/* * tcpprobe - Observe the TCP flow with kprobes. * * The idea for this came from Werner Almesberger's umlsim * Copyright (C) 2004, Stephen Hemminger * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include #include #include #include #include #include #include #include #include #include #include MODULE_AUTHOR("Stephen Hemminger "); MODULE_DESCRIPTION("TCP cwnd snooper"); MODULE_LICENSE("GPL"); MODULE_VERSION("1.1"); static int port __read_mostly = 0; MODULE_PARM_DESC(port, "Port to match (0=all)"); module_param(port, int, 0); static unsigned int bufsize __read_mostly = 4096; MODULE_PARM_DESC(bufsize, "Log buffer size in packets (4096)"); module_param(bufsize, uint, 0); static int full __read_mostly; MODULE_PARM_DESC(full, "Full log (1=every ack packet received, 0=only cwnd changes)"); module_param(full, int, 0); static const char procname[] = "tcpprobe"; struct tcp_log { ktime_t tstamp; __be32 saddr, daddr; __be16 sport, dport; u16 length; u32 snd_nxt; u32 snd_una; u32 snd_wnd; u32 rcv_wnd; u32 snd_cwnd; u32 ssthresh; u32 srtt; }; static struct { spinlock_t lock; wait_queue_head_t wait; ktime_t start; u32 lastcwnd; unsigned long head, tail; struct tcp_log *log; } tcp_probe; static inline int tcp_probe_used(void) { return (tcp_probe.head - tcp_probe.tail) & (bufsize - 1); } static inline int tcp_probe_avail(void) { return bufsize - tcp_probe_used() - 1; } /* * Hook inserted to be called before each receive packet. * Note: arguments must match tcp_rcv_established()! */ static int jtcp_rcv_established(struct sock *sk, struct sk_buff *skb, struct tcphdr *th, unsigned int len) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_sock *inet = inet_sk(sk); /* Only update if port matches */ if ((port == 0 || ntohs(inet->inet_dport) == port || ntohs(inet->inet_sport) == port) && (full || tp->snd_cwnd != tcp_probe.lastcwnd)) { spin_lock(&tcp_probe.lock); /* If log fills, just silently drop */ if (tcp_probe_avail() > 1) { struct tcp_log *p = tcp_probe.log + tcp_probe.head; p->tstamp = ktime_get(); p->saddr = inet->inet_saddr; p->sport = inet->inet_sport; p->daddr = inet->inet_daddr; p->dport = inet->inet_dport; p->length = skb->len; p->snd_nxt = tp->snd_nxt; p->snd_una = tp->snd_una; p->snd_cwnd = tp->snd_cwnd; p->snd_wnd = tp->snd_wnd; p->rcv_wnd = tp->rcv_wnd; p->ssthresh = tcp_current_ssthresh(sk); p->srtt = tp->srtt >> 3; tcp_probe.head = (tcp_probe.head + 1) & (bufsize - 1); } tcp_probe.lastcwnd = tp->snd_cwnd; spin_unlock(&tcp_probe.lock); wake_up(&tcp_probe.wait); } jprobe_return(); return 0; } static struct jprobe tcp_jprobe = { .kp = { .symbol_name = "tcp_rcv_established", }, .entry = jtcp_rcv_established, }; static int tcpprobe_open(struct inode *inode, struct file *file) { /* Reset (empty) log */ spin_lock_bh(&tcp_probe.lock); tcp_probe.head = tcp_probe.tail = 0; tcp_probe.start = ktime_get(); spin_unlock_bh(&tcp_probe.lock); return 0; } static int tcpprobe_sprint(char *tbuf, int n) { const struct tcp_log *p = tcp_probe.log + tcp_probe.tail; struct timespec tv = ktime_to_timespec(ktime_sub(p->tstamp, tcp_probe.start)); return scnprintf(tbuf, n, "%lu.%09lu %pI4:%u %pI4:%u %d %#x %#x %u %u %u %u %u\n", (unsigned long) tv.tv_sec, (unsigned long) tv.tv_nsec, &p->saddr, ntohs(p->sport), &p->daddr, ntohs(p->dport), p->length, p->snd_nxt, p->snd_una, p->snd_cwnd, p->ssthresh, p->snd_wnd, p->srtt, p->rcv_wnd); } static ssize_t tcpprobe_read(struct file *file, char __user *buf, size_t len, loff_t *ppos) { int error = 0; size_t cnt = 0; if (!buf) return -EINVAL; while (cnt < len) { char tbuf[164]; int width; /* Wait for data in buffer */ error = wait_event_interruptible(tcp_probe.wait, tcp_probe_used() > 0); if (error) break; spin_lock_bh(&tcp_probe.lock); if (tcp_probe.head == tcp_probe.tail) { /* multiple readers race? */ spin_unlock_bh(&tcp_probe.lock); continue; } width = tcpprobe_sprint(tbuf, sizeof(tbuf)); if (cnt + width < len) tcp_probe.tail = (tcp_probe.tail + 1) & (bufsize - 1); spin_unlock_bh(&tcp_probe.lock); /* if record greater than space available return partial buffer (so far) */ if (cnt + width >= len) break; if (copy_to_user(buf + cnt, tbuf, width)) return -EFAULT; cnt += width; } return cnt == 0 ? error : cnt; } static const struct file_operations tcpprobe_fops = { .owner = THIS_MODULE, .open = tcpprobe_open, .read = tcpprobe_read, .llseek = noop_llseek, }; static __init int tcpprobe_init(void) { int ret = -ENOMEM; init_waitqueue_head(&tcp_probe.wait); spin_lock_init(&tcp_probe.lock); if (bufsize == 0) return -EINVAL; bufsize = roundup_pow_of_two(bufsize); tcp_probe.log = kcalloc(bufsize, sizeof(struct tcp_log), GFP_KERNEL); if (!tcp_probe.log) goto err0; if (!proc_create(procname, S_IRUSR, init_net.proc_net, &tcpprobe_fops)) goto err0; ret = register_jprobe(&tcp_jprobe); if (ret) goto err1; pr_info("probe registered (port=%d) bufsize=%u\n", port, bufsize); return 0; err1: remove_proc_entry(procname, init_net.proc_net); err0: kfree(tcp_probe.log); return ret; } module_init(tcpprobe_init); static __exit void tcpprobe_exit(void) { remove_proc_entry(procname, init_net.proc_net); unregister_jprobe(&tcp_jprobe); kfree(tcp_probe.log); } module_exit(tcpprobe_exit);