litmus-rt.git - The LITMUS^RT kernel.

Branch	Commit message	Author	Age
archive/unc-master-3.0	P-FP: fix BUG_ON releated to priority inheritance	Bjoern Brandenburg	13 years
archived-2013.1	uncachedev: mmap memory that is not cached by CPUs	Glenn Elliott	12 years
archived-private-master	Merge branch 'wip-2.6.34' into old-private-master	Andrea Bastoni	15 years
archived-semi-part	Merge branch 'wip-semi-part' of ssh://cvs/cvs/proj/litmus/repo/litmus2010 int...	Andrea Bastoni	15 years
demo	Further refinements	Jonathan Herman	14 years
ecrts-pgm-final	Merge branch 'wip-ecrts14-pgm' of ssh://rtsrv.cs.unc.edu/home/litmus/litmus-r...	Glenn Elliott	12 years
ecrts14-pgm-final	Merge branch 'wip-ecrts14-pgm' of ssh://rtsrv.cs.unc.edu/home/litmus/litmus-r...	Glenn Elliott	12 years
gpusync-rtss12	Final GPUSync implementation.	Glenn Elliott	12 years
gpusync/staging	Rename IKGLP R2DGLP.	Glenn Elliott	12 years
linux-tip	Merge branch 'slab/urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/p...	Linus Torvalds	15 years
litmus2008-patch-series	add i386 feather-trace implementation	Bjoern B. Brandenburg	16 years
master	PSN-EDF: use inferred_sporadic_job_release_at	Bjoern Brandenburg	9 years
pgm	make it compile	Glenn Elliott	12 years
prop/litmus-signals	Infrastructure for Litmus signals.	Glenn Elliott	13 years
prop/robust-tie-break	Fixed bug in edf_higher_prio().	Glenn Elliott	13 years
staging	Fix tracepoint compilation error	Felipe Cerqueira	13 years
test	9/23/2016	Namhoon Kim	9 years
tracing-devel	Test kernel tracing events capabilities	Andrea Bastoni	16 years
v2.6.34-with-arm-patches	smsc911x: Add spinlocks around registers access	Catalin Marinas	15 years
v2015.1	Add ARM syscall def for get_current_budget	Bjoern Brandenburg	10 years
wip-2011.2-bbb	Litmus core: simplify np-section protocol	Bjoern B. Brandenburg	14 years
wip-2011.2-bbb-trace	Refactor sched_trace_log_message() -> debug_trace_log_message()	Andrea Bastoni	14 years
wip-2012.3-gpu	SOBLIV draining support for C-EDF.	Glenn Elliott	12 years
wip-2012.3-gpu-preport	pick up last C-RM file	Glenn Elliott	12 years
wip-2012.3-gpu-rtss13	Fix critical bug in GPU tracker.	Glenn Elliott	12 years
wip-2012.3-gpu-sobliv-budget-w-kshark	Proper sobliv draining and many bug fixes.	Glenn Elliott	12 years
wip-aedzl-final	Make it easier to compile AEDZL interfaces in liblitmus.	Glenn Elliott	15 years
wip-aedzl-revised	Add sched_trace data for Apative EDZL	Glenn Elliott	15 years
wip-arbit-deadline	Fix compilation bug.	Glenn Elliott	13 years
wip-aux-tasks	Description of refined aux task inheritance.	Glenn Elliott	13 years
wip-bbb	GSN-EDF & Core: improve debug TRACE'ing for NP sections	Bjoern B. Brandenburg	14 years
wip-bbb-prio-don	use correct timestamp	Bjoern B. Brandenburg	14 years
wip-better-break	Implement hash-based EDF tie-breaking.	Glenn Elliott	13 years
wip-binary-heap	Make C-EDF work with simplified binheap_delete	Glenn Elliott	13 years
wip-budget	Added support for choices in budget policy enforcement.	Glenn Elliott	15 years
wip-color	Summarize schedulability with final record	Jonathan Herman	13 years
wip-color-jlh	sched_color: Fixed two bugs causing crashing on experiment restart and a rare...	Jonathan Herman	13 years
wip-d10-hz1000	Enable HZ=1000 on District 10	Bjoern B. Brandenburg	15 years
wip-default-clustering	Feature: Make default C-EDF clustering compile-time configurable.	Glenn Elliott	15 years
wip-dissipation-jerickso	Update from 2.6.36 to 2.6.36.4	Jeremy Erickson	11 years
wip-dissipation2-jerickso	Update 2.6.36 to 2.6.36.4	Jeremy Erickson	11 years
wip-ecrts14-pgm	Merge branch 'wip-ecrts14-pgm' of ssh://rtsrv.cs.unc.edu/home/litmus/litmus-r...	Glenn Elliott	12 years
wip-edf-hsb	last tested version	Jonathan Herman	14 years
wip-edf-os	Lookup table EDF-os	Jeremy Erickson	12 years
wip-edf-tie-break	Merge branch 'wip-edf-tie-break' of ssh://rtsrv.cs.unc.edu/home/litmus/litmus...	Glenn Elliott	13 years
wip-edzl-critique	Use hr_timer's active checks instead of having own flag.	Glenn Elliott	15 years
wip-edzl-final	Implementation of the EDZL scheduler.	Glenn Elliott	15 years
wip-edzl-revised	Clean up comments.	Glenn Elliott	15 years
wip-events	Added support for tracing arbitrary actions.	Jonathan Herman	15 years
wip-extra-debug	DBG: add additional tracing	Bjoern B. Brandenburg	15 years
wip-fix-switch-jerickso	Attempt to fix race condition with plugin switching	Jeremy Erickson	15 years
wip-fix3	sched: show length of runqueue clock deactivation in /proc/sched_debug	Bjoern B. Brandenburg	15 years
wip-fmlp-dequeue	Improve FMLP queue management.	Glenn Elliott	14 years
wip-ft-irq-flag	Feather-Trace: keep track of interrupt-related interference.	Bjoern B. Brandenburg	14 years
wip-gpu-cleanup	Enable sched_trace log injection from userspace	Glenn Elliott	13 years
wip-gpu-interrupts	Remove option for threading of all softirqs.	Glenn Elliott	14 years
wip-gpu-rtas12	Generalized GPU cost predictors + EWMA. (untested)	Glenn Elliott	13 years
wip-gpu-rtss12	Final GPUSync implementation.	Glenn Elliott	13 years
wip-gpu-rtss12-srp	experimental changes to support GPUs under SRP	Glenn Elliott	13 years
wip-gpusync-merge	Cleanup priority tracking for budget enforcement.	Glenn Elliott	11 years
wip-ikglp	Move RSM and IKGLP imp. to own .c files	Glenn Elliott	13 years
wip-k-fmlp	Merge branch 'mpi-master' into wip-k-fmlp	Glenn Elliott	14 years
wip-kernel-coloring	Added recolor syscall	Namhoon Kim	7 years
wip-kernthreads	Kludge work-queue processing into klitirqd.	Glenn Elliott	15 years
wip-klmirqd-to-aux	Allow klmirqd threads to be given names.	Glenn Elliott	13 years
wip-kshark	Merge branch 'mpi-staging' into wip-kshark	Jonathan Herman	13 years
wip-litmus-3.2	Merge commit 'v3.2' into litmus-staging	Andrea Bastoni	13 years
wip-litmus2011.2	Cleanup: Coding conformance for affinity stuff.	Glenn Elliott	14 years
wip-litmus3.0-2011.2	Feather-Trace: keep track of interrupt-related interference.	Bjoern B. Brandenburg	14 years
wip-master-2.6.33-rt	Avoid deadlock when switching task policy to BACKGROUND (ugly)	Andrea Bastoni	15 years
wip-mc	Removed ARM-specific hacks which disabled less common mixed-criticality featu...	Jonathan Herman	12 years
wip-mc-bipasa	MC-EDF added	bipasa chattopadhyay	13 years
wip-mc-jerickso	Split C/D queues	Jeremy Erickson	15 years
wip-mc2-cache-slack	Manually patched mc^2 related code	Ming Yang	10 years
wip-mcrit-mac	cosmetic	Mac Mollison	15 years
wip-merge-3.0	Prevent Linux to send IPI and queue tasks on remote CPUs.	Andrea Bastoni	14 years
wip-merge-v3.0	Prevent Linux to send IPI and queue tasks on remote CPUs.	Andrea Bastoni	14 years
wip-migration-affinity	NULL affinity dereference in C-EDF.	Glenn Elliott	14 years
wip-mmap-uncache	share branch with others	Glenn Elliott	13 years
wip-modechange	RTSS 2017 submission	Namhoon Kim	8 years
wip-nested-locking	Appears to be working.	Bryan Ward	12 years
wip-omlp-gedf	First implementation of G-OMLP.	Glenn Elliott	15 years
wip-pai	Some cleanup of PAI	Glenn Elliott	14 years
wip-percore-lib	9/21/2016	Namhoon Kim	9 years
wip-performance	CONFIG_DONT_PREEMPT_ON_TIE: Don't preeempt a scheduled task on priority tie.	Glenn Elliott	14 years
wip-pgm	Add PGM support to C-FL	Glenn Elliott	12 years
wip-pgm-split	First draft of C-FL-split	Namhoon Kim	12 years
wip-pm-ovd	Add preemption-and-migration overhead tracing support	Andrea Bastoni	15 years
wip-prio-inh	P-EDF updated to use the generic pi framework.	Glenn Elliott	15 years
wip-prioq-dgl	BUG FIX: Support DGLs with PRIOQ_MUTEX	Glenn Elliott	13 years
wip-refactored-gedf	Generalizd architecture for GEDF-style scheduelrs to reduce code redundancy.	Glenn Elliott	15 years
wip-release-master-fix	bugfix: release master CPU must signal task was picked	Bjoern B. Brandenburg	14 years
wip-robust-tie-break	EDF priority tie-breaks.	Glenn Elliott	13 years
wip-rt-kshark	Move task time accounting into the complete_job method.	Jonathan Herman	13 years
wip-rtas12-pgm	Scheduling of PGM jobs.	Glenn Elliott	13 years
wip-semi-part	Fix compile error with newer GCC	Jeremy Erickson	12 years
wip-semi-part-edfos-jerickso	Use initial CPU set by client	Jeremy Erickson	12 years
wip-shared-lib	TODO: Fix condition checks in replicate_page_move_mapping()	Namhoon Kim	9 years
wip-shared-lib2	RTAS 2017 Submission ver.	Namhoon Kim	9 years
wip-shared-mem	Initial commit for shared library	Namhoon Kim	9 years
wip-splitting-jerickso	Fix release behavior	Jeremy Erickson	13 years
wip-splitting-omlp-jerickso	Bjoern's Dissertation Code with Priority Donation	Jeremy Erickson	13 years
wip-stage-binheap	An efficient binary heap implementation.	Glenn Elliott	13 years
wip-sun-port	Dynamic memory allocation and clean exit for FeatherTrace	Christopher Kenna	15 years
wip-timer-trace	bugfix: C-EDF, clear scheduled field of the correct CPU upon task_exit	Andrea Bastoni	15 years
wip-tracepoints	Add kernel-style events for sched_trace_XXX() functions	Andrea Bastoni	14 years

Tag	Download	Author	Age
2015.1	commit 8e51b37822...	Bjoern Brandenburg	10 years
2013.1	commit bcaacec1ca...	Glenn Elliott	12 years
2012.3	commit c158b5fbe4...	Jonathan Herman	13 years
2012.2	commit b53c479a0f...	Glenn Elliott	13 years
2012.1	commit 83b11ea1c6...	Bjoern B. Brandenburg	14 years
rtas12-mc-beta-exp	commit 8e236ee20f...	Christopher Kenna	14 years
2011.1	commit d11808b5c6...	Christopher Kenna	15 years
v2.6.37-rc4	commit e8a7e48bb2...	Linus Torvalds	15 years
v2.6.37-rc3	commit 3561d43fd2...	Linus Torvalds	15 years
v2.6.37-rc2	commit e53beacd23...	Linus Torvalds	15 years
v2.6.37-rc1	commit c8ddb2713c...	Linus Torvalds	15 years
v2.6.36	commit f6f94e2ab1...	Linus Torvalds	15 years
2010.2	commit 5c5456402d...	Bjoern B. Brandenburg	15 years
v2.6.36-rc8	commit cd07202cc8...	Linus Torvalds	15 years
v2.6.36-rc7	commit cb655d0f3d...	Linus Torvalds	15 years
v2.6.36-rc6	commit 899611ee7d...	Linus Torvalds	15 years
v2.6.36-rc5	commit b30a3f6257...	Linus Torvalds	15 years
v2.6.36-rc4	commit 49553c2ef8...	Linus Torvalds	15 years
v2.6.36-rc3	commit 2bfc96a127...	Linus Torvalds	15 years
v2.6.36-rc2	commit 76be97c1fc...	Linus Torvalds	15 years
v2.6.36-rc1	commit da5cabf80e...	Linus Torvalds	15 years
v2.6.35	commit 9fe6206f40...	Linus Torvalds	15 years
v2.6.35-rc6	commit b37fa16e78...	Linus Torvalds	15 years
v2.6.35-rc5	commit 1c5474a65b...	Linus Torvalds	15 years
v2.6.35-rc4	commit 815c4163b6...	Linus Torvalds	15 years
v2.6.35-rc3	commit 7e27d6e778...	Linus Torvalds	15 years
v2.6.35-rc2	commit e44a21b726...	Linus Torvalds	15 years
v2.6.35-rc1	commit 67a3e12b05...	Linus Torvalds	15 years
2010.1	commit 7c1ff4c544...	Andrea Bastoni	15 years
v2.6.34	commit e40152ee1e...	Linus Torvalds	15 years
v2.6.33.4	commit 4640b4e7d9...	Greg Kroah-Hartman	15 years
v2.6.34-rc7	commit b57f95a382...	Linus Torvalds	15 years
v2.6.34-rc6	commit 66f41d4c5c...	Linus Torvalds	15 years
v2.6.33.3	commit 3e7ad8ed97...	Greg Kroah-Hartman	15 years
v2.6.34-rc5	commit 01bf0b6457...	Linus Torvalds	15 years
v2.6.34-rc4	commit 0d0fb0f9c5...	Linus Torvalds	15 years
v2.6.33.2	commit 19f00f070c...	Greg Kroah-Hartman	15 years
v2.6.34-rc3	commit 2eaa9cfdf3...	Linus Torvalds	15 years
v2.6.34-rc2	commit 220bf991b0...	Linus Torvalds	15 years
v2.6.33.1	commit dbdafe5ccf...	Greg Kroah-Hartman	16 years
v2.6.34-rc1	commit 57d54889cd...	Linus Torvalds	16 years
v2.6.33	commit 60b341b778...	Linus Torvalds	16 years
v2.6.33-rc8	commit 724e6d3fe8...	Linus Torvalds	16 years
v2.6.33-rc7	commit 29275254ca...	Linus Torvalds	16 years
v2.6.33-rc6	commit abe94c756c...	Linus Torvalds	16 years
v2.6.33-rc5	commit 92dcffb916...	Linus Torvalds	16 years
v2.6.33-rc4	commit 7284ce6c9f...	Linus Torvalds	16 years
v2.6.33-rc3	commit 74d2e4f8d7...	Linus Torvalds	16 years
v2.6.33-rc2	commit 6b7b284958...	Linus Torvalds	16 years
v2.6.33-rc1	commit 55639353a0...	Linus Torvalds	16 years
v2.6.32	commit 22763c5cf3...	Linus Torvalds	16 years
v2.6.32-rc8	commit 648f4e3e50...	Linus Torvalds	16 years
v2.6.32-rc7	commit 156171c71a...	Linus Torvalds	16 years
v2.6.32-rc6	commit b419148e56...	Linus Torvalds	16 years
v2.6.32-rc5	commit 012abeea66...	Linus Torvalds	16 years
v2.6.32-rc4	commit 161291396e...	Linus Torvalds	16 years
v2.6.32-rc3	commit 374576a8b6...	Linus Torvalds	16 years
v2.6.32-rc1	commit 17d857be64...	Linus Torvalds	16 years
v2.6.32-rc2	commit 17d857be64...	Linus Torvalds	16 years
v2.6.31	commit 74fca6a428...	Linus Torvalds	16 years
v2.6.31-rc9	commit e07cccf404...	Linus Torvalds	16 years
v2.6.31-rc8	commit 326ba5010a...	Linus Torvalds	16 years
v2.6.31-rc7	commit 422bef879e...	Linus Torvalds	16 years
v2.6.31-rc6	commit 64f1607ffb...	Linus Torvalds	16 years
v2.6.31-rc5	commit ed680c4ad4...	Linus Torvalds	16 years
v2.6.31-rc4	commit 4be3bd7849...	Linus Torvalds	16 years
v2.6.31-rc3	commit 6847e154e3...	Linus Torvalds	16 years
v2.6.31-rc2	commit 8e4a718ff3...	Linus Torvalds	16 years
v2.6.31-rc1	commit 28d0325ce6...	Linus Torvalds	16 years
v2.6.30	commit 07a2039b8e...	Linus Torvalds	16 years
v2.6.30-rc8	commit 9fa7eb283c...	Linus Torvalds	16 years
v2.6.30-rc7	commit 59a3759d0f...	Linus Torvalds	16 years
v2.6.30-rc6	commit 1406de8e11...	Linus Torvalds	16 years
v2.6.30-rc5	commit 091bf7624d...	Linus Torvalds	16 years
v2.6.30-rc4	commit 091438dd56...	Linus Torvalds	16 years
v2.6.30-rc3	commit 0910697403...	Linus Torvalds	16 years
v2.6.30-rc2	commit 0882e8dd3a...	Linus Torvalds	16 years
v2.6.30-rc1	commit 577c9c456f...	Linus Torvalds	16 years
v2.6.29	commit 8e0ee43bc2...	Linus Torvalds	16 years
v2.6.29-rc8	commit 041b62374c...	Linus Torvalds	17 years
v2.6.29-rc7	commit fec6c6fec3...	Linus Torvalds	17 years
v2.6.29-rc6	commit 20f4d6c3a2...	Linus Torvalds	17 years
v2.6.29-rc5	commit d2f8d7ee1a...	Linus Torvalds	17 years
v2.6.29-rc4	commit 8e4921515c...	Linus Torvalds	17 years
v2.6.29-rc3	commit 18e352e4a7...	Linus Torvalds	17 years
v2.6.29-rc2	commit 1de9e8e70f...	Linus Torvalds	17 years
v2.6.29-rc1	commit c59765042f...	Linus Torvalds	17 years
v2.6.28	commit 4a6908a3a0...	Linus Torvalds	17 years
v2.6.28-rc9	commit 929096fe9f...	Linus Torvalds	17 years
v2.6.28-rc8	commit 8b1fae4e42...	Linus Torvalds	17 years
v2.6.28-rc7	commit 061e41fdb5...	Linus Torvalds	17 years
v2.6.28-rc6	commit 13d428afc0...	Linus Torvalds	17 years
v2.6.28-rc5	commit 9bf1a2445f...	Linus Torvalds	17 years
v2.6.28-rc4	commit f7160c7573...	Linus Torvalds	17 years
v2.6.28-rc3	commit 45beca08dd...	Linus Torvalds	17 years
v2.6.28-rc2	commit 0173a3265b...	Linus Torvalds	17 years
v2.6.28-rc1	commit 57f8f7b60d...	Linus Torvalds	17 years
v2.6.27	commit 3fa8749e58...	Linus Torvalds	17 years
v2.6.27-rc9	commit 4330ed8ed4...	Linus Torvalds	17 years
v2.6.27-rc8	commit 94aca1dac6...	Linus Torvalds	17 years
v2.6.27-rc7	commit 72d31053f6...	Linus Torvalds	17 years
v2.6.27-rc6	commit adee14b2e1...	Linus Torvalds	17 years
v2.6.27-rc5	commit 24342c34a0...	Linus Torvalds	17 years
v2.6.27-rc4	commit 6a55617ed5...	Linus Torvalds	17 years
v2.6.27-rc3	commit 30a2f3c60a...	Linus Torvalds	17 years
v2.6.27-rc2	commit 0967d61ea0...	Linus Torvalds	17 years
v2.6.27-rc1	commit 6e86841d05...	Linus Torvalds	17 years
v2.6.26	commit bce7f793da...	Linus Torvalds	17 years
v2.6.26-rc9	commit b7279469d6...	Linus Torvalds	17 years
v2.6.26-rc8	commit 543cf4cb3f...	Linus Torvalds	17 years
v2.6.26-rc7	commit d70ac829b7...	Linus Torvalds	17 years
v2.6.26-rc6	commit 5dd34572ad...	Linus Torvalds	17 years
v2.6.26-rc5	commit 53c8ba9540...	Linus Torvalds	17 years
v2.6.26-rc4	commit e490517a03...	Linus Torvalds	17 years
v2.6.26-rc3	commit b8291ad07a...	Linus Torvalds	17 years
v2.6.26-rc2	commit 492c2e476e...	Linus Torvalds	17 years
v2.6.26-rc1	commit 2ddcca36c8...	Linus Torvalds	17 years
v2.6.25	commit 4b119e21d0...	Linus Torvalds	17 years
v2.6.25-rc9	commit 120dd64cac...	Linus Torvalds	17 years
v2.6.25-rc8	commit 0e81a8ae37...	Linus Torvalds	17 years
v2.6.25-rc7	commit 05dda977f2...	Linus Torvalds	17 years
v2.6.25-rc6	commit a978b30af3...	Linus Torvalds	18 years
v2.6.25-rc5	commit cdeeeae056...	Linus Torvalds	18 years
v2.6.25-rc4	commit 29e8c3c304...	Linus Torvalds	18 years
v2.6.25-rc3	commit bfa274e243...	Linus Torvalds	18 years
v2.6.25-rc2	commit 101142c37b...	Linus Torvalds	18 years
v2.6.25-rc1	commit 19af35546d...	Linus Torvalds	18 years
v2.6.24	commit 49914084e7...	Linus Torvalds	18 years
v2.6.24-rc8	commit cbd9c88369...	Linus Torvalds	18 years
v2.6.24-rc7	commit 3ce5445046...	Linus Torvalds	18 years
v2.6.24-rc6	commit ea67db4cdb...	Linus Torvalds	18 years
v2.6.24-rc5	commit 82d29bf6dc...	Linus Torvalds	18 years
v2.6.24-rc4	commit 09b56adc98...	Linus Torvalds	18 years
v2.6.24-rc3	commit d9f8bcbf67...	Linus Torvalds	18 years
v2.6.24-rc2	commit dbeeb816e8...	Linus Torvalds	18 years
v2.6.24-rc1	commit c9927c2bf4...	Linus Torvalds	18 years
v2.6.23	commit bbf25010f1...	Linus Torvalds	18 years
v2.6.23-rc9	commit 3146b39c18...	Linus Torvalds	18 years
v2.6.23-rc8	commit 4942de4a0e...	Linus Torvalds	18 years
v2.6.23-rc7	commit 81cfe79b9c...	Linus Torvalds	18 years
v2.6.23-rc6	commit 0d4cbb5e7f...	Linus Torvalds	18 years
v2.6.23-rc5	commit 40ffbfad6b...	Linus Torvalds	18 years
v2.6.23-rc4	commit b07d68b5ca...	Linus Torvalds	18 years
v2.6.23-rc3	commit 39d3520c92...	Linus Torvalds	18 years
v2.6.23-rc2	commit d4ac2477fa...	Linus Torvalds	18 years
v2.6.23-rc1	commit f695baf2df...	Linus Torvalds	18 years
v2.6.22	commit 7dcca30a32...	Linus Torvalds	18 years
v2.6.22-rc7	commit a38d6181ff...	Linus Torvalds	18 years
v2.6.22-rc6	commit 189548642c...	Linus Torvalds	18 years
v2.6.22-rc5	commit 188e1f81ba...	Linus Torvalds	18 years
v2.6.22-rc4	commit 5ecd3100e6...	Linus Torvalds	18 years
v2.6.22-rc3	commit c420bc9f09...	Linus Torvalds	18 years
v2.6.22-rc2	commit 55b637c6a0...	Linus Torvalds	18 years
v2.6.22-rc1	commit 39403865d2...	Linus Torvalds	18 years
v2.6.21	commit de46c33745...	Linus Torvalds	18 years
v2.6.21-rc7	commit 94a05509a9...	Linus Torvalds	18 years
v2.6.21-rc6	commit a21bd69e15...	Linus Torvalds	18 years
v2.6.21-rc5	commit e0f2e3a06b...	Linus Torvalds	18 years
v2.6.21-rc4	commit db98e0b434...	Linus Torvalds	19 years
v2.6.21-rc3	commit 08e15e81a4...	Linus Torvalds	19 years
v2.6.21-rc2	commit 606135a308...	Linus Torvalds	19 years
v2.6.21-rc1	commit c8f71b01a5...	Linus Torvalds	19 years
v2.6.20	commit 62d0cfcb27...	Linus Torvalds	19 years
v2.6.20-rc7	commit f56df2f4db...	Linus Torvalds	19 years
v2.6.20-rc6	commit 99abfeafb5...	Linus Torvalds	19 years
v2.6.20-rc5	commit a8b3485287...	Linus Torvalds	19 years
v2.6.20-rc4	commit bf81b46482...	Linus Torvalds	19 years
v2.6.20-rc3	commit 669df1b478...	Linus Torvalds	19 years
v2.6.20-rc2	commit 3bf8ba38f3...	Linus Torvalds	19 years
v2.6.20-rc1	commit cc016448b0...	Linus Torvalds	19 years
v2.6.19	commit 0215ffb08c...	Linus Torvalds	19 years
v2.6.19-rc6	commit 44597f65f6...	Linus Torvalds	19 years
v2.6.19-rc5	commit 80c2188127...	Linus Torvalds	19 years
v2.6.19-rc4	commit ae99a78af3...	Linus Torvalds	19 years
v2.6.19-rc3	commit 7059abedd2...	Linus Torvalds	19 years
v2.6.19-rc2	commit b4bd8c6643...	Linus Torvalds	19 years
v2.6.19-rc1	commit d223a60106...	Linus Torvalds	19 years
v2.6.18	commit e478bec0ba...	Linus Torvalds	19 years
v2.6.18-rc7	commit 95064a75eb...	Linus Torvalds	19 years
v2.6.18-rc6	commit c336923b66...	Linus Torvalds	19 years
v2.6.18-rc5	commit 60d4684068...	Linus Torvalds	19 years
v2.6.18-rc4	commit 9f737633e6...	Linus Torvalds	19 years
v2.6.18-rc3	commit b6ff50833a...	Linus Torvalds	19 years
v2.6.18-rc2	commit 82d6897fef...	Linus Torvalds	19 years
v2.6.18-rc1	commit 120bda20c6...	Linus Torvalds	19 years
v2.6.17	commit 427abfa28a...	Linus Torvalds	19 years
v2.6.17-rc6	commit 1def630a6a...	Linus Torvalds	19 years
v2.6.17-rc5	commit a8bd60705a...	Linus Torvalds	19 years
v2.6.17-rc4	commit d8c3291c73...	Linus Torvalds	19 years
v2.6.17-rc3	commit 2be4d50295...	Linus Torvalds	19 years
v2.6.17-rc2	commit 8bbde0e6d5...	Linus Torvalds	19 years
v2.6.17-rc1	commit 6246b6128b...	Linus Torvalds	19 years
v2.6.16	commit 7705a8792b...	Linus Torvalds	20 years
v2.6.16-rc6	commit 535744878e...	Linus Torvalds	20 years
v2.6.16-rc5	commit b9a33cebac...	Linus Torvalds	20 years
v2.6.16-rc4	commit bd71c2b174...	Linus Torvalds	20 years
v2.6.16-rc3	commit e9bb4c9929...	Linus Torvalds	20 years
v2.6.16-rc2	commit 826eeb53a6...	Linus Torvalds	20 years
v2.6.16-rc1	commit 2664b25051...	Linus Torvalds	20 years
v2.6.15	commit 88026842b0...	Linus Torvalds	20 years
v2.6.15-rc7	commit f89f5948fc...	Linus Torvalds	20 years
v2.6.15-rc6	commit df7addbb45...	Linus Torvalds	20 years
v2.6.15-rc5	commit 436b0f76f2...	Linus Torvalds	20 years
v2.6.15-rc4	commit 5666c0947e...	Linus Torvalds	20 years
v2.6.15-rc3	commit 624f54be20...	Linus Torvalds	20 years
v2.6.15-rc2	commit 3bedff1d73...	Linus Torvalds	20 years
v2.6.15-rc1	commit cd52d1ee9a...	Linus Torvalds	20 years
v2.6.14	commit 741b2252a5...	Linus Torvalds	20 years
v2.6.14-rc5	commit 93918e9afc...	Linus Torvalds	20 years
v2.6.14-rc4	commit 907a426179...	Linus Torvalds	20 years
v2.6.14-rc3	commit 1c9426e8a5...	Linus Torvalds	20 years
v2.6.14-rc2	commit 676d55ae30...	Linus Torvalds	20 years
v2.6.14-rc1	commit 2f4ba45a75...	Linus Torvalds	20 years
v2.6.13	commit 02b3e4e2d7...	Linus Torvalds	20 years
v2.6.13-rc7	commit 0572e3da3f...	Linus Torvalds	20 years
v2.6.13-rc6	commit 6fc32179de...	Linus Torvalds	20 years
v2.6.13-rc5	commit 9a351e30d7...	Linus Torvalds	20 years
v2.6.13-rc4	commit 6395352334...	Linus Torvalds	20 years
v2.6.11	tree c39ae07f39...
v2.6.11-tree	tree c39ae07f39...
v2.6.12	commit 9ee1c939d1...
v2.6.12-rc2	commit 1da177e4c3...
v2.6.12-rc3	commit a2755a80f4...
v2.6.12-rc4	commit 88d7bd8cb9...
v2.6.12-rc5	commit 2a24ab628a...
v2.6.12-rc6	commit 7cef5677ef...
v2.6.13-rc1	commit 4c91aedb75...
v2.6.13-rc2	commit a18bcb7450...
v2.6.13-rc3	commit c32511e271...

/* Connection state tracking for netfilter. This is separated from, but required by, the NAT layer; it can also be used by an iptables extension. */ /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> * (C) 2003,2004 USAGI/WIDE Project <http://www.linux-ipv6.org> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ #include <linux/types.h> #include <linux/netfilter.h> #include <linux/module.h> #include <linux/sched.h> #include <linux/skbuff.h> #include <linux/proc_fs.h> #include <linux/vmalloc.h> #include <linux/stddef.h> #include <linux/slab.h> #include <linux/random.h> #include <linux/jhash.h> #include <linux/err.h> #include <linux/percpu.h> #include <linux/moduleparam.h> #include <linux/notifier.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/socket.h> #include <linux/mm.h> #include <linux/nsproxy.h> #include <linux/rculist_nulls.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_l3proto.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_expect.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_extend.h> #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_timestamp.h> #include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_nat_core.h> #define NF_CONNTRACK_VERSION "0.5.0" int (*nfnetlink_parse_nat_setup_hook)(struct nf_conn *ct, enum nf_nat_manip_type manip, const struct nlattr *attr) __read_mostly; EXPORT_SYMBOL_GPL(nfnetlink_parse_nat_setup_hook); DEFINE_SPINLOCK(nf_conntrack_lock); EXPORT_SYMBOL_GPL(nf_conntrack_lock); unsigned int nf_conntrack_htable_size __read_mostly; EXPORT_SYMBOL_GPL(nf_conntrack_htable_size); unsigned int nf_conntrack_max __read_mostly; EXPORT_SYMBOL_GPL(nf_conntrack_max); DEFINE_PER_CPU(struct nf_conn, nf_conntrack_untracked); EXPORT_PER_CPU_SYMBOL(nf_conntrack_untracked); unsigned int nf_conntrack_hash_rnd __read_mostly; static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple, u16 zone) { unsigned int n; /* The direction must be ignored, so we hash everything up to the * destination ports (which is a multiple of 4) and treat the last * three bytes manually. */ n = (sizeof(tuple->src) + sizeof(tuple->dst.u3)) / sizeof(u32); return jhash2((u32 *)tuple, n, zone ^ nf_conntrack_hash_rnd ^ (((__force __u16)tuple->dst.u.all << 16) | tuple->dst.protonum)); } static u32 __hash_bucket(u32 hash, unsigned int size) { return ((u64)hash * size) >> 32; } static u32 hash_bucket(u32 hash, const struct net *net) { return __hash_bucket(hash, net->ct.htable_size); } static u_int32_t __hash_conntrack(const struct nf_conntrack_tuple *tuple, u16 zone, unsigned int size) { return __hash_bucket(hash_conntrack_raw(tuple, zone), size); } static inline u_int32_t hash_conntrack(const struct net *net, u16 zone, const struct nf_conntrack_tuple *tuple) { return __hash_conntrack(tuple, zone, net->ct.htable_size); } bool nf_ct_get_tuple(const struct sk_buff *skb, unsigned int nhoff, unsigned int dataoff, u_int16_t l3num, u_int8_t protonum, struct nf_conntrack_tuple *tuple, const struct nf_conntrack_l3proto *l3proto, const struct nf_conntrack_l4proto *l4proto) { memset(tuple, 0, sizeof(*tuple)); tuple->src.l3num = l3num; if (l3proto->pkt_to_tuple(skb, nhoff, tuple) == 0) return false; tuple->dst.protonum = protonum; tuple->dst.dir = IP_CT_DIR_ORIGINAL; return l4proto->pkt_to_tuple(skb, dataoff, tuple); } EXPORT_SYMBOL_GPL(nf_ct_get_tuple); bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff, u_int16_t l3num, struct nf_conntrack_tuple *tuple) { struct nf_conntrack_l3proto *l3proto; struct nf_conntrack_l4proto *l4proto; unsigned int protoff; u_int8_t protonum; int ret; rcu_read_lock(); l3proto = __nf_ct_l3proto_find(l3num); ret = l3proto->get_l4proto(skb, nhoff, &protoff, &protonum); if (ret != NF_ACCEPT) { rcu_read_unlock(); return false; } l4proto = __nf_ct_l4proto_find(l3num, protonum); ret = nf_ct_get_tuple(skb, nhoff, protoff, l3num, protonum, tuple, l3proto, l4proto); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(nf_ct_get_tuplepr); bool nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, const struct nf_conntrack_tuple *orig, const struct nf_conntrack_l3proto *l3proto, const struct nf_conntrack_l4proto *l4proto) { memset(inverse, 0, sizeof(*inverse)); inverse->src.l3num = orig->src.l3num; if (l3proto->invert_tuple(inverse, orig) == 0) return false; inverse->dst.dir = !orig->dst.dir; inverse->dst.protonum = orig->dst.protonum; return l4proto->invert_tuple(inverse, orig); } EXPORT_SYMBOL_GPL(nf_ct_invert_tuple); static void clean_from_lists(struct nf_conn *ct) { pr_debug("clean_from_lists(%p)\n", ct); hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode); /* Destroy all pending expectations */ nf_ct_remove_expectations(ct); } static void destroy_conntrack(struct nf_conntrack *nfct) { struct nf_conn *ct = (struct nf_conn *)nfct; struct net *net = nf_ct_net(ct); struct nf_conntrack_l4proto *l4proto; pr_debug("destroy_conntrack(%p)\n", ct); NF_CT_ASSERT(atomic_read(&nfct->use) == 0); NF_CT_ASSERT(!timer_pending(&ct->timeout)); /* To make sure we don't get any weird locking issues here: * destroy_conntrack() MUST NOT be called with a write lock * to nf_conntrack_lock!!! -HW */ rcu_read_lock(); l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); if (l4proto && l4proto->destroy) l4proto->destroy(ct); rcu_read_unlock(); spin_lock_bh(&nf_conntrack_lock); /* Expectations will have been removed in clean_from_lists, * except TFTP can create an expectation on the first packet, * before connection is in the list, so we need to clean here, * too. */ nf_ct_remove_expectations(ct); /* We overload first tuple to link into unconfirmed list. */ if (!nf_ct_is_confirmed(ct)) { BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode)); hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); } NF_CT_STAT_INC(net, delete); spin_unlock_bh(&nf_conntrack_lock); if (ct->master) nf_ct_put(ct->master); pr_debug("destroy_conntrack: returning ct=%p to slab\n", ct); nf_conntrack_free(ct); } void nf_ct_delete_from_lists(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); nf_ct_helper_destroy(ct); spin_lock_bh(&nf_conntrack_lock); /* Inside lock so preempt is disabled on module removal path. * Otherwise we can get spurious warnings. */ NF_CT_STAT_INC(net, delete_list); clean_from_lists(ct); spin_unlock_bh(&nf_conntrack_lock); } EXPORT_SYMBOL_GPL(nf_ct_delete_from_lists); static void death_by_event(unsigned long ul_conntrack) { struct nf_conn *ct = (void *)ul_conntrack; struct net *net = nf_ct_net(ct); if (nf_conntrack_event(IPCT_DESTROY, ct) < 0) { /* bad luck, let's retry again */ ct->timeout.expires = jiffies + (random32() % net->ct.sysctl_events_retry_timeout); add_timer(&ct->timeout); return; } /* we've got the event delivered, now it's dying */ set_bit(IPS_DYING_BIT, &ct->status); spin_lock(&nf_conntrack_lock); hlist_nulls_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); spin_unlock(&nf_conntrack_lock); nf_ct_put(ct); } void nf_ct_insert_dying_list(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); /* add this conntrack to the dying list */ spin_lock_bh(&nf_conntrack_lock); hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, &net->ct.dying); spin_unlock_bh(&nf_conntrack_lock); /* set a new timer to retry event delivery */ setup_timer(&ct->timeout, death_by_event, (unsigned long)ct); ct->timeout.expires = jiffies + (random32() % net->ct.sysctl_events_retry_timeout); add_timer(&ct->timeout); } EXPORT_SYMBOL_GPL(nf_ct_insert_dying_list); static void death_by_timeout(unsigned long ul_conntrack) { struct nf_conn *ct = (void *)ul_conntrack; struct nf_conn_tstamp *tstamp; tstamp = nf_conn_tstamp_find(ct); if (tstamp && tstamp->stop == 0) tstamp->stop = ktime_to_ns(ktime_get_real()); if (!test_bit(IPS_DYING_BIT, &ct->status) && unlikely(nf_conntrack_event(IPCT_DESTROY, ct) < 0)) { /* destroy event was not delivered */ nf_ct_delete_from_lists(ct); nf_ct_insert_dying_list(ct); return; } set_bit(IPS_DYING_BIT, &ct->status); nf_ct_delete_from_lists(ct); nf_ct_put(ct); } /* * Warning : * - Caller must take a reference on returned object * and recheck nf_ct_tuple_equal(tuple, &h->tuple) * OR * - Caller must lock nf_conntrack_lock before calling this function */ static struct nf_conntrack_tuple_hash * ____nf_conntrack_find(struct net *net, u16 zone, const struct nf_conntrack_tuple *tuple, u32 hash) { struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; unsigned int bucket = hash_bucket(hash, net); /* Disable BHs the entire time since we normally need to disable them * at least once for the stats anyway. */ local_bh_disable(); begin: hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[bucket], hnnode) { if (nf_ct_tuple_equal(tuple, &h->tuple) && nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)) == zone) { NF_CT_STAT_INC(net, found); local_bh_enable(); return h; } NF_CT_STAT_INC(net, searched); } /* * if the nulls value we got at the end of this lookup is * not the expected one, we must restart lookup. * We probably met an item that was moved to another chain. */ if (get_nulls_value(n) != bucket) { NF_CT_STAT_INC(net, search_restart); goto begin; } local_bh_enable(); return NULL; } struct nf_conntrack_tuple_hash * __nf_conntrack_find(struct net *net, u16 zone, const struct nf_conntrack_tuple *tuple) { return ____nf_conntrack_find(net, zone, tuple, hash_conntrack_raw(tuple, zone)); } EXPORT_SYMBOL_GPL(__nf_conntrack_find); /* Find a connection corresponding to a tuple. */ static struct nf_conntrack_tuple_hash * __nf_conntrack_find_get(struct net *net, u16 zone, const struct nf_conntrack_tuple *tuple, u32 hash) { struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; rcu_read_lock(); begin: h = ____nf_conntrack_find(net, zone, tuple, hash); if (h) { ct = nf_ct_tuplehash_to_ctrack(h); if (unlikely(nf_ct_is_dying(ct) || !atomic_inc_not_zero(&ct->ct_general.use))) h = NULL; else { if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple) || nf_ct_zone(ct) != zone)) { nf_ct_put(ct); goto begin; } } } rcu_read_unlock(); return h; } struct nf_conntrack_tuple_hash * nf_conntrack_find_get(struct net *net, u16 zone, const struct nf_conntrack_tuple *tuple) { return __nf_conntrack_find_get(net, zone, tuple, hash_conntrack_raw(tuple, zone)); } EXPORT_SYMBOL_GPL(nf_conntrack_find_get); static void __nf_conntrack_hash_insert(struct nf_conn *ct, unsigned int hash, unsigned int repl_hash) { struct net *net = nf_ct_net(ct); hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, &net->ct.hash[hash]); hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode, &net->ct.hash[repl_hash]); } void nf_conntrack_hash_insert(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); unsigned int hash, repl_hash; u16 zone; zone = nf_ct_zone(ct); hash = hash_conntrack(net, zone, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); repl_hash = hash_conntrack(net, zone, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); __nf_conntrack_hash_insert(ct, hash, repl_hash); } EXPORT_SYMBOL_GPL(nf_conntrack_hash_insert); /* Confirm a connection given skb; places it in hash table */ int __nf_conntrack_confirm(struct sk_buff *skb) { unsigned int hash, repl_hash; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct nf_conn_help *help; struct nf_conn_tstamp *tstamp; struct hlist_nulls_node *n; enum ip_conntrack_info ctinfo; struct net *net; u16 zone; ct = nf_ct_get(skb, &ctinfo); net = nf_ct_net(ct); /* ipt_REJECT uses nf_conntrack_attach to attach related ICMP/TCP RST packets in other direction. Actual packet which created connection will be IP_CT_NEW or for an expected connection, IP_CT_RELATED. */ if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) return NF_ACCEPT; zone = nf_ct_zone(ct); /* reuse the hash saved before */ hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev; hash = hash_bucket(hash, net); repl_hash = hash_conntrack(net, zone, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); /* We're not in hash table, and we refuse to set up related connections for unconfirmed conns. But packet copies and REJECT will give spurious warnings here. */ /* NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 1); */ /* No external references means no one else could have confirmed us. */ NF_CT_ASSERT(!nf_ct_is_confirmed(ct)); pr_debug("Confirming conntrack %p\n", ct); spin_lock_bh(&nf_conntrack_lock); /* We have to check the DYING flag inside the lock to prevent a race against nf_ct_get_next_corpse() possibly called from user context, else we insert an already 'dead' hash, blocking further use of that particular connection -JM */ if (unlikely(nf_ct_is_dying(ct))) { spin_unlock_bh(&nf_conntrack_lock); return NF_ACCEPT; } /* See if there's one in the list already, including reverse: NAT could have grabbed it without realizing, since we're not in the hash. If there is, we lost race. */ hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode) if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, &h->tuple) && zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) goto out; hlist_nulls_for_each_entry(h, n, &net->ct.hash[repl_hash], hnnode) if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple, &h->tuple) && zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) goto out; /* Remove from unconfirmed list */ hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); /* Timer relative to confirmation time, not original setting time, otherwise we'd get timer wrap in weird delay cases. */ ct->timeout.expires += jiffies; add_timer(&ct->timeout); atomic_inc(&ct->ct_general.use); ct->status |= IPS_CONFIRMED; /* set conntrack timestamp, if enabled. */ tstamp = nf_conn_tstamp_find(ct); if (tstamp) { if (skb->tstamp.tv64 == 0) __net_timestamp((struct sk_buff *)skb); tstamp->start = ktime_to_ns(skb->tstamp); } /* Since the lookup is lockless, hash insertion must be done after * starting the timer and setting the CONFIRMED bit. The RCU barriers * guarantee that no other CPU can find the conntrack before the above * stores are visible. */ __nf_conntrack_hash_insert(ct, hash, repl_hash); NF_CT_STAT_INC(net, insert); spin_unlock_bh(&nf_conntrack_lock); help = nfct_help(ct); if (help && help->helper) nf_conntrack_event_cache(IPCT_HELPER, ct); nf_conntrack_event_cache(master_ct(ct) ? IPCT_RELATED : IPCT_NEW, ct); return NF_ACCEPT; out: NF_CT_STAT_INC(net, insert_failed); spin_unlock_bh(&nf_conntrack_lock); return NF_DROP; } EXPORT_SYMBOL_GPL(__nf_conntrack_confirm); /* Returns true if a connection correspondings to the tuple (required for NAT). */ int nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, const struct nf_conn *ignored_conntrack) { struct net *net = nf_ct_net(ignored_conntrack); struct nf_conntrack_tuple_hash *h; struct hlist_nulls_node *n; struct nf_conn *ct; u16 zone = nf_ct_zone(ignored_conntrack); unsigned int hash = hash_conntrack(net, zone, tuple); /* Disable BHs the entire time since we need to disable them at * least once for the stats anyway. */ rcu_read_lock_bh(); hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnnode) { ct = nf_ct_tuplehash_to_ctrack(h); if (ct != ignored_conntrack && nf_ct_tuple_equal(tuple, &h->tuple) && nf_ct_zone(ct) == zone) { NF_CT_STAT_INC(net, found); rcu_read_unlock_bh(); return 1; } NF_CT_STAT_INC(net, searched); } rcu_read_unlock_bh(); return 0; } EXPORT_SYMBOL_GPL(nf_conntrack_tuple_taken); #define NF_CT_EVICTION_RANGE 8 /* There's a small race here where we may free a just-assured connection. Too bad: we're in trouble anyway. */ static noinline int early_drop(struct net *net, unsigned int hash) { /* Use oldest entry, which is roughly LRU */ struct nf_conntrack_tuple_hash *h; struct nf_conn *ct = NULL, *tmp; struct hlist_nulls_node *n; unsigned int i, cnt = 0; int dropped = 0; rcu_read_lock(); for (i = 0; i < net->ct.htable_size; i++) { hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnnode) { tmp = nf_ct_tuplehash_to_ctrack(h); if (!test_bit(IPS_ASSURED_BIT, &tmp->status)) ct = tmp; cnt++; } if (ct != NULL) { if (likely(!nf_ct_is_dying(ct) && atomic_inc_not_zero(&ct->ct_general.use))) break; else ct = NULL; } if (cnt >= NF_CT_EVICTION_RANGE) break; hash = (hash + 1) % net->ct.htable_size; } rcu_read_unlock(); if (!ct) return dropped; if (del_timer(&ct->timeout)) { death_by_timeout((unsigned long)ct); dropped = 1; NF_CT_STAT_INC_ATOMIC(net, early_drop); } nf_ct_put(ct); return dropped; } void init_nf_conntrack_hash_rnd(void) { unsigned int rand; /* * Why not initialize nf_conntrack_rnd in a "init()" function ? * Because there isn't enough entropy when system initializing, * and we initialize it as late as possible. */ do { get_random_bytes(&rand, sizeof(rand)); } while (!rand); cmpxchg(&nf_conntrack_hash_rnd, 0, rand); } static struct nf_conn * __nf_conntrack_alloc(struct net *net, u16 zone, const struct nf_conntrack_tuple *orig, const struct nf_conntrack_tuple *repl, gfp_t gfp, u32 hash) { struct nf_conn *ct; if (unlikely(!nf_conntrack_hash_rnd)) { init_nf_conntrack_hash_rnd(); /* recompute the hash as nf_conntrack_hash_rnd is initialized */ hash = hash_conntrack_raw(orig, zone); } /* We don't want any race condition at early drop stage */ atomic_inc(&net->ct.count); if (nf_conntrack_max && unlikely(atomic_read(&net->ct.count) > nf_conntrack_max)) { if (!early_drop(net, hash_bucket(hash, net))) { atomic_dec(&net->ct.count); if (net_ratelimit()) printk(KERN_WARNING "nf_conntrack: table full, dropping" " packet.\n"); return ERR_PTR(-ENOMEM); } } /* * Do not use kmem_cache_zalloc(), as this cache uses * SLAB_DESTROY_BY_RCU. */ ct = kmem_cache_alloc(net->ct.nf_conntrack_cachep, gfp); if (ct == NULL) { atomic_dec(&net->ct.count); return ERR_PTR(-ENOMEM); } /* * Let ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.next * and ct->tuplehash[IP_CT_DIR_REPLY].hnnode.next unchanged. */ memset(&ct->tuplehash[IP_CT_DIR_MAX], 0, offsetof(struct nf_conn, proto) - offsetof(struct nf_conn, tuplehash[IP_CT_DIR_MAX])); spin_lock_init(&ct->lock); ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig; ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.pprev = NULL; ct->tuplehash[IP_CT_DIR_REPLY].tuple = *repl; /* save hash for reusing when confirming */ *(unsigned long *)(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev) = hash; /* Don't set timer yet: wait for confirmation */ setup_timer(&ct->timeout, death_by_timeout, (unsigned long)ct); write_pnet(&ct->ct_net, net); #ifdef CONFIG_NF_CONNTRACK_ZONES if (zone) { struct nf_conntrack_zone *nf_ct_zone; nf_ct_zone = nf_ct_ext_add(ct, NF_CT_EXT_ZONE, GFP_ATOMIC); if (!nf_ct_zone) goto out_free; nf_ct_zone->id = zone; } #endif /* * changes to lookup keys must be done before setting refcnt to 1 */ smp_wmb(); atomic_set(&ct->ct_general.use, 1); return ct; #ifdef CONFIG_NF_CONNTRACK_ZONES out_free: kmem_cache_free(net->ct.nf_conntrack_cachep, ct); return ERR_PTR(-ENOMEM); #endif } struct nf_conn *nf_conntrack_alloc(struct net *net, u16 zone, const struct nf_conntrack_tuple *orig, const struct nf_conntrack_tuple *repl, gfp_t gfp) { return __nf_conntrack_alloc(net, zone, orig, repl, gfp, 0); } EXPORT_SYMBOL_GPL(nf_conntrack_alloc); void nf_conntrack_free(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); nf_ct_ext_destroy(ct); atomic_dec(&net->ct.count); nf_ct_ext_free(ct); kmem_cache_free(net->ct.nf_conntrack_cachep, ct); } EXPORT_SYMBOL_GPL(nf_conntrack_free); /* Allocate a new conntrack: we return -ENOMEM if classification failed due to stress. Otherwise it really is unclassifiable. */ static struct nf_conntrack_tuple_hash * init_conntrack(struct net *net, struct nf_conn *tmpl, const struct nf_conntrack_tuple *tuple, struct nf_conntrack_l3proto *l3proto, struct nf_conntrack_l4proto *l4proto, struct sk_buff *skb, unsigned int dataoff, u32 hash) { struct nf_conn *ct; struct nf_conn_help *help; struct nf_conntrack_tuple repl_tuple; struct nf_conntrack_ecache *ecache; struct nf_conntrack_expect *exp; u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE; if (!nf_ct_invert_tuple(&repl_tuple, tuple, l3proto, l4proto)) { pr_debug("Can't invert tuple.\n"); return NULL; } ct = __nf_conntrack_alloc(net, zone, tuple, &repl_tuple, GFP_ATOMIC, hash); if (IS_ERR(ct)) return (struct nf_conntrack_tuple_hash *)ct; if (!l4proto->new(ct, skb, dataoff)) { nf_conntrack_free(ct); pr_debug("init conntrack: can't track with proto module\n"); return NULL; } nf_ct_acct_ext_add(ct, GFP_ATOMIC); nf_ct_tstamp_ext_add(ct, GFP_ATOMIC); ecache = tmpl ? nf_ct_ecache_find(tmpl) : NULL; nf_ct_ecache_ext_add(ct, ecache ? ecache->ctmask : 0, ecache ? ecache->expmask : 0, GFP_ATOMIC); spin_lock_bh(&nf_conntrack_lock); exp = nf_ct_find_expectation(net, zone, tuple); if (exp) { pr_debug("conntrack: expectation arrives ct=%p exp=%p\n", ct, exp); /* Welcome, Mr. Bond. We've been expecting you... */ __set_bit(IPS_EXPECTED_BIT, &ct->status); ct->master = exp->master; if (exp->helper) { help = nf_ct_helper_ext_add(ct, GFP_ATOMIC); if (help) RCU_INIT_POINTER(help->helper, exp->helper); } #ifdef CONFIG_NF_CONNTRACK_MARK ct->mark = exp->master->mark; #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK ct->secmark = exp->master->secmark; #endif nf_conntrack_get(&ct->master->ct_general); NF_CT_STAT_INC(net, expect_new); } else { __nf_ct_try_assign_helper(ct, tmpl, GFP_ATOMIC); NF_CT_STAT_INC(net, new); } /* Overload tuple linked list to put us in unconfirmed list. */ hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, &net->ct.unconfirmed); spin_unlock_bh(&nf_conntrack_lock); if (exp) { if (exp->expectfn) exp->expectfn(ct, exp); nf_ct_expect_put(exp); } return &ct->tuplehash[IP_CT_DIR_ORIGINAL]; } /* On success, returns conntrack ptr, sets skb->nfct and ctinfo */ static inline struct nf_conn * resolve_normal_ct(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, u_int16_t l3num, u_int8_t protonum, struct nf_conntrack_l3proto *l3proto, struct nf_conntrack_l4proto *l4proto, int *set_reply, enum ip_conntrack_info *ctinfo) { struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE; u32 hash; if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num, protonum, &tuple, l3proto, l4proto)) { pr_debug("resolve_normal_ct: Can't get tuple\n"); return NULL; } /* look for tuple match */ hash = hash_conntrack_raw(&tuple, zone); h = __nf_conntrack_find_get(net, zone, &tuple, hash); if (!h) { h = init_conntrack(net, tmpl, &tuple, l3proto, l4proto, skb, dataoff, hash); if (!h) return NULL; if (IS_ERR(h)) return (void *)h; } ct = nf_ct_tuplehash_to_ctrack(h); /* It exists; we have (non-exclusive) reference. */ if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) { *ctinfo = IP_CT_ESTABLISHED_REPLY; /* Please set reply bit if this packet OK */ *set_reply = 1; } else { /* Once we've had two way comms, always ESTABLISHED. */ if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { pr_debug("nf_conntrack_in: normal packet for %p\n", ct); *ctinfo = IP_CT_ESTABLISHED; } else if (test_bit(IPS_EXPECTED_BIT, &ct->status)) { pr_debug("nf_conntrack_in: related packet for %p\n", ct); *ctinfo = IP_CT_RELATED; } else { pr_debug("nf_conntrack_in: new packet for %p\n", ct); *ctinfo = IP_CT_NEW; } *set_reply = 0; } skb->nfct = &ct->ct_general; skb->nfctinfo = *ctinfo; return ct; } unsigned int nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, struct sk_buff *skb) { struct nf_conn *ct, *tmpl = NULL; enum ip_conntrack_info ctinfo; struct nf_conntrack_l3proto *l3proto; struct nf_conntrack_l4proto *l4proto; unsigned int dataoff; u_int8_t protonum; int set_reply = 0; int ret; if (skb->nfct) { /* Previously seen (loopback or untracked)? Ignore. */ tmpl = (struct nf_conn *)skb->nfct; if (!nf_ct_is_template(tmpl)) { NF_CT_STAT_INC_ATOMIC(net, ignore); return NF_ACCEPT; } skb->nfct = NULL; } /* rcu_read_lock()ed by nf_hook_slow */ l3proto = __nf_ct_l3proto_find(pf); ret = l3proto->get_l4proto(skb, skb_network_offset(skb), &dataoff, &protonum); if (ret <= 0) { pr_debug("not prepared to track yet or error occurred\n"); NF_CT_STAT_INC_ATOMIC(net, error); NF_CT_STAT_INC_ATOMIC(net, invalid); ret = -ret; goto out; } l4proto = __nf_ct_l4proto_find(pf, protonum); /* It may be an special packet, error, unclean... * inverse of the return code tells to the netfilter * core what to do with the packet. */ if (l4proto->error != NULL) { ret = l4proto->error(net, tmpl, skb, dataoff, &ctinfo, pf, hooknum); if (ret <= 0) { NF_CT_STAT_INC_ATOMIC(net, error); NF_CT_STAT_INC_ATOMIC(net, invalid); ret = -ret; goto out; } /* ICMP[v6] protocol trackers may assign one conntrack. */ if (skb->nfct) goto out; } ct = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum, l3proto, l4proto, &set_reply, &ctinfo); if (!ct) { /* Not valid part of a connection */ NF_CT_STAT_INC_ATOMIC(net, invalid); ret = NF_ACCEPT; goto out; } if (IS_ERR(ct)) { /* Too stressed to deal. */ NF_CT_STAT_INC_ATOMIC(net, drop); ret = NF_DROP; goto out; } NF_CT_ASSERT(skb->nfct); ret = l4proto->packet(ct, skb, dataoff, ctinfo, pf, hooknum); if (ret <= 0) { /* Invalid: inverse of the return code tells * the netfilter core what to do */ pr_debug("nf_conntrack_in: Can't track with proto module\n"); nf_conntrack_put(skb->nfct); skb->nfct = NULL; NF_CT_STAT_INC_ATOMIC(net, invalid); if (ret == -NF_DROP) NF_CT_STAT_INC_ATOMIC(net, drop); ret = -ret; goto out; } if (set_reply && !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_REPLY, ct); out: if (tmpl) { /* Special case: we have to repeat this hook, assign the * template again to this packet. We assume that this packet * has no conntrack assigned. This is used by nf_ct_tcp. */ if (ret == NF_REPEAT) skb->nfct = (struct nf_conntrack *)tmpl; else nf_ct_put(tmpl); } return ret; } EXPORT_SYMBOL_GPL(nf_conntrack_in); bool nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse, const struct nf_conntrack_tuple *orig) { bool ret; rcu_read_lock(); ret = nf_ct_invert_tuple(inverse, orig, __nf_ct_l3proto_find(orig->src.l3num), __nf_ct_l4proto_find(orig->src.l3num, orig->dst.protonum)); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(nf_ct_invert_tuplepr); /* Alter reply tuple (maybe alter helper). This is for NAT, and is implicitly racy: see __nf_conntrack_confirm */ void nf_conntrack_alter_reply(struct nf_conn *ct, const struct nf_conntrack_tuple *newreply) { struct nf_conn_help *help = nfct_help(ct); /* Should be unconfirmed, so not in hash table yet */ NF_CT_ASSERT(!nf_ct_is_confirmed(ct)); pr_debug("Altering reply tuple of %p to ", ct); nf_ct_dump_tuple(newreply); ct->tuplehash[IP_CT_DIR_REPLY].tuple = *newreply; if (ct->master || (help && !hlist_empty(&help->expectations))) return; rcu_read_lock(); __nf_ct_try_assign_helper(ct, NULL, GFP_ATOMIC); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(nf_conntrack_alter_reply); /* Refresh conntrack for this many jiffies and do accounting if do_acct is 1 */ void __nf_ct_refresh_acct(struct nf_conn *ct, enum ip_conntrack_info ctinfo, const struct sk_buff *skb, unsigned long extra_jiffies, int do_acct) { NF_CT_ASSERT(ct->timeout.data == (unsigned long)ct); NF_CT_ASSERT(skb); /* Only update if this is not a fixed timeout */ if (test_bit(IPS_FIXED_TIMEOUT_BIT, &ct->status)) goto acct; /* If not in hash table, timer will not be active yet */ if (!nf_ct_is_confirmed(ct)) { ct->timeout.expires = extra_jiffies; } else { unsigned long newtime = jiffies + extra_jiffies; /* Only update the timeout if the new timeout is at least HZ jiffies from the old timeout. Need del_timer for race avoidance (may already be dying). */ if (newtime - ct->timeout.expires >= HZ) mod_timer_pending(&ct->timeout, newtime); } acct: if (do_acct) { struct nf_conn_counter *acct; acct = nf_conn_acct_find(ct); if (acct) { spin_lock_bh(&ct->lock); acct[CTINFO2DIR(ctinfo)].packets++; acct[CTINFO2DIR(ctinfo)].bytes += skb->len; spin_unlock_bh(&ct->lock); } } } EXPORT_SYMBOL_GPL(__nf_ct_refresh_acct); bool __nf_ct_kill_acct(struct nf_conn *ct, enum ip_conntrack_info ctinfo, const struct sk_buff *skb, int do_acct) { if (do_acct) { struct nf_conn_counter *acct; acct = nf_conn_acct_find(ct); if (acct) { spin_lock_bh(&ct->lock); acct[CTINFO2DIR(ctinfo)].packets++; acct[CTINFO2DIR(ctinfo)].bytes += skb->len - skb_network_offset(skb); spin_unlock_bh(&ct->lock); } } if (del_timer(&ct->timeout)) { ct->timeout.function((unsigned long)ct); return true; } return false; } EXPORT_SYMBOL_GPL(__nf_ct_kill_acct); #ifdef CONFIG_NF_CONNTRACK_ZONES static struct nf_ct_ext_type nf_ct_zone_extend __read_mostly = { .len = sizeof(struct nf_conntrack_zone), .align = __alignof__(struct nf_conntrack_zone), .id = NF_CT_EXT_ZONE, }; #endif #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> #include <linux/mutex.h> /* Generic function for tcp/udp/sctp/dccp and alike. This needs to be * in ip_conntrack_core, since we don't want the protocols to autoload * or depend on ctnetlink */ int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { NLA_PUT_BE16(skb, CTA_PROTO_SRC_PORT, tuple->src.u.tcp.port); NLA_PUT_BE16(skb, CTA_PROTO_DST_PORT, tuple->dst.u.tcp.port); return 0; nla_put_failure: return -1; } EXPORT_SYMBOL_GPL(nf_ct_port_tuple_to_nlattr); const struct nla_policy nf_ct_port_nla_policy[CTA_PROTO_MAX+1] = { [CTA_PROTO_SRC_PORT] = { .type = NLA_U16 }, [CTA_PROTO_DST_PORT] = { .type = NLA_U16 }, }; EXPORT_SYMBOL_GPL(nf_ct_port_nla_policy); int nf_ct_port_nlattr_to_tuple(struct nlattr *tb[], struct nf_conntrack_tuple *t) { if (!tb[CTA_PROTO_SRC_PORT] || !tb[CTA_PROTO_DST_PORT]) return -EINVAL; t->src.u.tcp.port = nla_get_be16(tb[CTA_PROTO_SRC_PORT]); t->dst.u.tcp.port = nla_get_be16(tb[CTA_PROTO_DST_PORT]); return 0; } EXPORT_SYMBOL_GPL(nf_ct_port_nlattr_to_tuple); int nf_ct_port_nlattr_tuple_size(void) { return nla_policy_len(nf_ct_port_nla_policy, CTA_PROTO_MAX + 1); } EXPORT_SYMBOL_GPL(nf_ct_port_nlattr_tuple_size); #endif /* Used by ipt_REJECT and ip6t_REJECT. */ static void nf_conntrack_attach(struct sk_buff *nskb, struct sk_buff *skb) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; /* This ICMP is in reverse direction to the packet which caused it */ ct = nf_ct_get(skb, &ctinfo); if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) ctinfo = IP_CT_RELATED_REPLY; else ctinfo = IP_CT_RELATED; /* Attach to new skbuff, and increment count */ nskb->nfct = &ct->ct_general; nskb->nfctinfo = ctinfo; nf_conntrack_get(nskb->nfct); } /* Bring out ya dead! */ static struct nf_conn * get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), void *data, unsigned int *bucket) { struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct hlist_nulls_node *n; spin_lock_bh(&nf_conntrack_lock); for (; *bucket < net->ct.htable_size; (*bucket)++) { hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) { ct = nf_ct_tuplehash_to_ctrack(h); if (iter(ct, data)) goto found; } } hlist_nulls_for_each_entry(h, n, &net->ct.unconfirmed, hnnode) { ct = nf_ct_tuplehash_to_ctrack(h); if (iter(ct, data)) set_bit(IPS_DYING_BIT, &ct->status); } spin_unlock_bh(&nf_conntrack_lock); return NULL; found: atomic_inc(&ct->ct_general.use); spin_unlock_bh(&nf_conntrack_lock); return ct; } void nf_ct_iterate_cleanup(struct net *net, int (*iter)(struct nf_conn *i, void *data), void *data) { struct nf_conn *ct; unsigned int bucket = 0; while ((ct = get_next_corpse(net, iter, data, &bucket)) != NULL) { /* Time to push up daises... */ if (del_timer(&ct->timeout)) death_by_timeout((unsigned long)ct); /* ... else the timer will get him soon. */ nf_ct_put(ct); } } EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup); struct __nf_ct_flush_report { u32 pid; int report; }; static int kill_report(struct nf_conn *i, void *data) { struct __nf_ct_flush_report *fr = (struct __nf_ct_flush_report *)data; struct nf_conn_tstamp *tstamp; tstamp = nf_conn_tstamp_find(i); if (tstamp && tstamp->stop == 0) tstamp->stop = ktime_to_ns(ktime_get_real()); /* If we fail to deliver the event, death_by_timeout() will retry */ if (nf_conntrack_event_report(IPCT_DESTROY, i, fr->pid, fr->report) < 0) return 1; /* Avoid the delivery of the destroy event in death_by_timeout(). */ set_bit(IPS_DYING_BIT, &i->status); return 1; } static int kill_all(struct nf_conn *i, void *data) { return 1; } void nf_ct_free_hashtable(void *hash, unsigned int size) { if (is_vmalloc_addr(hash)) vfree(hash); else free_pages((unsigned long)hash, get_order(sizeof(struct hlist_head) * size)); } EXPORT_SYMBOL_GPL(nf_ct_free_hashtable); void nf_conntrack_flush_report(struct net *net, u32 pid, int report) { struct __nf_ct_flush_report fr = { .pid = pid, .report = report, }; nf_ct_iterate_cleanup(net, kill_report, &fr); } EXPORT_SYMBOL_GPL(nf_conntrack_flush_report); static void nf_ct_release_dying_list(struct net *net) { struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct hlist_nulls_node *n; spin_lock_bh(&nf_conntrack_lock); hlist_nulls_for_each_entry(h, n, &net->ct.dying, hnnode) { ct = nf_ct_tuplehash_to_ctrack(h); /* never fails to remove them, no listeners at this point */ nf_ct_kill(ct); } spin_unlock_bh(&nf_conntrack_lock); } static int untrack_refs(void) { int cnt = 0, cpu; for_each_possible_cpu(cpu) { struct nf_conn *ct = &per_cpu(nf_conntrack_untracked, cpu); cnt += atomic_read(&ct->ct_general.use) - 1; } return cnt; } static void nf_conntrack_cleanup_init_net(void) { while (untrack_refs() > 0) schedule(); nf_conntrack_helper_fini(); nf_conntrack_proto_fini(); #ifdef CONFIG_NF_CONNTRACK_ZONES nf_ct_extend_unregister(&nf_ct_zone_extend); #endif } static void nf_conntrack_cleanup_net(struct net *net) { i_see_dead_people: nf_ct_iterate_cleanup(net, kill_all, NULL); nf_ct_release_dying_list(net); if (atomic_read(&net->ct.count) != 0) { schedule(); goto i_see_dead_people; } nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size); nf_conntrack_ecache_fini(net); nf_conntrack_tstamp_fini(net); nf_conntrack_acct_fini(net); nf_conntrack_expect_fini(net); kmem_cache_destroy(net->ct.nf_conntrack_cachep); kfree(net->ct.slabname); free_percpu(net->ct.stat); } /* Mishearing the voices in his head, our hero wonders how he's supposed to kill the mall. */ void nf_conntrack_cleanup(struct net *net) { if (net_eq(net, &init_net)) RCU_INIT_POINTER(ip_ct_attach, NULL); /* This makes sure all current packets have passed through netfilter framework. Roll on, two-stage module delete... */ synchronize_net(); nf_conntrack_cleanup_net(net); if (net_eq(net, &init_net)) { RCU_INIT_POINTER(nf_ct_destroy, NULL); nf_conntrack_cleanup_init_net(); } } void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls) { struct hlist_nulls_head *hash; unsigned int nr_slots, i; size_t sz; BUILD_BUG_ON(sizeof(struct hlist_nulls_head) != sizeof(struct hlist_head)); nr_slots = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_nulls_head)); sz = nr_slots * sizeof(struct hlist_nulls_head); hash = (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, get_order(sz)); if (!hash) { printk(KERN_WARNING "nf_conntrack: falling back to vmalloc.\n"); hash = __vmalloc(sz, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL); } if (hash && nulls) for (i = 0; i < nr_slots; i++) INIT_HLIST_NULLS_HEAD(&hash[i], i); return hash; } EXPORT_SYMBOL_GPL(nf_ct_alloc_hashtable); int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) { int i, bucket; unsigned int hashsize, old_size; struct hlist_nulls_head *hash, *old_hash; struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; if (current->nsproxy->net_ns != &init_net) return -EOPNOTSUPP; /* On boot, we can set this without any fancy locking. */ if (!nf_conntrack_htable_size) return param_set_uint(val, kp); hashsize = simple_strtoul(val, NULL, 0); if (!hashsize) return -EINVAL; hash = nf_ct_alloc_hashtable(&hashsize, 1); if (!hash) return -ENOMEM; /* Lookups in the old hash might happen in parallel, which means we * might get false negatives during connection lookup. New connections * created because of a false negative won't make it into the hash * though since that required taking the lock. */ spin_lock_bh(&nf_conntrack_lock); for (i = 0; i < init_net.ct.htable_size; i++) { while (!hlist_nulls_empty(&init_net.ct.hash[i])) { h = hlist_nulls_entry(init_net.ct.hash[i].first, struct nf_conntrack_tuple_hash, hnnode); ct = nf_ct_tuplehash_to_ctrack(h); hlist_nulls_del_rcu(&h->hnnode); bucket = __hash_conntrack(&h->tuple, nf_ct_zone(ct), hashsize); hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]); } } old_size = init_net.ct.htable_size; old_hash = init_net.ct.hash; init_net.ct.htable_size = nf_conntrack_htable_size = hashsize; init_net.ct.hash = hash; spin_unlock_bh(&nf_conntrack_lock); nf_ct_free_hashtable(old_hash, old_size); return 0; } EXPORT_SYMBOL_GPL(nf_conntrack_set_hashsize); module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint, &nf_conntrack_htable_size, 0600); void nf_ct_untracked_status_or(unsigned long bits) { int cpu; for_each_possible_cpu(cpu) per_cpu(nf_conntrack_untracked, cpu).status |= bits; } EXPORT_SYMBOL_GPL(nf_ct_untracked_status_or); static int nf_conntrack_init_init_net(void) { int max_factor = 8; int ret, cpu; /* Idea from tcp.c: use 1/16384 of memory. On i386: 32MB * machine has 512 buckets. >= 1GB machines have 16384 buckets. */ if (!nf_conntrack_htable_size) { nf_conntrack_htable_size = (((totalram_pages << PAGE_SHIFT) / 16384) / sizeof(struct hlist_head)); if (totalram_pages > (1024 * 1024 * 1024 / PAGE_SIZE)) nf_conntrack_htable_size = 16384; if (nf_conntrack_htable_size < 32) nf_conntrack_htable_size = 32; /* Use a max. factor of four by default to get the same max as * with the old struct list_heads. When a table size is given * we use the old value of 8 to avoid reducing the max. * entries. */ max_factor = 4; } nf_conntrack_max = max_factor * nf_conntrack_htable_size; printk(KERN_INFO "nf_conntrack version %s (%u buckets, %d max)\n", NF_CONNTRACK_VERSION, nf_conntrack_htable_size, nf_conntrack_max); ret = nf_conntrack_proto_init(); if (ret < 0) goto err_proto; ret = nf_conntrack_helper_init(); if (ret < 0) goto err_helper; #ifdef CONFIG_NF_CONNTRACK_ZONES ret = nf_ct_extend_register(&nf_ct_zone_extend); if (ret < 0) goto err_extend; #endif /* Set up fake conntrack: to never be deleted, not in any hashes */ for_each_possible_cpu(cpu) { struct nf_conn *ct = &per_cpu(nf_conntrack_untracked, cpu); write_pnet(&ct->ct_net, &init_net); atomic_set(&ct->ct_general.use, 1); } /* - and look it like as a confirmed connection */ nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED); return 0; #ifdef CONFIG_NF_CONNTRACK_ZONES err_extend: nf_conntrack_helper_fini(); #endif err_helper: nf_conntrack_proto_fini(); err_proto: return ret; } /* * We need to use special "null" values, not used in hash table */ #define UNCONFIRMED_NULLS_VAL ((1<<30)+0) #define DYING_NULLS_VAL ((1<<30)+1) static int nf_conntrack_init_net(struct net *net) { int ret; atomic_set(&net->ct.count, 0); INIT_HLIST_NULLS_HEAD(&net->ct.unconfirmed, UNCONFIRMED_NULLS_VAL); INIT_HLIST_NULLS_HEAD(&net->ct.dying, DYING_NULLS_VAL); net->ct.stat = alloc_percpu(struct ip_conntrack_stat); if (!net->ct.stat) { ret = -ENOMEM; goto err_stat; } net->ct.slabname = kasprintf(GFP_KERNEL, "nf_conntrack_%p", net); if (!net->ct.slabname) { ret = -ENOMEM; goto err_slabname; } net->ct.nf_conntrack_cachep = kmem_cache_create(net->ct.slabname, sizeof(struct nf_conn), 0, SLAB_DESTROY_BY_RCU, NULL); if (!net->ct.nf_conntrack_cachep) { printk(KERN_ERR "Unable to create nf_conn slab cache\n"); ret = -ENOMEM; goto err_cache; } net->ct.htable_size = nf_conntrack_htable_size; net->ct.hash = nf_ct_alloc_hashtable(&net->ct.htable_size, 1); if (!net->ct.hash) { ret = -ENOMEM; printk(KERN_ERR "Unable to create nf_conntrack_hash\n"); goto err_hash; } ret = nf_conntrack_expect_init(net); if (ret < 0) goto err_expect; ret = nf_conntrack_acct_init(net); if (ret < 0) goto err_acct; ret = nf_conntrack_tstamp_init(net); if (ret < 0) goto err_tstamp; ret = nf_conntrack_ecache_init(net); if (ret < 0) goto err_ecache; return 0; err_ecache: nf_conntrack_tstamp_fini(net); err_tstamp: nf_conntrack_acct_fini(net); err_acct: nf_conntrack_expect_fini(net); err_expect: nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size); err_hash: kmem_cache_destroy(net->ct.nf_conntrack_cachep); err_cache: kfree(net->ct.slabname); err_slabname: free_percpu(net->ct.stat); err_stat: return ret; } s16 (*nf_ct_nat_offset)(const struct nf_conn *ct, enum ip_conntrack_dir dir, u32 seq); EXPORT_SYMBOL_GPL(nf_ct_nat_offset); int nf_conntrack_init(struct net *net) { int ret; if (net_eq(net, &init_net)) { ret = nf_conntrack_init_init_net(); if (ret < 0) goto out_init_net; } ret = nf_conntrack_init_net(net); if (ret < 0) goto out_net; if (net_eq(net, &init_net)) { /* For use by REJECT target */ RCU_INIT_POINTER(ip_ct_attach, nf_conntrack_attach); RCU_INIT_POINTER(nf_ct_destroy, destroy_conntrack); /* Howto get NAT offsets */ RCU_INIT_POINTER(nf_ct_nat_offset, NULL); } return 0; out_net: if (net_eq(net, &init_net)) nf_conntrack_cleanup_init_net(); out_init_net: return ret; }