Merge tag 'modules-5.19-rc1' of git://git.kernel.org/pub/scm/linux/ke…

…rnel/git/mcgrof/linux Pull modules updates from Luis Chamberlain: - It was time to tidy up kernel/module.c and one way of starting with that effort was to split it up into files. At my request Aaron Tomlin spearheaded that effort with the goal to not introduce any functional at all during that endeavour. The penalty for the split is +1322 bytes total, +112 bytes in data, +1210 bytes in text while bss is unchanged. One of the benefits of this other than helping make the code easier to read and review is summoning more help on review for changes with livepatching so kernel/module/livepatch.c is now pegged as maintained by the live patching folks. The before and after with just the move on a defconfig on x86-64: $ size kernel/module.o text data bss dec hex filename 38434 4540 104 43078 a846 kernel/module.o $ size -t kernel/module/*.o text data bss dec hex filename 4785 120 0 4905 1329 kernel/module/kallsyms.o 28577 4416 104 33097 8149 kernel/module/main.o 1158 8 0 1166 48e kernel/module/procfs.o 902 108 0 1010 3f2 kernel/module/strict_rwx.o 3390 0 0 3390 d3e kernel/module/sysfs.o 832 0 0 832 340 kernel/module/tree_lookup.o 39644 4652 104 44400 ad70 (TOTALS) - Aaron added module unload taint tracking (MODULE_UNLOAD_TAINT_TRACKING), to enable tracking unloaded modules which did taint the kernel. - Christophe Leroy added CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC which lets architectures to request having modules data in vmalloc area instead of module area. There are three reasons why an architecture might want this: a) On some architectures (like book3s/32) it is not possible to protect against execution on a page basis. The exec stuff can be mapped by different arch segment sizes (on book3s/32 that is 256M segments). By default the module area is in an Exec segment while vmalloc area is in a NoExec segment. Using vmalloc lets you muck with module data as NoExec on those architectures whereas before you could not. b) By pushing more module data to vmalloc you also increase the probability of module text to remain within a closer distance from kernel core text and this reduces trampolines, this has been reported on arm first and powerpc folks are following that lead. c) Free'ing module_alloc() (Exec by default) area leaves this exposed as Exec by default, some architectures have some security enhancements to set this as NoExec on free, and splitting module data with text let's future generic special allocators be added to the kernel without having developers try to grok the tribal knowledge per arch. Work like Rick Edgecombe's permission vmalloc interface [0] becomes easier to address over time. [0] https://lore.kernel.org/lkml/[email protected]/#r - Masahiro Yamada's symbol search enhancements * tag 'modules-5.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux: (33 commits) module: merge check_exported_symbol() into find_exported_symbol_in_section() module: do not binary-search in __ksymtab_gpl if fsa->gplok is false module: do not pass opaque pointer for symbol search module: show disallowed symbol name for inherit_taint() module: fix [e_shstrndx].sh_size=0 OOB access module: Introduce module unload taint tracking module: Move module_assert_mutex_or_preempt() to internal.h module: Make module_flags_taint() accept a module's taints bitmap and usable outside core code module.h: simplify MODULE_IMPORT_NS powerpc: Select ARCH_WANTS_MODULES_DATA_IN_VMALLOC on book3s/32 and 8xx module: Remove module_addr_min and module_addr_max module: Add CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC module: Introduce data_layout module: Prepare for handling several RB trees module: Always have struct mod_tree_root module: Rename debug_align() as strict_align() module: Rework layout alignment to avoid BUG_ON()s module: Move module_enable_x() and frob_text() in strict_rwx.c module: Make module_enable_x() independent of CONFIG_ARCH_HAS_STRICT_MODULE_RWX module: Move version support into a separate file ...
kawasaki · May 27, 2022 · ef98f9c · ef98f9c
2 parents 44d3572 + 7390b94
commit ef98f9c
Show file tree

Hide file tree

Showing 29 changed files with 2,384 additions and 2,052 deletions.
diff --git a/MAINTAINERS b/MAINTAINERS
@@ -10987,6 +10987,7 @@ F:	drivers/tty/serial/kgdboc.c
 F:	include/linux/kdb.h
 F:	include/linux/kgdb.h
 F:	kernel/debug/
+F:	kernel/module/kdb.c
 
 KHADAS MCU MFD DRIVER
 M:	Neil Armstrong <[email protected]>
@@ -11440,6 +11441,7 @@ F:	arch/s390/include/asm/livepatch.h
 F:	arch/x86/include/asm/livepatch.h
 F:	include/linux/livepatch.h
 F:	kernel/livepatch/
+F:	kernel/module/livepatch.c
 F:	lib/livepatch/
 F:	samples/livepatch/
 F:	tools/testing/selftests/livepatch/
@@ -13371,7 +13373,7 @@ L:	[email protected]
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux.git modules-next
 F:	include/linux/module.h
-F:	kernel/module.c
+F:	kernel/module/
 
 MONOLITHIC POWER SYSTEM PMIC DRIVER
 M:	Saravanan Sekar <[email protected]>

diff --git a/arch/Kconfig b/arch/Kconfig
@@ -892,6 +892,12 @@ config MODULES_USE_ELF_REL
 	  Modules only use ELF REL relocations.  Modules with ELF RELA
 	  relocations will give an error.
 
+config ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	bool
+	help
+	  For architectures like powerpc/32 which have constraints on module
+	  allocation and need to allocate module data outside of module area.
+
 config HAVE_IRQ_EXIT_ON_IRQ_STACK
 	bool
 	help

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
@@ -158,6 +158,7 @@ config PPC
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select ARCH_WANT_IRQS_OFF_ACTIVATE_MM
 	select ARCH_WANT_LD_ORPHAN_WARN
+	select ARCH_WANTS_MODULES_DATA_IN_VMALLOC	if PPC_BOOK3S_32 || PPC_8xx
 	select ARCH_WEAK_RELEASE_ACQUIRE
 	select BINFMT_ELF
 	select BUILDTIME_TABLE_SORT

diff --git a/include/linux/kdb.h b/include/linux/kdb.h
@@ -222,5 +222,6 @@ enum {
 
 extern int kdbgetintenv(const char *, int *);
 extern int kdb_set(int, const char **);
+int kdb_lsmod(int argc, const char **argv);
 
 #endif	/* !_KDB_H */
diff --git a/include/linux/module.h b/include/linux/module.h
@@ -290,8 +290,7 @@ extern typeof(name) __mod_##type##__##name##_device_table		\
  * files require multiple MODULE_FIRMWARE() specifiers */
 #define MODULE_FIRMWARE(_firmware) MODULE_INFO(firmware, _firmware)
 
-#define _MODULE_IMPORT_NS(ns)	MODULE_INFO(import_ns, #ns)
-#define MODULE_IMPORT_NS(ns)	_MODULE_IMPORT_NS(ns)
+#define MODULE_IMPORT_NS(ns)	MODULE_INFO(import_ns, __stringify(ns))
 
 struct notifier_block;
 
@@ -422,6 +421,9 @@ struct module {
 	/* Core layout: rbtree is accessed frequently, so keep together. */
 	struct module_layout core_layout __module_layout_align;
 	struct module_layout init_layout;
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	struct module_layout data_layout;
+#endif
 
 	/* Arch-specific module values */
 	struct mod_arch_specific arch;
@@ -569,6 +571,11 @@ bool is_module_text_address(unsigned long addr);
 static inline bool within_module_core(unsigned long addr,
 				      const struct module *mod)
 {
+#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC
+	if ((unsigned long)mod->data_layout.base <= addr &&
+	    addr < (unsigned long)mod->data_layout.base + mod->data_layout.size)
+		return true;
+#endif
 	return (unsigned long)mod->core_layout.base <= addr &&
 	       addr < (unsigned long)mod->core_layout.base + mod->core_layout.size;
 }
@@ -663,19 +670,15 @@ static inline bool module_requested_async_probing(struct module *module)
 	return module && module->async_probe_requested;
 }
 
-#ifdef CONFIG_LIVEPATCH
 static inline bool is_livepatch_module(struct module *mod)
 {
+#ifdef CONFIG_LIVEPATCH
 	return mod->klp;
-}
-#else /* !CONFIG_LIVEPATCH */
-static inline bool is_livepatch_module(struct module *mod)
-{
+#else
 	return false;
+#endif
 }
-#endif /* CONFIG_LIVEPATCH */
 
-bool is_module_sig_enforced(void);
 void set_module_sig_enforced(void);
 
 #else /* !CONFIG_MODULES... */
@@ -802,10 +805,6 @@ static inline bool module_requested_async_probing(struct module *module)
 	return false;
 }
 
-static inline bool is_module_sig_enforced(void)
-{
-	return false;
-}
 
 static inline void set_module_sig_enforced(void)
 {
@@ -857,11 +856,18 @@ static inline bool retpoline_module_ok(bool has_retpoline)
 #endif
 
 #ifdef CONFIG_MODULE_SIG
+bool is_module_sig_enforced(void);
+
 static inline bool module_sig_ok(struct module *module)
 {
 	return module->sig_ok;
 }
 #else	/* !CONFIG_MODULE_SIG */
+static inline bool is_module_sig_enforced(void)
+{
+	return false;
+}
+
 static inline bool module_sig_ok(struct module *module)
 {
 	return true;

diff --git a/init/Kconfig b/init/Kconfig
@@ -1983,6 +1983,17 @@ config MODULE_FORCE_UNLOAD
 	  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
+	default n
+	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"
 	help

diff --git a/kernel/Makefile b/kernel/Makefile
@@ -29,7 +29,6 @@ KCOV_INSTRUMENT_softirq.o := n
 KCSAN_SANITIZE_softirq.o = n
 # These are called from save_stack_trace() on slub debug path,
 # and produce insane amounts of uninteresting coverage.
-KCOV_INSTRUMENT_module.o := n
 KCOV_INSTRUMENT_extable.o := n
 KCOV_INSTRUMENT_stacktrace.o := n
 # Don't self-instrument.
@@ -53,6 +52,7 @@ obj-y += rcu/
 obj-y += livepatch/
 obj-y += dma/
 obj-y += entry/
+obj-$(CONFIG_MODULES) += module/
 
 obj-$(CONFIG_KCMP) += kcmp.o
 obj-$(CONFIG_FREEZER) += freezer.o
@@ -66,9 +66,6 @@ ifneq ($(CONFIG_SMP),y)
 obj-y += up.o
 endif
 obj-$(CONFIG_UID16) += uid16.o
-obj-$(CONFIG_MODULES) += module.o
-obj-$(CONFIG_MODULE_DECOMPRESS) += module_decompress.o
-obj-$(CONFIG_MODULE_SIG) += module_signing.o
 obj-$(CONFIG_MODULE_SIG_FORMAT) += module_signature.o
 obj-$(CONFIG_KALLSYMS) += kallsyms.o
 obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o

diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
@@ -9,7 +9,6 @@
  * Copyright (c) 2009 Wind River Systems, Inc.  All Rights Reserved.
  */
 
-#include <linux/module.h>
 #include <linux/types.h>
 #include <linux/ctype.h>
 #include <linux/kernel.h>

diff --git a/kernel/debug/kdb/kdb_keyboard.c b/kernel/debug/kdb/kdb_keyboard.c
@@ -11,7 +11,6 @@
 #include <linux/kdb.h>
 #include <linux/keyboard.h>
 #include <linux/ctype.h>
-#include <linux/module.h>
 #include <linux/io.h>
 
 /* Keyboard Controller Registers on normal PCs. */

diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c
@@ -26,7 +26,6 @@
 #include <linux/utsname.h>
 #include <linux/vmalloc.h>
 #include <linux/atomic.h>
-#include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/mm.h>
 #include <linux/init.h>
@@ -2060,54 +2059,6 @@ static int kdb_ef(int argc, const char **argv)
 	return 0;
 }
 
-#if defined(CONFIG_MODULES)
-/*
- * kdb_lsmod - This function implements the 'lsmod' command.  Lists
- *	currently loaded kernel modules.
- *	Mostly taken from userland lsmod.
- */
-static 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, kdb_modules, list) {
-		if (mod->state == MODULE_STATE_UNFORMED)
-			continue;
-
-		kdb_printf("%-20s%8u  0x%px ", mod->name,
-			   mod->core_layout.size, (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->core_layout.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;
-}
-
-#endif	/* CONFIG_MODULES */
-
 /*
  * kdb_env - This function implements the 'env' command.  Display the
  *	current environment variables.

diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h
@@ -226,10 +226,6 @@ extern void kdb_kbd_cleanup_state(void);
 #define kdb_kbd_cleanup_state()
 #endif /* ! CONFIG_KDB_KEYBOARD */
 
-#ifdef CONFIG_MODULES
-extern struct list_head *kdb_modules;
-#endif /* CONFIG_MODULES */
-
 extern char kdb_prompt_str[];
 
 #define	KDB_WORD_SIZE	((int)sizeof(unsigned long))

diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c
@@ -17,7 +17,6 @@
 #include <linux/stddef.h>
 #include <linux/vmalloc.h>
 #include <linux/ptrace.h>
-#include <linux/module.h>
 #include <linux/highmem.h>
 #include <linux/hardirq.h>
 #include <linux/delay.h>

diff --git a/kernel/module-internal.h b/kernel/module-internal.h
diff --git a/kernel/module/Makefile b/kernel/module/Makefile
@@ -0,0 +1,21 @@
+# 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_module.o := n
+
+obj-y += main.o strict_rwx.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
diff --git a/kernel/module/debug_kmemleak.c b/kernel/module/debug_kmemleak.c
@@ -0,0 +1,30 @@
+// 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)
+{
+	unsigned int i;
+
+	/* only scan the sections containing data */
+	kmemleak_scan_area(mod, sizeof(struct module), GFP_KERNEL);
+
+	for (i = 1; i < info->hdr->e_shnum; i++) {
+		/* Scan all writable sections that's not executable */
+		if (!(info->sechdrs[i].sh_flags & SHF_ALLOC) ||
+		    !(info->sechdrs[i].sh_flags & SHF_WRITE) ||
+		    (info->sechdrs[i].sh_flags & SHF_EXECINSTR))
+			continue;
+
+		kmemleak_scan_area((void *)info->sechdrs[i].sh_addr,
+				   info->sechdrs[i].sh_size, GFP_KERNEL);
+	}
+}