mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-24 09:50:04 +00:00
92b31a9af7
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> |
||
|---|---|---|
| .. | ||
| 842 | ||
| fonts | ||
| lz4 | ||
| lzo | ||
| mpi | ||
| raid6 | ||
| reed_solomon | ||
| xz | ||
| zlib_deflate | ||
| zlib_inflate | ||
| .gitignore | ||
| argv_split.c | ||
| asn1_decoder.c | ||
| assoc_array.c | ||
| atomic64.c | ||
| atomic64_test.c | ||
| audit.c | ||
| bcd.c | ||
| bch.c | ||
| bitmap.c | ||
| bitrev.c | ||
| bsearch.c | ||
| btree.c | ||
| bug.c | ||
| build_OID_registry | ||
| bust_spinlocks.c | ||
| chacha20.c | ||
| check_signature.c | ||
| checksum.c | ||
| clz_ctz.c | ||
| clz_tab.c | ||
| cmdline.c | ||
| compat_audit.c | ||
| cordic.c | ||
| cpu_rmap.c | ||
| cpumask.c | ||
| crc-ccitt.c | ||
| crc-itu-t.c | ||
| crc-t10dif.c | ||
| crc4.c | ||
| crc7.c | ||
| crc8.c | ||
| crc16.c | ||
| crc32.c | ||
| crc32defs.h | ||
| crc32test.c | ||
| ctype.c | ||
| debug_info.c | ||
| debug_locks.c | ||
| debugobjects.c | ||
| dec_and_lock.c | ||
| decompress.c | ||
| decompress_bunzip2.c | ||
| decompress_inflate.c | ||
| decompress_unlz4.c | ||
| decompress_unlzma.c | ||
| decompress_unlzo.c | ||
| decompress_unxz.c | ||
| devres.c | ||
| digsig.c | ||
| div64.c | ||
| dma-debug.c | ||
| dma-noop.c | ||
| dma-virt.c | ||
| dump_stack.c | ||
| dynamic_debug.c | ||
| dynamic_queue_limits.c | ||
| earlycpio.c | ||
| errseq.c | ||
| extable.c | ||
| fault-inject.c | ||
| fdt.c | ||
| fdt_empty_tree.c | ||
| fdt_ro.c | ||
| fdt_rw.c | ||
| fdt_strerror.c | ||
| fdt_sw.c | ||
| fdt_wip.c | ||
| find_bit.c | ||
| flex_array.c | ||
| flex_proportions.c | ||
| gcd.c | ||
| gen_crc32table.c | ||
| genalloc.c | ||
| glob.c | ||
| globtest.c | ||
| hexdump.c | ||
| hweight.c | ||
| idr.c | ||
| inflate.c | ||
| int_sqrt.c | ||
| interval_tree.c | ||
| interval_tree_test.c | ||
| iomap.c | ||
| iomap_copy.c | ||
| iommu-common.c | ||
| iommu-helper.c | ||
| ioremap.c | ||
| iov_iter.c | ||
| irq_poll.c | ||
| irq_regs.c | ||
| is_single_threaded.c | ||
| jedec_ddr_data.c | ||
| kasprintf.c | ||
| Kconfig | ||
| Kconfig.debug | ||
| Kconfig.kasan | ||
| Kconfig.kgdb | ||
| Kconfig.kmemcheck | ||
| Kconfig.ubsan | ||
| kfifo.c | ||
| klist.c | ||
| kobject.c | ||
| kobject_uevent.c | ||
| kstrtox.c | ||
| kstrtox.h | ||
| lcm.c | ||
| libcrc32c.c | ||
| list_debug.c | ||
| list_sort.c | ||
| 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-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 | ||
| lockref.c | ||
| lru_cache.c | ||
| Makefile | ||
| memory-notifier-error-inject.c | ||
| memweight.c | ||
| net_utils.c | ||
| netdev-notifier-error-inject.c | ||
| nlattr.c | ||
| nmi_backtrace.c | ||
| nodemask.c | ||
| notifier-error-inject.c | ||
| notifier-error-inject.h | ||
| of-reconfig-notifier-error-inject.c | ||
| oid_registry.c | ||
| once.c | ||
| parman.c | ||
| parser.c | ||
| pci_iomap.c | ||
| percpu-refcount.c | ||
| percpu_counter.c | ||
| percpu_ida.c | ||
| percpu_test.c | ||
| plist.c | ||
| pm-notifier-error-inject.c | ||
| prime_numbers.c | ||
| radix-tree.c | ||
| random32.c | ||
| ratelimit.c | ||
| rational.c | ||
| rbtree.c | ||
| rbtree_test.c | ||
| reciprocal_div.c | ||
| refcount.c | ||
| rhashtable.c | ||
| sbitmap.c | ||
| scatterlist.c | ||
| seq_buf.c | ||
| sg_pool.c | ||
| sg_split.c | ||
| sha1.c | ||
| show_mem.c | ||
| siphash.c | ||
| smp_processor_id.c | ||
| sort.c | ||
| stackdepot.c | ||
| stmp_device.c | ||
| string.c | ||
| string_helpers.c | ||
| strncpy_from_user.c | ||
| strnlen_user.c | ||
| swiotlb.c | ||
| syscall.c | ||
| test-kstrtox.c | ||
| test-string_helpers.c | ||
| test_bitmap.c | ||
| test_bpf.c | ||
| test_firmware.c | ||
| test_hash.c | ||
| test_hexdump.c | ||
| test_kasan.c | ||
| test_kmod.c | ||
| test_list_sort.c | ||
| test_module.c | ||
| test_parman.c | ||
| test_printf.c | ||
| test_rhashtable.c | ||
| test_siphash.c | ||
| test_sort.c | ||
| test_static_key_base.c | ||
| test_static_keys.c | ||
| test_sysctl.c | ||
| test_user_copy.c | ||
| test_uuid.c | ||
| textsearch.c | ||
| timerqueue.c | ||
| ts_bm.c | ||
| ts_fsm.c | ||
| ts_kmp.c | ||
| ubsan.c | ||
| ubsan.h | ||
| ucs2_string.c | ||
| usercopy.c | ||
| uuid.c | ||
| vsprintf.c | ||
| win_minmax.c | ||