Hello everyone, building up on Stefan's and my patches and Daniel's useful hint regarding filter.txt, I assembled this short patch. It attempts to clarify the tp_status situtation, considering that zero has a special meaning and most bits are actually mutually exclusive. I added filter.txt and and Daniel's and Chetan's excellent psock_tpacket.c (IIRC Michael has already done that, but not yet pushed to the public git repo) to the "see also" section. I also appended packet.7 to getsockopt.2's "see also" section. Cheers, Carsten diff --git a/man2/getsockopt.2 b/man2/getsockopt.2 index 925fa90..151cd31 100644 --- a/man2/getsockopt.2 +++ b/man2/getsockopt.2 @@ -205,6 +205,7 @@ system. .BR getprotoent (3), .BR protocols (5), .BR ip (7), +.BR packet (7), .BR socket (7), .BR tcp (7), .BR udp (7), diff --git a/man7/packet.7 b/man7/packet.7 index d8257f9..1ffcf32 100644 --- a/man7/packet.7 +++ b/man7/packet.7 @@ -319,9 +319,20 @@ original fanout algorithm selects a backlogged socket, the packet rolls over to the next available one. .TP .BR PACKET_LOSS " (with " PACKET_TX_RING ) -If set, do not silently drop a packet on transmission error, but -return it with status set to -.BR TP_STATUS_WRONG_FORMAT . +When a malformed packet is encountered on a transmit ring, the default is +to reset its +.I tp_status +to +.BR TP_STATUS_WRONG_FORMAT +and abort the transmission immediately (it and following packets are left +lingering on the ring). +However if +.BR PACKET_LOSS +is set, any malformed packet will be skipped, its +.I tp_status +reset to +.BR TP_STATUS_AVAILABLE +and the transmission process continued. .TP .BR PACKET_RESERVE " (with " PACKET_RX_RING ) By default, a packet receive ring writes packets immediately following the @@ -353,15 +364,21 @@ Packet socket and application communicate the head and tail of the ring through the .I tp_status field. -The packet socket owns all slots with status +The packet socket owns all slots with +.I tp_status +equal to .BR TP_STATUS_KERNEL . After filling a slot, it changes the status of the slot to transfer ownership to the application. -During normal operation, the new status is -.BR TP_STATUS_USER , -to signal that a correctly received packet has been stored. +During normal operation, the new +.I tp_status +value has at least the +.BR TP_STATUS_USER +bit set, to signal that a received packet has been stored. When the application has finished processing a packet, it transfers -ownership of the slot back to the socket by setting the status to +ownership of the slot back to the socket by setting +.I tp_status +equal to .BR TP_STATUS_KERNEL . Packet sockets implement multiple variants of the packet ring. The implementation details are described in @@ -400,9 +417,13 @@ Create a memory-mapped ring buffer for packet transmission. This option is similar to .BR PACKET_RX_RING and takes the same arguments. -The application writes packets into slots with status +The application writes packets into slots with +.I tp_status +equal to .BR TP_STATUS_AVAILABLE -and schedules them for transmission by changing the status to +and schedules them for transmission by changing +.I tp_status +to .BR TP_STATUS_SEND_REQUEST . When packets are ready to be transmitted, the application calls .BR send (2) @@ -417,9 +438,11 @@ If an address is passed using or .BR sendmsg (2), then that overrides the socket default. -On successful transmission, the socket resets the slot to +On successful transmission, the socket resets +.I tp_status +to .BR TP_STATUS_AVAILABLE . -It discards packets silently on error unless +It immediately aborts the transmission on error unless .BR PACKET_LOSS is set. .TP @@ -625,3 +648,12 @@ RFC\ 1700 for the IEEE 802.3 IP encapsulation. The .I <linux/if_ether.h> include file for physical layer protocols. + +The Linux kernel source tree. +.IR /Documentation/networking/filter.txt +describes how to apply Berkeley Packet Filters to packet sockets. +.IR /tools/testing/selftests/net/psock_tpacket.c +contains usage examples for all available versions of +.BR PACKET_RX_RING +and +.BR PACKET_TX_RING . -- To unsubscribe from this list: send the line "unsubscribe linux-man" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
