is subject to conditions on the replacement functions.
they may only call functions which are async-signal-safe, as specified
either by POSIX or as an implementation-defined extension. if any
allocator functions are replaced, at least malloc, realloc, and free
must be provided. if calloc is not provided, it will behave as
malloc+memset. any of the memalign-family functions not provided will
fail with ENOMEM.
in order to implement the above properties, calloc and __memalign
check that they are using their own malloc or free, respectively.
choice to check malloc or free is based on considerations of
supporting __simple_malloc. in order to make this work, calloc is
split into separate versions for __simple_malloc and full malloc;
commit ba819787ee already did most of
the split anyway, and completing it saves an extra call frame.
previously, use of -Bsymbolic-functions made dynamic interposition
impossible. now, we are using an explicit dynamic-list, so add
allocator functions to the list. most are not referenced anyway, but
all are added for completeness.
instead of using a waiters count, add a bit to the lock field
indicating that the lock may have waiters. threads which obtain the
lock after contending for it will perform a potentially-spurious wake
when they release the lock.
the Linux SYS_nice syscall is unusable because it does not return the
newly set priority. always use SYS_setpriority. also avoid overflows
in addition of inc by handling large inc values directly without
examining the old nice value.
Implementation of __malloc0 in malloc.c takes care to preserve zero
pages by overwriting only non-zero data. However, malloc must have
already modified auxiliary heap data just before and beyond the
allocated region, so we know that edge pages need not be preserved.
For allocations smaller than one page, pass them immediately to memset.
Otherwise, use memset to handle partial pages at the head and tail of
the allocation, and scan complete pages in the interior. Optimize the
scanning loop by processing 16 bytes per iteration and handling rest of
page via memset as soon as a non-zero byte is found.
the catan implementation from OpenBSD includes a FIXME-annotated
"overflow" branch that produces a meaningless and incorrect
large-magnitude result. it was reachable via three paths,
corresponding to gotos removed by this commit, in order:
1. pure imaginary argument with imaginary component greater than 1 in
magnitude. this case does not seem at all exceptional and is
handled (at least with the quality currently expected from our
complex math functions) by the existing non-exceptional code path.
2. arguments on the unit circle, including the pure-real argument 1.0.
these are not exceptional except for ±i, which should produce
results with infinite imaginary component and which lead to
computation of atan2(±0,0) in the existing non-exceptional code
path. such calls to atan2() however are well-defined by POSIX.
3. the specific argument +i. this route should be unreachable due to
the above (2), but subtle rounding effects might have made it
possible in rare cases. continuing on the non-exceptional code path
in this case would lead to computing the (real) log of an infinite
argument, then producing a NAN when multiplying it by I.
for now, remove the exceptional code paths entirely. replace the
multiplication by I with construction of a complex number using the
CMPLX macro so that the NAN issue (3) prevented cannot arise.
with these changes, catan should give reasonably correct results for
real arguments, and should no longer give completely-wrong results for
pure-imaginary arguments outside the interval (-i,+i).
the factor of -i noted in the comment at the top of casin.c was
omitted from the actual code, yielding a result rotated 90 degrees and
propagating into errors in other functions defined in terms of casin.
implement multiplication by -i as a rotation of the real and imaginary
parts of the result, rather than by actual multiplication, since the
latter cannot be optimized without knowledge that the operand is
finite. here, the rotation is the actual intent, anyway.
Commit 8a6bd7307d added support for
padding specifier extensions to strftime, but did not modify wcsftime.
In the process, it added a parameter to __strftime_fmt_1 in strftime.c,
but failed to update the prototype in wcsftime.c. This was found by
compiling musl with LTO:
src/time/wcsftime.c:7:13: warning: type of '__strftime_fmt_1' does \
not match original declaration [-Wlto-type-mismatch]
Fix the prototype of __strftime_fmt_1 in wcsftime.c, and generate the
'pad' argument the same way as it is done in strftime.
it was reported by Erik Bosman that poll fails without setting revents
when the nfds argument exceeds the current value for RLIMIT_NOFILE,
causing the subsequent open calls to be bypassed. if the rlimit is
either 1 or 2, this leaves fd 0 and 1 potentially closed but openable
when the application code is reached.
based on a brief reading of the poll syscall documentation and code,
it may be possible for poll to fail under other attacker-controlled
conditions as well. if it turns out these are reasonable conditions
that may happen in the real world, we may have to go back and
implement fallbacks to probe each fd individually if poll fails, but
for now, keep things simple and treat all poll failures as fatal.
if double precision r=x*y+z is not a half way case between two single
precision floats or it is an exact result then fmaf returns (float)r.
however the exactness check was wrong when |x*y| < |z| and could cause
incorrectly rounded result in nearest rounding mode when r is a half
way case.
fmaf(-0x1.26524ep-54, -0x1.cb7868p+11, 0x1.d10f5ep-29)
was incorrectly rounded up to 0x1.d117ap-29 instead of 0x1.d1179ep-29.
(exact result is 0x1.d1179efffffffecp-29, r is 0x1.d1179fp-29)
use of MB_CUR_MAX encoded a hidden dependency on the currently active
locale for the calling thread, whereas nl_langinfo_l is supposed to
report for the locale passed as an argument.
general policy is that all source files defining a public API or an
ABI mechanism referenced by a public header should include the public
header that declares the interface, so that the compiler or analysis
tools can check the consistency of the declarations. Alexander Monakov
pointed out a number of violations of this principle a few years back.
fix them now.
add a member of appropriate type to the fpos_t union so that accesses
are well-defined. use long long instead of off_t since off_t is not
always exposed in stdio.h and there's no namespace-clean alias for it.
access is still performed using pointer casts rather than by naming
the union member as a matter of style; to the extent possible, the
naming of fields in opaque types defined in the public headers is not
treated as an API contract with the implementation. access via the
pointer cast is valid as long as the union has a member of matching
type.
previously this macro used an odd if/else form instead of the more
idiomatic do/while(0), making it unsafe against omission of trailing
semicolon. the omission would make the following statement conditional
instead of producing an error.
formally, calling readv with a zero-length first iov component should
behave identically to calling read on just the second component, but
presence of a zero-length iov component has triggered bugs in some
kernels and performs significantly worse than a simple read on some
file types.
the stdio FILE read backend's return type is size_t, not ssize_t, and
all of the special (non-fd-backed) FILE types already return the
number of bytes read (zero) on error or eof. only __stdio_read leaked
a syscall error return into its return value.
fread had a workaround for this behavior going all the way back to the
original check-in. remove the workaround since it's no longer needed.
the ':' in optstring has special meaning as a flag applying to the
previous option character, or to getopt's error handling behavior when
it appears at the beginning. don't also accept a "-:" option based on
its presence.
based loosely on patch by Hauke Mehrtens; converted to wrap the public
API of the underlying getrandom function rather than direct syscalls,
so that if/when a fallback implementation of getrandom is added it
will automatically get picked up by getentropy too.
this is more extensible if we need to consider additional errors, and
more efficient as long as the compiler does not know it can cache the
result of __errno_location (a surprisingly complex issue detailed in
commit a603a75a72).
It's better to make execvp continue PATH search on ENOTDIR rather than
issuing an error. Bogus entries should not render rest of PATH invalid.
Maintainer's note: POSIX seems to require the search to continue like
this as part of XBD 8.3 Other Environment Variables. Only errors that
conclusively determine non-existence are candidates for continuing;
otherwise for consistency we have to report the error.
when a null buffer pointer is passed to fmemopen, requesting it
allocate its own memory buffer, extremely large size arguments near
SIZE_MAX could overflow and result in underallocation. this results
from omission of the size of the cookie structure in the overflow
check but inclusion of it in the calloc call.
instead of accounting for individual small contributions to the total
allocation size needed, simply reject sizes larger than PTRDIFF_MAX,
which will necessarily fail anyway. then adding arbitrary fixed-size
structures is safe without matching up the expressions in the
comparison and the allocation.
Currently getcwd(3) can succeed without returning an absolute path
because the underlying getcwd syscall, starting with linux commit
v2.6.36-rc1~96^2~2, may succeed without returning an absolute path.
This is a conformance issue because "The getcwd() function shall
place an absolute pathname of the current working directory
in the array pointed to by buf, and return buf".
Fix this by checking the path returned by syscall and failing with
ENOENT if the path is not absolute. The error code is chosen for
consistency with the case when the current directory is unlinked.
Similar issue was fixed in glibc recently, see
https://sourceware.org/bugzilla/show_bug.cgi?id=22679
it's unclear from the specification whether the word "consumes" in
"consumes more than four bytes to represent a year" refers just to
significant places or includes leading zeros due to field width
padding. however the examples in the rationale indicate that the
latter was the intent. in particular, the year 270 is shown being
formatted by %+5Y as +0270 rather than 00270.
previously '+' prefixing was implemented just by comparing the year
against 10000. instead, count the number of significant digits and
padding bytes to be added, and use the total to determine whether to
apply the '+' prefix.
based on testing by Dennis Wölfing.
the code to strip initial sign and leading zeros inadvertently
stripped all the zeros and the subsequent '-' separating the month.
instead, only strip sign characters from the very first position, and
only strip zeros when they are followed by another digit.
based on testing by Dennis Wölfing.
in the original submission of the patch that became commit
7c709f2d4f, and in subsequent reading of
it by others, it was not clear that the new member had to be inserted
before canary_at_end, or that inserting it at that location was safe.
add comments to document.
Do not retry waitpid if the child was terminated by a signal. Do not
examine status: since we are not passing any flags, we will not receive
stop or continue notifications.
commit f9fb20b42d switched from using a
pipe for the result to conveying it via the child process exit status.
Alexander Monakov pointed out that the latter could fail if the
application is not expecting faccessat to produce a child and performs
a wait operation with __WCLONE or __WALL, and that it is not clear
whether it's guaranteed to work when SIGCHLD's disposition has been
set to SIG_IGN.
in addition, that commit introduced a bug that caused EACCES to be
produced instead of EBUSY due to an exit path that was overlooked when
the error channel was changed, and introduced a spurious retry loop
around the wait operation.
Consider the first equals sign found in the option to be the delimiter
between it and its argument, even if it matches an equals sign in the
option name. This avoids consuming the equals sign, which would prevent
finding the argument. Instead, it forces a partial match of the part of
the option name before the equals sign.
Maintainer's note: GNU getopt_long does not explicitly document this
behavior, but it can be seen as a consequence of how partial matches
are specified, and at least GNU (bfd) ld is known to make use of it.
If we find a partial option name match, we need to keep looking for
ambiguous/conflicting options. However, we need to remember the position
in the candidate argument to find its option-argument later, if there is
one. This fixes e.g. option "foobar" being given as "--fooba=baz".
commit 78897b0dc0 wrongly simplified
Dmitry Levin's original submitted patch fixing alt-form octal with the
zero flag and field width present, omitting the special case where the
value is zero. as a result, printf("%#o",0) wrongly prints "00" rather
than "0".
the logic prior to this commit was actually better, in that it was
aligned with how the alt-form flag (#) for printf is specified ("it
shall increase the precision"). at the time there was no good way to
avoid the zero flag issue with the old logic, but commit
167dfe9672 added tracking of whether an
explicit precision was provided.
revert commit 78897b0dc0 and switch to
using the explicit precision indicator for suppressing the zero flag.
In some places there has been a direct usage of the functions. Use the
macros consistently everywhere, such that it might be easier later on to
capture the fast path directly inside the macro and only have the call
overhead on the slow path.
A variant of this new lock algorithm has been presented at SAC'16, see
https://hal.inria.fr/hal-01304108. A full version of that paper is
available at https://hal.inria.fr/hal-01236734.
The main motivation of this is to improve on the safety of the basic lock
implementation in musl. This is achieved by squeezing a lock flag and a
congestion count (= threads inside the critical section) into a single
int. Thereby an unlock operation does exactly one memory
transfer (a_fetch_add) and never touches the value again, but still
detects if a waiter has to be woken up.
This is a fix of a use-after-free bug in pthread_detach that had
temporarily been patched. Therefore this patch also reverts
c1e27367a9
This is also the only place where internal knowledge of the lock
algorithm is used.
The main price for the improved safety is a little bit larger code.
Under high congestion, the scheduling behavior will be different
compared to the previous algorithm. In that case, a successful
put-to-sleep may appear out of order compared to the arrival in the
critical section.
previously, the charset names without endianness specified were always
interpreted as big endian. unicode specifies that UTF-16 and UTF-32
have BOM-determined endianness if BOM is present, and are otherwise
big endian. since commit 5b546faa67
added support for stateful encodings, it is now possible to implement
BOM support via the conversion descriptor state.
for conversions to these charsets, the output is always big endian and
does not have a BOM.
Rich Felker
Alexander Monakov
Samuel Holland
Szabolcs Nagy
Hauke Mehrtens
Przemyslaw Pawelczyk
Dmitry V. Levin
William Pitcock
Jens Gustedt