/*
* CDDL HEADER START
*
* The contents of this file are subject to the terms of the
* Common Development and Distribution License (the "License").
* You may not use this file except in compliance with the License.
*
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
* See the License for the specific language governing permissions
* and limitations under the License.
*
* When distributing Covered Code, include this CDDL HEADER in each
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
* If applicable, add the following below this CDDL HEADER, with the
* fields enclosed by brackets "[]" replaced with your own identifying
* information: Portions Copyright [yyyy] [name of copyright owner]
*
* CDDL HEADER END
*/
/*
* Copyright 2009 Sun Microsystems, Inc. All rights reserved.
* Use is subject to license terms.
*/
#include <assert.h>
#include <stdio.h>
#include <stdlib.h>
#include <stddef.h>
#include <string.h>
#include <memory.h>
#include <sys/sysmacros.h>
#include "Pcontrol.h"
#include "Psymtab_machelf.h"
/*
* This file contains code for use by Psymtab.c that is compiled once
* for each supported ELFCLASS.
*
* When processing ELF files, it is common to encounter a situation where
* a program with one ELFCLASS (32 or 64-bit) is required to examine a
* file with a different ELFCLASS. For example, the 32-bit linker (ld) may
* be used to link a 64-bit program. The simplest solution to this problem
* is to duplicate each such piece of code, modifying only the data types,
* and to use if statements to select the code to run. The problem with
* doing it that way is that the resulting code is difficult to maintain.
* It is inevitable that the copies will not always get modified identically,
* and will drift apart. The only robust solution is to generate the
* multiple instances of code automatically from a single piece of code.
*
* The solution used within the Solaris linker is to write the code once,
* code twice, once with _ELF64 defined (to generate ELFCLASS64 code) and
* once without (to generate ELFCLASS32). We use the same approach here.
*
* Note that the _ELF64 definition does not refer to the ELFCLASS of
* the resulting code, but rather, to the ELFCLASS of the data it
* examines. By repeating the above double-compilation for both 32-bit
* and 64-bit builds, we end up with 4 instances, which collectively
* can handle any combination of program and ELF data class:
*
* \ Compilation class
* \ 32 64
* \------------------
* |
* 32 | X X
* ELF Data Class |
* 64 | X X
*/
/*
* Read data from the specified process and construct an in memory
* image of an ELF file that will let us use libelf for most of the
* work we need to later (e.g. symbol table lookups). This is used
* in cases where no usable on-disk image for the process is available.
* We need sections for the dynsym, dynstr, and plt, and we need
* the program headers from the text section. The former is used in
* Pbuild_file_symtab(); the latter is used in several functions in
* Pcore.c to reconstruct the origin of each mapping from the load
* object that spawned it.
*
* Here are some useful pieces of elf trivia that will help
* to elucidate this code.
*
* All the information we need about the dynstr can be found in these
* two entries in the dynamic section:
*
* DT_STRTAB base of dynstr
* DT_STRSZ size of dynstr
*
* So deciphering the dynstr is pretty straightforward.
*
* The dynsym is a little trickier.
*
* DT_SYMTAB base of dynsym
* DT_SYMENT size of a dynstr entry (Elf{32,64}_Sym)
* DT_HASH base of hash table for dynamic lookups
*
* The DT_SYMTAB entry gives us any easy way of getting to the base
* of the dynsym, but getting the size involves rooting around in the
* dynamic lookup hash table. Here's the layout of the hash table:
*
* +-------------------+
* | nbucket | All values are 32-bit
* +-------------------+ (Elf32_Word or Elf64_Word)
* | nchain |
* +-------------------+
* | bucket[0] |
* | . . . |
* | bucket[nbucket-1] |
* +-------------------+
* | chain[0] |
* | . . . |
* | chain[nchain-1] |
* +-------------------+
* (figure 5-12 from the SYS V Generic ABI)
*
* Symbols names are hashed into a particular bucket which contains
* an index into the symbol table. Each entry in the symbol table
* has a corresponding entry in the chain table which tells the
* consumer where the next entry in the hash chain is. We can use
* the nchain field to find out the size of the dynsym.
*
* If there is a dynsym present, there may also be an optional
* section called the SUNW_ldynsym that augments the dynsym by
* providing local function symbols. When the Solaris linker lays
* out a file that has both of these sections, it makes sure that
* the data for the two sections is adjacent with the SUNW_ldynsym
* in front. This allows the runtime linker to treat these two
* symbol tables as being a single larger table. There are two
* items in the dynamic section for this:
*
* DT_SUNW_SYMTAB base of the SUNW_ldynsym
* DT_SUNW_SYMSZ total size of SUNW_ldynsym and dynsym
* added together. We can figure out the
* size of the SUNW_ldynsym section by
* subtracting the size of the dynsym
* (described above) from this value.
*
* We can figure out the size of the .plt section, but it takes some
* doing. We need to use the following information:
*
* DT_PLTGOT GOT PLT entry offset (on x86) or PLT offset (on sparc)
* DT_JMPREL base of the PLT's relocation section
* DT_PLTRELSZ size of the PLT's relocation section
* DT_PLTREL type of the PLT's relocation section
*
* We can use the number of relocation entries to calculate the size of
* the PLT. We get the address of the PLT by looking up the
* _PROCEDURE_LINKAGE_TABLE_ symbol.
*
* For more information, check out the System V Generic ABI.
*/
/*
* The fake_elfXX() function generated by this file uses the following
* string as the string table for the section names. Since it is critical
* to count correctly, and to improve readability, the SHSTR_NDX_ macros
* supply the proper offset for each name within the string.
*/
static char shstr[] =
".shstrtab\0.dynsym\0.dynstr\0.dynamic\0.plt\0.SUNW_ldynsym";
/* Offsets within shstr for each name */
#define SHSTR_NDX_shstrtab 0
/*
* Section header alignment for 32 and 64-bit ELF files differs
*/
#ifdef _ELF64
#else
#endif
/*
* This is the smallest number of PLT relocation entries allowed in a proper
* .plt section.
*/
#ifdef __sparc
#else
#ifdef __lint
/*
* On x86, lint would complain about unsigned comparison with
* PLTREL_MIN_ENTRIES. This define fakes up the value of PLTREL_MIN_ENTRIES
* and silences lint. On SPARC, there is no such issue.
*/
#else
#define PLTREL_MIN_ENTRIES 0
#endif
#endif
#ifdef _ELF64
Elf *
#else
Elf *
#endif
{
enum {
};
/*
* Mask of dynamic options that must be present in a well
* formed dynamic section. We need all of these in order to
* put together a complete set of elf sections. They are
* mandatory in both executables and shared objects so if one
* of them is missing, we're in some trouble and should abort.
* The PLT items are expected, but we will let them slide if
* need be. The DI_SUNW_SYM* items are completely optional, so
* we use them if they are present and ignore them otherwise.
*/
int di_mask = 0;
int dynstr_shndx;
uint_t i;
goto bad;
} else {
goto bad;
goto bad;
}
/*
* Iterate over the items in the dynamic section, grabbing
* the address of items we want and saving them in dp[].
*/
/* For the .plt section */
case DT_PLTGOT:
break;
case DT_JMPREL:
break;
case DT_PLTRELSZ:
d[DI_PLTRELSZ] = &dp[i];
break;
case DT_PLTREL:
break;
/* For the .dynsym section */
case DT_SYMTAB:
break;
case DT_HASH:
break;
case DT_SYMENT:
break;
case DT_SUNW_SYMTAB:
d[DI_SUNW_SYMTAB] = &dp[i];
break;
case DT_SUNW_SYMSZ:
d[DI_SUNW_SYMSZ] = &dp[i];
break;
/* For the .dynstr section */
case DT_STRTAB:
break;
case DT_STRSZ:
break;
}
}
/* Ensure all required entries were collected */
dprintf("text section missing required dynamic entries\n");
goto bad;
}
/* SUNW_ldynsym must be adjacent to dynsym. Ignore if not */
d[DI_SUNW_SYMTAB] = NULL;
d[DI_SUNW_SYMSZ] = NULL;
}
/* elf header */
/* program headers from in-core elf fragment */
/* unused shdr, and .shstrtab section */
dprintf("Pread of .hash at %lx failed\n",
(long)(hptr));
goto bad;
}
}
/*
* .dynsym and .SUNW_ldynsym sections.
*
* The string table section used for the symbol table and
* dynamic sections lies immediately after the dynsym, so the
* presence of SUNW_ldynsym changes the dynstr section index.
*/
if (d[DI_SUNW_SYMTAB] != NULL) {
dynstr_shndx = 4;
} else {
ldynsym_size = 0;
dynstr_shndx = 3;
}
/* .dynstr section */
/* .dynamic section */
/* .plt section */
} else {
/* fall back to the platform default */
dprintf("DI_PLTREL not found, defaulting to Rel");
#else /* (!(__i386 || __amd64)) || _ELF64 */
dprintf("DI_PLTREL not found, defaulting to Rela");
#endif /* (!(__i386 || __amd64) || _ELF64 */
}
if (pltentries < PLTREL_MIN_ENTRIES) {
dprintf("too few PLT relocation entries "
"(found %lu, expected at least %d)\n",
(long)pltentries, PLTREL_MIN_ENTRIES);
goto bad;
}
goto done_with_plt;
/*
* Now that we know the number of plt relocation entries
* we can calculate the size of the plt.
*/
#if defined(__sparc)
/* The sparc PLT always has a (delay slot) nop at the end */
pltsz += 4;
#endif /* __sparc */
}
goto bad;
/* LINTED - alignment */
/*
* Plt and SUNW_ldynsym sections are optional. C logical
* binary operators return a 0 or 1 value, so the following
* adds 1 for each optional section present.
*/
/* LINTED - alignment */
/*
* Copying the program headers directly from the process's
* address space is a little suspect, but since we only
* use them for their address and size values, this is fine.
*/
dprintf("failed to read program headers\n");
goto bad;
}
/*
* The first elf section is always skipped.
*/
sp++;
/*
* Section Header: .shstrtab
*/
sp->sh_entsize = 0;
sp++;
/*
* Section Header: .SUNW_ldynsym
*/
if (d[DI_SUNW_SYMTAB] != NULL) {
/* Index of 1st global in table that has none == # items */
dprintf("failed to read .SUNW_ldynsym at %lx\n",
goto bad;
}
/* No need to round up ldynsym data. Dynsym data is same type */
sp++;
}
/*
* Section Header: .dynsym
*/
dprintf("failed to read .dynsym at %lx\n",
goto bad;
}
sp++;
/*
* Section Header: .dynstr
*/
sp->sh_entsize = 0;
dprintf("failed to read .dynstr\n");
goto bad;
}
sp++;
/*
* Section Header: .dynamic
*/
sp++;
/*
* Section Header: .plt
*/
if (pltsz != 0) {
/*
* Now we need to find the address of the plt by looking
* up the "_PROCEDURE_LINKAGE_TABLE_" symbol.
*/
/* get the address of the symtab and strtab sections */
}
/* find the .hash bucket address for this symbol */
/* read the elf hash bucket index */
sizeof (ndx)) {
goto bad;
}
while (ndx) {
dprintf("Pread of .symtab at %lx failed\n",
goto bad;
}
strtabname) < 0) {
dprintf("Pread of .strtab at %lx failed\n",
(long)strtabname);
goto bad;
}
break;
sizeof (ndx)) {
dprintf("Pread of .hash at %lx failed\n",
(long)hash);
goto bad;
}
}
#if defined(__sparc)
dprintf("warning: DI_PLTGOT (%lx) doesn't match "
".plt symbol pointer (%lx)",
}
#endif /* __sparc */
if (ndx == 0) {
"Failed to find \"_PROCEDURE_LINKAGE_TABLE_\"\n");
goto bad;
}
dprintf("failed to read .plt at %lx\n",
goto bad;
}
sp++;
}
/* make sure we didn't write past the end of allocated memory */
sp++;
return (NULL);
}
return (elf);
bad:
return (NULL);
}