maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/clang/test/CodeGen/builtins-bpf-preserve-field...

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

27 lines
1.6 KiB
C
Raw Normal View History

[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
2019-10-09 02:23:17 +08:00
// REQUIRES: bpf-registered-target
BPF: move AbstractMemberAccess and PreserveDIType passes to EP_EarlyAsPossible Move abstractMemberAccess and PreserveDIType passes as early as possible, right after clang code generation. Currently, compiler may transform the above code p1 = llvm.bpf.builtin.preserve.struct.access(base, 0, 0); p2 = llvm.bpf.builtin.preserve.struct.access(p1, 1, 2); a = llvm.bpf.builtin.preserve_field_info(p2, EXIST); if (a) { p1 = llvm.bpf.builtin.preserve.struct.access(base, 0, 0); p2 = llvm.bpf.builtin.preserve.struct.access(p1, 1, 2); bpf_probe_read(buf, buf_size, p2); } to p1 = llvm.bpf.builtin.preserve.struct.access(base, 0, 0); p2 = llvm.bpf.builtin.preserve.struct.access(p1, 1, 2); a = llvm.bpf.builtin.preserve_field_info(p2, EXIST); if (a) { bpf_probe_read(buf, buf_size, p2); } and eventually assembly code looks like reloc_exist = 1; reloc_member_offset = 10; //calculate member offset from base p2 = base + reloc_member_offset; if (reloc_exist) { bpf_probe_read(bpf, buf_size, p2); } if during libbpf relocation resolution, reloc_exist is actually resolved to 0 (not exist), reloc_member_offset relocation cannot be resolved and will be patched with illegal instruction. This will cause verifier failure. This patch attempts to address this issue by do chaining analysis and replace chains with special globals right after clang code gen. This will remove the cse possibility described in the above. The IR typically looks like %6 = load @llvm.sk_buff:0:50$0:0:0:2:0 %7 = bitcast %struct.sk_buff* %2 to i8* %8 = getelementptr i8, i8* %7, %6 for a particular address computation relocation. But this transformation has another consequence, code sinking may happen like below: PHI = <possibly different @preserve_*_access_globals> %7 = bitcast %struct.sk_buff* %2 to i8* %8 = getelementptr i8, i8* %7, %6 For such cases, we will not able to generate relocations since multiple relocations are merged into one. This patch introduced a passthrough builtin to prevent such optimization. Looks like inline assembly has more impact for optimizaiton, e.g., inlining. Using passthrough has less impact on optimizations. A new IR pass is introduced at the beginning of target-dependent IR optimization, which does: - report fatal error if any reloc global in PHI nodes - remove all bpf passthrough builtin functions Changes for existing CORE tests: - for clang tests, add "-Xclang -disable-llvm-passes" flags to avoid builtin->reloc_global transformation so the test is still able to check correctness for clang generated IR. - for llvm CodeGen/BPF tests, add "opt -O2 <ir_file> | llvm-dis" command before "llc" command since "opt" is needed to call newly-placed builtin->reloc_global transformation. Add target triple in the IR file since "opt" requires it. - Since target triple is added in IR file, if a test may produce different results for different endianness, two tests will be created, one for bpfeb and another for bpfel, e.g., some tests for relocation of lshift/rshift of bitfields. - field-reloc-bitfield-1.ll has different relocations compared to old codes. This is because for the structure in the test, new code returns struct layout alignment 4 while old code is 8. Align 8 is more precise and permits double load. With align 4, the new mechanism uses 4-byte load, so generating different relocations. - test intrinsic-transforms.ll is removed. This is used to test cse on intrinsics so we do not lose metadata. Now metadata is attached to global and not instruction, it won't get lost with cse. Differential Revision: https://reviews.llvm.org/D87153
2020-09-03 13:56:41 +08:00
// RUN: %clang -target bpf -emit-llvm -S -g -Xclang -disable-llvm-passes %s -o - | FileCheck %s
[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
2019-10-09 02:23:17 +08:00
#define _(x, y) (__builtin_preserve_field_info((x), (y)))
struct s1 {
char a;
char b:2;
};
struct s2 {
struct s1 s;
};
unsigned unit1(struct s2 *arg) {
return _(arg->s.a, 10) + _(arg->s.b, 10);
}
// CHECK: define dso_local i32 @unit1
[BPF] Use elementtype attribute for preserve.array/struct.index intrinsics Use the elementtype attribute introduced in D105407 for the llvm.preserve.array/struct.index intrinsics. It carries the element type of the GEP these intrinsics effectively encode. This patch: * Adds a verifier check that the attribute is required. * Adds it in the IRBuilder methods for these intrinsics. * Autoupgrades old bitcode without the attribute. * Updates the lowering code to use the attribute rather than the pointer element type. * Updates lots of tests to specify the attribute. * Adds -force-opaque-pointers to the intrinsic-array.ll test to demonstrate they work now. https://reviews.llvm.org/D106184
2021-07-17 02:26:40 +08:00
// CHECK: call %struct.s1* @llvm.preserve.struct.access.index.p0s_struct.s1s.p0s_struct.s2s(%struct.s2* elementtype(%struct.s2) %{{[0-9a-z]+}}, i32 0, i32 0), !dbg !{{[0-9]+}}, !llvm.preserve.access.index ![[STRUCT_S2:[0-9]+]]
// CHECK: call i8* @llvm.preserve.struct.access.index.p0i8.p0s_struct.s1s(%struct.s1* elementtype(%struct.s1) %{{[0-9a-z]+}}, i32 0, i32 0), !dbg !{{[0-9]+}}, !llvm.preserve.access.index ![[STRUCT_S1:[0-9]+]]
[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
2019-10-09 02:23:17 +08:00
// CHECK: call i32 @llvm.bpf.preserve.field.info.p0i8(i8* %{{[0-9a-z]+}}, i64 10), !dbg !{{[0-9]+}}
[BPF] Use elementtype attribute for preserve.array/struct.index intrinsics Use the elementtype attribute introduced in D105407 for the llvm.preserve.array/struct.index intrinsics. It carries the element type of the GEP these intrinsics effectively encode. This patch: * Adds a verifier check that the attribute is required. * Adds it in the IRBuilder methods for these intrinsics. * Autoupgrades old bitcode without the attribute. * Updates the lowering code to use the attribute rather than the pointer element type. * Updates lots of tests to specify the attribute. * Adds -force-opaque-pointers to the intrinsic-array.ll test to demonstrate they work now. https://reviews.llvm.org/D106184
2021-07-17 02:26:40 +08:00
// CHECK: call %struct.s1* @llvm.preserve.struct.access.index.p0s_struct.s1s.p0s_struct.s2s(%struct.s2* elementtype(%struct.s2) %{{[0-9a-z]+}}, i32 0, i32 0), !dbg !{{[0-9]+}}, !llvm.preserve.access.index ![[STRUCT_S2:[0-9]+]]
// CHECK: call i8* @llvm.preserve.struct.access.index.p0i8.p0s_struct.s1s(%struct.s1* elementtype(%struct.s1) %{{[0-9a-z]+}}, i32 1, i32 1), !dbg !{{[0-9]+}}, !llvm.preserve.access.index ![[STRUCT_S1:[0-9]+]]
[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
2019-10-09 02:23:17 +08:00
// CHECK: call i32 @llvm.bpf.preserve.field.info.p0i8(i8* %{{[0-9a-z]+}}, i64 10), !dbg !{{[0-9]+}}
// CHECK: ![[STRUCT_S2]] = distinct !DICompositeType(tag: DW_TAG_structure_type, name: "s2"
// CHECK: ![[STRUCT_S1]] = distinct !DICompositeType(tag: DW_TAG_structure_type, name: "s1"