about summary refs log tree commit diff
path: root/src/thread
Commit message (Collapse)AuthorAgeFilesLines
* store pthread stack guard sizes for pthread_getattr_npWilliam Pitcock2018-02-032-1/+3
|
* revise the definition of multiple basic locks in the codeJens Gustedt2018-01-093-3/+3
| | | | In all cases this is just a change from two volatile int to one.
* consistently use the LOCK an UNLOCK macrosJens Gustedt2018-01-096-12/+12
| | | | | | | 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.
* new lock algorithm with state and congestion count in one atomic intJens Gustedt2018-01-092-8/+52
| | | | | | | | | | | | | | | | | | | | | | | | | | | | 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 c1e27367a9b26b9baac0f37a12349fc36567c8b6 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.
* fix read-after-free type error in pthread_detachRich Felker2017-10-131-1/+2
| | | | | | | | | | | calling __unlock on t->exitlock is not valid because __unlock reads the waiters count after making the atomic store that could allow pthread_exit to continue and unmap the thread's stack and the object t points to. for now, inline the __unlock logic with an unconditional futex wake operation so that the waiters count is not needed. once __lock/__unlock have been made safe for self-synchronized destruction, we could switch back to using them.
* fix signal masking race in pthread_create with priority attributesRich Felker2017-09-061-2/+7
| | | | | | | | | | | if the parent thread was able to set the new thread's priority before it reached the check for 'startlock', the new thread failed to restore its signal mask and thus ran with all signals blocked. concept for patch by Sergei, who reported the issue; unnecessary changes were removed and comments added since the whole 'startlock' thing is non-idiomatic and confusing. eventually it should be replaced with use of idiomatic synchronization primitives.
* trap UB from attempts to join a detached threadRich Felker2017-08-111-0/+1
| | | | | | | | | | | | | | passing to pthread_join the id of a thread which is not joinable results in undefined behavior. in principle the check to trap does not necessarily work if pthread_detach was called after thread creation, since no effort is made here to synchronize access to t->detached, but the check is well-defined and harmless for callers which did not invoke UB, and likely to help catch erroneous code that would otherwise mysteriously hang. patch by William Pitcock.
* unify the use of FUTEX_PRIVATEJens Gustedt2017-07-043-3/+3
| | | | | | The flag 1<<7 is used in several places for different purposes that are not always easy to distinguish. Mark those usages that correspond to the flag that is used by the kernel for futexes.
* use hard-coded sh4a atomic opcodes to avoid linker errors on shRich Felker2017-06-081-4/+4
| | | | | | | when using the sh4a opcodes, the assembler tags the resulting object file as requiring sh4a. the linker then refuses to (static) link it with object files marked as requiring j2, since there is no isa level that includes both sh4a and j2 instructions.
* fix build regression in arm atomics asm with new binutilsRich Felker2017-02-151-1/+1
| | | | | | | | | | | | | | | | | | binutils commit bada43421274615d0d5f629a61a60b7daa71bc15 tightened immediate fixup handling in gas in such a way that the final .arch of an object file must be compatible with the fixups used when the instruction was assembled; this in turn broke assembling of atomics.s, at least in thumb mode. it's not clear whether this should be considered a bug in gas, but .object_arch is preferable anyway for our purpose here of controlling the ISA level tag on the object file being produced, and it's the intended directive for use in object files with runtime code selection. research by Szabolcs Nagy confirmed that .object_arch is supported in all relevant versions of binutils and clang's integrated assembler. patch by Reiner Herrmann.
* fix spurious EINTR errors from multithreaded set*id, etc.Rich Felker2017-01-191-1/+1
| | | | | | | | | commit 78a8ef47c4d92b7680c52a85f80a81e29da86bb9 inadvertently removed the SA_RESTART flag from the sigaction for the internal signal handler used by __synccall for broadcasting. as a result, programs which did not use interrupting signals but which used set*id() in a multithreaded context could wrongly observe EINTR errors they're not prepared to handle.
* fix crashes in x32 __tls_get_addrrofl0r2017-01-131-2/+2
| | | | | | x32 has another gratuitous difference to all other archs: it passes an array of 64bit values to __tls_get_addr(). usually it is an array of size_t.
* rework arm atomic/tp backends to be thumb-compatible and fdpic-readyRich Felker2016-12-194-56/+69
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | three problems are addressed: - use of pc arithmetic, which was difficult if not impossible to make correct in thumb mode on all models, so that relative rather than absolute pointers to the backends could be used. this was designed back when there was no coherent model for the early stages of the dynamic linker before relocations, and is no longer necessary. - assumption that data (the relative pointers to the backends) can be accessed at a constant displacement from the code. this will not be possible on future fdpic subarchs (for cortex-m), so move responsibility for loading the backend code address to the caller. - hard-coded arm opcodes using the .word directive. instead, use the .arch directive to work around the assembler's refusal to assemble instructions not available (or in some cases, available but just considered deprecated) in the target isa level. the obscure v6t2 arch is used for v6 code so as to (1) allow generation of thumb2 output if -mthumb is active, and (2) avoid warnings/errors for mcr barriers that clang would produce if we just set arch to v7-a. in addition, the __aeabi_read_tp function is moved out of the inner workings and implemented as an asm wrapper around a C function, so that asm code does not need to read global data. the asm wrapper serves to satisfy the ABI calling convention requirements for this function.
* add s390x portBobby Bingham2016-11-115-0/+111
|
* add limited pthread_setattr_default_np API to set stack size defaultsRich Felker2016-11-082-4/+43
| | | | | | | | | based on patch by Timo Teräs: While generally this is a bad API, it is the only existing API to affect c++ (std::thread) and c11 (thrd_create) thread stack size. This patch allows applications only to increate stack and guard page sizes.
* fix pthread_create regression from stack/guard size simplificationRich Felker2016-11-081-1/+4
| | | | | | | commit 33ce920857405d4f4b342c85b74588a15e2702e5 broke pthread_create in the case where a null attribute pointer is passed; rather than using the default sizes, sizes of 0 (plus the remainder of one page after TLS/TCB use) were used.
* simplify pthread_attr_t stack/guard size representationRich Felker2016-11-077-11/+13
| | | | | | | | previously, the pthread_attr_t object was always initialized all-zero, and stack/guard size were represented as differences versus their defaults. this required lots of confusing offset arithmetic everywhere they were used. instead, have pthread_attr_init fill in the default values, and work with absolute sizes everywhere.
* add pthread_setname_npFelix Janda2016-10-201-0/+26
| | | | the thread name is displayed by gdb's "info threads".
* pthread: implement try/timed join variantsBobby Bingham2016-06-301-3/+17
|
* fix failure to obtain EOWNERDEAD status for process-shared robust mutexesRich Felker2016-06-273-3/+3
| | | | | | | | | | | | | | | | | | | | | | | | | Linux's documentation (robust-futex-ABI.txt) claims that, when a process dies with a futex on the robust list, bit 30 (0x40000000) is set to indicate the status. however, what actually happens is that bits 0-30 are replaced with the value 0x40000000, i.e. bits 0-29 (containing the old owner tid) are cleared at the same time bit 30 is set. our userspace-side code for robust mutexes was written based on that documentation, assuming that kernel would never produce a futex value of 0x40000000, since the low (owner) bits would always be non-zero. commit d338b506e39b1e2c68366b12be90704c635602ce introduced this assumption explicitly while fixing another bug in how non-recoverable status for robust mutexes was tracked. presumably the tests conducted at that time only checked non-process-shared robust mutexes, which are handled in pthread_exit (which implemented the documented kernel protocol, not the actual one) rather than by the kernel. change pthread_exit robust list processing to match the kernel behavior, clearing bits 0-29 while setting bit 30, and use the value 0x7fffffff instead of 0x40000000 to encode non-recoverable status. the choice of value here is arbitrary; any value with at least one of bits 0-29 set should work just as well,
* add powerpc64 portBobby Bingham2016-05-084-0/+101
|
* fix thread structure/dtv-pointer corruption on powerpcRich Felker2016-04-251-0/+5
| | | | | | | | | | | | | | per the powerpc psabi, offset 4 of the stack at call time belongs to the callee and is used for spilling lr (return address). in addition, offset 0 on the stack must contain a pointer to the previous stack frame, or a null pointer for the initial stack frame of a thread. __clone failed to setup any stack frame on the new thread's stack, thereby allowing the start function it called to clobber offset 4 of the new thread's struct __pthread, which contains the dtv pointer. add code to setup a proper stack frame and align the stack pointer to a multiple of 16 (also an abi requirement) if it was not already aligned.
* add mips n32 port (ILP32 ABI for mips64)Rich Felker2016-04-183-0/+90
| | | | based on patch submitted by Jaydeep Patil, with minor changes.
* add mips64 portRich Felker2016-03-063-0/+91
| | | | | patch by Mahesh Bodapati and Jaydeep Patil of Imagination Technologies.
* remove workaround for broken mips assemblersRich Felker2016-02-081-5/+1
| | | | | | | | | | | | | | | | | | | | the workaround was for a bug that botched .gpword references to local labels, applying a nonsensical random offset of -0x4000 to them. this reverses commit 5e396fb996a80b035d0f6ecf7fed50f68aa3ebb7 and a removes a similar hack that was added to syscall_cp.s in the later commit 756c8af8589265e99e454fe3adcda1d0bc5e1963. it turns out one additional instance of the same idiom, the GETFUNCSYM macro in arch/mips/reloc.h, was still affected by the assembler bug and does not admit an easy workaround without making assumptions about how the macro is used. the previous workarounds made static linking work but left the early-stage dynamic linker broken and thus had limited usefulness. instead, affected users (using binutils versions older than 2.20) will need to fix the bug on the binutils side; the trivial patch is commit 453f5985b13e35161984bf1bf657bbab11515aa4 in the binutils-gdb repository.
* in mips cancellable syscall asm, don't assume gp register is validRich Felker2016-02-041-2/+13
| | | | | | | | | | the old __cp_cancel code path loaded the address of __cancel from the GOT using the $gp register, which happened to be set to point to the correct GOT by the calling C function, but there is no ABI requirement that this happen. instead, go the roundabout way and compute the address of __cancel via pc-relative and gp-relative addressing starting with a fake return address generated by a bal instruction, which is the same trick crt1 uses to bootstrap.
* avoid using signals when a thread attempts to cancel itselfRich Felker2016-02-041-0/+1
| | | | | not only is pthread_kill expensive in this case; it also breaks testing under qemu app-level emulation.
* fix misaligned pointer-like objects in arm atomics asm source fileRich Felker2016-01-301-0/+2
| | | | | | | | this file's .data section was not aligned, and just happened to get the correct alignment with past builds. it's likely that the move of atomic.s from arch/arm/src to src/thread/arm caused the change in alignment, which broke the atomic and thread-pointer access fragments on actual armv5 hardware.
* move sh __unmapself code from arch/sh/src to main src treeRich Felker2016-01-222-0/+24
|
* move x32 sysinfo impl and syscall fixup code out of arch/x32/srcRich Felker2016-01-221-0/+38
| | | | | all such arch-specific translation units are being moved to appropriate arch dirs under the main src tree.
* move arm-specific translation units out of arch/arm/src, to src/*/armRich Felker2016-01-223-1/+160
| | | | | | | this is possible with the new build system that allows src/*/$(ARCH)/* files which do not shadow a file in the parent directory, and yields a more logical organization. eventually it will be possible to remove arch/*/src from the build system.
* overhaul sh atomics for new atomics framework, add j-core cas.l backendRich Felker2016-01-213-0/+105
| | | | | | | | | | | | | | | | sh needs runtime-selected atomic backends since there are a number of supported models that use non-forwards-compatible (non-smp-compatible) atomic mechanisms. previously, the code paths for this were highly inefficient since they involved C function calls with multiple branches in the callee and heavy spills in the caller. the new code performs calls the runtime-selected asm fragment from inline asm with extremely minimal clobbers, rather than using a function call. for the sh4a case where the atomic mechanism is known and there is no forward-compatibility issue, the movli.l and movco.l instructions are provided as a_ll and a_sc, allowing the new shared atomic.h to generate efficient inline versions of all the basic atomic operations without needing a cas loop.
* eliminate use of SHARED macro in __tls_get_addrRich Felker2015-11-111-6/+6
| | | | | | this was only a tiny optimization, and static-linked binaries should not be calling __tls_get_addr anyway since the linker is supposed to perform relaxation, resulting in use of the local-exec TLS model.
* eliminate use of SHARED macro to suppress visibility attributesRich Felker2015-11-112-6/+0
| | | | | | | | | | | | | | | | this is the first and simplest stage of removal of the SHARED macro, which will eventually allow libc.a and libc.so to be produced from the same object files. the original motivation for these #ifdefs which are now being removed was to allow building a static-only libc using a compiler that does not support visibility. however, SHARED was the wrong condition to test for this anyway; various assembly-language sources refer to hidden symbols and declare them with the .hidden directive, making it wrong to define the referenced symbols as non-hidden. if there is a need in the future to build libc using compilers that lack visibility, support could be moved to the build system or perhaps the __PIC__ macro could be checked instead of SHARED.
* explicitly assemble all arm asm sources as UALRich Felker2015-11-103-0/+3
| | | | | | | | these files are all accepted as legacy arm syntax when producing arm code, but legacy syntax cannot be used for producing thumb2 with access to the full ISA. even after switching to UAL, some asm source files contain instructions which are not valid in thumb mode, so these will need to be addressed separately.
* remove non-working pre-armv4t support from arm asmRich Felker2015-11-092-4/+0
| | | | | | | | | | | | | | | the idea of the three-instruction sequence being removed was to be able to return to thumb code when used on armv4t+ from a thumb caller, but also to be able to run on armv4 without the bx instruction available (in which case the low bit of lr would always be 0). however, without compiler support for generating such a sequence from C code, which does not exist and which there is unlikely to be interest in implementing, there is little point in having it in the asm, and it would likely be easier to add pre-armv4t support via enhanced linker handling of R_ARM_V4BX than at the compiler level. removing this code simplifies adding support for building libc in thumb2-only form (for cortex-m).
* use explicit __cp_cancel label in cancellable syscall asm for all archsRich Felker2015-11-028-28/+32
| | | | | | | | | | | | | previously, only archs that needed to do stack cleanup defined a __cp_cancel label for acting on cancellation in their syscall asm, and a default definition was provided by a weak alias to __cancel, the C function. this resulted in wrong codegen for arm on gcc versions affected by pr 68178 and possibly similar issues (like pr 66609) on other archs, and also created an inconsistency where the __cp_begin and __cp_end labels were treated as const data but __cp_cancel was treated as a function. this in turn caused incorrect code generation on archs where function pointers point to function descriptors rather than code (for now, only sh/fdpic).
* properly access mcontext_t program counter in cancellation handlerRich Felker2015-11-021-3/+4
| | | | | | | | | using the actual mcontext_t definition rather than an overlaid pointer array both improves correctness/readability and eliminates some ugly hacks for archs with 64-bit registers bit 32-bit program counter. also fix UB due to comparison of pointers not in a common array object.
* add missing memory barrier to pthread_joinBobby Bingham2015-10-151-0/+1
| | | | | | | POSIX requires pthread_join to synchronize memory on success. The futex wait inside __timedwait_cp cannot handle this because it's not called in all cases. Also, in the case of a spurious wake, tid can become zero between the wake and when the joining thread checks it.
* make sh clone asm fdpic-compatibleRich Felker2015-09-121-3/+9
| | | | | | | | | | | clone calls back to a function pointer provided by the caller, which will actually be a pointer to a function descriptor on fdpic. the obvious solution is to have a separate version of clone for fdpic, but I have taken a simpler approach to go around the problem. instead of calling the pointed-to function from asm, a direct call is made to an internal C function which then calls the pointed-to function. this lets the C compiler generate the appropriate calling convention for an indirect call with no need for ABI-specific assembly.
* fix local-dynamic model TLS on mips and powerpcRich Felker2015-06-251-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | the TLS ABI spec for mips, powerpc, and some other (presently unsupported) RISC archs has the return value of __tls_get_addr offset by +0x8000 and the result of DTPOFF relocations offset by -0x8000. I had previously assumed this part of the ABI was actually just an implementation detail, since the adjustments cancel out. however, when the local dynamic model is used for accessing TLS that's known to be in the same DSO, either of the following may happen: 1. the -0x8000 offset may already be applied to the argument structure passed to __tls_get_addr at ld time, without any opportunity for runtime relocations. 2. __tls_get_addr may be used with a zero offset argument to obtain a base address for the module's TLS, to which the caller then applies immediate offsets for individual objects accessed using the local dynamic model. since the immediate offsets have the -0x8000 adjustment applied to them, the base address they use needs to include the +0x8000 offset. it would be possible, but more complex, to store the pointers in the dtv[] array with the +0x8000 offset pre-applied, to avoid the runtime cost of adding 0x8000 on each call to __tls_get_addr. this change could be made later if measurements show that it would help.
* work around mips detached thread exit breakage due to kernel regressionRich Felker2015-06-201-0/+1
| | | | | | | | | linux kernel commit 46e12c07b3b9603c60fc1d421ff18618241cb081 caused the mips syscall mechanism to fail with EFAULT when the userspace stack pointer is invalid, breaking __unmapself used for detached thread exit. the workaround is to set $sp to a known-valid, readable address, and the simplest one to obtain is the address of the current function, which is available (per o32 calling convention) in $25.
* ignore ENOSYS error from mprotect in pthread_create and dynamic linkerRich Felker2015-06-171-1/+2
| | | | | this error simply indicated a system without memory protection (NOMMU) and should not cause failure in the caller.
* switch to using trap number 31 for syscalls on shRich Felker2015-06-163-5/+5
| | | | | | | | | | | | | | | | | | | nominally the low bits of the trap number on sh are the number of syscall arguments, but they have never been used by the kernel, and some code making syscalls does not even know the number of arguments and needs to pass an arbitrary high number anyway. sh3/sh4 traditionally used the trap range 16-31 for syscalls, but part of this range overlapped with hardware exceptions/interrupts on sh2 hardware, so an incompatible range 32-47 was chosen for sh2. using trap number 31 everywhere, since it's in the existing sh3/sh4 range and does not conflict with sh2 hardware, is a proposed unification of the kernel syscall convention that will allow binaries to be shared between sh2 and sh3/sh4. if this is not accepted into the kernel, we can refit the sh2 target with runtime selection mechanisms for the trap number, but doing so would be invasive and would entail non-trivial overhead.
* switch sh port's __unmapself to generic version when running on sh2/nommuRich Felker2015-06-161-3/+3
| | | | | | | | | | | | | due to the way the interrupt and syscall trap mechanism works, userspace on sh2 must never set the stack pointer to an invalid value. thus, the approach used on most archs, where __unmapself executes with no stack for the interval between SYS_munmap and SYS_exit, is not viable on sh2. in order not to pessimize sh3/sh4, the sh asm version of __unmapself is not removed. instead it's renamed and redirected through code that calls either the generic (safe) __unmapself or the sh3/sh4 asm, depending on compile-time and run-time conditions.
* add support for sh2 interrupt-masking-based atomics to sh portRich Felker2015-06-161-6/+0
| | | | | | | | | | | | | | | | | | | the sh2 target is being considered an ISA subset of sh3/sh4, in the sense that binaries built for sh2 are intended to be usable on later cpu models/kernels with mmu support. so rather than hard-coding sh2-specific atomics, the runtime atomic selection mechanisms that was already in place has been extended to add sh2 atomics. at this time, the sh2 atomics are not SMP-compatible; since the ISA lacks actual atomic operations, the new code instead masks interrupts for the duration of the atomic operation, producing an atomic result on single-core. this is only possible because the kernel/hardware does not impose protections against userspace doing so. additional changes will be needed to support future SMP systems. care has been taken to avoid producing significant additional code size in the case where it's known at compile-time that the target is not sh2 and does not need sh2-specific code.
* refactor stdio open file list handling, move it out of global libc structRich Felker2015-06-161-1/+2
| | | | | | | | | | | | | functions which open in-memory FILE stream variants all shared a tail with __fdopen, adding the FILE structure to stdio's open file list. replacing this common tail with a function call reduces code size and duplication of logic. the list is also partially encapsulated now. function signatures were chosen to facilitate tail call optimization and reduce the need for additional accessor functions. with these changes, static linked programs that do not use stdio no longer have an open file list at all.
* implement arch-generic version of __unmapselfRich Felker2015-06-101-0/+29
| | | | | | | | | | | | this can be used to put off writing an asm version of __unmapself for new archs, or as a permanent solution on archs where it's not practical or even possible to run momentarily with no stack. the concept here is simple: the caller takes a lock on a global shared stack and uses it to make the munmap and exit syscalls. the only trick is unlocking, which must be done after the thread exits, and this is achieved by using the set_tid_address syscall to have the kernel zero and futex-wake the lock word as part of the exit syscall.
* mark mips cancellable syscall code as codeRich Felker2015-05-251-0/+3
| | | | otherwise disassemblers treat it as data.
* eliminate costly tricks to avoid TLS access for current locale stateRich Felker2015-05-161-6/+0
| | | | | | | | | | | | | | | the code being removed used atomics to track whether any threads might be using a locale other than the current global locale, and whether any threads might have abstract 8-bit (non-UTF-8) LC_CTYPE active, a feature which was never committed (still pending). the motivations were to support early execution prior to setup of the thread pointer, to partially support systems (ancient kernels) where thread pointer setup is not possible, and to avoid high performance cost on archs where accessing the thread pointer may be very slow. since commit 19a1fe670acb3ab9ead0fe31859ca7d4fe40dd54, the thread pointer is always available, so these hacks are no longer needed. removing them greatly simplifies the affected code.