Index: stable/11/lib/libc/sys/_umtx_op.2 =================================================================== --- stable/11/lib/libc/sys/_umtx_op.2 (revision 321144) +++ stable/11/lib/libc/sys/_umtx_op.2 (revision 321145) @@ -1,1427 +1,1427 @@ .\" Copyright (c) 2016 The FreeBSD Foundation, Inc. .\" All rights reserved. .\" .\" This documentation was written by .\" Konstantin Belousov under sponsorship .\" from the FreeBSD Foundation. .\" .\" Redistribution and use in source and binary forms, with or without .\" modification, are permitted provided that the following conditions .\" are met: .\" 1. Redistributions of source code must retain the above copyright .\" notice, this list of conditions and the following disclaimer. .\" 2. Redistributions in binary form must reproduce the above copyright .\" notice, this list of conditions and the following disclaimer in the .\" documentation and/or other materials provided with the distribution. .\" .\" THIS SOFTWARE IS PROVIDED BY THE AUTHORS AND CONTRIBUTORS ``AS IS'' AND .\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE .\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE .\" ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHORS OR CONTRIBUTORS BE LIABLE .\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL .\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS .\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) .\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT .\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY .\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF .\" SUCH DAMAGE. .\" .\" $FreeBSD$ .\" -.Dd May 29, 2016 +.Dd May 23, 2017 .Dt _UMTX_OP 2 .Os .Sh NAME .Nm _umtx_op .Nd interface for implementation of userspace threading synchronization primitives .Sh LIBRARY .Lb libc .Sh SYNOPSIS .In sys/types.h .In sys/umtx.h .Ft int .Fn _umtx_op "void *obj" "int op" "u_long val" "void *uaddr" "void *uaddr2" .Sh DESCRIPTION The .Fn _umtx_op system call provides kernel support for userspace implementation of the threading synchronization primitives. The .Lb libthr uses the syscall to implement .St -p1003.1-2001 pthread locks, like mutexes, condition variables and so on. .Ss STRUCTURES The operations, performed by the .Fn _umtx_op syscall, operate on userspace objects which are described by the following structures. Reserved fields and paddings are omitted. All objects require ABI-mandated alignment, but this is not currently enforced consistently on all architectures. .Pp The following flags are defined for flag fields of all structures: .Bl -tag -width "Dv USYNC_PROCESS_SHARED" .It Dv USYNC_PROCESS_SHARED Allow selection of the process-shared sleep queue for the thread sleep container, when the lock ownership cannot be granted immediately, and the operation must sleep. The process-shared or process-private sleep queue is selected based on the attributes of the memory mapping which contains the first byte of the structure, see .Xr mmap 2 . Otherwise, if the flag is not specified, the process-private sleep queue is selected regardless of the memory mapping attributes, as an optimization. .Pp See the .Sx SLEEP QUEUES subsection below for more details on sleep queues. .El .Pp .Bl -hang -offset indent .It Sy Mutex .Bd -literal struct umutex { volatile lwpid_t m_owner; uint32_t m_flags; uint32_t m_ceilings[2]; uintptr_t m_rb_lnk; }; .Ed .Pp The .Dv m_owner field is the actual lock. It contains either the thread identifier of the lock owner in the locked state, or zero when the lock is unowned. The highest bit set indicates that there is contention on the lock. The constants are defined for special values: .Bl -tag -width "Dv UMUTEX_RB_OWNERDEAD" .It Dv UMUTEX_UNOWNED Zero, the value stored in the unowned lock. .It Dv UMUTEX_CONTESTED The contenion indicator. .It Dv UMUTEX_RB_OWNERDEAD A thread owning the robust mutex terminated. The mutex is in unlocked state. .It Dv UMUTEX_RB_NOTRECOV The robust mutex is in a non-recoverable state. It cannot be locked until reinitialized. .El .Pp The .Dv m_flags field may contain the following umutex-specific flags, in addition to the common flags: .Bl -tag -width "Dv UMUTEX_NONCONSISTENT" .It Dv UMUTEX_PRIO_INHERIT Mutex implements .Em Priority Inheritance protocol. .It Dv UMUTEX_PRIO_PROTECT Mutex implements .Em Priority Protection protocol. .It Dv UMUTEX_ROBUST Mutex is robust, as described in the .Sx ROBUST UMUTEXES section below. .It Dv UMUTEX_NONCONSISTENT Robust mutex is in a transient non-consistent state. Not used by kernel. .El .Pp In the manual page, mutexes not having .Dv UMUTEX_PRIO_INHERIT and .Dv UMUTEX_PRIO_PROTECT flags set, are called normal mutexes. Each type of mutex, i.e. normal mutexes, priority-inherited mutexes, and priority-protected mutexes, have a separate sleep queue associated with the given key. .Pp For priority protected mutexes, the .Dv m_ceilings array contains priority ceiling values. The .Dv m_ceilings[0] is the ceiling value for the mutex, as specified by .St -p1003.1-2008 for the .Em Priority Protected mutex protocol. The .Dv m_ceilings[1] is used only for the unlock of a priority protected mutex, when unlock is done in an order other than the reversed lock order. In this case, .Dv m_ceilings[1] must contain the ceiling value for the last locked priority protected mutex, for proper priority reassignment. If, instead, the unlocking mutex was the last priority propagated mutex locked by the thread, .Dv m_ceilings[1] should contain \-1. This is required because kernel does not maintain the ordered lock list. .It Sy Condition variable .Bd -literal struct ucond { volatile uint32_t c_has_waiters; uint32_t c_flags; uint32_t c_clockid; }; .Ed .Pp A non-zero .Dv c_has_waiters value indicates that there are in-kernel waiters for the condition, executing the .Dv UMTX_OP_CV_WAIT request. .Pp The .Dv c_flags field contains flags. Only the common flags, i.e. .Dv USYNC_PROCESS_SHARED , are defined for ucond. .Pp The .Dv c_clockid member provides the clock identifier to use for timeout, when the .Dv UMTX_OP_CV_WAIT request has both the .Dv CVWAIT_CLOCKID flag and the timeout specified. Valid clock identifiers are subset of the valid clock ids for the .Xr clock_gettime 2 syscall, namely, .Dv CLOCK_REALTIME , .Dv CLOCK_VIRTUAL , .Dv CLOCK_PROF , .Dv CLOCK_MONOTONIC , .Dv CLOCK_UPTIME , .Dv CLOCK_UPTIME_PRECISE , .Dv CLOCK_UPTIME_FAST , .Dv CLOCK_REALTIME_PRECISE , .Dv CLOCK_REALTIME_FAST , .Dv CLOCK_MONOTONIC_PRECISE , .Dv CLOCK_MONOTONIC_FAST , and .Dv CLOCK_SECOND are allowed. .It Sy Reader/writer lock .Bd -literal struct urwlock { volatile int32_t rw_state; uint32_t rw_flags; uint32_t rw_blocked_readers; uint32_t rw_blocked_writers; }; .Ed .Pp The .Dv rw_state field is the actual lock. It contains both the flags and counter of the read locks which were granted. Names of the .Dv rw_state bits are following: .Bl -tag -width "Dv URWLOCK_WRITE_WAITERS" .It Dv URWLOCK_WRITE_OWNER Write lock was granted. .It Dv URWLOCK_WRITE_WAITERS There are write lock waiters. .It Dv URWLOCK_READ_WAITERS There are read lock waiters. .It Dv URWLOCK_READER_COUNT(c) Returns the count of currently granted read locks. .El .Pp At any given time there may be only one thread to which the writer lock is granted on the .Vt struct rwlock , and no threads are granted read lock. Or, at the given time, up to .Dv URWLOCK_MAX_READERS threads may be granted the read lock simultaneously, but write lock is not granted to any thread. .Pp The following flags for the .Dv rw_flags member of .Vt struct urwlock are defined, in addition to the common flags: .Bl -tag -width "Dv URWLOCK_PREFER_READER" .It Dv URWLOCK_PREFER_READER If specified, immediately grant read lock requests when .Dv urwlock is already read-locked, even in presence of unsatisfied write lock requests. By default, if there is a write lock waiter, further read requests are not granted, to prevent unfair write lock waiter starvation. .El .Pp The .Dv rw_blocked_readers and .Dv rw_blocked_writers members contain the count of threads which are sleeping in kernel, waiting for the associated request type to be granted. The fields are used by kernel to update the .Dv URWLOCK_READ_WAITERS and .Dv URWLOCK_WRITE_WAITERS flags of the .Dv rw_state lock after requesting thread was woken up. .It Sy Semaphore .Bd -literal struct _usem2 { volatile uint32_t _count; uint32_t _flags; }; .Ed .Pp The .Dv _count word represents a counting semaphore. A non-zero value indicates an unlocked (posted) semaphore, while zero represents the locked state. The maximal supported semaphore count is .Dv USEM_MAX_COUNT . .Pp The .Dv _count word, besides the counter of posts (unlocks), also contains the .Dv USEM_HAS_WAITERS bit, which indicates that locked semaphore has waiting threads. .Pp The .Dv USEM_COUNT() macro, applied to the .Dv _count word, returns the current semaphore counter, i.e. the number of posts issued on the semaphore. .Pp The following bits for the .Dv _flags member of .Vt struct _usem2 are defined, in addition to the common flags: .Bl -tag -width "Dv USEM_NAMED" .It Dv USEM_NAMED Flag is ignored by kernel. .El .It Sy Timeout parameter .Bd -literal struct _umtx_time { struct timespec _timeout; uint32_t _flags; uint32_t _clockid; }; .Ed .Pp Several .Fn _umtx_op operations allow the blocking time to be limited, failing the request if it cannot be satisfied in the specified time period. The timeout is specified by passing either the address of .Vt struct timespec , or its extended variant, .Vt struct _umtx_time , as the .Fa uaddr2 argument of .Fn _umtx_op . They are distinguished by the .Fa uaddr value, which must be equal to the size of the structure pointed to by .Fa uaddr2 , casted to .Vt uintptr_t . .Pp The .Dv _timeout member specifies the time when the timeout should occur. Legal values for clock identifier .Dv _clockid are shared with the .Fa clock_id argument to the .Xr clock_gettime 2 function, and use the same underlying clocks. The specified clock is used to obtain the current time value. Interval counting is always performed by the monotonic wall clock. .Pp The .Dv _flags argument allows the following flags to further define the timeout behaviour: .Bl -tag -width "It Dv UMTX_ABSTIME" .It Dv UMTX_ABSTIME The .Dv _timeout value is the absolute time. The thread will be unblocked and the request failed when specified clock value is equal or exceeds the .Dv _timeout. .Pp If the flag is absent, the timeout value is relative, that is the amount of time, measured by the monotonic wall clock from the moment of the request start. .El .El .Ss SLEEP QUEUES .Pp When a locking request cannot be immediately satisfied, the thread is typically put to .Em sleep , which is a non-runnable state terminated by the .Em wake operation. Lock operations include a .Em try variant which returns an error rather than sleeping if the lock cannot be obtained. Also, .Fn _umtx_op provides requests which explicitly put the thread to sleep. .Pp Wakes need to know which threads to make runnable, so sleeping threads are grouped into containers called .Em sleep queues . A sleep queue is identified by a key, which for .Fn _umtx_op is defined as the physical address of some variable. Note that the .Em physical address is used, which means that same variable mapped multiple times will give one key value. This mechanism enables the construction of .Em process-shared locks. .Pp A related attribute of the key is shareability. Some requests always interpret keys as private for the current process, creating sleep queues with the scope of the current process even if the memory is shared. Others either select the shareability automatically from the mapping attributes, or take additional input as the .Dv USYNC_PROCESS_SHARED common flag. This is done as optimization, allowing the lock scope to be limited regardless of the kind of backing memory. .Pp Only the address of the start byte of the variable specified as key is important for determining corresponding sleep queue. The size of the variable does not matter, so e.g. sleep on the same address interpeted as .Vt uint32_t and .Vt long on a little-endian 64-bit platform would collide. .Pp The last attribute of the key is the object type. The sleep queue to which a sleeping thread is assigned is an individual one for simple wait requests, mutexes, rwlocks, condvars and other primitives, even when the physical address of the key is same. .Pp When waking up a limited number of threads from a given sleep queue, the highest priority threads that have been blocked for the longest on the queue are selected. .Ss ROBUST UMUTEXES The .Em robust umutexes are provided as a substrate for a userspace library to implement .Tn POSIX robust mutexes. A robust umutex must have the .Dv UMUTEX_ROBUST flag set. .Pp On thread termination, the kernel walks two lists of mutexes. The two lists head addresses must be provided by a prior call to .Dv UMTX_OP_ROBUST_LISTS request. The lists are singly-linked. The link to next element is provided by the .Dv m_rb_lnk member of the .Vt struct umutex . .Pp Robust list processing is aborted if the kernel finds a mutex with any of the following conditions: .Bl -dash -offset indent -compact .It the .Dv UMUTEX_ROBUST flag is not set .It not owned by the current thread, except when the mutex is pointed to by the .Dv robust_inactive member of the .Vt struct umtx_robust_lists_params , registered for the current thread .It the combination of mutex flags is invalid .It read of the umutex memory faults .It the list length limit described in .Xr libthr 3 is reached. .El .Pp Every mutex in both lists is unlocked as if the .Dv UMTX_OP_MUTEX_UNLOCK request is performed on it, but instead of the .Dv UMUTEX_UNOWNED value, the .Dv m_owner field is written with the .Dv UMUTEX_RB_OWNERDEAD value. When a mutex in the .Dv UMUTEX_RB_OWNERDEAD state is locked by kernel due to the .Dv UMTX_OP_MUTEX_TRYLOCK and .Dv UMTX_OP_MUTEX_LOCK requests, the lock is granted and .Er EOWNERDEAD error is returned. .Pp Also, the kernel handles the .Dv UMUTEX_RB_NOTRECOV value of .Dv the m_owner field specially, always returning the .Er ENOTRECOVERABLE error for lock attempts, without granting the lock. .Ss OPERATIONS The following operations, requested by the .Fa op argument to the function, are implemented: .Bl -tag -width "It Dv UMTX_OP_WAIT_UINT_PRIVATE" .It Dv UMTX_OP_WAIT Wait. The arguments for the request are: .Bl -tag -width "It Fa obj" .It Fa obj Pointer to a variable of type .Vt long . .It Fa val Current value of the .Dv *obj . .El .Pp The current value of the variable pointed to by the .Fa obj argument is compared with the .Fa val . If they are equal, the requesting thread is put to interruptible sleep until woken up or the optionally specified timeout expires. .Pp The comparison and sleep are atomic. In other words, if another thread writes a new value to .Dv *obj and then issues .Dv UMTX_OP_WAKE , the request is guaranteed to not miss the wakeup, which might otherwise happen between comparison and blocking. .Pp The physical address of memory where the .Fa *obj variable is located, is used as a key to index sleeping threads. .Pp The read of the current value of the .Dv *obj variable is not guarded by barriers. In particular, it is the user's duty to ensure the lock acquire and release memory semantics, if the .Dv UMTX_OP_WAIT and .Dv UMTX_OP_WAKE requests are used as a substrate for implementing a simple lock. .Pp The request is not restartable. An unblocked signal delivered during the wait always results in sleep interruption and .Er EINTR error. .Pp Optionally, a timeout for the request may be specified. .It Dv UMTX_OP_WAKE Wake the threads possibly sleeping due to .Dv UMTX_OP_WAIT . The arguments for the request are: .Bl -tag -width "It Fa obj" .It Fa obj Pointer to a variable, used as a key to find sleeping threads. .It Fa val Up to .Fa val threads are woken up by this request. Specify .Dv INT_MAX to wake up all waiters. .El .It Dv UMTX_OP_MUTEX_TRYLOCK Try to lock umutex. The arguments to the request are: .Bl -tag -width "It Fa obj" .It Fa obj Pointer to the umutex. .El .Pp Operates same as the .Dv UMTX_OP_MUTEX_LOCK request, but returns .Er EBUSY instead of sleeping if the lock cannot be obtained immediately. .It Dv UMTX_OP_MUTEX_LOCK Lock umutex. The arguments to the request are: .Bl -tag -width "It Fa obj" .It Fa obj Pointer to the umutex. .El .Pp Locking is performed by writing the current thread id into the .Dv m_owner word of the .Vt struct umutex . The write is atomic, preserves the .Dv UMUTEX_CONTESTED contention indicator, and provides the acquire barrier for lock entrance semantic. .Pp If the lock cannot be obtained immediately because another thread owns the lock, the current thread is put to sleep, with .Dv UMUTEX_CONTESTED bit set before. Upon wake up, the lock conditions are re-tested. .Pp The request adheres to the priority protection or inheritance protocol of the mutex, specified by the .Dv UMUTEX_PRIO_PROTECT or .Dv UMUTEX_PRIO_INHERIT flag, respectively. .Pp Optionally, a timeout for the request may be specified. .Pp A request with a timeout specified is not restartable. An unblocked signal delivered during the wait always results in sleep interruption and .Er EINTR error. A request without timeout specified is always restarted after return from a signal handler. .It Dv UMTX_OP_MUTEX_UNLOCK Unlock umutex. The arguments to the request are: .Bl -tag -width "It Fa obj" .It Fa obj Pointer to the umutex. .El .Pp Unlocks the mutex, by writing .Dv UMUTEX_UNOWNED (zero) value into .Dv m_owner word of the .Vt struct umutex . The write is done with a release barrier, to provide lock leave semantic. .Pp If there are threads sleeping in the sleep queue associated with the umutex, one thread is woken up. If more than one thread sleeps in the sleep queue, the .Dv UMUTEX_CONTESTED bit is set together with the write of the .Dv UMUTEX_UNOWNED value into .Dv m_owner . .Pp The request adheres to the priority protection or inheritance protocol of the mutex, specified by the .Dv UMUTEX_PRIO_PROTECT or .Dv UMUTEX_PRIO_INHERIT flag, respectively. See description of the .Dv m_ceilings member of the .Vt struct umutex structure for additional details of the request operation on the priority protected protocol mutex. .It Dv UMTX_OP_SET_CEILING Set ceiling for the priority protected umutex. The arguments to the request are: .Bl -tag -width "It Fa obj" .It Fa obj Pointer to the umutex. .It Fa val New ceiling value. .It Fa uaddr Address of a variable of type .Vt uint32_t . If not .Dv NULL and the update was successful, the previous ceiling value is written to the location pointed to by .Fa uaddr . .El .Pp The request locks the umutex pointed to by the .Fa obj parameter, waiting for the lock if not immediately available. After the lock is obtained, the new ceiling value .Fa val is written to the .Dv m_ceilings[0] member of the .Vt struct umutex, after which the umutex is unlocked. .Pp The locking does not adhere to the priority protect protocol, to conform to the .Tn POSIX requirements for the .Xr pthread_mutex_setprioceiling 3 interface. .It Dv UMTX_OP_CV_WAIT Wait for a condition. The arguments to the request are: .Bl -tag -width "It Fa uaddr2" .It Fa obj Pointer to the .Vt struct ucond . .It Fa val Request flags, see below. .It Fa uaddr Pointer to the umutex. .It Fa uaddr2 Optional pointer to a .Vt struct timespec for timeout specification. .El .Pp The request must be issued by the thread owning the mutex pointed to by the .Fa uaddr argument. The .Dv c_hash_waiters member of the .Vt struct ucond , pointed to by the .Fa obj argument, is set to an arbitrary non-zero value, after which the .Fa uaddr mutex is unlocked (following the appropriate protocol), and the current thread is put to sleep on the sleep queue keyed by the .Fa obj argument. The operations are performed atomically. It is guaranteed to not miss a wakeup from .Dv UMTX_OP_CV_SIGNAL or .Dv UMTX_OP_CV_BROADCAST sent between mutex unlock and putting the current thread on the sleep queue. .Pp Upon wakeup, if the timeout expired and no other threads are sleeping in the same sleep queue, the .Dv c_hash_waiters member is cleared. After wakeup, the .Fa uaddr umutex is not relocked. .Pp The following flags are defined: .Bl -tag -width "Dv CVWAIT_CLOCKID" .It Dv CVWAIT_ABSTIME Timeout is absolute. .It Dv CVWAIT_CLOCKID Clockid is provided. .El .Pp Optionally, a timeout for the request may be specified. Unlike other requests, the timeout value is specified directly by a .Vt struct timespec , pointed to by the .Fa uaddr2 argument. If the .Dv CVWAIT_CLOCKID flag is provided, the timeout uses the clock from the .Dv c_clockid member of the .Vt struct ucond , pointed to by .Fa obj argument. Otherwise, .Dv CLOCK_REALTIME is used, regardless of the clock identifier possibly specified in the .Vt struct _umtx_time . If the .Dv CVWAIT_ABSTIME flag is supplied, the timeout specifies absolute time value, otherwise it denotes a relative time interval. .Pp The request is not restartable. An unblocked signal delivered during the wait always results in sleep interruption and .Er EINTR error. .It Dv UMTX_OP_CV_SIGNAL Wake up one condition waiter. The arguments to the request are: .Bl -tag -width "It Fa obj" .It Fa obj Pointer to .Vt struct ucond . .El .Pp The request wakes up at most one thread sleeping on the sleep queue keyed by the .Fa obj argument. If the woken up thread was the last on the sleep queue, the .Dv c_has_waiters member of the .Vt struct ucond is cleared. .It Dv UMTX_OP_CV_BROADCAST Wake up all condition waiters. The arguments to the request are: .Bl -tag -width "It Fa obj" .It Fa obj Pointer to .Vt struct ucond . .El .Pp The request wakes up all threads sleeping on the sleep queue keyed by the .Fa obj argument. The .Dv c_has_waiters member of the .Vt struct ucond is cleared. .It Dv UMTX_OP_WAIT_UINT Same as .Dv UMTX_OP_WAIT , but the type of the variable pointed to by .Fa obj is .Vt u_int , i.e. 32-bit integer. .It Dv UMTX_OP_RW_RDLOCK Read-lock a .Vt struct rwlock lock. The arguments to the request are: .Bl -tag -width "It Fa obj" .It Fa obj Pointer to the lock (of type .Vt struct rwlock ) to be read-locked. .It Fa val Additional flags to augment locking behaviour. The valid flags in the .Fa val argument are: .Bl -tag -width "It Dv URWLOCK_PREFER_READER" .It Dv URWLOCK_PREFER_READER .El .El .Pp The request obtains the read lock on the specified .Vt struct rwlock by incrementing the count of readers in the .Dv rw_state word of the structure. If the .Dv URWLOCK_WRITE_OWNER bit is set in the word .Dv rw_state , the lock was granted to a writer which has not yet relinquished its ownership. In this case the current thread is put to sleep until it makes sense to retry. .Pp If the .Dv URWLOCK_PREFER_READER flag is set either in the .Dv rw_flags word of the structure, or in the .Fa val argument of the request, the presence of the threads trying to obtain the write lock on the same structure does not prevent the current thread from trying to obtain the read lock. Otherwise, if the flag is not set, and the .Dv URWLOCK_WRITE_WAITERS flag is set in .Dv rw_state , the current thread does not attempt to obtain read-lock. Instead it sets the .Dv URWLOCK_READ_WAITERS in the .Dv rw_state word and puts itself to sleep on corresponding sleep queue. Upon wakeup, the locking conditions are re-evaluated. .Pp Optionally, a timeout for the request may be specified. .Pp The request is not restartable. An unblocked signal delivered during the wait always results in sleep interruption and .Er EINTR error. .It Dv UMTX_OP_RW_WRLOCK Write-lock a .Vt struct rwlock lock. The arguments to the request are: .Bl -tag -width "It Fa obj" .It Fa obj Pointer to the lock (of type .Vt struct rwlock ) to be write-locked. .El .Pp The request obtains a write lock on the specified .Vt struct rwlock , by setting the .Dv URWLOCK_WRITE_OWNER bit in the .Dv rw_state word of the structure. If there is already a write lock owner, as indicated by the .Dv URWLOCK_WRITE_OWNER bit being set, or there are read lock owners, as indicated by the read-lock counter, the current thread does not attempt to obtain the write-lock. Instead it sets the .Dv URWLOCK_WRITE_WAITERS in the .Dv rw_state word and puts itself to sleep on corresponding sleep queue. Upon wakeup, the locking conditions are re-evaluated. .Pp Optionally, a timeout for the request may be specified. .Pp The request is not restartable. An unblocked signal delivered during the wait always results in sleep interruption and .Er EINTR error. .It Dv UMTX_OP_RW_UNLOCK Unlock rwlock. The arguments to the request are: .Bl -tag -width "It Fa obj" .It Fa obj Pointer to the lock (of type .Vt struct rwlock ) to be unlocked. .El .Pp The unlock type (read or write) is determined by the current lock state. Note that the .Vt struct rwlock does not save information about the identity of the thread which acquired the lock. .Pp If there are pending writers after the unlock, and the .Dv URWLOCK_PREFER_READER flag is not set in the .Dv rw_flags member of the .Fa *obj structure, one writer is woken up, selected as described in the .Sx SLEEP QUEUES subsection. If the .Dv URWLOCK_PREFER_READER flag is set, a pending writer is woken up only if there is no pending readers. .Pp If there are no pending writers, or, in the case that the .Dv URWLOCK_PREFER_READER flag is set, then all pending readers are woken up by unlock. .It Dv UMTX_OP_WAIT_UINT_PRIVATE Same as .Dv UMTX_OP_WAIT_UINT , but unconditionally select the process-private sleep queue. .It Dv UMTX_OP_WAKE_PRIVATE Same as .Dv UMTX_OP_WAKE , but unconditionally select the process-private sleep queue. .It Dv UMTX_OP_MUTEX_WAIT Wait for mutex availability. The arguments to the request are: .Bl -tag -width "It Fa obj" .It Fa obj Address of the mutex. .El .Pp Similarly to the .Dv UMTX_OP_MUTEX_LOCK , put the requesting thread to sleep if the mutex lock cannot be obtained immediately. The .Dv UMUTEX_CONTESTED bit is set in the .Dv m_owner word of the mutex to indicate that there is a waiter, before the thread is added to the sleep queue. Unlike the .Dv UMTX_OP_MUTEX_LOCK request, the lock is not obtained. .Pp The operation is not implemented for priority protected and priority inherited protocol mutexes. .Pp Optionally, a timeout for the request may be specified. .Pp .Pp A request with a timeout specified is not restartable. An unblocked signal delivered during the wait always results in sleep interruption and .Er EINTR error. A request without a timeout automatically restarts if the signal disposition requested restart via the .Dv SA_RESTART flag in .Vt struct sigaction member .Dv sa_flags . .It Dv UMTX_OP_NWAKE_PRIVATE Wake up a batch of sleeping threads. The arguments to the request are: .Bl -tag -width "It Fa obj" .It Fa obj Pointer to the array of pointers. .It Fa val Number of elements in the array pointed to by .Fa obj . .El .Pp For each element in the array pointed to by .Fa obj , wakes up all threads waiting on the .Em private sleep queue with the key being the byte addressed by the array element. .It Dv UMTX_OP_MUTEX_WAKE Check if a normal umutex is unlocked and wake up a waiter. The arguments for the request are: .Bl -tag -width "It Fa obj" .It Fa obj Pointer to the umutex. .El .Pp If the .Dv m_owner word of the mutex pointed to by the .Fa obj argument indicates unowned mutex, which has its contention indicator bit .Dv UMUTEX_CONTESTED set, clear the bit and wake up one waiter in the sleep queue associated with the byte addressed by the .Fa obj , if any. Only normal mutexes are supported by the request. The sleep queue is always one for a normal mutex type. .Pp This request is deprecated in favor of .Dv UMTX_OP_MUTEX_WAKE2 since mutexes using it cannot synchronize their own destruction. That is, the .Dv m_owner word has already been set to .Dv UMUTEX_UNOWNED when this request is made, so that another thread can lock, unlock and destroy the mutex (if no other thread uses the mutex afterwards). Clearing the .Dv UMUTEX_CONTESTED bit may then modify freed memory. .It Dv UMTX_OP_MUTEX_WAKE2 Check if a umutex is unlocked and wake up a waiter. The arguments for the request are: .Bl -tag -width "It Fa obj" .It Fa obj Pointer to the umutex. .It Fa val The umutex flags. .El .Pp The request does not read the .Dv m_flags member of the .Vt struct umutex ; instead, the .Fa val argument supplies flag information, in particular, to determine the sleep queue where the waiters are found for wake up. .Pp If the mutex is unowned, one waiter is woken up. .Pp If the mutex memory cannot be accessed, all waiters are woken up. .Pp If there is more than one waiter on the sleep queue, or there is only one waiter but the mutex is owned by a thread, the .Dv UMUTEX_CONTESTED bit is set in the .Dv m_owner word of the .Vt struct umutex . .It Dv UMTX_OP_SEM2_WAIT Wait until semaphore is available. The arguments to the request are: .Bl -tag -width "It Fa obj" .It Fa obj Pointer to the semaphore (of type .Vt struct _usem2 ) . .El Put the requesting thread onto a sleep queue if the semaphore counter is zero. If the thread is put to sleep, the .Dv USEM_HAS_WAITERS bit is set in the .Dv _count word to indicate waiters. The function returns either due to .Dv _count indicating the semaphore is available (non-zero count due to post), or due to a wakeup. The return does not guarantee that the semaphore is available, nor does it consume the semaphore lock on successful return. .Pp Optionally, a timeout for the request may be specified. .Pp A request with non-absolute timeout value is not restartable. An unblocked signal delivered during such wait results in sleep interruption and .Er EINTR error. .It Dv UMTX_OP_SEM2_WAKE Wake up waiters on semaphore lock. The arguments to the request are: .Bl -tag -width "It Fa obj" .It Fa obj Pointer to the semaphore (of type .Vt struct _usem2 ) . .El .Pp The request wakes up one waiter for the semaphore lock. The function does not increment the semaphore lock count. If the .Dv USEM_HAS_WAITERS bit was set in the .Dv _count word, and the last sleeping thread was woken up, the bit is cleared. .It Dv UMTX_OP_SHM Manage anonymous .Tn POSIX shared memory objects (see .Xr shm_open 2 ) , which can be attached to a byte of physical memory, mapped into the process address space. The objects are used to implement process-shared locks in .Dv libthr . .Pp The .Fa val argument specifies the sub-request of the .Dv UMTX_OP_SHM request: .Bl -tag -width "Dv UMTX_SHM_DESTROY" .It Dv UMTX_SHM_CREAT Creates the anonymous shared memory object, which can be looked up with the specified key .Fa uaddr. If the object associated with the .Fa uaddr key already exists, it is returned instead of creating a new object. The object's size is one page. On success, the file descriptor referencing the object is returned. The descriptor can be used for mapping the object using .Xr mmap 2 , or for other shared memory operations. .It Dv UMTX_SHM_LOOKUP Same as .Dv UMTX_SHM_CREATE request, but if there is no shared memory object associated with the specified key .Fa uaddr , an error is returned, and no new object is created. .It Dv UMTX_SHM_DESTROY De-associate the shared object with the specified key .Fa uaddr. The object is destroyed after the last open file descriptor is closed and the last mapping for it is destroyed. .It Dv UMTX_SHM_ALIVE Checks whether there is a live shared object associated with the supplied key .Fa uaddr . Returns zero if there is, and an error otherwise. This request is an optimization of the .Dv UMTX_SHM_LOOKUP request. It is cheaper when only the liveness of the associated object is asked for, since no file descriptor is installed in the process fd table on success. .El .Pp The .Fa uaddr argument specifies the virtual address, which backing physical memory byte identity is used as a key for the anonymous shared object creation or lookup. .It Dv UMTX_OP_ROBUST_LISTS Register the list heads for the current thread's robust mutex lists. The arguments to the request are: .Bl -tag -width "It Fa obj" .It Fa val Size of the structure passed in the .Fa uaddr argument. .It Fa uaddr Pointer to the structure of type .Vt struct umtx_robust_lists_params . .El .Pp The structure is defined as .Bd -literal struct umtx_robust_lists_params { uintptr_t robust_list_offset; uintptr_t robust_priv_list_offset; uintptr_t robust_inact_offset; }; .Ed .Pp The .Dv robust_list_offset member contains address of the first element in the list of locked robust shared mutexes. The .Dv robust_priv_list_offset member contains address of the first element in the list of locked robust private mutexes. The private and shared robust locked lists are split to allow fast termination of the shared list on fork, in the child. .Pp The .Dv robust_inact_offset contains a pointer to the mutex which might be locked in nearby future, or might have been just unlocked. It is typically set by the lock or unlock mutex implementation code around the whole operation, since lists can be only changed race-free when the thread owns the mutex. The kernel inspects the .Dv robust_inact_offset in addition to walking the shared and private lists. Also, the mutex pointed to by .Dv robust_inact_offset is handled more loosely at the thread termination time, than other mutexes on the list. That mutex is allowed to be not owned by the current thread, in which case list processing is continued. See .Sx ROBUST UMUTEXES subsection for details. .El .Sh RETURN VALUES If successful, all requests, except .Dv UMTX_SHM_CREAT and .Dv UMTX_SHM_LOOKUP sub-requests of the .Dv UMTX_OP_SHM request, will return zero. The .Dv UMTX_SHM_CREAT and .Dv UMTX_SHM_LOOKUP return a shared memory file descriptor on success. On error \-1 is returned, and the .Va errno variable is set to indicate the error. .Sh ERRORS The .Fn _umtx_op operations will return the following errors: .Bl -tag -width "Bq Er ENOTRECOVERABLE" .It Bq Er EFAULT One of the arguments point to invalid memory. .It Bq Er EINVAL The clock identifier, specified for the .Vt struct _umtx_time timeout parameter, or in the .Dv c_clockid member of .Vt struct ucond, is invalid. .It Bq Er EINVAL The type of the mutex, encoded by the .Dv m_flags member of .Vt struct umutex , is invalid. .It Bq Er EINVAL The .Dv m_owner member of the .Vt struct umutex has changed the lock owner thread identifier during unlock. .It Bq Er EINVAL The .Dv timeout.tv_sec or .Dv timeout.tv_nsec member of .Vt struct _umtx_time is less than zero, or .Dv timeout.tv_nsec is greater than 1000000000. .It Bq Er EINVAL The .Fa op argument specifies invalid operation. .It Bq Er EINVAL The .Fa uaddr argument for the .Dv UMTX_OP_SHM request specifies invalid operation. .It Bq Er EINVAL The .Dv UMTX_OP_SET_CEILING request specifies non priority protected mutex. .It Bq Er EINVAL The new ceiling value for the .Dv UMTX_OP_SET_CEILING request, or one or more of the values read from the .Dv m_ceilings array during lock or unlock operations, is greater than .Dv RTP_PRIO_MAX . .It Bq Er EPERM Unlock attempted on an object not owned by the current thread. .It Bq Er EOWNERDEAD The lock was requested on an umutex where the .Dv m_owner field was set to the .Dv UMUTEX_RB_OWNERDEAD value, indicating terminated robust mutex. The lock was granted to the caller, so this error in fact indicates success with additional conditions. .It Bq Er ENOTRECOVERABLE The lock was requested on an umutex which .Dv m_owner field is equal to the .Dv UMUTEX_RB_NOTRECOV value, indicating abandoned robust mutex after termination. The lock was not granted to the caller. .It Bq Er ENOTTY The shared memory object, associated with the address passed to the .Dv UMTX_SHM_ALIVE sub-request of .Dv UMTX_OP_SHM request, was destroyed. .It Bq Er ESRCH For the .Dv UMTX_SHM_LOOKUP , .Dv UMTX_SHM_DESTROY , and .Dv UMTX_SHM_ALIVE sub-requests of the .Dv UMTX_OP_SHM request, there is no shared memory object associated with the provided key. .It Bq Er ENOMEM The .Dv UMTX_SHM_CREAT sub-request of the .Dv UMTX_OP_SHM request cannot be satisfied, because allocation of the shared memory object would exceed the .Dv RLIMIT_UMTXP resource limit, see .Xr setrlimit 2 . .It Bq Er EAGAIN The maximum number of readers .Dv ( URWLOCK_MAX_READERS ) were already granted ownership of the given .Vt struct rwlock for read. .It Bq Er EBUSY A try mutex lock operation was not able to obtain the lock. .It Bq Er ETIMEDOUT The request specified a timeout in the .Fa uaddr and .Fa uaddr2 arguments, and timed out before obtaining the lock or being woken up. .It Bq Er EINTR A signal was delivered during wait, for a non-restartable operation. Operations with timeouts are typically non-restartable, but timeouts specified in absolute time may be restartable. .It Bq Er ERESTART A signal was delivered during wait, for a restartable operation. Mutex lock requests without timeout specified are restartable. The error is not returned to userspace code since restart is handled by usual adjustment of the instruction counter. .El -.Sh BUGS -A window between a unlocking robust mutex and resetting the pointer in the -.Dv robust_inact_offset -member of the registered -.Vt struct umtx_robust_lists_params -allows another thread to destroy the mutex, thus making the kernel inspect -freed or reused memory. -The -.Li libthr -implementation is only vulnerable to this race when operating on -a shared mutex. -A possible fix for the current implementation is to strengthen the checks -for shared mutexes before terminating them, in particular, verifying -that the mutex memory is mapped from a shared memory object allocated -by the -.Dv UMTX_OP_SHM -request. -This is not done because it is believed that the race is adequately -covered by other consistency checks, while adding the check would -prevent alternative implementations of -.Li libpthread . .Sh SEE ALSO .Xr clock_gettime 2 , .Xr mmap 2 , -.Xr shm_open 2 , .Xr setrlimit 2 , +.Xr shm_open 2 , .Xr sigaction 2 , .Xr thr_exit 2 , .Xr thr_kill 2 , .Xr thr_kill2 2 , .Xr thr_new 2 , .Xr thr_self 2 , .Xr thr_set_name 2 , .Xr signal 3 .Sh STANDARDS The .Fn _umtx_op system call is non-standard and is used by the .Lb libthr to implement .St -p1003.1-2001 .Xr pthread 3 functionality. +.Sh BUGS +A window between a unlocking robust mutex and resetting the pointer in the +.Dv robust_inact_offset +member of the registered +.Vt struct umtx_robust_lists_params +allows another thread to destroy the mutex, thus making the kernel inspect +freed or reused memory. +The +.Li libthr +implementation is only vulnerable to this race when operating on +a shared mutex. +A possible fix for the current implementation is to strengthen the checks +for shared mutexes before terminating them, in particular, verifying +that the mutex memory is mapped from a shared memory object allocated +by the +.Dv UMTX_OP_SHM +request. +This is not done because it is believed that the race is adequately +covered by other consistency checks, while adding the check would +prevent alternative implementations of +.Li libpthread . Index: stable/11/lib/libc/sys/cap_enter.2 =================================================================== --- stable/11/lib/libc/sys/cap_enter.2 (revision 321144) +++ stable/11/lib/libc/sys/cap_enter.2 (revision 321145) @@ -1,155 +1,155 @@ .\" .\" Copyright (c) 2008-2009 Robert N. M. Watson .\" All rights reserved. .\" .\" This software was developed at the University of Cambridge Computer .\" Laboratory with support from a grant from Google, Inc. .\" .\" Redistribution and use in source and binary forms, with or without .\" modification, are permitted provided that the following conditions .\" are met: .\" 1. Redistributions of source code must retain the above copyright .\" notice, this list of conditions and the following disclaimer. .\" 2. Redistributions in binary form must reproduce the above copyright .\" notice, this list of conditions and the following disclaimer in the .\" documentation and/or other materials provided with the distribution. .\" .\" THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND .\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE .\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE .\" ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE .\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL .\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS .\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) .\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT .\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY .\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF .\" SUCH DAMAGE. .\" .\" $FreeBSD$ .\" -.Dd September 27, 2016 +.Dd May 23, 2017 .Dt CAP_ENTER 2 .Os .Sh NAME .Nm cap_enter , .Nm cap_getmode .Nd Capability mode system calls .Sh LIBRARY .Lb libc .Sh SYNOPSIS .In sys/capsicum.h .Ft int .Fn cap_enter "void" .Ft int .Fn cap_getmode "u_int *modep" .Sh DESCRIPTION .Fn cap_enter places the current process into capability mode, a mode of execution in which processes may only issue system calls operating on file descriptors or reading limited global system state. Access to global name spaces, such as file system or IPC name spaces, is prevented. If the process is already in a capability mode sandbox, the system call is a no-op. Future process descendants created with .Xr fork 2 or .Xr pdfork 2 will be placed in capability mode from inception. .Pp When combined with .Xr cap_rights_limit 2 , .Xr cap_ioctls_limit 2 , .Xr cap_fcntls_limit 2 , .Fn cap_enter may be used to create kernel-enforced sandboxes in which appropriately-crafted applications or application components may be run. .Pp .Fn cap_getmode returns a flag indicating whether or not the process is in a capability mode sandbox. .Sh RUN-TIME SETTINGS If the .Dv kern.trap_enocap sysctl MIB is set to a non-zero value, then for any process executing in a capability mode sandbox, any syscall which results in either an .Er ENOTCAPABLE or .Er ECAPMODE error also generates the synchronous .Dv SIGTRAP signal to the thread on the syscall return. On signal delivery, the .Va si_errno member of the .Fa siginfo signal handler parameter is set to the syscall error value, and the .Va si_code member is set to .Dv TRAP_CAP . .Pp See also the .Dv PROC_TRAPCAP_CTL and .Dv PROC_TRAPCAP_STATUS operations of the .Xr procctl 2 function for similar per-process functionality. .Sh CAVEAT Creating effective process sandboxes is a tricky process that involves identifying the least possible rights required by the process and then passing those rights into the process in a safe manner. Consumers of .Fn cap_enter should also be aware of other inherited rights, such as access to VM resources, memory contents, and other process properties that should be considered. It is advisable to use .Xr fexecve 2 to create a runtime environment inside the sandbox that has as few implicitly acquired rights as possible. .Sh RETURN VALUES .Rv -std cap_enter cap_getmode .Sh ERRORS The .Fn cap_enter and .Fn cap_getmode system calls will fail if: .Bl -tag -width Er .It Bq Er ENOSYS The kernel is compiled without: .Pp .Cd "options CAPABILITY_MODE" .El .Pp The .Fn cap_getmode system call may also return the following error: .Bl -tag -width Er .It Bq Er EFAULT Pointer .Fa modep points outside the process's allocated address space. .El .Sh SEE ALSO .Xr cap_fcntls_limit 2 , .Xr cap_ioctls_limit 2 , .Xr cap_rights_limit 2 , -.Xr procctl 2 , -.Xr sysctl 2 , .Xr fexecve 2 , +.Xr procctl 2 , .Xr cap_sandboxed 3 , -.Xr capsicum 4 +.Xr capsicum 4 , +.Xr sysctl 9 .Sh HISTORY Support for capabilities and capabilities mode was developed as part of the .Tn TrustedBSD Project. .Sh AUTHORS These functions and the capability facility were created by .An "Robert N. M. Watson" at the University of Cambridge Computer Laboratory with support from a grant from Google, Inc. Index: stable/11/lib/libc/sys/kill.2 =================================================================== --- stable/11/lib/libc/sys/kill.2 (revision 321144) +++ stable/11/lib/libc/sys/kill.2 (revision 321145) @@ -1,156 +1,156 @@ .\" Copyright (c) 1980, 1991, 1993 .\" The Regents of the University of California. All rights reserved. .\" .\" Redistribution and use in source and binary forms, with or without .\" modification, are permitted provided that the following conditions .\" are met: .\" 1. Redistributions of source code must retain the above copyright .\" notice, this list of conditions and the following disclaimer. .\" 2. Redistributions in binary form must reproduce the above copyright .\" notice, this list of conditions and the following disclaimer in the .\" documentation and/or other materials provided with the distribution. .\" 4. Neither the name of the University nor the names of its contributors .\" may be used to endorse or promote products derived from this software .\" without specific prior written permission. .\" .\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND .\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE .\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE .\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE .\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL .\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS .\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) .\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT .\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY .\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF .\" SUCH DAMAGE. .\" .\" @(#)kill.2 8.3 (Berkeley) 4/19/94 .\" $FreeBSD$ .\" .Dd March 15, 2012 .Dt KILL 2 .Os .Sh NAME .Nm kill .Nd send signal to a process .Sh LIBRARY .Lb libc .Sh SYNOPSIS .In sys/types.h .In signal.h .Ft int .Fn kill "pid_t pid" "int sig" .Sh DESCRIPTION The .Fn kill system call sends the signal given by .Fa sig to .Fa pid , a process or a group of processes. The .Fa sig argument may be one of the signals specified in .Xr sigaction 2 or it may be 0, in which case error checking is performed but no signal is actually sent. This can be used to check the validity of .Fa pid . .Pp For a process to have permission to send a signal to a process designated by .Fa pid , the user must be the super-user, or the real or saved user ID of the receiving process must match the real or effective user ID of the sending process. A single exception is the signal SIGCONT, which may always be sent to any process with the same session ID as the sender. In addition, if the .Va security.bsd.conservative_signals -.Xr sysctl +.Xr sysctl 9 is set to 1, the user is not a super-user, and the receiver is set-uid, then only job control and terminal control signals may be sent (in particular, only SIGKILL, SIGINT, SIGTERM, SIGALRM, SIGSTOP, SIGTTIN, SIGTTOU, SIGTSTP, SIGHUP, SIGUSR1, SIGUSR2). .Bl -tag -width Ds .It \&If Fa pid No \&is greater than zero : The .Fa sig signal is sent to the process whose ID is equal to .Fa pid . .It \&If Fa pid No \&is zero : The .Fa sig signal is sent to all processes whose group ID is equal to the process group ID of the sender, and for which the process has permission; this is a variant of .Xr killpg 2 . .It \&If Fa pid No \&is -1 : If the user has super-user privileges, the signal is sent to all processes excluding system processes (with .Dv P_SYSTEM flag set), process with ID 1 (usually .Xr init 8 ) , and the process sending the signal. If the user is not the super user, the signal is sent to all processes with the same uid as the user excluding the process sending the signal. No error is returned if any process could be signaled. .El .Pp For compatibility with System V, if the process number is negative but not -1, the signal is sent to all processes whose process group ID is equal to the absolute value of the process number. This is a variant of .Xr killpg 2 . .Sh RETURN VALUES .Rv -std kill .Sh ERRORS The .Fn kill system call will fail and no signal will be sent if: .Bl -tag -width Er .It Bq Er EINVAL The .Fa sig argument is not a valid signal number. .It Bq Er ESRCH No process or process group can be found corresponding to that specified by .Fa pid . .It Bq Er EPERM The sending process does not have permission to send .Va sig to the receiving process. .El .Sh SEE ALSO .Xr getpgrp 2 , .Xr getpid 2 , .Xr killpg 2 , .Xr sigaction 2 , .Xr sigqueue 2 , .Xr raise 3 , .Xr init 8 .Sh STANDARDS The .Fn kill system call is expected to conform to .St -p1003.1-90 . .Sh HISTORY The .Fn kill function appeared in .At v7 . Index: stable/11/lib/libc/sys/open.2 =================================================================== --- stable/11/lib/libc/sys/open.2 (revision 321144) +++ stable/11/lib/libc/sys/open.2 (revision 321145) @@ -1,510 +1,511 @@ .\" Copyright (c) 1980, 1991, 1993 .\" The Regents of the University of California. All rights reserved. .\" .\" Redistribution and use in source and binary forms, with or without .\" modification, are permitted provided that the following conditions .\" are met: .\" 1. Redistributions of source code must retain the above copyright .\" notice, this list of conditions and the following disclaimer. .\" 2. Redistributions in binary form must reproduce the above copyright .\" notice, this list of conditions and the following disclaimer in the .\" documentation and/or other materials provided with the distribution. .\" 4. Neither the name of the University nor the names of its contributors .\" may be used to endorse or promote products derived from this software .\" without specific prior written permission. .\" .\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND .\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE .\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE .\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE .\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL .\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS .\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) .\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT .\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY .\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF .\" SUCH DAMAGE. .\" .\" @(#)open.2 8.2 (Berkeley) 11/16/93 .\" $FreeBSD$ .\" .Dd November 22, 2016 .Dt OPEN 2 .Os .Sh NAME .Nm open , openat .Nd open or create a file for reading, writing or executing .Sh LIBRARY .Lb libc .Sh SYNOPSIS .In fcntl.h .Ft int .Fn open "const char *path" "int flags" "..." .Ft int .Fn openat "int fd" "const char *path" "int flags" "..." .Sh DESCRIPTION The file name specified by .Fa path is opened for either execution or reading and/or writing as specified by the argument .Fa flags and the file descriptor returned to the calling process. The .Fa flags argument may indicate the file is to be created if it does not exist (by specifying the .Dv O_CREAT flag). In this case .Fn open and .Fn openat require an additional argument .Fa "mode_t mode" , and the file is created with mode .Fa mode as described in .Xr chmod 2 and modified by the process' umask value (see .Xr umask 2 ) . .Pp The .Fn openat function is equivalent to the .Fn open function except in the case where the .Fa path specifies a relative path. In this case the file to be opened is determined relative to the directory associated with the file descriptor .Fa fd instead of the current working directory. The .Fa flag parameter and the optional fourth parameter correspond exactly to the parameters of .Fn open . If .Fn openat is passed the special value .Dv AT_FDCWD in the .Fa fd parameter, the current working directory is used and the behavior is identical to a call to .Fn open . .Pp The flags specified are formed by .Em or Ns 'ing the following values .Pp .Bd -literal -offset indent -compact O_RDONLY open for reading only O_WRONLY open for writing only O_RDWR open for reading and writing O_EXEC open for execute only O_NONBLOCK do not block on open O_APPEND append on each write O_CREAT create file if it does not exist O_TRUNC truncate size to 0 O_EXCL error if create and file exists O_SHLOCK atomically obtain a shared lock O_EXLOCK atomically obtain an exclusive lock O_DIRECT eliminate or reduce cache effects O_FSYNC synchronous writes O_SYNC synchronous writes O_NOFOLLOW do not follow symlinks O_NOCTTY ignored O_TTY_INIT ignored O_DIRECTORY error if file is not a directory O_CLOEXEC set FD_CLOEXEC upon open O_VERIFY verify the contents of the file .Ed .Pp Opening a file with .Dv O_APPEND set causes each write on the file to be appended to the end. If .Dv O_TRUNC is specified and the file exists, the file is truncated to zero length. If .Dv O_EXCL is set with .Dv O_CREAT and the file already exists, .Fn open returns an error. This may be used to implement a simple exclusive access locking mechanism. If .Dv O_EXCL is set and the last component of the pathname is a symbolic link, .Fn open will fail even if the symbolic link points to a non-existent name. If the .Dv O_NONBLOCK flag is specified and the .Fn open system call would result in the process being blocked for some reason (e.g., waiting for carrier on a dialup line), .Fn open returns immediately. The descriptor remains in non-blocking mode for subsequent operations. .Pp If .Dv O_FSYNC is used in the mask, all writes will immediately be written to disk, the kernel will not cache written data and all writes on the descriptor will not return until the data to be written completes. .Pp .Dv O_SYNC is a synonym for .Dv O_FSYNC required by .Tn POSIX . .Pp If .Dv O_NOFOLLOW is used in the mask and the target file passed to .Fn open is a symbolic link then the .Fn open will fail. .Pp When opening a file, a lock with .Xr flock 2 semantics can be obtained by setting .Dv O_SHLOCK for a shared lock, or .Dv O_EXLOCK for an exclusive lock. If creating a file with .Dv O_CREAT , the request for the lock will never fail (provided that the underlying file system supports locking). .Pp .Dv O_DIRECT may be used to minimize or eliminate the cache effects of reading and writing. The system will attempt to avoid caching the data you read or write. If it cannot avoid caching the data, it will minimize the impact the data has on the cache. Use of this flag can drastically reduce performance if not used with care. .Pp .Dv O_NOCTTY may be used to ensure the OS does not assign this file as the controlling terminal when it opens a tty device. This is the default on .Fx , but is present for .Tn POSIX compatibility. The .Fn open system call will not assign controlling terminals on .Fx . .Pp .Dv O_TTY_INIT may be used to ensure the OS restores the terminal attributes when initially opening a TTY. This is the default on .Fx , but is present for .Tn POSIX compatibility. The initial call to .Fn open on a TTY will always restore default terminal attributes on .Fx . .Pp .Dv O_DIRECTORY may be used to ensure the resulting file descriptor refers to a directory. This flag can be used to prevent applications with elevated privileges from opening files which are even unsafe to open with .Dv O_RDONLY , such as device nodes. .Pp .Dv O_CLOEXEC may be used to set .Dv FD_CLOEXEC flag for the newly returned file descriptor. .Pp .Dv O_VERIFY may be used to indicate to the kernel that the contents of the file should be verified before allowing the open to proceed. The details of what .Dq verified means is implementation specific. The run-time linker (rtld) uses this flag to ensure shared objects have been verified before operating on them. .Pp If successful, .Fn open returns a non-negative integer, termed a file descriptor. It returns \-1 on failure. The file pointer used to mark the current position within the file is set to the beginning of the file. .Pp If a sleeping open of a device node from .Xr devfs 5 is interrupted by a signal, the call always fails with .Er EINTR , even if the .Dv SA_RESTART flag is set for the signal. A sleeping open of a fifo (see .Xr mkfifo 2 ) is restarted as normal. .Pp When a new file is created it is given the group of the directory which contains it. .Pp Unless .Dv O_CLOEXEC flag was specified, the new descriptor is set to remain open across .Xr execve 2 system calls; see .Xr close 2 , .Xr fcntl 2 and .Dv O_CLOEXEC description. .Pp The system imposes a limit on the number of file descriptors open simultaneously by one process. The .Xr getdtablesize 2 system call returns the current system limit. .Sh RETURN VALUES If successful, .Fn open and .Fn openat return a non-negative integer, termed a file descriptor. They return \-1 on failure, and set .Va errno to indicate the error. .Sh ERRORS The named file is opened unless: .Bl -tag -width Er .It Bq Er ENOTDIR A component of the path prefix is not a directory. .It Bq Er ENAMETOOLONG A component of a pathname exceeded 255 characters, or an entire path name exceeded 1023 characters. .It Bq Er ENOENT .Dv O_CREAT is not set and the named file does not exist. .It Bq Er ENOENT A component of the path name that must exist does not exist. .It Bq Er EACCES Search permission is denied for a component of the path prefix. .It Bq Er EACCES The required permissions (for reading and/or writing) are denied for the given flags. .It Bq Er EACCES .Dv O_TRUNC is specified and write permission is denied. .It Bq Er EACCES .Dv O_CREAT is specified, the file does not exist, and the directory in which it is to be created does not permit writing. .It Bq Er EPERM .Dv O_CREAT is specified, the file does not exist, and the directory in which it is to be created has its immutable flag set, see the .Xr chflags 2 manual page for more information. .It Bq Er EPERM The named file has its immutable flag set and the file is to be modified. .It Bq Er EPERM The named file has its append-only flag set, the file is to be modified, and .Dv O_TRUNC is specified or .Dv O_APPEND is not specified. .It Bq Er ELOOP Too many symbolic links were encountered in translating the pathname. .It Bq Er EISDIR The named file is a directory, and the arguments specify it is to be modified. .It Bq Er EROFS The named file resides on a read-only file system, and the file is to be modified. .It Bq Er EROFS .Dv O_CREAT is specified and the named file would reside on a read-only file system. .It Bq Er EMFILE The process has already reached its limit for open file descriptors. .It Bq Er ENFILE The system file table is full. .It Bq Er EMLINK .Dv O_NOFOLLOW was specified and the target is a symbolic link. .It Bq Er ENXIO The named file is a character special or block special file, and the device associated with this special file does not exist. .It Bq Er ENXIO .Dv O_NONBLOCK is set, the named file is a fifo, .Dv O_WRONLY is set, and no process has the file open for reading. .It Bq Er EINTR The .Fn open operation was interrupted by a signal. .It Bq Er EOPNOTSUPP .Dv O_SHLOCK or .Dv O_EXLOCK is specified but the underlying file system does not support locking. .It Bq Er EOPNOTSUPP The named file is a special file mounted through a file system that does not support access to it (e.g.\& NFS). .It Bq Er EWOULDBLOCK .Dv O_NONBLOCK and one of .Dv O_SHLOCK or .Dv O_EXLOCK is specified and the file is locked. .It Bq Er ENOSPC .Dv O_CREAT is specified, the file does not exist, and the directory in which the entry for the new file is being placed cannot be extended because there is no space left on the file system containing the directory. .It Bq Er ENOSPC .Dv O_CREAT is specified, the file does not exist, and there are no free inodes on the file system on which the file is being created. .It Bq Er EDQUOT .Dv O_CREAT is specified, the file does not exist, and the directory in which the entry for the new file is being placed cannot be extended because the user's quota of disk blocks on the file system containing the directory has been exhausted. .It Bq Er EDQUOT .Dv O_CREAT is specified, the file does not exist, and the user's quota of inodes on the file system on which the file is being created has been exhausted. .It Bq Er EIO An I/O error occurred while making the directory entry or allocating the inode for .Dv O_CREAT . .It Bq Er ETXTBSY The file is a pure procedure (shared text) file that is being executed and the .Fn open system call requests write access. .It Bq Er EFAULT The .Fa path argument points outside the process's allocated address space. .It Bq Er EEXIST .Dv O_CREAT and .Dv O_EXCL were specified and the file exists. .It Bq Er EOPNOTSUPP An attempt was made to open a socket (not currently implemented). .It Bq Er EINVAL An attempt was made to open a descriptor with an illegal combination of .Dv O_RDONLY , .Dv O_WRONLY , .Dv O_RDWR and .Dv O_EXEC . .It Bq Er EBADF The .Fa path argument does not specify an absolute path and the .Fa fd argument is neither .Dv AT_FDCWD nor a valid file descriptor open for searching. .It Bq Er ENOTDIR The .Fa path argument is not an absolute path and .Fa fd is neither .Dv AT_FDCWD nor a file descriptor associated with a directory. .It Bq Er ENOTDIR .Dv O_DIRECTORY is specified and the file is not a directory. .El .Sh SEE ALSO .Xr chmod 2 , .Xr close 2 , .Xr dup 2 , .Xr fexecve 2 , .Xr fhopen 2 , .Xr getdtablesize 2 , .Xr getfh 2 , .Xr lgetfh 2 , .Xr lseek 2 , .Xr read 2 , .Xr umask 2 , .Xr write 2 , -.Xr fopen 3 -.Sh HISTORY -The -.Fn open -function appeared in -.At v6 . -The -.Fn openat -function was introduced in -.Fx 8.0 . +.Xr fopen 3 , +.Xr capsicum 4 .Sh STANDARDS These functions are specified by .St -p1003.1-2008 . .Fx sets .Va errno to .Er EMLINK instead of .Er ELOOP as specified by .Tn POSIX when .Dv O_NOFOLLOW is set in flags and the final component of pathname is a symbolic link to distinguish it from the case of too many symbolic link traversals in one of its non-final components. +.Sh HISTORY +The +.Fn open +function appeared in +.At v6 . +The +.Fn openat +function was introduced in +.Fx 8.0 . .Sh BUGS The Open Group Extended API Set 2 specification requires that the test for whether .Fa fd is searchable is based on whether .Fa fd is open for searching, not whether the underlying directory currently permits searches. The present implementation of the .Fa openat checks the current permissions of directory instead. Index: stable/11/lib/libc/sys/ptrace.2 =================================================================== --- stable/11/lib/libc/sys/ptrace.2 (revision 321144) +++ stable/11/lib/libc/sys/ptrace.2 (revision 321145) @@ -1,1066 +1,1066 @@ .\" $FreeBSD$ .\" $NetBSD: ptrace.2,v 1.2 1995/02/27 12:35:37 cgd Exp $ .\" .\" This file is in the public domain. .Dd August 29, 2016 .Dt PTRACE 2 .Os .Sh NAME .Nm ptrace .Nd process tracing and debugging .Sh LIBRARY .Lb libc .Sh SYNOPSIS .In sys/types.h .In sys/ptrace.h .Ft int .Fn ptrace "int request" "pid_t pid" "caddr_t addr" "int data" .Sh DESCRIPTION The .Fn ptrace system call provides tracing and debugging facilities. It allows one process (the .Em tracing process) to control another (the .Em traced process). The tracing process must first attach to the traced process, and then issue a series of .Fn ptrace system calls to control the execution of the process, as well as access process memory and register state. For the duration of the tracing session, the traced process will be .Dq re-parented , with its parent process ID (and resulting behavior) changed to the tracing process. It is permissible for a tracing process to attach to more than one other process at a time. When the tracing process has completed its work, it must detach the traced process; if a tracing process exits without first detaching all processes it has attached, those processes will be killed. .Pp Most of the time, the traced process runs normally, but when it receives a signal (see .Xr sigaction 2 ) , it stops. The tracing process is expected to notice this via .Xr wait 2 or the delivery of a .Dv SIGCHLD signal, examine the state of the stopped process, and cause it to terminate or continue as appropriate. The signal may be a normal process signal, generated as a result of traced process behavior, or use of the .Xr kill 2 system call; alternatively, it may be generated by the tracing facility as a result of attaching, stepping by the tracing process, or an event in the traced process. The tracing process may choose to intercept the signal, using it to observe process behavior (such as .Dv SIGTRAP ) , or forward the signal to the process if appropriate. The .Fn ptrace system call is the mechanism by which all this happens. .Pp A traced process may report additional signal stops corresponding to events in the traced process. These additional signal stops are reported as .Dv SIGTRAP or .Dv SIGSTOP signals. The tracing process can use the .Dv PT_LWPINFO request to determine which events are associated with a .Dv SIGTRAP or .Dv SIGSTOP signal. Note that multiple events may be associated with a single signal. For example, events indicated by the .Dv PL_FLAG_BORN , .Dv PL_FLAG_FORKED , and .Dv PL_FLAG_EXEC flags are also reported as a system call exit event .Pq Dv PL_FLAG_SCX . The signal stop for a new child process enabled via .Dv PTRACE_FORK will report a .Dv SIGSTOP signal. All other additional signal stops use .Dv SIGTRAP . .Pp Each traced process has a tracing event mask. An event in the traced process only reports a signal stop if the corresponding flag is set in the tracing event mask. The current set of tracing event flags include: .Bl -tag -width "Dv PTRACE_SYSCALL" .It Dv PTRACE_EXEC Report a stop for a successful invocation of .Xr execve 2 . This event is indicated by the .Dv PL_FLAG_EXEC flag in the .Va pl_flags member of .Vt "struct ptrace_lwpinfo" . .It Dv PTRACE_SCE Report a stop on each system call entry. This event is indicated by the .Dv PL_FLAG_SCE flag in the .Va pl_flags member of .Vt "struct ptrace_lwpinfo" . .It Dv PTRACE_SCX Report a stop on each system call exit. This event is indicated by the .Dv PL_FLAG_SCX flag in the .Va pl_flags member of .Vt "struct ptrace_lwpinfo" . .It Dv PTRACE_SYSCALL Report stops for both system call entry and exit. .It Dv PTRACE_FORK This event flag controls tracing for new child processes of a traced process. .Pp When this event flag is enabled, new child processes will enable tracing and stop before executing their first instruction. The new child process will include the .Dv PL_FLAG_CHILD flag in the .Va pl_flags member of .Vt "struct ptrace_lwpinfo" . The traced process will report a stop that includes the .Dv PL_FLAG_FORKED flag. The process ID of the new child process will also be present in the .Va pl_child_pid member of .Vt "struct ptrace_lwpinfo" . If the new child process was created via .Xr vfork 2 , the traced process's stop will also include the .Dv PL_FLAG_VFORKED flag. Note that new child processes will be attached with the default tracing event mask; they do not inherit the event mask of the traced process. .Pp When this event flag is not enabled, new child processes will execute without tracing enabled. .It Dv PTRACE_LWP This event flag controls tracing of LWP .Pq kernel thread creation and destruction. -When this event is enabled, +When this event is enabled, new LWPs will stop and report an event with .Dv PL_FLAG_BORN set before executing their first instruction, and exiting LWPs will stop and report an event with .Dv PL_FLAG_EXITED set before completing their termination. .Pp Note that new processes do not report an event for the creation of their initial thread, and exiting processes do not report an event for the termination of the last thread. .It Dv PTRACE_VFORK Report a stop event when a parent process resumes after a .Xr vfork 2 . .Pp When a thread in the traced process creates a new child process via .Xr vfork 2 , the stop that reports .Dv PL_FLAG_FORKED and .Dv PL_FLAG_SCX occurs just after the child process is created, but before the thread waits for the child process to stop sharing process memory. If a debugger is not tracing the new child process, it must ensure that no breakpoints are enabled in the shared process memory before detaching from the new child process. This means that no breakpoints are enabled in the parent process either. .Pp The .Dv PTRACE_VFORK flag enables a new stop that indicates when the new child process stops sharing the process memory of the parent process. A debugger can reinsert breakpoints in the parent process and resume it in response to this event. This event is indicated by setting the .Dv PL_FLAG_VFORK_DONE flag. .El .Pp The default tracing event mask when attaching to a process via .Dv PT_ATTACH , .Dv PT_TRACE_ME , or .Dv PTRACE_FORK includes only .Dv PTRACE_EXEC events. -All other event flags are disabled. +All other event flags are disabled. .Pp The .Fa request argument specifies what operation is being performed; the meaning of the rest of the arguments depends on the operation, but except for one special case noted below, all .Fn ptrace calls are made by the tracing process, and the .Fa pid argument specifies the process ID of the traced process or a corresponding thread ID. The .Fa request argument can be: .Bl -tag -width "Dv PT_GET_EVENT_MASK" .It Dv PT_TRACE_ME This request is the only one used by the traced process; it declares that the process expects to be traced by its parent. All the other arguments are ignored. (If the parent process does not expect to trace the child, it will probably be rather confused by the results; once the traced process stops, it cannot be made to continue except via .Fn ptrace . ) When a process has used this request and calls .Xr execve 2 or any of the routines built on it (such as .Xr execv 3 ) , it will stop before executing the first instruction of the new image. Also, any setuid or setgid bits on the executable being executed will be ignored. If the child was created by .Xr vfork 2 system call or .Xr rfork 2 call with the .Dv RFMEM flag specified, the debugging events are reported to the parent only after the .Xr execve 2 is executed. .It Dv PT_READ_I , Dv PT_READ_D These requests read a single .Vt int of data from the traced process's address space. Traditionally, .Fn ptrace has allowed for machines with distinct address spaces for instruction and data, which is why there are two requests: conceptually, .Dv PT_READ_I reads from the instruction space and .Dv PT_READ_D reads from the data space. In the current .Fx implementation, these two requests are completely identical. The .Fa addr argument specifies the address (in the traced process's virtual address space) at which the read is to be done. This address does not have to meet any alignment constraints. The value read is returned as the return value from .Fn ptrace . .It Dv PT_WRITE_I , Dv PT_WRITE_D These requests parallel .Dv PT_READ_I and .Dv PT_READ_D , except that they write rather than read. The .Fa data argument supplies the value to be written. .It Dv PT_IO This request allows reading and writing arbitrary amounts of data in the traced process's address space. The .Fa addr argument specifies a pointer to a .Vt "struct ptrace_io_desc" , which is defined as follows: .Bd -literal struct ptrace_io_desc { int piod_op; /* I/O operation */ void *piod_offs; /* child offset */ void *piod_addr; /* parent offset */ size_t piod_len; /* request length */ }; /* * Operations in piod_op. */ #define PIOD_READ_D 1 /* Read from D space */ #define PIOD_WRITE_D 2 /* Write to D space */ #define PIOD_READ_I 3 /* Read from I space */ #define PIOD_WRITE_I 4 /* Write to I space */ .Ed .Pp The .Fa data argument is ignored. The actual number of bytes read or written is stored in .Va piod_len upon return. .It Dv PT_CONTINUE The traced process continues execution. The .Fa addr argument is an address specifying the place where execution is to be resumed (a new value for the program counter), or .Po Vt caddr_t Pc Ns 1 to indicate that execution is to pick up where it left off. The .Fa data argument provides a signal number to be delivered to the traced process as it resumes execution, or 0 if no signal is to be sent. .It Dv PT_STEP The traced process is single stepped one instruction. The .Fa addr argument should be passed .Po Vt caddr_t Pc Ns 1 . The .Fa data argument provides a signal number to be delivered to the traced process as it resumes execution, or 0 if no signal is to be sent. .It Dv PT_KILL The traced process terminates, as if .Dv PT_CONTINUE had been used with .Dv SIGKILL given as the signal to be delivered. .It Dv PT_ATTACH This request allows a process to gain control of an otherwise unrelated process and begin tracing it. It does not need any cooperation from the to-be-traced process. In this case, .Fa pid specifies the process ID of the to-be-traced process, and the other two arguments are ignored. This request requires that the target process must have the same real UID as the tracing process, and that it must not be executing a setuid or setgid executable. (If the tracing process is running as root, these restrictions do not apply.) The tracing process will see the newly-traced process stop and may then control it as if it had been traced all along. .It Dv PT_DETACH This request is like PT_CONTINUE, except that it does not allow specifying an alternate place to continue execution, and after it succeeds, the traced process is no longer traced and continues execution normally. .It Dv PT_GETREGS This request reads the traced process's machine registers into the .Do .Vt "struct reg" .Dc (defined in .In machine/reg.h ) pointed to by .Fa addr . .It Dv PT_SETREGS This request is the converse of .Dv PT_GETREGS ; it loads the traced process's machine registers from the .Do .Vt "struct reg" .Dc (defined in .In machine/reg.h ) pointed to by .Fa addr . .It Dv PT_GETFPREGS This request reads the traced process's floating-point registers into the .Do .Vt "struct fpreg" .Dc (defined in .In machine/reg.h ) pointed to by .Fa addr . .It Dv PT_SETFPREGS This request is the converse of .Dv PT_GETFPREGS ; it loads the traced process's floating-point registers from the .Do .Vt "struct fpreg" .Dc (defined in .In machine/reg.h ) pointed to by .Fa addr . .It Dv PT_GETDBREGS This request reads the traced process's debug registers into the .Do .Vt "struct dbreg" .Dc (defined in .In machine/reg.h ) pointed to by .Fa addr . .It Dv PT_SETDBREGS This request is the converse of .Dv PT_GETDBREGS ; it loads the traced process's debug registers from the .Do .Vt "struct dbreg" .Dc (defined in .In machine/reg.h ) pointed to by .Fa addr . .It Dv PT_LWPINFO This request can be used to obtain information about the kernel thread, also known as light-weight process, that caused the traced process to stop. The .Fa addr argument specifies a pointer to a .Vt "struct ptrace_lwpinfo" , which is defined as follows: .Bd -literal struct ptrace_lwpinfo { lwpid_t pl_lwpid; int pl_event; int pl_flags; sigset_t pl_sigmask; sigset_t pl_siglist; siginfo_t pl_siginfo; char pl_tdname[MAXCOMLEN + 1]; pid_t pl_child_pid; u_int pl_syscall_code; u_int pl_syscall_narg; }; .Ed .Pp The .Fa data argument is to be set to the size of the structure known to the caller. This allows the structure to grow without affecting older programs. .Pp The fields in the .Vt "struct ptrace_lwpinfo" have the following meaning: .Bl -tag -width indent -compact .It Va pl_lwpid LWP id of the thread .It Va pl_event Event that caused the stop. Currently defined events are: .Bl -tag -width "Dv PL_EVENT_SIGNAL" -compact .It Dv PL_EVENT_NONE No reason given .It Dv PL_EVENT_SIGNAL Thread stopped due to the pending signal .El .It Va pl_flags Flags that specify additional details about observed stop. Currently defined flags are: .Bl -tag -width indent -compact .It Dv PL_FLAG_SCE The thread stopped due to system call entry, right after the kernel is entered. The debugger may examine syscall arguments that are stored in memory and registers according to the ABI of the current process, and modify them, if needed. .It Dv PL_FLAG_SCX The thread is stopped immediately before syscall is returning to the usermode. The debugger may examine system call return values in the ABI-defined registers and/or memory. .It Dv PL_FLAG_EXEC When .Dv PL_FLAG_SCX is set, this flag may be additionally specified to inform that the program being executed by debuggee process has been changed by successful execution of a system call from the .Fn execve 2 family. .It Dv PL_FLAG_SI Indicates that .Va pl_siginfo member of .Vt "struct ptrace_lwpinfo" contains valid information. .It Dv PL_FLAG_FORKED Indicates that the process is returning from a call to .Fn fork 2 that created a new child process. The process identifier of the new process is available in the .Va pl_child_pid member of .Vt "struct ptrace_lwpinfo" . .It Dv PL_FLAG_CHILD The flag is set for first event reported from a new child which is automatically attached when .Dv PTRACE_FORK is enabled. .It Dv PL_FLAG_BORN This flag is set for the first event reported from a new LWP when .Dv PTRACE_LWP is enabled. It is reported along with .Dv PL_FLAG_SCX . .It Dv PL_FLAG_EXITED This flag is set for the last event reported by an exiting LWP when .Dv PTRACE_LWP is enabled. Note that this event is not reported when the last LWP in a process exits. The termination of the last thread is reported via a normal process exit event. .It Dv PL_FLAG_VFORKED Indicates that the thread is returning from a call to .Xr vfork 2 that created a new child process. This flag is set in addition to .Dv PL_FLAG_FORKED . .It Dv PL_FLAG_VFORK_DONE Indicates that the thread has resumed after a child process created via .Xr vfork 2 has stopped sharing its address space with the traced process. .El .It Va pl_sigmask The current signal mask of the LWP .It Va pl_siglist The current pending set of signals for the LWP. Note that signals that are delivered to the process would not appear on an LWP siglist until the thread is selected for delivery. .It Va pl_siginfo The siginfo that accompanies the signal pending. Only valid for .Dv PL_EVENT_SIGNAL stop when .Dv PL_FLAG_SI is set in .Va pl_flags . .It Va pl_tdname The name of the thread. .It Va pl_child_pid The process identifier of the new child process. Only valid for a .Dv PL_EVENT_SIGNAL stop when .Dv PL_FLAG_FORKED is set in .Va pl_flags . .It Va pl_syscall_code The ABI-specific identifier of the current system call. Note that for indirect system calls this field reports the indirected system call. Only valid when .Dv PL_FLAG_SCE or .Dv PL_FLAG_SCX is set in .Va pl_flags. .It Va pl_syscall_narg The number of arguments passed to the current system call not counting the system call identifier. Note that for indirect system calls this field reports the arguments passed to the indirected system call. Only valid when .Dv PL_FLAG_SCE or .Dv PL_FLAG_SCX is set in .Va pl_flags. .El .It Dv PT_GETNUMLWPS This request returns the number of kernel threads associated with the traced process. .It Dv PT_GETLWPLIST This request can be used to get the current thread list. A pointer to an array of type .Vt lwpid_t should be passed in .Fa addr , with the array size specified by .Fa data . The return value from .Fn ptrace is the count of array entries filled in. .It Dv PT_SETSTEP This request will turn on single stepping of the specified process. .It Dv PT_CLEARSTEP This request will turn off single stepping of the specified process. .It Dv PT_SUSPEND This request will suspend the specified thread. .It Dv PT_RESUME This request will resume the specified thread. .It Dv PT_TO_SCE This request will set the .Dv PTRACE_SCE event flag to trace all future system call entries and continue the process. The .Fa addr and .Fa data arguments are used the same as for .Dv PT_CONTINUE. .It Dv PT_TO_SCX This request will set the .Dv PTRACE_SCX event flag to trace all future system call exits and continue the process. The .Fa addr and .Fa data arguments are used the same as for .Dv PT_CONTINUE. .It Dv PT_SYSCALL This request will set the .Dv PTRACE_SYSCALL event flag to trace all future system call entries and exits and continue the process. The .Fa addr and .Fa data arguments are used the same as for .Dv PT_CONTINUE. .It Dv PT_FOLLOW_FORK This request controls tracing for new child processes of a traced process. If .Fa data is non-zero, .Dv PTRACE_FORK is set in the traced process's event tracing mask. If .Fa data is zero, .Dv PTRACE_FORK is cleared from the traced process's event tracing mask. .It Dv PT_LWP_EVENTS This request controls tracing of LWP creation and destruction. If .Fa data is non-zero, .Dv PTRACE_LWP is set in the traced process's event tracing mask. If .Fa data is zero, .Dv PTRACE_LWP is cleared from the traced process's event tracing mask. .It Dv PT_GET_EVENT_MASK This request reads the traced process's event tracing mask into the integer pointed to by .Fa addr . The size of the integer must be passed in .Fa data . .It Dv PT_SET_EVENT_MASK This request sets the traced process's event tracing mask from the integer pointed to by .Fa addr . The size of the integer must be passed in .Fa data . .It Dv PT_VM_TIMESTAMP This request returns the generation number or timestamp of the memory map of the traced process as the return value from .Fn ptrace . This provides a low-cost way for the tracing process to determine if the VM map changed since the last time this request was made. .It Dv PT_VM_ENTRY This request is used to iterate over the entries of the VM map of the traced process. The .Fa addr argument specifies a pointer to a .Vt "struct ptrace_vm_entry" , which is defined as follows: .Bd -literal struct ptrace_vm_entry { int pve_entry; int pve_timestamp; u_long pve_start; u_long pve_end; u_long pve_offset; u_int pve_prot; u_int pve_pathlen; long pve_fileid; uint32_t pve_fsid; char *pve_path; }; .Ed .Pp The first entry is returned by setting .Va pve_entry to zero. Subsequent entries are returned by leaving .Va pve_entry unmodified from the value returned by previous requests. The .Va pve_timestamp field can be used to detect changes to the VM map while iterating over the entries. The tracing process can then take appropriate action, such as restarting. By setting .Va pve_pathlen to a non-zero value on entry, the pathname of the backing object is returned in the buffer pointed to by .Va pve_path , provided the entry is backed by a vnode. The .Va pve_pathlen field is updated with the actual length of the pathname (including the terminating null character). The .Va pve_offset field is the offset within the backing object at which the range starts. The range is located in the VM space at .Va pve_start and extends up to .Va pve_end (inclusive). .Pp The .Fa data argument is ignored. .El .Sh x86 MACHINE-SPECIFIC REQUESTS .Bl -tag -width "Dv PT_GETXSTATE_INFO" .It Dv PT_GETXMMREGS Copy the XMM FPU state into the buffer pointed to by the argument .Fa addr . The buffer has the same layout as the 32-bit save buffer for the machine instruction .Dv FXSAVE . .Pp This request is only valid for i386 programs, both on native 32-bit systems and on amd64 kernels. For 64-bit amd64 programs, the XMM state is reported as part of the FPU state returned by the .Dv PT_GETFPREGS request. .Pp The .Fa data argument is ignored. .It Dv PT_SETXMMREGS Load the XMM FPU state for the thread from the buffer pointed to by the argument .Fa addr . The buffer has the same layout as the 32-bit load buffer for the machine instruction .Dv FXRSTOR . .Pp As with .Dv PT_GETXMMREGS, this request is only valid for i386 programs. .Pp The .Fa data argument is ignored. .It Dv PT_GETXSTATE_INFO Report which XSAVE FPU extensions are supported by the CPU and allowed in userspace programs. The .Fa addr argument must point to a variable of type .Vt struct ptrace_xstate_info , which contains the information on the request return. .Vt struct ptrace_xstate_info is defined as follows: .Bd -literal struct ptrace_xstate_info { uint64_t xsave_mask; uint32_t xsave_len; }; .Ed The .Dv xsave_mask field is a bitmask of the currently enabled extensions. The meaning of the bits is defined in the Intel and AMD processor documentation. The .Dv xsave_len field reports the length of the XSAVE area for storing the hardware state for currently enabled extensions in the format defined by the x86 .Dv XSAVE machine instruction. .Pp The .Fa data argument value must be equal to the size of the .Vt struct ptrace_xstate_info . .It Dv PT_GETXSTATE Return the content of the XSAVE area for the thread. The .Fa addr argument points to the buffer where the content is copied, and the .Fa data argument specifies the size of the buffer. The kernel copies out as much content as allowed by the buffer size. The buffer layout is specified by the layout of the save area for the .Dv XSAVE machine instruction. .It Dv PT_SETXSTATE Load the XSAVE state for the thread from the buffer specified by the .Fa addr pointer. The buffer size is passed in the .Fa data argument. The buffer must be at least as large as the .Vt struct savefpu (defined in .Pa x86/fpu.h ) to allow the complete x87 FPU and XMM state load. It must not be larger than the XSAVE state length, as reported by the .Dv xsave_len field from the .Vt struct ptrace_xstate_info of the .Dv PT_GETXSTATE_INFO request. Layout of the buffer is identical to the layout of the load area for the .Dv XRSTOR machine instruction. .It Dv PT_GETFSBASE Return the value of the base used when doing segmented memory addressing using the %fs segment register. The .Fa addr argument points to an .Vt unsigned long variable where the base value is stored. .Pp The .Fa data argument is ignored. .It Dv PT_GETGSBASE Like the .Dv PT_GETFSBASE request, but returns the base for the %gs segment register. .It Dv PT_SETFSBASE Set the base for the %fs segment register to the value pointed to by the .Fa addr argument. .Fa addr must point to the .Vt unsigned long variable containing the new base. .Pp The .Fa data argument is ignored. .It Dv PT_SETGSBASE Like the .Dv PT_SETFSBASE request, but sets the base for the %gs segment register. .El .Sh PowerPC MACHINE-SPECIFIC REQUESTS .Bl -tag -width "Dv PT_SETVRREGS" .It Dv PT_GETVRREGS Return the thread's .Dv ALTIVEC machine state in the buffer pointed to by .Fa addr . .Pp The .Fa data argument is ignored. .It Dv PT_SETVRREGS Set the thread's .Dv ALTIVEC machine state from the buffer pointed to by .Fa addr . .Pp The .Fa data argument is ignored. .El .Pp Additionally, other machine-specific requests can exist. .Sh RETURN VALUES Most requests return 0 on success and \-1 on error. Some requests can cause .Fn ptrace to return \-1 as a non-error value, among them are .Dv PT_READ_I and .Dv PT_READ_D , which return the value read from the process memory on success. To disambiguate, .Va errno can be set to 0 before the call and checked afterwards. .Pp The current .Fn ptrace implementation always sets .Va errno to 0 before calling into the kernel, both for historic reasons and for consistency with other operating systems. It is recommended to assign zero to .Va errno explicitly for forward compatibility. .Sh ERRORS The .Fn ptrace system call may fail if: .Bl -tag -width Er .It Bq Er ESRCH .Bl -bullet -compact .It No process having the specified process ID exists. .El .It Bq Er EINVAL .Bl -bullet -compact .It A process attempted to use .Dv PT_ATTACH on itself. .It The .Fa request argument was not one of the legal requests. .It The signal number (in .Fa data ) to .Dv PT_CONTINUE was neither 0 nor a legal signal number. .It .Dv PT_GETREGS , .Dv PT_SETREGS , .Dv PT_GETFPREGS , .Dv PT_SETFPREGS , .Dv PT_GETDBREGS , or .Dv PT_SETDBREGS was attempted on a process with no valid register set. (This is normally true only of system processes.) .It .Dv PT_VM_ENTRY was given an invalid value for .Fa pve_entry . This can also be caused by changes to the VM map of the process. .It The size (in .Fa data ) provided to .Dv PT_LWPINFO was less than or equal to zero, or larger than the .Vt ptrace_lwpinfo structure known to the kernel. .It The size (in .Fa data ) provided to the x86-specific .Dv PT_GETXSTATE_INFO request was not equal to the size of the .Vt struct ptrace_xstate_info . .It The size (in .Fa data ) provided to the x86-specific .Dv PT_SETXSTATE request was less than the size of the x87 plus the XMM save area. .It The size (in .Fa data ) provided to the x86-specific .Dv PT_SETXSTATE request was larger than returned in the .Dv xsave_len member of the .Vt struct ptrace_xstate_info from the .Dv PT_GETXSTATE_INFO request. .It The base value, provided to the amd64-specific requests .Dv PT_SETFSBASE or .Dv PT_SETGSBASE , pointed outside of the valid user address space. This error will not occur in 32-bit programs. .El .It Bq Er EBUSY .Bl -bullet -compact .It .Dv PT_ATTACH was attempted on a process that was already being traced. .It A request attempted to manipulate a process that was being traced by some process other than the one making the request. .It A request (other than .Dv PT_ATTACH ) specified a process that was not stopped. .El .It Bq Er EPERM .Bl -bullet -compact .It A request (other than .Dv PT_ATTACH ) attempted to manipulate a process that was not being traced at all. .It An attempt was made to use .Dv PT_ATTACH on a process in violation of the requirements listed under .Dv PT_ATTACH above. .El .It Bq Er ENOENT .Bl -bullet -compact .It .Dv PT_VM_ENTRY previously returned the last entry of the memory map. No more entries exist. .El .It Bq Er ENAMETOOLONG .Bl -bullet -compact .It .Dv PT_VM_ENTRY cannot return the pathname of the backing object because the buffer is not big enough. .Fa pve_pathlen holds the minimum buffer size required on return. .El .El .Sh SEE ALSO .Xr execve 2 , .Xr sigaction 2 , .Xr wait 2 , .Xr execv 3 , .Xr i386_clr_watch 3 , .Xr i386_set_watch 3 .Sh HISTORY The .Fn ptrace function appeared in .At v7 . Index: stable/11/lib/libc/sys/rctl_add_rule.2 =================================================================== --- stable/11/lib/libc/sys/rctl_add_rule.2 (revision 321144) +++ stable/11/lib/libc/sys/rctl_add_rule.2 (revision 321145) @@ -1,220 +1,220 @@ .\" Copyright (c) 2016 Eric Badger .\" All rights reserved. .\" .\" Redistribution and use in source and binary forms, with or without .\" modification, are permitted provided that the following conditions .\" are met: .\" 1. Redistributions of source code must retain the above copyright .\" notice, this list of conditions and the following disclaimer. .\" 2. Redistributions in binary form must reproduce the above copyright .\" notice, this list of conditions and the following disclaimer in the .\" documentation and/or other materials provided with the distribution. .\" .\" THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND .\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE .\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE .\" ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE .\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL .\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS .\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) .\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT .\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY .\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF .\" SUCH DAMAGE. .\" .\" $FreeBSD$ .\" .Dd September 14, 2016 .Dt RCTL_ADD_RULE 2 .Os .Sh NAME -.Nm rctl_add_rule, -.Nm rctl_get_limits -.Nm rctl_get_racct, -.Nm rctl_get_rules, +.Nm rctl_add_rule , +.Nm rctl_get_limits , +.Nm rctl_get_racct , +.Nm rctl_get_rules , .Nm rctl_remove_rule .Nd manipulate and query the resource limits database .Sh LIBRARY .Lb libc .Sh SYNOPSIS .In sys/rctl.h .Ft int .Fo rctl_add_rule .Fa "const char *inbufp" "size_t inbuflen" "char *outbufp" "size_t outbuflen" .Fc .Ft int .Fo rctl_get_limits .Fa "const char *inbufp" "size_t inbuflen" "char *outbufp" "size_t outbuflen" .Fc .Ft int .Fo rctl_get_racct .Fa "const char *inbufp" "size_t inbuflen" "char *outbufp" "size_t outbuflen" .Fc .Ft int .Fo rctl_get_rules .Fa "const char *inbufp" "size_t inbuflen" "char *outbufp" "size_t outbuflen" .Fc .Ft int .Fo rctl_remove_rule .Fa "const char *inbufp" "size_t inbuflen" "char *outbufp" "size_t outbuflen" .Fc .Sh DESCRIPTION These system calls are used to manipulate and query the resource limits database. For all functions, .Fa inbuflen refers to the length of the buffer pointed to by .Fa inbufp and .Fa outbuflen refers to the length of the buffer pointed to by .Fa outbufp . .Pp The .Fn rctl_add_rule function adds the rule pointed to by .Fa inbufp to the resource limits database. The .Fa outbufp and .Fa outbuflen arguments are unused. Rule format is as described in .Xr rctl 8 , with exceptions noted in the .Sx RULES AND FILTERS section. .Pp The .Fn rctl_get_limits function returns in .Fa outbufp a comma-separated list of rules that apply to the process that matches the filter specified in .Fa inbufp . This includes rules with a subject of the process itself as well as rules with a different subject (such as user or loginclass) that apply to the process. .Pp The .Fn rctl_get_racct function returns resource usage information for a given subject. The subject is specified by passing a filter in .Fa inbufp . Filter syntax is as described in .Xr rctl 8 , with exceptions noted in the .Sx RULES AND FILTERS section. A comma-separated list of resources and the amount used of each by the specified subject is returned in .Fa outbufp . The resource and amount is formatted as .Qq resource=amount . .Pp The .Fn rctl_get_rules function returns in .Fa outbufp a comma-separated list of rules from the resource limits database that match the filter passed in .Fa inbufp . Filter syntax is as described in .Xr rctl 8 , with exceptions noted in the .Sx RULES AND FILTERS section. A filter of .Va :: may be passed to return all rules. .Pp The .Fn rctl_remove_rule function removes all rules matching the filter passed in .Fa inbufp from the resource limits database. Filter syntax is as described in .Xr rctl 8 , with exceptions noted in the .Sx RULES AND FILTERS section. .Fa outbufp and .Fa outbuflen are unused. .Sh RULES AND FILTERS This section explains how the rule and filter format described in .Xr rctl 8 differs from the format passed to the system calls themselves. The rctl tool provides several conveniences that the system calls do not. When using the system call: .Bl -dash -offset indent .It The subject must be fully specified. For example, abbreviating .Ql user to .Ql u is not acceptable. .It User and group IDs must be numeric. For example, .Ql root must be expressed as .Ql 0 . .It Units are not permitted on resource amounts. For example, a quantity of 1024 bytes must be expressed as .Ql 1024 and not .Ql 1k . .El .Sh RETURN VALUES .Rv -std .Sh ERRORS The rctl system calls may fail if: .Bl -tag -width Er .It Bq Er ENOSYS RACCT/RCTL support is not present in the kernel or the .Va kern.racct.enable sysctl is 0. .It Bq Er EINVAL The rule or filter passed in .Fa inbufp is invalid. .It Bq Er EPERM User has insufficient privileges to carry out the requested operation. .It Bq Er E2BIG .Fa inbufp or .Fa outbufp are too large. .It Bq Er ESRCH No process matched the provided rule or filter. .It Bq Er ENAMETOOLONG The loginclass or jail name specified is too long. .It Bq Er ERANGE The rule amount is outside of the allowable range or .Fa outbufp is too small. .It Bq Er EOPNOTSUPP The requested operation is not supported for the given rule or filter. .It Bq Er EFAULT .Fa inbufp or .Fa outbufp refer to invalid addresses. .El .Sh SEE ALSO .Xr rctl 8 .Sh HISTORY The rctl family of system calls appeared in .Fx 9.0 . .Sh AUTHORS .An -nosplit The rctl system calls were developed by .An Edward Tomasz Napierala Aq Mt trasz@FreeBSD.org under sponsorship from the FreeBSD Foundation. This manual page was written by .An Eric Badger Aq Mt badger@FreeBSD.org . Index: stable/11 =================================================================== --- stable/11 (revision 321144) +++ stable/11 (revision 321145) Property changes on: stable/11 ___________________________________________________________________ Modified: svn:mergeinfo ## -0,0 +0,1 ## Merged /head:r318715,318717-318721