freebsd-skq/sys/kern
hiren 0d12306188 There are times when it would be really nice to have a record of the last few
packets and/or state transitions from each TCP socket. That would help with
narrowing down certain problems we see in the field that are hard to reproduce
without understanding the history of how we got into a certain state. This
change provides just that.

It saves copies of the last N packets in a list in the tcpcb. When the tcpcb is
destroyed, the list is freed. I thought this was likely to be more
performance-friendly than saving copies of the tcpcb. Plus, with the packets,
you should be able to reverse-engineer what happened to the tcpcb.

To enable the feature, you will need to compile a kernel with the TCPPCAP
option. Even then, the feature defaults to being deactivated. You can activate
it by setting a positive value for the number of captured packets. You can do
that on either a global basis or on a per-socket basis (via a setsockopt call).

There is no way to get the packets out of the kernel other than using kmem or
getting a coredump. I thought that would help some of the legal/privacy concerns
regarding such a feature. However, it should be possible to add a future effort
to export them in PCAP format.

I tested this at low scale, and found that there were no mbuf leaks and the peak
mbuf usage appeared to be unchanged with and without the feature.

The main performance concern I can envision is the number of mbufs that would be
used on systems with a large number of sockets. If you save five packets per
direction per socket and have 3,000 sockets, that will consume at least 30,000
mbufs just to keep these packets. I tried to reduce the concerns associated with
this by limiting the number of clusters (not mbufs) that could be used for this
feature. Again, in my testing, that appears to work correctly.

Differential Revision:	D3100
Submitted by:		Jonathan Looney <jlooney at juniper dot net>
Reviewed by:		gnn, hiren
2015-10-14 00:35:37 +00:00
..
bus_if.m Add a bus method to fetch the VM domain for the given device/bus. 2014-10-09 05:33:25 +00:00
capabilities.conf Add futimens and utimensat system calls. 2015-01-23 21:07:08 +00:00
clock_if.m
cpufreq_if.m
device_if.m Change the default method for device_quiesce() to return 0 instead of 2015-01-08 21:46:28 +00:00
genassym.sh genassym.sh: call nm(1) with NMFLAGS. 2015-08-14 22:57:13 +00:00
imgact_aout.c Implement lockless resource limits. 2015-06-10 10:48:12 +00:00
imgact_binmisc.c At the suggestion of jhb, replace atomic_set/clear calls with use of 2015-06-24 15:52:26 +00:00
imgact_elf32.c
imgact_elf64.c
imgact_elf.c Fix core corruption caused by race in note_procstat_vmmap 2015-10-06 18:07:00 +00:00
imgact_gzip.c Implement lockless resource limits. 2015-06-10 10:48:12 +00:00
imgact_shell.c Allow multiple image activators to run on the same execution by changing 2014-09-04 21:31:25 +00:00
inflate.c
init_main.c Remove now obsolete comment. 2015-08-28 20:06:58 +00:00
init_sysent.c Add an initial NUMA affinity/policy configuration for threads and processes. 2015-07-11 15:21:37 +00:00
kern_acct.c
kern_alq.c Prevent alq from panic when the invalid alq_file path specified. 2014-04-05 16:54:47 +00:00
kern_clock.c Initialize ticks so that it wraps 10 minutes after boot to increase the 2015-02-05 01:43:21 +00:00
kern_clocksource.c Fix typo in comment. 2015-07-20 09:37:42 +00:00
kern_condvar.c Revert r282971. It depends on condvar consumers not destroying condvars 2015-05-21 16:43:26 +00:00
kern_conf.c Fix for out of order device destruction notifications when using the 2015-03-22 13:11:56 +00:00
kern_cons.c CALLOUT_MPSAFE has lost its meaning since r141428, i.e., for more than ten 2015-05-22 17:05:21 +00:00
kern_context.c
kern_cpu.c Pull in r267961 and r267973 again. Fix for issues reported will follow. 2014-06-28 03:56:17 +00:00
kern_cpuset.c Un-static cpuset_which() - it's useful in other contexts, such as some 2015-06-26 04:14:05 +00:00
kern_ctf.c Don't specify a resid parameter if we're just going to ignore it. Instead, 2015-02-20 20:49:00 +00:00
kern_descrip.c fd: make rights a mandatory argument to fgetvp_rights 2015-09-07 20:05:56 +00:00
kern_dtrace.c Commit the rest of the changes that were intended to be part of r266826. 2014-05-29 01:42:22 +00:00
kern_dump.c Factor out duplicated code from dumpsys() on each architecture into generic 2015-01-07 01:01:39 +00:00
kern_environment.c Test if 'env' is NULL before doing memset() and strlen(), 2014-10-23 18:23:50 +00:00
kern_et.c Trivial change / forced-commit to document prior change that slipped in 2015-03-16 19:29:19 +00:00
kern_event.c kqueue: simplify kern_kqueue by not refing/unrefing creds too early 2015-09-23 12:45:08 +00:00
kern_exec.c Fix core corruption caused by race in note_procstat_vmmap 2015-10-06 18:07:00 +00:00
kern_exit.c Enforce the maxproc limitation before allocating struct proc, initial 2015-10-08 11:07:09 +00:00
kern_fail.c Use a regular sbuf + SYSCTL_OUT() rather than sbuf_new_for_sysctl() with 2015-03-16 19:18:45 +00:00
kern_ffclock.c The SYSCTL data pointers can come from userspace and must not be 2014-10-28 12:00:39 +00:00
kern_fork.c Enforce the maxproc limitation before allocating struct proc, initial 2015-10-08 11:07:09 +00:00
kern_gzio.c Move zlib.c from net to libkern. 2015-04-22 14:38:58 +00:00
kern_hhook.c
kern_idle.c
kern_intr.c The part of r285680 which removed release semantic for two stores to 2015-07-21 14:39:34 +00:00
kern_jail.c Add support to the jail framework to be able to mount linsysfs(5) and 2015-07-19 08:52:35 +00:00
kern_khelp.c
kern_kthread.c Limit rights on process descriptors. 2015-07-31 10:21:58 +00:00
kern_ktr.c Expand ktr_mask to be a 64-bit unsigned integer. 2015-05-22 11:09:41 +00:00
kern_ktrace.c Pull in r267961 and r267973 again. Fix for issues reported will follow. 2014-06-28 03:56:17 +00:00
kern_linker.c sysctl: switch sysctllock to a sleepable rmlock, take 2 2015-09-15 23:06:56 +00:00
kern_lock.c Don't modify curthread->td_locks unless INVARIANTS is enabled. 2015-08-02 00:03:08 +00:00
kern_lockf.c Improve style and fix a possible use-after-free case introduced in r268384 2015-01-10 06:48:35 +00:00
kern_lockstat.c Consistently use a reader/writer flag for lockstat probes in rwlock(9) and 2015-07-19 22:24:33 +00:00
kern_loginclass.c cred: add proc_set_cred helper 2015-03-16 00:10:03 +00:00
kern_malloc.c The vmem callback to reclaim kmem arena address space on low or 2015-05-09 20:08:36 +00:00
kern_mbuf.c Fix integer truncation bug in malloc(9) 2015-04-01 12:42:26 +00:00
kern_mib.c Huge cleanup of random(4) code. 2015-06-30 17:00:45 +00:00
kern_module.c Provide better debug message on kernel module name clash. 2015-10-10 09:21:55 +00:00
kern_mtxpool.c Garbage collect mtxpool_lockbuilder, the mutex pool historically used 2014-05-02 07:57:40 +00:00
kern_mutex.c Don't modify curthread->td_locks unless INVARIANTS is enabled. 2015-08-02 00:03:08 +00:00
kern_ntptime.c Use the monotonic (uptime) counter rather than time-of-day to measure elapsed 2015-07-12 18:38:17 +00:00
kern_numa.c Add an initial NUMA affinity/policy configuration for threads and processes. 2015-07-11 15:21:37 +00:00
kern_osd.c Pull in r267961 and r267973 again. Fix for issues reported will follow. 2014-06-28 03:56:17 +00:00
kern_physio.c Rewrite physio() to not allocate pbufs for unmapped I/O. 2015-04-21 10:55:53 +00:00
kern_pmc.c Pull in r267961 and r267973 again. Fix for issues reported will follow. 2014-06-28 03:56:17 +00:00
kern_poll.c When a kernel has DEVICE_POLLING turned on but no drivers have 2015-04-14 14:22:34 +00:00
kern_priv.c Pull in r267961 and r267973 again. Fix for issues reported will follow. 2014-06-28 03:56:17 +00:00
kern_proc.c Fix core corruption caused by race in note_procstat_vmmap 2015-10-06 18:07:00 +00:00
kern_procctl.c If process becomes reaper (procctl(PROC_REAP_ACQUIRE)) while already 2015-08-20 22:44:26 +00:00
kern_prot.c Get rid of lim_update_thread and cred_update_thread. 2015-07-16 14:30:11 +00:00
kern_racct.c save some bytes by using more concise SDT_PROBE<n> instead of SDT_PROBE 2015-09-28 12:14:16 +00:00
kern_rangelock.c
kern_rctl.c Add kern.racct.enable tunable and RACCT_DISABLED config option. 2015-04-29 10:23:02 +00:00
kern_resource.c Get rid of lim_update_thread and cred_update_thread. 2015-07-16 14:30:11 +00:00
kern_rmlock.c Threads holding a read lock of a sleepable rm lock are not permitted 2015-09-15 22:16:21 +00:00
kern_rwlock.c Don't modify curthread->td_locks unless INVARIANTS is enabled. 2015-08-02 00:03:08 +00:00
kern_sdt.c Print a backtrace if the SDT(9) stub gets called so that there's at least 2014-02-22 01:41:45 +00:00
kern_sema.c
kern_sharedpage.c Copy the fencing of the algorithm to do lock-less update and reading 2015-08-04 12:33:51 +00:00
kern_shutdown.c Disable suspend when we're shutting down. This solves the "tell FreeBSD 2015-10-01 10:52:26 +00:00
kern_sig.c save some bytes by using more concise SDT_PROBE<n> instead of SDT_PROBE 2015-09-28 12:14:16 +00:00
kern_switch.c Revert for r277213: 2015-01-22 11:12:42 +00:00
kern_sx.c Don't modify curthread->td_locks unless INVARIANTS is enabled. 2015-08-02 00:03:08 +00:00
kern_synch.c Remove several write-only variables, all reported by the gcc 4.9 2015-05-29 13:24:17 +00:00
kern_syscalls.c Implement lockless resource limits. 2015-06-10 10:48:12 +00:00
kern_sysctl.c sysctl: switch sysctllock to a sleepable rmlock, take 2 2015-09-15 23:06:56 +00:00
kern_tc.c Use per-cpu values for base and last in tc_cpu_ticks(). The values 2015-09-25 13:03:57 +00:00
kern_thr.c Add an API for easily creating userspace threads in kernelspace. 2015-07-20 10:20:04 +00:00
kern_thread.c Get rid of lim_update_thread and cred_update_thread. 2015-07-16 14:30:11 +00:00
kern_time.c Fix an off by one in ppsratecheck(). If you asked for N=1 you'd get one, 2015-01-11 20:48:29 +00:00
kern_timeout.c save some bytes by using more concise SDT_PROBE<n> instead of SDT_PROBE 2015-09-28 12:14:16 +00:00
kern_umtx.c Fix bad arithmetic in umtx_key_get() to compute object offset. 2015-08-04 06:01:13 +00:00
kern_uuid.c Fix a bug in be_uuid_dec(); it called le16dec() instead of be16dec(), 2014-02-13 22:24:36 +00:00
kern_xxx.c
ksched.c Use P1B_PRIO_MAX to designate max posix priority for the RR/FIFO 2015-08-30 18:02:57 +00:00
link_elf_obj.c Add support for weak symbols to the kernel linkers. It means that 2015-09-20 01:27:59 +00:00
link_elf.c Add support for weak symbols to the kernel linkers. It means that 2015-09-20 01:27:59 +00:00
linker_if.m
Make.tags.inc Remove AppleTalk support. 2014-03-14 06:29:43 +00:00
Makefile
makesyscalls.sh Import the CloudABI datatypes and create a system call table. 2015-07-09 07:20:15 +00:00
md4c.c
md5c.c
p1003_1b.c In preparation for switching linuxulator to the use the native 1:1 2015-05-24 14:44:06 +00:00
posix4_mib.c
sched_4bsd.c kgdb uses td_oncpu to determine if a thread is running and should use 2015-08-03 20:43:36 +00:00
sched_ule.c Summary: Add the interactivity equations to the header comment for our 2015-08-26 16:36:41 +00:00
serdev_if.m
stack_protector.c Use nitems() macro instead of __arraycount() 2015-06-16 20:19:00 +00:00
subr_acl_nfs4.c Expose an interface to determine if an ACE is inherited. 2015-09-04 00:14:20 +00:00
subr_acl_posix1e.c
subr_autoconf.c
subr_blist.c
subr_bufring.c
subr_bus_dma.c Add bus_dmamap_load_ma() function to load map with the array of 2013-10-27 21:39:16 +00:00
subr_bus.c Huge cleanup of random(4) code. 2015-06-30 17:00:45 +00:00
subr_busdma_bufalloc.c Fix integer truncation bug in malloc(9) 2015-04-01 12:42:26 +00:00
subr_capability.c Remove duplicated includes. 2014-06-26 13:57:44 +00:00
subr_clock.c For architectures where time_t is wide enough, in particular, 64bit 2014-12-12 09:37:18 +00:00
subr_counter.c Create two public UMA_ZONE_PCPU zones: 64 bit sized and pointer sized. 2014-02-10 19:59:46 +00:00
subr_devstat.c Fix multiple incorrect SYSCTL arguments in the kernel: 2014-10-21 07:31:21 +00:00
subr_disk.c
subr_dummy_vdso_tc.c Update the vdso timehands only via tc_windup(). 2015-01-20 03:54:30 +00:00
subr_eventhandler.c
subr_fattime.c Where appropriate, use the modern terms for the one true time base 2014-12-21 05:07:11 +00:00
subr_firmware.c Create a dedicated function for ensuring that cdir and rdir are populated. 2015-07-11 16:22:48 +00:00
subr_hash.c
subr_hints.c Add a new device control utility for new-bus devices called devctl. This 2015-02-06 16:09:01 +00:00
subr_kdb.c Fix multiple incorrect SYSCTL arguments in the kernel: 2014-10-21 07:31:21 +00:00
subr_kobj.c
subr_lock.c Add _NEW flag to mtx(9), sx(9), rmlock(9) and rwlock(9). 2014-12-13 21:00:10 +00:00
subr_log.c
subr_mbpool.c All mbuf external free functions never fail, so let them be void. 2014-07-11 13:58:48 +00:00
subr_mchain.c
subr_module.c preload_search_info: make sure mod is set 2015-08-21 15:57:57 +00:00
subr_msgbuf.c Pull in r267961 and r267973 again. Fix for issues reported will follow. 2014-06-28 03:56:17 +00:00
subr_param.c Ensure that maxproc does not exceed pid_max, at the time of boot. 2015-09-21 15:02:59 +00:00
subr_pcpu.c Create two public UMA_ZONE_PCPU zones: 64 bit sized and pointer sized. 2014-02-10 19:59:46 +00:00
subr_pctrie.c
subr_power.c
subr_prf.c Add support for reading MAM attributes to camcontrol(8) and libcam(3). 2015-06-09 21:39:38 +00:00
subr_prof.c The process spin lock currently has the following distinct uses: 2014-11-26 14:10:00 +00:00
subr_rman.c Nuke the never-used RF_TIMESHARE feature, reducing the complexity of the 2014-07-16 22:18:19 +00:00
subr_rtc.c
subr_sbuf.c Fail the sbuf if vsnprintf(3) fails. 2015-10-02 09:23:14 +00:00
subr_scanf.c
subr_sfbuf.c Move KASSERT into locked region. 2014-08-11 15:06:07 +00:00
subr_sglist.c Fix a couple of panics when detaching from a cxgbe/cxl interface that was 2015-01-26 16:26:28 +00:00
subr_sleepqueue.c Revert for r277213: 2015-01-22 11:12:42 +00:00
subr_smp.c The smp_rendezvous_cpus() function should ensure that all accesses 2015-07-21 22:56:46 +00:00
subr_stack.c
subr_syscall.c Fix various edge cases related to system call tracing. 2015-10-06 19:29:05 +00:00
subr_taskqueue.c MFuser/delphij/zfs-arc-rebase@r281754: 2015-05-26 01:40:33 +00:00
subr_terminal.c vt(4): Adjust the cursor position after changing the window size 2014-11-01 17:05:15 +00:00
subr_trap.c racct: perform a lockless check for p_throttled 2015-07-13 22:52:11 +00:00
subr_turnstile.c ddb: finish converting boolean values. 2015-05-21 15:16:18 +00:00
subr_uio.c Implement lockless resource limits. 2015-06-10 10:48:12 +00:00
subr_unit.c
subr_vmem.c CALLOUT_MPSAFE has lost its meaning since r141428, i.e., for more than ten 2015-05-22 17:05:21 +00:00
subr_witness.c o Revert the other functional half of r239864, i. e. the merge of r134227 2015-07-24 15:13:21 +00:00
sys_capability.c Introduce kern_cap_rights_limit(). 2015-08-11 08:43:50 +00:00
sys_generic.c Cover a race between doselwakeup() and selfdfree(). If doselwakeup() 2015-07-09 09:22:21 +00:00
sys_pipe.c Make pipes in CloudABI work. 2015-07-29 17:18:27 +00:00
sys_procdesc.c The si_status field of the siginfo_t, provided by the waitid(2) and 2015-07-18 09:02:50 +00:00
sys_process.c Include additional info in ptrace(2) KTR traces: 2015-10-05 21:36:53 +00:00
sys_socket.c In preparation of merging projects/sendfile, transform bare access to 2014-11-12 09:57:15 +00:00
syscalls.c Regenerate syscalls. 2015-07-11 15:22:11 +00:00
syscalls.master Regenerate syscalls. 2015-07-11 15:22:11 +00:00
systrace_args.c Regenerate syscalls. 2015-07-11 15:22:11 +00:00
sysv_ipc.c
sysv_msg.c Add kern.racct.enable tunable and RACCT_DISABLED config option. 2015-04-29 10:23:02 +00:00
sysv_sem.c Add kern.racct.enable tunable and RACCT_DISABLED config option. 2015-04-29 10:23:02 +00:00
sysv_shm.c Change the default setting of kern.ipc.shm_allow_removed from 0 to 1. 2015-10-10 09:29:47 +00:00
tty_compat.c
tty_info.c
tty_inq.c
tty_outq.c
tty_pts.c Implement lockless resource limits. 2015-06-10 10:48:12 +00:00
tty_tty.c tty: replace several curthread->td_proc with stored curproc 2015-07-06 18:53:56 +00:00
tty_ttydisc.c
tty.c filedesc: simplify fget_unlocked & friends 2015-02-17 23:54:06 +00:00
uipc_accf.c The accept filter code is not specific to the FreeBSD IPv4 network stack, 2014-07-26 19:27:34 +00:00
uipc_debug.c Fix sb_state constant names as used e.g. to display in DDB ``show sockbuf''. 2015-07-21 09:57:13 +00:00
uipc_domain.c CALLOUT_MPSAFE has lost its meaning since r141428, i.e., for more than ten 2015-05-22 17:05:21 +00:00
uipc_mbuf2.c Add const-qualifiers for source mbuf argument in m_dup(), m_copym(), 2015-08-08 15:50:46 +00:00
uipc_mbuf.c There are times when it would be really nice to have a record of the last few 2015-10-14 00:35:37 +00:00
uipc_mbufhash.c Reduce header pollution. 2015-03-17 14:16:50 +00:00
uipc_mqueue.c fd: remove filedesc argument from fdclose 2015-04-11 15:40:28 +00:00
uipc_sem.c Call ksem_get() with initialized 'rights'. 2015-07-23 23:18:03 +00:00
uipc_shm.c Add kern_shm_open(). 2015-08-01 07:21:14 +00:00
uipc_sockbuf.c Implement lockless resource limits. 2015-06-10 10:48:12 +00:00
uipc_socket.c Make shutdown() return ENOTCONN as required by POSIX, part deux. 2015-07-27 13:17:57 +00:00
uipc_syscalls.c Make shutdown() return ENOTCONN as required by POSIX, part deux. 2015-07-27 13:17:57 +00:00
uipc_usrreq.c fd: make the common case in filecaps_copy work lockless 2015-09-07 20:02:56 +00:00
vfs_acl.c Replace struct filedesc argument in getvnode with struct thread 2015-06-16 13:09:18 +00:00
vfs_aio.c Mutex memory is not zeroed, add MTX_NEW. 2015-07-06 14:09:00 +00:00
vfs_bio.c Perform a single batched update to the object's paging-in-progress count 2015-10-03 17:04:52 +00:00
vfs_cache.c save some bytes by using more concise SDT_PROBE<n> instead of SDT_PROBE 2015-09-28 12:14:16 +00:00
vfs_cluster.c Refactor unmapped buffer address handling. 2015-07-23 19:13:41 +00:00
vfs_default.c Ensure that vop_stdadvise() does not call getblk() on vnodes that have an 2015-10-01 16:34:53 +00:00
vfs_export.c After the changes in r274118 make NOIP kernels compile by hiding an 2014-11-06 12:19:39 +00:00
vfs_extattr.c Replace struct filedesc argument in getvnode with struct thread 2015-06-16 13:09:18 +00:00
vfs_hash.c Track changes to kern.maxvnodes and appropriately increase or decrease 2015-09-06 05:50:51 +00:00
vfs_init.c sysctl: switch sysctllock to a sleepable rmlock, take 2 2015-09-15 23:06:56 +00:00
vfs_lookup.c save some bytes by using more concise SDT_PROBE<n> instead of SDT_PROBE 2015-09-28 12:14:16 +00:00
vfs_mount.c Make vfs_unmountall() unmount /dev after /, not before. The only 2015-08-24 13:18:13 +00:00
vfs_mountroot.c Remove root_mount_wait(). It's not used anywhere. 2015-10-09 12:11:37 +00:00
vfs_subr.c Remove a check for a condition that is always false by a preceding KASSERT 2015-09-26 22:26:55 +00:00
vfs_syscalls.c Revert r288628 and instead fix a discrepancy between the posix_fadvise(2) 2015-10-03 22:27:14 +00:00
vfs_vnops.c Fix r283998 that broke mapin events for hwpmc. 2015-10-08 09:54:33 +00:00
vnode_if.src kevent(2): Note DOOMED vnodes with NOTE_REVOKE 2015-09-15 20:22:30 +00:00