Resguardo inicial

linux-7.2.3/kernel/module/Kconfig

@@ -0,0 +1,463 @@
+# SPDX-License-Identifier: GPL-2.0-only
+menuconfig MODULES
+	bool "Enable loadable module support"
+	modules
+	select EXECMEM
+	help
+	  Kernel modules are small pieces of compiled code which can
+	  be inserted in the running kernel, rather than being
+	  permanently built into the kernel.  You use the "modprobe"
+	  tool to add (and sometimes remove) them.  If you say Y here,
+	  many parts of the kernel can be built as modules (by
+	  answering M instead of Y where indicated): this is most
+	  useful for infrequently used options which are not required
+	  for booting.  For more information, see the man pages for
+	  modprobe, lsmod, modinfo, insmod and rmmod.
+
+	  If you say Y here, you will need to run "make
+	  modules_install" to put the modules under /lib/modules/
+	  where modprobe can find them (you may need to be root to do
+	  this).
+
+	  If unsure, say Y.
+
+if MODULES
+
+config MODULE_DEBUGFS
+	bool
+
+config MODULE_DEBUG
+	bool "Module debugging"
+	depends on DEBUG_FS
+	help
+	  Allows you to enable / disable features which can help you debug
+	  modules. You don't need these options on production systems.
+
+if MODULE_DEBUG
+
+config MODULE_STATS
+	bool "Module statistics"
+	depends on DEBUG_FS
+	select MODULE_DEBUGFS
+	help
+	  This option allows you to maintain a record of module statistics.
+	  For example, size of all modules, average size, text size, a list
+	  of failed modules and the size for each of those. For failed
+	  modules we keep track of modules which failed due to either the
+	  existing module taking too long to load or that module was already
+	  loaded.
+
+	  You should enable this if you are debugging production loads
+	  and want to see if userspace or the kernel is doing stupid things
+	  with loading modules when it shouldn't or if you want to help
+	  optimize userspace / kernel space module autoloading schemes.
+	  You might want to do this because failed modules tend to use
+	  up significant amount of memory, and so you'd be doing everyone a
+	  favor in avoiding these failures proactively.
+
+	  This functionality is also useful for those experimenting with
+	  module .text ELF section optimization.
+
+	  If unsure, say N.
+
+config MODULE_DEBUG_AUTOLOAD_DUPS
+	bool "Debug duplicate modules with auto-loading"
+	help
+	  Module autoloading allows in-kernel code to request modules through
+	  the *request_module*() API calls. This in turn just calls userspace
+	  modprobe. Although modprobe checks to see if a module is already
+	  loaded before trying to load a module there is a small time window in
+	  which multiple duplicate requests can end up in userspace and multiple
+	  modprobe calls race calling finit_module() around the same time for
+	  duplicate modules. The finit_module() system call can consume in the
+	  worst case more than twice the respective module size in virtual
+	  memory for each duplicate module requests. Although duplicate module
+	  requests are non-fatal virtual memory is a limited resource and each
+	  duplicate module request ends up just unnecessarily straining virtual
+	  memory.
+
+	  This debugging facility will create pr_warn() splats for duplicate
+	  module requests to help identify if module auto-loading may be the
+	  culprit to your early boot virtual memory pressure. Since virtual
+	  memory abuse caused by duplicate module requests could render a
+	  system unusable this functionality will also converge races in
+	  requests for the same module to a single request. You can boot with
+	  the module.enable_dups_trace=1 kernel parameter to use WARN_ON()
+	  instead of the pr_warn().
+
+	  If the first module request used request_module_nowait() we cannot
+	  use that as the anchor to wait for duplicate module requests, since
+	  users of request_module() do want a proper return value. If a call
+	  for the same module happened earlier with request_module() though,
+	  then a duplicate request_module_nowait() would be detected. The
+	  non-wait request_module() call is synchronous and waits until modprobe
+	  completes. Subsequent auto-loading requests for the same module do
+	  not trigger a new finit_module() calls and do not strain virtual
+	  memory, and so as soon as modprobe successfully completes we remove
+	  tracking for duplicates for that module.
+
+	  Enable this functionality to try to debug virtual memory abuse during
+	  boot on systems which are failing to boot or if you suspect you may be
+	  straining virtual memory during boot, and you want to identify if the
+	  abuse was due to module auto-loading. These issues are currently only
+	  known to occur on systems with many CPUs (over 400) and is likely the
+	  result of udev issuing duplicate module requests for each CPU, and so
+	  module auto-loading is not the culprit. There may very well still be
+	  many duplicate module auto-loading requests which could be optimized
+	  for and this debugging facility can be used to help identify them.
+
+	  Only enable this for debugging system functionality, never have it
+	  enabled on real systems.
+
+config MODULE_DEBUG_AUTOLOAD_DUPS_TRACE
+	bool "Force full stack trace when duplicates are found"
+	depends on MODULE_DEBUG_AUTOLOAD_DUPS
+	help
+	  Enabling this will force a full stack trace for duplicate module
+	  auto-loading requests using WARN_ON() instead of pr_warn(). You
+	  should keep this disabled at all times unless you are a developer
+	  and are doing a manual inspection and want to debug exactly why
+	  these duplicates occur.
+
+endif # MODULE_DEBUG
+
+config MODULE_FORCE_LOAD
+	bool "Forced module loading"
+	default n
+	help
+	  Allow loading of modules without version information (ie. modprobe
+	  --force).  Forced module loading sets the 'F' (forced) taint flag and
+	  is usually a really bad idea.
+
+config MODULE_UNLOAD
+	bool "Module unloading"
+	help
+	  Without this option you will not be able to unload any
+	  modules (note that some modules may not be unloadable
+	  anyway), which makes your kernel smaller, faster
+	  and simpler.  If unsure, say Y.
+
+config MODULE_FORCE_UNLOAD
+	bool "Forced module unloading"
+	depends on MODULE_UNLOAD
+	help
+	  This option allows you to force a module to unload, even if the
+	  kernel believes it is unsafe: the kernel will remove the module
+	  without waiting for anyone to stop using it (using the -f option to
+	  rmmod).  This is mainly for kernel developers and desperate users.
+	  If unsure, say N.
+
+config MODULE_UNLOAD_TAINT_TRACKING
+	bool "Tainted module unload tracking"
+	depends on MODULE_UNLOAD
+	select MODULE_DEBUGFS
+	help
+	  This option allows you to maintain a record of each unloaded
+	  module that tainted the kernel. In addition to displaying a
+	  list of linked (or loaded) modules e.g. on detection of a bad
+	  page (see bad_page()), the aforementioned details are also
+	  shown. If unsure, say N.
+
+config MODVERSIONS
+	bool "Module versioning support"
+	depends on !COMPILE_TEST
+	help
+	  Usually, you have to use modules compiled with your kernel.
+	  Saying Y here makes it sometimes possible to use modules
+	  compiled for different kernels, by adding enough information
+	  to the modules to (hopefully) spot any changes which would
+	  make them incompatible with the kernel you are running.  If
+	  unsure, say N.
+
+if MODVERSIONS
+
+choice
+	prompt "Module versioning implementation"
+	help
+	  Select the tool used to calculate symbol versions for modules.
+
+	  If unsure, select GENKSYMS.
+
+config GENKSYMS
+	bool "genksyms (from source code)"
+	help
+	  Calculate symbol versions from pre-processed source code using
+	  genksyms.
+
+	  If unsure, say Y.
+
+config GENDWARFKSYMS
+	bool "gendwarfksyms (from debugging information)"
+	depends on DEBUG_INFO
+	# Requires full debugging information, split DWARF not supported.
+	depends on !DEBUG_INFO_REDUCED && !DEBUG_INFO_SPLIT
+	# Requires ELF object files.
+	depends on !LTO
+	# To avoid conflicts with the discarded __gendwarfksyms_ptr symbols on
+	# X86, requires pahole before commit 47dcb534e253 ("btf_encoder: Stop
+	# indexing symbols for VARs") or after commit 9810758003ce ("btf_encoder:
+	# Verify 0 address DWARF variables are in ELF section").
+	depends on !X86 || !DEBUG_INFO_BTF || PAHOLE_VERSION < 128 || PAHOLE_VERSION > 129
+	help
+	  Calculate symbol versions from DWARF debugging information using
+	  gendwarfksyms. Requires DEBUG_INFO to be enabled.
+
+	  If unsure, say N.
+endchoice
+
+config ASM_MODVERSIONS
+	bool
+	default HAVE_ASM_MODVERSIONS
+	help
+	  This enables module versioning for exported symbols also from
+	  assembly. This can be enabled only when the target architecture
+	  supports it.
+
+config EXTENDED_MODVERSIONS
+	bool "Extended Module Versioning Support"
+	help
+	  This enables extended MODVERSIONs support, allowing long symbol
+	  names to be versioned.
+
+	  The most likely reason you would enable this is to enable Rust
+	  support. If unsure, say N.
+
+config BASIC_MODVERSIONS
+	bool "Basic Module Versioning Support"
+	default y
+	help
+	  This enables basic MODVERSIONS support, allowing older tools or
+	  kernels to potentially load modules.
+
+	  Disabling this may cause older `modprobe` or `kmod` to be unable
+	  to read MODVERSIONS information from built modules. With this
+	  disabled, older kernels may treat this module as unversioned.
+
+	  This is enabled by default when MODVERSIONS are enabled.
+	  If unsure, say Y.
+
+endif # MODVERSIONS
+
+config MODULE_SRCVERSION_ALL
+	bool "Source checksum for all modules"
+	help
+	  Modules which contain a MODULE_VERSION get an extra "srcversion"
+	  field inserted into their modinfo section, which contains a
+	  sum of the source files which made it.  This helps maintainers
+	  see exactly which source was used to build a module (since
+	  others sometimes change the module source without updating
+	  the version).  With this option, such a "srcversion" field
+	  will be created for all modules.  If unsure, say N.
+
+config MODULE_SIG
+	bool "Module signature verification"
+	select MODULE_SIG_FORMAT
+	help
+	  Check modules for valid signatures upon load: the signature
+	  is simply appended to the module. For more information see
+	  <file:Documentation/admin-guide/module-signing.rst>.
+
+	  Note that this option adds the OpenSSL development packages as a
+	  kernel build dependency so that the signing tool can use its crypto
+	  library.
+
+	  You should enable this option if you wish to use either
+	  CONFIG_SECURITY_LOCKDOWN_LSM or lockdown functionality imposed via
+	  another LSM - otherwise unsigned modules will be loadable regardless
+	  of the lockdown policy.
+
+	  !!!WARNING!!!  If you enable this option, you MUST make sure that the
+	  module DOES NOT get stripped after being signed.  This includes the
+	  debuginfo strip done by some packagers (such as rpmbuild) and
+	  inclusion into an initramfs that wants the module size reduced.
+
+config MODULE_SIG_FORCE
+	bool "Require modules to be validly signed"
+	depends on MODULE_SIG
+	help
+	  Reject unsigned modules or signed modules for which we don't have a
+	  key.  Without this, such modules will simply taint the kernel.
+
+if MODULE_SIG || IMA_APPRAISE_MODSIG
+
+config MODULE_SIG_ALL
+	bool "Automatically sign all modules"
+	default y
+	help
+	  Sign all modules during make modules_install. Without this option,
+	  modules must be signed manually, using the scripts/sign-file tool.
+
+comment "Do not forget to sign required modules with scripts/sign-file"
+	depends on MODULE_SIG_FORCE && !MODULE_SIG_ALL
+
+choice
+	prompt "Hash algorithm to sign modules"
+	default MODULE_SIG_SHA512
+	help
+	  This determines which sort of hashing algorithm will be used during
+	  signature generation.  This algorithm _must_ be built into the kernel
+	  directly so that signature verification can take place.  It is not
+	  possible to load a signed module containing the algorithm to check
+	  the signature on that module.
+
+config MODULE_SIG_SHA256
+	bool "SHA-256"
+	select CRYPTO_SHA256
+
+config MODULE_SIG_SHA384
+	bool "SHA-384"
+	select CRYPTO_SHA512
+
+config MODULE_SIG_SHA512
+	bool "SHA-512"
+	select CRYPTO_SHA512
+
+config MODULE_SIG_SHA3_256
+	bool "SHA3-256"
+	select CRYPTO_SHA3
+
+config MODULE_SIG_SHA3_384
+	bool "SHA3-384"
+	select CRYPTO_SHA3
+
+config MODULE_SIG_SHA3_512
+	bool "SHA3-512"
+	select CRYPTO_SHA3
+
+endchoice
+
+config MODULE_SIG_HASH
+	string
+	default "sha256" if MODULE_SIG_SHA256
+	default "sha384" if MODULE_SIG_SHA384
+	default "sha512" if MODULE_SIG_SHA512
+	default "sha3-256" if MODULE_SIG_SHA3_256
+	default "sha3-384" if MODULE_SIG_SHA3_384
+	default "sha3-512" if MODULE_SIG_SHA3_512
+
+endif # MODULE_SIG || IMA_APPRAISE_MODSIG
+
+config MODULE_COMPRESS
+	bool "Module compression"
+	help
+	  Enable module compression to reduce on-disk size of module binaries.
+	  This is fully compatible with signed modules.
+
+	  The tool used to work with modules needs to support the selected
+	  compression type. kmod MAY support gzip, xz and zstd. Other tools
+	  might have a limited selection of the supported types.
+
+	  Note that for modules inside an initrd or initramfs, it's more
+	  efficient to compress the whole ramdisk instead.
+
+	  If unsure, say N.
+
+if MODULE_COMPRESS
+
+choice
+	prompt "Module compression type"
+	help
+	  Choose the supported algorithm for module compression.
+
+config MODULE_COMPRESS_GZIP
+	bool "GZIP"
+	help
+	  Support modules compressed with GZIP. The installed modules are
+	  suffixed with .ko.gz.
+
+config MODULE_COMPRESS_XZ
+	bool "XZ"
+	help
+	  Support modules compressed with XZ. The installed modules are
+	  suffixed with .ko.xz.
+
+config MODULE_COMPRESS_ZSTD
+	bool "ZSTD"
+	help
+	  Support modules compressed with ZSTD. The installed modules are
+	  suffixed with .ko.zst.
+
+endchoice
+
+config MODULE_COMPRESS_ALL
+	bool "Automatically compress all modules"
+	default y
+	help
+	  Compress all modules during 'make modules_install'.
+
+	  Your build system needs to provide the appropriate compression tool
+	  for the selected compression type. External modules will also be
+	  compressed in the same way during the installation.
+
+config MODULE_DECOMPRESS
+	bool "Support in-kernel module decompression"
+	select ZLIB_INFLATE if MODULE_COMPRESS_GZIP
+	select XZ_DEC if MODULE_COMPRESS_XZ
+	select ZSTD_DECOMPRESS if MODULE_COMPRESS_ZSTD
+	help
+	  Support for decompressing kernel modules by the kernel itself
+	  instead of relying on userspace to perform this task. Useful when
+	  load pinning security policy is enabled.
+
+	  If unsure, say N.
+
+endif # MODULE_COMPRESS
+
+config MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS
+	bool "Allow loading of modules with missing namespace imports"
+	help
+	  Symbols exported with EXPORT_SYMBOL_NS*() are considered exported in
+	  a namespace. A module that makes use of a symbol exported with such a
+	  namespace is required to import the namespace via MODULE_IMPORT_NS("").
+	  There is no technical reason to enforce correct namespace imports,
+	  but it creates consistency between symbols defining namespaces and
+	  users importing namespaces they make use of. This option relaxes this
+	  requirement and lifts the enforcement when loading a module.
+
+	  If unsure, say N.
+
+config MODPROBE_PATH
+	string "Path to modprobe binary"
+	default "/sbin/modprobe"
+	help
+	  When kernel code requests a module, it does so by calling
+	  the "modprobe" userspace utility. This option allows you to
+	  set the path where that binary is found. This can be changed
+	  at runtime via the sysctl file
+	  /proc/sys/kernel/modprobe. Setting this to the empty string
+	  removes the kernel's ability to request modules (but
+	  userspace can still load modules explicitly).
+
+config TRIM_UNUSED_KSYMS
+	bool "Trim unused exported kernel symbols"
+	help
+	  The kernel and some modules make many symbols available for
+	  other modules to use via EXPORT_SYMBOL() and variants. Depending
+	  on the set of modules being selected in your kernel configuration,
+	  many of those exported symbols might never be used.
+
+	  This option allows for unused exported symbols to be dropped from
+	  the build. In turn, this provides the compiler more opportunities
+	  (especially when using LTO) for optimizing the code and reducing
+	  binary size.  This might have some security advantages as well.
+
+	  If unsure, or if you need to build out-of-tree modules, say N.
+
+config UNUSED_KSYMS_WHITELIST
+	string "Whitelist of symbols to keep in ksymtab"
+	depends on TRIM_UNUSED_KSYMS
+	help
+	  By default, all unused exported symbols will be un-exported from the
+	  build when TRIM_UNUSED_KSYMS is selected.
+
+	  UNUSED_KSYMS_WHITELIST allows to whitelist symbols that must be kept
+	  exported at all times, even in absence of in-tree users. The value to
+	  set here is the path to a text file containing the list of symbols,
+	  one per line. The path can be absolute, or relative to the kernel
+	  source or obj tree.
+
+config MODULES_TREE_LOOKUP
+	def_bool y
+	depends on PERF_EVENTS || TRACING || CFI
+
+endif # MODULES

linux-7.2.3/kernel/module/Makefile

@@ -0,0 +1,25 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for linux kernel module support
+#
+
+# These are called from save_stack_trace() on slub debug path,
+# and produce insane amounts of uninteresting coverage.
+KCOV_INSTRUMENT_main.o := n
+
+obj-y += main.o
+obj-y += strict_rwx.o
+obj-y += kmod.o
+obj-$(CONFIG_MODULE_DEBUG_AUTOLOAD_DUPS) += dups.o
+obj-$(CONFIG_MODULE_DECOMPRESS) += decompress.o
+obj-$(CONFIG_MODULE_SIG) += signing.o
+obj-$(CONFIG_LIVEPATCH) += livepatch.o
+obj-$(CONFIG_MODULES_TREE_LOOKUP) += tree_lookup.o
+obj-$(CONFIG_DEBUG_KMEMLEAK) += debug_kmemleak.o
+obj-$(CONFIG_KALLSYMS) += kallsyms.o
+obj-$(CONFIG_PROC_FS) += procfs.o
+obj-$(CONFIG_SYSFS) += sysfs.o
+obj-$(CONFIG_KGDB_KDB) += kdb.o
+obj-$(CONFIG_MODVERSIONS) += version.o
+obj-$(CONFIG_MODULE_UNLOAD_TAINT_TRACKING) += tracking.o
+obj-$(CONFIG_MODULE_STATS) += stats.o

linux-7.2.3/kernel/module/debug_kmemleak.c

@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Module kmemleak support
+ *
+ * Copyright (C) 2009 Catalin Marinas
+ */
+
+#include <linux/module.h>
+#include <linux/kmemleak.h>
+#include "internal.h"
+
+void kmemleak_load_module(const struct module *mod,
+			  const struct load_info *info)
+{
+	/* only scan writable, non-executable sections */
+	for_each_mod_mem_type(type) {
+		if (type != MOD_DATA && type != MOD_INIT_DATA &&
+		    !mod->mem[type].is_rox)
+			kmemleak_no_scan(mod->mem[type].base);
+	}
+}

linux-7.2.3/kernel/module/decompress.c

@@ -0,0 +1,370 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright 2021 Google LLC.
+ */
+
+#include <linux/init.h>
+#include <linux/highmem.h>
+#include <linux/kobject.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/sysfs.h>
+#include <linux/vmalloc.h>
+
+#include "internal.h"
+
+static int module_extend_max_pages(struct load_info *info, unsigned int extent)
+{
+	struct page **new_pages;
+	unsigned int new_max = info->max_pages + extent;
+
+	new_pages = kvrealloc(info->pages,
+			      size_mul(new_max, sizeof(*info->pages)),
+			      GFP_KERNEL);
+	if (!new_pages)
+		return -ENOMEM;
+
+	info->pages = new_pages;
+	info->max_pages = new_max;
+
+	return 0;
+}
+
+static struct page *module_get_next_page(struct load_info *info)
+{
+	struct page *page;
+	int error;
+
+	if (info->max_pages == info->used_pages) {
+		error = module_extend_max_pages(info, info->used_pages);
+		if (error)
+			return ERR_PTR(error);
+	}
+
+	page = alloc_page(GFP_KERNEL | __GFP_HIGHMEM);
+	if (!page)
+		return ERR_PTR(-ENOMEM);
+
+	info->pages[info->used_pages++] = page;
+	return page;
+}
+
+#if defined(CONFIG_MODULE_COMPRESS_GZIP)
+#include <linux/zlib.h>
+#define MODULE_COMPRESSION	gzip
+#define MODULE_DECOMPRESS_FN	module_gzip_decompress
+
+/*
+ * Calculate length of the header which consists of signature, header
+ * flags, time stamp and operating system ID (10 bytes total), plus
+ * an optional filename.
+ */
+static size_t module_gzip_header_len(const u8 *buf, size_t size)
+{
+	const u8 signature[] = { 0x1f, 0x8b, 0x08 };
+	size_t len = 10;
+
+	if (size < len || memcmp(buf, signature, sizeof(signature)))
+		return 0;
+
+	if (buf[3] & 0x08) {
+		do {
+			/*
+			 * If we can't find the end of the file name we must
+			 * be dealing with a corrupted file.
+			 */
+			if (len == size)
+				return 0;
+		} while (buf[len++] != '\0');
+	}
+
+	return len;
+}
+
+static ssize_t module_gzip_decompress(struct load_info *info,
+				      const void *buf, size_t size)
+{
+	struct z_stream_s s = { 0 };
+	size_t new_size = 0;
+	size_t gzip_hdr_len;
+	ssize_t retval;
+	int rc;
+
+	gzip_hdr_len = module_gzip_header_len(buf, size);
+	if (!gzip_hdr_len) {
+		pr_err("not a gzip compressed module\n");
+		return -EINVAL;
+	}
+
+	s.next_in = buf + gzip_hdr_len;
+	s.avail_in = size - gzip_hdr_len;
+
+	s.workspace = kvmalloc(zlib_inflate_workspacesize(), GFP_KERNEL);
+	if (!s.workspace)
+		return -ENOMEM;
+
+	rc = zlib_inflateInit2(&s, -MAX_WBITS);
+	if (rc != Z_OK) {
+		pr_err("failed to initialize decompressor: %d\n", rc);
+		retval = -EINVAL;
+		goto out;
+	}
+
+	do {
+		struct page *page = module_get_next_page(info);
+
+		if (IS_ERR(page)) {
+			retval = PTR_ERR(page);
+			goto out_inflate_end;
+		}
+
+		s.next_out = kmap_local_page(page);
+		s.avail_out = PAGE_SIZE;
+		rc = zlib_inflate(&s, 0);
+		kunmap_local(s.next_out);
+
+		new_size += PAGE_SIZE - s.avail_out;
+	} while (rc == Z_OK);
+
+	if (rc != Z_STREAM_END) {
+		pr_err("decompression failed with status %d\n", rc);
+		retval = -EINVAL;
+		goto out_inflate_end;
+	}
+
+	retval = new_size;
+
+out_inflate_end:
+	zlib_inflateEnd(&s);
+out:
+	kvfree(s.workspace);
+	return retval;
+}
+#elif defined(CONFIG_MODULE_COMPRESS_XZ)
+#include <linux/xz.h>
+#define MODULE_COMPRESSION	xz
+#define MODULE_DECOMPRESS_FN	module_xz_decompress
+
+static ssize_t module_xz_decompress(struct load_info *info,
+				    const void *buf, size_t size)
+{
+	static const u8 signature[] = { 0xfd, '7', 'z', 'X', 'Z', 0 };
+	struct xz_dec *xz_dec;
+	struct xz_buf xz_buf;
+	enum xz_ret xz_ret;
+	size_t new_size = 0;
+	ssize_t retval;
+
+	if (size < sizeof(signature) ||
+	    memcmp(buf, signature, sizeof(signature))) {
+		pr_err("not an xz compressed module\n");
+		return -EINVAL;
+	}
+
+	xz_dec = xz_dec_init(XZ_DYNALLOC, (u32)-1);
+	if (!xz_dec)
+		return -ENOMEM;
+
+	xz_buf.in_size = size;
+	xz_buf.in = buf;
+	xz_buf.in_pos = 0;
+
+	do {
+		struct page *page = module_get_next_page(info);
+
+		if (IS_ERR(page)) {
+			retval = PTR_ERR(page);
+			goto out;
+		}
+
+		xz_buf.out = kmap_local_page(page);
+		xz_buf.out_pos = 0;
+		xz_buf.out_size = PAGE_SIZE;
+		xz_ret = xz_dec_run(xz_dec, &xz_buf);
+		kunmap_local(xz_buf.out);
+
+		new_size += xz_buf.out_pos;
+	} while (xz_buf.out_pos == PAGE_SIZE && xz_ret == XZ_OK);
+
+	if (xz_ret != XZ_STREAM_END) {
+		pr_err("decompression failed with status %d\n", xz_ret);
+		retval = -EINVAL;
+		goto out;
+	}
+
+	retval = new_size;
+
+ out:
+	xz_dec_end(xz_dec);
+	return retval;
+}
+#elif defined(CONFIG_MODULE_COMPRESS_ZSTD)
+#include <linux/zstd.h>
+#define MODULE_COMPRESSION	zstd
+#define MODULE_DECOMPRESS_FN	module_zstd_decompress
+
+static ssize_t module_zstd_decompress(struct load_info *info,
+				    const void *buf, size_t size)
+{
+	static const u8 signature[] = { 0x28, 0xb5, 0x2f, 0xfd };
+	ZSTD_outBuffer zstd_dec;
+	ZSTD_inBuffer zstd_buf;
+	zstd_frame_header header;
+	size_t wksp_size;
+	void *wksp = NULL;
+	ZSTD_DStream *dstream;
+	size_t ret;
+	size_t new_size = 0;
+	int retval;
+
+	if (size < sizeof(signature) ||
+	    memcmp(buf, signature, sizeof(signature))) {
+		pr_err("not a zstd compressed module\n");
+		return -EINVAL;
+	}
+
+	zstd_buf.src = buf;
+	zstd_buf.pos = 0;
+	zstd_buf.size = size;
+
+	ret = zstd_get_frame_header(&header, zstd_buf.src, zstd_buf.size);
+	if (ret != 0) {
+		pr_err("ZSTD-compressed data has an incomplete frame header\n");
+		retval = -EINVAL;
+		goto out;
+	}
+	if (header.windowSize > (1 << ZSTD_WINDOWLOG_MAX)) {
+		pr_err("ZSTD-compressed data has too large a window size\n");
+		retval = -EINVAL;
+		goto out;
+	}
+
+	wksp_size = zstd_dstream_workspace_bound(header.windowSize);
+	wksp = kvmalloc(wksp_size, GFP_KERNEL);
+	if (!wksp) {
+		retval = -ENOMEM;
+		goto out;
+	}
+
+	dstream = zstd_init_dstream(header.windowSize, wksp, wksp_size);
+	if (!dstream) {
+		pr_err("Can't initialize ZSTD stream\n");
+		retval = -ENOMEM;
+		goto out;
+	}
+
+	do {
+		struct page *page = module_get_next_page(info);
+
+		if (IS_ERR(page)) {
+			retval = PTR_ERR(page);
+			goto out;
+		}
+
+		zstd_dec.dst = kmap_local_page(page);
+		zstd_dec.pos = 0;
+		zstd_dec.size = PAGE_SIZE;
+
+		ret = zstd_decompress_stream(dstream, &zstd_dec, &zstd_buf);
+		kunmap_local(zstd_dec.dst);
+		retval = zstd_get_error_code(ret);
+		if (retval)
+			break;
+
+		new_size += zstd_dec.pos;
+	} while (zstd_dec.pos == PAGE_SIZE && ret != 0);
+
+	if (retval) {
+		pr_err("ZSTD-decompression failed with status %d\n", retval);
+		retval = -EINVAL;
+		goto out;
+	}
+
+	retval = new_size;
+
+ out:
+	kvfree(wksp);
+	return retval;
+}
+#else
+#error "Unexpected configuration for CONFIG_MODULE_DECOMPRESS"
+#endif
+
+int module_decompress(struct load_info *info, const void *buf, size_t size)
+{
+	unsigned int n_pages;
+	ssize_t data_size;
+	int error;
+
+#if defined(CONFIG_MODULE_STATS)
+	info->compressed_len = size;
+#endif
+
+	/*
+	 * Start with number of pages twice as big as needed for
+	 * compressed data.
+	 */
+	n_pages = DIV_ROUND_UP(size, PAGE_SIZE) * 2;
+	error = module_extend_max_pages(info, n_pages);
+	if (error)
+		return error;
+
+	data_size = MODULE_DECOMPRESS_FN(info, buf, size);
+	if (data_size < 0) {
+		error = data_size;
+		goto err;
+	}
+
+	info->hdr = vmap(info->pages, info->used_pages, VM_MAP, PAGE_KERNEL);
+	if (!info->hdr) {
+		error = -ENOMEM;
+		goto err;
+	}
+
+	info->len = data_size;
+	return 0;
+
+err:
+	module_decompress_cleanup(info);
+	return error;
+}
+
+void module_decompress_cleanup(struct load_info *info)
+{
+	int i;
+
+	if (info->hdr)
+		vunmap(info->hdr);
+
+	for (i = 0; i < info->used_pages; i++)
+		__free_page(info->pages[i]);
+
+	kvfree(info->pages);
+
+	info->pages = NULL;
+	info->max_pages = info->used_pages = 0;
+}
+
+#ifdef CONFIG_SYSFS
+static ssize_t compression_show(struct kobject *kobj,
+				struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, __stringify(MODULE_COMPRESSION) "\n");
+}
+
+static struct kobj_attribute module_compression_attr = __ATTR_RO(compression);
+
+static int __init module_decompress_sysfs_init(void)
+{
+	int error;
+
+	error = sysfs_create_file(&module_kset->kobj,
+				  &module_compression_attr.attr);
+	if (error)
+		pr_warn("Failed to create 'compression' attribute");
+
+	return 0;
+}
+late_initcall(module_decompress_sysfs_init);
+#endif

linux-7.2.3/kernel/module/dups.c

@@ -0,0 +1,247 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * kmod dups - the kernel module autoloader duplicate suppressor
+ *
+ * Copyright (C) 2023 Luis Chamberlain <mcgrof@kernel.org>
+ */
+
+#define pr_fmt(fmt)     "module: " fmt
+
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/sched/task.h>
+#include <linux/binfmts.h>
+#include <linux/syscalls.h>
+#include <linux/unistd.h>
+#include <linux/kmod.h>
+#include <linux/slab.h>
+#include <linux/completion.h>
+#include <linux/cred.h>
+#include <linux/file.h>
+#include <linux/workqueue.h>
+#include <linux/security.h>
+#include <linux/mount.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/resource.h>
+#include <linux/notifier.h>
+#include <linux/suspend.h>
+#include <linux/rwsem.h>
+#include <linux/ptrace.h>
+#include <linux/async.h>
+#include <linux/uaccess.h>
+
+#include "internal.h"
+
+#undef MODULE_PARAM_PREFIX
+#define MODULE_PARAM_PREFIX "module."
+static bool enable_dups_trace = IS_ENABLED(CONFIG_MODULE_DEBUG_AUTOLOAD_DUPS_TRACE);
+module_param(enable_dups_trace, bool_enable_only, 0644);
+
+/*
+ * Protects dup_kmod_reqs list, adds / removals with RCU.
+ */
+static DEFINE_MUTEX(kmod_dup_mutex);
+static LIST_HEAD(dup_kmod_reqs);
+
+struct kmod_dup_req {
+	struct list_head list;
+	char name[MODULE_NAME_LEN];
+	struct completion first_req_done;
+	struct work_struct complete_work;
+	struct delayed_work delete_work;
+	int dup_ret;
+};
+
+static struct kmod_dup_req *kmod_dup_request_lookup(char *module_name)
+{
+	struct kmod_dup_req *kmod_req;
+
+	list_for_each_entry_rcu(kmod_req, &dup_kmod_reqs, list,
+				lockdep_is_held(&kmod_dup_mutex)) {
+		if (strlen(kmod_req->name) == strlen(module_name) &&
+		    !memcmp(kmod_req->name, module_name, strlen(module_name))) {
+			return kmod_req;
+                }
+        }
+
+	return NULL;
+}
+
+static void kmod_dup_request_delete(struct work_struct *work)
+{
+	struct kmod_dup_req *kmod_req;
+	kmod_req = container_of(to_delayed_work(work), struct kmod_dup_req, delete_work);
+
+	/*
+	 * The typical situation is a module successully loaded. In that
+	 * situation the module will be present already in userspace. If
+	 * new requests come in after that, userspace will already know the
+	 * module is loaded so will just return 0 right away. There is still
+	 * a small chance right after we delete this entry new request_module()
+	 * calls may happen after that, they can happen. These heuristics
+	 * are to protect finit_module() abuse for auto-loading, if modules
+	 * are still tryign to auto-load even if a module is already loaded,
+	 * that's on them, and those inneficiencies should not be fixed by
+	 * kmod. The inneficies there are a call to modprobe and modprobe
+	 * just returning 0.
+	 */
+	mutex_lock(&kmod_dup_mutex);
+	list_del_rcu(&kmod_req->list);
+	synchronize_rcu();
+	mutex_unlock(&kmod_dup_mutex);
+	kfree(kmod_req);
+}
+
+static void kmod_dup_request_complete(struct work_struct *work)
+{
+	struct kmod_dup_req *kmod_req;
+
+	kmod_req = container_of(work, struct kmod_dup_req, complete_work);
+
+	/*
+	 * This will ensure that the kernel will let all the waiters get
+	 * informed its time to check the return value. It's time to
+	 * go home.
+	 */
+	complete_all(&kmod_req->first_req_done);
+
+	/*
+	 * Now that we have allowed prior request_module() calls to go on
+	 * with life, let's schedule deleting this entry. We don't have
+	 * to do it right away, but we *eventually* want to do it so to not
+	 * let this linger forever as this is just a boot optimization for
+	 * possible abuses of vmalloc() incurred by finit_module() thrashing.
+	 */
+	queue_delayed_work(system_dfl_wq, &kmod_req->delete_work, 60 * HZ);
+}
+
+bool kmod_dup_request_exists_wait(char *module_name, bool wait, int *dup_ret)
+{
+	struct kmod_dup_req *kmod_req, *new_kmod_req;
+	int ret;
+
+	/*
+	 * Pre-allocate the entry in case we have to use it later
+	 * to avoid contention with the mutex.
+	 */
+	new_kmod_req = kzalloc_obj(*new_kmod_req);
+	if (!new_kmod_req)
+		return false;
+
+	memcpy(new_kmod_req->name, module_name, strlen(module_name));
+	INIT_WORK(&new_kmod_req->complete_work, kmod_dup_request_complete);
+	INIT_DELAYED_WORK(&new_kmod_req->delete_work, kmod_dup_request_delete);
+	init_completion(&new_kmod_req->first_req_done);
+
+	mutex_lock(&kmod_dup_mutex);
+
+	kmod_req = kmod_dup_request_lookup(module_name);
+	if (!kmod_req) {
+		/*
+		 * If the first request that came through for a module
+		 * was with request_module_nowait() we cannot wait for it
+		 * and share its return value with other users which may
+		 * have used request_module() and need a proper return value
+		 * so just skip using them as an anchor.
+		 *
+		 * If a prior request to this one came through with
+		 * request_module() though, then a request_module_nowait()
+		 * would benefit from duplicate detection.
+		 */
+		if (!wait) {
+			kfree(new_kmod_req);
+			pr_debug("New request_module_nowait() for %s -- cannot track duplicates for this request\n", module_name);
+			mutex_unlock(&kmod_dup_mutex);
+			return false;
+		}
+
+		/*
+		 * There was no duplicate, just add the request so we can
+		 * keep tab on duplicates later.
+		 */
+		pr_debug("New request_module() for %s\n", module_name);
+		list_add_rcu(&new_kmod_req->list, &dup_kmod_reqs);
+		mutex_unlock(&kmod_dup_mutex);
+		return false;
+	}
+	mutex_unlock(&kmod_dup_mutex);
+
+	/* We are dealing with a duplicate request now */
+	kfree(new_kmod_req);
+
+	/*
+	 * To fix these try to use try_then_request_module() instead as that
+	 * will check if the component you are looking for is present or not.
+	 * You could also just queue a single request to load the module once,
+	 * instead of having each and everything you need try to request for
+	 * the module.
+	 *
+	 * Duplicate request_module() calls  can cause quite a bit of wasted
+	 * vmalloc() space when racing with userspace.
+	 */
+	if (enable_dups_trace)
+		WARN(1, "module-autoload: duplicate request for module %s\n", module_name);
+	else
+		pr_warn("module-autoload: duplicate request for module %s\n", module_name);
+
+	if (!wait) {
+		/*
+		 * If request_module_nowait() was used then the user just
+		 * wanted to issue the request and if another module request
+		 * was already its way with the same name we don't care for
+		 * the return value either. Let duplicate request_module_nowait()
+		 * calls bail out right away.
+		 */
+		*dup_ret = 0;
+		return true;
+	}
+
+	/*
+	 * If a duplicate request_module() was used they *may* care for
+	 * the return value, so we have no other option but to wait for
+	 * the first caller to complete. If the first caller used
+	 * the request_module_nowait() call, subsquent callers will
+	 * deal with the comprmise of getting a successful call with this
+	 * optimization enabled ...
+	 */
+	ret = wait_for_completion_state(&kmod_req->first_req_done,
+					TASK_KILLABLE);
+	if (ret) {
+		*dup_ret = ret;
+		return true;
+	}
+
+	/* Now the duplicate request has the same exact return value as the first request */
+	*dup_ret = kmod_req->dup_ret;
+
+	return true;
+}
+
+void kmod_dup_request_announce(char *module_name, int ret)
+{
+	struct kmod_dup_req *kmod_req;
+
+	mutex_lock(&kmod_dup_mutex);
+
+	kmod_req = kmod_dup_request_lookup(module_name);
+	if (!kmod_req)
+		goto out;
+
+	kmod_req->dup_ret = ret;
+
+	/*
+	 * If we complete() here we may allow duplicate threads
+	 * to continue before the first one that submitted the
+	 * request. We're in no rush also, given that each and
+	 * every bounce back to userspace is slow we avoid that
+	 * with a slight delay here. So queueue up the completion
+	 * and let duplicates suffer, just wait a tad bit longer.
+	 * There is no rush. But we also don't want to hold the
+	 * caller up forever or introduce any boot delays.
+	 */
+	queue_work(system_dfl_wq, &kmod_req->complete_work);
+
+out:
+	mutex_unlock(&kmod_dup_mutex);
+}

linux-7.2.3/kernel/module/internal.h

@@ -0,0 +1,423 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* Module internals
+ *
+ * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ * Copyright (C) 2023 Luis Chamberlain <mcgrof@kernel.org>
+ */
+
+#include <linux/elf.h>
+#include <linux/compiler.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/mm.h>
+
+#ifndef ARCH_SHF_SMALL
+#define ARCH_SHF_SMALL 0
+#endif
+
+/*
+ * Use highest 4 bits of sh_entsize to store the mod_mem_type of this
+ * section. This leaves 28 bits for offset on 32-bit systems, which is
+ * about 256 MiB (WARN_ON_ONCE if we exceed that).
+ */
+
+#define SH_ENTSIZE_TYPE_BITS	4
+#define SH_ENTSIZE_TYPE_SHIFT	(BITS_PER_LONG - SH_ENTSIZE_TYPE_BITS)
+#define SH_ENTSIZE_TYPE_MASK	((1UL << SH_ENTSIZE_TYPE_BITS) - 1)
+#define SH_ENTSIZE_OFFSET_MASK	((1UL << (BITS_PER_LONG - SH_ENTSIZE_TYPE_BITS)) - 1)
+
+/* Maximum number of characters written by module_flags() */
+#define MODULE_FLAGS_BUF_SIZE (TAINT_FLAGS_COUNT + 4)
+
+struct kernel_symbol {
+#ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS
+	int value_offset;
+	int name_offset;
+	int namespace_offset;
+#else
+	unsigned long value;
+	const char *name;
+	const char *namespace;
+#endif
+};
+
+extern struct mutex module_mutex;
+extern struct list_head modules;
+
+extern const struct module_attribute *const modinfo_attrs[];
+extern const size_t modinfo_attrs_count;
+
+/* Provided by the linker */
+extern const struct kernel_symbol __start___ksymtab[];
+extern const struct kernel_symbol __stop___ksymtab[];
+extern const u32 __start___kcrctab[];
+extern const u8 __start___kflagstab[];
+
+#define KMOD_PATH_LEN 256
+extern char modprobe_path[];
+
+struct load_info {
+	const char *name;
+	/* pointer to module in temporary copy, freed at end of load_module() */
+	struct module *mod;
+	Elf_Ehdr *hdr;
+	unsigned long len;
+	Elf_Shdr *sechdrs;
+	char *secstrings, *strtab;
+	unsigned long symoffs, stroffs, init_typeoffs, core_typeoffs;
+	bool sig_ok;
+#ifdef CONFIG_KALLSYMS
+	unsigned long mod_kallsyms_init_off;
+#endif
+#ifdef CONFIG_MODULE_DECOMPRESS
+#ifdef CONFIG_MODULE_STATS
+	unsigned long compressed_len;
+#endif
+	struct page **pages;
+	unsigned int max_pages;
+	unsigned int used_pages;
+#endif
+	struct {
+		unsigned int sym;
+		unsigned int str;
+		unsigned int mod;
+		unsigned int vers;
+		unsigned int info;
+		unsigned int pcpu;
+		unsigned int vers_ext_crc;
+		unsigned int vers_ext_name;
+	} index;
+};
+
+enum mod_license {
+	NOT_GPL_ONLY,
+	GPL_ONLY,
+};
+
+struct find_symbol_arg {
+	/* Input */
+	const char *name;
+	bool gplok;
+	bool warn;
+
+	/* Output */
+	struct module *owner;
+	const u32 *crc;
+	const struct kernel_symbol *sym;
+	enum mod_license license;
+};
+
+/* modules using other modules */
+struct module_use {
+	struct list_head source_list;
+	struct list_head target_list;
+	struct module *source, *target;
+};
+
+int mod_verify_sig(const void *mod, struct load_info *info);
+int try_to_force_load(struct module *mod, const char *reason);
+bool find_symbol(struct find_symbol_arg *fsa);
+struct module *find_module_all(const char *name, size_t len, bool even_unformed);
+int cmp_name(const void *name, const void *sym);
+long module_get_offset_and_type(struct module *mod, enum mod_mem_type type,
+				Elf_Shdr *sechdr, unsigned int section);
+char *module_flags(struct module *mod, char *buf, bool show_state);
+size_t module_flags_taint(unsigned long taints, char *buf);
+
+char *module_next_tag_pair(char *string, unsigned long *secsize);
+
+#define for_each_modinfo_entry(entry, info, name) \
+	for (entry = get_modinfo(info, name); entry; entry = get_next_modinfo(info, name, entry))
+
+static inline unsigned long kernel_symbol_value(const struct kernel_symbol *sym)
+{
+#ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS
+	return (unsigned long)offset_to_ptr(&sym->value_offset);
+#else
+	return sym->value;
+#endif
+}
+
+#ifdef CONFIG_LIVEPATCH
+int copy_module_elf(struct module *mod, struct load_info *info);
+void free_module_elf(struct module *mod);
+#else /* !CONFIG_LIVEPATCH */
+static inline int copy_module_elf(struct module *mod, struct load_info *info)
+{
+	return 0;
+}
+
+static inline void free_module_elf(struct module *mod) { }
+#endif /* CONFIG_LIVEPATCH */
+
+static inline bool set_livepatch_module(struct module *mod)
+{
+#ifdef CONFIG_LIVEPATCH
+	mod->klp = true;
+	return true;
+#else
+	return false;
+#endif
+}
+
+/**
+ * enum fail_dup_mod_reason - state at which a duplicate module was detected
+ *
+ * @FAIL_DUP_MOD_BECOMING: the module is read properly, passes all checks but
+ * 	we've determined that another module with the same name is already loaded
+ * 	or being processed on our &modules list. This happens on early_mod_check()
+ * 	right before layout_and_allocate(). The kernel would have already
+ * 	vmalloc()'d space for the entire module through finit_module(). If
+ * 	decompression was used two vmap() spaces were used. These failures can
+ * 	happen when userspace has not seen the module present on the kernel and
+ * 	tries to load the module multiple times at same time.
+ * @FAIL_DUP_MOD_LOAD: the module has been read properly, passes all validation
+ *	checks and the kernel determines that the module was unique and because
+ *	of this allocated yet another private kernel copy of the module space in
+ *	layout_and_allocate() but after this determined in add_unformed_module()
+ *	that another module with the same name is already loaded or being processed.
+ *	These failures should be mitigated as much as possible and are indicative
+ *	of really fast races in loading modules. Without module decompression
+ *	they waste twice as much vmap space. With module decompression three
+ *	times the module's size vmap space is wasted.
+ */
+enum fail_dup_mod_reason {
+	FAIL_DUP_MOD_BECOMING = 0,
+	FAIL_DUP_MOD_LOAD,
+};
+
+#ifdef CONFIG_MODULE_DEBUGFS
+extern struct dentry *mod_debugfs_root;
+#endif
+
+#ifdef CONFIG_MODULE_STATS
+
+#define mod_stat_add_long(count, var) atomic_long_add(count, var)
+#define mod_stat_inc(name) atomic_inc(name)
+
+extern atomic_long_t total_mod_size;
+extern atomic_long_t total_text_size;
+extern atomic_long_t invalid_kread_bytes;
+extern atomic_long_t invalid_decompress_bytes;
+
+extern atomic_t modcount;
+extern atomic_t failed_kreads;
+extern atomic_t failed_decompress;
+struct mod_fail_load {
+	struct list_head list;
+	char name[MODULE_NAME_LEN];
+	atomic_long_t count;
+	unsigned long dup_fail_mask;
+};
+
+int try_add_failed_module(const char *name, enum fail_dup_mod_reason reason);
+void mod_stat_bump_invalid(struct load_info *info, int flags);
+void mod_stat_bump_becoming(struct load_info *info, int flags);
+
+#else
+
+#define mod_stat_add_long(name, var)
+#define mod_stat_inc(name)
+
+static inline int try_add_failed_module(const char *name,
+					enum fail_dup_mod_reason reason)
+{
+	return 0;
+}
+
+static inline void mod_stat_bump_invalid(struct load_info *info, int flags)
+{
+}
+
+static inline void mod_stat_bump_becoming(struct load_info *info, int flags)
+{
+}
+
+#endif /* CONFIG_MODULE_STATS */
+
+#ifdef CONFIG_MODULE_DEBUG_AUTOLOAD_DUPS
+bool kmod_dup_request_exists_wait(char *module_name, bool wait, int *dup_ret);
+void kmod_dup_request_announce(char *module_name, int ret);
+#else
+static inline bool kmod_dup_request_exists_wait(char *module_name, bool wait, int *dup_ret)
+{
+	return false;
+}
+
+static inline void kmod_dup_request_announce(char *module_name, int ret)
+{
+}
+#endif
+
+#ifdef CONFIG_MODULE_UNLOAD_TAINT_TRACKING
+struct mod_unload_taint {
+	struct list_head list;
+	char name[MODULE_NAME_LEN];
+	unsigned long taints;
+	u64 count;
+};
+
+int try_add_tainted_module(struct module *mod);
+void print_unloaded_tainted_modules(void);
+#else /* !CONFIG_MODULE_UNLOAD_TAINT_TRACKING */
+static inline int try_add_tainted_module(struct module *mod)
+{
+	return 0;
+}
+
+static inline void print_unloaded_tainted_modules(void)
+{
+}
+#endif /* CONFIG_MODULE_UNLOAD_TAINT_TRACKING */
+
+#ifdef CONFIG_MODULE_DECOMPRESS
+int module_decompress(struct load_info *info, const void *buf, size_t size);
+void module_decompress_cleanup(struct load_info *info);
+#else
+static inline int module_decompress(struct load_info *info,
+				    const void *buf, size_t size)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void module_decompress_cleanup(struct load_info *info)
+{
+}
+#endif
+
+struct mod_tree_root {
+#ifdef CONFIG_MODULES_TREE_LOOKUP
+	struct latch_tree_root root;
+#endif
+	unsigned long addr_min;
+	unsigned long addr_max;
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	unsigned long data_addr_min;
+	unsigned long data_addr_max;
+#endif
+};
+
+extern struct mod_tree_root mod_tree;
+
+#ifdef CONFIG_MODULES_TREE_LOOKUP
+void mod_tree_insert(struct module *mod);
+void mod_tree_remove_init(struct module *mod);
+void mod_tree_remove(struct module *mod);
+struct module *mod_find(unsigned long addr, struct mod_tree_root *tree);
+#else /* !CONFIG_MODULES_TREE_LOOKUP */
+
+static inline void mod_tree_insert(struct module *mod) { }
+static inline void mod_tree_remove_init(struct module *mod) { }
+static inline void mod_tree_remove(struct module *mod) { }
+static inline struct module *mod_find(unsigned long addr, struct mod_tree_root *tree)
+{
+	struct module *mod;
+
+	list_for_each_entry_rcu(mod, &modules, list,
+				lockdep_is_held(&module_mutex)) {
+		if (within_module(addr, mod))
+			return mod;
+	}
+
+	return NULL;
+}
+#endif /* CONFIG_MODULES_TREE_LOOKUP */
+
+int module_enable_rodata_ro(const struct module *mod);
+int module_enable_rodata_ro_after_init(const struct module *mod);
+int module_enable_data_nx(const struct module *mod);
+int module_enable_text_rox(const struct module *mod);
+int module_enforce_rwx_sections(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs,
+				const char *secstrings,
+				const struct module *mod);
+void module_mark_ro_after_init(const Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
+			       const char *secstrings);
+
+#ifdef CONFIG_MODULE_SIG
+int module_sig_check(struct load_info *info, int flags);
+#else /* !CONFIG_MODULE_SIG */
+static inline int module_sig_check(struct load_info *info, int flags)
+{
+	return 0;
+}
+#endif /* !CONFIG_MODULE_SIG */
+
+#ifdef CONFIG_DEBUG_KMEMLEAK
+void kmemleak_load_module(const struct module *mod, const struct load_info *info);
+#else /* !CONFIG_DEBUG_KMEMLEAK */
+static inline void kmemleak_load_module(const struct module *mod,
+					const struct load_info *info) { }
+#endif /* CONFIG_DEBUG_KMEMLEAK */
+
+#ifdef CONFIG_KALLSYMS
+void init_build_id(struct module *mod, const struct load_info *info);
+void layout_symtab(struct module *mod, struct load_info *info);
+void add_kallsyms(struct module *mod, const struct load_info *info);
+
+static inline bool sect_empty(const Elf_Shdr *sect)
+{
+	return !(sect->sh_flags & SHF_ALLOC) || sect->sh_size == 0;
+}
+#else /* !CONFIG_KALLSYMS */
+static inline void init_build_id(struct module *mod, const struct load_info *info) { }
+static inline void layout_symtab(struct module *mod, struct load_info *info) { }
+static inline void add_kallsyms(struct module *mod, const struct load_info *info) { }
+#endif /* CONFIG_KALLSYMS */
+
+#ifdef CONFIG_SYSFS
+int mod_sysfs_setup(struct module *mod, const struct load_info *info,
+		    struct kernel_param *kparam, unsigned int num_params);
+void mod_sysfs_teardown(struct module *mod);
+void init_param_lock(struct module *mod);
+#else /* !CONFIG_SYSFS */
+static inline int mod_sysfs_setup(struct module *mod,
+			   	  const struct load_info *info,
+			   	  struct kernel_param *kparam,
+			   	  unsigned int num_params)
+{
+	return 0;
+}
+
+static inline void mod_sysfs_teardown(struct module *mod) { }
+static inline void init_param_lock(struct module *mod) { }
+#endif /* CONFIG_SYSFS */
+
+#ifdef CONFIG_MODVERSIONS
+int check_version(const struct load_info *info,
+		  const char *symname, struct module *mod, const u32 *crc);
+void module_layout(struct module *mod, struct modversion_info *ver, struct kernel_param *kp,
+		   struct kernel_symbol *ks, struct tracepoint * const *tp);
+int check_modstruct_version(const struct load_info *info, struct module *mod);
+int same_magic(const char *amagic, const char *bmagic, bool has_crcs);
+struct modversion_info_ext {
+	size_t remaining;
+	const u32 *crc;
+	const char *name;
+};
+void modversion_ext_start(const struct load_info *info, struct modversion_info_ext *ver);
+void modversion_ext_advance(struct modversion_info_ext *ver);
+#define for_each_modversion_info_ext(ver, info) \
+	for (modversion_ext_start(info, &ver); ver.remaining > 0; modversion_ext_advance(&ver))
+#else /* !CONFIG_MODVERSIONS */
+static inline int check_version(const struct load_info *info,
+				const char *symname,
+				struct module *mod,
+				const u32 *crc)
+{
+	return 1;
+}
+
+static inline int check_modstruct_version(const struct load_info *info,
+					  struct module *mod)
+{
+	return 1;
+}
+
+static inline int same_magic(const char *amagic, const char *bmagic, bool has_crcs)
+{
+	return strcmp(amagic, bmagic) == 0;
+}
+#endif /* CONFIG_MODVERSIONS */

linux-7.2.3/kernel/module/kallsyms.c

@@ -0,0 +1,496 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Module kallsyms support
+ *
+ * Copyright (C) 2010 Rusty Russell
+ */
+
+#include <linux/module.h>
+#include <linux/module_symbol.h>
+#include <linux/kallsyms.h>
+#include <linux/buildid.h>
+#include <linux/bsearch.h>
+#include "internal.h"
+
+/* Lookup exported symbol in given range of kernel_symbols */
+static const struct kernel_symbol *lookup_exported_symbol(const char *name,
+							  const struct kernel_symbol *start,
+							  const struct kernel_symbol *stop)
+{
+	return bsearch(name, start, stop - start,
+			sizeof(struct kernel_symbol), cmp_name);
+}
+
+static int is_exported(const char *name, unsigned long value,
+		       const struct module *mod)
+{
+	const struct kernel_symbol *ks;
+
+	if (!mod)
+		ks = lookup_exported_symbol(name, __start___ksymtab, __stop___ksymtab);
+	else
+		ks = lookup_exported_symbol(name, mod->syms, mod->syms + mod->num_syms);
+
+	return ks && kernel_symbol_value(ks) == value;
+}
+
+/* As per nm */
+static char elf_type(const Elf_Sym *sym, const struct load_info *info)
+{
+	const Elf_Shdr *sechdrs = info->sechdrs;
+
+	if (ELF_ST_BIND(sym->st_info) == STB_WEAK) {
+		if (ELF_ST_TYPE(sym->st_info) == STT_OBJECT)
+			return 'v';
+		else
+			return 'w';
+	}
+	if (sym->st_shndx == SHN_UNDEF)
+		return 'U';
+	if (sym->st_shndx == SHN_ABS || sym->st_shndx == info->index.pcpu)
+		return 'a';
+	if (sym->st_shndx >= SHN_LORESERVE)
+		return '?';
+	if (sechdrs[sym->st_shndx].sh_flags & SHF_EXECINSTR)
+		return 't';
+	if (sechdrs[sym->st_shndx].sh_flags & SHF_ALLOC &&
+	    sechdrs[sym->st_shndx].sh_type != SHT_NOBITS) {
+		if (!(sechdrs[sym->st_shndx].sh_flags & SHF_WRITE))
+			return 'r';
+		else if (sechdrs[sym->st_shndx].sh_flags & ARCH_SHF_SMALL)
+			return 'g';
+		else
+			return 'd';
+	}
+	if (sechdrs[sym->st_shndx].sh_type == SHT_NOBITS) {
+		if (sechdrs[sym->st_shndx].sh_flags & ARCH_SHF_SMALL)
+			return 's';
+		else
+			return 'b';
+	}
+	if (strstarts(info->secstrings + sechdrs[sym->st_shndx].sh_name,
+		      ".debug")) {
+		return 'n';
+	}
+	return '?';
+}
+
+static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs,
+			   unsigned int shnum, unsigned int pcpundx)
+{
+	const Elf_Shdr *sec;
+	enum mod_mem_type type;
+
+	if (src->st_shndx == SHN_UNDEF ||
+	    src->st_shndx >= shnum ||
+	    !src->st_name)
+		return false;
+
+#ifdef CONFIG_KALLSYMS_ALL
+	if (src->st_shndx == pcpundx)
+		return true;
+#endif
+
+	sec = sechdrs + src->st_shndx;
+	type = sec->sh_entsize >> SH_ENTSIZE_TYPE_SHIFT;
+	if (!(sec->sh_flags & SHF_ALLOC)
+#ifndef CONFIG_KALLSYMS_ALL
+	    || !(sec->sh_flags & SHF_EXECINSTR)
+#endif
+	    || mod_mem_type_is_init(type))
+		return false;
+
+	return true;
+}
+
+/*
+ * We only allocate and copy the strings needed by the parts of symtab
+ * we keep.  This is simple, but has the effect of making multiple
+ * copies of duplicates.  We could be more sophisticated, see
+ * linux-kernel thread starting with
+ * <73defb5e4bca04a6431392cc341112b1@localhost>.
+ */
+void layout_symtab(struct module *mod, struct load_info *info)
+{
+	Elf_Shdr *symsect = info->sechdrs + info->index.sym;
+	Elf_Shdr *strsect = info->sechdrs + info->index.str;
+	const Elf_Sym *src;
+	unsigned int i, nsrc, ndst, strtab_size = 0;
+	struct module_memory *mod_mem_data = &mod->mem[MOD_DATA];
+	struct module_memory *mod_mem_init_data = &mod->mem[MOD_INIT_DATA];
+
+	/* Put symbol section at end of init part of module. */
+	symsect->sh_flags |= SHF_ALLOC;
+	symsect->sh_entsize = module_get_offset_and_type(mod, MOD_INIT_DATA,
+							 symsect, info->index.sym);
+	pr_debug("\t%s\n", info->secstrings + symsect->sh_name);
+
+	src = (void *)info->hdr + symsect->sh_offset;
+	nsrc = symsect->sh_size / sizeof(*src);
+
+	/* Compute total space required for the core symbols' strtab. */
+	for (ndst = i = 0; i < nsrc; i++) {
+		if (i == 0 || is_livepatch_module(mod) ||
+		    is_core_symbol(src + i, info->sechdrs, info->hdr->e_shnum,
+				   info->index.pcpu)) {
+			strtab_size += strlen(&info->strtab[src[i].st_name]) + 1;
+			ndst++;
+		}
+	}
+
+	/* Append room for core symbols at end of core part. */
+	info->symoffs = ALIGN(mod_mem_data->size, symsect->sh_addralign ?: 1);
+	info->stroffs = mod_mem_data->size = info->symoffs + ndst * sizeof(Elf_Sym);
+	mod_mem_data->size += strtab_size;
+	/* Note add_kallsyms() computes strtab_size as core_typeoffs - stroffs */
+	info->core_typeoffs = mod_mem_data->size;
+	mod_mem_data->size += ndst * sizeof(char);
+
+	/* Put string table section at end of init part of module. */
+	strsect->sh_flags |= SHF_ALLOC;
+	strsect->sh_entsize = module_get_offset_and_type(mod, MOD_INIT_DATA,
+							 strsect, info->index.str);
+	pr_debug("\t%s\n", info->secstrings + strsect->sh_name);
+
+	/* We'll tack temporary mod_kallsyms on the end. */
+	mod_mem_init_data->size = ALIGN(mod_mem_init_data->size,
+					__alignof__(struct mod_kallsyms));
+	info->mod_kallsyms_init_off = mod_mem_init_data->size;
+
+	mod_mem_init_data->size += sizeof(struct mod_kallsyms);
+	info->init_typeoffs = mod_mem_init_data->size;
+	mod_mem_init_data->size += nsrc * sizeof(char);
+}
+
+/*
+ * We use the full symtab and strtab which layout_symtab arranged to
+ * be appended to the init section.  Later we switch to the cut-down
+ * core-only ones.
+ */
+void add_kallsyms(struct module *mod, const struct load_info *info)
+{
+	unsigned int i, ndst;
+	const Elf_Sym *src;
+	Elf_Sym *dst;
+	char *s;
+	Elf_Shdr *symsec = &info->sechdrs[info->index.sym];
+	unsigned long strtab_size;
+	void *data_base = mod->mem[MOD_DATA].base;
+	void *init_data_base = mod->mem[MOD_INIT_DATA].base;
+	struct mod_kallsyms *kallsyms;
+
+	kallsyms = init_data_base + info->mod_kallsyms_init_off;
+
+	kallsyms->symtab = (void *)symsec->sh_addr;
+	kallsyms->num_symtab = symsec->sh_size / sizeof(Elf_Sym);
+	/* Make sure we get permanent strtab: don't use info->strtab. */
+	kallsyms->strtab = (void *)info->sechdrs[info->index.str].sh_addr;
+	kallsyms->typetab = init_data_base + info->init_typeoffs;
+
+	/*
+	 * Now populate the cut down core kallsyms for after init
+	 * and set types up while we still have access to sections.
+	 */
+	mod->core_kallsyms.symtab = dst = data_base + info->symoffs;
+	mod->core_kallsyms.strtab = s = data_base + info->stroffs;
+	mod->core_kallsyms.typetab = data_base + info->core_typeoffs;
+	strtab_size = info->core_typeoffs - info->stroffs;
+	src = kallsyms->symtab;
+	for (ndst = i = 0; i < kallsyms->num_symtab; i++) {
+		kallsyms->typetab[i] = elf_type(src + i, info);
+		if (i == 0 || is_livepatch_module(mod) ||
+		    is_core_symbol(src + i, info->sechdrs, info->hdr->e_shnum,
+				   info->index.pcpu)) {
+			ssize_t ret;
+
+			mod->core_kallsyms.typetab[ndst] =
+				kallsyms->typetab[i];
+			dst[ndst] = src[i];
+			dst[ndst++].st_name = s - mod->core_kallsyms.strtab;
+			ret = strscpy(s, &kallsyms->strtab[src[i].st_name],
+				      strtab_size);
+			if (ret < 0)
+				break;
+			s += ret + 1;
+			strtab_size -= ret + 1;
+		}
+	}
+
+	/* Set up to point into init section. */
+	rcu_assign_pointer(mod->kallsyms, kallsyms);
+	mod->core_kallsyms.num_symtab = ndst;
+}
+
+#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID)
+void init_build_id(struct module *mod, const struct load_info *info)
+{
+	const Elf_Shdr *sechdr;
+	unsigned int i;
+
+	for (i = 0; i < info->hdr->e_shnum; i++) {
+		sechdr = &info->sechdrs[i];
+		if (!sect_empty(sechdr) && sechdr->sh_type == SHT_NOTE &&
+		    !build_id_parse_buf((void *)sechdr->sh_addr, mod->build_id,
+					sechdr->sh_size))
+			break;
+	}
+}
+#else
+void init_build_id(struct module *mod, const struct load_info *info)
+{
+}
+#endif
+
+static const char *kallsyms_symbol_name(struct mod_kallsyms *kallsyms, unsigned int symnum)
+{
+	return kallsyms->strtab + kallsyms->symtab[symnum].st_name;
+}
+
+/*
+ * Given a module and address, find the corresponding symbol and return its name
+ * while providing its size and offset if needed.
+ */
+static const char *find_kallsyms_symbol(struct module *mod,
+					unsigned long addr,
+					unsigned long *size,
+					unsigned long *offset)
+{
+	unsigned int i, best = 0;
+	unsigned long nextval, bestval;
+	struct mod_kallsyms *kallsyms = rcu_dereference(mod->kallsyms);
+	struct module_memory *mod_mem;
+
+	/* At worse, next value is at end of module */
+	if (within_module_init(addr, mod))
+		mod_mem = &mod->mem[MOD_INIT_TEXT];
+	else
+		mod_mem = &mod->mem[MOD_TEXT];
+
+	nextval = (unsigned long)mod_mem->base + mod_mem->size;
+
+	bestval = kallsyms_symbol_value(&kallsyms->symtab[best]);
+
+	/*
+	 * Scan for closest preceding symbol, and next symbol. (ELF
+	 * starts real symbols at 1).
+	 */
+	for (i = 1; i < kallsyms->num_symtab; i++) {
+		const Elf_Sym *sym = &kallsyms->symtab[i];
+		unsigned long thisval = kallsyms_symbol_value(sym);
+
+		if (sym->st_shndx == SHN_UNDEF)
+			continue;
+
+		/*
+		 * We ignore unnamed symbols: they're uninformative
+		 * and inserted at a whim.
+		 */
+		if (*kallsyms_symbol_name(kallsyms, i) == '\0' ||
+		    is_mapping_symbol(kallsyms_symbol_name(kallsyms, i)))
+			continue;
+
+		if (thisval <= addr && thisval > bestval) {
+			best = i;
+			bestval = thisval;
+		}
+		if (thisval > addr && thisval < nextval)
+			nextval = thisval;
+	}
+
+	if (!best)
+		return NULL;
+
+	if (size)
+		*size = nextval - bestval;
+	if (offset)
+		*offset = addr - bestval;
+
+	return kallsyms_symbol_name(kallsyms, best);
+}
+
+void * __weak dereference_module_function_descriptor(struct module *mod,
+						     void *ptr)
+{
+	return ptr;
+}
+
+/*
+ * For kallsyms to ask for address resolution.  NULL means not found.  Careful
+ * not to lock to avoid deadlock on oopses, RCU is enough.
+ */
+int module_address_lookup(unsigned long addr,
+			  unsigned long *size,
+			  unsigned long *offset,
+			  char **modname,
+			  const unsigned char **modbuildid,
+			  char *namebuf)
+{
+	const char *sym;
+	int ret = 0;
+	struct module *mod;
+
+	guard(rcu)();
+	mod = __module_address(addr);
+	if (mod) {
+		if (modname)
+			*modname = mod->name;
+		if (modbuildid)
+			*modbuildid = module_buildid(mod);
+
+		sym = find_kallsyms_symbol(mod, addr, size, offset);
+
+		if (sym)
+			ret = strscpy(namebuf, sym, KSYM_NAME_LEN);
+	}
+	return ret;
+}
+
+int lookup_module_symbol_name(unsigned long addr, char *symname)
+{
+	struct module *mod;
+
+	guard(rcu)();
+	list_for_each_entry_rcu(mod, &modules, list) {
+		if (mod->state == MODULE_STATE_UNFORMED)
+			continue;
+		if (within_module(addr, mod)) {
+			const char *sym;
+
+			sym = find_kallsyms_symbol(mod, addr, NULL, NULL);
+			if (!sym)
+				goto out;
+
+			strscpy(symname, sym, KSYM_NAME_LEN);
+			return 0;
+		}
+	}
+out:
+	return -ERANGE;
+}
+
+int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
+		       char *name, char *module_name, int *exported)
+{
+	struct module *mod;
+
+	guard(rcu)();
+	list_for_each_entry_rcu(mod, &modules, list) {
+		struct mod_kallsyms *kallsyms;
+
+		if (mod->state == MODULE_STATE_UNFORMED)
+			continue;
+		kallsyms = rcu_dereference(mod->kallsyms);
+		if (symnum < kallsyms->num_symtab) {
+			const Elf_Sym *sym = &kallsyms->symtab[symnum];
+
+			*value = kallsyms_symbol_value(sym);
+			*type = kallsyms->typetab[symnum];
+			strscpy(name, kallsyms_symbol_name(kallsyms, symnum), KSYM_NAME_LEN);
+			strscpy(module_name, mod->name, MODULE_NAME_LEN);
+			*exported = is_exported(name, *value, mod);
+			return 0;
+		}
+		symnum -= kallsyms->num_symtab;
+	}
+	return -ERANGE;
+}
+
+/* Given a module and name of symbol, find and return the symbol's value */
+static unsigned long __find_kallsyms_symbol_value(struct module *mod, const char *name)
+{
+	unsigned int i;
+	struct mod_kallsyms *kallsyms = rcu_dereference(mod->kallsyms);
+
+	for (i = 0; i < kallsyms->num_symtab; i++) {
+		const Elf_Sym *sym = &kallsyms->symtab[i];
+
+		if (strcmp(name, kallsyms_symbol_name(kallsyms, i)) == 0 &&
+		    sym->st_shndx != SHN_UNDEF)
+			return kallsyms_symbol_value(sym);
+	}
+	return 0;
+}
+
+static unsigned long __module_kallsyms_lookup_name(const char *name)
+{
+	struct module *mod;
+	char *colon;
+
+	colon = strnchr(name, MODULE_NAME_LEN, ':');
+	if (colon) {
+		mod = find_module_all(name, colon - name, false);
+		if (mod)
+			return __find_kallsyms_symbol_value(mod, colon + 1);
+		return 0;
+	}
+
+	list_for_each_entry_rcu(mod, &modules, list) {
+		unsigned long ret;
+
+		if (mod->state == MODULE_STATE_UNFORMED)
+			continue;
+		ret = __find_kallsyms_symbol_value(mod, name);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+/* Look for this name: can be of form module:name. */
+unsigned long module_kallsyms_lookup_name(const char *name)
+{
+	/* Don't lock: we're in enough trouble already. */
+	guard(rcu)();
+	return __module_kallsyms_lookup_name(name);
+}
+
+unsigned long find_kallsyms_symbol_value(struct module *mod, const char *name)
+{
+	guard(rcu)();
+	return __find_kallsyms_symbol_value(mod, name);
+}
+
+int module_kallsyms_on_each_symbol(const char *modname,
+				   int (*fn)(void *, const char *, unsigned long),
+				   void *data)
+{
+	struct module *mod;
+	unsigned int i;
+	int ret = 0;
+
+	mutex_lock(&module_mutex);
+	list_for_each_entry(mod, &modules, list) {
+		struct mod_kallsyms *kallsyms;
+
+		if (mod->state == MODULE_STATE_UNFORMED)
+			continue;
+
+		if (modname && strcmp(modname, mod->name))
+			continue;
+
+		kallsyms = rcu_dereference_check(mod->kallsyms,
+						 lockdep_is_held(&module_mutex));
+
+		for (i = 0; i < kallsyms->num_symtab; i++) {
+			const Elf_Sym *sym = &kallsyms->symtab[i];
+
+			if (sym->st_shndx == SHN_UNDEF)
+				continue;
+
+			ret = fn(data, kallsyms_symbol_name(kallsyms, i),
+				 kallsyms_symbol_value(sym));
+			if (ret != 0)
+				goto out;
+		}
+
+		/*
+		 * The given module is found, the subsequent modules do not
+		 * need to be compared.
+		 */
+		if (modname)
+			break;
+	}
+out:
+	mutex_unlock(&module_mutex);
+	return ret;
+}

linux-7.2.3/kernel/module/kdb.c

@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Module kdb support
+ *
+ * Copyright (C) 2010 Jason Wessel
+ */
+
+#include <linux/module.h>
+#include <linux/kdb.h>
+#include "internal.h"
+
+/*
+ * kdb_lsmod - This function implements the 'lsmod' command.  Lists
+ *	currently loaded kernel modules.
+ *	Mostly taken from userland lsmod.
+ */
+int kdb_lsmod(int argc, const char **argv)
+{
+	struct module *mod;
+
+	if (argc != 0)
+		return KDB_ARGCOUNT;
+
+	kdb_printf("Module                  Size  modstruct     Used by\n");
+	list_for_each_entry(mod, &modules, list) {
+		if (mod->state == MODULE_STATE_UNFORMED)
+			continue;
+
+		kdb_printf("%-20s%8u", mod->name, mod->mem[MOD_TEXT].size);
+		kdb_printf("/%8u", mod->mem[MOD_RODATA].size);
+		kdb_printf("/%8u", mod->mem[MOD_RO_AFTER_INIT].size);
+		kdb_printf("/%8u", mod->mem[MOD_DATA].size);
+
+		kdb_printf("  0x%px ", (void *)mod);
+#ifdef CONFIG_MODULE_UNLOAD
+		kdb_printf("%4d ", module_refcount(mod));
+#endif
+		if (mod->state == MODULE_STATE_GOING)
+			kdb_printf(" (Unloading)");
+		else if (mod->state == MODULE_STATE_COMING)
+			kdb_printf(" (Loading)");
+		else
+			kdb_printf(" (Live)");
+		kdb_printf(" 0x%px", mod->mem[MOD_TEXT].base);
+		kdb_printf("/0x%px", mod->mem[MOD_RODATA].base);
+		kdb_printf("/0x%px", mod->mem[MOD_RO_AFTER_INIT].base);
+		kdb_printf("/0x%px", mod->mem[MOD_DATA].base);
+
+#ifdef CONFIG_MODULE_UNLOAD
+		{
+			struct module_use *use;
+
+			kdb_printf(" [ ");
+			list_for_each_entry(use, &mod->source_list,
+					    source_list)
+				kdb_printf("%s ", use->target->name);
+			kdb_printf("]\n");
+		}
+#endif
+	}
+
+	return 0;
+}

linux-7.2.3/kernel/module/kmod.c

@@ -0,0 +1,180 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * kmod - the kernel module loader
+ *
+ * Copyright (C) 2023 Luis Chamberlain <mcgrof@kernel.org>
+ */
+
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/sched/task.h>
+#include <linux/binfmts.h>
+#include <linux/syscalls.h>
+#include <linux/unistd.h>
+#include <linux/kmod.h>
+#include <linux/slab.h>
+#include <linux/completion.h>
+#include <linux/cred.h>
+#include <linux/file.h>
+#include <linux/workqueue.h>
+#include <linux/security.h>
+#include <linux/mount.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/resource.h>
+#include <linux/notifier.h>
+#include <linux/suspend.h>
+#include <linux/rwsem.h>
+#include <linux/ptrace.h>
+#include <linux/async.h>
+#include <linux/uaccess.h>
+
+#include <trace/events/module.h>
+#include "internal.h"
+
+/*
+ * Assuming:
+ *
+ * threads = div64_u64((u64) totalram_pages * (u64) PAGE_SIZE,
+ *		       (u64) THREAD_SIZE * 8UL);
+ *
+ * If you need less than 50 threads would mean we're dealing with systems
+ * smaller than 3200 pages. This assumes you are capable of having ~13M memory,
+ * and this would only be an upper limit, after which the OOM killer would take
+ * effect. Systems like these are very unlikely if modules are enabled.
+ */
+#define MAX_KMOD_CONCURRENT 50
+static DEFINE_SEMAPHORE(kmod_concurrent_max, MAX_KMOD_CONCURRENT);
+
+/*
+ * This is a restriction on having *all* MAX_KMOD_CONCURRENT threads
+ * running at the same time without returning. When this happens we
+ * believe you've somehow ended up with a recursive module dependency
+ * creating a loop.
+ *
+ * We have no option but to fail.
+ *
+ * Userspace should proactively try to detect and prevent these.
+ */
+#define MAX_KMOD_ALL_BUSY_TIMEOUT 5
+
+/*
+	modprobe_path is set via /proc/sys.
+*/
+char modprobe_path[KMOD_PATH_LEN] = CONFIG_MODPROBE_PATH;
+
+static void free_modprobe_argv(struct subprocess_info *info)
+{
+	kfree(info->argv[3]); /* check call_modprobe() */
+	kfree(info->argv);
+}
+
+static int call_modprobe(char *orig_module_name, int wait)
+{
+	struct subprocess_info *info;
+	static char *envp[] = {
+		"HOME=/",
+		"TERM=linux",
+		"PATH=/sbin:/usr/sbin:/bin:/usr/bin",
+		NULL
+	};
+	char *module_name;
+	int ret;
+
+	char **argv = kmalloc(sizeof(char *[5]), GFP_KERNEL);
+	if (!argv)
+		goto out;
+
+	module_name = kstrdup(orig_module_name, GFP_KERNEL);
+	if (!module_name)
+		goto free_argv;
+
+	argv[0] = modprobe_path;
+	argv[1] = "-q";
+	argv[2] = "--";
+	argv[3] = module_name;	/* check free_modprobe_argv() */
+	argv[4] = NULL;
+
+	info = call_usermodehelper_setup(modprobe_path, argv, envp, GFP_KERNEL,
+					 NULL, free_modprobe_argv, NULL);
+	if (!info)
+		goto free_module_name;
+
+	ret = call_usermodehelper_exec(info, wait | UMH_KILLABLE);
+	kmod_dup_request_announce(orig_module_name, ret);
+	return ret;
+
+free_module_name:
+	kfree(module_name);
+free_argv:
+	kfree(argv);
+out:
+	kmod_dup_request_announce(orig_module_name, -ENOMEM);
+	return -ENOMEM;
+}
+
+/**
+ * __request_module - try to load a kernel module
+ * @wait: wait (or not) for the operation to complete
+ * @fmt: printf style format string for the name of the module
+ * @...: arguments as specified in the format string
+ *
+ * Load a module using the user mode module loader. The function returns
+ * zero on success or a negative errno code or positive exit code from
+ * "modprobe" on failure. Note that a successful module load does not mean
+ * the module did not then unload and exit on an error of its own. Callers
+ * must check that the service they requested is now available not blindly
+ * invoke it.
+ *
+ * If module auto-loading support is disabled then this function
+ * simply returns -ENOENT.
+ */
+int __request_module(bool wait, const char *fmt, ...)
+{
+	va_list args;
+	char module_name[MODULE_NAME_LEN];
+	int ret, dup_ret;
+
+	/*
+	 * We don't allow synchronous module loading from async.  Module
+	 * init may invoke async_synchronize_full() which will end up
+	 * waiting for this task which already is waiting for the module
+	 * loading to complete, leading to a deadlock.
+	 */
+	WARN_ON_ONCE(wait && current_is_async());
+
+	if (!modprobe_path[0])
+		return -ENOENT;
+
+	va_start(args, fmt);
+	ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args);
+	va_end(args);
+	if (ret >= MODULE_NAME_LEN)
+		return -ENAMETOOLONG;
+
+	ret = security_kernel_module_request(module_name);
+	if (ret)
+		return ret;
+
+	ret = down_timeout(&kmod_concurrent_max, MAX_KMOD_ALL_BUSY_TIMEOUT * HZ);
+	if (ret) {
+		pr_warn_ratelimited("request_module: modprobe %s cannot be processed, kmod busy with %d threads for more than %d seconds now",
+				    module_name, MAX_KMOD_CONCURRENT, MAX_KMOD_ALL_BUSY_TIMEOUT);
+		return ret;
+	}
+
+	trace_module_request(module_name, wait, _RET_IP_);
+
+	if (kmod_dup_request_exists_wait(module_name, wait, &dup_ret)) {
+		ret = dup_ret;
+		goto out;
+	}
+
+	ret = call_modprobe(module_name, wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC);
+
+out:
+	up(&kmod_concurrent_max);
+
+	return ret;
+}
+EXPORT_SYMBOL(__request_module);

linux-7.2.3/kernel/module/livepatch.c

@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Module livepatch support
+ *
+ * Copyright (C) 2016 Jessica Yu <jeyu@redhat.com>
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+/*
+ * Persist ELF information about a module. Copy the ELF header,
+ * section header table, section string table, and symtab section
+ * index from info to mod->klp_info.
+ */
+int copy_module_elf(struct module *mod, struct load_info *info)
+{
+	unsigned int size, symndx;
+	int ret;
+
+	size = sizeof(*mod->klp_info);
+	mod->klp_info = kmalloc(size, GFP_KERNEL);
+	if (!mod->klp_info)
+		return -ENOMEM;
+
+	/* ELF header */
+	size = sizeof(mod->klp_info->hdr);
+	memcpy(&mod->klp_info->hdr, info->hdr, size);
+
+	/* ELF section header table */
+	size = sizeof(*info->sechdrs) * info->hdr->e_shnum;
+	mod->klp_info->sechdrs = kmemdup(info->sechdrs, size, GFP_KERNEL);
+	if (!mod->klp_info->sechdrs) {
+		ret = -ENOMEM;
+		goto free_info;
+	}
+
+	/* ELF section name string table */
+	size = info->sechdrs[info->hdr->e_shstrndx].sh_size;
+	mod->klp_info->secstrings = kmemdup(info->secstrings, size, GFP_KERNEL);
+	if (!mod->klp_info->secstrings) {
+		ret = -ENOMEM;
+		goto free_sechdrs;
+	}
+
+	/* ELF symbol section index */
+	symndx = info->index.sym;
+	mod->klp_info->symndx = symndx;
+
+	/*
+	 * For livepatch modules, core_kallsyms.symtab is a complete
+	 * copy of the original symbol table. Adjust sh_addr to point
+	 * to core_kallsyms.symtab since the copy of the symtab in module
+	 * init memory is freed at the end of do_init_module().
+	 */
+	mod->klp_info->sechdrs[symndx].sh_addr = (unsigned long)mod->core_kallsyms.symtab;
+
+	return 0;
+
+free_sechdrs:
+	kfree(mod->klp_info->sechdrs);
+free_info:
+	kfree(mod->klp_info);
+	return ret;
+}
+
+void free_module_elf(struct module *mod)
+{
+	kfree(mod->klp_info->sechdrs);
+	kfree(mod->klp_info->secstrings);
+	kfree(mod->klp_info);
+}

linux-7.2.3/kernel/module/procfs.c

@@ -0,0 +1,152 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Module proc support
+ *
+ * Copyright (C) 2008 Alexey Dobriyan
+ */
+
+#include <linux/module.h>
+#include <linux/kallsyms.h>
+#include <linux/mutex.h>
+#include <linux/seq_file.h>
+#include <linux/proc_fs.h>
+#include "internal.h"
+
+#ifdef CONFIG_MODULE_UNLOAD
+static inline void print_unload_info(struct seq_file *m, struct module *mod)
+{
+	struct module_use *use;
+	int printed_something = 0;
+
+	seq_printf(m, " %i ", module_refcount(mod));
+
+	/*
+	 * Always include a trailing , so userspace can differentiate
+	 * between this and the old multi-field proc format.
+	 */
+	list_for_each_entry(use, &mod->source_list, source_list) {
+		printed_something = 1;
+		seq_printf(m, "%s,", use->source->name);
+	}
+
+	if (mod->init && !mod->exit) {
+		printed_something = 1;
+		seq_puts(m, "[permanent],");
+	}
+
+	if (!printed_something)
+		seq_puts(m, "-");
+}
+#else /* !CONFIG_MODULE_UNLOAD */
+static inline void print_unload_info(struct seq_file *m, struct module *mod)
+{
+	/* We don't know the usage count, or what modules are using. */
+	seq_puts(m, " - -");
+}
+#endif /* CONFIG_MODULE_UNLOAD */
+
+/* Called by the /proc file system to return a list of modules. */
+static void *m_start(struct seq_file *m, loff_t *pos)
+{
+	mutex_lock(&module_mutex);
+	return seq_list_start(&modules, *pos);
+}
+
+static void *m_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	return seq_list_next(p, &modules, pos);
+}
+
+static void m_stop(struct seq_file *m, void *p)
+{
+	mutex_unlock(&module_mutex);
+}
+
+static unsigned int module_total_size(struct module *mod)
+{
+	int size = 0;
+
+	for_each_mod_mem_type(type)
+		size += mod->mem[type].size;
+	return size;
+}
+
+static int m_show(struct seq_file *m, void *p)
+{
+	struct module *mod = list_entry(p, struct module, list);
+	char buf[MODULE_FLAGS_BUF_SIZE];
+	void *value;
+	unsigned int size;
+
+	/* We always ignore unformed modules. */
+	if (mod->state == MODULE_STATE_UNFORMED)
+		return 0;
+
+	size = module_total_size(mod);
+	seq_printf(m, "%s %u", mod->name, size);
+	print_unload_info(m, mod);
+
+	/* Informative for users. */
+	seq_printf(m, " %s",
+		   mod->state == MODULE_STATE_GOING ? "Unloading" :
+		   mod->state == MODULE_STATE_COMING ? "Loading" :
+		   "Live");
+	/* Used by oprofile and other similar tools. */
+	value = m->private ? NULL : mod->mem[MOD_TEXT].base;
+	seq_printf(m, " 0x%px", value);
+
+	/* Taints info */
+	if (mod->taints)
+		seq_printf(m, " %s", module_flags(mod, buf, true));
+
+	seq_puts(m, "\n");
+	return 0;
+}
+
+/*
+ * Format: modulename size refcount deps address
+ *
+ * Where refcount is a number or -, and deps is a comma-separated list
+ * of depends or -.
+ */
+static const struct seq_operations modules_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= m_show
+};
+
+/*
+ * This also sets the "private" pointer to non-NULL if the
+ * kernel pointers should be hidden (so you can just test
+ * "m->private" to see if you should keep the values private).
+ *
+ * We use the same logic as for /proc/kallsyms.
+ */
+static int modules_open(struct inode *inode, struct file *file)
+{
+	int err = seq_open(file, &modules_op);
+
+	if (!err) {
+		struct seq_file *m = file->private_data;
+
+		m->private = kallsyms_show_value(file->f_cred) ? NULL : (void *)8ul;
+	}
+
+	return err;
+}
+
+static const struct proc_ops modules_proc_ops = {
+	.proc_flags	= PROC_ENTRY_PERMANENT,
+	.proc_open	= modules_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= seq_release,
+};
+
+static int __init proc_modules_init(void)
+{
+	proc_create("modules", 0, NULL, &modules_proc_ops);
+	return 0;
+}
+module_init(proc_modules_init);

linux-7.2.3/kernel/module/signing.c

@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Module signature checker
+ *
+ * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/module_signature.h>
+#include <linux/string.h>
+#include <linux/verification.h>
+#include <linux/security.h>
+#include <crypto/public_key.h>
+#include <uapi/linux/module.h>
+#include "internal.h"
+
+#undef MODULE_PARAM_PREFIX
+#define MODULE_PARAM_PREFIX "module."
+
+static bool sig_enforce = IS_ENABLED(CONFIG_MODULE_SIG_FORCE);
+module_param(sig_enforce, bool_enable_only, 0644);
+
+/*
+ * Export sig_enforce kernel cmdline parameter to allow other subsystems rely
+ * on that instead of directly to CONFIG_MODULE_SIG_FORCE config.
+ */
+bool is_module_sig_enforced(void)
+{
+	return sig_enforce;
+}
+EXPORT_SYMBOL(is_module_sig_enforced);
+
+void set_module_sig_enforced(void)
+{
+	sig_enforce = true;
+}
+
+/*
+ * Verify the signature on a module.
+ */
+int mod_verify_sig(const void *mod, struct load_info *info)
+{
+	struct module_signature ms;
+	size_t sig_len, modlen = info->len;
+	int ret;
+
+	pr_devel("==>%s(,%zu)\n", __func__, modlen);
+
+	if (modlen <= sizeof(ms))
+		return -EBADMSG;
+
+	memcpy(&ms, mod + (modlen - sizeof(ms)), sizeof(ms));
+
+	ret = mod_check_sig(&ms, modlen, "module");
+	if (ret)
+		return ret;
+
+	sig_len = be32_to_cpu(ms.sig_len);
+	modlen -= sig_len + sizeof(ms);
+	info->len = modlen;
+
+	return verify_pkcs7_signature(mod, modlen, mod + modlen, sig_len,
+				      VERIFY_USE_SECONDARY_KEYRING,
+				      VERIFYING_MODULE_SIGNATURE,
+				      NULL, NULL);
+}
+
+int module_sig_check(struct load_info *info, int flags)
+{
+	int err = -ENODATA;
+	const unsigned long markerlen = sizeof(MODULE_SIGNATURE_MARKER) - 1;
+	const char *reason;
+	const void *mod = info->hdr;
+	bool mangled_module = flags & (MODULE_INIT_IGNORE_MODVERSIONS |
+				       MODULE_INIT_IGNORE_VERMAGIC);
+	/*
+	 * Do not allow mangled modules as a module with version information
+	 * removed is no longer the module that was signed.
+	 */
+	if (!mangled_module &&
+	    info->len > markerlen &&
+	    memcmp(mod + info->len - markerlen, MODULE_SIGNATURE_MARKER, markerlen) == 0) {
+		/* We truncate the module to discard the signature */
+		info->len -= markerlen;
+		err = mod_verify_sig(mod, info);
+		if (!err) {
+			info->sig_ok = true;
+			return 0;
+		}
+	}
+
+	/*
+	 * We don't permit modules to be loaded into the trusted kernels
+	 * without a valid signature on them, but if we're not enforcing,
+	 * certain errors are non-fatal.
+	 */
+	switch (err) {
+	case -ENODATA:
+		reason = "unsigned module";
+		break;
+	case -ENOPKG:
+		reason = "module with unsupported crypto";
+		break;
+	case -ENOKEY:
+		reason = "module with unavailable key";
+		break;
+
+	default:
+		/*
+		 * All other errors are fatal, including lack of memory,
+		 * unparseable signatures, and signature check failures --
+		 * even if signatures aren't required.
+		 */
+		return err;
+	}
+
+	if (is_module_sig_enforced()) {
+		pr_notice("Loading of %s is rejected\n", reason);
+		return -EKEYREJECTED;
+	}
+
+	return security_locked_down(LOCKDOWN_MODULE_SIGNATURE);
+}

linux-7.2.3/kernel/module/stats.c

@@ -0,0 +1,432 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Debugging module statistics.
+ *
+ * Copyright (C) 2023 Luis Chamberlain <mcgrof@kernel.org>
+ */
+
+#include <linux/module.h>
+#include <uapi/linux/module.h>
+#include <linux/string.h>
+#include <linux/printk.h>
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/debugfs.h>
+#include <linux/rculist.h>
+#include <linux/math.h>
+
+#include "internal.h"
+
+/**
+ * DOC: module debugging statistics overview
+ *
+ * Enabling CONFIG_MODULE_STATS enables module debugging statistics which
+ * are useful to monitor and root cause memory pressure issues with module
+ * loading. These statistics are useful to allow us to improve production
+ * workloads.
+ *
+ * The current module debugging statistics supported help keep track of module
+ * loading failures to enable improvements either for kernel module auto-loading
+ * usage (request_module()) or interactions with userspace. Statistics are
+ * provided to track all possible failures in the finit_module() path and memory
+ * wasted in this process space.  Each of the failure counters are associated
+ * to a type of module loading failure which is known to incur a certain amount
+ * of memory allocation loss. In the worst case loading a module will fail after
+ * a 3 step memory allocation process:
+ *
+ *   a) memory allocated with kernel_read_file_from_fd()
+ *   b) module decompression processes the file read from
+ *      kernel_read_file_from_fd(), and vmap() is used to map
+ *      the decompressed module to a new local buffer which represents
+ *      a copy of the decompressed module passed from userspace. The buffer
+ *      from kernel_read_file_from_fd() is freed right away.
+ *   c) layout_and_allocate() allocates space for the final resting
+ *      place where we would keep the module if it were to be processed
+ *      successfully.
+ *
+ * If a failure occurs after these three different allocations only one
+ * counter will be incremented with the summation of the allocated bytes freed
+ * incurred during this failure. Likewise, if module loading failed only after
+ * step b) a separate counter is used and incremented for the bytes freed and
+ * not used during both of those allocations.
+ *
+ * Virtual memory space can be limited, for example on x86 virtual memory size
+ * defaults to 128 MiB. We should strive to limit and avoid wasting virtual
+ * memory allocations when possible. These module debugging statistics help
+ * to evaluate how much memory is being wasted on bootup due to module loading
+ * failures.
+ *
+ * All counters are designed to be incremental. Atomic counters are used so to
+ * remain simple and avoid delays and deadlocks.
+ */
+
+/**
+ * DOC: dup_failed_modules - tracks duplicate failed modules
+ *
+ * Linked list of modules which failed to be loaded because an already existing
+ * module with the same name was already being processed or already loaded.
+ * The finit_module() system call incurs heavy virtual memory allocations. In
+ * the worst case an finit_module() system call can end up allocating virtual
+ * memory 3 times:
+ *
+ *   1) kernel_read_file_from_fd() call uses vmalloc()
+ *   2) optional module decompression uses vmap()
+ *   3) layout_and allocate() can use vzalloc() or an arch specific variation of
+ *      vmalloc to deal with ELF sections requiring special permissions
+ *
+ * In practice on a typical boot today most finit_module() calls fail due to
+ * the module with the same name already being loaded or about to be processed.
+ * All virtual memory allocated to these failed modules will be freed with
+ * no functional use.
+ *
+ * To help with this the dup_failed_modules allows us to track modules which
+ * failed to load due to the fact that a module was already loaded or being
+ * processed.  There are only two points at which we can fail such calls,
+ * we list them below along with the number of virtual memory allocation
+ * calls:
+ *
+ *   a) FAIL_DUP_MOD_BECOMING: at the end of early_mod_check() before
+ *	layout_and_allocate().
+ *	- with module decompression: 2 virtual memory allocation calls
+ *	- without module decompression: 1 virtual memory allocation calls
+ *   b) FAIL_DUP_MOD_LOAD: after layout_and_allocate() on add_unformed_module()
+ *   	- with module decompression 3 virtual memory allocation calls
+ *   	- without module decompression 2 virtual memory allocation calls
+ *
+ * We should strive to get this list to be as small as possible. If this list
+ * is not empty it is a reflection of possible work or optimizations possible
+ * either in-kernel or in userspace.
+ */
+static LIST_HEAD(dup_failed_modules);
+
+/**
+ * DOC: module statistics debugfs counters
+ *
+ * The total amount of wasted virtual memory allocation space during module
+ * loading can be computed by adding the total from the summation:
+ *
+ *   * @invalid_kread_bytes +
+ *     @invalid_decompress_bytes +
+ *     @invalid_becoming_bytes +
+ *     @invalid_mod_bytes
+ *
+ * The following debugfs counters are available to inspect module loading
+ * failures:
+ *
+ *   * total_mod_size: total bytes ever used by all modules we've dealt with on
+ *     this system
+ *   * total_text_size: total bytes of the .text and .init.text ELF section
+ *     sizes we've dealt with on this system
+ *   * invalid_kread_bytes: bytes allocated and then freed on failures which
+ *     happen due to the initial kernel_read_file_from_fd(). kernel_read_file_from_fd()
+ *     uses vmalloc(). These should typically not happen unless your system is
+ *     under memory pressure.
+ *   * invalid_decompress_bytes: number of bytes allocated and freed due to
+ *     memory allocations in the module decompression path that use vmap().
+ *     These typically should not happen unless your system is under memory
+ *     pressure.
+ *   * invalid_becoming_bytes: total number of bytes allocated and freed used
+ *     to read the kernel module userspace wants us to read before we
+ *     promote it to be processed to be added to our @modules linked list. These
+ *     failures can happen if we had a check in between a successful kernel_read_file_from_fd()
+ *     call and right before we allocate the our private memory for the module
+ *     which would be kept if the module is successfully loaded. The most common
+ *     reason for this failure is when userspace is racing to load a module
+ *     which it does not yet see loaded. The first module to succeed in
+ *     add_unformed_module() will add a module to our &modules list and
+ *     subsequent loads of modules with the same name will error out at the
+ *     end of early_mod_check(). The check for module_patient_check_exists()
+ *     at the end of early_mod_check() prevents duplicate allocations
+ *     on layout_and_allocate() for modules already being processed. These
+ *     duplicate failed modules are non-fatal, however they typically are
+ *     indicative of userspace not seeing a module in userspace loaded yet and
+ *     unnecessarily trying to load a module before the kernel even has a chance
+ *     to begin to process prior requests. Although duplicate failures can be
+ *     non-fatal, we should try to reduce vmalloc() pressure proactively, so
+ *     ideally after boot this will be close to as 0 as possible.  If module
+ *     decompression was used we also add to this counter the cost of the
+ *     initial kernel_read_file_from_fd() of the compressed module. If module
+ *     decompression was not used the value represents the total allocated and
+ *     freed bytes in kernel_read_file_from_fd() calls for these type of
+ *     failures. These failures can occur because:
+ *
+ *    * module_sig_check() - module signature checks
+ *    * elf_validity_cache_copy() - some ELF validation issue
+ *    * early_mod_check():
+ *
+ *      * blacklisting
+ *      * failed to rewrite section headers
+ *      * version magic
+ *      * live patch requirements didn't check out
+ *      * the module was detected as being already present
+ *
+ *   * invalid_mod_bytes: these are the total number of bytes allocated and
+ *     freed due to failures after we did all the sanity checks of the module
+ *     which userspace passed to us and after our first check that the module
+ *     is unique.  A module can still fail to load if we detect the module is
+ *     loaded after we allocate space for it with layout_and_allocate(), we do
+ *     this check right before processing the module as live and run its
+ *     initialization routines. Note that you have a failure of this type it
+ *     also means the respective kernel_read_file_from_fd() memory space was
+ *     also freed and not used, and so we increment this counter with twice
+ *     the size of the module. Additionally if you used module decompression
+ *     the size of the compressed module is also added to this counter.
+ *
+ *  * modcount: how many modules we've loaded in our kernel life time
+ *  * failed_kreads: how many modules failed due to failed kernel_read_file_from_fd()
+ *  * failed_decompress: how many failed module decompression attempts we've had.
+ *    These really should not happen unless your compression / decompression
+ *    might be broken.
+ *  * failed_becoming: how many modules failed after we kernel_read_file_from_fd()
+ *    it and before we allocate memory for it with layout_and_allocate(). This
+ *    counter is never incremented if you manage to validate the module and
+ *    call layout_and_allocate() for it.
+ *  * failed_load_modules: how many modules failed once we've allocated our
+ *    private space for our module using layout_and_allocate(). These failures
+ *    should hopefully mostly be dealt with already. Races in theory could
+ *    still exist here, but it would just mean the kernel had started processing
+ *    two threads concurrently up to early_mod_check() and one thread won.
+ *    These failures are good signs the kernel or userspace is doing something
+ *    seriously stupid or that could be improved. We should strive to fix these,
+ *    but it is perhaps not easy to fix them. A recent example are the modules
+ *    requests incurred for frequency modules, a separate module request was
+ *    being issued for each CPU on a system.
+ */
+
+atomic_long_t total_mod_size;
+atomic_long_t total_text_size;
+atomic_long_t invalid_kread_bytes;
+atomic_long_t invalid_decompress_bytes;
+static atomic_long_t invalid_becoming_bytes;
+static atomic_long_t invalid_mod_bytes;
+atomic_t modcount;
+atomic_t failed_kreads;
+atomic_t failed_decompress;
+static atomic_t failed_becoming;
+static atomic_t failed_load_modules;
+
+static const char *mod_fail_to_str(struct mod_fail_load *mod_fail)
+{
+	if (test_bit(FAIL_DUP_MOD_BECOMING, &mod_fail->dup_fail_mask) &&
+	    test_bit(FAIL_DUP_MOD_LOAD, &mod_fail->dup_fail_mask))
+		return "Becoming & Load";
+	if (test_bit(FAIL_DUP_MOD_BECOMING, &mod_fail->dup_fail_mask))
+		return "Becoming";
+	if (test_bit(FAIL_DUP_MOD_LOAD, &mod_fail->dup_fail_mask))
+		return "Load";
+	return "Bug-on-stats";
+}
+
+void mod_stat_bump_invalid(struct load_info *info, int flags)
+{
+	atomic_long_add(info->len * 2, &invalid_mod_bytes);
+	atomic_inc(&failed_load_modules);
+#if defined(CONFIG_MODULE_DECOMPRESS)
+	if (flags & MODULE_INIT_COMPRESSED_FILE)
+		atomic_long_add(info->compressed_len, &invalid_mod_bytes);
+#endif
+}
+
+void mod_stat_bump_becoming(struct load_info *info, int flags)
+{
+	atomic_inc(&failed_becoming);
+	atomic_long_add(info->len, &invalid_becoming_bytes);
+#if defined(CONFIG_MODULE_DECOMPRESS)
+	if (flags & MODULE_INIT_COMPRESSED_FILE)
+		atomic_long_add(info->compressed_len, &invalid_becoming_bytes);
+#endif
+}
+
+int try_add_failed_module(const char *name, enum fail_dup_mod_reason reason)
+{
+	struct mod_fail_load *mod_fail;
+
+	list_for_each_entry_rcu(mod_fail, &dup_failed_modules, list,
+				lockdep_is_held(&module_mutex)) {
+		if (!strcmp(mod_fail->name, name)) {
+			atomic_long_inc(&mod_fail->count);
+			__set_bit(reason, &mod_fail->dup_fail_mask);
+			goto out;
+		}
+	}
+
+	mod_fail = kzalloc_obj(*mod_fail);
+	if (!mod_fail)
+		return -ENOMEM;
+	memcpy(mod_fail->name, name, strlen(name));
+	__set_bit(reason, &mod_fail->dup_fail_mask);
+	atomic_long_inc(&mod_fail->count);
+	list_add_rcu(&mod_fail->list, &dup_failed_modules);
+out:
+	return 0;
+}
+
+/*
+ * At 64 bytes per module and assuming a 1024 bytes preamble we can fit the
+ * 112 module prints within 8k.
+ *
+ * 1024 + (64*112) = 8k
+ */
+#define MAX_PREAMBLE 1024
+#define MAX_FAILED_MOD_PRINT 112
+#define MAX_BYTES_PER_MOD 64
+static ssize_t read_file_mod_stats(struct file *file, char __user *user_buf,
+				   size_t count, loff_t *ppos)
+{
+	struct mod_fail_load *mod_fail;
+	unsigned int len, size, count_failed = 0;
+	char *buf;
+	int ret;
+	u32 live_mod_count, fkreads, fdecompress, fbecoming, floads;
+	unsigned long total_size, text_size, ikread_bytes, ibecoming_bytes,
+		idecompress_bytes, imod_bytes, total_virtual_lost;
+
+	live_mod_count = atomic_read(&modcount);
+	fkreads = atomic_read(&failed_kreads);
+	fdecompress = atomic_read(&failed_decompress);
+	fbecoming = atomic_read(&failed_becoming);
+	floads = atomic_read(&failed_load_modules);
+
+	total_size = atomic_long_read(&total_mod_size);
+	text_size = atomic_long_read(&total_text_size);
+	ikread_bytes = atomic_long_read(&invalid_kread_bytes);
+	idecompress_bytes = atomic_long_read(&invalid_decompress_bytes);
+	ibecoming_bytes = atomic_long_read(&invalid_becoming_bytes);
+	imod_bytes = atomic_long_read(&invalid_mod_bytes);
+
+	total_virtual_lost = ikread_bytes + idecompress_bytes + ibecoming_bytes + imod_bytes;
+
+	size = MAX_PREAMBLE + min((unsigned int)(floads + fbecoming),
+				  (unsigned int)MAX_FAILED_MOD_PRINT) * MAX_BYTES_PER_MOD;
+	buf = kzalloc(size, GFP_KERNEL);
+	if (buf == NULL)
+		return -ENOMEM;
+
+	/* The beginning of our debug preamble */
+	len = scnprintf(buf, size, "%25s\t%u\n", "Mods ever loaded", live_mod_count);
+
+	len += scnprintf(buf + len, size - len, "%25s\t%u\n", "Mods failed on kread", fkreads);
+
+	len += scnprintf(buf + len, size - len, "%25s\t%u\n", "Mods failed on decompress",
+			 fdecompress);
+	len += scnprintf(buf + len, size - len, "%25s\t%u\n", "Mods failed on becoming", fbecoming);
+
+	len += scnprintf(buf + len, size - len, "%25s\t%u\n", "Mods failed on load", floads);
+
+	len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Total module size", total_size);
+	len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Total mod text size", text_size);
+
+	len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Failed kread bytes", ikread_bytes);
+
+	len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Failed decompress bytes",
+			 idecompress_bytes);
+
+	len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Failed becoming bytes", ibecoming_bytes);
+
+	len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Failed kmod bytes", imod_bytes);
+
+	len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Virtual mem wasted bytes", total_virtual_lost);
+
+	if (live_mod_count && total_size) {
+		len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Average mod size",
+				 DIV_ROUND_UP(total_size, live_mod_count));
+	}
+
+	if (live_mod_count && text_size) {
+		len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Average mod text size",
+				 DIV_ROUND_UP(text_size, live_mod_count));
+	}
+
+	/*
+	 * We use WARN_ON_ONCE() for the counters to ensure we always have parity
+	 * for keeping tabs on a type of failure with one type of byte counter.
+	 * The counters for imod_bytes does not increase for fkreads failures
+	 * for example, and so on.
+	 */
+
+	WARN_ON_ONCE(ikread_bytes && !fkreads);
+	if (fkreads && ikread_bytes) {
+		len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Avg fail kread bytes",
+				 DIV_ROUND_UP(ikread_bytes, fkreads));
+	}
+
+	WARN_ON_ONCE(ibecoming_bytes && !fbecoming);
+	if (fbecoming && ibecoming_bytes) {
+		len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Avg fail becoming bytes",
+				 DIV_ROUND_UP(ibecoming_bytes, fbecoming));
+	}
+
+	WARN_ON_ONCE(idecompress_bytes && !fdecompress);
+	if (fdecompress && idecompress_bytes) {
+		len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Avg fail decomp bytes",
+				 DIV_ROUND_UP(idecompress_bytes, fdecompress));
+	}
+
+	WARN_ON_ONCE(imod_bytes && !floads);
+	if (floads && imod_bytes) {
+		len += scnprintf(buf + len, size - len, "%25s\t%lu\n", "Average fail load bytes",
+				 DIV_ROUND_UP(imod_bytes, floads));
+	}
+
+	/* End of our debug preamble header. */
+
+	/* Catch when we've gone beyond our expected preamble */
+	WARN_ON_ONCE(len >= MAX_PREAMBLE);
+
+	if (list_empty(&dup_failed_modules))
+		goto out;
+
+	len += scnprintf(buf + len, size - len, "Duplicate failed modules:\n");
+	len += scnprintf(buf + len, size - len, "%25s\t%15s\t%25s\n",
+			 "Module-name", "How-many-times", "Reason");
+	mutex_lock(&module_mutex);
+
+
+	list_for_each_entry_rcu(mod_fail, &dup_failed_modules, list) {
+		if (WARN_ON_ONCE(++count_failed >= MAX_FAILED_MOD_PRINT))
+			goto out_unlock;
+		len += scnprintf(buf + len, size - len, "%25s\t%15lu\t%25s\n", mod_fail->name,
+				 atomic_long_read(&mod_fail->count), mod_fail_to_str(mod_fail));
+	}
+out_unlock:
+	mutex_unlock(&module_mutex);
+out:
+	ret = simple_read_from_buffer(user_buf, count, ppos, buf, len);
+	kfree(buf);
+	return ret;
+}
+#undef MAX_PREAMBLE
+#undef MAX_FAILED_MOD_PRINT
+#undef MAX_BYTES_PER_MOD
+
+static const struct file_operations fops_mod_stats = {
+	.read = read_file_mod_stats,
+	.open = simple_open,
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
+};
+
+#define mod_debug_add_ulong(name) debugfs_create_ulong(#name, 0400, mod_debugfs_root, (unsigned long *) &name.counter)
+#define mod_debug_add_atomic(name) debugfs_create_atomic_t(#name, 0400, mod_debugfs_root, &name)
+static int __init module_stats_init(void)
+{
+	mod_debug_add_ulong(total_mod_size);
+	mod_debug_add_ulong(total_text_size);
+	mod_debug_add_ulong(invalid_kread_bytes);
+	mod_debug_add_ulong(invalid_decompress_bytes);
+	mod_debug_add_ulong(invalid_becoming_bytes);
+	mod_debug_add_ulong(invalid_mod_bytes);
+
+	mod_debug_add_atomic(modcount);
+	mod_debug_add_atomic(failed_kreads);
+	mod_debug_add_atomic(failed_decompress);
+	mod_debug_add_atomic(failed_becoming);
+	mod_debug_add_atomic(failed_load_modules);
+
+	debugfs_create_file("stats", 0400, mod_debugfs_root, mod_debugfs_root, &fops_mod_stats);
+
+	return 0;
+}
+#undef mod_debug_add_ulong
+#undef mod_debug_add_atomic
+module_init(module_stats_init);

linux-7.2.3/kernel/module/strict_rwx.c

@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Module strict rwx
+ *
+ * Copyright (C) 2015 Rusty Russell
+ */
+
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+#include <linux/set_memory.h>
+#include <linux/execmem.h>
+#include "internal.h"
+
+static int module_set_memory(const struct module *mod, enum mod_mem_type type,
+			     int (*set_memory)(unsigned long start, int num_pages))
+{
+	const struct module_memory *mod_mem = &mod->mem[type];
+
+	if (!mod_mem->base)
+		return 0;
+
+	set_vm_flush_reset_perms(mod_mem->base);
+	return set_memory((unsigned long)mod_mem->base, mod_mem->size >> PAGE_SHIFT);
+}
+
+/*
+ * Since some arches are moving towards PAGE_KERNEL module allocations instead
+ * of PAGE_KERNEL_EXEC, keep module_enable_x() independent of
+ * CONFIG_STRICT_MODULE_RWX because they are needed regardless of whether we
+ * are strict.
+ */
+int module_enable_text_rox(const struct module *mod)
+{
+	for_class_mod_mem_type(type, text) {
+		const struct module_memory *mem = &mod->mem[type];
+		int ret;
+
+		if (mem->is_rox)
+			ret = execmem_restore_rox(mem->base, mem->size);
+		else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
+			ret = module_set_memory(mod, type, set_memory_rox);
+		else
+			ret = module_set_memory(mod, type, set_memory_x);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+int module_enable_rodata_ro(const struct module *mod)
+{
+	int ret;
+
+	if (!IS_ENABLED(CONFIG_STRICT_MODULE_RWX) || !rodata_enabled)
+		return 0;
+
+	ret = module_set_memory(mod, MOD_RODATA, set_memory_ro);
+	if (ret)
+		return ret;
+	ret = module_set_memory(mod, MOD_INIT_RODATA, set_memory_ro);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+int module_enable_rodata_ro_after_init(const struct module *mod)
+{
+	if (!IS_ENABLED(CONFIG_STRICT_MODULE_RWX) || !rodata_enabled)
+		return 0;
+
+	return module_set_memory(mod, MOD_RO_AFTER_INIT, set_memory_ro);
+}
+
+int module_enable_data_nx(const struct module *mod)
+{
+	if (!IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
+		return 0;
+
+	for_class_mod_mem_type(type, data) {
+		int ret = module_set_memory(mod, type, set_memory_nx);
+
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+int module_enforce_rwx_sections(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs,
+				const char *secstrings,
+				const struct module *mod)
+{
+	const unsigned long shf_wx = SHF_WRITE | SHF_EXECINSTR;
+	int i;
+
+	if (!IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
+		return 0;
+
+	for (i = 0; i < hdr->e_shnum; i++) {
+		if ((sechdrs[i].sh_flags & shf_wx) == shf_wx) {
+			pr_err("%s: section %s (index %d) has invalid WRITE|EXEC flags\n",
+			       mod->name, secstrings + sechdrs[i].sh_name, i);
+			return -ENOEXEC;
+		}
+	}
+
+	return 0;
+}
+
+static const char *const ro_after_init[] = {
+	/*
+	 * Section .data..ro_after_init holds data explicitly annotated by
+	 * __ro_after_init.
+	 */
+	".data..ro_after_init",
+
+	/*
+	 * Section __jump_table holds data structures that are never modified,
+	 * with the exception of entries that refer to code in the __init
+	 * section, which are marked as such at module load time.
+	 */
+	"__jump_table",
+
+#ifdef CONFIG_HAVE_STATIC_CALL_INLINE
+	/*
+	 * Section .static_call_sites holds data structures that need to be
+	 * sorted and processed at module load time but are never modified
+	 * afterwards.
+	 */
+	".static_call_sites",
+#endif
+};
+
+void module_mark_ro_after_init(const Elf_Ehdr *hdr, Elf_Shdr *sechdrs,
+			       const char *secstrings)
+{
+	int i, j;
+
+	for (i = 1; i < hdr->e_shnum; i++) {
+		Elf_Shdr *shdr = &sechdrs[i];
+
+		for (j = 0; j < ARRAY_SIZE(ro_after_init); j++) {
+			if (strcmp(secstrings + shdr->sh_name,
+				   ro_after_init[j]) == 0) {
+				shdr->sh_flags |= SHF_RO_AFTER_INIT;
+				break;
+			}
+		}
+	}
+}

linux-7.2.3/kernel/module/sysfs.c

@@ -0,0 +1,439 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Module sysfs support
+ *
+ * Copyright (C) 2008 Rusty Russell
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/fs.h>
+#include <linux/sysfs.h>
+#include <linux/slab.h>
+#include <linux/kallsyms.h>
+#include <linux/mutex.h>
+#include "internal.h"
+
+/*
+ * /sys/module/foo/sections stuff
+ * J. Corbet <corbet@lwn.net>
+ */
+#ifdef CONFIG_KALLSYMS
+struct module_sect_attrs {
+	struct attribute_group grp;
+	struct bin_attribute attrs[];
+};
+
+#define MODULE_SECT_READ_SIZE (3 /* "0x", "\n" */ + (BITS_PER_LONG / 4))
+static ssize_t module_sect_read(struct file *file, struct kobject *kobj,
+				const struct bin_attribute *battr,
+				char *buf, loff_t pos, size_t count)
+{
+	char bounce[MODULE_SECT_READ_SIZE + 1];
+	size_t wrote;
+
+	if (pos != 0)
+		return -EINVAL;
+
+	/*
+	 * Since we're a binary read handler, we must account for the
+	 * trailing NUL byte that sprintf will write: if "buf" is
+	 * too small to hold the NUL, or the NUL is exactly the last
+	 * byte, the read will look like it got truncated by one byte.
+	 * Since there is no way to ask sprintf nicely to not write
+	 * the NUL, we have to use a bounce buffer.
+	 */
+	wrote = scnprintf(bounce, sizeof(bounce), "0x%px\n",
+			  kallsyms_show_value(file->f_cred)
+				? battr->private : NULL);
+	count = min(count, wrote);
+	memcpy(buf, bounce, count);
+
+	return count;
+}
+
+static void free_sect_attrs(struct module_sect_attrs *sect_attrs)
+{
+	const struct bin_attribute *const *bin_attr;
+
+	for (bin_attr = sect_attrs->grp.bin_attrs; *bin_attr; bin_attr++)
+		kfree((*bin_attr)->attr.name);
+	kfree(sect_attrs->grp.bin_attrs);
+	kfree(sect_attrs);
+}
+
+static int add_sect_attrs(struct module *mod, const struct load_info *info)
+{
+	struct module_sect_attrs *sect_attrs;
+	const struct bin_attribute **gattr;
+	struct bin_attribute *sattr;
+	unsigned int nloaded = 0, i;
+	int ret;
+
+	/* Count loaded sections and allocate structures */
+	for (i = 0; i < info->hdr->e_shnum; i++)
+		if (!sect_empty(&info->sechdrs[i]))
+			nloaded++;
+	sect_attrs = kzalloc_flex(*sect_attrs, attrs, nloaded);
+	if (!sect_attrs)
+		return -ENOMEM;
+
+	gattr = kzalloc_objs(*gattr, nloaded + 1);
+	if (!gattr) {
+		kfree(sect_attrs);
+		return -ENOMEM;
+	}
+
+	/* Setup section attributes. */
+	sect_attrs->grp.name = "sections";
+	sect_attrs->grp.bin_attrs = gattr;
+
+	sattr = &sect_attrs->attrs[0];
+	for (i = 0; i < info->hdr->e_shnum; i++) {
+		Elf_Shdr *sec = &info->sechdrs[i];
+
+		if (sect_empty(sec))
+			continue;
+		sysfs_bin_attr_init(sattr);
+		sattr->attr.name =
+			kstrdup(info->secstrings + sec->sh_name, GFP_KERNEL);
+		if (!sattr->attr.name) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		sattr->read = module_sect_read;
+		sattr->private = (void *)sec->sh_addr;
+		sattr->size = MODULE_SECT_READ_SIZE;
+		sattr->attr.mode = 0400;
+		*(gattr++) = sattr++;
+	}
+
+	ret = sysfs_create_group(&mod->mkobj.kobj, &sect_attrs->grp);
+	if (ret)
+		goto out;
+
+	mod->sect_attrs = sect_attrs;
+	return 0;
+out:
+	free_sect_attrs(sect_attrs);
+	return ret;
+}
+
+static void remove_sect_attrs(struct module *mod)
+{
+	if (mod->sect_attrs) {
+		sysfs_remove_group(&mod->mkobj.kobj,
+				   &mod->sect_attrs->grp);
+		/*
+		 * We are positive that no one is using any sect attrs
+		 * at this point.  Deallocate immediately.
+		 */
+		free_sect_attrs(mod->sect_attrs);
+		mod->sect_attrs = NULL;
+	}
+}
+
+/*
+ * /sys/module/foo/notes/.section.name gives contents of SHT_NOTE sections.
+ */
+
+struct module_notes_attrs {
+	struct attribute_group grp;
+	struct bin_attribute attrs[];
+};
+
+static void free_notes_attrs(struct module_notes_attrs *notes_attrs)
+{
+	kfree(notes_attrs->grp.bin_attrs);
+	kfree(notes_attrs);
+}
+
+static int add_notes_attrs(struct module *mod, const struct load_info *info)
+{
+	unsigned int notes, loaded, i;
+	struct module_notes_attrs *notes_attrs;
+	const struct bin_attribute **gattr;
+	struct bin_attribute *nattr;
+	int ret;
+
+	/* Count notes sections and allocate structures.  */
+	notes = 0;
+	for (i = 0; i < info->hdr->e_shnum; i++)
+		if (!sect_empty(&info->sechdrs[i]) &&
+		    info->sechdrs[i].sh_type == SHT_NOTE)
+			++notes;
+
+	if (notes == 0)
+		return 0;
+
+	notes_attrs = kzalloc_flex(*notes_attrs, attrs, notes);
+	if (!notes_attrs)
+		return -ENOMEM;
+
+	gattr = kzalloc_objs(*gattr, notes + 1);
+	if (!gattr) {
+		kfree(notes_attrs);
+		return -ENOMEM;
+	}
+
+	notes_attrs->grp.name = "notes";
+	notes_attrs->grp.bin_attrs = gattr;
+
+	nattr = &notes_attrs->attrs[0];
+	for (loaded = i = 0; i < info->hdr->e_shnum; ++i) {
+		if (sect_empty(&info->sechdrs[i]))
+			continue;
+		if (info->sechdrs[i].sh_type == SHT_NOTE) {
+			sysfs_bin_attr_init(nattr);
+			nattr->attr.name = mod->sect_attrs->attrs[loaded].attr.name;
+			nattr->attr.mode = 0444;
+			nattr->size = info->sechdrs[i].sh_size;
+			nattr->private = (void *)info->sechdrs[i].sh_addr;
+			nattr->read = sysfs_bin_attr_simple_read;
+			*(gattr++) = nattr++;
+		}
+		++loaded;
+	}
+
+	ret = sysfs_create_group(&mod->mkobj.kobj, &notes_attrs->grp);
+	if (ret)
+		goto out;
+
+	mod->notes_attrs = notes_attrs;
+	return 0;
+
+out:
+	free_notes_attrs(notes_attrs);
+	return ret;
+}
+
+static void remove_notes_attrs(struct module *mod)
+{
+	if (mod->notes_attrs) {
+		sysfs_remove_group(&mod->mkobj.kobj,
+				   &mod->notes_attrs->grp);
+		/*
+		 * We are positive that no one is using any notes attrs
+		 * at this point.  Deallocate immediately.
+		 */
+		free_notes_attrs(mod->notes_attrs);
+		mod->notes_attrs = NULL;
+	}
+}
+
+#else /* !CONFIG_KALLSYMS */
+static inline int add_sect_attrs(struct module *mod, const struct load_info *info)
+{
+	return 0;
+}
+static inline void remove_sect_attrs(struct module *mod) { }
+static inline int add_notes_attrs(struct module *mod, const struct load_info *info)
+{
+	return 0;
+}
+static inline void remove_notes_attrs(struct module *mod) { }
+#endif /* CONFIG_KALLSYMS */
+
+static void del_usage_links(struct module *mod)
+{
+#ifdef CONFIG_MODULE_UNLOAD
+	struct module_use *use;
+
+	mutex_lock(&module_mutex);
+	list_for_each_entry(use, &mod->target_list, target_list)
+		sysfs_remove_link(use->target->holders_dir, mod->name);
+	mutex_unlock(&module_mutex);
+#endif
+}
+
+static int add_usage_links(struct module *mod)
+{
+	int ret = 0;
+#ifdef CONFIG_MODULE_UNLOAD
+	struct module_use *use;
+
+	mutex_lock(&module_mutex);
+	list_for_each_entry(use, &mod->target_list, target_list) {
+		ret = sysfs_create_link(use->target->holders_dir,
+					&mod->mkobj.kobj, mod->name);
+		if (ret)
+			break;
+	}
+	mutex_unlock(&module_mutex);
+	if (ret)
+		del_usage_links(mod);
+#endif
+	return ret;
+}
+
+static void module_remove_modinfo_attrs(struct module *mod, int end)
+{
+	const struct module_attribute *attr;
+	int i;
+
+	for (i = 0; (attr = &mod->modinfo_attrs[i]); i++) {
+		if (end >= 0 && i > end)
+			break;
+		/* pick a field to test for end of list */
+		if (!attr->attr.name)
+			break;
+		sysfs_remove_file(&mod->mkobj.kobj, &attr->attr);
+		if (attr->free)
+			attr->free(mod);
+	}
+	kfree(mod->modinfo_attrs);
+}
+
+static int module_add_modinfo_attrs(struct module *mod)
+{
+	const struct module_attribute *attr;
+	struct module_attribute *temp_attr;
+	int error = 0;
+	int i;
+
+	mod->modinfo_attrs = kzalloc((sizeof(struct module_attribute) *
+					(modinfo_attrs_count + 1)),
+					GFP_KERNEL);
+	if (!mod->modinfo_attrs)
+		return -ENOMEM;
+
+	temp_attr = mod->modinfo_attrs;
+	for (i = 0; (attr = modinfo_attrs[i]); i++) {
+		if (!attr->test || attr->test(mod)) {
+			memcpy(temp_attr, attr, sizeof(*temp_attr));
+			sysfs_attr_init(&temp_attr->attr);
+			error = sysfs_create_file(&mod->mkobj.kobj,
+						  &temp_attr->attr);
+			if (error)
+				goto error_out;
+			++temp_attr;
+		}
+	}
+
+	return 0;
+
+error_out:
+	if (i > 0)
+		module_remove_modinfo_attrs(mod, --i);
+	else
+		kfree(mod->modinfo_attrs);
+	return error;
+}
+
+static void mod_kobject_put(struct module *mod)
+{
+	DECLARE_COMPLETION_ONSTACK(c);
+
+	mod->mkobj.kobj_completion = &c;
+	kobject_put(&mod->mkobj.kobj);
+	wait_for_completion(&c);
+}
+
+static int mod_sysfs_init(struct module *mod)
+{
+	int err;
+	struct kobject *kobj;
+
+	if (!module_kset) {
+		pr_err("%s: module sysfs not initialized\n", mod->name);
+		err = -EINVAL;
+		goto out;
+	}
+
+	kobj = kset_find_obj(module_kset, mod->name);
+	if (kobj) {
+		pr_err("%s: module is already loaded\n", mod->name);
+		kobject_put(kobj);
+		err = -EINVAL;
+		goto out;
+	}
+
+	mod->mkobj.mod = mod;
+
+	memset(&mod->mkobj.kobj, 0, sizeof(mod->mkobj.kobj));
+	mod->mkobj.kobj.kset = module_kset;
+	err = kobject_init_and_add(&mod->mkobj.kobj, &module_ktype, NULL,
+				   "%s", mod->name);
+	if (err)
+		mod_kobject_put(mod);
+
+out:
+	return err;
+}
+
+int mod_sysfs_setup(struct module *mod,
+		    const struct load_info *info,
+			   struct kernel_param *kparam,
+			   unsigned int num_params)
+{
+	int err;
+
+	err = mod_sysfs_init(mod);
+	if (err)
+		goto out;
+
+	mod->holders_dir = kobject_create_and_add("holders", &mod->mkobj.kobj);
+	if (!mod->holders_dir) {
+		err = -ENOMEM;
+		goto out_unreg;
+	}
+
+	err = module_param_sysfs_setup(mod, kparam, num_params);
+	if (err)
+		goto out_unreg_holders;
+
+	err = module_add_modinfo_attrs(mod);
+	if (err)
+		goto out_unreg_param;
+
+	err = add_usage_links(mod);
+	if (err)
+		goto out_unreg_modinfo_attrs;
+
+	err = add_sect_attrs(mod, info);
+	if (err)
+		goto out_del_usage_links;
+
+	err = add_notes_attrs(mod, info);
+	if (err)
+		goto out_unreg_sect_attrs;
+
+	return 0;
+
+out_unreg_sect_attrs:
+	remove_sect_attrs(mod);
+out_del_usage_links:
+	del_usage_links(mod);
+out_unreg_modinfo_attrs:
+	module_remove_modinfo_attrs(mod, -1);
+out_unreg_param:
+	module_param_sysfs_remove(mod);
+out_unreg_holders:
+	kobject_put(mod->holders_dir);
+out_unreg:
+	mod_kobject_put(mod);
+out:
+	return err;
+}
+
+static void mod_sysfs_fini(struct module *mod)
+{
+	remove_notes_attrs(mod);
+	remove_sect_attrs(mod);
+	mod_kobject_put(mod);
+}
+
+void mod_sysfs_teardown(struct module *mod)
+{
+	del_usage_links(mod);
+	module_remove_modinfo_attrs(mod, -1);
+	module_param_sysfs_remove(mod);
+	kobject_put(mod->mkobj.drivers_dir);
+	kobject_put(mod->holders_dir);
+	mod_sysfs_fini(mod);
+}
+
+void init_param_lock(struct module *mod)
+{
+	mutex_init(&mod->param_lock);
+}

linux-7.2.3/kernel/module/tracking.c

@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Module taint unload tracking support
+ *
+ * Copyright (C) 2022 Aaron Tomlin
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/printk.h>
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/debugfs.h>
+#include <linux/rculist.h>
+#include "internal.h"
+
+static LIST_HEAD(unloaded_tainted_modules);
+extern struct dentry *mod_debugfs_root;
+
+int try_add_tainted_module(struct module *mod)
+{
+	struct mod_unload_taint *mod_taint;
+
+	if (!mod->taints)
+		goto out;
+
+	list_for_each_entry_rcu(mod_taint, &unloaded_tainted_modules, list,
+				lockdep_is_held(&module_mutex)) {
+		if (!strcmp(mod_taint->name, mod->name) &&
+		    mod_taint->taints & mod->taints) {
+			mod_taint->count++;
+			goto out;
+		}
+	}
+
+	mod_taint = kmalloc_obj(*mod_taint);
+	if (unlikely(!mod_taint))
+		return -ENOMEM;
+	strscpy(mod_taint->name, mod->name, MODULE_NAME_LEN);
+	mod_taint->taints = mod->taints;
+	list_add_rcu(&mod_taint->list, &unloaded_tainted_modules);
+	mod_taint->count = 1;
+out:
+	return 0;
+}
+
+void print_unloaded_tainted_modules(void)
+{
+	struct mod_unload_taint *mod_taint;
+	char buf[MODULE_FLAGS_BUF_SIZE];
+
+	if (!list_empty(&unloaded_tainted_modules)) {
+		printk(KERN_DEFAULT "Unloaded tainted modules:");
+		list_for_each_entry_rcu(mod_taint, &unloaded_tainted_modules,
+					list) {
+			size_t l;
+
+			l = module_flags_taint(mod_taint->taints, buf);
+			buf[l++] = '\0';
+			pr_cont(" %s(%s):%llu", mod_taint->name, buf,
+				mod_taint->count);
+		}
+	}
+}
+
+#ifdef CONFIG_DEBUG_FS
+static void *unloaded_tainted_modules_seq_start(struct seq_file *m, loff_t *pos)
+	__acquires(rcu)
+{
+	rcu_read_lock();
+	return seq_list_start_rcu(&unloaded_tainted_modules, *pos);
+}
+
+static void *unloaded_tainted_modules_seq_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	return seq_list_next_rcu(p, &unloaded_tainted_modules, pos);
+}
+
+static void unloaded_tainted_modules_seq_stop(struct seq_file *m, void *p)
+	__releases(rcu)
+{
+	rcu_read_unlock();
+}
+
+static int unloaded_tainted_modules_seq_show(struct seq_file *m, void *p)
+{
+	struct mod_unload_taint *mod_taint;
+	char buf[MODULE_FLAGS_BUF_SIZE];
+	size_t l;
+
+	mod_taint = list_entry(p, struct mod_unload_taint, list);
+	l = module_flags_taint(mod_taint->taints, buf);
+	buf[l++] = '\0';
+
+	seq_printf(m, "%s (%s) %llu", mod_taint->name, buf, mod_taint->count);
+	seq_puts(m, "\n");
+
+	return 0;
+}
+
+static const struct seq_operations unloaded_tainted_modules_seq_ops = {
+	.start = unloaded_tainted_modules_seq_start,
+	.next  = unloaded_tainted_modules_seq_next,
+	.stop  = unloaded_tainted_modules_seq_stop,
+	.show  = unloaded_tainted_modules_seq_show,
+};
+
+static int unloaded_tainted_modules_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &unloaded_tainted_modules_seq_ops);
+}
+
+static const struct file_operations unloaded_tainted_modules_fops = {
+	.open = unloaded_tainted_modules_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = seq_release,
+};
+
+static int __init unloaded_tainted_modules_init(void)
+{
+	debugfs_create_file("unloaded_tainted", 0444, mod_debugfs_root, NULL,
+			    &unloaded_tainted_modules_fops);
+	return 0;
+}
+module_init(unloaded_tainted_modules_init);
+#endif /* CONFIG_DEBUG_FS */

linux-7.2.3/kernel/module/tree_lookup.c

@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Modules tree lookup
+ *
+ * Copyright (C) 2015 Peter Zijlstra
+ * Copyright (C) 2015 Rusty Russell
+ */
+
+#include <linux/module.h>
+#include <linux/rbtree_latch.h>
+#include "internal.h"
+
+/*
+ * Use a latched RB-tree for __module_address(); this allows us to use
+ * RCU lookups of the address from any context.
+ *
+ * This is conditional on PERF_EVENTS || TRACING || CFI because those can
+ * really hit __module_address() hard by doing a lot of stack unwinding;
+ * potentially from NMI context.
+ */
+
+static __always_inline unsigned long __mod_tree_val(struct latch_tree_node *n)
+{
+	struct module_memory *mod_mem = container_of(n, struct module_memory, mtn.node);
+
+	return (unsigned long)mod_mem->base;
+}
+
+static __always_inline unsigned long __mod_tree_size(struct latch_tree_node *n)
+{
+	struct module_memory *mod_mem = container_of(n, struct module_memory, mtn.node);
+
+	return (unsigned long)mod_mem->size;
+}
+
+static __always_inline bool
+mod_tree_less(struct latch_tree_node *a, struct latch_tree_node *b)
+{
+	return __mod_tree_val(a) < __mod_tree_val(b);
+}
+
+static __always_inline int
+mod_tree_comp(void *key, struct latch_tree_node *n)
+{
+	unsigned long val = (unsigned long)key;
+	unsigned long start, end;
+
+	start = __mod_tree_val(n);
+	if (val < start)
+		return -1;
+
+	end = start + __mod_tree_size(n);
+	if (val >= end)
+		return 1;
+
+	return 0;
+}
+
+static const struct latch_tree_ops mod_tree_ops = {
+	.less = mod_tree_less,
+	.comp = mod_tree_comp,
+};
+
+static noinline void __mod_tree_insert(struct mod_tree_node *node, struct mod_tree_root *tree)
+{
+	latch_tree_insert(&node->node, &tree->root, &mod_tree_ops);
+}
+
+static void __mod_tree_remove(struct mod_tree_node *node, struct mod_tree_root *tree)
+{
+	latch_tree_erase(&node->node, &tree->root, &mod_tree_ops);
+}
+
+/*
+ * These modifications: insert, remove_init and remove; are serialized by the
+ * module_mutex.
+ */
+void mod_tree_insert(struct module *mod)
+{
+	for_each_mod_mem_type(type) {
+		mod->mem[type].mtn.mod = mod;
+		if (mod->mem[type].size)
+			__mod_tree_insert(&mod->mem[type].mtn, &mod_tree);
+	}
+}
+
+void mod_tree_remove_init(struct module *mod)
+{
+	for_class_mod_mem_type(type, init) {
+		if (mod->mem[type].size)
+			__mod_tree_remove(&mod->mem[type].mtn, &mod_tree);
+	}
+}
+
+void mod_tree_remove(struct module *mod)
+{
+	for_each_mod_mem_type(type) {
+		if (mod->mem[type].size)
+			__mod_tree_remove(&mod->mem[type].mtn, &mod_tree);
+	}
+}
+
+struct module *mod_find(unsigned long addr, struct mod_tree_root *tree)
+{
+	struct latch_tree_node *ltn;
+
+	ltn = latch_tree_find((void *)addr, &tree->root, &mod_tree_ops);
+	if (!ltn)
+		return NULL;
+
+	return container_of(ltn, struct mod_tree_node, node)->mod;
+}

linux-7.2.3/kernel/module/version.c

@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Module version support
+ *
+ * Copyright (C) 2008 Rusty Russell
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/printk.h>
+#include "internal.h"
+
+int check_version(const struct load_info *info,
+		  const char *symname,
+			 struct module *mod,
+			 const u32 *crc)
+{
+	Elf_Shdr *sechdrs = info->sechdrs;
+	unsigned int versindex = info->index.vers;
+	unsigned int i, num_versions;
+	struct modversion_info *versions;
+	struct modversion_info_ext version_ext;
+
+	/* Exporting module didn't supply crcs?  OK, we're already tainted. */
+	if (!crc)
+		return 1;
+
+	/* If we have extended version info, rely on it */
+	if (info->index.vers_ext_crc) {
+		for_each_modversion_info_ext(version_ext, info) {
+			if (strcmp(version_ext.name, symname) != 0)
+				continue;
+			if (*version_ext.crc == *crc)
+				return 1;
+			pr_debug("Found checksum %X vs module %X\n",
+				 *crc, *version_ext.crc);
+			goto bad_version;
+		}
+		pr_warn_once("%s: no extended symbol version for %s\n",
+			     info->name, symname);
+		return 1;
+	}
+
+	/* No versions at all?  modprobe --force does this. */
+	if (versindex == 0)
+		return try_to_force_load(mod, symname) == 0;
+
+	versions = (void *)sechdrs[versindex].sh_addr;
+	num_versions = sechdrs[versindex].sh_size
+		/ sizeof(struct modversion_info);
+
+	for (i = 0; i < num_versions; i++) {
+		u32 crcval;
+
+		if (strcmp(versions[i].name, symname) != 0)
+			continue;
+
+		crcval = *crc;
+		if (versions[i].crc == crcval)
+			return 1;
+		pr_debug("Found checksum %X vs module %lX\n",
+			 crcval, versions[i].crc);
+		goto bad_version;
+	}
+
+	/* Broken toolchain. Warn once, then let it go.. */
+	pr_warn_once("%s: no symbol version for %s\n", info->name, symname);
+	return 1;
+
+bad_version:
+	pr_warn("%s: disagrees about version of symbol %s\n", info->name, symname);
+	return 0;
+}
+
+int check_modstruct_version(const struct load_info *info,
+			    struct module *mod)
+{
+	struct find_symbol_arg fsa = {
+		.name	= "module_layout",
+		.gplok	= true,
+	};
+	bool have_symbol;
+
+	/*
+	 * Since this should be found in kernel (which can't be removed), no
+	 * locking is necessary. Regardless use a RCU read section to keep
+	 * lockdep happy.
+	 */
+	scoped_guard(rcu)
+		have_symbol = find_symbol(&fsa);
+	BUG_ON(!have_symbol);
+
+	return check_version(info, "module_layout", mod, fsa.crc);
+}
+
+/* First part is kernel version, which we ignore if module has crcs. */
+int same_magic(const char *amagic, const char *bmagic,
+	       bool has_crcs)
+{
+	if (has_crcs) {
+		amagic += strcspn(amagic, " ");
+		bmagic += strcspn(bmagic, " ");
+	}
+	return strcmp(amagic, bmagic) == 0;
+}
+
+void modversion_ext_start(const struct load_info *info,
+			  struct modversion_info_ext *start)
+{
+	unsigned int crc_idx = info->index.vers_ext_crc;
+	unsigned int name_idx = info->index.vers_ext_name;
+	Elf_Shdr *sechdrs = info->sechdrs;
+
+	/*
+	 * Both of these fields are needed for this to be useful
+	 * Any future fields should be initialized to NULL if absent.
+	 */
+	if (crc_idx == 0 || name_idx == 0) {
+		start->remaining = 0;
+		return;
+	}
+
+	start->crc = (const u32 *)sechdrs[crc_idx].sh_addr;
+	start->name = (const char *)sechdrs[name_idx].sh_addr;
+	start->remaining = sechdrs[crc_idx].sh_size / sizeof(*start->crc);
+}
+
+void modversion_ext_advance(struct modversion_info_ext *vers)
+{
+	vers->remaining--;
+	vers->crc++;
+	vers->name += strlen(vers->name) + 1;
+}
+
+/*
+ * Generate the signature for all relevant module structures here.
+ * If these change, we don't want to try to parse the module.
+ */
+void module_layout(struct module *mod,
+		   struct modversion_info *ver,
+		   struct kernel_param *kp,
+		   struct kernel_symbol *ks,
+		   struct tracepoint * const *tp)
+{
+}
+EXPORT_SYMBOL(module_layout);