summaryrefslogtreecommitdiffstats
path: root/sys/compat/linux/linux_futex.c
Commit message (Collapse)AuthorAgeFilesLines
* Fix some typos that were causing probe argument types to show up as unknown.markj2013-10-011-1/+1
| | | | | | Reviewed by: rwatson (mac provider) Approved by: re (glebius) MFC after: 1 week
* Arithmetic on pointers takes into account the size of the type. Properly ↵dchagin2013-01-251-2/+2
| | | | | | cast the pointer to avoid incorrect pointer scaling. MFC after: 1 Week
* - >500 static DTrace probes for the linuxulatornetchild2012-05-051-84/+425
| | | | | | | | | | | | | | | | | | - DTrace scripts to check for errors, performance, ... they serve mostly as examples of what you can do with the static probe;s with moderate load the scripts may be overwhelmed, excessive lock-tracing may influence program behavior (see the last design decission) Design decissions: - use "linuxulator" as the provider for the native bitsize; add the bitsize for the non-native emulation (e.g. "linuxuator32" on amd64) - Add probes only for locks which are acquired in one function and released in another function. Locks which are aquired and released in the same function should be easy to pair in the code, inter-function locking is more easy to verify in DTrace. - Probes for locks should be fired after locking and before releasing to prevent races (to provide data/function stability in DTrace, see the man-page of "dtrace -v ..." and the corresponding DTrace docs).
* Mark MALLOC_DEFINEs static that have no corresponding MALLOC_DECLAREs.ed2011-11-071-2/+2
| | | | This means that their use is restricted to a single C file.
* Remove now-obsolete comment.jhb2011-03-101-6/+1
| | | | | Submitted by: netchild MFC after: 1 week
* Print out shared flag for debug purpose.dchagin2011-03-031-8/+8
| | | | MFC after: 1 Week
* Switch PROCESS_SHARE to AUTO_SHARE (as umtx do). Even for SHARED,dchagin2011-03-031-1/+1
| | | | | | | | if page mapped MAP_ANON linux uses private algorithm too. Disscussed with: jhb MFC after: 3 Days
* Use umtx_key objects to uniquely identify futexes. Private futexes injhb2011-02-231-17/+32
| | | | | | | | | | | | different processes that happen to use the same user address in the separate processes will now be treated as distinct futexes rather than the same futex. We can now honor shared futexes properly by mapping them to a PROCESS_SHARED umtx_key. Private futexes use THREAD_SHARED umtx_key objects. In conjunction with: dchagin Reviewed by: kib MFC after: 1 week
* Style(9) fix. Do not initialize variables in the declarations.dchagin2011-02-141-2/+5
|
* Sort include files in the alphabetical order.dchagin2011-02-131-1/+1
|
* Remove comment about 'ftlk' LOR.dchagin2011-02-131-2/+1
|
* Stop printing the LOR, as this is expected behavior.dchagin2011-02-131-1/+1
|
* The bitset field of freshly created futex should be initialized explicity.dchagin2011-02-131-0/+1
| | | | Otherwise, REQUEUE operations fails.
* Rename used_requeue and use it as bitwise field to store more flags.dchagin2011-02-121-2/+2
| | | | Reimplement used_requeue logic with LINUX_XDEPR_REQUEUEOP flag.
* Yet another unimplemented futex operation, print out about.dchagin2011-01-311-0/+7
| | | | | Submitted by: arundel MFC after: 1 month.
* Implement a futex BITSET op.dchagin2011-01-311-25/+44
| | | | | Submitted by: arundel MFC after: 1 month.
* Remove trailing dot from the unimplemented futex messages to makenetchild2010-11-221-5/+5
| | | | | | | them consistent with the syscall and ipc messages. Submitted by: arundel MFC after: 3 days
* Some style(9) fixes.netchild2010-11-151-5/+5
| | | | | Submitted by: arundel MFC after: 1 week
* - print out the PID and program name of the program trying to use annetchild2010-11-151-6/+42
| | | | | | | | | | | | | | | | | unsupported futex operation - for those futex operations which are known to be not supported, print out which futex operation it is - shortcut the error return of the unsupported FUTEX_CLOCK_REALTIME in some cases: FUTEX_CLOCK_REALTIME can be used to tell linux to use CLOCK_REALTIME instead of CLOCK_MONOTONIC. FUTEX_CLOCK_REALTIME however must only be set, if either FUTEX_WAIT_BITSET or FUTEX_WAIT_REQUEUE_PI are set too. If that's not the case we can die with ENOSYS right at the beginning. Submitted by: arundel Reviewed by: rdivacky (earlier iteration of the patch) MFC after: 1 week
* Simplify timeout check in futex_wait() using itimerfix() and return errorjkim2010-10-061-22/+10
| | | | | if the given timeout is invalid. Consistently use int type for timeout and correct a format string in futex_sleep().
* Fix a comparision of an uninitialised pointer.netchild2010-10-061-1/+1
| | | | | | Submitted by: arundel Found by: clang analysis (automatic service by uqs@) Reviewed by: rdivacky
* Remove extraneous semicolons, no functional changes.mbr2010-01-071-1/+1
| | | | | Submitted by: Marc Balmer <marc@msys.ch> MFC after: 1 week
* Unlock process lock when return error from getrobustlist call.dchagin2009-06-141-1/+3
| | | | | | Tested by: Alexander Best <alexbestms at math uni-muenster de> Approved by: kib (mentor) MFC after: 3 days
* Add KTR(9) tracing for futex emulation.dchagin2009-05-071-11/+49
| | | | | Approved by: kib (mentor) MFC after: 1 month
* Move extern variable definitions to the header file.dchagin2009-05-021-1/+1
| | | | | Approved by: kib (mentor) MFC after: 1 month
* Reimplement futexes.dchagin2009-05-011-358/+449
| | | | | | | | | | | | | | | | | | | | Old implemention used Giant to protect the kernel data structures, but at the same time called malloc(M_WAITOK), that could cause the calling thread to sleep and lost Giant protection. User-visible result was the missed wakeup. New implementation uses one sx lock per futex. The sx protects the futex structures and allows to sleep while copyin or copyout are performed. Unlike linux, we return EINVAL when FUTEX_CMP_REQUEUE operation is requested and either caller specified futexes are equial or second futex already exists. This is acceptable since the situation can only occur from the application error, and glibc falls back to old FUTEX_WAKE operation when FUTEX_CMP_REQUEUE returns an error. Approved by: kib (mentor) MFC after: 1 month
* Remove support for FUTEX_REQUEUE operation.dchagin2009-04-191-13/+18
| | | | | | | | | | | | | | | | Glibc does not use this operation since 2.3.3 version (Jun 2004), as it is racy and replaced by FUTEX_CMP_REQUEUE operation. Glibc versions prior to 2.3.3 fall back to FUTEX_WAKE when FUTEX_REQUEUE returned EINVAL. Any application directly using FUTEX_REQUEUE without return value checking are definitely broken. Limit quantity of messages per process about unsupported operation. Approved by: kib (mentor) MFC after: 1 month
* Sort include files in the alphabetical order.dchagin2009-03-161-5/+4
| | | | | Approved by: kib (mentor) MFC after: 2 weeks
* Ignore FUTEX_FD op, as it is done by linux.dchagin2009-03-151-7/+0
| | | | | Approved by: kib (mentor) MFC after: 2 weeks
* Include linux_futex.h before linux_emul.hdchagin2009-03-151-1/+1
| | | | | Approved by: kib (mentor) MFC after: 6 days
* In the robust futexes list head, futex_offset shall be signed,kib2008-11-161-2/+2
| | | | | | and glibc actually supplies negative offsets. Change l_ulong to l_long. Submitted by: dchagin
* Make robust futexes work on linux32/amd64. Use PTRIN to readkib2008-10-141-3/+3
| | | | | | | | user-mode pointers. Change types used in the structures definitions to properly-sized architecture-specific types. Submitted by: dchagin MFC after: 1 week
* Implement robust futexes. Most of the code is modelled afterrdivacky2008-05-131-0/+161
| | | | | | | | | | | what Linux does. This is because robust futexes are mostly userspace thing which we cannot alter. Two syscalls maintain pointer to userspace list and when process exits a routine walks this list waking up processes sleeping on futexes from that list. Reviewed by: kib (mentor) MFC after: 1 month
* o Add stub support for some new futex operations,rdivacky2008-03-201-2/+24
| | | | | | | | | | | | | | | | | so the annoying message is not printed. o Don't warn about FUTEX_FD not being implemented and return ENOSYS instead of 0 (eg. success). o Clear FUTEX_PRIVATE_FLAG as we actually implement only private futexes so there is no reason to return ENOSYS when app asks for a private futex. We don't reject shared futexes because they worked just fine with our implementation so far. Approved by: kib (mentor) Tested by: bsam MFC after: 1 week
* Return ENOSYS instead of 0 for the unknown futex operations.kib2008-03-021-1/+1
| | | | | Submitted by: rdivacky Reported and tested by: Gary Stanley <gary velocity-servers net>
* Move futex support code from <arch>/support.s into linux compat directory.kib2007-05-231-75/+38
| | | | | | | | | | Implement all futex atomic operations in assembler to not depend on the fuword() that does not allow to distinguish between -1 and failure return. Correctly return 0 from atomic operations on success. In collaboration with: rdivacky Tested by: Scot Hetzel <swhetzel gmail com>, Milos Vyletel <mvyletel mzm cz> Sponsored by: Google SoC 2007
* MFP4: Linux futex support for amd64.jkim2007-03-301-87/+129
| | | | | | | Initial patch was submitted by kib and additional work was done by Divacky Roman. Tested by: emulation
* MFp4 (110541):netchild2007-02-251-2/+7
| | | | | | Sync with rev 1.7 in NetBSD. Obtained from: NetBSD
* MFp4 (110523, parts which apply cleanly):netchild2007-02-251-70/+73
| | | | | | | | | semi-automatic style(9) The futex stuff already differs a lot (only a small part does not differ) from NetBSD, so we are already way off and can't apply changes from NetBSD automatically. As we need to merge everything by hand already, we can even make the files comply to our world order.
* Change futex lock from mutex to sx. Make futex_get atomic (protected by thenetchild2006-09-091-8/+4
| | | | | | | | futex lock). Sponsored by: Google SoC 2006 Submitted by: rdivacky Suggested by: jhb
* - don't wake every sleeper just the first one [1]netchild2006-09-091-5/+2
| | | | | | - remove debuging printf [2] Submitted by: intron <mag@intron.ac> [1], rdivacky [2]
* Correct the number of retries in a futex_wake() call.netchild2006-08-261-2/+6
| | | | | Sponsored by: Google SoC 2006 Submitted by: rdivacky
* ifdef DEBUG a printfssouhlal2006-08-191-0/+2
| | | | Submitted by: rdivacky
* Fix the DEBUG build:netchild2006-08-171-2/+3
| | | | | | | | | - linux_emul.c [1] - linux_futex.c [2] Sponsored by: Google SoC 2006 [1] Submitted by: rdivacky [1] netchild [2]
* Add some new files needed for linux 2.6.x compatibility.netchild2006-08-151-0/+500
Please don't style(9) the NetBSD code, we want to stay in sync. Not imported on a vendor branch since we need local changes. Sponsored by: Google SoC 2006 Submitted by: rdivacky With help from: manu@NetBSD.org Obtained from: NetBSD (linux_{futex,time}.*)
OpenPOWER on IntegriCloud