linux_dsm_epyc7002/lib
Daniel Borkmann 92b31a9af7 bpf: add BPF_J{LT,LE,SLT,SLE} instructions
Currently, eBPF only understands BPF_JGT (>), BPF_JGE (>=),
BPF_JSGT (s>), BPF_JSGE (s>=) instructions, this means that
particularly *JLT/*JLE counterparts involving immediates need
to be rewritten from e.g. X < [IMM] by swapping arguments into
[IMM] > X, meaning the immediate first is required to be loaded
into a register Y := [IMM], such that then we can compare with
Y > X. Note that the destination operand is always required to
be a register.

This has the downside of having unnecessarily increased register
pressure, meaning complex program would need to spill other
registers temporarily to stack in order to obtain an unused
register for the [IMM]. Loading to registers will thus also
affect state pruning since we need to account for that register
use and potentially those registers that had to be spilled/filled
again. As a consequence slightly more stack space might have
been used due to spilling, and BPF programs are a bit longer
due to extra code involving the register load and potentially
required spill/fills.

Thus, add BPF_JLT (<), BPF_JLE (<=), BPF_JSLT (s<), BPF_JSLE (s<=)
counterparts to the eBPF instruction set. Modifying LLVM to
remove the NegateCC() workaround in a PoC patch at [1] and
allowing it to also emit the new instructions resulted in
cilium's BPF programs that are injected into the fast-path to
have a reduced program length in the range of 2-3% (e.g.
accumulated main and tail call sections from one of the object
file reduced from 4864 to 4729 insns), reduced complexity in
the range of 10-30% (e.g. accumulated sections reduced in one
of the cases from 116432 to 88428 insns), and reduced stack
usage in the range of 1-5% (e.g. accumulated sections from one
of the object files reduced from 824 to 784b).

The modification for LLVM will be incorporated in a backwards
compatible way. Plan is for LLVM to have i) a target specific
option to offer a possibility to explicitly enable the extension
by the user (as we have with -m target specific extensions today
for various CPU insns), and ii) have the kernel checked for
presence of the extensions and enable them transparently when
the user is selecting more aggressive options such as -march=native
in a bpf target context. (Other frontends generating BPF byte
code, e.g. ply can probe the kernel directly for its code
generation.)

  [1] https://github.com/borkmann/llvm/tree/bpf-insns

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-09 16:53:56 -07:00
..
842 Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial 2016-03-17 21:38:27 -07:00
fonts lib/fonts/Kconfig: keep non-Sparc fonts listed together 2017-02-27 18:43:46 -08:00
lz4 lib/lz4: remove back-compat wrappers 2017-02-24 17:46:57 -08:00
lzo
mpi mpi: Fix NULL ptr dereference in mpi_powm() [ver #3] 2016-11-25 12:57:50 +11:00
raid6 lib/raid6: Add log-of-2 table for RAID6 HW requiring disk position 2017-05-16 10:01:57 +05:30
reed_solomon
xz
zlib_deflate
zlib_inflate lib/zlib_inflate/inftrees.c: fix potential buffer overflow 2017-05-08 17:15:12 -07:00
.gitignore
argv_split.c
asn1_decoder.c Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6 2016-05-17 09:33:39 -07:00
assoc_array.c assoc_array: don't call compare_object() on a node 2016-04-06 14:06:48 +01:00
atomic64_test.c lib/atomic64_test.c: add a test that atomic64_inc_not_zero() returns an int 2017-07-14 15:05:13 -07:00
atomic64.c locking/atomic: Implement atomic{,64,_long}_fetch_{add,sub,and,andnot,or,xor}{,_relaxed,_acquire,_release}() 2016-06-16 10:48:32 +02:00
audit.c
bcd.c
bch.c
bitmap.c bitmap: optimise bitmap_set and bitmap_clear of a single bit 2017-07-10 16:32:34 -07:00
bitrev.c
bsearch.c lib/bsearch.c: micro-optimize pivot position calculation 2017-07-10 16:32:35 -07:00
btree.c
bug.c debug: Add _ONCE() logic to report_bug() 2017-03-30 09:37:20 +02:00
build_OID_registry
bust_spinlocks.c
chacha20.c random: replace non-blocking pool with a Chacha20-based CRNG 2016-07-03 00:57:23 -04:00
check_signature.c
checksum.c
clz_ctz.c
clz_tab.c
cmdline.c lib/cmdline.c: fix get_options() overflow while parsing ranges 2017-06-23 16:15:55 -07:00
compat_audit.c
cordic.c
cpu_rmap.c
cpumask.c sched/fair, cpumask: Export for_each_cpu_wrap() 2017-05-15 10:15:23 +02:00
crc4.c lib: Add crc4 module 2017-06-09 11:52:07 +02:00
crc7.c
crc8.c
crc16.c
crc32.c lib: add module support to crc32 tests 2017-02-24 17:46:57 -08:00
crc32defs.h
crc32test.c lib: add module support to crc32 tests 2017-02-24 17:46:57 -08:00
crc-ccitt.c
crc-itu-t.c
crc-t10dif.c
ctype.c
debug_info.c
debug_locks.c
debugobjects.c sched/headers: Prepare for new header dependencies before moving code to <linux/sched/task_stack.h> 2017-03-02 08:42:36 +01:00
dec_and_lock.c
decompress_bunzip2.c
decompress_inflate.c
decompress_unlz4.c lib/decompress_unlz4: change module to work with new LZ4 module version 2017-02-24 17:46:57 -08:00
decompress_unlzma.c
decompress_unlzo.c
decompress_unxz.c
decompress.c
devres.c devres: fix devm_ioremap_*() offset parameter kerneldoc description 2017-04-24 13:53:13 -05:00
digsig.c KEYS: Differentiate uses of rcu_dereference_key() and user_key_payload() 2017-03-02 10:09:00 +11:00
div64.c
dma-debug.c dmaengine updates for 4.12-rc1 2017-05-09 15:40:28 -07:00
dma-noop.c dma: Take into account dma_pfn_offset 2017-06-28 06:55:01 -07:00
dma-virt.c dma-virt: remove dma_supported and mapping_error methods 2017-06-28 06:54:41 -07:00
dump_stack.c sched/headers: Prepare for new header dependencies before moving code to <linux/sched/debug.h> 2017-03-02 08:42:34 +01:00
dynamic_debug.c dynamic_debug: add jump label support 2016-08-04 08:50:07 -04:00
dynamic_queue_limits.c
earlycpio.c lib/cpio: Make find_cpio_data()'s offset arg optional 2016-06-08 11:04:19 +02:00
errseq.c lib: add errseq_t type and infrastructure for handling it 2017-07-06 07:02:24 -04:00
extable.c lib/extable.c: use bsearch() library function in search_extable() 2017-07-10 16:32:35 -07:00
fault-inject.c fault-inject: simplify access check for fail-nth 2017-07-14 15:05:13 -07:00
fdt_empty_tree.c
fdt_ro.c
fdt_rw.c
fdt_strerror.c
fdt_sw.c
fdt_wip.c
fdt.c
find_bit.c lib/find_bit.c: micro-optimise find_next_*_bit 2017-02-24 17:46:57 -08:00
flex_array.c
flex_proportions.c percpu_counter: Rename __percpu_counter_add to percpu_counter_add_batch 2017-06-20 15:42:32 -04:00
gcd.c lib/GCD.c: use binary GCD algorithm instead of Euclidean 2016-05-20 17:58:30 -07:00
gen_crc32table.c
genalloc.c lib/genalloc.c: start search from start of chunk 2016-10-27 18:43:43 -07:00
glob.c lib: add module support to glob tests 2017-02-24 17:46:57 -08:00
globtest.c lib: add module support to glob tests 2017-02-24 17:46:57 -08:00
hexdump.c
hweight.c x86/hweight: Get rid of the special calling convention 2016-06-08 15:01:02 +02:00
idr.c idr: Add missing __rcu annotations 2017-02-13 21:44:10 -05:00
inflate.c
int_sqrt.c
interval_tree_test.c lib/interval_tree_test.c: allow full tree search 2017-07-10 16:32:35 -07:00
interval_tree.c
iomap_copy.c
iomap.c
iommu-common.c
iommu-helper.c lib/iommu-helper: skip to next segment 2016-08-02 19:35:07 -04:00
ioremap.c mm: convert generic code to 5-level paging 2017-03-09 11:48:47 -08:00
iov_iter.c Merge branch 'uaccess-work.iov_iter' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 2017-07-07 20:39:20 -07:00
irq_poll.c This adds a new gcc plugin named "latent_entropy". It is designed to 2016-10-15 10:03:15 -07:00
irq_regs.c
is_single_threaded.c sched/headers: Prepare to move 'init_task' and 'init_thread_union' from <linux/sched.h> to <linux/sched/task.h> 2017-03-02 08:42:38 +01:00
jedec_ddr_data.c
kasprintf.c
Kconfig libnvdimm for 4.13 2017-07-07 09:44:06 -07:00
Kconfig.debug Add wait_for_random_bytes() and get_random_*_wait() functions so that 2017-07-15 12:44:02 -07:00
Kconfig.kasan mm, kasan: switch SLUB to stackdepot, enable memory quarantine for SLUB 2016-07-28 16:07:41 -07:00
Kconfig.kgdb lib: update location of kgdb documentation 2017-05-16 08:44:22 -03:00
Kconfig.kmemcheck
Kconfig.ubsan Kconfig: lib/Kconfig.ubsan fix reference to ubsan documentation 2016-12-14 16:04:08 -08:00
kfifo.c
klist.c
kobject_uevent.c kobject: support passing in variables for synthetic uevents 2017-05-25 18:30:51 +02:00
kobject.c kobject: Export kobject_get_unless_zero() 2017-03-22 20:11:35 -06:00
kstrtox.c lib/kstrtox.c: use "unsigned int" more 2017-07-10 16:32:34 -07:00
kstrtox.h
lcm.c
libcrc32c.c crypto: Work around deallocated stack frame reference gcc bug on sparc. 2017-06-08 17:36:03 +08:00
list_debug.c bug: switch data corruption check to __must_check 2017-02-24 17:46:56 -08:00
list_sort.c lib: add module support to linked list sorting tests 2017-05-08 17:15:10 -07:00
llist.c
locking-selftest-hardirq.h
locking-selftest-mutex.h
locking-selftest-rlock-hardirq.h
locking-selftest-rlock-softirq.h
locking-selftest-rlock.h
locking-selftest-rsem.h
locking-selftest-rtmutex.h locking/selftest: Add RT-mutex support 2017-06-08 10:35:50 +02:00
locking-selftest-softirq.h
locking-selftest-spin-hardirq.h
locking-selftest-spin-softirq.h
locking-selftest-spin.h
locking-selftest-wlock-hardirq.h
locking-selftest-wlock-softirq.h
locking-selftest-wlock.h
locking-selftest-wsem.h
locking-selftest.c locking/selftest: Add RT-mutex support 2017-06-08 10:35:50 +02:00
lockref.c locking/core: Remove cpu_relax_lowlatency() users 2016-11-16 10:15:10 +01:00
lru_cache.c
Makefile kmod: add test driver to stress test the module loader 2017-07-14 15:05:13 -07:00
memory-notifier-error-inject.c
memweight.c
net_utils.c
netdev-notifier-error-inject.c
nlattr.c net netlink: Add new type NLA_BITFIELD32 2017-07-30 19:28:08 -07:00
nmi_backtrace.c printk: Use the main logbuf in NMI when logbuf_lock is available 2017-05-19 14:42:19 +02:00
nodemask.c include/linux/nodemask.h: create next_node_in() helper 2016-05-19 19:12:14 -07:00
notifier-error-inject.c
notifier-error-inject.h
of-reconfig-notifier-error-inject.c
oid_registry.c
once.c
parman.c lib: Introduce priority array area manager 2017-02-03 16:35:42 -05:00
parser.c parser: add u64 number parser 2016-12-06 10:17:03 +02:00
pci_iomap.c
percpu_counter.c writeback: rework wb_[dec|inc]_stat family of functions 2017-07-12 16:26:05 -07:00
percpu_ida.c sched/headers: Prepare to remove the <linux/gfp.h> include from <linux/sched.h> 2017-03-02 08:42:34 +01:00
percpu_test.c
percpu-refcount.c percpu-refcount: support synchronous switch to atomic mode. 2017-03-22 19:18:43 -07:00
plist.c sched/headers: Prepare for new header dependencies before moving code to <linux/sched/clock.h> 2017-03-02 08:42:27 +01:00
pm-notifier-error-inject.c
prime_numbers.c lib/prime_numbers: Suppress warn on kmalloc failure 2017-01-23 09:17:12 +01:00
radix-tree.c lockdep: allow to disable reclaim lockup detection 2017-05-03 15:52:09 -07:00
random32.c This adds a new gcc plugin named "latent_entropy". It is designed to 2016-10-15 10:03:15 -07:00
ratelimit.c ratelimit: extend to print suppressed messages on release 2016-08-02 19:35:06 -04:00
rational.c
rbtree_test.c
rbtree.c rbtree: use designated initializers 2017-02-24 17:46:57 -08:00
reciprocal_div.c
refcount.c locking/refcount: Create unchecked atomic_t implementation 2017-06-28 18:54:46 +02:00
rhashtable.c Add wait_for_random_bytes() and get_random_*_wait() functions so that 2017-07-15 12:44:02 -07:00
sbitmap.c sbitmap: add sbitmap_get_shallow() operation 2017-04-14 14:06:52 -06:00
scatterlist.c scatterlist: add sg_zero_buffer() helper 2017-06-15 14:30:14 +02:00
seq_buf.c
sg_pool.c lib: scatterlist: move SG pool code from SCSI driver to lib/sg_pool.c 2016-04-15 16:53:14 -04:00
sg_split.c
sha1.c
show_mem.c lib/show_mem.c: teach show_mem to work with the given nodemask 2017-02-22 16:41:30 -08:00
siphash.c siphash: implement HalfSipHash1-3 for hash tables 2017-01-09 13:58:57 -05:00
smp_processor_id.c sched/core: Enable might_sleep() and smp_processor_id() checks early 2017-05-23 10:01:38 +02:00
sort.c lib: add CONFIG_TEST_SORT to enable self-test of sort() 2017-02-24 17:46:57 -08:00
stackdepot.c lib/stackdepot: export save/fetch stack for drivers 2016-11-11 08:12:37 -08:00
stmp_device.c
string_helpers.c string_helpers: add kstrdup_quotable_file 2016-04-21 10:47:26 +10:00
string.c include/linux/string.h: add the option of fortified string.h functions 2017-07-12 16:26:03 -07:00
strncpy_from_user.c lib: harden strncpy_from_user 2016-10-11 15:06:30 -07:00
strnlen_user.c kill strlen_user() 2017-05-15 23:40:22 -04:00
swiotlb.c swiotlb: ensure that page-sized mappings are page-aligned 2017-01-15 12:37:24 -05:00
syscall.c lib/syscall: Clear return values when no stack 2017-03-24 07:43:35 +01:00
test_bitmap.c bitmap: optimise bitmap_set and bitmap_clear of a single bit 2017-07-10 16:32:34 -07:00
test_bpf.c bpf: add BPF_J{LT,LE,SLT,SLE} instructions 2017-08-09 16:53:56 -07:00
test_firmware.c test_firmware: add test custom fallback trigger 2017-01-25 11:52:34 +01:00
test_hash.c lib/test_hash.c: fix warning in preprocessor symbol evaluation 2016-09-01 17:52:01 -07:00
test_hexdump.c
test_kasan.c kasan: report only the first error by default 2017-03-31 17:13:30 -07:00
test_kmod.c kmod: add test driver to stress test the module loader 2017-07-14 15:05:13 -07:00
test_list_sort.c lib: add module support to linked list sorting tests 2017-05-08 17:15:10 -07:00
test_module.c
test_parman.c lib: fix spelling mistake: "actualy" -> "actually" 2017-02-26 11:03:38 -05:00
test_printf.c mm, printk: introduce new format string for flags 2016-03-15 16:55:16 -07:00
test_rhashtable.c lib: test_rhashtable: Fix KASAN warning 2017-07-25 12:35:23 -07:00
test_siphash.c siphash: implement HalfSipHash1-3 for hash tables 2017-01-09 13:58:57 -05:00
test_sort.c Revert "lib/test_sort.c: make it explicitly non-modular" 2017-05-08 17:15:10 -07:00
test_static_key_base.c
test_static_keys.c
test_sysctl.c test_sysctl: test against int proc_dointvec() array support 2017-07-12 16:26:00 -07:00
test_user_copy.c lib: remove check for AVR32 arch in test_user_copy 2017-05-01 09:36:30 +02:00
test_uuid.c uuid: fix incorrect uuid_equal conversion in test_uuid_test 2017-07-21 09:38:30 +02:00
test-kstrtox.c
test-string_helpers.c
textsearch.c
timerqueue.c timerqueue: Use rb_entry_safe() instead of open-coding it 2017-01-20 08:03:42 +01:00
ts_bm.c
ts_fsm.c
ts_kmp.c
ubsan.c UBSAN: fix typo in format string 2016-08-02 17:31:41 -04:00
ubsan.h
ucs2_string.c lib/ucs2_string: Speed up ucs2_utf8size() 2016-09-09 16:08:46 +01:00
usercopy.c copy_{from,to}_user(): move kasan checks and might_fault() out-of-line 2017-06-29 22:21:20 -04:00
uuid.c uuid: hoist uuid_is_null() helper from libnvdimm 2017-06-05 16:59:05 +02:00
vsprintf.c DeviceTree for 4.13: 2017-07-07 10:37:54 -07:00
win_minmax.c lib/win_minmax: windowed min or max estimator 2016-09-21 00:22:59 -04:00