From 69e3c75f4d541a6eb151b3ef91f34033cb3ad6e1 Mon Sep 17 00:00:00 2001 From: Johann Baudy Date: Mon, 18 May 2009 22:11:22 -0700 Subject: [PATCH] net: TX_RING and packet mmap New packet socket feature that makes packet socket more efficient for transmission. - It reduces number of system call through a PACKET_TX_RING mechanism, based on PACKET_RX_RING (Circular buffer allocated in kernel space which is mmapped from user space). - It minimizes CPU copy using fragmented SKB (almost zero copy). Signed-off-by: Johann Baudy Signed-off-by: David S. Miller --- Documentation/networking/packet_mmap.txt | 138 +++++- include/linux/if_packet.h | 20 +- include/linux/skbuff.h | 3 + net/packet/af_packet.c | 602 ++++++++++++++++++----- 4 files changed, 622 insertions(+), 141 deletions(-) diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt index 07c53d596035..a22fd85e3796 100644 --- a/Documentation/networking/packet_mmap.txt +++ b/Documentation/networking/packet_mmap.txt @@ -4,16 +4,18 @@ This file documents the CONFIG_PACKET_MMAP option available with the PACKET socket interface on 2.4 and 2.6 kernels. This type of sockets is used for -capture network traffic with utilities like tcpdump or any other that uses -the libpcap library. - -You can find the latest version of this document at +capture network traffic with utilities like tcpdump or any other that needs +raw access to network interface. +You can find the latest version of this document at: http://pusa.uv.es/~ulisses/packet_mmap/ -Please send me your comments to +Howto can be found at: + http://wiki.gnu-log.net (packet_mmap) +Please send your comments to Ulisses Alonso Camaró + Johann Baudy ------------------------------------------------------------------------------- + Why use PACKET_MMAP @@ -25,19 +27,24 @@ to capture each packet, it requires two if you want to get packet's timestamp (like libpcap always does). In the other hand PACKET_MMAP is very efficient. PACKET_MMAP provides a size -configurable circular buffer mapped in user space. This way reading packets just -needs to wait for them, most of the time there is no need to issue a single -system call. By using a shared buffer between the kernel and the user -also has the benefit of minimizing packet copies. +configurable circular buffer mapped in user space that can be used to either +send or receive packets. This way reading packets just needs to wait for them, +most of the time there is no need to issue a single system call. Concerning +transmission, multiple packets can be sent through one system call to get the +highest bandwidth. +By using a shared buffer between the kernel and the user also has the benefit +of minimizing packet copies. -It's fine to use PACKET_MMAP to improve the performance of the capture process, -but it isn't everything. At least, if you are capturing at high speeds (this -is relative to the cpu speed), you should check if the device driver of your -network interface card supports some sort of interrupt load mitigation or -(even better) if it supports NAPI, also make sure it is enabled. +It's fine to use PACKET_MMAP to improve the performance of the capture and +transmission process, but it isn't everything. At least, if you are capturing +at high speeds (this is relative to the cpu speed), you should check if the +device driver of your network interface card supports some sort of interrupt +load mitigation or (even better) if it supports NAPI, also make sure it is +enabled. For transmission, check the MTU (Maximum Transmission Unit) used and +supported by devices of your network. -------------------------------------------------------------------------------- -+ How to use CONFIG_PACKET_MMAP ++ How to use CONFIG_PACKET_MMAP to improve capture process -------------------------------------------------------------------------------- From the user standpoint, you should use the higher level libpcap library, which @@ -57,7 +64,7 @@ the low level details or want to improve libpcap by including PACKET_MMAP support. -------------------------------------------------------------------------------- -+ How to use CONFIG_PACKET_MMAP directly ++ How to use CONFIG_PACKET_MMAP directly to improve capture process -------------------------------------------------------------------------------- From the system calls stand point, the use of PACKET_MMAP involves @@ -66,6 +73,7 @@ the following process: [setup] socket() -------> creation of the capture socket setsockopt() ---> allocation of the circular buffer (ring) + option: PACKET_RX_RING mmap() ---------> mapping of the allocated buffer to the user process @@ -96,6 +104,65 @@ Next I will describe PACKET_MMAP settings and it's constraints, also the mapping of the circular buffer in the user process and the use of this buffer. +-------------------------------------------------------------------------------- ++ How to use CONFIG_PACKET_MMAP directly to improve transmission process +-------------------------------------------------------------------------------- +Transmission process is similar to capture as shown below. + +[setup] socket() -------> creation of the transmission socket + setsockopt() ---> allocation of the circular buffer (ring) + option: PACKET_TX_RING + bind() ---------> bind transmission socket with a network interface + mmap() ---------> mapping of the allocated buffer to the + user process + +[transmission] poll() ---------> wait for free packets (optional) + send() ---------> send all packets that are set as ready in + the ring + The flag MSG_DONTWAIT can be used to return + before end of transfer. + +[shutdown] close() --------> destruction of the transmission socket and + deallocation of all associated resources. + +Binding the socket to your network interface is mandatory (with zero copy) to +know the header size of frames used in the circular buffer. + +As capture, each frame contains two parts: + + -------------------- +| struct tpacket_hdr | Header. It contains the status of +| | of this frame +|--------------------| +| data buffer | +. . Data that will be sent over the network interface. +. . + -------------------- + + bind() associates the socket to your network interface thanks to + sll_ifindex parameter of struct sockaddr_ll. + + Initialization example: + + struct sockaddr_ll my_addr; + struct ifreq s_ifr; + ... + + strncpy (s_ifr.ifr_name, "eth0", sizeof(s_ifr.ifr_name)); + + /* get interface index of eth0 */ + ioctl(this->socket, SIOCGIFINDEX, &s_ifr); + + /* fill sockaddr_ll struct to prepare binding */ + my_addr.sll_family = AF_PACKET; + my_addr.sll_protocol = ETH_P_ALL; + my_addr.sll_ifindex = s_ifr.ifr_ifindex; + + /* bind socket to eth0 */ + bind(this->socket, (struct sockaddr *)&my_addr, sizeof(struct sockaddr_ll)); + + A complete tutorial is available at: http://wiki.gnu-log.net/ + -------------------------------------------------------------------------------- + PACKET_MMAP settings -------------------------------------------------------------------------------- @@ -103,7 +170,10 @@ the use of this buffer. To setup PACKET_MMAP from user level code is done with a call like + - Capture process setsockopt(fd, SOL_PACKET, PACKET_RX_RING, (void *) &req, sizeof(req)) + - Transmission process + setsockopt(fd, SOL_PACKET, PACKET_TX_RING, (void *) &req, sizeof(req)) The most significant argument in the previous call is the req parameter, this parameter must to have the following structure: @@ -117,11 +187,11 @@ this parameter must to have the following structure: }; This structure is defined in /usr/include/linux/if_packet.h and establishes a -circular buffer (ring) of unswappable memory mapped in the capture process. +circular buffer (ring) of unswappable memory. Being mapped in the capture process allows reading the captured frames and related meta-information like timestamps without requiring a system call. -Captured frames are grouped in blocks. Each block is a physically contiguous +Frames are grouped in blocks. Each block is a physically contiguous region of memory and holds tp_block_size/tp_frame_size frames. The total number of blocks is tp_block_nr. Note that tp_frame_nr is a redundant parameter because @@ -336,6 +406,7 @@ struct tpacket_hdr). If this field is 0 means that the frame is ready to be used for the kernel, If not, there is a frame the user can read and the following flags apply: ++++ Capture process: from include/linux/if_packet.h #define TP_STATUS_COPY 2 @@ -391,6 +462,37 @@ packets are in the ring: It doesn't incur in a race condition to first check the status value and then poll for frames. + +++ Transmission process +Those defines are also used for transmission: + + #define TP_STATUS_AVAILABLE 0 // Frame is available + #define TP_STATUS_SEND_REQUEST 1 // Frame will be sent on next send() + #define TP_STATUS_SENDING 2 // Frame is currently in transmission + #define TP_STATUS_WRONG_FORMAT 4 // Frame format is not correct + +First, the kernel initializes all frames to TP_STATUS_AVAILABLE. To send a +packet, the user fills a data buffer of an available frame, sets tp_len to +current data buffer size and sets its status field to TP_STATUS_SEND_REQUEST. +This can be done on multiple frames. Once the user is ready to transmit, it +calls send(). Then all buffers with status equal to TP_STATUS_SEND_REQUEST are +forwarded to the network device. The kernel updates each status of sent +frames with TP_STATUS_SENDING until the end of transfer. +At the end of each transfer, buffer status returns to TP_STATUS_AVAILABLE. + + header->tp_len = in_i_size; + header->tp_status = TP_STATUS_SEND_REQUEST; + retval = send(this->socket, NULL, 0, 0); + +The user can also use poll() to check if a buffer is available: +(status == TP_STATUS_SENDING) + + struct pollfd pfd; + pfd.fd = fd; + pfd.revents = 0; + pfd.events = POLLOUT; + retval = poll(&pfd, 1, timeout); + -------------------------------------------------------------------------------- + THANKS -------------------------------------------------------------------------------- diff --git a/include/linux/if_packet.h b/include/linux/if_packet.h index 18db0668065a..5b2badeb9497 100644 --- a/include/linux/if_packet.h +++ b/include/linux/if_packet.h @@ -46,6 +46,8 @@ struct sockaddr_ll #define PACKET_VERSION 10 #define PACKET_HDRLEN 11 #define PACKET_RESERVE 12 +#define PACKET_TX_RING 13 +#define PACKET_LOSS 14 struct tpacket_stats { @@ -63,14 +65,22 @@ struct tpacket_auxdata __u16 tp_vlan_tci; }; +/* Rx ring - header status */ +#define TP_STATUS_KERNEL 0x0 +#define TP_STATUS_USER 0x1 +#define TP_STATUS_COPY 0x2 +#define TP_STATUS_LOSING 0x4 +#define TP_STATUS_CSUMNOTREADY 0x8 + +/* Tx ring - header status */ +#define TP_STATUS_AVAILABLE 0x0 +#define TP_STATUS_SEND_REQUEST 0x1 +#define TP_STATUS_SENDING 0x2 +#define TP_STATUS_WRONG_FORMAT 0x4 + struct tpacket_hdr { unsigned long tp_status; -#define TP_STATUS_KERNEL 0 -#define TP_STATUS_USER 1 -#define TP_STATUS_COPY 2 -#define TP_STATUS_LOSING 4 -#define TP_STATUS_CSUMNOTREADY 8 unsigned int tp_len; unsigned int tp_snaplen; unsigned short tp_mac; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 1b5c3d298f43..aff494ba6a31 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -203,6 +203,9 @@ struct skb_shared_info { #ifdef CONFIG_HAS_DMA dma_addr_t dma_maps[MAX_SKB_FRAGS + 1]; #endif + /* Intermediate layers must ensure that destructor_arg + * remains valid until skb destructor */ + void * destructor_arg; }; /* We divide dataref into two halves. The higher 16 bits hold references diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index f546e81acc45..766e6b41f7ca 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -39,6 +39,7 @@ * will simply extend the hardware address * byte arrays at the end of sockaddr_ll * and packet_mreq. + * Johann Baudy : Added TX RING. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -157,7 +158,25 @@ struct packet_mreq_max }; #ifdef CONFIG_PACKET_MMAP -static int packet_set_ring(struct sock *sk, struct tpacket_req *req, int closing); +static int packet_set_ring(struct sock *sk, struct tpacket_req *req, + int closing, int tx_ring); + +struct packet_ring_buffer { + char * *pg_vec; + unsigned int head; + unsigned int frames_per_block; + unsigned int frame_size; + unsigned int frame_max; + + unsigned int pg_vec_order; + unsigned int pg_vec_pages; + unsigned int pg_vec_len; + + atomic_t pending; +}; + +struct packet_sock; +static int tpacket_snd(struct packet_sock *po, struct msghdr *msg); #endif static void packet_flush_mclist(struct sock *sk); @@ -167,11 +186,8 @@ struct packet_sock { struct sock sk; struct tpacket_stats stats; #ifdef CONFIG_PACKET_MMAP - char * *pg_vec; - unsigned int head; - unsigned int frames_per_block; - unsigned int frame_size; - unsigned int frame_max; + struct packet_ring_buffer rx_ring; + struct packet_ring_buffer tx_ring; int copy_thresh; #endif struct packet_type prot_hook; @@ -185,12 +201,10 @@ struct packet_sock { struct packet_mclist *mclist; #ifdef CONFIG_PACKET_MMAP atomic_t mapped; - unsigned int pg_vec_order; - unsigned int pg_vec_pages; - unsigned int pg_vec_len; enum tpacket_versions tp_version; unsigned int tp_hdrlen; unsigned int tp_reserve; + unsigned int tp_loss:1; #endif }; @@ -206,35 +220,6 @@ struct packet_skb_cb { #ifdef CONFIG_PACKET_MMAP -static void *packet_lookup_frame(struct packet_sock *po, unsigned int position, - int status) -{ - unsigned int pg_vec_pos, frame_offset; - union { - struct tpacket_hdr *h1; - struct tpacket2_hdr *h2; - void *raw; - } h; - - pg_vec_pos = position / po->frames_per_block; - frame_offset = position % po->frames_per_block; - - h.raw = po->pg_vec[pg_vec_pos] + (frame_offset * po->frame_size); - switch (po->tp_version) { - case TPACKET_V1: - if (status != (h.h1->tp_status ? TP_STATUS_USER : - TP_STATUS_KERNEL)) - return NULL; - break; - case TPACKET_V2: - if (status != (h.h2->tp_status ? TP_STATUS_USER : - TP_STATUS_KERNEL)) - return NULL; - break; - } - return h.raw; -} - static void __packet_set_status(struct packet_sock *po, void *frame, int status) { union { @@ -247,12 +232,88 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status) switch (po->tp_version) { case TPACKET_V1: h.h1->tp_status = status; + flush_dcache_page(virt_to_page(&h.h1->tp_status)); break; case TPACKET_V2: h.h2->tp_status = status; + flush_dcache_page(virt_to_page(&h.h2->tp_status)); break; + default: + printk(KERN_ERR "TPACKET version not supported\n"); + BUG(); + } + + smp_wmb(); +} + +static int __packet_get_status(struct packet_sock *po, void *frame) +{ + union { + struct tpacket_hdr *h1; + struct tpacket2_hdr *h2; + void *raw; + } h; + + smp_rmb(); + + h.raw = frame; + switch (po->tp_version) { + case TPACKET_V1: + flush_dcache_page(virt_to_page(&h.h1->tp_status)); + return h.h1->tp_status; + case TPACKET_V2: + flush_dcache_page(virt_to_page(&h.h2->tp_status)); + return h.h2->tp_status; + default: + printk(KERN_ERR "TPACKET version not supported\n"); + BUG(); + return 0; } } + +static void *packet_lookup_frame(struct packet_sock *po, + struct packet_ring_buffer *rb, + unsigned int position, + int status) +{ + unsigned int pg_vec_pos, frame_offset; + union { + struct tpacket_hdr *h1; + struct tpacket2_hdr *h2; + void *raw; + } h; + + pg_vec_pos = position / rb->frames_per_block; + frame_offset = position % rb->frames_per_block; + + h.raw = rb->pg_vec[pg_vec_pos] + (frame_offset * rb->frame_size); + + if (status != __packet_get_status(po, h.raw)) + return NULL; + + return h.raw; +} + +static inline void *packet_current_frame(struct packet_sock *po, + struct packet_ring_buffer *rb, + int status) +{ + return packet_lookup_frame(po, rb, rb->head, status); +} + +static inline void *packet_previous_frame(struct packet_sock *po, + struct packet_ring_buffer *rb, + int status) +{ + unsigned int previous = rb->head ? rb->head - 1 : rb->frame_max; + return packet_lookup_frame(po, rb, previous, status); +} + +static inline void packet_increment_head(struct packet_ring_buffer *buff) +{ + buff->head = buff->head != buff->frame_max ? buff->head+1 : 0; +} + #endif static inline struct packet_sock *pkt_sk(struct sock *sk) @@ -648,7 +709,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packe macoff = netoff - maclen; } - if (macoff + snaplen > po->frame_size) { + if (macoff + snaplen > po->rx_ring.frame_size) { if (po->copy_thresh && atomic_read(&sk->sk_rmem_alloc) + skb->truesize < (unsigned)sk->sk_rcvbuf) { @@ -661,16 +722,16 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packe if (copy_skb) skb_set_owner_r(copy_skb, sk); } - snaplen = po->frame_size - macoff; + snaplen = po->rx_ring.frame_size - macoff; if ((int)snaplen < 0) snaplen = 0; } spin_lock(&sk->sk_receive_queue.lock); - h.raw = packet_lookup_frame(po, po->head, TP_STATUS_KERNEL); + h.raw = packet_current_frame(po, &po->rx_ring, TP_STATUS_KERNEL); if (!h.raw) goto ring_is_full; - po->head = po->head != po->frame_max ? po->head+1 : 0; + packet_increment_head(&po->rx_ring); po->stats.tp_packets++; if (copy_skb) { status |= TP_STATUS_COPY; @@ -727,7 +788,6 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packe __packet_set_status(po, h.raw, status); smp_mb(); - { struct page *p_start, *p_end; u8 *h_end = h.raw + macoff + snaplen - 1; @@ -760,10 +820,249 @@ ring_is_full: goto drop_n_restore; } +static void tpacket_destruct_skb(struct sk_buff *skb) +{ + struct packet_sock *po = pkt_sk(skb->sk); + void * ph; + + BUG_ON(skb == NULL); + + if (likely(po->tx_ring.pg_vec)) { + ph = skb_shinfo(skb)->destructor_arg; + BUG_ON(__packet_get_status(po, ph) != TP_STATUS_SENDING); + BUG_ON(atomic_read(&po->tx_ring.pending) == 0); + atomic_dec(&po->tx_ring.pending); + __packet_set_status(po, ph, TP_STATUS_AVAILABLE); + } + + sock_wfree(skb); +} + +static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff * skb, + void * frame, struct net_device *dev, int size_max, + __be16 proto, unsigned char * addr) +{ + union { + struct tpacket_hdr *h1; + struct tpacket2_hdr *h2; + void *raw; + } ph; + int to_write, offset, len, tp_len, nr_frags, len_max; + struct socket *sock = po->sk.sk_socket; + struct page *page; + void *data; + int err; + + ph.raw = frame; + + skb->protocol = proto; + skb->dev = dev; + skb->priority = po->sk.sk_priority; + skb_shinfo(skb)->destructor_arg = ph.raw; + + switch (po->tp_version) { + case TPACKET_V2: + tp_len = ph.h2->tp_len; + break; + default: + tp_len = ph.h1->tp_len; + break; + } + if (unlikely(tp_len > size_max)) { + printk(KERN_ERR "packet size is too long (%d > %d)\n", + tp_len, size_max); + return -EMSGSIZE; + } + + skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reset_network_header(skb); + + data = ph.raw + po->tp_hdrlen - sizeof(struct sockaddr_ll); + to_write = tp_len; + + if (sock->type == SOCK_DGRAM) { + err = dev_hard_header(skb, dev, ntohs(proto), addr, + NULL, tp_len); + if (unlikely(err < 0)) + return -EINVAL; + } else if (dev->hard_header_len ) { + /* net device doesn't like empty head */ + if (unlikely(tp_len <= dev->hard_header_len)) { + printk(KERN_ERR "packet size is too short " + "(%d < %d)\n", tp_len, + dev->hard_header_len); + return -EINVAL; + } + + skb_push(skb, dev->hard_header_len); + err = skb_store_bits(skb, 0, data, + dev->hard_header_len); + if (unlikely(err)) + return err; + + data += dev->hard_header_len; + to_write -= dev->hard_header_len; + } + + err = -EFAULT; + page = virt_to_page(data); + offset = offset_in_page(data); + len_max = PAGE_SIZE - offset; + len = ((to_write > len_max) ? len_max : to_write); + + skb->data_len = to_write; + skb->len += to_write; + skb->truesize += to_write; + atomic_add(to_write, &po->sk.sk_wmem_alloc); + + while (likely(to_write)) { + nr_frags = skb_shinfo(skb)->nr_frags; + + if (unlikely(nr_frags >= MAX_SKB_FRAGS)) { + printk(KERN_ERR "Packet exceed the number " + "of skb frags(%lu)\n", + MAX_SKB_FRAGS); + return -EFAULT; + } + + flush_dcache_page(page); + get_page(page); + skb_fill_page_desc(skb, + nr_frags, + page++, offset, len); + to_write -= len; + offset = 0; + len_max = PAGE_SIZE; + len = ((to_write > len_max) ? len_max : to_write); + } + + return tp_len; +} + +static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) +{ + struct socket *sock; + struct sk_buff *skb; + struct net_device *dev; + __be16 proto; + int ifindex, err, reserve = 0; + void * ph; + struct sockaddr_ll *saddr=(struct sockaddr_ll *)msg->msg_name; + int tp_len, size_max; + unsigned char *addr; + int len_sum = 0; + int status = 0; + + sock = po->sk.sk_socket; + + mutex_lock(&po->pg_vec_lock); + + err = -EBUSY; + if (saddr == NULL) { + ifindex = po->ifindex; + proto = po->num; + addr = NULL; + } else { + err = -EINVAL; + if (msg->msg_namelen < sizeof(struct sockaddr_ll)) + goto out; + if (msg->msg_namelen < (saddr->sll_halen + + offsetof(struct sockaddr_ll, + sll_addr))) + goto out; + ifindex = saddr->sll_ifindex; + proto = saddr->sll_protocol; + addr = saddr->sll_addr; + } + + dev = dev_get_by_index(sock_net(&po->sk), ifindex); + err = -ENXIO; + if (unlikely(dev == NULL)) + goto out; + + reserve = dev->hard_header_len; + + err = -ENETDOWN; + if (unlikely(!(dev->flags & IFF_UP))) + goto out_put; + + size_max = po->tx_ring.frame_size + - sizeof(struct skb_shared_info) + - po->tp_hdrlen + - LL_ALLOCATED_SPACE(dev) + - sizeof(struct sockaddr_ll); + + if (size_max > dev->mtu + reserve) + size_max = dev->mtu + reserve; + + do { + ph = packet_current_frame(po, &po->tx_ring, + TP_STATUS_SEND_REQUEST); + + if (unlikely(ph == NULL)) { + schedule(); + continue; + } + + status = TP_STATUS_SEND_REQUEST; + skb = sock_alloc_send_skb(&po->sk, + LL_ALLOCATED_SPACE(dev) + + sizeof(struct sockaddr_ll), + 0, &err); + + if (unlikely(skb == NULL)) + goto out_status; + + tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto, + addr); + + if (unlikely(tp_len < 0)) { + if (po->tp_loss) { + __packet_set_status(po, ph, + TP_STATUS_AVAILABLE); + packet_increment_head(&po->tx_ring); + kfree_skb(skb); + continue; + } else { + status = TP_STATUS_WRONG_FORMAT; + err = tp_len; + goto out_status; + } + } + + skb->destructor = tpacket_destruct_skb; + __packet_set_status(po, ph, TP_STATUS_SENDING); + atomic_inc(&po->tx_ring.pending); + + status = TP_STATUS_SEND_REQUEST; + err = dev_queue_xmit(skb); + if (unlikely(err > 0 && (err = net_xmit_errno(err)) != 0)) + goto out_xmit; + packet_increment_head(&po->tx_ring); + len_sum += tp_len; + } + while (likely((ph != NULL) || ((!(msg->msg_flags & MSG_DONTWAIT)) + && (atomic_read(&po->tx_ring.pending)))) + ); + + err = len_sum; + goto out_put; + +out_xmit: + skb->destructor = sock_wfree; + atomic_dec(&po->tx_ring.pending); +out_status: + __packet_set_status(po, ph, status); + kfree_skb(skb); +out_put: + dev_put(dev); +out: + mutex_unlock(&po->pg_vec_lock); + return err; +} #endif - -static int packet_sendmsg(struct kiocb *iocb, struct socket *sock, +static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; @@ -854,6 +1153,19 @@ out: return err; } +static int packet_sendmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *msg, size_t len) +{ +#ifdef CONFIG_PACKET_MMAP + struct sock *sk = sock->sk; + struct packet_sock *po = pkt_sk(sk); + if (po->tx_ring.pg_vec) + return tpacket_snd(po, msg); + else +#endif + return packet_snd(sock, msg, len); +} + /* * Close a PACKET socket. This is fairly simple. We immediately go * to 'closed' state and remove our protocol entry in the device list. @@ -864,6 +1176,9 @@ static int packet_release(struct socket *sock) struct sock *sk = sock->sk; struct packet_sock *po; struct net *net; +#ifdef CONFIG_PACKET_MMAP + struct tpacket_req req; +#endif if (!sk) return 0; @@ -893,11 +1208,13 @@ static int packet_release(struct socket *sock) packet_flush_mclist(sk); #ifdef CONFIG_PACKET_MMAP - if (po->pg_vec) { - struct tpacket_req req; - memset(&req, 0, sizeof(req)); - packet_set_ring(sk, &req, 1); - } + memset(&req, 0, sizeof(req)); + + if (po->rx_ring.pg_vec) + packet_set_ring(sk, &req, 1, 0); + + if (po->tx_ring.pg_vec) + packet_set_ring(sk, &req, 1, 1); #endif /* @@ -1391,7 +1708,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (level != SOL_PACKET) return -ENOPROTOOPT; - switch(optname) { + switch (optname) { case PACKET_ADD_MEMBERSHIP: case PACKET_DROP_MEMBERSHIP: { @@ -1415,6 +1732,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv #ifdef CONFIG_PACKET_MMAP case PACKET_RX_RING: + case PACKET_TX_RING: { struct tpacket_req req; @@ -1422,7 +1740,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv return -EINVAL; if (copy_from_user(&req,optval,sizeof(req))) return -EFAULT; - return packet_set_ring(sk, &req, 0); + return packet_set_ring(sk, &req, 0, optname == PACKET_TX_RING); } case PACKET_COPY_THRESH: { @@ -1442,7 +1760,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->pg_vec) + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; @@ -1461,13 +1779,26 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->pg_vec) + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; po->tp_reserve = val; return 0; } + case PACKET_LOSS: + { + unsigned int val; + + if (optlen != sizeof(val)) + return -EINVAL; + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) + return -EBUSY; + if (copy_from_user(&val, optval, sizeof(val))) + return -EFAULT; + po->tp_loss = !!val; + return 0; + } #endif case PACKET_AUXDATA: { @@ -1517,7 +1848,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, if (len < 0) return -EINVAL; - switch(optname) { + switch (optname) { case PACKET_STATISTICS: if (len > sizeof(struct tpacket_stats)) len = sizeof(struct tpacket_stats); @@ -1573,6 +1904,12 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, val = po->tp_reserve; data = &val; break; + case PACKET_LOSS: + if (len > sizeof(unsigned int)) + len = sizeof(unsigned int); + val = po->tp_loss; + data = &val; + break; #endif default: return -ENOPROTOOPT; @@ -1643,7 +1980,7 @@ static int packet_ioctl(struct socket *sock, unsigned int cmd, { struct sock *sk = sock->sk; - switch(cmd) { + switch (cmd) { case SIOCOUTQ: { int amount = atomic_read(&sk->sk_wmem_alloc); @@ -1705,13 +2042,17 @@ static unsigned int packet_poll(struct file * file, struct socket *sock, unsigned int mask = datagram_poll(file, sock, wait); spin_lock_bh(&sk->sk_receive_queue.lock); - if (po->pg_vec) { - unsigned last = po->head ? po->head-1 : po->frame_max; - - if (packet_lookup_frame(po, last, TP_STATUS_USER)) + if (po->rx_ring.pg_vec) { + if (!packet_previous_frame(po, &po->rx_ring, TP_STATUS_KERNEL)) mask |= POLLIN | POLLRDNORM; } spin_unlock_bh(&sk->sk_receive_queue.lock); + spin_lock_bh(&sk->sk_write_queue.lock); + if (po->tx_ring.pg_vec) { + if (packet_current_frame(po, &po->tx_ring, TP_STATUS_AVAILABLE)) + mask |= POLLOUT | POLLWRNORM; + } + spin_unlock_bh(&sk->sk_write_queue.lock); return mask; } @@ -1788,21 +2129,33 @@ out_free_pgvec: goto out; } -static int packet_set_ring(struct sock *sk, struct tpacket_req *req, int closing) +static int packet_set_ring(struct sock *sk, struct tpacket_req *req, + int closing, int tx_ring) { char **pg_vec = NULL; struct packet_sock *po = pkt_sk(sk); int was_running, order = 0; + struct packet_ring_buffer *rb; + struct sk_buff_head *rb_queue; __be16 num; - int err = 0; + int err; + + rb = tx_ring ? &po->tx_ring : &po->rx_ring; + rb_queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue; + + err = -EBUSY; + if (!closing) { + if (atomic_read(&po->mapped)) + goto out; + if (atomic_read(&rb->pending)) + goto out; + } if (req->tp_block_nr) { - int i; - /* Sanity tests and some calculations */ - - if (unlikely(po->pg_vec)) - return -EBUSY; + err = -EBUSY; + if (unlikely(rb->pg_vec)) + goto out; switch (po->tp_version) { case TPACKET_V1: @@ -1813,42 +2166,35 @@ static int packet_set_ring(struct sock *sk, struct tpacket_req *req, int closing break; } + err = -EINVAL; if (unlikely((int)req->tp_block_size <= 0)) - return -EINVAL; + goto out; if (unlikely(req->tp_block_size & (PAGE_SIZE - 1))) - return -EINVAL; + goto out; if (unlikely(req->tp_frame_size < po->tp_hdrlen + - po->tp_reserve)) - return -EINVAL; + po->tp_reserve)) + goto out; if (unlikely(req->tp_frame_size & (TPACKET_ALIGNMENT - 1))) - return -EINVAL; + goto out; - po->frames_per_block = req->tp_block_size/req->tp_frame_size; - if (unlikely(po->frames_per_block <= 0)) - return -EINVAL; - if (unlikely((po->frames_per_block * req->tp_block_nr) != - req->tp_frame_nr)) - return -EINVAL; + rb->frames_per_block = req->tp_block_size/req->tp_frame_size; + if (unlikely(rb->frames_per_block <= 0)) + goto out; + if (unlikely((rb->frames_per_block * req->tp_block_nr) != + req->tp_frame_nr)) + goto out; err = -ENOMEM; order = get_order(req->tp_block_size); pg_vec = alloc_pg_vec(req, order); if (unlikely(!pg_vec)) goto out; - - for (i = 0; i < req->tp_block_nr; i++) { - void *ptr = pg_vec[i]; - int k; - - for (k = 0; k < po->frames_per_block; k++) { - __packet_set_status(po, ptr, TP_STATUS_KERNEL); - ptr += req->tp_frame_size; - } - } - /* Done */ - } else { + } + /* Done */ + else { + err = -EINVAL; if (unlikely(req->tp_frame_nr)) - return -EINVAL; + goto out; } lock_sock(sk); @@ -1872,23 +2218,24 @@ static int packet_set_ring(struct sock *sk, struct tpacket_req *req, int closing if (closing || atomic_read(&po->mapped) == 0) { err = 0; #define XC(a, b) ({ __typeof__ ((a)) __t; __t = (a); (a) = (b); __t; }) + spin_lock_bh(&rb_queue->lock); + pg_vec = XC(rb->pg_vec, pg_vec); + rb->frame_max = (req->tp_frame_nr - 1); + rb->head = 0; + rb->frame_size = req->tp_frame_size; + spin_unlock_bh(&rb_queue->lock); - spin_lock_bh(&sk->sk_receive_queue.lock); - pg_vec = XC(po->pg_vec, pg_vec); - po->frame_max = (req->tp_frame_nr - 1); - po->head = 0; - po->frame_size = req->tp_frame_size; - spin_unlock_bh(&sk->sk_receive_queue.lock); + order = XC(rb->pg_vec_order, order); + req->tp_block_nr = XC(rb->pg_vec_len, req->tp_block_nr); - order = XC(po->pg_vec_order, order); - req->tp_block_nr = XC(po->pg_vec_len, req->tp_block_nr); - - po->pg_vec_pages = req->tp_block_size/PAGE_SIZE; - po->prot_hook.func = po->pg_vec ? tpacket_rcv : packet_rcv; - skb_queue_purge(&sk->sk_receive_queue); + rb->pg_vec_pages = req->tp_block_size/PAGE_SIZE; + po->prot_hook.func = (po->rx_ring.pg_vec) ? + tpacket_rcv : packet_rcv; + skb_queue_purge(rb_queue); #undef XC if (atomic_read(&po->mapped)) - printk(KERN_DEBUG "packet_mmap: vma is busy: %d\n", atomic_read(&po->mapped)); + printk(KERN_DEBUG "packet_mmap: vma is busy: %d\n", + atomic_read(&po->mapped)); } mutex_unlock(&po->pg_vec_lock); @@ -1909,11 +2256,13 @@ out: return err; } -static int packet_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) +static int packet_mmap(struct file *file, struct socket *sock, + struct vm_area_struct *vma) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); - unsigned long size; + unsigned long size, expected_size; + struct packet_ring_buffer *rb; unsigned long start; int err = -EINVAL; int i; @@ -1921,26 +2270,43 @@ static int packet_mmap(struct file *file, struct socket *sock, struct vm_area_st if (vma->vm_pgoff) return -EINVAL; - size = vma->vm_end - vma->vm_start; - mutex_lock(&po->pg_vec_lock); - if (po->pg_vec == NULL) + + expected_size = 0; + for (rb = &po->rx_ring; rb <= &po->tx_ring; rb++) { + if (rb->pg_vec) { + expected_size += rb->pg_vec_len + * rb->pg_vec_pages + * PAGE_SIZE; + } + } + + if (expected_size == 0) goto out; - if (size != po->pg_vec_len*po->pg_vec_pages*PAGE_SIZE) + + size = vma->vm_end - vma->vm_start; + if (size != expected_size) goto out; start = vma->vm_start; - for (i = 0; i < po->pg_vec_len; i++) { - struct page *page = virt_to_page(po->pg_vec[i]); - int pg_num; + for (rb = &po->rx_ring; rb <= &po->tx_ring; rb++) { + if (rb->pg_vec == NULL) + continue; - for (pg_num = 0; pg_num < po->pg_vec_pages; pg_num++, page++) { - err = vm_insert_page(vma, start, page); - if (unlikely(err)) - goto out; - start += PAGE_SIZE; + for (i = 0; i < rb->pg_vec_len; i++) { + struct page *page = virt_to_page(rb->pg_vec[i]); + int pg_num; + + for (pg_num = 0; pg_num < rb->pg_vec_pages; + pg_num++,page++) { + err = vm_insert_page(vma, start, page); + if (unlikely(err)) + goto out; + start += PAGE_SIZE; + } } } + atomic_inc(&po->mapped); vma->vm_ops = &packet_mmap_ops; err = 0;