path: root/src/structs.rs

use bitflags::bitflags;

#[repr(C, packed)]
#[derive(Debug, Copy, Clone)]
pub struct ElfIdent {
    /// Magic number - 0x7F, then 'ELF' in ASCII
    pub magic: [u8; 4],

    /// 1 = 32 bit, 2 = 64 bit
    pub class: Class,

    // 1 = little endian, 2 = big endian
    pub data: Endian,

    /// ELF header version
    pub version: u8,

    /// OS ABI - usually 0 for System V
    pub OSABI: OSABI,

    // This field is used to distinguish among incompatible versions of an ABI.
    pub ABIVersion: u8,

    /// Unused/padding
    pub _unused: [u8; 7],
}

impl std::fmt::Display for ElfIdent {
    fn fmt(&self, formatter: &mut std::fmt::Formatter) -> std::fmt::Result {
        formatter.write_str("  Magic:   ")?;

        for b in unsafe { *(std::ptr::addr_of!(self.magic) as *const [u8; 16]) } {
            formatter.pad(&format!("{:02x?} ", b))?;
        }

        formatter.write_str("\n")?;

        formatter.write_fmt(format_args!(
            "  Class:                             {:?}\n",
            self.class
        ))?;
        formatter.write_fmt(format_args!(
            "  Data:                              {}\n",
            self.data
        ))?;
        formatter.write_fmt(format_args!(
            "  Version:                           {} ({})\n",
            self.version,
            match self.version {
                0 => "invalid",
                1 => "current",
                2_u8..=u8::MAX => todo!(), // need to cover all cases
            }
        ))?;
        formatter.write_fmt(format_args!(
            "  OS/ABI:                            {}\n",
            self.OSABI
        ))?;
        formatter.write_fmt(format_args!(
            "  ABI Version:                       {}\n",
            self.ABIVersion
        ))
    }
}

// https://man7.org/linux/man-pages/man5/elf.5.html
// https://wiki.osdev.org/ELF
// https://en.wikipedia.org/wiki/Executable_and_Linkable_Format
#[repr(C)]
#[derive(Debug)]
pub struct ElfHeader {
    pub ident: ElfIdent,

    /// 1 = relocatable, 2 = executable, 3 = shared, 4 = core
    pub r#type: Type,

    /// Instruction set - see table below
    pub machine: Machine,

    /// ELF Version
    pub version: u32,

    /// Program entry position (virtual)
    pub entry: u64,

    /// Program header table position (bytes into file)
    pub phoff: u64,

    /// Section header table position (bytes into file)
    pub shoff: u64,

    /// This member holds processor-specific flags associated with the file
    /// Currently, no flags have been defined.
    pub flags: u32,

    /// Header size
    pub ehsize: u16,

    /// Size of an entry in the program header table
    pub phentsize: u16,

    /// Number of entries in the program header table
    pub phnum: u16,

    /// Size of an entry in the section header table
    pub shentsize: u16,

    /// Number of entries in the section header table
    pub shnum: u16,

    /// Index in section header table with the section names
    pub shstrndx: u16,
}

impl std::fmt::Display for ElfHeader {
    fn fmt(&self, formatter: &mut std::fmt::Formatter) -> std::fmt::Result {
        // yes, this is really what they do in readelf.c
        formatter.write_fmt(format_args!("{}", self.ident))?;
        formatter.write_fmt(format_args!(
            "  Type:                              {}\n",
            self.r#type
        ))?;
        formatter.write_fmt(format_args!(
            "  Machine:                           {}\n",
            self.machine
        ))?;
        formatter.write_fmt(format_args!(
            "  Version:                           {:#02x?}\n",
            self.version
        ))?;
        formatter.write_fmt(format_args!(
            "  Entry point address:               {:#x?}\n",
            self.entry
        ))?;
        formatter.write_fmt(format_args!(
            "  Start of program headers:          {} (bytes into file)\n",
            self.phoff
        ))?;
        formatter.write_fmt(format_args!(
            "  Start of section headers:          {} (bytes into file)\n",
            self.shoff
        ))?;
        formatter.write_fmt(format_args!(
            "  Flags:                             {:#x?}\n",
            self.flags
        ))?;
        formatter.write_fmt(format_args!(
            "  Size of this header:               {} (bytes)\n",
            self.ehsize
        ))?;
        formatter.write_fmt(format_args!(
            "  Size of program headers:           {} (bytes)\n",
            self.phentsize
        ))?;
        formatter.write_fmt(format_args!(
            "  Number of program headers:         {}\n",
            self.phnum
        ))?;
        formatter.write_fmt(format_args!(
            "  Size of section headers:           {} (bytes)\n",
            self.shentsize
        ))?;
        formatter.write_fmt(format_args!(
            "  Number of section headers:         {}\n",
            self.shnum
        ))?;
        formatter.write_fmt(format_args!(
            "  Section header string table index: {}\n",
            self.shstrndx
        ))
    }
}

#[derive(Debug, Copy, Clone)]
#[repr(u16)]
pub enum Type {
    None = 0,
    Rel = 1,
    Exec = 2,
    Dyn = 3,
    Core = 4,
}

impl std::fmt::Display for Type {
    fn fmt(&self, formatter: &mut std::fmt::Formatter) -> std::fmt::Result {
        match self {
            Type::None => formatter.write_str("NONE (None)"),
            Type::Rel => formatter.write_str("REL (Relocatable file)"),
            Type::Exec => formatter.write_str("EXEC (Executable file)"),
            Type::Dyn => formatter.write_str("DYN (Shared object file)"),
            Type::Core => formatter.write_str("CORE (Core file)"),
        }
    }
}

#[derive(Debug, Copy, Clone)]
#[repr(u16)]
pub enum Machine {
    // there are many many many more, im just gonna do x86
    // https://github.com/bminor/binutils-gdb/blob/master/binutils/readelf.c#L2746
    None = 1,
    X86_64 = 62,
}

impl std::fmt::Display for Machine {
    fn fmt(&self, formatter: &mut std::fmt::Formatter) -> std::fmt::Result {
        match self {
            Machine::None => formatter.write_str("None"),
            Machine::X86_64 => formatter.write_str("Advanced Micro Devices X86-64"),
        }
    }
}

#[derive(Debug, Copy, Clone)]
#[repr(u8)]
pub enum Class {
    ELF32 = 1,
    ELF64 = 2,
}

#[derive(Debug, Copy, Clone)]
#[repr(u8)]
pub enum OSABI {
    None = 0x00,
    SystemV = 0x01,
    // HPUX = 0x02,
    // Solaris = 0x03,
    // IRIX = 0x04,
    // FreeBSD = 0x05,
    // TRU64 = 0x06,
    // ARM = 0x07,
    Standalone = 0x08,
}

impl std::fmt::Display for OSABI {
    fn fmt(&self, formatter: &mut std::fmt::Formatter) -> std::fmt::Result {
        match self {
            OSABI::None => formatter.write_str("UNIX - System V"),
            OSABI::SystemV => formatter.write_str("UNIX - System V"),
            OSABI::Standalone => formatter.write_str("Standalone"),
        }
    }
}

#[derive(Debug, Copy, Clone)]
#[repr(u8)]
pub enum Endian {
    Little = 1,
    Big = 2,
}

impl std::fmt::Display for Endian {
    fn fmt(&self, formatter: &mut std::fmt::Formatter) -> std::fmt::Result {
        match self {
            Endian::Little => formatter.write_str("2's complement, little endian"),
            Endian::Big => formatter.write_str("1's complement, big endian"),
        }
    }
}

#[derive(Debug, Copy, Clone)]
#[repr(C)]
pub struct ElfSectionHeader {
    /// This member specifies the name of the section.  Its value
    /// is an index into the section header string table section,
    /// giving the location of a null-terminated string.
    pub name: u32,

    /// This member categorizes the section's contents and
    /// semantics.
    pub r#type: ElfSectionType,

    /// Sections support one-bit flags that describe miscellaneous
    /// attributes.  If a flag bit is set in sh_flags, the
    /// attribute is "on" for the section.  Otherwise, the
    /// attribute is "off" or does not apply.  Undefined
    /// attributes are set to zero.
    pub flags: ElfSectionFlags,

    /// If this section appears in the memory image of a process,
    /// this member holds the address at which the section's first
    /// byte should reside.  Otherwise, the member contains zero.
    pub addr: u64,

    /// This member's value holds the byte offset from the
    /// beginning of the file to the first byte in the section.
    /// One section type, SHT_NOBITS, occupies no space in the
    /// file, and its sh_offset member locates the conceptual
    /// placement in the file.
    pub offset: u64,

    /// This member holds the section's size in bytes.  Unless the
    /// section type is SHT_NOBITS, the section occupies sh_size
    /// bytes in the file.  A section of type SHT_NOBITS may have
    /// a nonzero size, but it occupies no space in the file.
    pub size: u64,

    /// This member holds a section header table index link, whose
    /// interpretation depends on the section type.
    pub link: u32,

    /// This member holds extra information, whose interpretation
    /// depends on the section type.
    pub info: u32,

    /// Some sections have address alignment constraints.  If a
    /// section holds a doubleword, the system must ensure
    /// doubleword alignment for the entire section.  That is, the
    /// value of sh_addr must be congruent to zero, modulo the
    /// value of sh_addralign.  Only zero and positive integral
    /// powers of two are allowed.  The value 0 or 1 means that
    /// the section has no alignment constraints.
    pub addralign: u64,

    /// Some sections hold a table of fixed-sized entries, such as
    /// a symbol table.  For such a section, this member gives the
    /// size in bytes for each entry.  This member contains zero
    /// if the section does not hold a table of fixed-size
    /// entries.
    pub entsize: u64,
}

impl std::fmt::Display for ElfSectionHeader {
    fn fmt(&self, formatter: &mut std::fmt::Formatter) -> std::fmt::Result {
        formatter.write_fmt(format_args!(
            "{: <16} {:0>16x} {:0>8x}\n       {:0>16x} {:0>16x} {: ^10} {: <5} {: <5} {}",
            self.r#type,
            self.addr,
            self.offset,
            self.size,
            self.entsize,
            self.flags,
            self.link,
            self.info,
            self.addralign
        ))?;
        Ok(())
    }
}

#[derive(Debug, Copy, Clone, PartialEq)]
#[repr(u32)]
pub enum ElfSectionType {
    /// This value marks the section header as inactive.
    /// It does not have an associated section.  Other
    /// members of the section header have undefined
    /// values.
    Null = 0,

    /// This section holds information defined by the
    /// program, whose format and meaning are determined
    /// solely by the program.
    ProgBits = 1,

    /// This section holds a symbol table.  Typically,
    /// SHT_SYMTAB provides symbols for link editing,
    /// though it may also be used for dynamic linking.  As
    /// a complete symbol table, it may contain many
    /// symbols unnecessary for dynamic linking.  An object
    /// file can also contain a SHT_DYNSYM section.
    SymTab = 2,

    /// This section holds a string table.  An object file
    /// may have multiple string table sections.
    StrTab = 3,

    /// This section holds relocation entries with explicit
    /// addends, such as type Elf32_Rela for the 32-bit
    /// class of object files.  An object may have multiple
    /// relocation sections.
    Rela = 4,

    /// This section holds a symbol hash table.  An object
    /// participating in dynamic linking must contain a
    /// symbol hash table.  An object file may have only
    /// one hash table.
    Hash = 5,

    /// This section holds information for dynamic linking.
    /// An object file may have only one dynamic section.
    Dynamic = 6,

    /// This section holds notes (ElfN_Nhdr).
    Note = 7,

    /// A section of this type occupies no space in the
    /// file but otherwise resembles SHT_PROGBITS.
    /// Although this section contains no bytes, the
    /// sh_offset member contains the conceptual file
    /// offset.
    NoBits = 8,

    /// This section holds relocation offsets without
    /// explicit addends, such as type Elf32_Rel for the
    /// 32-bit class of object files.  An object file may
    /// have multiple relocation sections.
    Rel = 9,

    /// This section is reserved but has unspecified
    /// semantics.
    ShLib = 10,

    /// This section holds a minimal set of dynamic linking
    /// symbols.  An object file can also contain a
    /// SHT_SYMTAB section.
    DynSym = 11,

    InitArray = 14,
    FiniArray = 15,

    GnuHash = 0x6FFFFFF6,
    VerNeed = 0x6FFFFFFE,
    VerSym = 0x6FFFFFFF,
}

impl std::fmt::Display for ElfSectionType {
    fn fmt(&self, formatter: &mut std::fmt::Formatter) -> std::fmt::Result {
        match self {
            ElfSectionType::Null => "NULL".fmt(formatter),
            ElfSectionType::ProgBits => "PROGBITS".fmt(formatter),
            ElfSectionType::SymTab => "SYMTAB".fmt(formatter),
            ElfSectionType::StrTab => "STRTAB".fmt(formatter),
            ElfSectionType::Rela => "RELA".fmt(formatter),
            ElfSectionType::Hash => "HASH".fmt(formatter),
            ElfSectionType::Dynamic => "DYNAMIC".fmt(formatter),
            ElfSectionType::Note => "NOTE".fmt(formatter),
            ElfSectionType::NoBits => "NOBITS".fmt(formatter),
            ElfSectionType::Rel => "REL".fmt(formatter),
            ElfSectionType::ShLib => "SHLIB".fmt(formatter),
            ElfSectionType::DynSym => "DYNSYM".fmt(formatter),
            ElfSectionType::InitArray => "INIT_ARRAY".fmt(formatter),
            ElfSectionType::FiniArray => "FINI_ARRAY".fmt(formatter),
            ElfSectionType::GnuHash => "GNU_HASH".fmt(formatter),
            ElfSectionType::VerNeed => "VERNEED".fmt(formatter),
            ElfSectionType::VerSym => "VERSYM".fmt(formatter),
        }
    }
}

bitflags! {
    #[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord, Hash)]
    pub struct ElfSectionFlags: u64 {
        const WRITE = 0x1;
        const ALLOC = 0x2;
        const EXEC = 0x4;
    }
}

// PAIN IN THE ASS!!!!!!!
// https://github.com/aixoss/binutils/blob/master/binutils/readelf.c#L4966
// https://github.com/llvm-mirror/llvm/blob/2c4ca6832fa6b306ee6a7010bfb80a3f2596f824/tools/llvm-readobj/ELFDumper.cpp#L1176
impl std::fmt::Display for ElfSectionFlags {
    fn fmt(&self, formatter: &mut std::fmt::Formatter) -> std::fmt::Result {
        "  A".fmt(formatter);
        Ok(())
    }
}

#[derive(Debug, Clone, PartialEq, Eq)]
#[repr(C)]
pub struct ElfSymbol {
    /// This member holds an index into the symbol table's string table,
    /// which holds the character representations of the symbol names. If the
    /// value is non-zero, it represents a string table index that gives the
    /// symbol name. Otherwise, the symbol table entry has no name.
    pub name: u32,

    /// This member specifies the symbol's type and binding attributes.
    pub info: u8,

    /// This member currently specifies a symbol's visibility.
    pub other: u8,

    /// Every symbol table entry is defined in relation to some section. This
    /// member holds the relevant section header table index. As the sh_link and
    /// sh_info interpretation table and the related text describe, some section
    /// indexes indicate special meanings.
    ///
    /// If this member contains SHN_XINDEX, then the actual section header index
    /// is too large to fit in this field. The actual value is contained in the
    /// associated section of type SHT_SYMTAB_SHNDX.
    pub shndx: u16,

    /// This member gives the value of the associated symbol. Depending on the
    /// context, this may be an absolute value, an address, and so on.
    ///
    /// * In relocatable files, st_value holds alignment constraints for a
    ///   symbol whose section index is SHN_COMMON.
    /// * In relocatable files, st_value holds a section offset for a defined
    ///   symbol. st_value is an offset from the beginning of the section that
    ///   st_shndx identifies.
    /// * In executable and shared object files, st_value holds a virtual
    ///   address. To make these files' symbols more useful for the dynamic
    ///   linker, the section offset (file interpretation) gives way to a
    ///   virtual address (memory interpretation) for which the section number
    ///   is irrelevant.
    pub value: u64,

    /// This member gives the symbol's size.
    /// For example, a data object's size is the number of bytes contained in
    /// the object. This member holds 0 if the symbol has no size or an unknown
    /// size.
    pub size: u64,
}