4 files changed, 245 insertions, 93 deletions
diff --git a/lib/libsys/clock_gettime.2 b/lib/libsys/clock_gettime.2
index 89551d0f720b..841673648dfc 100644
--- a/lib/libsys/clock_gettime.2
+++ b/lib/libsys/clock_gettime.2
@@ -27,7 +27,7 @@
 .\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 .\" SUCH DAMAGE.
 .\"
-.Dd August 10, 2024
+.Dd October 15, 2025
 .Dt CLOCK_GETTIME 2
 .Os
 .Sh NAME
@@ -80,7 +80,6 @@ Behavior during a leap second is not defined by and POSIX standard.
 Increments in SI seconds, even while the system is suspended.
 Its epoch is unspecified.
 The count is not adjusted by leap seconds.
-.Fx implements
 .It Dv CLOCK_UPTIME
 .It Dv CLOCK_UPTIME_PRECISE
 .It Dv CLOCK_UPTIME_FAST
diff --git a/lib/libsys/getrlimitusage.2 b/lib/libsys/getrlimitusage.2
index e2114def56c2..d0e92d7f88b4 100644
--- a/lib/libsys/getrlimitusage.2
+++ b/lib/libsys/getrlimitusage.2
@@ -25,7 +25,7 @@
 .\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 .\" SUCH DAMAGE.
 .\"
-.Dd September 27, 2024
+.Dd October 24, 2025
 .Dt GETRLIMITUSAGE 2
 .Os
 .Sh NAME
@@ -97,4 +97,4 @@ and
 The
 .Fn getrlimitusage
 system call appeared in
-.Bx 15.0 .
+.Fx 14.2 .
diff --git a/lib/libsys/kqueue.2 b/lib/libsys/kqueue.2
index 96c9b0222a37..a8ebabf02cf7 100644
--- a/lib/libsys/kqueue.2
+++ b/lib/libsys/kqueue.2
@@ -97,10 +97,37 @@ system call also creates a new kernel event queue, and additionally takes
 a
 .Fa flags
 argument, which is a bitwise-inclusive OR of the following flags:
-.Bl -tag -width "KQUEUE_CLOEXEC"
+.Bl -tag -width "KQUEUE_CPONFORK"
 .It Dv KQUEUE_CLOEXEC
 The returned file descriptor is automatically closed on
 .Xr execve 2
+.It Dv KQUEUE_CPONFORK
+When this flag is set, the created kqueue is copied into
+the child process on
+.Xr fork 2
+calls.
+The kqueue descriptor index of the new kqueue will be inherited by the child,
+that is, the numeric value of the descriptor will remain the same.
+.Pp
+Copying is deep, that is, each registered event in the original kqueue is
+copied (and not shared) into the new kqueue.
+This is contrary to how other descriptor types are handled upon
+.Xr fork 2 ,
+where the copied file descriptor references the same file object
+as the source descriptor (shallow copy).
+.Pp
+By default, in other words, when the flag is not set, kqueues from
+the parent are not copied on fork to the child process.
+The corresponding file descriptor indeces are unused in the child.
+.Pp
+Registered events that reference file descriptors which are not
+duplicated on fork, are not copied into the new kqueue.
+For instance, if the event references a file descriptor opened with the
+.Dv O_CLOEXEC
+flag set, it is not copied.
+Similarly, if event references a kqueue opened without the
+.Dv KQUEUE_CPONFORK
+flag, the event is not copied.
 .El
 .Pp
 The
diff --git a/lib/libsys/socket.2 b/lib/libsys/socket.2
index b211611c6354..48b8f4e87489 100644
--- a/lib/libsys/socket.2
+++ b/lib/libsys/socket.2
@@ -25,7 +25,7 @@
 .\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 .\" SUCH DAMAGE.
 .\"
-.Dd May 17, 2025
+.Dd September 28, 2025
 .Dt SOCKET 2
 .Os
 .Sh NAME
@@ -64,7 +64,7 @@ PF_NETGRAPH	Netgraph sockets,
 PF_NETLINK	Netlink protocols,
 PF_BLUETOOTH	Bluetooth protocols,
 PF_INET_SDP	OFED socket direct protocol (IPv4),
-AF_HYPERV	HyperV sockets
+PF_HYPERV	HyperV sockets
 .Ed
 .Pp
 Each protocol family is connected to an address family, which has the
@@ -89,32 +89,6 @@ SOCK_RAW	Raw-protocol interface,
 SOCK_SEQPACKET	Sequenced packet stream
 .Ed
 .Pp
-A
-.Dv SOCK_STREAM
-type provides sequenced, reliable,
-two-way connection based byte streams.
-An out-of-band data transmission mechanism may be supported.
-A
-.Dv SOCK_DGRAM
-socket supports
-datagrams (connectionless, unreliable messages of
-a fixed (typically small) maximum length).
-A
-.Dv SOCK_SEQPACKET
-socket may provide a sequenced, reliable,
-two-way connection-based data transmission path for datagrams
-of fixed maximum length; a consumer may be required to read
-an entire packet with each read system call.
-This facility may have protocol-specific properties.
-.Dv SOCK_RAW
-sockets provide access to internal network protocols and interfaces.
-The
-.Dv SOCK_RAW
-type is available only to the super-user and is described in
-.Xr ip 4
-and
-.Xr ip6 4 .
-.Pp
 Additionally, the following flags are allowed in the
 .Fa type
 argument:
@@ -140,32 +114,23 @@ particular to the
 in which communication
 is to take place; see
 .Xr protocols 5 .
-.Pp
 The
 .Fa protocol
 argument may be set to zero (0) to request the default
 implementation of a socket type for the protocol, if any.
-.Pp
-Sockets of type
+.Sh STREAM SOCKET TYPE
+The
+.Dv SOCK_STREAM
+socket type provides reliable, sequenced, full-duplex octet streams between
+the socket and a peer to which the socket is connected.
+A socket of type
 .Dv SOCK_STREAM
-are full-duplex byte streams, similar
-to pipes.
-A stream socket must be in a
+needs to be in a
 .Em connected
-state before any data may be sent or received
-on it.
+state before any data can be sent or received.
 A connection to another socket is created with a
 .Xr connect 2
 system call.
-Once connected, data may be transferred using
-.Xr read 2
-and
-.Xr write 2
-calls or some variant of the
-.Xr send 2
-and
-.Xr recv 2
-functions.
 (Some protocol families, such as the Internet family,
 support the notion of an
 .Dq implied connect ,
@@ -173,62 +138,210 @@ which permits data to be sent piggybacked onto a connect operation by
 using the
 .Xr sendto 2
 system call.)
-When a session has been completed a
-.Xr close 2
-may be performed.
-Out-of-band data may also be transmitted as described in
+Once connected, data may be sent using
+.Xr send 2 ,
+.Xr sendto 2 ,
+.Xr sendmsg 2
+and
+.Xr write 2
+system calls.
+Data may be received using
+.Xr recv 2 ,
+.Xr recvfrom 2 ,
+.Xr recvmsg 2 ,
+and
+.Xr read 2
+system calls.
+Record boundaries are not maintained; data sent on a stream socket using output
+operations of one size can be received using input operations of smaller or
+larger sizes without loss of data.
+Data may be buffered; successful return from an output function does not imply
+that the data has been delivered to the peer or even transmitted from the local
+system.
+For certain protocols out-of-band data may also be transmitted as described in
 .Xr send 2
 and received as described in
 .Xr recv 2 .
 .Pp
-The communications protocols used to implement a
-.Dv SOCK_STREAM
-ensure that data
-is not lost or duplicated.
-If a piece of data for which the
-peer protocol has buffer space cannot be successfully transmitted
-within a reasonable length of time, then
-the connection is considered broken and calls
-will indicate an error with
--1 returns and with
-.Er ETIMEDOUT
-as the specific code
-in the global variable
-.Va errno .
-The protocols optionally keep sockets
-.Dq warm
-by forcing transmissions
-roughly every minute in the absence of other activity.
-An error is then indicated if no response can be
-elicited on an otherwise
-idle connection for an extended period (e.g.\& 5 minutes).
-By default, a
+If data cannot be successfully transmitted within a given time then the
+connection is considered broken, and subsequent operations shall fail with
+a protocol specific error code.
+A
 .Dv SIGPIPE
-signal is raised if a process sends
-on a broken stream, but this behavior may be inhibited via
+signal is raised if a thread attempts to send data on a broken stream (one that
+is no longer connected).
+The signal can be suppressed by the
+.Dv MSG_NOSIGNAL
+flag with distinct
+.Xr send 2 ,
+.Xr sendto 2 ,
+and
+.Xr sendmsg 2
+system calls or by the
+.Dv SO_NOSIGPIPE
+socket option set on the socket with
 .Xr setsockopt 2 .
 .Pp
-.Dv SOCK_SEQPACKET
-sockets employ the same system calls
-as
+The
 .Dv SOCK_STREAM
-sockets.
-The only difference
-is that
-.Xr read 2
-calls will return only the amount of data requested,
-and any remaining in the arriving packet will be discarded.
+socket is supported by the following protocol families:
+.Dv PF_INET ,
+.Dv PF_INET6 ,
+.Dv PF_UNIX ,
+.Dv PF_BLUETOOTH ,
+.Dv PF_HYPERV ,
+and
+.Dv PF_INET_SDP .
+Out-of-band data transmission mechanism is supported for stream sockets of
+.Dv PF_INET
+and
+.Dv PF_INET6
+protocol families.
+.Sh DATAGRAM SOCKET TYPE
+The
+.Dv SOCK_DGRAM
+socket type supports connectionless data transfer which is not necessarily
+acknowledged or reliable.
+Datagrams can be sent to the address specified (possibly multicast or
+broadcast) in each output operation, and incoming datagrams can be received
+from multiple sources.
+The source address of each datagram is available when receiving the datagram
+with
+.Xr recvfrom 2
+or
+.Xr recvmsg 2 .
+An application can also pre-specify a peer address with
+.Xr sendto 2
+or
+.Xr sendmsg 2 ,
+in which case calls to output functions that do not specify a peer address
+shall send to the pre-specified peer.
+If a peer has been specified, only datagrams from that peer shall be received.
+A datagram shall be sent in a single output operation, and needs to be received
+in a single input operation.
+The maximum size of a datagram is protocol-specific.
+Output datagrams may be buffered within the system; thus, a successful return
+from an output function does not guarantee that a datagram is actually sent or
+received.
 .Pp
+The
 .Dv SOCK_DGRAM
+socket is supported by the following protocol families:
+.Dv PF_INET ,
+.Dv PF_INET6 ,
+.Dv PF_UNIX ,
+.Dv PF_NETGRAPH ,
 and
-.Dv SOCK_RAW
-sockets allow sending of datagrams to correspondents
-named in
+.Dv PF_NETLINK .
+.Sh SEQUENCED PACKET SOCKET TYPE
+The
+.Dv SOCK_SEQPACKET
+socket type is similar to the
+.Dv SOCK_STREAM
+type, and is also connection-oriented.
+The only difference between these types is that record boundaries are
+maintained using the
+.Dv SOCK_SEQPACKET
+type.
+A record can be sent using one or more output operations and received using one
+or more input operations, but a single operation never transfers parts of more
+than one record.
+Record boundaries are set by the sender with the
+.Dv MSG_EOR
+flag of
 .Xr send 2
-calls.
-Datagrams are generally received with
+or
+.Xr sendmsg 2
+functions.
+There is no possibility to set a record boundary with
+.Xr write 2 .
+Record boundaries are visible to the receiver via the
+.Dv MSG_EOR
+flag in the received message flags returned by the
+.Xr recvmsg 2
+function.
+It is protocol-specific whether a maximum record size is imposed.
+.Pp
+The
+.Dv SOCK_SEQPACKET
+socket is supported by the following protocol families:
+.Dv PF_INET ,
+.Dv PF_INET6 ,
+and
+.Dv PF_UNIX .
+.Pp
+.Sh RAW SOCKET TYPE
+The
+.Dv SOCK_RAW
+socket type provides access to internal network protocols and interfaces.
+It is a datagram socket in its nature, thus has the same semantics of
+read and write operations.
+The
+.Dv SOCK_RAW
+type is available only to the super-user and is described in
+.Xr ip 4
+and
+.Xr ip6 4 .
+.Sh NON-BLOCKING MODE
+A socket can be created in
+.Em non-blocking mode
+with the help of
+.Dv SOCK_NONBLOCK
+flag.
+Alternatively, the non-blocking mode on a socket can be turned on and off with
+the help of the
+.Dv O_NONBLOCK
+flag of the
+.Xr fcntl 2
+system call.
+.Pp
+When a non-blocking socket has not enough data in its receive buffer to fulfill
+the application supplied buffer, then data receiving system calls like
+.Xr recv 2 ,
 .Xr recvfrom 2 ,
-which returns the next datagram with its return address.
+.Xr recvmsg 2
+and
+.Xr read 2
+will not block waiting for the data but immediately return.
+Return value will indicate amount of bytes read into the supplied buffer.
+The
+.Va errno
+will be set to
+.Dv EAGAIN
+.Po
+has same value as
+.Dv EWOULDBLOCK
+.Pc .
+.Pp
+If application tries to send more data on a non-blocking socket than the socket
+send buffer can accomodate with
+.Xr send 2 ,
+.Xr sendto 2 ,
+.Xr sendmsg 2
+or
+.Xr write 2
+system calls partial data will be sent.
+Return value will indicate amount of bytes sent.
+The
+.Va errno
+will be set to
+.Dv EAGAIN .
+Note that sockets of
+.Dv SOCK_DGRAM
+type are unreliable, thus for these sockets sending operations will never fail
+with
+.Dv EAGAIN
+in non-blocking mode neither will block in blocking mode.
+.Sh OTHER OPERATIONS ON SOCKETS
+Since socket descriptors are file descriptors, many generic file operations
+performed by
+.Xr fcntl 2 ,
+apply.
+Socket descriptors can be used with all event engines, such as
+.Xr kevent 2 ,
+.Xr select 2
+and
+.Xr poll 2 .
 .Pp
 An
 .Xr fcntl 2
@@ -250,6 +363,12 @@ The
 and
 .Xr getsockopt 2
 system calls are used to set and get options, respectively.
+.Pp
+Connection associated with a socket can be terminated by
+.Xr close 2
+system call.
+One direction of communication can be disabled with
+.Xr shutdown 2 .
 .Sh RETURN VALUES
 A -1 is returned if an error occurs, otherwise the return
 value is a descriptor referencing the socket.
@@ -282,16 +401,23 @@ The socket type is not supported by the protocol.
 .Sh SEE ALSO
 .Xr accept 2 ,
 .Xr bind 2 ,
+.Xr close 2 ,
 .Xr connect 2 ,
+.Xr fcntl 2 ,
 .Xr getpeername 2 ,
 .Xr getsockname 2 ,
 .Xr getsockopt 2 ,
 .Xr ioctl 2 ,
+.Xr kevent 2 ,
 .Xr listen 2 ,
+.Xr poll 2 ,
 .Xr read 2 ,
 .Xr recv 2 ,
 .Xr select 2 ,
 .Xr send 2 ,
+.Xr sendmsg 2 ,
+.Xr sendto 2 ,
+.Xr signal 3 ,
 .Xr shutdown 2 ,
 .Xr socketpair 2 ,
 .Xr write 2 ,