2018-12-20 00:40:25 +08:00
|
|
|
//===- BTFDebug.cpp - BTF Generator ---------------------------------------===//
|
|
|
|
//
|
2019-01-19 16:50:56 +08:00
|
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
2018-12-20 00:40:25 +08:00
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//
|
|
|
|
// This file contains support for writing BTF debug info.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
|
|
#include "BTFDebug.h"
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
#include "BPF.h"
|
|
|
|
#include "BPFCORE.h"
|
|
|
|
#include "MCTargetDesc/BPFMCTargetDesc.h"
|
2018-12-20 00:40:25 +08:00
|
|
|
#include "llvm/BinaryFormat/ELF.h"
|
|
|
|
#include "llvm/CodeGen/AsmPrinter.h"
|
|
|
|
#include "llvm/CodeGen/MachineModuleInfo.h"
|
|
|
|
#include "llvm/MC/MCContext.h"
|
|
|
|
#include "llvm/MC/MCObjectFileInfo.h"
|
|
|
|
#include "llvm/MC/MCSectionELF.h"
|
|
|
|
#include "llvm/MC/MCStreamer.h"
|
2019-04-03 00:15:46 +08:00
|
|
|
#include "llvm/Support/LineIterator.h"
|
2018-12-20 00:40:25 +08:00
|
|
|
|
|
|
|
using namespace llvm;
|
|
|
|
|
|
|
|
static const char *BTFKindStr[] = {
|
|
|
|
#define HANDLE_BTF_KIND(ID, NAME) "BTF_KIND_" #NAME,
|
|
|
|
#include "BTF.def"
|
|
|
|
};
|
|
|
|
|
|
|
|
/// Emit a BTF common type.
|
|
|
|
void BTFTypeBase::emitType(MCStreamer &OS) {
|
|
|
|
OS.AddComment(std::string(BTFKindStr[Kind]) + "(id = " + std::to_string(Id) +
|
|
|
|
")");
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(BTFType.NameOff);
|
2018-12-20 00:40:25 +08:00
|
|
|
OS.AddComment("0x" + Twine::utohexstr(BTFType.Info));
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(BTFType.Info);
|
|
|
|
OS.emitInt32(BTFType.Size);
|
2018-12-20 00:40:25 +08:00
|
|
|
}
|
|
|
|
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
BTFTypeDerived::BTFTypeDerived(const DIDerivedType *DTy, unsigned Tag,
|
|
|
|
bool NeedsFixup)
|
|
|
|
: DTy(DTy), NeedsFixup(NeedsFixup) {
|
2018-12-20 00:40:25 +08:00
|
|
|
switch (Tag) {
|
|
|
|
case dwarf::DW_TAG_pointer_type:
|
|
|
|
Kind = BTF::BTF_KIND_PTR;
|
|
|
|
break;
|
|
|
|
case dwarf::DW_TAG_const_type:
|
|
|
|
Kind = BTF::BTF_KIND_CONST;
|
|
|
|
break;
|
|
|
|
case dwarf::DW_TAG_volatile_type:
|
|
|
|
Kind = BTF::BTF_KIND_VOLATILE;
|
|
|
|
break;
|
|
|
|
case dwarf::DW_TAG_typedef:
|
|
|
|
Kind = BTF::BTF_KIND_TYPEDEF;
|
|
|
|
break;
|
|
|
|
case dwarf::DW_TAG_restrict_type:
|
|
|
|
Kind = BTF::BTF_KIND_RESTRICT;
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
llvm_unreachable("Unknown DIDerivedType Tag");
|
|
|
|
}
|
|
|
|
BTFType.Info = Kind << 24;
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFTypeDerived::completeType(BTFDebug &BDebug) {
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
if (IsCompleted)
|
|
|
|
return;
|
|
|
|
IsCompleted = true;
|
|
|
|
|
2018-12-20 00:40:25 +08:00
|
|
|
BTFType.NameOff = BDebug.addString(DTy->getName());
|
|
|
|
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
if (NeedsFixup)
|
|
|
|
return;
|
|
|
|
|
2018-12-20 00:40:25 +08:00
|
|
|
// The base type for PTR/CONST/VOLATILE could be void.
|
2019-05-07 10:06:37 +08:00
|
|
|
const DIType *ResolvedType = DTy->getBaseType();
|
2018-12-20 00:40:25 +08:00
|
|
|
if (!ResolvedType) {
|
|
|
|
assert((Kind == BTF::BTF_KIND_PTR || Kind == BTF::BTF_KIND_CONST ||
|
|
|
|
Kind == BTF::BTF_KIND_VOLATILE) &&
|
|
|
|
"Invalid null basetype");
|
|
|
|
BTFType.Type = 0;
|
|
|
|
} else {
|
|
|
|
BTFType.Type = BDebug.getTypeId(ResolvedType);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFTypeDerived::emitType(MCStreamer &OS) { BTFTypeBase::emitType(OS); }
|
|
|
|
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
void BTFTypeDerived::setPointeeType(uint32_t PointeeType) {
|
|
|
|
BTFType.Type = PointeeType;
|
|
|
|
}
|
|
|
|
|
2018-12-20 00:40:25 +08:00
|
|
|
/// Represent a struct/union forward declaration.
|
|
|
|
BTFTypeFwd::BTFTypeFwd(StringRef Name, bool IsUnion) : Name(Name) {
|
|
|
|
Kind = BTF::BTF_KIND_FWD;
|
|
|
|
BTFType.Info = IsUnion << 31 | Kind << 24;
|
|
|
|
BTFType.Type = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFTypeFwd::completeType(BTFDebug &BDebug) {
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
if (IsCompleted)
|
|
|
|
return;
|
|
|
|
IsCompleted = true;
|
|
|
|
|
2018-12-20 00:40:25 +08:00
|
|
|
BTFType.NameOff = BDebug.addString(Name);
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFTypeFwd::emitType(MCStreamer &OS) { BTFTypeBase::emitType(OS); }
|
|
|
|
|
|
|
|
BTFTypeInt::BTFTypeInt(uint32_t Encoding, uint32_t SizeInBits,
|
|
|
|
uint32_t OffsetInBits, StringRef TypeName)
|
|
|
|
: Name(TypeName) {
|
|
|
|
// Translate IR int encoding to BTF int encoding.
|
|
|
|
uint8_t BTFEncoding;
|
|
|
|
switch (Encoding) {
|
|
|
|
case dwarf::DW_ATE_boolean:
|
|
|
|
BTFEncoding = BTF::INT_BOOL;
|
|
|
|
break;
|
|
|
|
case dwarf::DW_ATE_signed:
|
|
|
|
case dwarf::DW_ATE_signed_char:
|
|
|
|
BTFEncoding = BTF::INT_SIGNED;
|
|
|
|
break;
|
|
|
|
case dwarf::DW_ATE_unsigned:
|
|
|
|
case dwarf::DW_ATE_unsigned_char:
|
|
|
|
BTFEncoding = 0;
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
llvm_unreachable("Unknown BTFTypeInt Encoding");
|
|
|
|
}
|
|
|
|
|
|
|
|
Kind = BTF::BTF_KIND_INT;
|
|
|
|
BTFType.Info = Kind << 24;
|
|
|
|
BTFType.Size = roundupToBytes(SizeInBits);
|
|
|
|
IntVal = (BTFEncoding << 24) | OffsetInBits << 16 | SizeInBits;
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFTypeInt::completeType(BTFDebug &BDebug) {
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
if (IsCompleted)
|
|
|
|
return;
|
|
|
|
IsCompleted = true;
|
|
|
|
|
2018-12-20 00:40:25 +08:00
|
|
|
BTFType.NameOff = BDebug.addString(Name);
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFTypeInt::emitType(MCStreamer &OS) {
|
|
|
|
BTFTypeBase::emitType(OS);
|
|
|
|
OS.AddComment("0x" + Twine::utohexstr(IntVal));
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(IntVal);
|
2018-12-20 00:40:25 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
BTFTypeEnum::BTFTypeEnum(const DICompositeType *ETy, uint32_t VLen) : ETy(ETy) {
|
|
|
|
Kind = BTF::BTF_KIND_ENUM;
|
|
|
|
BTFType.Info = Kind << 24 | VLen;
|
|
|
|
BTFType.Size = roundupToBytes(ETy->getSizeInBits());
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFTypeEnum::completeType(BTFDebug &BDebug) {
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
if (IsCompleted)
|
|
|
|
return;
|
|
|
|
IsCompleted = true;
|
|
|
|
|
2018-12-20 00:40:25 +08:00
|
|
|
BTFType.NameOff = BDebug.addString(ETy->getName());
|
|
|
|
|
|
|
|
DINodeArray Elements = ETy->getElements();
|
|
|
|
for (const auto Element : Elements) {
|
|
|
|
const auto *Enum = cast<DIEnumerator>(Element);
|
|
|
|
|
|
|
|
struct BTF::BTFEnum BTFEnum;
|
|
|
|
BTFEnum.NameOff = BDebug.addString(Enum->getName());
|
|
|
|
// BTF enum value is 32bit, enforce it.
|
|
|
|
BTFEnum.Val = static_cast<uint32_t>(Enum->getValue());
|
|
|
|
EnumValues.push_back(BTFEnum);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFTypeEnum::emitType(MCStreamer &OS) {
|
|
|
|
BTFTypeBase::emitType(OS);
|
|
|
|
for (const auto &Enum : EnumValues) {
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(Enum.NameOff);
|
|
|
|
OS.emitInt32(Enum.Val);
|
2018-12-20 00:40:25 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2019-08-03 07:16:44 +08:00
|
|
|
BTFTypeArray::BTFTypeArray(uint32_t ElemTypeId, uint32_t NumElems) {
|
2018-12-20 00:40:25 +08:00
|
|
|
Kind = BTF::BTF_KIND_ARRAY;
|
2019-03-29 05:59:49 +08:00
|
|
|
BTFType.NameOff = 0;
|
2018-12-20 00:40:25 +08:00
|
|
|
BTFType.Info = Kind << 24;
|
2019-03-29 05:59:49 +08:00
|
|
|
BTFType.Size = 0;
|
|
|
|
|
|
|
|
ArrayInfo.ElemType = ElemTypeId;
|
|
|
|
ArrayInfo.Nelems = NumElems;
|
2018-12-20 00:40:25 +08:00
|
|
|
}
|
|
|
|
|
2019-03-29 05:59:49 +08:00
|
|
|
/// Represent a BTF array.
|
2018-12-20 00:40:25 +08:00
|
|
|
void BTFTypeArray::completeType(BTFDebug &BDebug) {
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
if (IsCompleted)
|
|
|
|
return;
|
|
|
|
IsCompleted = true;
|
2018-12-20 00:40:25 +08:00
|
|
|
|
|
|
|
// The IR does not really have a type for the index.
|
|
|
|
// A special type for array index should have been
|
|
|
|
// created during initial type traversal. Just
|
|
|
|
// retrieve that type id.
|
|
|
|
ArrayInfo.IndexType = BDebug.getArrayIndexTypeId();
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFTypeArray::emitType(MCStreamer &OS) {
|
|
|
|
BTFTypeBase::emitType(OS);
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(ArrayInfo.ElemType);
|
|
|
|
OS.emitInt32(ArrayInfo.IndexType);
|
|
|
|
OS.emitInt32(ArrayInfo.Nelems);
|
2018-12-20 00:40:25 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/// Represent either a struct or a union.
|
|
|
|
BTFTypeStruct::BTFTypeStruct(const DICompositeType *STy, bool IsStruct,
|
|
|
|
bool HasBitField, uint32_t Vlen)
|
|
|
|
: STy(STy), HasBitField(HasBitField) {
|
|
|
|
Kind = IsStruct ? BTF::BTF_KIND_STRUCT : BTF::BTF_KIND_UNION;
|
|
|
|
BTFType.Size = roundupToBytes(STy->getSizeInBits());
|
|
|
|
BTFType.Info = (HasBitField << 31) | (Kind << 24) | Vlen;
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFTypeStruct::completeType(BTFDebug &BDebug) {
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
if (IsCompleted)
|
|
|
|
return;
|
|
|
|
IsCompleted = true;
|
|
|
|
|
2018-12-20 00:40:25 +08:00
|
|
|
BTFType.NameOff = BDebug.addString(STy->getName());
|
|
|
|
|
|
|
|
// Add struct/union members.
|
|
|
|
const DINodeArray Elements = STy->getElements();
|
|
|
|
for (const auto *Element : Elements) {
|
|
|
|
struct BTF::BTFMember BTFMember;
|
|
|
|
const auto *DDTy = cast<DIDerivedType>(Element);
|
|
|
|
|
|
|
|
BTFMember.NameOff = BDebug.addString(DDTy->getName());
|
|
|
|
if (HasBitField) {
|
|
|
|
uint8_t BitFieldSize = DDTy->isBitField() ? DDTy->getSizeInBits() : 0;
|
|
|
|
BTFMember.Offset = BitFieldSize << 24 | DDTy->getOffsetInBits();
|
|
|
|
} else {
|
|
|
|
BTFMember.Offset = DDTy->getOffsetInBits();
|
|
|
|
}
|
2019-07-26 05:47:27 +08:00
|
|
|
const auto *BaseTy = DDTy->getBaseType();
|
|
|
|
BTFMember.Type = BDebug.getTypeId(BaseTy);
|
2018-12-20 00:40:25 +08:00
|
|
|
Members.push_back(BTFMember);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFTypeStruct::emitType(MCStreamer &OS) {
|
|
|
|
BTFTypeBase::emitType(OS);
|
|
|
|
for (const auto &Member : Members) {
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(Member.NameOff);
|
|
|
|
OS.emitInt32(Member.Type);
|
2018-12-20 00:40:25 +08:00
|
|
|
OS.AddComment("0x" + Twine::utohexstr(Member.Offset));
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(Member.Offset);
|
2018-12-20 00:40:25 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-01-29 03:23:46 +08:00
|
|
|
std::string BTFTypeStruct::getName() { return std::string(STy->getName()); }
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
|
2018-12-20 00:40:25 +08:00
|
|
|
/// The Func kind represents both subprogram and pointee of function
|
|
|
|
/// pointers. If the FuncName is empty, it represents a pointee of function
|
|
|
|
/// pointer. Otherwise, it represents a subprogram. The func arg names
|
|
|
|
/// are empty for pointee of function pointer case, and are valid names
|
|
|
|
/// for subprogram.
|
|
|
|
BTFTypeFuncProto::BTFTypeFuncProto(
|
|
|
|
const DISubroutineType *STy, uint32_t VLen,
|
|
|
|
const std::unordered_map<uint32_t, StringRef> &FuncArgNames)
|
|
|
|
: STy(STy), FuncArgNames(FuncArgNames) {
|
|
|
|
Kind = BTF::BTF_KIND_FUNC_PROTO;
|
|
|
|
BTFType.Info = (Kind << 24) | VLen;
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFTypeFuncProto::completeType(BTFDebug &BDebug) {
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
if (IsCompleted)
|
|
|
|
return;
|
|
|
|
IsCompleted = true;
|
|
|
|
|
2018-12-20 00:40:25 +08:00
|
|
|
DITypeRefArray Elements = STy->getTypeArray();
|
2019-05-07 10:06:37 +08:00
|
|
|
auto RetType = Elements[0];
|
2018-12-20 00:40:25 +08:00
|
|
|
BTFType.Type = RetType ? BDebug.getTypeId(RetType) : 0;
|
|
|
|
BTFType.NameOff = 0;
|
|
|
|
|
|
|
|
// For null parameter which is typically the last one
|
|
|
|
// to represent the vararg, encode the NameOff/Type to be 0.
|
|
|
|
for (unsigned I = 1, N = Elements.size(); I < N; ++I) {
|
|
|
|
struct BTF::BTFParam Param;
|
2019-05-07 10:06:37 +08:00
|
|
|
auto Element = Elements[I];
|
2018-12-20 00:40:25 +08:00
|
|
|
if (Element) {
|
|
|
|
Param.NameOff = BDebug.addString(FuncArgNames[I]);
|
|
|
|
Param.Type = BDebug.getTypeId(Element);
|
|
|
|
} else {
|
|
|
|
Param.NameOff = 0;
|
|
|
|
Param.Type = 0;
|
|
|
|
}
|
|
|
|
Parameters.push_back(Param);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFTypeFuncProto::emitType(MCStreamer &OS) {
|
|
|
|
BTFTypeBase::emitType(OS);
|
|
|
|
for (const auto &Param : Parameters) {
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(Param.NameOff);
|
|
|
|
OS.emitInt32(Param.Type);
|
2018-12-20 00:40:25 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2019-12-18 08:24:23 +08:00
|
|
|
BTFTypeFunc::BTFTypeFunc(StringRef FuncName, uint32_t ProtoTypeId,
|
|
|
|
uint32_t Scope)
|
2018-12-20 00:40:25 +08:00
|
|
|
: Name(FuncName) {
|
|
|
|
Kind = BTF::BTF_KIND_FUNC;
|
2019-12-18 08:24:23 +08:00
|
|
|
BTFType.Info = (Kind << 24) | Scope;
|
2018-12-20 00:40:25 +08:00
|
|
|
BTFType.Type = ProtoTypeId;
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFTypeFunc::completeType(BTFDebug &BDebug) {
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
if (IsCompleted)
|
|
|
|
return;
|
|
|
|
IsCompleted = true;
|
|
|
|
|
2018-12-20 00:40:25 +08:00
|
|
|
BTFType.NameOff = BDebug.addString(Name);
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFTypeFunc::emitType(MCStreamer &OS) { BTFTypeBase::emitType(OS); }
|
|
|
|
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
BTFKindVar::BTFKindVar(StringRef VarName, uint32_t TypeId, uint32_t VarInfo)
|
|
|
|
: Name(VarName) {
|
|
|
|
Kind = BTF::BTF_KIND_VAR;
|
|
|
|
BTFType.Info = Kind << 24;
|
|
|
|
BTFType.Type = TypeId;
|
|
|
|
Info = VarInfo;
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFKindVar::completeType(BTFDebug &BDebug) {
|
|
|
|
BTFType.NameOff = BDebug.addString(Name);
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFKindVar::emitType(MCStreamer &OS) {
|
|
|
|
BTFTypeBase::emitType(OS);
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(Info);
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
BTFKindDataSec::BTFKindDataSec(AsmPrinter *AsmPrt, std::string SecName)
|
|
|
|
: Asm(AsmPrt), Name(SecName) {
|
|
|
|
Kind = BTF::BTF_KIND_DATASEC;
|
|
|
|
BTFType.Info = Kind << 24;
|
|
|
|
BTFType.Size = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFKindDataSec::completeType(BTFDebug &BDebug) {
|
|
|
|
BTFType.NameOff = BDebug.addString(Name);
|
|
|
|
BTFType.Info |= Vars.size();
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFKindDataSec::emitType(MCStreamer &OS) {
|
|
|
|
BTFTypeBase::emitType(OS);
|
|
|
|
|
|
|
|
for (const auto &V : Vars) {
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(std::get<0>(V));
|
2020-02-14 05:26:21 +08:00
|
|
|
Asm->emitLabelReference(std::get<1>(V), 4);
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(std::get<2>(V));
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-12-20 00:40:25 +08:00
|
|
|
uint32_t BTFStringTable::addString(StringRef S) {
|
|
|
|
// Check whether the string already exists.
|
|
|
|
for (auto &OffsetM : OffsetToIdMap) {
|
|
|
|
if (Table[OffsetM.second] == S)
|
|
|
|
return OffsetM.first;
|
|
|
|
}
|
|
|
|
// Not find, add to the string table.
|
|
|
|
uint32_t Offset = Size;
|
|
|
|
OffsetToIdMap[Offset] = Table.size();
|
2020-01-29 03:23:46 +08:00
|
|
|
Table.push_back(std::string(S));
|
2018-12-20 00:40:25 +08:00
|
|
|
Size += S.size() + 1;
|
|
|
|
return Offset;
|
|
|
|
}
|
|
|
|
|
|
|
|
BTFDebug::BTFDebug(AsmPrinter *AP)
|
|
|
|
: DebugHandlerBase(AP), OS(*Asm->OutStreamer), SkipInstruction(false),
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
LineInfoGenerated(false), SecNameOff(0), ArrayIndexTypeId(0),
|
|
|
|
MapDefNotCollected(true) {
|
2018-12-20 00:40:25 +08:00
|
|
|
addString("\0");
|
|
|
|
}
|
|
|
|
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
uint32_t BTFDebug::addType(std::unique_ptr<BTFTypeBase> TypeEntry,
|
|
|
|
const DIType *Ty) {
|
2018-12-20 00:40:25 +08:00
|
|
|
TypeEntry->setId(TypeEntries.size() + 1);
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
uint32_t Id = TypeEntry->getId();
|
|
|
|
DIToIdMap[Ty] = Id;
|
2018-12-20 00:40:25 +08:00
|
|
|
TypeEntries.push_back(std::move(TypeEntry));
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
return Id;
|
2018-12-20 00:40:25 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
uint32_t BTFDebug::addType(std::unique_ptr<BTFTypeBase> TypeEntry) {
|
|
|
|
TypeEntry->setId(TypeEntries.size() + 1);
|
|
|
|
uint32_t Id = TypeEntry->getId();
|
|
|
|
TypeEntries.push_back(std::move(TypeEntry));
|
|
|
|
return Id;
|
|
|
|
}
|
|
|
|
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
void BTFDebug::visitBasicType(const DIBasicType *BTy, uint32_t &TypeId) {
|
2018-12-20 00:40:25 +08:00
|
|
|
// Only int types are supported in BTF.
|
|
|
|
uint32_t Encoding = BTy->getEncoding();
|
|
|
|
if (Encoding != dwarf::DW_ATE_boolean && Encoding != dwarf::DW_ATE_signed &&
|
|
|
|
Encoding != dwarf::DW_ATE_signed_char &&
|
|
|
|
Encoding != dwarf::DW_ATE_unsigned &&
|
|
|
|
Encoding != dwarf::DW_ATE_unsigned_char)
|
|
|
|
return;
|
|
|
|
|
|
|
|
// Create a BTF type instance for this DIBasicType and put it into
|
|
|
|
// DIToIdMap for cross-type reference check.
|
2019-08-15 23:54:37 +08:00
|
|
|
auto TypeEntry = std::make_unique<BTFTypeInt>(
|
2018-12-20 00:40:25 +08:00
|
|
|
Encoding, BTy->getSizeInBits(), BTy->getOffsetInBits(), BTy->getName());
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
TypeId = addType(std::move(TypeEntry), BTy);
|
2018-12-20 00:40:25 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/// Handle subprogram or subroutine types.
|
|
|
|
void BTFDebug::visitSubroutineType(
|
|
|
|
const DISubroutineType *STy, bool ForSubprog,
|
|
|
|
const std::unordered_map<uint32_t, StringRef> &FuncArgNames,
|
|
|
|
uint32_t &TypeId) {
|
|
|
|
DITypeRefArray Elements = STy->getTypeArray();
|
|
|
|
uint32_t VLen = Elements.size() - 1;
|
|
|
|
if (VLen > BTF::MAX_VLEN)
|
|
|
|
return;
|
|
|
|
|
|
|
|
// Subprogram has a valid non-zero-length name, and the pointee of
|
|
|
|
// a function pointer has an empty name. The subprogram type will
|
|
|
|
// not be added to DIToIdMap as it should not be referenced by
|
|
|
|
// any other types.
|
2019-08-15 23:54:37 +08:00
|
|
|
auto TypeEntry = std::make_unique<BTFTypeFuncProto>(STy, VLen, FuncArgNames);
|
2018-12-20 00:40:25 +08:00
|
|
|
if (ForSubprog)
|
|
|
|
TypeId = addType(std::move(TypeEntry)); // For subprogram
|
|
|
|
else
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
TypeId = addType(std::move(TypeEntry), STy); // For func ptr
|
2018-12-20 00:40:25 +08:00
|
|
|
|
|
|
|
// Visit return type and func arg types.
|
|
|
|
for (const auto Element : Elements) {
|
2019-05-07 10:06:37 +08:00
|
|
|
visitTypeEntry(Element);
|
2018-12-20 00:40:25 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/// Handle structure/union types.
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
void BTFDebug::visitStructType(const DICompositeType *CTy, bool IsStruct,
|
|
|
|
uint32_t &TypeId) {
|
2018-12-20 00:40:25 +08:00
|
|
|
const DINodeArray Elements = CTy->getElements();
|
|
|
|
uint32_t VLen = Elements.size();
|
|
|
|
if (VLen > BTF::MAX_VLEN)
|
|
|
|
return;
|
|
|
|
|
|
|
|
// Check whether we have any bitfield members or not
|
|
|
|
bool HasBitField = false;
|
|
|
|
for (const auto *Element : Elements) {
|
|
|
|
auto E = cast<DIDerivedType>(Element);
|
|
|
|
if (E->isBitField()) {
|
|
|
|
HasBitField = true;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
auto TypeEntry =
|
2019-08-15 23:54:37 +08:00
|
|
|
std::make_unique<BTFTypeStruct>(CTy, IsStruct, HasBitField, VLen);
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
StructTypes.push_back(TypeEntry.get());
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
TypeId = addType(std::move(TypeEntry), CTy);
|
2018-12-20 00:40:25 +08:00
|
|
|
|
|
|
|
// Visit all struct members.
|
|
|
|
for (const auto *Element : Elements)
|
|
|
|
visitTypeEntry(cast<DIDerivedType>(Element));
|
|
|
|
}
|
|
|
|
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
void BTFDebug::visitArrayType(const DICompositeType *CTy, uint32_t &TypeId) {
|
2019-03-29 05:59:49 +08:00
|
|
|
// Visit array element type.
|
2019-09-25 06:38:43 +08:00
|
|
|
uint32_t ElemTypeId;
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
const DIType *ElemType = CTy->getBaseType();
|
|
|
|
visitTypeEntry(ElemType, ElemTypeId, false, false);
|
2019-07-26 05:47:27 +08:00
|
|
|
|
2019-09-25 06:38:43 +08:00
|
|
|
// Visit array dimensions.
|
|
|
|
DINodeArray Elements = CTy->getElements();
|
|
|
|
for (int I = Elements.size() - 1; I >= 0; --I) {
|
|
|
|
if (auto *Element = dyn_cast_or_null<DINode>(Elements[I]))
|
|
|
|
if (Element->getTag() == dwarf::DW_TAG_subrange_type) {
|
|
|
|
const DISubrange *SR = cast<DISubrange>(Element);
|
|
|
|
auto *CI = SR->getCount().dyn_cast<ConstantInt *>();
|
|
|
|
int64_t Count = CI->getSExtValue();
|
|
|
|
|
|
|
|
// For struct s { int b; char c[]; }, the c[] will be represented
|
|
|
|
// as an array with Count = -1.
|
|
|
|
auto TypeEntry =
|
|
|
|
std::make_unique<BTFTypeArray>(ElemTypeId,
|
|
|
|
Count >= 0 ? Count : 0);
|
|
|
|
if (I == 0)
|
|
|
|
ElemTypeId = addType(std::move(TypeEntry), CTy);
|
|
|
|
else
|
|
|
|
ElemTypeId = addType(std::move(TypeEntry));
|
|
|
|
}
|
2019-03-29 05:59:49 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
// The array TypeId is the type id of the outermost dimension.
|
|
|
|
TypeId = ElemTypeId;
|
2018-12-20 00:40:25 +08:00
|
|
|
|
|
|
|
// The IR does not have a type for array index while BTF wants one.
|
|
|
|
// So create an array index type if there is none.
|
|
|
|
if (!ArrayIndexTypeId) {
|
2019-08-15 23:54:37 +08:00
|
|
|
auto TypeEntry = std::make_unique<BTFTypeInt>(dwarf::DW_ATE_unsigned, 32,
|
2018-12-20 00:40:25 +08:00
|
|
|
0, "__ARRAY_SIZE_TYPE__");
|
|
|
|
ArrayIndexTypeId = addType(std::move(TypeEntry));
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
void BTFDebug::visitEnumType(const DICompositeType *CTy, uint32_t &TypeId) {
|
2018-12-20 00:40:25 +08:00
|
|
|
DINodeArray Elements = CTy->getElements();
|
|
|
|
uint32_t VLen = Elements.size();
|
|
|
|
if (VLen > BTF::MAX_VLEN)
|
|
|
|
return;
|
|
|
|
|
2019-08-15 23:54:37 +08:00
|
|
|
auto TypeEntry = std::make_unique<BTFTypeEnum>(CTy, VLen);
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
TypeId = addType(std::move(TypeEntry), CTy);
|
2018-12-20 00:40:25 +08:00
|
|
|
// No need to visit base type as BTF does not encode it.
|
|
|
|
}
|
|
|
|
|
|
|
|
/// Handle structure/union forward declarations.
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
void BTFDebug::visitFwdDeclType(const DICompositeType *CTy, bool IsUnion,
|
|
|
|
uint32_t &TypeId) {
|
2019-08-15 23:54:37 +08:00
|
|
|
auto TypeEntry = std::make_unique<BTFTypeFwd>(CTy->getName(), IsUnion);
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
TypeId = addType(std::move(TypeEntry), CTy);
|
2018-12-20 00:40:25 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/// Handle structure, union, array and enumeration types.
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
void BTFDebug::visitCompositeType(const DICompositeType *CTy,
|
|
|
|
uint32_t &TypeId) {
|
2018-12-20 00:40:25 +08:00
|
|
|
auto Tag = CTy->getTag();
|
|
|
|
if (Tag == dwarf::DW_TAG_structure_type || Tag == dwarf::DW_TAG_union_type) {
|
|
|
|
// Handle forward declaration differently as it does not have members.
|
|
|
|
if (CTy->isForwardDecl())
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
visitFwdDeclType(CTy, Tag == dwarf::DW_TAG_union_type, TypeId);
|
2018-12-20 00:40:25 +08:00
|
|
|
else
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
visitStructType(CTy, Tag == dwarf::DW_TAG_structure_type, TypeId);
|
2018-12-20 00:40:25 +08:00
|
|
|
} else if (Tag == dwarf::DW_TAG_array_type)
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
visitArrayType(CTy, TypeId);
|
2018-12-20 00:40:25 +08:00
|
|
|
else if (Tag == dwarf::DW_TAG_enumeration_type)
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
visitEnumType(CTy, TypeId);
|
2018-12-20 00:40:25 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/// Handle pointer, typedef, const, volatile, restrict and member types.
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
void BTFDebug::visitDerivedType(const DIDerivedType *DTy, uint32_t &TypeId,
|
|
|
|
bool CheckPointer, bool SeenPointer) {
|
2018-12-20 00:40:25 +08:00
|
|
|
unsigned Tag = DTy->getTag();
|
|
|
|
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
/// Try to avoid chasing pointees, esp. structure pointees which may
|
|
|
|
/// unnecessary bring in a lot of types.
|
|
|
|
if (CheckPointer && !SeenPointer) {
|
|
|
|
SeenPointer = Tag == dwarf::DW_TAG_pointer_type;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (CheckPointer && SeenPointer) {
|
|
|
|
const DIType *Base = DTy->getBaseType();
|
|
|
|
if (Base) {
|
|
|
|
if (const auto *CTy = dyn_cast<DICompositeType>(Base)) {
|
|
|
|
auto CTag = CTy->getTag();
|
|
|
|
if ((CTag == dwarf::DW_TAG_structure_type ||
|
|
|
|
CTag == dwarf::DW_TAG_union_type) &&
|
|
|
|
!CTy->isForwardDecl()) {
|
|
|
|
/// Find a candidate, generate a fixup. Later on the struct/union
|
|
|
|
/// pointee type will be replaced with either a real type or
|
|
|
|
/// a forward declaration.
|
2019-08-15 23:54:37 +08:00
|
|
|
auto TypeEntry = std::make_unique<BTFTypeDerived>(DTy, Tag, true);
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
auto &Fixup = FixupDerivedTypes[CTy->getName()];
|
|
|
|
Fixup.first = CTag == dwarf::DW_TAG_union_type;
|
|
|
|
Fixup.second.push_back(TypeEntry.get());
|
|
|
|
TypeId = addType(std::move(TypeEntry), DTy);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-12-20 00:40:25 +08:00
|
|
|
if (Tag == dwarf::DW_TAG_pointer_type || Tag == dwarf::DW_TAG_typedef ||
|
|
|
|
Tag == dwarf::DW_TAG_const_type || Tag == dwarf::DW_TAG_volatile_type ||
|
|
|
|
Tag == dwarf::DW_TAG_restrict_type) {
|
2019-08-15 23:54:37 +08:00
|
|
|
auto TypeEntry = std::make_unique<BTFTypeDerived>(DTy, Tag, false);
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
TypeId = addType(std::move(TypeEntry), DTy);
|
2018-12-20 00:40:25 +08:00
|
|
|
} else if (Tag != dwarf::DW_TAG_member) {
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Visit base type of pointer, typedef, const, volatile, restrict or
|
|
|
|
// struct/union member.
|
2019-03-22 09:30:50 +08:00
|
|
|
uint32_t TempTypeId = 0;
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
if (Tag == dwarf::DW_TAG_member)
|
|
|
|
visitTypeEntry(DTy->getBaseType(), TempTypeId, true, false);
|
|
|
|
else
|
|
|
|
visitTypeEntry(DTy->getBaseType(), TempTypeId, CheckPointer, SeenPointer);
|
2018-12-20 00:40:25 +08:00
|
|
|
}
|
|
|
|
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
void BTFDebug::visitTypeEntry(const DIType *Ty, uint32_t &TypeId,
|
|
|
|
bool CheckPointer, bool SeenPointer) {
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
if (!Ty || DIToIdMap.find(Ty) != DIToIdMap.end()) {
|
|
|
|
TypeId = DIToIdMap[Ty];
|
2018-12-20 00:40:25 +08:00
|
|
|
return;
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
}
|
2018-12-20 00:40:25 +08:00
|
|
|
|
|
|
|
if (const auto *BTy = dyn_cast<DIBasicType>(Ty))
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
visitBasicType(BTy, TypeId);
|
2018-12-20 00:40:25 +08:00
|
|
|
else if (const auto *STy = dyn_cast<DISubroutineType>(Ty))
|
|
|
|
visitSubroutineType(STy, false, std::unordered_map<uint32_t, StringRef>(),
|
|
|
|
TypeId);
|
|
|
|
else if (const auto *CTy = dyn_cast<DICompositeType>(Ty))
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
visitCompositeType(CTy, TypeId);
|
2018-12-20 00:40:25 +08:00
|
|
|
else if (const auto *DTy = dyn_cast<DIDerivedType>(Ty))
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
visitDerivedType(DTy, TypeId, CheckPointer, SeenPointer);
|
2018-12-20 00:40:25 +08:00
|
|
|
else
|
|
|
|
llvm_unreachable("Unknown DIType");
|
|
|
|
}
|
|
|
|
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
void BTFDebug::visitTypeEntry(const DIType *Ty) {
|
|
|
|
uint32_t TypeId;
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
visitTypeEntry(Ty, TypeId, false, false);
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFDebug::visitMapDefType(const DIType *Ty, uint32_t &TypeId) {
|
|
|
|
if (!Ty || DIToIdMap.find(Ty) != DIToIdMap.end()) {
|
|
|
|
TypeId = DIToIdMap[Ty];
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
// MapDef type is a struct type
|
|
|
|
const auto *CTy = dyn_cast<DICompositeType>(Ty);
|
|
|
|
if (!CTy)
|
|
|
|
return;
|
|
|
|
|
|
|
|
auto Tag = CTy->getTag();
|
|
|
|
if (Tag != dwarf::DW_TAG_structure_type || CTy->isForwardDecl())
|
|
|
|
return;
|
|
|
|
|
|
|
|
// Record this type
|
|
|
|
const DINodeArray Elements = CTy->getElements();
|
|
|
|
bool HasBitField = false;
|
|
|
|
for (const auto *Element : Elements) {
|
|
|
|
auto E = cast<DIDerivedType>(Element);
|
|
|
|
if (E->isBitField()) {
|
|
|
|
HasBitField = true;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
auto TypeEntry =
|
2019-08-15 23:54:37 +08:00
|
|
|
std::make_unique<BTFTypeStruct>(CTy, true, HasBitField, Elements.size());
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
StructTypes.push_back(TypeEntry.get());
|
|
|
|
TypeId = addType(std::move(TypeEntry), CTy);
|
|
|
|
|
|
|
|
// Visit all struct members
|
|
|
|
for (const auto *Element : Elements) {
|
|
|
|
const auto *MemberType = cast<DIDerivedType>(Element);
|
|
|
|
visitTypeEntry(MemberType->getBaseType());
|
|
|
|
}
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
}
|
|
|
|
|
2018-12-20 00:40:25 +08:00
|
|
|
/// Read file contents from the actual file or from the source
|
|
|
|
std::string BTFDebug::populateFileContent(const DISubprogram *SP) {
|
|
|
|
auto File = SP->getFile();
|
|
|
|
std::string FileName;
|
|
|
|
|
2019-02-02 13:54:59 +08:00
|
|
|
if (!File->getFilename().startswith("/") && File->getDirectory().size())
|
2018-12-20 00:40:25 +08:00
|
|
|
FileName = File->getDirectory().str() + "/" + File->getFilename().str();
|
|
|
|
else
|
2020-01-29 03:23:46 +08:00
|
|
|
FileName = std::string(File->getFilename());
|
2018-12-20 00:40:25 +08:00
|
|
|
|
|
|
|
// No need to populate the contends if it has been populated!
|
|
|
|
if (FileContent.find(FileName) != FileContent.end())
|
|
|
|
return FileName;
|
|
|
|
|
|
|
|
std::vector<std::string> Content;
|
|
|
|
std::string Line;
|
|
|
|
Content.push_back(Line); // Line 0 for empty string
|
|
|
|
|
2019-04-03 00:15:46 +08:00
|
|
|
std::unique_ptr<MemoryBuffer> Buf;
|
2018-12-20 00:40:25 +08:00
|
|
|
auto Source = File->getSource();
|
2019-04-03 00:15:46 +08:00
|
|
|
if (Source)
|
|
|
|
Buf = MemoryBuffer::getMemBufferCopy(*Source);
|
|
|
|
else if (ErrorOr<std::unique_ptr<MemoryBuffer>> BufOrErr =
|
|
|
|
MemoryBuffer::getFile(FileName))
|
|
|
|
Buf = std::move(*BufOrErr);
|
|
|
|
if (Buf)
|
|
|
|
for (line_iterator I(*Buf, false), E; I != E; ++I)
|
2020-01-29 03:23:46 +08:00
|
|
|
Content.push_back(std::string(*I));
|
2018-12-20 00:40:25 +08:00
|
|
|
|
|
|
|
FileContent[FileName] = Content;
|
|
|
|
return FileName;
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFDebug::constructLineInfo(const DISubprogram *SP, MCSymbol *Label,
|
|
|
|
uint32_t Line, uint32_t Column) {
|
|
|
|
std::string FileName = populateFileContent(SP);
|
|
|
|
BTFLineInfo LineInfo;
|
|
|
|
|
|
|
|
LineInfo.Label = Label;
|
|
|
|
LineInfo.FileNameOff = addString(FileName);
|
|
|
|
// If file content is not available, let LineOff = 0.
|
|
|
|
if (Line < FileContent[FileName].size())
|
|
|
|
LineInfo.LineOff = addString(FileContent[FileName][Line]);
|
|
|
|
else
|
|
|
|
LineInfo.LineOff = 0;
|
|
|
|
LineInfo.LineNum = Line;
|
|
|
|
LineInfo.ColumnNum = Column;
|
|
|
|
LineInfoTable[SecNameOff].push_back(LineInfo);
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFDebug::emitCommonHeader() {
|
|
|
|
OS.AddComment("0x" + Twine::utohexstr(BTF::MAGIC));
|
2020-02-15 14:40:47 +08:00
|
|
|
OS.emitIntValue(BTF::MAGIC, 2);
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt8(BTF::VERSION);
|
|
|
|
OS.emitInt8(0);
|
2018-12-20 00:40:25 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
void BTFDebug::emitBTFSection() {
|
2019-03-05 09:01:21 +08:00
|
|
|
// Do not emit section if no types and only "" string.
|
|
|
|
if (!TypeEntries.size() && StringTable.getSize() == 1)
|
|
|
|
return;
|
|
|
|
|
2018-12-20 00:40:25 +08:00
|
|
|
MCContext &Ctx = OS.getContext();
|
|
|
|
OS.SwitchSection(Ctx.getELFSection(".BTF", ELF::SHT_PROGBITS, 0));
|
|
|
|
|
|
|
|
// Emit header.
|
|
|
|
emitCommonHeader();
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(BTF::HeaderSize);
|
2018-12-20 00:40:25 +08:00
|
|
|
|
|
|
|
uint32_t TypeLen = 0, StrLen;
|
|
|
|
for (const auto &TypeEntry : TypeEntries)
|
|
|
|
TypeLen += TypeEntry->getSize();
|
|
|
|
StrLen = StringTable.getSize();
|
|
|
|
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(0);
|
|
|
|
OS.emitInt32(TypeLen);
|
|
|
|
OS.emitInt32(TypeLen);
|
|
|
|
OS.emitInt32(StrLen);
|
2018-12-20 00:40:25 +08:00
|
|
|
|
|
|
|
// Emit type table.
|
|
|
|
for (const auto &TypeEntry : TypeEntries)
|
|
|
|
TypeEntry->emitType(OS);
|
|
|
|
|
|
|
|
// Emit string table.
|
|
|
|
uint32_t StringOffset = 0;
|
|
|
|
for (const auto &S : StringTable.getTable()) {
|
|
|
|
OS.AddComment("string offset=" + std::to_string(StringOffset));
|
2020-02-15 10:16:24 +08:00
|
|
|
OS.emitBytes(S);
|
|
|
|
OS.emitBytes(StringRef("\0", 1));
|
2018-12-20 00:40:25 +08:00
|
|
|
StringOffset += S.size() + 1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFDebug::emitBTFExtSection() {
|
2019-10-10 23:33:09 +08:00
|
|
|
// Do not emit section if empty FuncInfoTable and LineInfoTable
|
|
|
|
// and FieldRelocTable.
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
if (!FuncInfoTable.size() && !LineInfoTable.size() &&
|
2019-10-10 23:33:09 +08:00
|
|
|
!FieldRelocTable.size())
|
2019-03-05 09:01:21 +08:00
|
|
|
return;
|
|
|
|
|
2018-12-20 00:40:25 +08:00
|
|
|
MCContext &Ctx = OS.getContext();
|
|
|
|
OS.SwitchSection(Ctx.getELFSection(".BTF.ext", ELF::SHT_PROGBITS, 0));
|
|
|
|
|
|
|
|
// Emit header.
|
|
|
|
emitCommonHeader();
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(BTF::ExtHeaderSize);
|
2018-12-20 00:40:25 +08:00
|
|
|
|
|
|
|
// Account for FuncInfo/LineInfo record size as well.
|
|
|
|
uint32_t FuncLen = 4, LineLen = 4;
|
2019-10-10 23:33:09 +08:00
|
|
|
// Do not account for optional FieldReloc.
|
|
|
|
uint32_t FieldRelocLen = 0;
|
2018-12-20 00:40:25 +08:00
|
|
|
for (const auto &FuncSec : FuncInfoTable) {
|
|
|
|
FuncLen += BTF::SecFuncInfoSize;
|
|
|
|
FuncLen += FuncSec.second.size() * BTF::BPFFuncInfoSize;
|
|
|
|
}
|
|
|
|
for (const auto &LineSec : LineInfoTable) {
|
|
|
|
LineLen += BTF::SecLineInfoSize;
|
|
|
|
LineLen += LineSec.second.size() * BTF::BPFLineInfoSize;
|
|
|
|
}
|
[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
|
|
|
for (const auto &FieldRelocSec : FieldRelocTable) {
|
|
|
|
FieldRelocLen += BTF::SecFieldRelocSize;
|
|
|
|
FieldRelocLen += FieldRelocSec.second.size() * BTF::BPFFieldRelocSize;
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
}
|
|
|
|
|
[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
|
|
|
if (FieldRelocLen)
|
|
|
|
FieldRelocLen += 4;
|
2018-12-20 00:40:25 +08:00
|
|
|
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(0);
|
|
|
|
OS.emitInt32(FuncLen);
|
|
|
|
OS.emitInt32(FuncLen);
|
|
|
|
OS.emitInt32(LineLen);
|
|
|
|
OS.emitInt32(FuncLen + LineLen);
|
|
|
|
OS.emitInt32(FieldRelocLen);
|
2018-12-20 00:40:25 +08:00
|
|
|
|
|
|
|
// Emit func_info table.
|
|
|
|
OS.AddComment("FuncInfo");
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(BTF::BPFFuncInfoSize);
|
2018-12-20 00:40:25 +08:00
|
|
|
for (const auto &FuncSec : FuncInfoTable) {
|
|
|
|
OS.AddComment("FuncInfo section string offset=" +
|
|
|
|
std::to_string(FuncSec.first));
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(FuncSec.first);
|
|
|
|
OS.emitInt32(FuncSec.second.size());
|
2018-12-20 00:40:25 +08:00
|
|
|
for (const auto &FuncInfo : FuncSec.second) {
|
2020-02-14 05:26:21 +08:00
|
|
|
Asm->emitLabelReference(FuncInfo.Label, 4);
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(FuncInfo.TypeId);
|
2018-12-20 00:40:25 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// Emit line_info table.
|
|
|
|
OS.AddComment("LineInfo");
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(BTF::BPFLineInfoSize);
|
2018-12-20 00:40:25 +08:00
|
|
|
for (const auto &LineSec : LineInfoTable) {
|
|
|
|
OS.AddComment("LineInfo section string offset=" +
|
|
|
|
std::to_string(LineSec.first));
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(LineSec.first);
|
|
|
|
OS.emitInt32(LineSec.second.size());
|
2018-12-20 00:40:25 +08:00
|
|
|
for (const auto &LineInfo : LineSec.second) {
|
2020-02-14 05:26:21 +08:00
|
|
|
Asm->emitLabelReference(LineInfo.Label, 4);
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(LineInfo.FileNameOff);
|
|
|
|
OS.emitInt32(LineInfo.LineOff);
|
2018-12-20 00:40:25 +08:00
|
|
|
OS.AddComment("Line " + std::to_string(LineInfo.LineNum) + " Col " +
|
|
|
|
std::to_string(LineInfo.ColumnNum));
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(LineInfo.LineNum << 10 | LineInfo.ColumnNum);
|
2018-12-20 00:40:25 +08:00
|
|
|
}
|
|
|
|
}
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
|
[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
|
|
|
// Emit field reloc table.
|
|
|
|
if (FieldRelocLen) {
|
|
|
|
OS.AddComment("FieldReloc");
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(BTF::BPFFieldRelocSize);
|
[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
|
|
|
for (const auto &FieldRelocSec : FieldRelocTable) {
|
|
|
|
OS.AddComment("Field reloc section string offset=" +
|
|
|
|
std::to_string(FieldRelocSec.first));
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(FieldRelocSec.first);
|
|
|
|
OS.emitInt32(FieldRelocSec.second.size());
|
[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
|
|
|
for (const auto &FieldRelocInfo : FieldRelocSec.second) {
|
2020-02-14 05:26:21 +08:00
|
|
|
Asm->emitLabelReference(FieldRelocInfo.Label, 4);
|
2020-03-01 00:25:22 +08:00
|
|
|
OS.emitInt32(FieldRelocInfo.TypeID);
|
|
|
|
OS.emitInt32(FieldRelocInfo.OffsetNameOff);
|
|
|
|
OS.emitInt32(FieldRelocInfo.RelocKind);
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
2018-12-20 00:40:25 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
void BTFDebug::beginFunctionImpl(const MachineFunction *MF) {
|
|
|
|
auto *SP = MF->getFunction().getSubprogram();
|
|
|
|
auto *Unit = SP->getUnit();
|
|
|
|
|
|
|
|
if (Unit->getEmissionKind() == DICompileUnit::NoDebug) {
|
|
|
|
SkipInstruction = true;
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
SkipInstruction = false;
|
|
|
|
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
// Collect MapDef types. Map definition needs to collect
|
|
|
|
// pointee types. Do it first. Otherwise, for the following
|
|
|
|
// case:
|
|
|
|
// struct m { ...};
|
|
|
|
// struct t {
|
|
|
|
// struct m *key;
|
|
|
|
// };
|
|
|
|
// foo(struct t *arg);
|
|
|
|
//
|
|
|
|
// struct mapdef {
|
|
|
|
// ...
|
|
|
|
// struct m *key;
|
|
|
|
// ...
|
|
|
|
// } __attribute__((section(".maps"))) hash_map;
|
|
|
|
//
|
|
|
|
// If subroutine foo is traversed first, a type chain
|
|
|
|
// "ptr->struct m(fwd)" will be created and later on
|
|
|
|
// when traversing mapdef, since "ptr->struct m" exists,
|
|
|
|
// the traversal of "struct m" will be omitted.
|
|
|
|
if (MapDefNotCollected) {
|
|
|
|
processGlobals(true);
|
|
|
|
MapDefNotCollected = false;
|
|
|
|
}
|
|
|
|
|
2018-12-20 00:40:25 +08:00
|
|
|
// Collect all types locally referenced in this function.
|
|
|
|
// Use RetainedNodes so we can collect all argument names
|
|
|
|
// even if the argument is not used.
|
|
|
|
std::unordered_map<uint32_t, StringRef> FuncArgNames;
|
|
|
|
for (const DINode *DN : SP->getRetainedNodes()) {
|
|
|
|
if (const auto *DV = dyn_cast<DILocalVariable>(DN)) {
|
|
|
|
// Collect function arguments for subprogram func type.
|
|
|
|
uint32_t Arg = DV->getArg();
|
2019-03-15 13:51:25 +08:00
|
|
|
if (Arg) {
|
2019-05-07 10:06:37 +08:00
|
|
|
visitTypeEntry(DV->getType());
|
2018-12-20 00:40:25 +08:00
|
|
|
FuncArgNames[Arg] = DV->getName();
|
2019-03-15 13:51:25 +08:00
|
|
|
}
|
2018-12-20 00:40:25 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// Construct subprogram func proto type.
|
|
|
|
uint32_t ProtoTypeId;
|
|
|
|
visitSubroutineType(SP->getType(), true, FuncArgNames, ProtoTypeId);
|
|
|
|
|
|
|
|
// Construct subprogram func type
|
2019-12-18 08:24:23 +08:00
|
|
|
uint8_t Scope = SP->isLocalToUnit() ? BTF::FUNC_STATIC : BTF::FUNC_GLOBAL;
|
2018-12-20 00:40:25 +08:00
|
|
|
auto FuncTypeEntry =
|
2019-12-18 08:24:23 +08:00
|
|
|
std::make_unique<BTFTypeFunc>(SP->getName(), ProtoTypeId, Scope);
|
2018-12-20 00:40:25 +08:00
|
|
|
uint32_t FuncTypeId = addType(std::move(FuncTypeEntry));
|
|
|
|
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
for (const auto &TypeEntry : TypeEntries)
|
|
|
|
TypeEntry->completeType(*this);
|
|
|
|
|
2018-12-20 00:40:25 +08:00
|
|
|
// Construct funcinfo and the first lineinfo for the function.
|
|
|
|
MCSymbol *FuncLabel = Asm->getFunctionBegin();
|
|
|
|
BTFFuncInfo FuncInfo;
|
|
|
|
FuncInfo.Label = FuncLabel;
|
|
|
|
FuncInfo.TypeId = FuncTypeId;
|
|
|
|
if (FuncLabel->isInSection()) {
|
|
|
|
MCSection &Section = FuncLabel->getSection();
|
|
|
|
const MCSectionELF *SectionELF = dyn_cast<MCSectionELF>(&Section);
|
|
|
|
assert(SectionELF && "Null section for Function Label");
|
|
|
|
SecNameOff = addString(SectionELF->getSectionName());
|
|
|
|
} else {
|
|
|
|
SecNameOff = addString(".text");
|
|
|
|
}
|
|
|
|
FuncInfoTable[SecNameOff].push_back(FuncInfo);
|
|
|
|
}
|
|
|
|
|
|
|
|
void BTFDebug::endFunctionImpl(const MachineFunction *MF) {
|
|
|
|
SkipInstruction = false;
|
|
|
|
LineInfoGenerated = false;
|
|
|
|
SecNameOff = 0;
|
|
|
|
}
|
|
|
|
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
/// On-demand populate struct types as requested from abstract member
|
|
|
|
/// accessing.
|
|
|
|
unsigned BTFDebug::populateStructType(const DIType *Ty) {
|
|
|
|
unsigned Id;
|
|
|
|
visitTypeEntry(Ty, Id, false, false);
|
|
|
|
for (const auto &TypeEntry : TypeEntries)
|
|
|
|
TypeEntry->completeType(*this);
|
|
|
|
return Id;
|
|
|
|
}
|
|
|
|
|
[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
|
|
|
/// Generate a struct member field relocation.
|
[BPF] Enable relocation location for load/store/shifts
Previous btf field relocation is always at assignment like
r1 = 4
which is converted from an ld_imm64 instruction.
This patch did an optimization such that relocation
instruction might be load/store/shift. Specically, the
following insns may also have relocation, except BPF_MOV:
LDB, LDH, LDW, LDD, STB, STH, STW, STD,
LDB32, LDH32, LDW32, STB32, STH32, STW32,
SLL, SRL, SRA
To accomplish this, a few BPF target specific
codegen only instructions are invented. They
are generated at backend BPF SimplifyPatchable phase,
which is at early llc phase when SSA form is available.
The new codegen only instructions will be converted to
real proper instructions at the codegen and BTF emission stage.
Note that, as revealed by a few tests, this optimization might
be actual generating more relocations:
Scenario 1:
if (...) {
... __builtin_preserve_field_info(arg->b2, 0) ...
} else {
... __builtin_preserve_field_info(arg->b2, 0) ...
}
Compiler could do CSE to only have one relocation. But if both
of the above is translated into codegen internal instructions,
the compiler will not be able to do that.
Scenario 2:
offset = ... __builtin_preserve_field_info(arg->b2, 0) ...
...
... offset ...
... offset ...
... offset ...
For whatever reason, the compiler might be temporarily do copy
propagation of the righthand of "offset" assignment like
... __builtin_preserve_field_info(arg->b2, 0) ...
... __builtin_preserve_field_info(arg->b2, 0) ...
and CSE will be able to deduplicate later.
But if these intrinsics are converted to BPF pseudo instructions,
they will not be able to get deduplicated.
I do not expect we have big instruction count difference.
It may actually reduce instruction count since now relocation
is in deeper insn dependency chain.
For example, for test offset-reloc-fieldinfo-2.ll, this patch
generates 7 instead of 6 relocations for non-alu32 mode, but it
actually reduced instruction count from 29 to 26.
Differential Revision: https://reviews.llvm.org/D71790
2019-12-20 07:21:53 +08:00
|
|
|
void BTFDebug::generateFieldReloc(const MCSymbol *ORSym, DIType *RootTy,
|
|
|
|
StringRef AccessPattern) {
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
unsigned RootId = populateStructType(RootTy);
|
2019-08-03 07:16:44 +08:00
|
|
|
size_t FirstDollar = AccessPattern.find_first_of('$');
|
|
|
|
size_t FirstColon = AccessPattern.find_first_of(':');
|
[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
|
|
|
size_t SecondColon = AccessPattern.find_first_of(':', FirstColon + 1);
|
2019-08-03 07:16:44 +08:00
|
|
|
StringRef IndexPattern = AccessPattern.substr(FirstDollar + 1);
|
[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
|
|
|
StringRef RelocKindStr = AccessPattern.substr(FirstColon + 1,
|
|
|
|
SecondColon - FirstColon);
|
|
|
|
StringRef PatchImmStr = AccessPattern.substr(SecondColon + 1,
|
|
|
|
FirstDollar - SecondColon);
|
|
|
|
|
|
|
|
BTFFieldReloc FieldReloc;
|
|
|
|
FieldReloc.Label = ORSym;
|
|
|
|
FieldReloc.OffsetNameOff = addString(IndexPattern);
|
|
|
|
FieldReloc.TypeID = RootId;
|
2020-01-29 03:23:46 +08:00
|
|
|
FieldReloc.RelocKind = std::stoull(std::string(RelocKindStr));
|
|
|
|
PatchImms[AccessPattern.str()] = std::stoul(std::string(PatchImmStr));
|
[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
|
|
|
FieldRelocTable[SecNameOff].push_back(FieldReloc);
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
}
|
|
|
|
|
[BPF] Enable relocation location for load/store/shifts
Previous btf field relocation is always at assignment like
r1 = 4
which is converted from an ld_imm64 instruction.
This patch did an optimization such that relocation
instruction might be load/store/shift. Specically, the
following insns may also have relocation, except BPF_MOV:
LDB, LDH, LDW, LDD, STB, STH, STW, STD,
LDB32, LDH32, LDW32, STB32, STH32, STW32,
SLL, SRL, SRA
To accomplish this, a few BPF target specific
codegen only instructions are invented. They
are generated at backend BPF SimplifyPatchable phase,
which is at early llc phase when SSA form is available.
The new codegen only instructions will be converted to
real proper instructions at the codegen and BTF emission stage.
Note that, as revealed by a few tests, this optimization might
be actual generating more relocations:
Scenario 1:
if (...) {
... __builtin_preserve_field_info(arg->b2, 0) ...
} else {
... __builtin_preserve_field_info(arg->b2, 0) ...
}
Compiler could do CSE to only have one relocation. But if both
of the above is translated into codegen internal instructions,
the compiler will not be able to do that.
Scenario 2:
offset = ... __builtin_preserve_field_info(arg->b2, 0) ...
...
... offset ...
... offset ...
... offset ...
For whatever reason, the compiler might be temporarily do copy
propagation of the righthand of "offset" assignment like
... __builtin_preserve_field_info(arg->b2, 0) ...
... __builtin_preserve_field_info(arg->b2, 0) ...
and CSE will be able to deduplicate later.
But if these intrinsics are converted to BPF pseudo instructions,
they will not be able to get deduplicated.
I do not expect we have big instruction count difference.
It may actually reduce instruction count since now relocation
is in deeper insn dependency chain.
For example, for test offset-reloc-fieldinfo-2.ll, this patch
generates 7 instead of 6 relocations for non-alu32 mode, but it
actually reduced instruction count from 29 to 26.
Differential Revision: https://reviews.llvm.org/D71790
2019-12-20 07:21:53 +08:00
|
|
|
void BTFDebug::processReloc(const MachineOperand &MO) {
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
// check whether this is a candidate or not
|
|
|
|
if (MO.isGlobal()) {
|
|
|
|
const GlobalValue *GVal = MO.getGlobal();
|
|
|
|
auto *GVar = dyn_cast<GlobalVariable>(GVal);
|
|
|
|
if (GVar && GVar->hasAttribute(BPFCoreSharedInfo::AmaAttr)) {
|
|
|
|
MCSymbol *ORSym = OS.getContext().createTempSymbol();
|
2020-02-15 11:21:58 +08:00
|
|
|
OS.emitLabel(ORSym);
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
|
|
|
|
MDNode *MDN = GVar->getMetadata(LLVMContext::MD_preserve_access_index);
|
|
|
|
DIType *Ty = dyn_cast<DIType>(MDN);
|
[BPF] Enable relocation location for load/store/shifts
Previous btf field relocation is always at assignment like
r1 = 4
which is converted from an ld_imm64 instruction.
This patch did an optimization such that relocation
instruction might be load/store/shift. Specically, the
following insns may also have relocation, except BPF_MOV:
LDB, LDH, LDW, LDD, STB, STH, STW, STD,
LDB32, LDH32, LDW32, STB32, STH32, STW32,
SLL, SRL, SRA
To accomplish this, a few BPF target specific
codegen only instructions are invented. They
are generated at backend BPF SimplifyPatchable phase,
which is at early llc phase when SSA form is available.
The new codegen only instructions will be converted to
real proper instructions at the codegen and BTF emission stage.
Note that, as revealed by a few tests, this optimization might
be actual generating more relocations:
Scenario 1:
if (...) {
... __builtin_preserve_field_info(arg->b2, 0) ...
} else {
... __builtin_preserve_field_info(arg->b2, 0) ...
}
Compiler could do CSE to only have one relocation. But if both
of the above is translated into codegen internal instructions,
the compiler will not be able to do that.
Scenario 2:
offset = ... __builtin_preserve_field_info(arg->b2, 0) ...
...
... offset ...
... offset ...
... offset ...
For whatever reason, the compiler might be temporarily do copy
propagation of the righthand of "offset" assignment like
... __builtin_preserve_field_info(arg->b2, 0) ...
... __builtin_preserve_field_info(arg->b2, 0) ...
and CSE will be able to deduplicate later.
But if these intrinsics are converted to BPF pseudo instructions,
they will not be able to get deduplicated.
I do not expect we have big instruction count difference.
It may actually reduce instruction count since now relocation
is in deeper insn dependency chain.
For example, for test offset-reloc-fieldinfo-2.ll, this patch
generates 7 instead of 6 relocations for non-alu32 mode, but it
actually reduced instruction count from 29 to 26.
Differential Revision: https://reviews.llvm.org/D71790
2019-12-20 07:21:53 +08:00
|
|
|
generateFieldReloc(ORSym, Ty, GVar->getName());
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-12-20 00:40:25 +08:00
|
|
|
void BTFDebug::beginInstruction(const MachineInstr *MI) {
|
|
|
|
DebugHandlerBase::beginInstruction(MI);
|
|
|
|
|
|
|
|
if (SkipInstruction || MI->isMetaInstruction() ||
|
|
|
|
MI->getFlag(MachineInstr::FrameSetup))
|
|
|
|
return;
|
|
|
|
|
|
|
|
if (MI->isInlineAsm()) {
|
|
|
|
// Count the number of register definitions to find the asm string.
|
|
|
|
unsigned NumDefs = 0;
|
|
|
|
for (; MI->getOperand(NumDefs).isReg() && MI->getOperand(NumDefs).isDef();
|
|
|
|
++NumDefs)
|
|
|
|
;
|
|
|
|
|
|
|
|
// Skip this inline asm instruction if the asmstr is empty.
|
|
|
|
const char *AsmStr = MI->getOperand(NumDefs).getSymbolName();
|
|
|
|
if (AsmStr[0] == 0)
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
[BPF] Enable relocation location for load/store/shifts
Previous btf field relocation is always at assignment like
r1 = 4
which is converted from an ld_imm64 instruction.
This patch did an optimization such that relocation
instruction might be load/store/shift. Specically, the
following insns may also have relocation, except BPF_MOV:
LDB, LDH, LDW, LDD, STB, STH, STW, STD,
LDB32, LDH32, LDW32, STB32, STH32, STW32,
SLL, SRL, SRA
To accomplish this, a few BPF target specific
codegen only instructions are invented. They
are generated at backend BPF SimplifyPatchable phase,
which is at early llc phase when SSA form is available.
The new codegen only instructions will be converted to
real proper instructions at the codegen and BTF emission stage.
Note that, as revealed by a few tests, this optimization might
be actual generating more relocations:
Scenario 1:
if (...) {
... __builtin_preserve_field_info(arg->b2, 0) ...
} else {
... __builtin_preserve_field_info(arg->b2, 0) ...
}
Compiler could do CSE to only have one relocation. But if both
of the above is translated into codegen internal instructions,
the compiler will not be able to do that.
Scenario 2:
offset = ... __builtin_preserve_field_info(arg->b2, 0) ...
...
... offset ...
... offset ...
... offset ...
For whatever reason, the compiler might be temporarily do copy
propagation of the righthand of "offset" assignment like
... __builtin_preserve_field_info(arg->b2, 0) ...
... __builtin_preserve_field_info(arg->b2, 0) ...
and CSE will be able to deduplicate later.
But if these intrinsics are converted to BPF pseudo instructions,
they will not be able to get deduplicated.
I do not expect we have big instruction count difference.
It may actually reduce instruction count since now relocation
is in deeper insn dependency chain.
For example, for test offset-reloc-fieldinfo-2.ll, this patch
generates 7 instead of 6 relocations for non-alu32 mode, but it
actually reduced instruction count from 29 to 26.
Differential Revision: https://reviews.llvm.org/D71790
2019-12-20 07:21:53 +08:00
|
|
|
if (MI->getOpcode() == BPF::LD_imm64) {
|
|
|
|
// If the insn is "r2 = LD_imm64 @<an AmaAttr global>",
|
|
|
|
// add this insn into the .BTF.ext FieldReloc subsection.
|
|
|
|
// Relocation looks like:
|
|
|
|
// . SecName:
|
|
|
|
// . InstOffset
|
|
|
|
// . TypeID
|
|
|
|
// . OffSetNameOff
|
|
|
|
// . RelocType
|
|
|
|
// Later, the insn is replaced with "r2 = <offset>"
|
|
|
|
// where "<offset>" equals to the offset based on current
|
|
|
|
// type definitions.
|
|
|
|
processReloc(MI->getOperand(1));
|
|
|
|
} else if (MI->getOpcode() == BPF::CORE_MEM ||
|
|
|
|
MI->getOpcode() == BPF::CORE_ALU32_MEM ||
|
|
|
|
MI->getOpcode() == BPF::CORE_SHIFT) {
|
|
|
|
// relocation insn is a load, store or shift insn.
|
|
|
|
processReloc(MI->getOperand(3));
|
2019-12-18 08:24:23 +08:00
|
|
|
} else if (MI->getOpcode() == BPF::JAL) {
|
|
|
|
// check extern function references
|
|
|
|
const MachineOperand &MO = MI->getOperand(0);
|
|
|
|
if (MO.isGlobal()) {
|
|
|
|
processFuncPrototypes(dyn_cast<Function>(MO.getGlobal()));
|
|
|
|
}
|
[BPF] Enable relocation location for load/store/shifts
Previous btf field relocation is always at assignment like
r1 = 4
which is converted from an ld_imm64 instruction.
This patch did an optimization such that relocation
instruction might be load/store/shift. Specically, the
following insns may also have relocation, except BPF_MOV:
LDB, LDH, LDW, LDD, STB, STH, STW, STD,
LDB32, LDH32, LDW32, STB32, STH32, STW32,
SLL, SRL, SRA
To accomplish this, a few BPF target specific
codegen only instructions are invented. They
are generated at backend BPF SimplifyPatchable phase,
which is at early llc phase when SSA form is available.
The new codegen only instructions will be converted to
real proper instructions at the codegen and BTF emission stage.
Note that, as revealed by a few tests, this optimization might
be actual generating more relocations:
Scenario 1:
if (...) {
... __builtin_preserve_field_info(arg->b2, 0) ...
} else {
... __builtin_preserve_field_info(arg->b2, 0) ...
}
Compiler could do CSE to only have one relocation. But if both
of the above is translated into codegen internal instructions,
the compiler will not be able to do that.
Scenario 2:
offset = ... __builtin_preserve_field_info(arg->b2, 0) ...
...
... offset ...
... offset ...
... offset ...
For whatever reason, the compiler might be temporarily do copy
propagation of the righthand of "offset" assignment like
... __builtin_preserve_field_info(arg->b2, 0) ...
... __builtin_preserve_field_info(arg->b2, 0) ...
and CSE will be able to deduplicate later.
But if these intrinsics are converted to BPF pseudo instructions,
they will not be able to get deduplicated.
I do not expect we have big instruction count difference.
It may actually reduce instruction count since now relocation
is in deeper insn dependency chain.
For example, for test offset-reloc-fieldinfo-2.ll, this patch
generates 7 instead of 6 relocations for non-alu32 mode, but it
actually reduced instruction count from 29 to 26.
Differential Revision: https://reviews.llvm.org/D71790
2019-12-20 07:21:53 +08:00
|
|
|
}
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
|
2018-12-20 00:40:25 +08:00
|
|
|
// Skip this instruction if no DebugLoc or the DebugLoc
|
|
|
|
// is the same as the previous instruction.
|
|
|
|
const DebugLoc &DL = MI->getDebugLoc();
|
|
|
|
if (!DL || PrevInstLoc == DL) {
|
|
|
|
// This instruction will be skipped, no LineInfo has
|
|
|
|
// been generated, construct one based on function signature.
|
|
|
|
if (LineInfoGenerated == false) {
|
|
|
|
auto *S = MI->getMF()->getFunction().getSubprogram();
|
|
|
|
MCSymbol *FuncLabel = Asm->getFunctionBegin();
|
|
|
|
constructLineInfo(S, FuncLabel, S->getLine(), 0);
|
|
|
|
LineInfoGenerated = true;
|
|
|
|
}
|
|
|
|
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Create a temporary label to remember the insn for lineinfo.
|
|
|
|
MCSymbol *LineSym = OS.getContext().createTempSymbol();
|
2020-02-15 11:21:58 +08:00
|
|
|
OS.emitLabel(LineSym);
|
2018-12-20 00:40:25 +08:00
|
|
|
|
|
|
|
// Construct the lineinfo.
|
|
|
|
auto SP = DL.get()->getScope()->getSubprogram();
|
|
|
|
constructLineInfo(SP, LineSym, DL.getLine(), DL.getCol());
|
|
|
|
|
|
|
|
LineInfoGenerated = true;
|
|
|
|
PrevInstLoc = DL;
|
|
|
|
}
|
|
|
|
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
void BTFDebug::processGlobals(bool ProcessingMapDef) {
|
2018-12-20 00:40:25 +08:00
|
|
|
// Collect all types referenced by globals.
|
|
|
|
const Module *M = MMI->getModule();
|
2019-03-15 13:51:25 +08:00
|
|
|
for (const GlobalVariable &Global : M->globals()) {
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
// Decide the section name.
|
|
|
|
StringRef SecName;
|
|
|
|
if (Global.hasSection()) {
|
|
|
|
SecName = Global.getSection();
|
2019-11-23 00:45:37 +08:00
|
|
|
} else if (Global.hasInitializer()) {
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
// data, bss, or readonly sections
|
|
|
|
if (Global.isConstant())
|
|
|
|
SecName = ".rodata";
|
|
|
|
else
|
|
|
|
SecName = Global.getInitializer()->isZeroValue() ? ".bss" : ".data";
|
2019-12-11 03:05:22 +08:00
|
|
|
} else {
|
|
|
|
// extern variables without explicit section,
|
|
|
|
// put them into ".extern" section.
|
|
|
|
SecName = ".extern";
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
if (ProcessingMapDef != SecName.startswith(".maps"))
|
|
|
|
continue;
|
|
|
|
|
2019-03-15 13:51:25 +08:00
|
|
|
SmallVector<DIGlobalVariableExpression *, 1> GVs;
|
|
|
|
Global.getDebugInfo(GVs);
|
2019-11-13 03:31:52 +08:00
|
|
|
|
|
|
|
// No type information, mostly internal, skip it.
|
|
|
|
if (GVs.size() == 0)
|
|
|
|
continue;
|
|
|
|
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
uint32_t GVTypeId = 0;
|
2019-03-15 13:51:25 +08:00
|
|
|
for (auto *GVE : GVs) {
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
if (SecName.startswith(".maps"))
|
|
|
|
visitMapDefType(GVE->getVariable()->getType(), GVTypeId);
|
|
|
|
else
|
|
|
|
visitTypeEntry(GVE->getVariable()->getType(), GVTypeId, false, false);
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Only support the following globals:
|
|
|
|
// . static variables
|
2019-12-07 15:00:41 +08:00
|
|
|
// . non-static weak or non-weak global variables
|
2019-11-23 00:45:37 +08:00
|
|
|
// . weak or non-weak extern global variables
|
|
|
|
// Whether DataSec is readonly or not can be found from corresponding ELF
|
|
|
|
// section flags. Whether a BTF_KIND_VAR is a weak symbol or not
|
|
|
|
// can be found from the corresponding ELF symbol table.
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
auto Linkage = Global.getLinkage();
|
|
|
|
if (Linkage != GlobalValue::InternalLinkage &&
|
2019-12-07 15:00:41 +08:00
|
|
|
Linkage != GlobalValue::ExternalLinkage &&
|
2019-11-23 00:45:37 +08:00
|
|
|
Linkage != GlobalValue::WeakAnyLinkage &&
|
|
|
|
Linkage != GlobalValue::ExternalWeakLinkage)
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
continue;
|
|
|
|
|
2019-11-23 00:45:37 +08:00
|
|
|
uint32_t GVarInfo;
|
|
|
|
if (Linkage == GlobalValue::InternalLinkage) {
|
|
|
|
GVarInfo = BTF::VAR_STATIC;
|
|
|
|
} else if (Global.hasInitializer()) {
|
|
|
|
GVarInfo = BTF::VAR_GLOBAL_ALLOCATED;
|
|
|
|
} else {
|
|
|
|
GVarInfo = BTF::VAR_GLOBAL_EXTERNAL;
|
|
|
|
}
|
|
|
|
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
auto VarEntry =
|
2019-08-15 23:54:37 +08:00
|
|
|
std::make_unique<BTFKindVar>(Global.getName(), GVTypeId, GVarInfo);
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
uint32_t VarId = addType(std::move(VarEntry));
|
|
|
|
|
2019-12-11 03:05:22 +08:00
|
|
|
assert(!SecName.empty());
|
2019-11-23 00:45:37 +08:00
|
|
|
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
// Find or create a DataSec
|
2020-01-29 03:23:46 +08:00
|
|
|
if (DataSecEntries.find(std::string(SecName)) == DataSecEntries.end()) {
|
|
|
|
DataSecEntries[std::string(SecName)] =
|
|
|
|
std::make_unique<BTFKindDataSec>(Asm, std::string(SecName));
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
// Calculate symbol size
|
|
|
|
const DataLayout &DL = Global.getParent()->getDataLayout();
|
|
|
|
uint32_t Size = DL.getTypeAllocSize(Global.getType()->getElementType());
|
|
|
|
|
2020-01-29 03:23:46 +08:00
|
|
|
DataSecEntries[std::string(SecName)]->addVar(VarId, Asm->getSymbol(&Global),
|
|
|
|
Size);
|
2018-12-20 00:40:25 +08:00
|
|
|
}
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/// Emit proper patchable instructions.
|
|
|
|
bool BTFDebug::InstLower(const MachineInstr *MI, MCInst &OutMI) {
|
|
|
|
if (MI->getOpcode() == BPF::LD_imm64) {
|
|
|
|
const MachineOperand &MO = MI->getOperand(1);
|
|
|
|
if (MO.isGlobal()) {
|
|
|
|
const GlobalValue *GVal = MO.getGlobal();
|
|
|
|
auto *GVar = dyn_cast<GlobalVariable>(GVal);
|
|
|
|
if (GVar && GVar->hasAttribute(BPFCoreSharedInfo::AmaAttr)) {
|
[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
|
|
|
// Emit "mov ri, <imm>" for patched immediate.
|
|
|
|
uint32_t Imm = PatchImms[GVar->getName().str()];
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
OutMI.setOpcode(BPF::MOV_ri);
|
|
|
|
OutMI.addOperand(MCOperand::createReg(MI->getOperand(0).getReg()));
|
|
|
|
OutMI.addOperand(MCOperand::createImm(Imm));
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
}
|
[BPF] Enable relocation location for load/store/shifts
Previous btf field relocation is always at assignment like
r1 = 4
which is converted from an ld_imm64 instruction.
This patch did an optimization such that relocation
instruction might be load/store/shift. Specically, the
following insns may also have relocation, except BPF_MOV:
LDB, LDH, LDW, LDD, STB, STH, STW, STD,
LDB32, LDH32, LDW32, STB32, STH32, STW32,
SLL, SRL, SRA
To accomplish this, a few BPF target specific
codegen only instructions are invented. They
are generated at backend BPF SimplifyPatchable phase,
which is at early llc phase when SSA form is available.
The new codegen only instructions will be converted to
real proper instructions at the codegen and BTF emission stage.
Note that, as revealed by a few tests, this optimization might
be actual generating more relocations:
Scenario 1:
if (...) {
... __builtin_preserve_field_info(arg->b2, 0) ...
} else {
... __builtin_preserve_field_info(arg->b2, 0) ...
}
Compiler could do CSE to only have one relocation. But if both
of the above is translated into codegen internal instructions,
the compiler will not be able to do that.
Scenario 2:
offset = ... __builtin_preserve_field_info(arg->b2, 0) ...
...
... offset ...
... offset ...
... offset ...
For whatever reason, the compiler might be temporarily do copy
propagation of the righthand of "offset" assignment like
... __builtin_preserve_field_info(arg->b2, 0) ...
... __builtin_preserve_field_info(arg->b2, 0) ...
and CSE will be able to deduplicate later.
But if these intrinsics are converted to BPF pseudo instructions,
they will not be able to get deduplicated.
I do not expect we have big instruction count difference.
It may actually reduce instruction count since now relocation
is in deeper insn dependency chain.
For example, for test offset-reloc-fieldinfo-2.ll, this patch
generates 7 instead of 6 relocations for non-alu32 mode, but it
actually reduced instruction count from 29 to 26.
Differential Revision: https://reviews.llvm.org/D71790
2019-12-20 07:21:53 +08:00
|
|
|
} else if (MI->getOpcode() == BPF::CORE_MEM ||
|
|
|
|
MI->getOpcode() == BPF::CORE_ALU32_MEM ||
|
|
|
|
MI->getOpcode() == BPF::CORE_SHIFT) {
|
|
|
|
const MachineOperand &MO = MI->getOperand(3);
|
|
|
|
if (MO.isGlobal()) {
|
|
|
|
const GlobalValue *GVal = MO.getGlobal();
|
|
|
|
auto *GVar = dyn_cast<GlobalVariable>(GVal);
|
|
|
|
if (GVar && GVar->hasAttribute(BPFCoreSharedInfo::AmaAttr)) {
|
|
|
|
uint32_t Imm = PatchImms[GVar->getName().str()];
|
|
|
|
OutMI.setOpcode(MI->getOperand(1).getImm());
|
|
|
|
if (MI->getOperand(0).isImm())
|
|
|
|
OutMI.addOperand(MCOperand::createImm(MI->getOperand(0).getImm()));
|
|
|
|
else
|
|
|
|
OutMI.addOperand(MCOperand::createReg(MI->getOperand(0).getReg()));
|
|
|
|
OutMI.addOperand(MCOperand::createReg(MI->getOperand(2).getReg()));
|
|
|
|
OutMI.addOperand(MCOperand::createImm(Imm));
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
}
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
}
|
|
|
|
return false;
|
|
|
|
}
|
2018-12-20 00:40:25 +08:00
|
|
|
|
2019-12-18 08:24:23 +08:00
|
|
|
void BTFDebug::processFuncPrototypes(const Function *F) {
|
|
|
|
if (!F)
|
|
|
|
return;
|
2019-11-23 00:45:37 +08:00
|
|
|
|
2019-12-18 08:24:23 +08:00
|
|
|
const DISubprogram *SP = F->getSubprogram();
|
|
|
|
if (!SP || SP->isDefinition())
|
|
|
|
return;
|
2019-11-23 00:45:37 +08:00
|
|
|
|
2019-12-18 08:24:23 +08:00
|
|
|
// Do not emit again if already emitted.
|
|
|
|
if (ProtoFunctions.find(F) != ProtoFunctions.end())
|
|
|
|
return;
|
|
|
|
ProtoFunctions.insert(F);
|
2019-11-23 00:45:37 +08:00
|
|
|
|
2019-12-18 08:24:23 +08:00
|
|
|
uint32_t ProtoTypeId;
|
|
|
|
const std::unordered_map<uint32_t, StringRef> FuncArgNames;
|
|
|
|
visitSubroutineType(SP->getType(), false, FuncArgNames, ProtoTypeId);
|
2019-11-23 00:45:37 +08:00
|
|
|
|
2019-12-18 08:24:23 +08:00
|
|
|
uint8_t Scope = BTF::FUNC_EXTERN;
|
|
|
|
auto FuncTypeEntry =
|
|
|
|
std::make_unique<BTFTypeFunc>(SP->getName(), ProtoTypeId, Scope);
|
|
|
|
addType(std::move(FuncTypeEntry));
|
2019-11-23 00:45:37 +08:00
|
|
|
}
|
|
|
|
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
void BTFDebug::endModule() {
|
|
|
|
// Collect MapDef globals if not collected yet.
|
|
|
|
if (MapDefNotCollected) {
|
|
|
|
processGlobals(true);
|
|
|
|
MapDefNotCollected = false;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Collect global types/variables except MapDef globals.
|
|
|
|
processGlobals(false);
|
2019-11-23 00:45:37 +08:00
|
|
|
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
for (auto &DataSec : DataSecEntries)
|
|
|
|
addType(std::move(DataSec.second));
|
|
|
|
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
// Fixups
|
|
|
|
for (auto &Fixup : FixupDerivedTypes) {
|
|
|
|
StringRef TypeName = Fixup.first;
|
|
|
|
bool IsUnion = Fixup.second.first;
|
|
|
|
|
|
|
|
// Search through struct types
|
|
|
|
uint32_t StructTypeId = 0;
|
|
|
|
for (const auto &StructType : StructTypes) {
|
|
|
|
if (StructType->getName() == TypeName) {
|
|
|
|
StructTypeId = StructType->getId();
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (StructTypeId == 0) {
|
2019-08-15 23:54:37 +08:00
|
|
|
auto FwdTypeEntry = std::make_unique<BTFTypeFwd>(TypeName, IsUnion);
|
[BPF] Support for compile once and run everywhere
Introduction
============
This patch added intial support for bpf program compile once
and run everywhere (CO-RE).
The main motivation is for bpf program which depends on
kernel headers which may vary between different kernel versions.
The initial discussion can be found at https://lwn.net/Articles/773198/.
Currently, bpf program accesses kernel internal data structure
through bpf_probe_read() helper. The idea is to capture the
kernel data structure to be accessed through bpf_probe_read()
and relocate them on different kernel versions.
On each host, right before bpf program load, the bpfloader
will look at the types of the native linux through vmlinux BTF,
calculates proper access offset and patch the instruction.
To accommodate this, three intrinsic functions
preserve_{array,union,struct}_access_index
are introduced which in clang will preserve the base pointer,
struct/union/array access_index and struct/union debuginfo type
information. Later, bpf IR pass can reconstruct the whole gep
access chains without looking at gep itself.
This patch did the following:
. An IR pass is added to convert preserve_*_access_index to
global variable who name encodes the getelementptr
access pattern. The global variable has metadata
attached to describe the corresponding struct/union
debuginfo type.
. An SimplifyPatchable MachineInstruction pass is added
to remove unnecessary loads.
. The BTF output pass is enhanced to generate relocation
records located in .BTF.ext section.
Typical CO-RE also needs support of global variables which can
be assigned to different values to different hosts. For example,
kernel version can be used to guard different versions of codes.
This patch added the support for patchable externals as well.
Example
=======
The following is an example.
struct pt_regs {
long arg1;
long arg2;
};
struct sk_buff {
int i;
struct net_device *dev;
};
#define _(x) (__builtin_preserve_access_index(x))
static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr) =
(void *) 4;
extern __attribute__((section(".BPF.patchable_externs"))) unsigned __kernel_version;
int bpf_prog(struct pt_regs *ctx) {
struct net_device *dev = 0;
// ctx->arg* does not need bpf_probe_read
if (__kernel_version >= 41608)
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg1)->dev));
else
bpf_probe_read(&dev, sizeof(dev), _(&((struct sk_buff *)ctx->arg2)->dev));
return dev != 0;
}
In the above, we want to translate the third argument of
bpf_probe_read() as relocations.
-bash-4.4$ clang -target bpf -O2 -g -S trace.c
The compiler will generate two new subsections in .BTF.ext,
OffsetReloc and ExternReloc.
OffsetReloc is to record the structure member offset operations,
and ExternalReloc is to record the external globals where
only u8, u16, u32 and u64 are supported.
BPFOffsetReloc Size
struct SecLOffsetReloc for ELF section #1
A number of struct BPFOffsetReloc for ELF section #1
struct SecOffsetReloc for ELF section #2
A number of struct BPFOffsetReloc for ELF section #2
...
BPFExternReloc Size
struct SecExternReloc for ELF section #1
A number of struct BPFExternReloc for ELF section #1
struct SecExternReloc for ELF section #2
A number of struct BPFExternReloc for ELF section #2
struct BPFOffsetReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t TypeID; ///< TypeID for the relocation
uint32_t OffsetNameOff; ///< The string to traverse types
};
struct BPFExternReloc {
uint32_t InsnOffset; ///< Byte offset in this section
uint32_t ExternNameOff; ///< The string for external variable
};
Note that only externs with attribute section ".BPF.patchable_externs"
are considered for Extern Reloc which will be patched by bpf loader
right before the load.
For the above test case, two offset records and one extern record
will be generated:
OffsetReloc records:
.long .Ltmp12 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
.long .Ltmp18 # Insn Offset
.long 7 # TypeId
.long 242 # Type Decode String
ExternReloc record:
.long .Ltmp5 # Insn Offset
.long 165 # External Variable
In string table:
.ascii "0:1" # string offset=242
.ascii "__kernel_version" # string offset=165
The default member offset can be calculated as
the 2nd member offset (0 representing the 1st member) of struct "sk_buff".
The asm code:
.Ltmp5:
.Ltmp6:
r2 = 0
r3 = 41608
.Ltmp7:
.Ltmp8:
.loc 1 18 9 is_stmt 0 # t.c:18:9
.Ltmp9:
if r3 > r2 goto LBB0_2
.Ltmp10:
.Ltmp11:
.loc 1 0 9 # t.c:0:9
.Ltmp12:
r2 = 8
.Ltmp13:
.loc 1 19 66 is_stmt 1 # t.c:19:66
.Ltmp14:
.Ltmp15:
r3 = *(u64 *)(r1 + 0)
goto LBB0_3
.Ltmp16:
.Ltmp17:
LBB0_2:
.loc 1 0 66 is_stmt 0 # t.c:0:66
.Ltmp18:
r2 = 8
.loc 1 21 66 is_stmt 1 # t.c:21:66
.Ltmp19:
r3 = *(u64 *)(r1 + 8)
.Ltmp20:
.Ltmp21:
LBB0_3:
.loc 1 0 66 is_stmt 0 # t.c:0:66
r3 += r2
r1 = r10
.Ltmp22:
.Ltmp23:
.Ltmp24:
r1 += -8
r2 = 8
call 4
For instruction .Ltmp12 and .Ltmp18, "r2 = 8", the number
8 is the structure offset based on the current BTF.
Loader needs to adjust it if it changes on the host.
For instruction .Ltmp5, "r2 = 0", the external variable
got a default value 0, loader needs to supply an appropriate
value for the particular host.
Compiling to generate object code and disassemble:
0000000000000000 bpf_prog:
0: b7 02 00 00 00 00 00 00 r2 = 0
1: 7b 2a f8 ff 00 00 00 00 *(u64 *)(r10 - 8) = r2
2: b7 02 00 00 00 00 00 00 r2 = 0
3: b7 03 00 00 88 a2 00 00 r3 = 41608
4: 2d 23 03 00 00 00 00 00 if r3 > r2 goto +3 <LBB0_2>
5: b7 02 00 00 08 00 00 00 r2 = 8
6: 79 13 00 00 00 00 00 00 r3 = *(u64 *)(r1 + 0)
7: 05 00 02 00 00 00 00 00 goto +2 <LBB0_3>
0000000000000040 LBB0_2:
8: b7 02 00 00 08 00 00 00 r2 = 8
9: 79 13 08 00 00 00 00 00 r3 = *(u64 *)(r1 + 8)
0000000000000050 LBB0_3:
10: 0f 23 00 00 00 00 00 00 r3 += r2
11: bf a1 00 00 00 00 00 00 r1 = r10
12: 07 01 00 00 f8 ff ff ff r1 += -8
13: b7 02 00 00 08 00 00 00 r2 = 8
14: 85 00 00 00 04 00 00 00 call 4
Instructions #2, #5 and #8 need relocation resoutions from the loader.
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D61524
llvm-svn: 365503
2019-07-09 23:28:41 +08:00
|
|
|
StructTypeId = addType(std::move(FwdTypeEntry));
|
|
|
|
}
|
|
|
|
|
|
|
|
for (auto &DType : Fixup.second.second) {
|
|
|
|
DType->setPointeeType(StructTypeId);
|
|
|
|
}
|
|
|
|
}
|
[BPF] Add BTF Var and DataSec Support
Two new kinds, BTF_KIND_VAR and BTF_KIND_DATASEC, are added.
BTF_KIND_VAR has the following specification:
btf_type.name: var name
btf_type.info: type kind
btf_type.type: var type
// btf_type is followed by one u32
u32: varinfo (currently, only 0 - static, 1 - global allocated in elf sections)
Not all globals are supported in this patch. The following globals are supported:
. static variables with or without section attributes
. global variables with section attributes
The inclusion of globals with section attributes
is for future potential extraction of key/value
type id's from map definition.
BTF_KIND_DATASEC has the following specification:
btf_type.name: section name associated with variable or
one of .data/.bss/.readonly
btf_type.info: type kind and vlen for # of variables
btf_type.size: 0
#vlen number of the following:
u32: id of corresponding BTF_KIND_VAR
u32: in-session offset of the var
u32: the size of memory var occupied
At the time of debug info emission, the data section
size is unknown, so the btf_type.size = 0 for
BTF_KIND_DATASEC. The loader can patch it during
loading time.
The in-session offseet of the var is only available
for static variables. For global variables, the
loader neeeds to assign the global variable symbol value in
symbol table to in-section offset.
The size of memory is used to specify the amount of the
memory a variable occupies. Typically, it equals to
the type size, but for certain structures, e.g.,
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
The static variable s2 has size of 20.
Note that for BTF_KIND_DATASEC name, the section name
does not contain object name. The compiler does have
input module name. For example, two cases below:
. clang -target bpf -O2 -g -c test.c
The compiler knows the input file (module) is test.c
and can generate sec name like test.data/test.bss etc.
. clang -target bpf -O2 -g -emit-llvm -c test.c -o - |
llc -march=bpf -filetype=obj -o test.o
The llc compiler has the input file as stdin, and
would generate something like stdin.data/stdin.bss etc.
which does not really make sense.
For any user specificed section name, e.g.,
static volatile int a __attribute__((section("id1")));
static volatile const int b __attribute__((section("id2")));
The DataSec with name "id1" and "id2" does not contain
information whether the section is readonly or not.
The loader needs to check the corresponding elf section
flags for such information.
A simple example:
-bash-4.4$ cat t.c
int g1;
int g2 = 3;
const int g3 = 4;
static volatile int s1;
struct tt {
int a;
int b;
char c[];
};
static volatile struct tt s2 = {3, 4, "abcdefghi"};
static volatile const int s3 = 4;
int m __attribute__((section("maps"), used)) = 4;
int test() { return g1 + g2 + g3 + s1 + s2.a + s3 + m; }
-bash-4.4$ clang -target bpf -O2 -g -S t.c
Checking t.s, 4 BTF_KIND_VAR's are generated (s1, s2, s3 and m).
4 BTF_KIND_DATASEC's are generated with names
".data", ".bss", ".rodata" and "maps".
Signed-off-by: Yonghong Song <yhs@fb.com>
Differential Revision: https://reviews.llvm.org/D59441
llvm-svn: 356326
2019-03-16 23:36:31 +08:00
|
|
|
|
2018-12-20 00:40:25 +08:00
|
|
|
// Complete BTF type cross refereences.
|
|
|
|
for (const auto &TypeEntry : TypeEntries)
|
|
|
|
TypeEntry->completeType(*this);
|
|
|
|
|
|
|
|
// Emit BTF sections.
|
|
|
|
emitBTFSection();
|
|
|
|
emitBTFExtSection();
|
|
|
|
}
|