1 Commits

Author	SHA1	Message	Date
Yonghong Song	05e46979d2	[BPF] do compile-once run-everywhere relocation for bitfields ... A bpf specific clang intrinsic is introduced: u32 __builtin_preserve_field_info(member_access, info_kind) Depending on info_kind, different information will be returned to the program. A relocation is also recorded for this builtin so that bpf loader can patch the instruction on the target host. This clang intrinsic is used to get certain information to facilitate struct/union member relocations. The offset relocation is extended by 4 bytes to include relocation kind. Currently supported relocation kinds are enum { FIELD_BYTE_OFFSET = 0, FIELD_BYTE_SIZE, FIELD_EXISTENCE, FIELD_SIGNEDNESS, FIELD_LSHIFT_U64, FIELD_RSHIFT_U64, }; for __builtin_preserve_field_info. The old access offset relocation is covered by FIELD_BYTE_OFFSET = 0. An example: struct s { int a; int b1:9; int b2:4; }; enum { FIELD_BYTE_OFFSET = 0, FIELD_BYTE_SIZE, FIELD_EXISTENCE, FIELD_SIGNEDNESS, FIELD_LSHIFT_U64, FIELD_RSHIFT_U64, }; void bpf_probe_read(void *, unsigned, const void *); int field_read(struct s *arg) { unsigned long long ull = 0; unsigned offset = __builtin_preserve_field_info(arg->b2, FIELD_BYTE_OFFSET); unsigned size = __builtin_preserve_field_info(arg->b2, FIELD_BYTE_SIZE); #ifdef USE_PROBE_READ bpf_probe_read(&ull, size, (const void *)arg + offset); unsigned lshift = __builtin_preserve_field_info(arg->b2, FIELD_LSHIFT_U64); #if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ lshift = lshift + (size << 3) - 64; #endif #else switch(size) { case 1: ull = *(unsigned char *)((void *)arg + offset); break; case 2: ull = *(unsigned short *)((void *)arg + offset); break; case 4: ull = *(unsigned int *)((void *)arg + offset); break; case 8: ull = *(unsigned long long *)((void *)arg + offset); break; } unsigned lshift = __builtin_preserve_field_info(arg->b2, FIELD_LSHIFT_U64); #endif ull <<= lshift; if (__builtin_preserve_field_info(arg->b2, FIELD_SIGNEDNESS)) return (long long)ull >> __builtin_preserve_field_info(arg->b2, FIELD_RSHIFT_U64); return ull >> __builtin_preserve_field_info(arg->b2, FIELD_RSHIFT_U64); } There is a minor overhead for bpf_probe_read() on big endian. The code and relocation generated for field_read where bpf_probe_read() is used to access argument data on little endian mode: r3 = r1 r1 = 0 r1 = 4 <=== relocation (FIELD_BYTE_OFFSET) r3 += r1 r1 = r10 r1 += -8 r2 = 4 <=== relocation (FIELD_BYTE_SIZE) call bpf_probe_read r2 = 51 <=== relocation (FIELD_LSHIFT_U64) r1 = *(u64 *)(r10 - 8) r1 <<= r2 r2 = 60 <=== relocation (FIELD_RSHIFT_U64) r0 = r1 r0 >>= r2 r3 = 1 <=== relocation (FIELD_SIGNEDNESS) if r3 == 0 goto LBB0_2 r1 s>>= r2 r0 = r1 LBB0_2: exit Compare to the above code between relocations FIELD_LSHIFT_U64 and FIELD_LSHIFT_U64, the code with big endian mode has four more instructions. r1 = 41 <=== relocation (FIELD_LSHIFT_U64) r6 += r1 r6 += -64 r6 <<= 32 r6 >>= 32 r1 = *(u64 *)(r10 - 8) r1 <<= r6 r2 = 60 <=== relocation (FIELD_RSHIFT_U64) The code and relocation generated when using direct load. r2 = 0 r3 = 4 r4 = 4 if r4 s> 3 goto LBB0_3 if r4 == 1 goto LBB0_5 if r4 == 2 goto LBB0_6 goto LBB0_9 LBB0_6: # %sw.bb1 r1 += r3 r2 = *(u16 *)(r1 + 0) goto LBB0_9 LBB0_3: # %entry if r4 == 4 goto LBB0_7 if r4 == 8 goto LBB0_8 goto LBB0_9 LBB0_8: # %sw.bb9 r1 += r3 r2 = *(u64 *)(r1 + 0) goto LBB0_9 LBB0_5: # %sw.bb r1 += r3 r2 = *(u8 *)(r1 + 0) goto LBB0_9 LBB0_7: # %sw.bb5 r1 += r3 r2 = *(u32 *)(r1 + 0) LBB0_9: # %sw.epilog r1 = 51 r2 <<= r1 r1 = 60 r0 = r2 r0 >>= r1 r3 = 1 if r3 == 0 goto LBB0_11 r2 s>>= r1 r0 = r2 LBB0_11: # %sw.epilog exit Considering verifier is able to do limited constant propogation following branches. The following is the code actually traversed. r2 = 0 r3 = 4 <=== relocation r4 = 4 <=== relocation if r4 s> 3 goto LBB0_3 LBB0_3: # %entry if r4 == 4 goto LBB0_7 LBB0_7: # %sw.bb5 r1 += r3 r2 = *(u32 *)(r1 + 0) LBB0_9: # %sw.epilog r1 = 51 <=== relocation r2 <<= r1 r1 = 60 <=== relocation r0 = r2 r0 >>= r1 r3 = 1 if r3 == 0 goto LBB0_11 r2 s>>= r1 r0 = r2 LBB0_11: # %sw.epilog exit For native load case, the load size is calculated to be the same as the size of load width LLVM otherwise used to load the value which is then used to extract the bitfield value. Differential Revision: https://reviews.llvm.org/D67980 llvm-svn: 374099	2019-10-08 18:23:17 +00:00