clamav/libclamav/pe.h

100 lines
4.2 KiB
C
Raw Normal View History

2004-05-11 23:30:57 +00:00
/*
2025-02-14 10:24:30 -05:00
* Copyright (C) 2013-2025 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
* Copyright (C) 2007-2013 Sourcefire, Inc.
2004-05-11 23:30:57 +00:00
*
* Authors: Alberto Wu, Tomasz Kojm, Andrew Williams
*
* Acknowledgements: The header structures were based upon a PE format
* analysis by B. Luevelsmeyer.
*
2004-05-11 23:30:57 +00:00
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
2004-05-11 23:30:57 +00:00
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
* MA 02110-1301, USA.
2004-05-11 23:30:57 +00:00
*/
#ifndef __PE_H
#define __PE_H
#include "clamav.h"
#include "others.h"
#include "fmap.h"
#include "bcfeatures.h"
PE parsing code improvements, db loading bug fixes Consolidate the PE parsing code into one function. I tried to preserve all existing functionality from the previous, distinct implementations to a large extent (with the exceptions mentioned below). If I noticed potential bugs/improvements, I added a TODO statement about those so that they can be fixed in a smaller commit later. Also, there are more TODOs in places where I'm not entirely sure why certain actions are performed - more research is needed for these. I'm submitting a pull request now so that regression testing can be done, and because merging what I have thus far now will likely have fewer conflicts than if I try to merge later PE parsing code improvements: - PEs without all 16 data directories are parsed more appropriately now - Added lots more debug statements Also: - Allow MAX_BC and MAX_TRACKED_PCRE to be specified via CFLAGS When doing performance testing with the latest CVD, MAX_BC and MAX_TRACKED_PCRE need to be raised to track all the events. Allow these to be specified via CFLAGS by not redefining them if they are already defined - Fix an issue preventing wildcard sizes in .MDB/.MSB rules I'm not sure what the original intent of the check I removed was, but it prevents using wildcard sizes in .MDB/.MSB rules. AFAICT these wildcard sizes should be handled appropriately by the MD5 section hash computation code, so I don't think a check on that is needed. - Fix several issues related to db loading - .imp files will now get loaded if they exist in a directory passed via clamscan's '-d' flag - .pwdb files will now get loaded if they exist in a directory passed via clamscan's '-d' flag even when compiling without yara support - Changes to .imp, .ign, and .ign2 files will now be reflected in calls to cl_statinidir and cl_statchkdir (and also .pwdb files, even when compiling without yara support) - The contents of .sfp files won't be included in some of the signature counts, and the contents of .cud files will be - Any local.gdb files will no longer be loaded twice - For .imp files, you are no longer required to specify a minimum flevel for wildcard rules, since this isn't needed
2019-01-08 00:09:08 -05:00
#include "pe_structs.h"
#include "execs.h"
2010-09-02 18:04:00 +03:00
/** Data for the bytecode PE hook
* \group_pe
PE parsing code improvements, db loading bug fixes Consolidate the PE parsing code into one function. I tried to preserve all existing functionality from the previous, distinct implementations to a large extent (with the exceptions mentioned below). If I noticed potential bugs/improvements, I added a TODO statement about those so that they can be fixed in a smaller commit later. Also, there are more TODOs in places where I'm not entirely sure why certain actions are performed - more research is needed for these. I'm submitting a pull request now so that regression testing can be done, and because merging what I have thus far now will likely have fewer conflicts than if I try to merge later PE parsing code improvements: - PEs without all 16 data directories are parsed more appropriately now - Added lots more debug statements Also: - Allow MAX_BC and MAX_TRACKED_PCRE to be specified via CFLAGS When doing performance testing with the latest CVD, MAX_BC and MAX_TRACKED_PCRE need to be raised to track all the events. Allow these to be specified via CFLAGS by not redefining them if they are already defined - Fix an issue preventing wildcard sizes in .MDB/.MSB rules I'm not sure what the original intent of the check I removed was, but it prevents using wildcard sizes in .MDB/.MSB rules. AFAICT these wildcard sizes should be handled appropriately by the MD5 section hash computation code, so I don't think a check on that is needed. - Fix several issues related to db loading - .imp files will now get loaded if they exist in a directory passed via clamscan's '-d' flag - .pwdb files will now get loaded if they exist in a directory passed via clamscan's '-d' flag even when compiling without yara support - Changes to .imp, .ign, and .ign2 files will now be reflected in calls to cl_statinidir and cl_statchkdir (and also .pwdb files, even when compiling without yara support) - The contents of .sfp files won't be included in some of the signature counts, and the contents of .cud files will be - Any local.gdb files will no longer be loaded twice - For .imp files, you are no longer required to specify a minimum flevel for wildcard rules, since this isn't needed
2019-01-08 00:09:08 -05:00
*
* NOTE: This structure must stay in-sync with the ones defined within the
* clamav-bytecode-compiler source at:
* - clang/lib/Headers/bytecode_pe.h
* - llvm/tools/clang/lib/Headers/bytecode_pe.h
* We allocate space for this, populate the values via cli_peheader, and pass
* it to the bytecode sig runtime for use.
*
* TODO Next time we are making changes to the clamav-bytecode-compiler
* source, update pe_image_optional_hdr32 and pe_image_optional_hdr64 to
* remove DataDirectory from both (like with the definitions here). Then,
* remove opt32_dirs and opt64_dirs below. There's no need to have these
* bytes in 3 places! Also, consider using a union to hold opt32 and opt64,
* since you never need more than one at a time.
*/
2009-10-02 17:33:11 +03:00
struct cli_pe_hook_data {
uint32_t offset;
uint32_t ep; /**< EntryPoint as file offset */
uint16_t nsections; /**< Number of sections */
uint16_t dummy; /* align */
struct pe_image_file_hdr file_hdr; /**< Header for this PE file */
struct pe_image_optional_hdr32 opt32; /**< 32-bit PE optional header */
PE parsing code improvements, db loading bug fixes Consolidate the PE parsing code into one function. I tried to preserve all existing functionality from the previous, distinct implementations to a large extent (with the exceptions mentioned below). If I noticed potential bugs/improvements, I added a TODO statement about those so that they can be fixed in a smaller commit later. Also, there are more TODOs in places where I'm not entirely sure why certain actions are performed - more research is needed for these. I'm submitting a pull request now so that regression testing can be done, and because merging what I have thus far now will likely have fewer conflicts than if I try to merge later PE parsing code improvements: - PEs without all 16 data directories are parsed more appropriately now - Added lots more debug statements Also: - Allow MAX_BC and MAX_TRACKED_PCRE to be specified via CFLAGS When doing performance testing with the latest CVD, MAX_BC and MAX_TRACKED_PCRE need to be raised to track all the events. Allow these to be specified via CFLAGS by not redefining them if they are already defined - Fix an issue preventing wildcard sizes in .MDB/.MSB rules I'm not sure what the original intent of the check I removed was, but it prevents using wildcard sizes in .MDB/.MSB rules. AFAICT these wildcard sizes should be handled appropriately by the MD5 section hash computation code, so I don't think a check on that is needed. - Fix several issues related to db loading - .imp files will now get loaded if they exist in a directory passed via clamscan's '-d' flag - .pwdb files will now get loaded if they exist in a directory passed via clamscan's '-d' flag even when compiling without yara support - Changes to .imp, .ign, and .ign2 files will now be reflected in calls to cl_statinidir and cl_statchkdir (and also .pwdb files, even when compiling without yara support) - The contents of .sfp files won't be included in some of the signature counts, and the contents of .cud files will be - Any local.gdb files will no longer be loaded twice - For .imp files, you are no longer required to specify a minimum flevel for wildcard rules, since this isn't needed
2019-01-08 00:09:08 -05:00
/** Our opt32 no longer includes DataDirectory[16], but the one in the
* bytecode compiler source still does. Add this here as a placeholder (and
* it gets used, so we need to populate it also */
PE parsing code improvements, db loading bug fixes Consolidate the PE parsing code into one function. I tried to preserve all existing functionality from the previous, distinct implementations to a large extent (with the exceptions mentioned below). If I noticed potential bugs/improvements, I added a TODO statement about those so that they can be fixed in a smaller commit later. Also, there are more TODOs in places where I'm not entirely sure why certain actions are performed - more research is needed for these. I'm submitting a pull request now so that regression testing can be done, and because merging what I have thus far now will likely have fewer conflicts than if I try to merge later PE parsing code improvements: - PEs without all 16 data directories are parsed more appropriately now - Added lots more debug statements Also: - Allow MAX_BC and MAX_TRACKED_PCRE to be specified via CFLAGS When doing performance testing with the latest CVD, MAX_BC and MAX_TRACKED_PCRE need to be raised to track all the events. Allow these to be specified via CFLAGS by not redefining them if they are already defined - Fix an issue preventing wildcard sizes in .MDB/.MSB rules I'm not sure what the original intent of the check I removed was, but it prevents using wildcard sizes in .MDB/.MSB rules. AFAICT these wildcard sizes should be handled appropriately by the MD5 section hash computation code, so I don't think a check on that is needed. - Fix several issues related to db loading - .imp files will now get loaded if they exist in a directory passed via clamscan's '-d' flag - .pwdb files will now get loaded if they exist in a directory passed via clamscan's '-d' flag even when compiling without yara support - Changes to .imp, .ign, and .ign2 files will now be reflected in calls to cl_statinidir and cl_statchkdir (and also .pwdb files, even when compiling without yara support) - The contents of .sfp files won't be included in some of the signature counts, and the contents of .cud files will be - Any local.gdb files will no longer be loaded twice - For .imp files, you are no longer required to specify a minimum flevel for wildcard rules, since this isn't needed
2019-01-08 00:09:08 -05:00
struct pe_image_data_dir opt32_dirs[16];
uint32_t dummy2; /* align */
struct pe_image_optional_hdr64 opt64; /**< 64-bit PE optional header */
struct pe_image_data_dir opt64_dirs[16]; /** See note about opt32_dirs */
struct pe_image_data_dir dirs[16]; /**< PE data directory header */
uint32_t e_lfanew; /**< address of new exe header */
uint32_t overlays; /**< number of overlays */
int32_t overlays_sz; /**< size of overlays */
uint32_t hdr_size; /**< internally needed by rawaddr */
2009-10-02 17:33:11 +03:00
};
int cli_scanpe(cli_ctx *ctx);
2004-05-11 23:30:57 +00:00
enum {
CL_GENHASH_PE_CLASS_SECTION,
CL_GENHASH_PE_CLASS_IMPTBL,
/* place new class types above this line */
CL_GENHASH_PE_CLASS_LAST
};
PE parsing code improvements, db loading bug fixes Consolidate the PE parsing code into one function. I tried to preserve all existing functionality from the previous, distinct implementations to a large extent (with the exceptions mentioned below). If I noticed potential bugs/improvements, I added a TODO statement about those so that they can be fixed in a smaller commit later. Also, there are more TODOs in places where I'm not entirely sure why certain actions are performed - more research is needed for these. I'm submitting a pull request now so that regression testing can be done, and because merging what I have thus far now will likely have fewer conflicts than if I try to merge later PE parsing code improvements: - PEs without all 16 data directories are parsed more appropriately now - Added lots more debug statements Also: - Allow MAX_BC and MAX_TRACKED_PCRE to be specified via CFLAGS When doing performance testing with the latest CVD, MAX_BC and MAX_TRACKED_PCRE need to be raised to track all the events. Allow these to be specified via CFLAGS by not redefining them if they are already defined - Fix an issue preventing wildcard sizes in .MDB/.MSB rules I'm not sure what the original intent of the check I removed was, but it prevents using wildcard sizes in .MDB/.MSB rules. AFAICT these wildcard sizes should be handled appropriately by the MD5 section hash computation code, so I don't think a check on that is needed. - Fix several issues related to db loading - .imp files will now get loaded if they exist in a directory passed via clamscan's '-d' flag - .pwdb files will now get loaded if they exist in a directory passed via clamscan's '-d' flag even when compiling without yara support - Changes to .imp, .ign, and .ign2 files will now be reflected in calls to cl_statinidir and cl_statchkdir (and also .pwdb files, even when compiling without yara support) - The contents of .sfp files won't be included in some of the signature counts, and the contents of .cud files will be - Any local.gdb files will no longer be loaded twice - For .imp files, you are no longer required to specify a minimum flevel for wildcard rules, since this isn't needed
2019-01-08 00:09:08 -05:00
// For info about these, see the cli_peheader definition in pe.c
#define CLI_PEHEADER_OPT_NONE 0x0
#define CLI_PEHEADER_OPT_COLLECT_JSON 0x1
#define CLI_PEHEADER_OPT_DBG_PRINT_INFO 0x2
#define CLI_PEHEADER_OPT_EXTRACT_VINFO 0x4
#define CLI_PEHEADER_OPT_STRICT_ON_PE_ERRORS 0x8
#define CLI_PEHEADER_OPT_REMOVE_MISSING_SECTIONS 0x10
PE parsing code improvements, db loading bug fixes Consolidate the PE parsing code into one function. I tried to preserve all existing functionality from the previous, distinct implementations to a large extent (with the exceptions mentioned below). If I noticed potential bugs/improvements, I added a TODO statement about those so that they can be fixed in a smaller commit later. Also, there are more TODOs in places where I'm not entirely sure why certain actions are performed - more research is needed for these. I'm submitting a pull request now so that regression testing can be done, and because merging what I have thus far now will likely have fewer conflicts than if I try to merge later PE parsing code improvements: - PEs without all 16 data directories are parsed more appropriately now - Added lots more debug statements Also: - Allow MAX_BC and MAX_TRACKED_PCRE to be specified via CFLAGS When doing performance testing with the latest CVD, MAX_BC and MAX_TRACKED_PCRE need to be raised to track all the events. Allow these to be specified via CFLAGS by not redefining them if they are already defined - Fix an issue preventing wildcard sizes in .MDB/.MSB rules I'm not sure what the original intent of the check I removed was, but it prevents using wildcard sizes in .MDB/.MSB rules. AFAICT these wildcard sizes should be handled appropriately by the MD5 section hash computation code, so I don't think a check on that is needed. - Fix several issues related to db loading - .imp files will now get loaded if they exist in a directory passed via clamscan's '-d' flag - .pwdb files will now get loaded if they exist in a directory passed via clamscan's '-d' flag even when compiling without yara support - Changes to .imp, .ign, and .ign2 files will now be reflected in calls to cl_statinidir and cl_statchkdir (and also .pwdb files, even when compiling without yara support) - The contents of .sfp files won't be included in some of the signature counts, and the contents of .cud files will be - Any local.gdb files will no longer be loaded twice - For .imp files, you are no longer required to specify a minimum flevel for wildcard rules, since this isn't needed
2019-01-08 00:09:08 -05:00
cl_error_t cli_pe_targetinfo(cli_ctx *ctx, struct cli_exe_info *peinfo);
cl_error_t cli_peheader(cli_ctx *ctx, struct cli_exe_info *peinfo, uint32_t opts);
PE parsing code improvements, db loading bug fixes Consolidate the PE parsing code into one function. I tried to preserve all existing functionality from the previous, distinct implementations to a large extent (with the exceptions mentioned below). If I noticed potential bugs/improvements, I added a TODO statement about those so that they can be fixed in a smaller commit later. Also, there are more TODOs in places where I'm not entirely sure why certain actions are performed - more research is needed for these. I'm submitting a pull request now so that regression testing can be done, and because merging what I have thus far now will likely have fewer conflicts than if I try to merge later PE parsing code improvements: - PEs without all 16 data directories are parsed more appropriately now - Added lots more debug statements Also: - Allow MAX_BC and MAX_TRACKED_PCRE to be specified via CFLAGS When doing performance testing with the latest CVD, MAX_BC and MAX_TRACKED_PCRE need to be raised to track all the events. Allow these to be specified via CFLAGS by not redefining them if they are already defined - Fix an issue preventing wildcard sizes in .MDB/.MSB rules I'm not sure what the original intent of the check I removed was, but it prevents using wildcard sizes in .MDB/.MSB rules. AFAICT these wildcard sizes should be handled appropriately by the MD5 section hash computation code, so I don't think a check on that is needed. - Fix several issues related to db loading - .imp files will now get loaded if they exist in a directory passed via clamscan's '-d' flag - .pwdb files will now get loaded if they exist in a directory passed via clamscan's '-d' flag even when compiling without yara support - Changes to .imp, .ign, and .ign2 files will now be reflected in calls to cl_statinidir and cl_statchkdir (and also .pwdb files, even when compiling without yara support) - The contents of .sfp files won't be included in some of the signature counts, and the contents of .cud files will be - Any local.gdb files will no longer be loaded twice - For .imp files, you are no longer required to specify a minimum flevel for wildcard rules, since this isn't needed
2019-01-08 00:09:08 -05:00
cl_error_t cli_check_auth_header(cli_ctx *ctx, struct cli_exe_info *peinfo);
Swap clean cache from MD5 to SHA2-256 Change the clean-cache to use SHA2-256 instead of MD5. Note that all references are changed to specify "SHA2-256" now instead of "SHA256", for clarity. But there is no plan to add support for SHA3 algorithms at this time. Significant code cleanup. E.g.: - Implemented goto-done error handling. - Used `uint8_t *` instead of `unsigned char *`. - Use `bool` for boolean checks, rather than `int. - Used `#defines` instead of magic numbers. - Removed duplicate `#defines` for things like hash length. Add new option to calculate and record additional hash types when the "generate metadata JSON" feature is enabled: - libclamav option: `CL_SCAN_GENERAL_STORE_EXTRA_HASHES` - clamscan option: `--json-store-extra-hashes` (default off) - clamd.conf option: `JsonStoreExtraHashes` (default 'no') Renamed the sigtool option `--sha256` to `--sha2-256`. The original option is still functional, but is deprecated. For the "generate metadata JSON" feature, the file hash is now stored as "sha2-256" instead of "FileMD5". If you enable the "extra hashes" option, then it will also record "md5" and "sha1". Deprecate and disable the internal "SHA collect" feature. This option had been hidden behind C #ifdef checks for an option that wasn't exposed through CMake, so it was basically unavailable anyways. Changes to calculate file hashes when they're needed and no sooner. For the FP feature in the matcher module, I have mimiced the optimization in the FMAP scan routine which makes it so that it can calculate multiple hashes in a single pass of the file. The `HandlerType` feature stores a hash of the file in the scan ctx to prevent retyping the exact same data more than once. I removed that hash field and replaced it with an attribute flag that is applied to the new recursion stack layer when retyping a file. This also closes a minor bug that would prevent retyping a file with an all-zero hash. :) The work upgrading cache.c to support SHA2-256 sized hashes thanks to: https://github.com/m-sola CLAM-255 CLAM-1858 CLAM-1859 CLAM-1860
2025-06-03 19:03:20 -04:00
cl_error_t cli_genhash_pe(cli_ctx *ctx, unsigned int class, cli_hash_type_t type, stats_section_t *hashes);
2010-02-15 18:12:02 +02:00
uint32_t cli_rawaddr(uint32_t, const struct cli_exe_section *, uint16_t, unsigned int *, size_t, uint32_t);
PE parsing code improvements, db loading bug fixes Consolidate the PE parsing code into one function. I tried to preserve all existing functionality from the previous, distinct implementations to a large extent (with the exceptions mentioned below). If I noticed potential bugs/improvements, I added a TODO statement about those so that they can be fixed in a smaller commit later. Also, there are more TODOs in places where I'm not entirely sure why certain actions are performed - more research is needed for these. I'm submitting a pull request now so that regression testing can be done, and because merging what I have thus far now will likely have fewer conflicts than if I try to merge later PE parsing code improvements: - PEs without all 16 data directories are parsed more appropriately now - Added lots more debug statements Also: - Allow MAX_BC and MAX_TRACKED_PCRE to be specified via CFLAGS When doing performance testing with the latest CVD, MAX_BC and MAX_TRACKED_PCRE need to be raised to track all the events. Allow these to be specified via CFLAGS by not redefining them if they are already defined - Fix an issue preventing wildcard sizes in .MDB/.MSB rules I'm not sure what the original intent of the check I removed was, but it prevents using wildcard sizes in .MDB/.MSB rules. AFAICT these wildcard sizes should be handled appropriately by the MD5 section hash computation code, so I don't think a check on that is needed. - Fix several issues related to db loading - .imp files will now get loaded if they exist in a directory passed via clamscan's '-d' flag - .pwdb files will now get loaded if they exist in a directory passed via clamscan's '-d' flag even when compiling without yara support - Changes to .imp, .ign, and .ign2 files will now be reflected in calls to cl_statinidir and cl_statchkdir (and also .pwdb files, even when compiling without yara support) - The contents of .sfp files won't be included in some of the signature counts, and the contents of .cud files will be - Any local.gdb files will no longer be loaded twice - For .imp files, you are no longer required to specify a minimum flevel for wildcard rules, since this isn't needed
2019-01-08 00:09:08 -05:00
void findres(uint32_t, uint32_t, fmap_t *map, struct cli_exe_info *, int (*)(void *, uint32_t, uint32_t, uint32_t, uint32_t), void *);
2009-11-11 03:58:22 +01:00
2004-05-11 23:30:57 +00:00
#endif