tools/syz-declextract: rewrite

syz-declextract accumulated a bunch of code health problems
so that now it's hard to change/extend it, lots of new features
can only be added in in hacky ways and cause lots of code duplication.
It's also completly untested. Rewrite the tool to:
 - move as much code as possible to Go (working with the clang tool
   is painful for a number of reasons)
 - allow testing and add unit tests (first layer of tests test
   what information is produced by the clang tool, second layer
   of tests test how that information is transformed to descriptions)
 - allow extending the clang tool output to export arbitrary info
   in non-hacky way (now it produces arbitrary JSON instead of a mix
   of incomplete descriptions and interfaces)
 - remove code duplication in the clang tool and provide common
   infrastructure to add new analysis w/o causing more duplication
 - provide more convinient primitives in the clang tool
 - improve code style consistency and stick to the LLVM code style
   (in particular, variable names must start with a capital letter,
   single-statement blocks are not surrounded with {})
 - remove intermixing of code that works on different levels
   (currently we have AST analysis + busness logic + printfs
   all intermixed with each other)
 - provide several helper Go packages for better code structuring
   (e.g. pkg/clangtool just runs the tool on source files in parallel
   and returns results, this already separates a bunch of low-level
   logic from the rest of the code under a simple abstraction)

I've tried to make the output match the current output as much as possible
so that the diff is managable (in some cases at the cost of code quality,
this should be fixed in future commits). There are still some differences,
but hopefully they are managable for review (more includes/defines,
reordered some netlink attributes).

Fixed minor bugs are fixed along the way, but mostly NFC:
1. Some unions were incorrectly emitted as [varlen]
   (C unions are never varlen).
2. Only a of [packed], [align[N]] attributes was emitted
   for struct (both couldn't be emitted).

1 files changed, 175 insertions, 0 deletions

diff --git a/pkg/declextract/entity.go b/pkg/declextract/entity.go
new file mode 100644
index 000000000..57e589e40
--- /dev/null
+++ b/pkg/declextract/entity.go
@@ -0,0 +1,175 @@
+// Copyright 2024 syzkaller project authors. All rights reserved.
+// Use of this source code is governed by Apache 2 LICENSE that can be found in the LICENSE file.
+
+package declextract
+
+import (
+	"bytes"
+	"encoding/json"
+	"slices"
+)
+
+type Output struct {
+	Includes        []string         `json:"includes,omitempty"`
+	Defines         []*Define        `json:"defines,omitempty"`
+	Enums           []*Enum          `json:"enums,omitempty"`
+	Structs         []*Struct        `json:"structs,omitempty"`
+	Syscalls        []*Syscall       `json:"syscalls,omitempty"`
+	IouringOps      []*IouringOp     `json:"iouring_ops,omitempty"`
+	NetlinkFamilies []*NetlinkFamily `json:"netlink_families,omitempty"`
+	NetlinkPolicies []*NetlinkPolicy `json:"netlink_policies,omitempty"`
+}
+
+type Define struct {
+	Name  string `json:"name,omitempty"`
+	Value string `json:"value,omitempty"`
+}
+
+type Field struct {
+	Name        string `json:"name,omitempty"`
+	IsAnonymous bool   `json:"is_anonymous,omitempty"`
+	BitWidth    int    `json:"bit_width,omitempty"`
+	CountedBy   int    `json:"counted_by,omitempty"`
+	Type        *Type  `json:"type,omitempty"`
+
+	syzType string
+}
+
+type Syscall struct {
+	Func       string   `json:"func,omitempty"`
+	Args       []*Field `json:"args,omitempty"`
+	SourceFile string   `json:"source_file,omitempty"`
+}
+
+type IouringOp struct {
+	Name       string `json:"name,omitempty"`
+	Func       string `json:"func,omitempty"`
+	SourceFile string `json:"source_file,omitempty"`
+}
+
+type NetlinkFamily struct {
+	Name       string       `json:"name,omitempty"`
+	Ops        []*NetlinkOp `json:"ops,omitempty"`
+	SourceFile string       `json:"source_file,omitempty"`
+}
+
+type NetlinkPolicy struct {
+	Name  string         `json:"name,omitempty"`
+	Attrs []*NetlinkAttr `json:"attrs,omitempty"`
+}
+
+type NetlinkOp struct {
+	Name   string `json:"name,omitempty"`
+	Func   string `json:"func,omitempty"`
+	Access string `json:"access,omitempty"`
+	Policy string `json:"policy,omitempty"`
+}
+
+type NetlinkAttr struct {
+	Name         string `json:"name,omitempty"`
+	Kind         string `json:"kind,omitempty"`
+	MaxSize      int    `json:"max_size,omitempty"`
+	NestedPolicy string `json:"nested_policy,omitempty"`
+	Elem         *Type  `json:"elem,omitempty"`
+}
+
+type Struct struct {
+	Name     string   `json:"name,omitempty"`
+	ByteSize int      `json:"byte_size,omitempty"`
+	IsUnion  bool     `json:"is_union,omitempty"`
+	IsPacked bool     `json:"is_packed,omitempty"`
+	Align    int      `json:"align,omitempty"`
+	Fields   []*Field `json:"fields,omitempty"`
+
+	// TODO: remove me.
+	isVarlen bool
+}
+
+type Enum struct {
+	Name   string   `json:"name,omitempty"`
+	Values []string `json:"values,omitempty"`
+}
+
+type Type struct {
+	Int    *IntType    `json:"int,omitempty"`
+	Ptr    *PtrType    `json:"ptr,omitempty"`
+	Array  *ArrayType  `json:"array,omitempty"`
+	Buffer *BufferType `json:"buffer,omitempty"`
+	Struct string      `json:"struct,omitempty"`
+}
+
+type IntType struct {
+	ByteSize int    `json:"byte_size,omitempty"`
+	Name     string `json:"name,omitempty"`
+	Base     string `json:"base,omitempty"`
+	Enum     string `json:"enum,omitempty"`
+
+	isBigEndian bool
+}
+
+type PtrType struct {
+	Elem    *Type `json:"elem,omitempty"`
+	IsConst bool  `json:"is_const,omitempty"`
+}
+
+type ArrayType struct {
+	Elem    *Type `json:"elem,omitempty"`
+	MinSize int   `json:"min_size,omitempty"`
+	MaxSize int   `json:"max_size,omitempty"`
+}
+
+type BufferType struct {
+	MinSize         int  `json:"min_size,omitempty"`
+	MaxSize         int  `json:"max_size,omitempty"`
+	IsString        bool `json:"is_string,omitempty"`
+	IsNonTerminated bool `json:"is_non_terminated,omitempty"`
+}
+
+func (out *Output) Merge(other *Output) {
+	out.Includes = append(out.Includes, other.Includes...)
+	out.Defines = append(out.Defines, other.Defines...)
+	out.Enums = append(out.Enums, other.Enums...)
+	out.Structs = append(out.Structs, other.Structs...)
+	out.Syscalls = append(out.Syscalls, other.Syscalls...)
+	out.IouringOps = append(out.IouringOps, other.IouringOps...)
+	out.NetlinkFamilies = append(out.NetlinkFamilies, other.NetlinkFamilies...)
+	out.NetlinkPolicies = append(out.NetlinkPolicies, other.NetlinkPolicies...)
+}
+
+func (out *Output) SortAndDedup() {
+	out.Includes = sortAndDedupSlice(out.Includes)
+	out.Defines = sortAndDedupSlice(out.Defines)
+	out.Enums = sortAndDedupSlice(out.Enums)
+	out.Structs = sortAndDedupSlice(out.Structs)
+	out.Syscalls = sortAndDedupSlice(out.Syscalls)
+	out.IouringOps = sortAndDedupSlice(out.IouringOps)
+	out.NetlinkFamilies = sortAndDedupSlice(out.NetlinkFamilies)
+	out.NetlinkPolicies = sortAndDedupSlice(out.NetlinkPolicies)
+}
+
+// SetSoureFile attaches the source file to the entities that need it.
+// The clang tool could do it, but it looks easier to do it here.
+func (out *Output) SetSourceFile(file string) {
+	for _, call := range out.Syscalls {
+		call.SourceFile = file
+	}
+	for _, fam := range out.NetlinkFamilies {
+		fam.SourceFile = file
+	}
+	for _, op := range out.IouringOps {
+		op.SourceFile = file
+	}
+}
+
+func sortAndDedupSlice[Slice ~[]E, E any](s Slice) Slice {
+	slices.SortFunc(s, func(a, b E) int {
+		aa, _ := json.Marshal(a)
+		bb, _ := json.Marshal(b)
+		return bytes.Compare(aa, bb)
+	})
+	return slices.CompactFunc(s, func(a, b E) bool {
+		aa, _ := json.Marshal(a)
+		bb, _ := json.Marshal(b)
+		return bytes.Equal(aa, bb)
+	})
+}