At long last, commit the zero copy sockets code.

MAKEDEV:	Add MAKEDEV glue for the ti(4) device nodes.

ti.4:		Update the ti(4) man page to include information on the
		TI_JUMBO_HDRSPLIT and TI_PRIVATE_JUMBOS kernel options,
		and also include information about the new character
		device interface and the associated ioctls.

man9/Makefile:	Add jumbo.9 and zero_copy.9 man pages and associated
		links.

jumbo.9:	New man page describing the jumbo buffer allocator
		interface and operation.

zero_copy.9:	New man page describing the general characteristics of
		the zero copy send and receive code, and what an
		application author should do to take advantage of the
		zero copy functionality.

NOTES:		Add entries for ZERO_COPY_SOCKETS, TI_PRIVATE_JUMBOS,
		TI_JUMBO_HDRSPLIT, MSIZE, and MCLSHIFT.

conf/files:	Add uipc_jumbo.c and uipc_cow.c.

conf/options:	Add the 5 options mentioned above.

kern_subr.c:	Receive side zero copy implementation.  This takes
		"disposable" pages attached to an mbuf, gives them to
		a user process, and then recycles the user's page.
		This is only active when ZERO_COPY_SOCKETS is turned on
		and the kern.ipc.zero_copy.receive sysctl variable is
		set to 1.

uipc_cow.c:	Send side zero copy functions.  Takes a page written
		by the user and maps it copy on write and assigns it
		kernel virtual address space.  Removes copy on write
		mapping once the buffer has been freed by the network
		stack.

uipc_jumbo.c:	Jumbo disposable page allocator code.  This allocates
		(optionally) disposable pages for network drivers that
		want to give the user the option of doing zero copy
		receive.

uipc_socket.c:	Add kern.ipc.zero_copy.{send,receive} sysctls that are
		enabled if ZERO_COPY_SOCKETS is turned on.

		Add zero copy send support to sosend() -- pages get
		mapped into the kernel instead of getting copied if
		they meet size and alignment restrictions.

uipc_syscalls.c:Un-staticize some of the sf* functions so that they
		can be used elsewhere.  (uipc_cow.c)

if_media.c:	In the SIOCGIFMEDIA ioctl in ifmedia_ioctl(), avoid
		calling malloc() with M_WAITOK.  Return an error if
		the M_NOWAIT malloc fails.

		The ti(4) driver and the wi(4) driver, at least, call
		this with a mutex held.  This causes witness warnings
		for 'ifconfig -a' with a wi(4) or ti(4) board in the
		system.  (I've only verified for ti(4)).

ip_output.c:	Fragment large datagrams so that each segment contains
		a multiple of PAGE_SIZE amount of data plus headers.
		This allows the receiver to potentially do page
		flipping on receives.

if_ti.c:	Add zero copy receive support to the ti(4) driver.  If
		TI_PRIVATE_JUMBOS is not defined, it now uses the
		jumbo(9) buffer allocator for jumbo receive buffers.

		Add a new character device interface for the ti(4)
		driver for the new debugging interface.  This allows
		(a patched version of) gdb to talk to the Tigon board
		and debug the firmware.  There are also a few additional
		debugging ioctls available through this interface.

		Add header splitting support to the ti(4) driver.

		Tweak some of the default interrupt coalescing
		parameters to more useful defaults.

		Add hooks for supporting transmit flow control, but
		leave it turned off with a comment describing why it
		is turned off.

if_tireg.h:	Change the firmware rev to 12.4.11, since we're really
		at 12.4.11 plus fixes from 12.4.13.

		Add defines needed for debugging.

		Remove the ti_stats structure, it is now defined in
		sys/tiio.h.

ti_fw.h:	12.4.11 firmware.

ti_fw2.h:	12.4.11 firmware, plus selected fixes from 12.4.13,
		and my header splitting patches.  Revision 12.4.13
		doesn't handle 10/100 negotiation properly.  (This
		firmware is the same as what was in the tree previously,
		with the addition of header splitting support.)

sys/jumbo.h:	Jumbo buffer allocator interface.

sys/mbuf.h:	Add a new external mbuf type, EXT_DISPOSABLE, to
		indicate that the payload buffer can be thrown away /
		flipped to a userland process.

socketvar.h:	Add prototype for socow_setup.

tiio.h:		ioctl interface to the character portion of the ti(4)
		driver, plus associated structure/type definitions.

uio.h:		Change prototype for uiomoveco() so that we'll know
		whether the source page is disposable.

ufs_readwrite.c:Update for new prototype of uiomoveco().

vm_fault.c:	In vm_fault(), check to see whether we need to do a page
		based copy on write fault.

vm_object.c:	Add a new function, vm_object_allocate_wait().  This
		does the same thing that vm_object allocate does, except
		that it gives the caller the opportunity to specify whether
		it should wait on the uma_zalloc() of the object structre.

		This allows vm objects to be allocated while holding a
		mutex.  (Without generating WITNESS warnings.)

		vm_object_allocate() is implemented as a call to
		vm_object_allocate_wait() with the malloc flag set to
		M_WAITOK.

vm_object.h:	Add prototype for vm_object_allocate_wait().

vm_page.c:	Add page-based copy on write setup, clear and fault
		routines.

vm_page.h:	Add page based COW function prototypes and variable in
		the vm_page structure.

Many thanks to Drew Gallatin, who wrote the zero copy send and receive
code, and to all the other folks who have tested and reviewed this code
over the years.

1 files changed, 102 insertions, 0 deletions

diff --git a/sys/kern/uipc_socket.c b/sys/kern/uipc_socket.c
index 2b9e0be..7cc27d3 100644
--- a/sys/kern/uipc_socket.c
+++ b/sys/kern/uipc_socket.c
@@ -35,6 +35,7 @@
  */
 
 #include "opt_inet.h"
+#include "opt_zero.h"
 
 #include <sys/param.h>
 #include <sys/systm.h>
@@ -94,6 +95,17 @@ SYSCTL_INT(_kern_ipc, KIPC_SOMAXCONN, somaxconn, CTLFLAG_RW,
 static int numopensockets;
 SYSCTL_INT(_kern_ipc, OID_AUTO, numopensockets, CTLFLAG_RD,
     &numopensockets, 0, "Number of open sockets");
+#ifdef ZERO_COPY_SOCKETS
+/* These aren't static because they're used in other files. */
+int so_zero_copy_send = 1;
+int so_zero_copy_receive = 1;
+SYSCTL_NODE(_kern_ipc, OID_AUTO, zero_copy, CTLFLAG_RD, 0,
+    "Zero copy controls");
+SYSCTL_INT(_kern_ipc_zero_copy, OID_AUTO, receive, CTLFLAG_RW,
+    &so_zero_copy_receive, 0, "Enable zero copy receive");
+SYSCTL_INT(_kern_ipc_zero_copy, OID_AUTO, send, CTLFLAG_RW,
+    &so_zero_copy_send, 0, "Enable zero copy send");
+#endif /* ZERO_COPY_SOCKETS */
 
 
 /*
@@ -471,6 +483,22 @@ bad:
  * must check for short counts if EINTR/ERESTART are returned.
  * Data and control buffers are freed on return.
  */
+
+#ifdef ZERO_COPY_SOCKETS
+struct so_zerocopy_stats{
+	int size_ok;
+	int align_ok;
+	int found_ifp;
+};
+struct so_zerocopy_stats so_zerocp_stats = {0,0,0};
+#include <netinet/in.h>
+#include <net/route.h>
+#include <netinet/in_pcb.h>
+#include <vm/vm.h>
+#include <vm/vm_page.h>
+#include <vm/vm_object.h>
+#endif /*ZERO_COPY_SOCKETS*/
+
 int
 sosend(so, addr, uio, top, control, flags, td)
 	register struct socket *so;
@@ -486,6 +514,9 @@ sosend(so, addr, uio, top, control, flags, td)
 	register long space, len, resid;
 	int clen = 0, error, s, dontroute, mlen;
 	int atomic = sosendallatonce(so) || top;
+#ifdef ZERO_COPY_SOCKETS
+	int cow_send;
+#endif /* ZERO_COPY_SOCKETS */
 
 	if (uio)
 		resid = uio->uio_resid;
@@ -574,6 +605,9 @@ restart:
 			if (flags & MSG_EOR)
 				top->m_flags |= M_EOR;
 		    } else do {
+#ifdef ZERO_COPY_SOCKETS
+			cow_send = 0;
+#endif /* ZERO_COPY_SOCKETS */
 			if (top == 0) {
 				MGETHDR(m, M_TRYWAIT, MT_DATA);
 				if (m == NULL) {
@@ -592,12 +626,32 @@ restart:
 				mlen = MLEN;
 			}
 			if (resid >= MINCLSIZE) {
+#ifdef ZERO_COPY_SOCKETS				
+				if (so_zero_copy_send &&
+				    resid>=PAGE_SIZE && 
+				    space>=PAGE_SIZE && 
+				    uio->uio_iov->iov_len>=PAGE_SIZE) {
+					so_zerocp_stats.size_ok++;
+					if (!((vm_offset_t)
+					  uio->uio_iov->iov_base & PAGE_MASK)){
+						so_zerocp_stats.align_ok++;
+						cow_send = socow_setup(m, uio);
+					}
+				} 
+				if (!cow_send){
+#endif /* ZERO_COPY_SOCKETS */
 				MCLGET(m, M_TRYWAIT);
 				if ((m->m_flags & M_EXT) == 0)
 					goto nopages;
 				mlen = MCLBYTES;
 				len = min(min(mlen, resid), space);
 			} else {
+#ifdef ZERO_COPY_SOCKETS
+					len = PAGE_SIZE;
+				}
+					
+			} else {
+#endif /* ZERO_COPY_SOCKETS */
 nopages:
 				len = min(min(mlen, resid), space);
 				/*
@@ -608,6 +662,11 @@ nopages:
 					MH_ALIGN(m, len);
 			}
 			space -= len;
+#ifdef ZERO_COPY_SOCKETS
+			if (cow_send)
+				error = 0;
+			else
+#endif /* ZERO_COPY_SOCKETS */
 			error = uiomove(mtod(m, caddr_t), (int)len, uio);
 			resid = uio->uio_resid;
 			m->m_len = len;
@@ -719,6 +778,27 @@ soreceive(so, psa, uio, mp0, controlp, flagsp)
 		if (error)
 			goto bad;
 		do {
+#ifdef ZERO_COPY_SOCKETS
+			if (so_zero_copy_receive) {
+				vm_page_t pg;
+				int disposable;
+
+				if ((m->m_flags & M_EXT)
+				 && (m->m_ext.ext_type == EXT_DISPOSABLE))
+					disposable = 1;
+				else
+					disposable = 0;
+
+				pg = PHYS_TO_VM_PAGE(vtophys(mtod(m, caddr_t)));
+				if (uio->uio_offset == -1)
+					uio->uio_offset =IDX_TO_OFF(pg->pindex);
+
+				error = uiomoveco(mtod(m, caddr_t), 
+						  min(uio->uio_resid, m->m_len),
+						  uio, pg->object,
+						  disposable);
+			} else
+#endif /* ZERO_COPY_SOCKETS */
 			error = uiomove(mtod(m, caddr_t),
 			    (int) min(uio->uio_resid, m->m_len), uio);
 			m = m_free(m);
@@ -874,6 +954,28 @@ dontblock:
 		 */
 		if (mp == 0) {
 			splx(s);
+#ifdef ZERO_COPY_SOCKETS
+			if (so_zero_copy_receive) {
+				vm_page_t pg;
+				int disposable;
+
+				if ((m->m_flags & M_EXT)
+				 && (m->m_ext.ext_type == EXT_DISPOSABLE))
+					disposable = 1;
+				else
+					disposable = 0;
+ 
+				pg = PHYS_TO_VM_PAGE(vtophys(mtod(m, caddr_t) +
+					moff));
+
+				if (uio->uio_offset == -1)
+					uio->uio_offset =IDX_TO_OFF(pg->pindex);
+
+				error = uiomoveco(mtod(m, caddr_t) + moff,
+						  (int)len, uio,pg->object,
+						  disposable);
+			} else
+#endif /* ZERO_COPY_SOCKETS */
 			error = uiomove(mtod(m, caddr_t) + moff, (int)len, uio);
 			s = splnet();
 			if (error)