2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-22 12:14:01 +08:00
linux-next/include/linux/module.h

906 lines
24 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Dynamic loading of modules into the kernel.
*
* Rewritten by Richard Henderson <rth@tamu.edu> Dec 1996
* Rewritten again by Rusty Russell, 2002
*/
#ifndef _LINUX_MODULE_H
#define _LINUX_MODULE_H
#include <linux/list.h>
#include <linux/stat.h>
#include <linux/compiler.h>
#include <linux/cache.h>
#include <linux/kmod.h>
#include <linux/init.h>
#include <linux/elf.h>
#include <linux/stringify.h>
#include <linux/kobject.h>
#include <linux/moduleparam.h>
#include <linux/jump_label.h>
#include <linux/export.h>
#include <linux/rbtree_latch.h>
#include <linux/error-injection.h>
tracepoint: Fix tracepoint array element size mismatch commit 46e0c9be206f ("kernel: tracepoints: add support for relative references") changes the layout of the __tracepoint_ptrs section on architectures supporting relative references. However, it does so without turning struct tracepoint * const into const int elsewhere in the tracepoint code, which has the following side-effect: Setting mod->num_tracepoints is done in by module.c: mod->tracepoints_ptrs = section_objs(info, "__tracepoints_ptrs", sizeof(*mod->tracepoints_ptrs), &mod->num_tracepoints); Basically, since sizeof(*mod->tracepoints_ptrs) is a pointer size (rather than sizeof(int)), num_tracepoints is erroneously set to half the size it should be on 64-bit arch. So a module with an odd number of tracepoints misses the last tracepoint due to effect of integer division. So in the module going notifier: for_each_tracepoint_range(mod->tracepoints_ptrs, mod->tracepoints_ptrs + mod->num_tracepoints, tp_module_going_check_quiescent, NULL); the expression (mod->tracepoints_ptrs + mod->num_tracepoints) actually evaluates to something within the bounds of the array, but miss the last tracepoint if the number of tracepoints is odd on 64-bit arch. Fix this by introducing a new typedef: tracepoint_ptr_t, which is either "const int" on architectures that have PREL32 relocations, or "struct tracepoint * const" on architectures that does not have this feature. Also provide a new tracepoint_ptr_defer() static inline to encapsulate deferencing this type rather than duplicate code and ugly idefs within the for_each_tracepoint_range() implementation. This issue appears in 4.19-rc kernels, and should ideally be fixed before the end of the rc cycle. Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Acked-by: Jessica Yu <jeyu@kernel.org> Link: http://lkml.kernel.org/r/20181013191050.22389-1-mathieu.desnoyers@efficios.com Link: http://lkml.kernel.org/r/20180704083651.24360-7-ard.biesheuvel@linaro.org Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Ingo Molnar <mingo@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: James Morris <james.morris@microsoft.com> Cc: James Morris <jmorris@namei.org> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Nicolas Pitre <nico@linaro.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Russell King <linux@armlinux.org.uk> Cc: "Serge E. Hallyn" <serge@hallyn.com> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Thomas Garnier <thgarnie@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Deacon <will.deacon@arm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2018-10-14 03:10:50 +08:00
#include <linux/tracepoint-defs.h>
srcu: Allocate per-CPU data for DEFINE_SRCU() in modules Adding DEFINE_SRCU() or DEFINE_STATIC_SRCU() to a loadable module requires that the size of the reserved region be increased, which is not something we want to be doing all that often. One approach would be to require that loadable modules define an srcu_struct and invoke init_srcu_struct() from their module_init function and cleanup_srcu_struct() from their module_exit function. However, this is more than a bit user unfriendly. This commit therefore creates an ___srcu_struct_ptrs linker section, and pointers to srcu_struct structures created by DEFINE_SRCU() and DEFINE_STATIC_SRCU() within a module are placed into that module's ___srcu_struct_ptrs section. The required init_srcu_struct() and cleanup_srcu_struct() functions are then automatically invoked as needed when that module is loaded and unloaded, thus allowing modules to continue to use DEFINE_SRCU() and DEFINE_STATIC_SRCU() while avoiding the need to increase the size of the reserved region. Many of the algorithms and some of the code was cheerfully cherry-picked from other code making use of linker sections, perhaps most notably from tracepoints. All bugs are nevertheless the sole property of the author. Suggested-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> [ paulmck: Use __section() and use "default" in srcu_module_notify()'s "switch" statement as suggested by Joel Fernandes. ] Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com> Tested-by: Joel Fernandes (Google) <joel@joelfernandes.org>
2019-04-06 07:15:00 +08:00
#include <linux/srcu.h>
#include <linux/percpu.h>
#include <asm/module.h>
/* Not Yet Implemented */
#define MODULE_SUPPORTED_DEVICE(name)
#define MODULE_NAME_LEN MAX_PARAM_PREFIX_LEN
struct modversion_info {
unsigned long crc;
char name[MODULE_NAME_LEN];
};
struct module;
2016-07-27 10:36:34 +08:00
struct exception_table_entry;
struct module_kobject {
struct kobject kobj;
struct module *mod;
struct kobject *drivers_dir;
struct module_param_attrs *mp;
module: Fix mod->mkobj.kobj potentially freed too early DEBUG_KOBJECT_RELEASE helps to find the issue attached below. After some investigation, it seems the reason is: The mod->mkobj.kobj(ffffffffa01600d0 below) is freed together with mod itself in free_module(). However, its children still hold references to it, as the delay caused by DEBUG_KOBJECT_RELEASE. So when the child(holders below) tries to decrease the reference count to its parent in kobject_del(), BUG happens as it tries to access already freed memory. This patch tries to fix it by waiting for the mod->mkobj.kobj to be really released in the module removing process (and some error code paths). [ 1844.175287] kobject: 'holders' (ffff88007c1f1600): kobject_release, parent ffffffffa01600d0 (delayed) [ 1844.178991] kobject: 'notes' (ffff8800370b2a00): kobject_release, parent ffffffffa01600d0 (delayed) [ 1845.180118] kobject: 'holders' (ffff88007c1f1600): kobject_cleanup, parent ffffffffa01600d0 [ 1845.182130] kobject: 'holders' (ffff88007c1f1600): auto cleanup kobject_del [ 1845.184120] BUG: unable to handle kernel paging request at ffffffffa01601d0 [ 1845.185026] IP: [<ffffffff812cda81>] kobject_put+0x11/0x60 [ 1845.185026] PGD 1a13067 PUD 1a14063 PMD 7bd30067 PTE 0 [ 1845.185026] Oops: 0000 [#1] PREEMPT [ 1845.185026] Modules linked in: xfs libcrc32c [last unloaded: kprobe_example] [ 1845.185026] CPU: 0 PID: 18 Comm: kworker/0:1 Tainted: G O 3.11.0-rc6-next-20130819+ #1 [ 1845.185026] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2007 [ 1845.185026] Workqueue: events kobject_delayed_cleanup [ 1845.185026] task: ffff88007ca51f00 ti: ffff88007ca5c000 task.ti: ffff88007ca5c000 [ 1845.185026] RIP: 0010:[<ffffffff812cda81>] [<ffffffff812cda81>] kobject_put+0x11/0x60 [ 1845.185026] RSP: 0018:ffff88007ca5dd08 EFLAGS: 00010282 [ 1845.185026] RAX: 0000000000002000 RBX: ffffffffa01600d0 RCX: ffffffff8177d638 [ 1845.185026] RDX: ffff88007ca5dc18 RSI: 0000000000000000 RDI: ffffffffa01600d0 [ 1845.185026] RBP: ffff88007ca5dd18 R08: ffffffff824e9810 R09: ffffffffffffffff [ 1845.185026] R10: ffff8800ffffffff R11: dead4ead00000001 R12: ffffffff81a95040 [ 1845.185026] R13: ffff88007b27a960 R14: ffff88007c1f1600 R15: 0000000000000000 [ 1845.185026] FS: 0000000000000000(0000) GS:ffffffff81a23000(0000) knlGS:0000000000000000 [ 1845.185026] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 1845.185026] CR2: ffffffffa01601d0 CR3: 0000000037207000 CR4: 00000000000006b0 [ 1845.185026] Stack: [ 1845.185026] ffff88007c1f1600 ffff88007c1f1600 ffff88007ca5dd38 ffffffff812cdb7e [ 1845.185026] 0000000000000000 ffff88007c1f1640 ffff88007ca5dd68 ffffffff812cdbfe [ 1845.185026] ffff88007c974800 ffff88007c1f1640 ffff88007ff61a00 0000000000000000 [ 1845.185026] Call Trace: [ 1845.185026] [<ffffffff812cdb7e>] kobject_del+0x2e/0x40 [ 1845.185026] [<ffffffff812cdbfe>] kobject_delayed_cleanup+0x6e/0x1d0 [ 1845.185026] [<ffffffff81063a45>] process_one_work+0x1e5/0x670 [ 1845.185026] [<ffffffff810639e3>] ? process_one_work+0x183/0x670 [ 1845.185026] [<ffffffff810642b3>] worker_thread+0x113/0x370 [ 1845.185026] [<ffffffff810641a0>] ? rescuer_thread+0x290/0x290 [ 1845.185026] [<ffffffff8106bfba>] kthread+0xda/0xe0 [ 1845.185026] [<ffffffff814ff0f0>] ? _raw_spin_unlock_irq+0x30/0x60 [ 1845.185026] [<ffffffff8106bee0>] ? kthread_create_on_node+0x130/0x130 [ 1845.185026] [<ffffffff8150751a>] ret_from_fork+0x7a/0xb0 [ 1845.185026] [<ffffffff8106bee0>] ? kthread_create_on_node+0x130/0x130 [ 1845.185026] Code: 81 48 c7 c7 28 95 ad 81 31 c0 e8 9b da 01 00 e9 4f ff ff ff 66 0f 1f 44 00 00 55 48 89 e5 53 48 89 fb 48 83 ec 08 48 85 ff 74 1d <f6> 87 00 01 00 00 01 74 1e 48 8d 7b 38 83 6b 38 01 0f 94 c0 84 [ 1845.185026] RIP [<ffffffff812cda81>] kobject_put+0x11/0x60 [ 1845.185026] RSP <ffff88007ca5dd08> [ 1845.185026] CR2: ffffffffa01601d0 [ 1845.185026] ---[ end trace 49a70afd109f5653 ]--- Signed-off-by: Li Zhong <zhong@linux.vnet.ibm.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2013-09-03 15:03:57 +08:00
struct completion *kobj_completion;
} __randomize_layout;
struct module_attribute {
struct attribute attr;
ssize_t (*show)(struct module_attribute *, struct module_kobject *,
char *);
ssize_t (*store)(struct module_attribute *, struct module_kobject *,
const char *, size_t count);
[PATCH] modules: add version and srcversion to sysfs This patch adds version and srcversion files to /sys/module/${modulename} containing the version and srcversion fields of the module's modinfo section (if present). /sys/module/e1000 |-- srcversion `-- version This patch differs slightly from the version posted in January, as it now uses the new kstrdup() call in -mm. Why put this in sysfs? a) Tools like DKMS, which deal with changing out individual kernel modules without replacing the whole kernel, can behave smarter if they can tell the version of a given module. The autoinstaller feature, for example, which determines if your system has a "good" version of a driver (i.e. if the one provided by DKMS has a newer verson than that provided by the kernel package installed), and to automatically compile and install a newer version if DKMS has it but your kernel doesn't yet have that version. b) Because sysadmins manually, or with tools like DKMS, can switch out modules on the file system, you can't count on 'modinfo foo.ko', which looks at /lib/modules/${kernelver}/... actually matching what is loaded into the kernel already. Hence asking sysfs for this. c) as the unbind-driver-from-device work takes shape, it will be possible to rebind a driver that's built-in (no .ko to modinfo for the version) to a newly loaded module. sysfs will have the currently-built-in version info, for comparison. d) tech support scripts can then easily grab the version info for what's running presently - a question I get often. There has been renewed interest in this patch on linux-scsi by driver authors. As the idea originated from GregKH, I leave his Signed-off-by: intact, though the implementation is nearly completely new. Compiled and run on x86 and x86_64. From: Matthew Dobson <colpatch@us.ibm.com> build fix From: Thierry Vignaud <tvignaud@mandriva.com> build fix From: Matthew Dobson <colpatch@us.ibm.com> warning fix Signed-off-by: Greg Kroah-Hartman <greg@kroah.com> Signed-off-by: Matt Domsch <Matt_Domsch@dell.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-24 13:05:15 +08:00
void (*setup)(struct module *, const char *);
int (*test)(struct module *);
void (*free)(struct module *);
};
struct module_version_attribute {
struct module_attribute mattr;
const char *module_name;
const char *version;
} __attribute__ ((__aligned__(sizeof(void *))));
extern ssize_t __modver_version_show(struct module_attribute *,
struct module_kobject *, char *);
extern struct module_attribute module_uevent;
/* These are either module local, or the kernel's dummy ones. */
extern int init_module(void);
extern void cleanup_module(void);
#ifndef MODULE
/**
* module_init() - driver initialization entry point
* @x: function to be run at kernel boot time or module insertion
*
* module_init() will either be called during do_initcalls() (if
* builtin) or at module insertion time (if a module). There can only
* be one per module.
*/
#define module_init(x) __initcall(x);
/**
* module_exit() - driver exit entry point
* @x: function to be run when driver is removed
*
* module_exit() will wrap the driver clean-up code
* with cleanup_module() when used with rmmod when
* the driver is a module. If the driver is statically
* compiled into the kernel, module_exit() has no effect.
* There can only be one per module.
*/
#define module_exit(x) __exitcall(x);
#else /* MODULE */
/*
* In most cases loadable modules do not need custom
* initcall levels. There are still some valid cases where
* a driver may be needed early if built in, and does not
* matter when built as a loadable module. Like bus
* snooping debug drivers.
*/
#define early_initcall(fn) module_init(fn)
#define core_initcall(fn) module_init(fn)
#define core_initcall_sync(fn) module_init(fn)
#define postcore_initcall(fn) module_init(fn)
#define postcore_initcall_sync(fn) module_init(fn)
#define arch_initcall(fn) module_init(fn)
#define subsys_initcall(fn) module_init(fn)
#define subsys_initcall_sync(fn) module_init(fn)
#define fs_initcall(fn) module_init(fn)
#define fs_initcall_sync(fn) module_init(fn)
#define rootfs_initcall(fn) module_init(fn)
#define device_initcall(fn) module_init(fn)
#define device_initcall_sync(fn) module_init(fn)
#define late_initcall(fn) module_init(fn)
#define late_initcall_sync(fn) module_init(fn)
#define console_initcall(fn) module_init(fn)
/* Each module must use one module_init(). */
#define module_init(initfn) \
static inline initcall_t __maybe_unused __inittest(void) \
{ return initfn; } \
include/linux/module.h: copy __init/__exit attrs to init/cleanup_module The upcoming GCC 9 release extends the -Wmissing-attributes warnings (enabled by -Wall) to C and aliases: it warns when particular function attributes are missing in the aliases but not in their target. In particular, it triggers for all the init/cleanup_module aliases in the kernel (defined by the module_init/exit macros), ending up being very noisy. These aliases point to the __init/__exit functions of a module, which are defined as __cold (among other attributes). However, the aliases themselves do not have the __cold attribute. Since the compiler behaves differently when compiling a __cold function as well as when compiling paths leading to calls to __cold functions, the warning is trying to point out the possibly-forgotten attribute in the alias. In order to keep the warning enabled, we decided to silence this case. Ideally, we would mark the aliases directly as __init/__exit. However, there are currently around 132 modules in the kernel which are missing __init/__exit in their init/cleanup functions (either because they are missing, or for other reasons, e.g. the functions being called from somewhere else); and a section mismatch is a hard error. A conservative alternative was to mark the aliases as __cold only. However, since we would like to eventually enforce __init/__exit to be always marked, we chose to use the new __copy function attribute (introduced by GCC 9 as well to deal with this). With it, we copy the attributes used by the target functions into the aliases. This way, functions that were not marked as __init/__exit won't have their aliases marked either, and therefore there won't be a section mismatch. Note that the warning would go away marking either the extern declaration, the definition, or both. However, we only mark the definition of the alias, since we do not want callers (which only see the declaration) to be compiled as if the function was __cold (and therefore the paths leading to those calls would be assumed to be unlikely). Link: https://lore.kernel.org/lkml/20190123173707.GA16603@gmail.com/ Link: https://lore.kernel.org/lkml/20190206175627.GA20399@gmail.com/ Suggested-by: Martin Sebor <msebor@gcc.gnu.org> Acked-by: Jessica Yu <jeyu@kernel.org> Signed-off-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
2019-01-20 03:59:34 +08:00
int init_module(void) __copy(initfn) __attribute__((alias(#initfn)));
/* This is only required if you want to be unloadable. */
#define module_exit(exitfn) \
static inline exitcall_t __maybe_unused __exittest(void) \
{ return exitfn; } \
include/linux/module.h: copy __init/__exit attrs to init/cleanup_module The upcoming GCC 9 release extends the -Wmissing-attributes warnings (enabled by -Wall) to C and aliases: it warns when particular function attributes are missing in the aliases but not in their target. In particular, it triggers for all the init/cleanup_module aliases in the kernel (defined by the module_init/exit macros), ending up being very noisy. These aliases point to the __init/__exit functions of a module, which are defined as __cold (among other attributes). However, the aliases themselves do not have the __cold attribute. Since the compiler behaves differently when compiling a __cold function as well as when compiling paths leading to calls to __cold functions, the warning is trying to point out the possibly-forgotten attribute in the alias. In order to keep the warning enabled, we decided to silence this case. Ideally, we would mark the aliases directly as __init/__exit. However, there are currently around 132 modules in the kernel which are missing __init/__exit in their init/cleanup functions (either because they are missing, or for other reasons, e.g. the functions being called from somewhere else); and a section mismatch is a hard error. A conservative alternative was to mark the aliases as __cold only. However, since we would like to eventually enforce __init/__exit to be always marked, we chose to use the new __copy function attribute (introduced by GCC 9 as well to deal with this). With it, we copy the attributes used by the target functions into the aliases. This way, functions that were not marked as __init/__exit won't have their aliases marked either, and therefore there won't be a section mismatch. Note that the warning would go away marking either the extern declaration, the definition, or both. However, we only mark the definition of the alias, since we do not want callers (which only see the declaration) to be compiled as if the function was __cold (and therefore the paths leading to those calls would be assumed to be unlikely). Link: https://lore.kernel.org/lkml/20190123173707.GA16603@gmail.com/ Link: https://lore.kernel.org/lkml/20190206175627.GA20399@gmail.com/ Suggested-by: Martin Sebor <msebor@gcc.gnu.org> Acked-by: Jessica Yu <jeyu@kernel.org> Signed-off-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
2019-01-20 03:59:34 +08:00
void cleanup_module(void) __copy(exitfn) __attribute__((alias(#exitfn)));
#endif
/* This means "can be init if no module support, otherwise module load
may call it." */
#ifdef CONFIG_MODULES
#define __init_or_module
#define __initdata_or_module
#define __initconst_or_module
#define __INIT_OR_MODULE .text
#define __INITDATA_OR_MODULE .data
#define __INITRODATA_OR_MODULE .section ".rodata","a",%progbits
#else
#define __init_or_module __init
#define __initdata_or_module __initdata
#define __initconst_or_module __initconst
#define __INIT_OR_MODULE __INIT
#define __INITDATA_OR_MODULE __INITDATA
#define __INITRODATA_OR_MODULE __INITRODATA
#endif /*CONFIG_MODULES*/
/* Generic info of form tag = "info" */
#define MODULE_INFO(tag, info) __MODULE_INFO(tag, tag, info)
/* For userspace: you can also call me... */
#define MODULE_ALIAS(_alias) MODULE_INFO(alias, _alias)
/* Soft module dependencies. See man modprobe.d for details.
* Example: MODULE_SOFTDEP("pre: module-foo module-bar post: module-baz")
*/
#define MODULE_SOFTDEP(_softdep) MODULE_INFO(softdep, _softdep)
kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf Commit bc081dd6e9f6 ("kbuild: generate modules.builtin") added infrastructure to generate modules.builtin, the list of all builtin modules. Basically, it works like this: - Kconfig generates include/config/tristate.conf, the list of tristate CONFIG options with a value in a capital letter. - scripts/Makefile.modbuiltin makes Kbuild descend into directories to collect the information of builtin modules. I am not a big fan of it because Kbuild ends up with traversing the source tree twice. I am not sure how perfectly it should work, but this approach cannot avoid false positives; even if the relevant CONFIG option is tristate, some Makefiles forces obj-m to obj-y. Some examples are: arch/powerpc/platforms/powermac/Makefile: obj-$(CONFIG_NVRAM:m=y) += nvram.o net/ipv6/Makefile: obj-$(subst m,y,$(CONFIG_IPV6)) += inet6_hashtables.o net/netlabel/Makefile: obj-$(subst m,y,$(CONFIG_IPV6)) += netlabel_calipso.o Nobody has complained about (or noticed) it, so it is probably fine to have false positives in modules.builtin. This commit simplifies the implementation. Let's exploit the fact that every module has MODULE_LICENSE(). (modpost shows a warning if MODULE_LICENSE is missing. If so, 0-day bot would already have blocked such a module.) I added MODULE_FILE to <linux/module.h>. When the code is being compiled as builtin, it will be filled with the file path of the module, and collected into modules.builtin.info. Then, scripts/link-vmlinux.sh extracts the list of builtin modules out of it. This new approach fixes the false-positives above, but adds another type of false-positives; non-modular code may have MODULE_LICENSE() by mistake. This is not a big deal, it is just the code is always orphan. We can clean it up if we like. You can see cleanup examples by: $ git log --grep='make.* explicitly non-modular' To sum up, this commits deletes lots of code, but still produces almost equivalent results. Please note it does not increase the vmlinux size at all. As you can see in include/asm-generic/vmlinux.lds.h, the .modinfo section is discarded in the link stage. Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
2019-12-19 16:33:29 +08:00
/*
* MODULE_FILE is used for generating modules.builtin
* So, make it no-op when this is being built as a module
*/
#ifdef MODULE
#define MODULE_FILE
#else
#define MODULE_FILE MODULE_INFO(file, KBUILD_MODFILE);
#endif
/*
* The following license idents are currently accepted as indicating free
* software modules
*
module: Cure the MODULE_LICENSE "GPL" vs. "GPL v2" bogosity The original MODULE_LICENSE string for kernel modules licensed under the GPL v2 (only / or later) was simply "GPL", which was - and still is - completely sufficient for the purpose of module loading and checking whether the module is free software or proprietary. In January 2003 this was changed with commit 3344ea3ad4b7 ("[PATCH] MODULE_LICENSE and EXPORT_SYMBOL_GPL support"). This commit can be found in the history git repository which holds the 1:1 import of Linus' bitkeeper repository: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git/commit/?id=3344ea3ad4b7c302c846a680dbaeedf96ed45c02 The main intention of the patch was to refuse linking proprietary modules against symbols exported with EXPORT_SYMBOL_GPL() at module load time. As a completely undocumented side effect it also introduced the distinction between "GPL" and "GPL v2" MODULE_LICENSE() strings: * "GPL" [GNU Public License v2 or later] * "GPL v2" [GNU Public License v2] * "GPL and additional rights" [GNU Public License v2 rights and more] * "Dual BSD/GPL" [GNU Public License v2 * or BSD license choice] * "Dual MPL/GPL" [GNU Public License v2 * or Mozilla license choice] This distinction was and still is wrong in several aspects: 1) It broke all modules which were using the "GPL" string in the MODULE_LICENSE() already and were licensed under GPL v2 only. A quick license scan over the tree at that time shows that at least 480 out of 1484 modules have been affected by this change back then. The number is probably way higher as this was just a quick check for clearly identifiable license information. There was exactly ONE instance of a "GPL v2" module license string in the kernel back then - drivers/net/tulip/xircom_tulip_cb.c which otherwise had no license information at all. There is no indication that the change above is any way related to this driver. The change happend with the 2.4.11 release which was on Oct. 9 2001 - so quite some time before the above commit. Unfortunately there is no trace on the intertubes to any discussion of this. 2) The dual licensed strings became ill defined as well because following the "GPL" vs. "GPL v2" distinction all dual licensed (or additional rights) MODULE_LICENSE strings would either require those dual licensed modules to be licensed under GPL v2 or later or just be unspecified for the dual licensing case. Neither choice is coherent with the GPL distinction. Due to the lack of a proper changelog and no real discussion on the patch submission other than a few implementation details, it's completely unclear why this distinction was introduced at all. Other than the comment in the module header file exists no documentation for this at all. From a license compliance and license scanning POV this distinction is a total nightmare. As of 5.0-rc2 2873 out of 9200 instances of MODULE_LICENSE() strings are conflicting with the actual license in the source code (either SPDX or license boilerplate/reference). A comparison between the scan of the history tree and a scan of current Linus tree shows to the extent that the git rename detection over Linus tree grafted with the history tree is halfways complete that almost none of the files which got broken in 2003 have been cleaned up vs. the MODULE_LICENSE string. So subtracting those 480 known instances from the conflicting 2800 of today more than 25% of the module authors got it wrong and it's a high propability that a large portion of the rest just got it right by chance. There is no value for the module loader to convey the detailed license information as the only decision to be made is whether the module is free software or not. The "and additional rights", "BSD" and "MPL" strings are not conclusive license information either. So there is no point in trying to make the GPL part conclusive and exact. As shown above it's already non conclusive for dual licensing and incoherent with a large portion of the module source. As an unintended side effect this distinction causes a major headache for license compliance, license scanners and the ongoing effort to clean up the license mess of the kernel. Therefore remove the well meant, but ill defined, distinction between "GPL" and "GPL v2" and document that: - "GPL" and "GPL v2" both express that the module is licensed under GPLv2 (without a distinction of 'only' and 'or later') and is therefore kernel license compliant. - None of the MODULE_LICENSE strings can be used for expressing or determining the exact license - Their sole purpose is to decide whether the module is free software or not. Add a MODULE_LICENSE subsection to the license rule documentation as well. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Philippe Ombredanne <pombredanne@nexb.com> Acked-by: Joe Perches <joe@perches.com> [jc: Did s/merily/merely/ ] Acked-by: Jessica Yu <jeyu@kernel.org> Signed-off-by: Jonathan Corbet <corbet@lwn.net>
2019-02-09 00:02:56 +08:00
* "GPL" [GNU Public License v2]
* "GPL v2" [GNU Public License v2]
* "GPL and additional rights" [GNU Public License v2 rights and more]
* "Dual BSD/GPL" [GNU Public License v2
* or BSD license choice]
* "Dual MIT/GPL" [GNU Public License v2
* or MIT license choice]
* "Dual MPL/GPL" [GNU Public License v2
* or Mozilla license choice]
*
* The following other idents are available
*
* "Proprietary" [Non free products]
*
module: Cure the MODULE_LICENSE "GPL" vs. "GPL v2" bogosity The original MODULE_LICENSE string for kernel modules licensed under the GPL v2 (only / or later) was simply "GPL", which was - and still is - completely sufficient for the purpose of module loading and checking whether the module is free software or proprietary. In January 2003 this was changed with commit 3344ea3ad4b7 ("[PATCH] MODULE_LICENSE and EXPORT_SYMBOL_GPL support"). This commit can be found in the history git repository which holds the 1:1 import of Linus' bitkeeper repository: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git/commit/?id=3344ea3ad4b7c302c846a680dbaeedf96ed45c02 The main intention of the patch was to refuse linking proprietary modules against symbols exported with EXPORT_SYMBOL_GPL() at module load time. As a completely undocumented side effect it also introduced the distinction between "GPL" and "GPL v2" MODULE_LICENSE() strings: * "GPL" [GNU Public License v2 or later] * "GPL v2" [GNU Public License v2] * "GPL and additional rights" [GNU Public License v2 rights and more] * "Dual BSD/GPL" [GNU Public License v2 * or BSD license choice] * "Dual MPL/GPL" [GNU Public License v2 * or Mozilla license choice] This distinction was and still is wrong in several aspects: 1) It broke all modules which were using the "GPL" string in the MODULE_LICENSE() already and were licensed under GPL v2 only. A quick license scan over the tree at that time shows that at least 480 out of 1484 modules have been affected by this change back then. The number is probably way higher as this was just a quick check for clearly identifiable license information. There was exactly ONE instance of a "GPL v2" module license string in the kernel back then - drivers/net/tulip/xircom_tulip_cb.c which otherwise had no license information at all. There is no indication that the change above is any way related to this driver. The change happend with the 2.4.11 release which was on Oct. 9 2001 - so quite some time before the above commit. Unfortunately there is no trace on the intertubes to any discussion of this. 2) The dual licensed strings became ill defined as well because following the "GPL" vs. "GPL v2" distinction all dual licensed (or additional rights) MODULE_LICENSE strings would either require those dual licensed modules to be licensed under GPL v2 or later or just be unspecified for the dual licensing case. Neither choice is coherent with the GPL distinction. Due to the lack of a proper changelog and no real discussion on the patch submission other than a few implementation details, it's completely unclear why this distinction was introduced at all. Other than the comment in the module header file exists no documentation for this at all. From a license compliance and license scanning POV this distinction is a total nightmare. As of 5.0-rc2 2873 out of 9200 instances of MODULE_LICENSE() strings are conflicting with the actual license in the source code (either SPDX or license boilerplate/reference). A comparison between the scan of the history tree and a scan of current Linus tree shows to the extent that the git rename detection over Linus tree grafted with the history tree is halfways complete that almost none of the files which got broken in 2003 have been cleaned up vs. the MODULE_LICENSE string. So subtracting those 480 known instances from the conflicting 2800 of today more than 25% of the module authors got it wrong and it's a high propability that a large portion of the rest just got it right by chance. There is no value for the module loader to convey the detailed license information as the only decision to be made is whether the module is free software or not. The "and additional rights", "BSD" and "MPL" strings are not conclusive license information either. So there is no point in trying to make the GPL part conclusive and exact. As shown above it's already non conclusive for dual licensing and incoherent with a large portion of the module source. As an unintended side effect this distinction causes a major headache for license compliance, license scanners and the ongoing effort to clean up the license mess of the kernel. Therefore remove the well meant, but ill defined, distinction between "GPL" and "GPL v2" and document that: - "GPL" and "GPL v2" both express that the module is licensed under GPLv2 (without a distinction of 'only' and 'or later') and is therefore kernel license compliant. - None of the MODULE_LICENSE strings can be used for expressing or determining the exact license - Their sole purpose is to decide whether the module is free software or not. Add a MODULE_LICENSE subsection to the license rule documentation as well. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Philippe Ombredanne <pombredanne@nexb.com> Acked-by: Joe Perches <joe@perches.com> [jc: Did s/merily/merely/ ] Acked-by: Jessica Yu <jeyu@kernel.org> Signed-off-by: Jonathan Corbet <corbet@lwn.net>
2019-02-09 00:02:56 +08:00
* Both "GPL v2" and "GPL" (the latter also in dual licensed strings) are
* merely stating that the module is licensed under the GPL v2, but are not
* telling whether "GPL v2 only" or "GPL v2 or later". The reason why there
* are two variants is a historic and failed attempt to convey more
* information in the MODULE_LICENSE string. For module loading the
* "only/or later" distinction is completely irrelevant and does neither
* replace the proper license identifiers in the corresponding source file
* nor amends them in any way. The sole purpose is to make the
* 'Proprietary' flagging work and to refuse to bind symbols which are
* exported with EXPORT_SYMBOL_GPL when a non free module is loaded.
*
* In the same way "BSD" is not a clear license information. It merely
* states, that the module is licensed under one of the compatible BSD
* license variants. The detailed and correct license information is again
* to be found in the corresponding source files.
*
* There are dual licensed components, but when running with Linux it is the
* GPL that is relevant so this is a non issue. Similarly LGPL linked with GPL
* is a GPL combined work.
*
* This exists for several reasons
* 1. So modinfo can show license info for users wanting to vet their setup
* is free
* 2. So the community can ignore bug reports including proprietary modules
* 3. So vendors can do likewise based on their own policies
*/
kbuild: create modules.builtin without Makefile.modbuiltin or tristate.conf Commit bc081dd6e9f6 ("kbuild: generate modules.builtin") added infrastructure to generate modules.builtin, the list of all builtin modules. Basically, it works like this: - Kconfig generates include/config/tristate.conf, the list of tristate CONFIG options with a value in a capital letter. - scripts/Makefile.modbuiltin makes Kbuild descend into directories to collect the information of builtin modules. I am not a big fan of it because Kbuild ends up with traversing the source tree twice. I am not sure how perfectly it should work, but this approach cannot avoid false positives; even if the relevant CONFIG option is tristate, some Makefiles forces obj-m to obj-y. Some examples are: arch/powerpc/platforms/powermac/Makefile: obj-$(CONFIG_NVRAM:m=y) += nvram.o net/ipv6/Makefile: obj-$(subst m,y,$(CONFIG_IPV6)) += inet6_hashtables.o net/netlabel/Makefile: obj-$(subst m,y,$(CONFIG_IPV6)) += netlabel_calipso.o Nobody has complained about (or noticed) it, so it is probably fine to have false positives in modules.builtin. This commit simplifies the implementation. Let's exploit the fact that every module has MODULE_LICENSE(). (modpost shows a warning if MODULE_LICENSE is missing. If so, 0-day bot would already have blocked such a module.) I added MODULE_FILE to <linux/module.h>. When the code is being compiled as builtin, it will be filled with the file path of the module, and collected into modules.builtin.info. Then, scripts/link-vmlinux.sh extracts the list of builtin modules out of it. This new approach fixes the false-positives above, but adds another type of false-positives; non-modular code may have MODULE_LICENSE() by mistake. This is not a big deal, it is just the code is always orphan. We can clean it up if we like. You can see cleanup examples by: $ git log --grep='make.* explicitly non-modular' To sum up, this commits deletes lots of code, but still produces almost equivalent results. Please note it does not increase the vmlinux size at all. As you can see in include/asm-generic/vmlinux.lds.h, the .modinfo section is discarded in the link stage. Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
2019-12-19 16:33:29 +08:00
#define MODULE_LICENSE(_license) MODULE_FILE MODULE_INFO(license, _license)
/*
* Author(s), use "Name <email>" or just "Name", for multiple
* authors use multiple MODULE_AUTHOR() statements/lines.
*/
#define MODULE_AUTHOR(_author) MODULE_INFO(author, _author)
/* What your module does. */
#define MODULE_DESCRIPTION(_description) MODULE_INFO(description, _description)
#ifdef MODULE
/* Creates an alias so file2alias.c can find device table. */
#define MODULE_DEVICE_TABLE(type, name) \
extern typeof(name) __mod_##type##__##name##_device_table \
__attribute__ ((unused, alias(__stringify(name))))
#else /* !MODULE */
#define MODULE_DEVICE_TABLE(type, name)
#endif
/* Version of form [<epoch>:]<version>[-<extra-version>].
* Or for CVS/RCS ID version, everything but the number is stripped.
* <epoch>: A (small) unsigned integer which allows you to start versions
* anew. If not mentioned, it's zero. eg. "2:1.0" is after
* "1:2.0".
* <version>: The <version> may contain only alphanumerics and the
* character `.'. Ordered by numeric sort for numeric parts,
* ascii sort for ascii parts (as per RPM or DEB algorithm).
* <extraversion>: Like <version>, but inserted for local
* customizations, eg "rh3" or "rusty1".
* Using this automatically adds a checksum of the .c files and the
* local headers in "srcversion".
*/
#if defined(MODULE) || !defined(CONFIG_SYSFS)
#define MODULE_VERSION(_version) MODULE_INFO(version, _version)
#else
#define MODULE_VERSION(_version) \
moduleparam: Save information about built-in modules in separate file Problem: When a kernel module is compiled as a separate module, some important information about the kernel module is available via .modinfo section of the module. In contrast, when the kernel module is compiled into the kernel, that information is not available. Information about built-in modules is necessary in the following cases: 1. When it is necessary to find out what additional parameters can be passed to the kernel at boot time. 2. When you need to know which module names and their aliases are in the kernel. This is very useful for creating an initrd image. Proposal: The proposed patch does not remove .modinfo section with module information from the vmlinux at the build time and saves it into a separate file after kernel linking. So, the kernel does not increase in size and no additional information remains in it. Information is stored in the same format as in the separate modules (null-terminated string array). Because the .modinfo section is already exported with a separate modules, we are not creating a new API. It can be easily read in the userspace: $ tr '\0' '\n' < modules.builtin.modinfo ext4.softdep=pre: crc32c ext4.license=GPL ext4.description=Fourth Extended Filesystem ext4.author=Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others ext4.alias=fs-ext4 ext4.alias=ext3 ext4.alias=fs-ext3 ext4.alias=ext2 ext4.alias=fs-ext2 md_mod.alias=block-major-9-* md_mod.alias=md md_mod.description=MD RAID framework md_mod.license=GPL md_mod.parmtype=create_on_open:bool md_mod.parmtype=start_dirty_degraded:int ... Co-Developed-by: Gleb Fotengauer-Malinovskiy <glebfm@altlinux.org> Signed-off-by: Gleb Fotengauer-Malinovskiy <glebfm@altlinux.org> Signed-off-by: Alexey Gladkov <gladkov.alexey@gmail.com> Acked-by: Jessica Yu <jeyu@kernel.org> Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
2019-04-30 00:11:14 +08:00
MODULE_INFO(version, _version); \
static struct module_version_attribute ___modver_attr = { \
.mattr = { \
.attr = { \
.name = "version", \
.mode = S_IRUGO, \
}, \
.show = __modver_version_show, \
}, \
.module_name = KBUILD_MODNAME, \
.version = _version, \
}; \
static const struct module_version_attribute \
__used __attribute__ ((__section__ ("__modver"))) \
* __moduleparam_const __modver_attr = &___modver_attr
#endif
/* Optional firmware file (or files) needed by the module
* format is simply firmware file name. Multiple firmware
* files require multiple MODULE_FIRMWARE() specifiers */
#define MODULE_FIRMWARE(_firmware) MODULE_INFO(firmware, _firmware)
#define MODULE_IMPORT_NS(ns) MODULE_INFO(import_ns, #ns)
struct notifier_block;
#ifdef CONFIG_MODULES
extern int modules_disabled; /* for sysctl */
/* Get/put a kernel symbol (calls must be symmetric) */
void *__symbol_get(const char *symbol);
void *__symbol_get_gpl(const char *symbol);
#define symbol_get(x) ((typeof(&x))(__symbol_get(__stringify(x))))
/* modules using other modules: kdb wants to see this. */
struct module_use {
struct list_head source_list;
struct list_head target_list;
struct module *source, *target;
};
enum module_state {
MODULE_STATE_LIVE, /* Normal state. */
MODULE_STATE_COMING, /* Full formed, running module_init. */
MODULE_STATE_GOING, /* Going away. */
MODULE_STATE_UNFORMED, /* Still setting it up. */
};
struct mod_tree_node {
struct module *mod;
struct latch_tree_node node;
};
struct module_layout {
/* The actual code + data. */
void *base;
/* Total size. */
unsigned int size;
/* The size of the executable code. */
unsigned int text_size;
/* Size of RO section of the module (text+rodata) */
unsigned int ro_size;
/* Size of RO after init section */
unsigned int ro_after_init_size;
#ifdef CONFIG_MODULES_TREE_LOOKUP
struct mod_tree_node mtn;
#endif
};
#ifdef CONFIG_MODULES_TREE_LOOKUP
/* Only touch one cacheline for common rbtree-for-core-layout case. */
#define __module_layout_align ____cacheline_aligned
#else
#define __module_layout_align
#endif
modules: fix longstanding /proc/kallsyms vs module insertion race. For CONFIG_KALLSYMS, we keep two symbol tables and two string tables. There's one full copy, marked SHF_ALLOC and laid out at the end of the module's init section. There's also a cut-down version that only contains core symbols and strings, and lives in the module's core section. After module init (and before we free the module memory), we switch the mod->symtab, mod->num_symtab and mod->strtab to point to the core versions. We do this under the module_mutex. However, kallsyms doesn't take the module_mutex: it uses preempt_disable() and rcu tricks to walk through the modules, because it's used in the oops path. It's also used in /proc/kallsyms. There's nothing atomic about the change of these variables, so we can get the old (larger!) num_symtab and the new symtab pointer; in fact this is what I saw when trying to reproduce. By grouping these variables together, we can use a carefully-dereferenced pointer to ensure we always get one or the other (the free of the module init section is already done in an RCU callback, so that's safe). We allocate the init one at the end of the module init section, and keep the core one inside the struct module itself (it could also have been allocated at the end of the module core, but that's probably overkill). Reported-by: Weilong Chen <chenweilong@huawei.com> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=111541 Cc: stable@kernel.org Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2016-02-03 14:25:26 +08:00
struct mod_kallsyms {
Elf_Sym *symtab;
unsigned int num_symtab;
char *strtab;
char *typetab;
modules: fix longstanding /proc/kallsyms vs module insertion race. For CONFIG_KALLSYMS, we keep two symbol tables and two string tables. There's one full copy, marked SHF_ALLOC and laid out at the end of the module's init section. There's also a cut-down version that only contains core symbols and strings, and lives in the module's core section. After module init (and before we free the module memory), we switch the mod->symtab, mod->num_symtab and mod->strtab to point to the core versions. We do this under the module_mutex. However, kallsyms doesn't take the module_mutex: it uses preempt_disable() and rcu tricks to walk through the modules, because it's used in the oops path. It's also used in /proc/kallsyms. There's nothing atomic about the change of these variables, so we can get the old (larger!) num_symtab and the new symtab pointer; in fact this is what I saw when trying to reproduce. By grouping these variables together, we can use a carefully-dereferenced pointer to ensure we always get one or the other (the free of the module init section is already done in an RCU callback, so that's safe). We allocate the init one at the end of the module init section, and keep the core one inside the struct module itself (it could also have been allocated at the end of the module core, but that's probably overkill). Reported-by: Weilong Chen <chenweilong@huawei.com> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=111541 Cc: stable@kernel.org Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2016-02-03 14:25:26 +08:00
};
module: preserve Elf information for livepatch modules For livepatch modules, copy Elf section, symbol, and string information from the load_info struct in the module loader. Persist copies of the original symbol table and string table. Livepatch manages its own relocation sections in order to reuse module loader code to write relocations. Livepatch modules must preserve Elf information such as section indices in order to apply livepatch relocation sections using the module loader's apply_relocate_add() function. In order to apply livepatch relocation sections, livepatch modules must keep a complete copy of their original symbol table in memory. Normally, a stripped down copy of a module's symbol table (containing only "core" symbols) is made available through module->core_symtab. But for livepatch modules, the symbol table copied into memory on module load must be exactly the same as the symbol table produced when the patch module was compiled. This is because the relocations in each livepatch relocation section refer to their respective symbols with their symbol indices, and the original symbol indices (and thus the symtab ordering) must be preserved in order for apply_relocate_add() to find the right symbol. Signed-off-by: Jessica Yu <jeyu@redhat.com> Reviewed-by: Miroslav Benes <mbenes@suse.cz> Acked-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Rusty Russell <rusty@rustcorp.com.au> Reviewed-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Jiri Kosina <jkosina@suse.cz>
2016-03-23 08:03:16 +08:00
#ifdef CONFIG_LIVEPATCH
struct klp_modinfo {
Elf_Ehdr hdr;
Elf_Shdr *sechdrs;
char *secstrings;
unsigned int symndx;
};
#endif
struct module {
enum module_state state;
/* Member of list of modules */
struct list_head list;
/* Unique handle for this module */
char name[MODULE_NAME_LEN];
/* Sysfs stuff. */
struct module_kobject mkobj;
struct module_attribute *modinfo_attrs;
[PATCH] modules: add version and srcversion to sysfs This patch adds version and srcversion files to /sys/module/${modulename} containing the version and srcversion fields of the module's modinfo section (if present). /sys/module/e1000 |-- srcversion `-- version This patch differs slightly from the version posted in January, as it now uses the new kstrdup() call in -mm. Why put this in sysfs? a) Tools like DKMS, which deal with changing out individual kernel modules without replacing the whole kernel, can behave smarter if they can tell the version of a given module. The autoinstaller feature, for example, which determines if your system has a "good" version of a driver (i.e. if the one provided by DKMS has a newer verson than that provided by the kernel package installed), and to automatically compile and install a newer version if DKMS has it but your kernel doesn't yet have that version. b) Because sysadmins manually, or with tools like DKMS, can switch out modules on the file system, you can't count on 'modinfo foo.ko', which looks at /lib/modules/${kernelver}/... actually matching what is loaded into the kernel already. Hence asking sysfs for this. c) as the unbind-driver-from-device work takes shape, it will be possible to rebind a driver that's built-in (no .ko to modinfo for the version) to a newly loaded module. sysfs will have the currently-built-in version info, for comparison. d) tech support scripts can then easily grab the version info for what's running presently - a question I get often. There has been renewed interest in this patch on linux-scsi by driver authors. As the idea originated from GregKH, I leave his Signed-off-by: intact, though the implementation is nearly completely new. Compiled and run on x86 and x86_64. From: Matthew Dobson <colpatch@us.ibm.com> build fix From: Thierry Vignaud <tvignaud@mandriva.com> build fix From: Matthew Dobson <colpatch@us.ibm.com> warning fix Signed-off-by: Greg Kroah-Hartman <greg@kroah.com> Signed-off-by: Matt Domsch <Matt_Domsch@dell.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-24 13:05:15 +08:00
const char *version;
const char *srcversion;
struct kobject *holders_dir;
/* Exported symbols */
const struct kernel_symbol *syms;
modversions: treat symbol CRCs as 32 bit quantities The modversion symbol CRCs are emitted as ELF symbols, which allows us to easily populate the kcrctab sections by relying on the linker to associate each kcrctab slot with the correct value. This has a couple of downsides: - Given that the CRCs are treated as memory addresses, we waste 4 bytes for each CRC on 64 bit architectures, - On architectures that support runtime relocation, a R_<arch>_RELATIVE relocation entry is emitted for each CRC value, which identifies it as a quantity that requires fixing up based on the actual runtime load offset of the kernel. This results in corrupted CRCs unless we explicitly undo the fixup (and this is currently being handled in the core module code) - Such runtime relocation entries take up 24 bytes of __init space each, resulting in a x8 overhead in [uncompressed] kernel size for CRCs. Switching to explicit 32 bit values on 64 bit architectures fixes most of these issues, given that 32 bit values are not treated as quantities that require fixing up based on the actual runtime load offset. Note that on some ELF64 architectures [such as PPC64], these 32-bit values are still emitted as [absolute] runtime relocatable quantities, even if the value resolves to a build time constant. Since relative relocations are always resolved at build time, this patch enables MODULE_REL_CRCS on powerpc when CONFIG_RELOCATABLE=y, which turns the absolute CRC references into relative references into .rodata where the actual CRC value is stored. So redefine all CRC fields and variables as u32, and redefine the __CRC_SYMBOL() macro for 64 bit builds to emit the CRC reference using inline assembler (which is necessary since 64-bit C code cannot use 32-bit types to hold memory addresses, even if they are ultimately resolved using values that do not exceed 0xffffffff). To avoid potential problems with legacy 32-bit architectures using legacy toolchains, the equivalent C definition of the kcrctab entry is retained for 32-bit architectures. Note that this mostly reverts commit d4703aefdbc8 ("module: handle ppc64 relocating kcrctabs when CONFIG_RELOCATABLE=y") Acked-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-03 17:54:06 +08:00
const s32 *crcs;
unsigned int num_syms;
/* Kernel parameters. */
#ifdef CONFIG_SYSFS
module: add per-module param_lock Add a "param_lock" mutex to each module, and update params.c to use the correct built-in or module mutex while locking kernel params. Remove the kparam_block_sysfs_r/w() macros, replace them with direct calls to kernel_param_[un]lock(module). The kernel param code currently uses a single mutex to protect modification of any and all kernel params. While this generally works, there is one specific problem with it; a module callback function cannot safely load another module, i.e. with request_module() or even with indirect calls such as crypto_has_alg(). If the module to be loaded has any of its params configured (e.g. with a /etc/modprobe.d/* config file), then the attempt will result in a deadlock between the first module param callback waiting for modprobe, and modprobe trying to lock the single kernel param mutex to set the new module's param. This fixes that by using per-module mutexes, so that each individual module is protected against concurrent changes in its own kernel params, but is not blocked by changes to other module params. All built-in modules continue to use the built-in mutex, since they will always be loaded at runtime and references (e.g. request_module(), crypto_has_alg()) to them will never cause load-time param changing. This also simplifies the interface used by modules to block sysfs access to their params; while there are currently functions to block and unblock sysfs param access which are split up by read and write and expect a single kernel param to be passed, their actual operation is identical and applies to all params, not just the one passed to them; they simply lock and unlock the global param mutex. They are replaced with direct calls to kernel_param_[un]lock(THIS_MODULE), which locks THIS_MODULE's param_lock, or if the module is built-in, it locks the built-in mutex. Suggested-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Dan Streetman <ddstreet@ieee.org> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2015-06-17 04:48:52 +08:00
struct mutex param_lock;
#endif
struct kernel_param *kp;
unsigned int num_kp;
/* GPL-only exported symbols. */
unsigned int num_gpl_syms;
const struct kernel_symbol *gpl_syms;
modversions: treat symbol CRCs as 32 bit quantities The modversion symbol CRCs are emitted as ELF symbols, which allows us to easily populate the kcrctab sections by relying on the linker to associate each kcrctab slot with the correct value. This has a couple of downsides: - Given that the CRCs are treated as memory addresses, we waste 4 bytes for each CRC on 64 bit architectures, - On architectures that support runtime relocation, a R_<arch>_RELATIVE relocation entry is emitted for each CRC value, which identifies it as a quantity that requires fixing up based on the actual runtime load offset of the kernel. This results in corrupted CRCs unless we explicitly undo the fixup (and this is currently being handled in the core module code) - Such runtime relocation entries take up 24 bytes of __init space each, resulting in a x8 overhead in [uncompressed] kernel size for CRCs. Switching to explicit 32 bit values on 64 bit architectures fixes most of these issues, given that 32 bit values are not treated as quantities that require fixing up based on the actual runtime load offset. Note that on some ELF64 architectures [such as PPC64], these 32-bit values are still emitted as [absolute] runtime relocatable quantities, even if the value resolves to a build time constant. Since relative relocations are always resolved at build time, this patch enables MODULE_REL_CRCS on powerpc when CONFIG_RELOCATABLE=y, which turns the absolute CRC references into relative references into .rodata where the actual CRC value is stored. So redefine all CRC fields and variables as u32, and redefine the __CRC_SYMBOL() macro for 64 bit builds to emit the CRC reference using inline assembler (which is necessary since 64-bit C code cannot use 32-bit types to hold memory addresses, even if they are ultimately resolved using values that do not exceed 0xffffffff). To avoid potential problems with legacy 32-bit architectures using legacy toolchains, the equivalent C definition of the kcrctab entry is retained for 32-bit architectures. Note that this mostly reverts commit d4703aefdbc8 ("module: handle ppc64 relocating kcrctabs when CONFIG_RELOCATABLE=y") Acked-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-03 17:54:06 +08:00
const s32 *gpl_crcs;
#ifdef CONFIG_UNUSED_SYMBOLS
/* unused exported symbols. */
const struct kernel_symbol *unused_syms;
modversions: treat symbol CRCs as 32 bit quantities The modversion symbol CRCs are emitted as ELF symbols, which allows us to easily populate the kcrctab sections by relying on the linker to associate each kcrctab slot with the correct value. This has a couple of downsides: - Given that the CRCs are treated as memory addresses, we waste 4 bytes for each CRC on 64 bit architectures, - On architectures that support runtime relocation, a R_<arch>_RELATIVE relocation entry is emitted for each CRC value, which identifies it as a quantity that requires fixing up based on the actual runtime load offset of the kernel. This results in corrupted CRCs unless we explicitly undo the fixup (and this is currently being handled in the core module code) - Such runtime relocation entries take up 24 bytes of __init space each, resulting in a x8 overhead in [uncompressed] kernel size for CRCs. Switching to explicit 32 bit values on 64 bit architectures fixes most of these issues, given that 32 bit values are not treated as quantities that require fixing up based on the actual runtime load offset. Note that on some ELF64 architectures [such as PPC64], these 32-bit values are still emitted as [absolute] runtime relocatable quantities, even if the value resolves to a build time constant. Since relative relocations are always resolved at build time, this patch enables MODULE_REL_CRCS on powerpc when CONFIG_RELOCATABLE=y, which turns the absolute CRC references into relative references into .rodata where the actual CRC value is stored. So redefine all CRC fields and variables as u32, and redefine the __CRC_SYMBOL() macro for 64 bit builds to emit the CRC reference using inline assembler (which is necessary since 64-bit C code cannot use 32-bit types to hold memory addresses, even if they are ultimately resolved using values that do not exceed 0xffffffff). To avoid potential problems with legacy 32-bit architectures using legacy toolchains, the equivalent C definition of the kcrctab entry is retained for 32-bit architectures. Note that this mostly reverts commit d4703aefdbc8 ("module: handle ppc64 relocating kcrctabs when CONFIG_RELOCATABLE=y") Acked-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-03 17:54:06 +08:00
const s32 *unused_crcs;
unsigned int num_unused_syms;
/* GPL-only, unused exported symbols. */
unsigned int num_unused_gpl_syms;
const struct kernel_symbol *unused_gpl_syms;
modversions: treat symbol CRCs as 32 bit quantities The modversion symbol CRCs are emitted as ELF symbols, which allows us to easily populate the kcrctab sections by relying on the linker to associate each kcrctab slot with the correct value. This has a couple of downsides: - Given that the CRCs are treated as memory addresses, we waste 4 bytes for each CRC on 64 bit architectures, - On architectures that support runtime relocation, a R_<arch>_RELATIVE relocation entry is emitted for each CRC value, which identifies it as a quantity that requires fixing up based on the actual runtime load offset of the kernel. This results in corrupted CRCs unless we explicitly undo the fixup (and this is currently being handled in the core module code) - Such runtime relocation entries take up 24 bytes of __init space each, resulting in a x8 overhead in [uncompressed] kernel size for CRCs. Switching to explicit 32 bit values on 64 bit architectures fixes most of these issues, given that 32 bit values are not treated as quantities that require fixing up based on the actual runtime load offset. Note that on some ELF64 architectures [such as PPC64], these 32-bit values are still emitted as [absolute] runtime relocatable quantities, even if the value resolves to a build time constant. Since relative relocations are always resolved at build time, this patch enables MODULE_REL_CRCS on powerpc when CONFIG_RELOCATABLE=y, which turns the absolute CRC references into relative references into .rodata where the actual CRC value is stored. So redefine all CRC fields and variables as u32, and redefine the __CRC_SYMBOL() macro for 64 bit builds to emit the CRC reference using inline assembler (which is necessary since 64-bit C code cannot use 32-bit types to hold memory addresses, even if they are ultimately resolved using values that do not exceed 0xffffffff). To avoid potential problems with legacy 32-bit architectures using legacy toolchains, the equivalent C definition of the kcrctab entry is retained for 32-bit architectures. Note that this mostly reverts commit d4703aefdbc8 ("module: handle ppc64 relocating kcrctabs when CONFIG_RELOCATABLE=y") Acked-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-03 17:54:06 +08:00
const s32 *unused_gpl_crcs;
#endif
#ifdef CONFIG_MODULE_SIG
/* Signature was verified. */
bool sig_ok;
#endif
bool async_probe_requested;
/* symbols that will be GPL-only in the near future. */
const struct kernel_symbol *gpl_future_syms;
modversions: treat symbol CRCs as 32 bit quantities The modversion symbol CRCs are emitted as ELF symbols, which allows us to easily populate the kcrctab sections by relying on the linker to associate each kcrctab slot with the correct value. This has a couple of downsides: - Given that the CRCs are treated as memory addresses, we waste 4 bytes for each CRC on 64 bit architectures, - On architectures that support runtime relocation, a R_<arch>_RELATIVE relocation entry is emitted for each CRC value, which identifies it as a quantity that requires fixing up based on the actual runtime load offset of the kernel. This results in corrupted CRCs unless we explicitly undo the fixup (and this is currently being handled in the core module code) - Such runtime relocation entries take up 24 bytes of __init space each, resulting in a x8 overhead in [uncompressed] kernel size for CRCs. Switching to explicit 32 bit values on 64 bit architectures fixes most of these issues, given that 32 bit values are not treated as quantities that require fixing up based on the actual runtime load offset. Note that on some ELF64 architectures [such as PPC64], these 32-bit values are still emitted as [absolute] runtime relocatable quantities, even if the value resolves to a build time constant. Since relative relocations are always resolved at build time, this patch enables MODULE_REL_CRCS on powerpc when CONFIG_RELOCATABLE=y, which turns the absolute CRC references into relative references into .rodata where the actual CRC value is stored. So redefine all CRC fields and variables as u32, and redefine the __CRC_SYMBOL() macro for 64 bit builds to emit the CRC reference using inline assembler (which is necessary since 64-bit C code cannot use 32-bit types to hold memory addresses, even if they are ultimately resolved using values that do not exceed 0xffffffff). To avoid potential problems with legacy 32-bit architectures using legacy toolchains, the equivalent C definition of the kcrctab entry is retained for 32-bit architectures. Note that this mostly reverts commit d4703aefdbc8 ("module: handle ppc64 relocating kcrctabs when CONFIG_RELOCATABLE=y") Acked-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-03 17:54:06 +08:00
const s32 *gpl_future_crcs;
unsigned int num_gpl_future_syms;
/* Exception table */
unsigned int num_exentries;
struct exception_table_entry *extable;
/* Startup function. */
int (*init)(void);
/* Core layout: rbtree is accessed frequently, so keep together. */
struct module_layout core_layout __module_layout_align;
struct module_layout init_layout;
x86: Add RO/NX protection for loadable kernel modules This patch is a logical extension of the protection provided by CONFIG_DEBUG_RODATA to LKMs. The protection is provided by splitting module_core and module_init into three logical parts each and setting appropriate page access permissions for each individual section: 1. Code: RO+X 2. RO data: RO+NX 3. RW data: RW+NX In order to achieve proper protection, layout_sections() have been modified to align each of the three parts mentioned above onto page boundary. Next, the corresponding page access permissions are set right before successful exit from load_module(). Further, free_module() and sys_init_module have been modified to set module_core and module_init as RW+NX right before calling module_free(). By default, the original section layout and access flags are preserved. When compiled with CONFIG_DEBUG_SET_MODULE_RONX=y, the patch will page-align each group of sections to ensure that each page contains only one type of content and will enforce RO/NX for each group of pages. -v1: Initial proof-of-concept patch. -v2: The patch have been re-written to reduce the number of #ifdefs and to make it architecture-agnostic. Code formatting has also been corrected. -v3: Opportunistic RO/NX protection is now unconditional. Section page-alignment is enabled when CONFIG_DEBUG_RODATA=y. -v4: Removed most macros and improved coding style. -v5: Changed page-alignment and RO/NX section size calculation -v6: Fixed comments. Restricted RO/NX enforcement to x86 only -v7: Introduced CONFIG_DEBUG_SET_MODULE_RONX, added calls to set_all_modules_text_rw() and set_all_modules_text_ro() in ftrace -v8: updated for compatibility with linux 2.6.33-rc5 -v9: coding style fixes -v10: more coding style fixes -v11: minor adjustments for -tip -v12: minor adjustments for v2.6.35-rc2-tip -v13: minor adjustments for v2.6.37-rc1-tip Signed-off-by: Siarhei Liakh <sliakh.lkml@gmail.com> Signed-off-by: Xuxian Jiang <jiang@cs.ncsu.edu> Acked-by: Arjan van de Ven <arjan@linux.intel.com> Reviewed-by: James Morris <jmorris@namei.org> Signed-off-by: H. Peter Anvin <hpa@zytor.com> Cc: Andi Kleen <ak@muc.de> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Dave Jones <davej@redhat.com> Cc: Kees Cook <kees.cook@canonical.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> LKML-Reference: <4CE2F914.9070106@free.fr> [ minor cleanliness edits, -v14: build failure fix ] Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-11-17 05:35:16 +08:00
/* Arch-specific module values */
struct mod_arch_specific arch;
taint/module: Clean up global and module taint flags handling The commit 66cc69e34e86a231 ("Fix: module signature vs tracepoints: add new TAINT_UNSIGNED_MODULE") updated module_taint_flags() to potentially print one more character. But it did not increase the size of the corresponding buffers in m_show() and print_modules(). We have recently done the same mistake when adding a taint flag for livepatching, see https://lkml.kernel.org/r/cfba2c823bb984690b73572aaae1db596b54a082.1472137475.git.jpoimboe@redhat.com Also struct module uses an incompatible type for mod-taints flags. It survived from the commit 2bc2d61a9638dab670d ("[PATCH] list module taint flags in Oops/panic"). There was used "int" for the global taint flags at these times. But only the global tain flags was later changed to "unsigned long" by the commit 25ddbb18aae33ad2 ("Make the taint flags reliable"). This patch defines TAINT_FLAGS_COUNT that can be used to create arrays and buffers of the right size. Note that we could not use enum because the taint flag indexes are used also in assembly code. Then it reworks the table that describes the taint flags. The TAINT_* numbers can be used as the index. Instead, we add information if the taint flag is also shown per-module. Finally, it uses "unsigned long", bit operations, and the updated taint_flags table also for mod->taints. It is not optimal because only few taint flags can be printed by module_taint_flags(). But better be on the safe side. IMHO, it is not worth the optimization and this is a good compromise. Signed-off-by: Petr Mladek <pmladek@suse.com> Link: http://lkml.kernel.org/r/1474458442-21581-1-git-send-email-pmladek@suse.com [jeyu@redhat.com: fix broken lkml link in changelog] Signed-off-by: Jessica Yu <jeyu@redhat.com>
2016-09-21 19:47:22 +08:00
unsigned long taints; /* same bits as kernel:taint_flags */
[PATCH] Generic BUG implementation This patch adds common handling for kernel BUGs, for use by architectures as they wish. The code is derived from arch/powerpc. The advantages of having common BUG handling are: - consistent BUG reporting across architectures - shared implementation of out-of-line file/line data - implement CONFIG_DEBUG_BUGVERBOSE consistently This means that in inline impact of BUG is just the illegal instruction itself, which is an improvement for i386 and x86-64. A BUG is represented in the instruction stream as an illegal instruction, which has file/line information associated with it. This extra information is stored in the __bug_table section in the ELF file. When the kernel gets an illegal instruction, it first confirms it might possibly be from a BUG (ie, in kernel mode, the right illegal instruction). It then calls report_bug(). This searches __bug_table for a matching instruction pointer, and if found, prints the corresponding file/line information. If report_bug() determines that it wasn't a BUG which caused the trap, it returns BUG_TRAP_TYPE_NONE. Some architectures (powerpc) implement WARN using the same mechanism; if the illegal instruction was the result of a WARN, then report_bug(Q) returns CONFIG_DEBUG_BUGVERBOSE; otherwise it returns BUG_TRAP_TYPE_BUG. lib/bug.c keeps a list of loaded modules which can be searched for __bug_table entries. The architecture must call module_bug_finalize()/module_bug_cleanup() from its corresponding module_finalize/cleanup functions. Unsetting CONFIG_DEBUG_BUGVERBOSE will reduce the kernel size by some amount. At the very least, filename and line information will not be recorded for each but, but architectures may decide to store no extra information per BUG at all. Unfortunately, gcc doesn't have a general way to mark an asm() as noreturn, so architectures will generally have to include an infinite loop (or similar) in the BUG code, so that gcc knows execution won't continue beyond that point. gcc does have a __builtin_trap() operator which may be useful to achieve the same effect, unfortunately it cannot be used to actually implement the BUG itself, because there's no way to get the instruction's address for use in generating the __bug_table entry. [randy.dunlap@oracle.com: Handle BUG=n, GENERIC_BUG=n to prevent build errors] [bunk@stusta.de: include/linux/bug.h must always #include <linux/module.h] Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Andi Kleen <ak@muc.de> Cc: Hugh Dickens <hugh@veritas.com> Cc: Michael Ellerman <michael@ellerman.id.au> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-08 18:36:19 +08:00
#ifdef CONFIG_GENERIC_BUG
/* Support for BUG */
unsigned num_bugs;
[PATCH] Generic BUG implementation This patch adds common handling for kernel BUGs, for use by architectures as they wish. The code is derived from arch/powerpc. The advantages of having common BUG handling are: - consistent BUG reporting across architectures - shared implementation of out-of-line file/line data - implement CONFIG_DEBUG_BUGVERBOSE consistently This means that in inline impact of BUG is just the illegal instruction itself, which is an improvement for i386 and x86-64. A BUG is represented in the instruction stream as an illegal instruction, which has file/line information associated with it. This extra information is stored in the __bug_table section in the ELF file. When the kernel gets an illegal instruction, it first confirms it might possibly be from a BUG (ie, in kernel mode, the right illegal instruction). It then calls report_bug(). This searches __bug_table for a matching instruction pointer, and if found, prints the corresponding file/line information. If report_bug() determines that it wasn't a BUG which caused the trap, it returns BUG_TRAP_TYPE_NONE. Some architectures (powerpc) implement WARN using the same mechanism; if the illegal instruction was the result of a WARN, then report_bug(Q) returns CONFIG_DEBUG_BUGVERBOSE; otherwise it returns BUG_TRAP_TYPE_BUG. lib/bug.c keeps a list of loaded modules which can be searched for __bug_table entries. The architecture must call module_bug_finalize()/module_bug_cleanup() from its corresponding module_finalize/cleanup functions. Unsetting CONFIG_DEBUG_BUGVERBOSE will reduce the kernel size by some amount. At the very least, filename and line information will not be recorded for each but, but architectures may decide to store no extra information per BUG at all. Unfortunately, gcc doesn't have a general way to mark an asm() as noreturn, so architectures will generally have to include an infinite loop (or similar) in the BUG code, so that gcc knows execution won't continue beyond that point. gcc does have a __builtin_trap() operator which may be useful to achieve the same effect, unfortunately it cannot be used to actually implement the BUG itself, because there's no way to get the instruction's address for use in generating the __bug_table entry. [randy.dunlap@oracle.com: Handle BUG=n, GENERIC_BUG=n to prevent build errors] [bunk@stusta.de: include/linux/bug.h must always #include <linux/module.h] Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Andi Kleen <ak@muc.de> Cc: Hugh Dickens <hugh@veritas.com> Cc: Michael Ellerman <michael@ellerman.id.au> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-08 18:36:19 +08:00
struct list_head bug_list;
struct bug_entry *bug_table;
#endif
#ifdef CONFIG_KALLSYMS
modules: fix longstanding /proc/kallsyms vs module insertion race. For CONFIG_KALLSYMS, we keep two symbol tables and two string tables. There's one full copy, marked SHF_ALLOC and laid out at the end of the module's init section. There's also a cut-down version that only contains core symbols and strings, and lives in the module's core section. After module init (and before we free the module memory), we switch the mod->symtab, mod->num_symtab and mod->strtab to point to the core versions. We do this under the module_mutex. However, kallsyms doesn't take the module_mutex: it uses preempt_disable() and rcu tricks to walk through the modules, because it's used in the oops path. It's also used in /proc/kallsyms. There's nothing atomic about the change of these variables, so we can get the old (larger!) num_symtab and the new symtab pointer; in fact this is what I saw when trying to reproduce. By grouping these variables together, we can use a carefully-dereferenced pointer to ensure we always get one or the other (the free of the module init section is already done in an RCU callback, so that's safe). We allocate the init one at the end of the module init section, and keep the core one inside the struct module itself (it could also have been allocated at the end of the module core, but that's probably overkill). Reported-by: Weilong Chen <chenweilong@huawei.com> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=111541 Cc: stable@kernel.org Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2016-02-03 14:25:26 +08:00
/* Protected by RCU and/or module_mutex: use rcu_dereference() */
struct mod_kallsyms __rcu *kallsyms;
modules: fix longstanding /proc/kallsyms vs module insertion race. For CONFIG_KALLSYMS, we keep two symbol tables and two string tables. There's one full copy, marked SHF_ALLOC and laid out at the end of the module's init section. There's also a cut-down version that only contains core symbols and strings, and lives in the module's core section. After module init (and before we free the module memory), we switch the mod->symtab, mod->num_symtab and mod->strtab to point to the core versions. We do this under the module_mutex. However, kallsyms doesn't take the module_mutex: it uses preempt_disable() and rcu tricks to walk through the modules, because it's used in the oops path. It's also used in /proc/kallsyms. There's nothing atomic about the change of these variables, so we can get the old (larger!) num_symtab and the new symtab pointer; in fact this is what I saw when trying to reproduce. By grouping these variables together, we can use a carefully-dereferenced pointer to ensure we always get one or the other (the free of the module init section is already done in an RCU callback, so that's safe). We allocate the init one at the end of the module init section, and keep the core one inside the struct module itself (it could also have been allocated at the end of the module core, but that's probably overkill). Reported-by: Weilong Chen <chenweilong@huawei.com> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=111541 Cc: stable@kernel.org Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2016-02-03 14:25:26 +08:00
struct mod_kallsyms core_kallsyms;
/* Section attributes */
struct module_sect_attrs *sect_attrs;
/* Notes attributes */
struct module_notes_attrs *notes_attrs;
#endif
/* The command line arguments (may be mangled). People like
keeping pointers to this stuff */
char *args;
#ifdef CONFIG_SMP
/* Per-cpu data. */
void __percpu *percpu;
unsigned int percpu_size;
#endif
tracing: Kernel Tracepoints Implementation of kernel tracepoints. Inspired from the Linux Kernel Markers. Allows complete typing verification by declaring both tracing statement inline functions and probe registration/unregistration static inline functions within the same macro "DEFINE_TRACE". No format string is required. See the tracepoint Documentation and Samples patches for usage examples. Taken from the documentation patch : "A tracepoint placed in code provides a hook to call a function (probe) that you can provide at runtime. A tracepoint can be "on" (a probe is connected to it) or "off" (no probe is attached). When a tracepoint is "off" it has no effect, except for adding a tiny time penalty (checking a condition for a branch) and space penalty (adding a few bytes for the function call at the end of the instrumented function and adds a data structure in a separate section). When a tracepoint is "on", the function you provide is called each time the tracepoint is executed, in the execution context of the caller. When the function provided ends its execution, it returns to the caller (continuing from the tracepoint site). You can put tracepoints at important locations in the code. They are lightweight hooks that can pass an arbitrary number of parameters, which prototypes are described in a tracepoint declaration placed in a header file." Addition and removal of tracepoints is synchronized by RCU using the scheduler (and preempt_disable) as guarantees to find a quiescent state (this is really RCU "classic"). The update side uses rcu_barrier_sched() with call_rcu_sched() and the read/execute side uses "preempt_disable()/preempt_enable()". We make sure the previous array containing probes, which has been scheduled for deletion by the rcu callback, is indeed freed before we proceed to the next update. It therefore limits the rate of modification of a single tracepoint to one update per RCU period. The objective here is to permit fast batch add/removal of probes on _different_ tracepoints. Changelog : - Use #name ":" #proto as string to identify the tracepoint in the tracepoint table. This will make sure not type mismatch happens due to connexion of a probe with the wrong type to a tracepoint declared with the same name in a different header. - Add tracepoint_entry_free_old. - Change __TO_TRACE to get rid of the 'i' iterator. Masami Hiramatsu <mhiramat@redhat.com> : Tested on x86-64. Performance impact of a tracepoint : same as markers, except that it adds about 70 bytes of instructions in an unlikely branch of each instrumented function (the for loop, the stack setup and the function call). It currently adds a memory read, a test and a conditional branch at the instrumentation site (in the hot path). Immediate values will eventually change this into a load immediate, test and branch, which removes the memory read which will make the i-cache impact smaller (changing the memory read for a load immediate removes 3-4 bytes per site on x86_32 (depending on mov prefixes), or 7-8 bytes on x86_64, it also saves the d-cache hit). About the performance impact of tracepoints (which is comparable to markers), even without immediate values optimizations, tests done by Hideo Aoki on ia64 show no regression. His test case was using hackbench on a kernel where scheduler instrumentation (about 5 events in code scheduler code) was added. Quoting Hideo Aoki about Markers : I evaluated overhead of kernel marker using linux-2.6-sched-fixes git tree, which includes several markers for LTTng, using an ia64 server. While the immediate trace mark feature isn't implemented on ia64, there is no major performance regression. So, I think that we don't have any issues to propose merging marker point patches into Linus's tree from the viewpoint of performance impact. I prepared two kernels to evaluate. The first one was compiled without CONFIG_MARKERS. The second one was enabled CONFIG_MARKERS. I downloaded the original hackbench from the following URL: http://devresources.linux-foundation.org/craiger/hackbench/src/hackbench.c I ran hackbench 5 times in each condition and calculated the average and difference between the kernels. The parameter of hackbench: every 50 from 50 to 800 The number of CPUs of the server: 2, 4, and 8 Below is the results. As you can see, major performance regression wasn't found in any case. Even if number of processes increases, differences between marker-enabled kernel and marker- disabled kernel doesn't increase. Moreover, if number of CPUs increases, the differences doesn't increase either. Curiously, marker-enabled kernel is better than marker-disabled kernel in more than half cases, although I guess it comes from the difference of memory access pattern. * 2 CPUs Number of | without | with | diff | diff | processes | Marker [Sec] | Marker [Sec] | [Sec] | [%] | -------------------------------------------------------------- 50 | 4.811 | 4.872 | +0.061 | +1.27 | 100 | 9.854 | 10.309 | +0.454 | +4.61 | 150 | 15.602 | 15.040 | -0.562 | -3.6 | 200 | 20.489 | 20.380 | -0.109 | -0.53 | 250 | 25.798 | 25.652 | -0.146 | -0.56 | 300 | 31.260 | 30.797 | -0.463 | -1.48 | 350 | 36.121 | 35.770 | -0.351 | -0.97 | 400 | 42.288 | 42.102 | -0.186 | -0.44 | 450 | 47.778 | 47.253 | -0.526 | -1.1 | 500 | 51.953 | 52.278 | +0.325 | +0.63 | 550 | 58.401 | 57.700 | -0.701 | -1.2 | 600 | 63.334 | 63.222 | -0.112 | -0.18 | 650 | 68.816 | 68.511 | -0.306 | -0.44 | 700 | 74.667 | 74.088 | -0.579 | -0.78 | 750 | 78.612 | 79.582 | +0.970 | +1.23 | 800 | 85.431 | 85.263 | -0.168 | -0.2 | -------------------------------------------------------------- * 4 CPUs Number of | without | with | diff | diff | processes | Marker [Sec] | Marker [Sec] | [Sec] | [%] | -------------------------------------------------------------- 50 | 2.586 | 2.584 | -0.003 | -0.1 | 100 | 5.254 | 5.283 | +0.030 | +0.56 | 150 | 8.012 | 8.074 | +0.061 | +0.76 | 200 | 11.172 | 11.000 | -0.172 | -1.54 | 250 | 13.917 | 14.036 | +0.119 | +0.86 | 300 | 16.905 | 16.543 | -0.362 | -2.14 | 350 | 19.901 | 20.036 | +0.135 | +0.68 | 400 | 22.908 | 23.094 | +0.186 | +0.81 | 450 | 26.273 | 26.101 | -0.172 | -0.66 | 500 | 29.554 | 29.092 | -0.461 | -1.56 | 550 | 32.377 | 32.274 | -0.103 | -0.32 | 600 | 35.855 | 35.322 | -0.533 | -1.49 | 650 | 39.192 | 38.388 | -0.804 | -2.05 | 700 | 41.744 | 41.719 | -0.025 | -0.06 | 750 | 45.016 | 44.496 | -0.520 | -1.16 | 800 | 48.212 | 47.603 | -0.609 | -1.26 | -------------------------------------------------------------- * 8 CPUs Number of | without | with | diff | diff | processes | Marker [Sec] | Marker [Sec] | [Sec] | [%] | -------------------------------------------------------------- 50 | 2.094 | 2.072 | -0.022 | -1.07 | 100 | 4.162 | 4.273 | +0.111 | +2.66 | 150 | 6.485 | 6.540 | +0.055 | +0.84 | 200 | 8.556 | 8.478 | -0.078 | -0.91 | 250 | 10.458 | 10.258 | -0.200 | -1.91 | 300 | 12.425 | 12.750 | +0.325 | +2.62 | 350 | 14.807 | 14.839 | +0.032 | +0.22 | 400 | 16.801 | 16.959 | +0.158 | +0.94 | 450 | 19.478 | 19.009 | -0.470 | -2.41 | 500 | 21.296 | 21.504 | +0.208 | +0.98 | 550 | 23.842 | 23.979 | +0.137 | +0.57 | 600 | 26.309 | 26.111 | -0.198 | -0.75 | 650 | 28.705 | 28.446 | -0.259 | -0.9 | 700 | 31.233 | 31.394 | +0.161 | +0.52 | 750 | 34.064 | 33.720 | -0.344 | -1.01 | 800 | 36.320 | 36.114 | -0.206 | -0.57 | -------------------------------------------------------------- Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: 'Peter Zijlstra' <peterz@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-19 00:16:16 +08:00
#ifdef CONFIG_TRACEPOINTS
unsigned int num_tracepoints;
tracepoint: Fix tracepoint array element size mismatch commit 46e0c9be206f ("kernel: tracepoints: add support for relative references") changes the layout of the __tracepoint_ptrs section on architectures supporting relative references. However, it does so without turning struct tracepoint * const into const int elsewhere in the tracepoint code, which has the following side-effect: Setting mod->num_tracepoints is done in by module.c: mod->tracepoints_ptrs = section_objs(info, "__tracepoints_ptrs", sizeof(*mod->tracepoints_ptrs), &mod->num_tracepoints); Basically, since sizeof(*mod->tracepoints_ptrs) is a pointer size (rather than sizeof(int)), num_tracepoints is erroneously set to half the size it should be on 64-bit arch. So a module with an odd number of tracepoints misses the last tracepoint due to effect of integer division. So in the module going notifier: for_each_tracepoint_range(mod->tracepoints_ptrs, mod->tracepoints_ptrs + mod->num_tracepoints, tp_module_going_check_quiescent, NULL); the expression (mod->tracepoints_ptrs + mod->num_tracepoints) actually evaluates to something within the bounds of the array, but miss the last tracepoint if the number of tracepoints is odd on 64-bit arch. Fix this by introducing a new typedef: tracepoint_ptr_t, which is either "const int" on architectures that have PREL32 relocations, or "struct tracepoint * const" on architectures that does not have this feature. Also provide a new tracepoint_ptr_defer() static inline to encapsulate deferencing this type rather than duplicate code and ugly idefs within the for_each_tracepoint_range() implementation. This issue appears in 4.19-rc kernels, and should ideally be fixed before the end of the rc cycle. Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Acked-by: Jessica Yu <jeyu@kernel.org> Link: http://lkml.kernel.org/r/20181013191050.22389-1-mathieu.desnoyers@efficios.com Link: http://lkml.kernel.org/r/20180704083651.24360-7-ard.biesheuvel@linaro.org Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Ingo Molnar <mingo@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: James Morris <james.morris@microsoft.com> Cc: James Morris <jmorris@namei.org> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Kees Cook <keescook@chromium.org> Cc: Nicolas Pitre <nico@linaro.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Russell King <linux@armlinux.org.uk> Cc: "Serge E. Hallyn" <serge@hallyn.com> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Thomas Garnier <thgarnie@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Will Deacon <will.deacon@arm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
2018-10-14 03:10:50 +08:00
tracepoint_ptr_t *tracepoints_ptrs;
tracing: Kernel Tracepoints Implementation of kernel tracepoints. Inspired from the Linux Kernel Markers. Allows complete typing verification by declaring both tracing statement inline functions and probe registration/unregistration static inline functions within the same macro "DEFINE_TRACE". No format string is required. See the tracepoint Documentation and Samples patches for usage examples. Taken from the documentation patch : "A tracepoint placed in code provides a hook to call a function (probe) that you can provide at runtime. A tracepoint can be "on" (a probe is connected to it) or "off" (no probe is attached). When a tracepoint is "off" it has no effect, except for adding a tiny time penalty (checking a condition for a branch) and space penalty (adding a few bytes for the function call at the end of the instrumented function and adds a data structure in a separate section). When a tracepoint is "on", the function you provide is called each time the tracepoint is executed, in the execution context of the caller. When the function provided ends its execution, it returns to the caller (continuing from the tracepoint site). You can put tracepoints at important locations in the code. They are lightweight hooks that can pass an arbitrary number of parameters, which prototypes are described in a tracepoint declaration placed in a header file." Addition and removal of tracepoints is synchronized by RCU using the scheduler (and preempt_disable) as guarantees to find a quiescent state (this is really RCU "classic"). The update side uses rcu_barrier_sched() with call_rcu_sched() and the read/execute side uses "preempt_disable()/preempt_enable()". We make sure the previous array containing probes, which has been scheduled for deletion by the rcu callback, is indeed freed before we proceed to the next update. It therefore limits the rate of modification of a single tracepoint to one update per RCU period. The objective here is to permit fast batch add/removal of probes on _different_ tracepoints. Changelog : - Use #name ":" #proto as string to identify the tracepoint in the tracepoint table. This will make sure not type mismatch happens due to connexion of a probe with the wrong type to a tracepoint declared with the same name in a different header. - Add tracepoint_entry_free_old. - Change __TO_TRACE to get rid of the 'i' iterator. Masami Hiramatsu <mhiramat@redhat.com> : Tested on x86-64. Performance impact of a tracepoint : same as markers, except that it adds about 70 bytes of instructions in an unlikely branch of each instrumented function (the for loop, the stack setup and the function call). It currently adds a memory read, a test and a conditional branch at the instrumentation site (in the hot path). Immediate values will eventually change this into a load immediate, test and branch, which removes the memory read which will make the i-cache impact smaller (changing the memory read for a load immediate removes 3-4 bytes per site on x86_32 (depending on mov prefixes), or 7-8 bytes on x86_64, it also saves the d-cache hit). About the performance impact of tracepoints (which is comparable to markers), even without immediate values optimizations, tests done by Hideo Aoki on ia64 show no regression. His test case was using hackbench on a kernel where scheduler instrumentation (about 5 events in code scheduler code) was added. Quoting Hideo Aoki about Markers : I evaluated overhead of kernel marker using linux-2.6-sched-fixes git tree, which includes several markers for LTTng, using an ia64 server. While the immediate trace mark feature isn't implemented on ia64, there is no major performance regression. So, I think that we don't have any issues to propose merging marker point patches into Linus's tree from the viewpoint of performance impact. I prepared two kernels to evaluate. The first one was compiled without CONFIG_MARKERS. The second one was enabled CONFIG_MARKERS. I downloaded the original hackbench from the following URL: http://devresources.linux-foundation.org/craiger/hackbench/src/hackbench.c I ran hackbench 5 times in each condition and calculated the average and difference between the kernels. The parameter of hackbench: every 50 from 50 to 800 The number of CPUs of the server: 2, 4, and 8 Below is the results. As you can see, major performance regression wasn't found in any case. Even if number of processes increases, differences between marker-enabled kernel and marker- disabled kernel doesn't increase. Moreover, if number of CPUs increases, the differences doesn't increase either. Curiously, marker-enabled kernel is better than marker-disabled kernel in more than half cases, although I guess it comes from the difference of memory access pattern. * 2 CPUs Number of | without | with | diff | diff | processes | Marker [Sec] | Marker [Sec] | [Sec] | [%] | -------------------------------------------------------------- 50 | 4.811 | 4.872 | +0.061 | +1.27 | 100 | 9.854 | 10.309 | +0.454 | +4.61 | 150 | 15.602 | 15.040 | -0.562 | -3.6 | 200 | 20.489 | 20.380 | -0.109 | -0.53 | 250 | 25.798 | 25.652 | -0.146 | -0.56 | 300 | 31.260 | 30.797 | -0.463 | -1.48 | 350 | 36.121 | 35.770 | -0.351 | -0.97 | 400 | 42.288 | 42.102 | -0.186 | -0.44 | 450 | 47.778 | 47.253 | -0.526 | -1.1 | 500 | 51.953 | 52.278 | +0.325 | +0.63 | 550 | 58.401 | 57.700 | -0.701 | -1.2 | 600 | 63.334 | 63.222 | -0.112 | -0.18 | 650 | 68.816 | 68.511 | -0.306 | -0.44 | 700 | 74.667 | 74.088 | -0.579 | -0.78 | 750 | 78.612 | 79.582 | +0.970 | +1.23 | 800 | 85.431 | 85.263 | -0.168 | -0.2 | -------------------------------------------------------------- * 4 CPUs Number of | without | with | diff | diff | processes | Marker [Sec] | Marker [Sec] | [Sec] | [%] | -------------------------------------------------------------- 50 | 2.586 | 2.584 | -0.003 | -0.1 | 100 | 5.254 | 5.283 | +0.030 | +0.56 | 150 | 8.012 | 8.074 | +0.061 | +0.76 | 200 | 11.172 | 11.000 | -0.172 | -1.54 | 250 | 13.917 | 14.036 | +0.119 | +0.86 | 300 | 16.905 | 16.543 | -0.362 | -2.14 | 350 | 19.901 | 20.036 | +0.135 | +0.68 | 400 | 22.908 | 23.094 | +0.186 | +0.81 | 450 | 26.273 | 26.101 | -0.172 | -0.66 | 500 | 29.554 | 29.092 | -0.461 | -1.56 | 550 | 32.377 | 32.274 | -0.103 | -0.32 | 600 | 35.855 | 35.322 | -0.533 | -1.49 | 650 | 39.192 | 38.388 | -0.804 | -2.05 | 700 | 41.744 | 41.719 | -0.025 | -0.06 | 750 | 45.016 | 44.496 | -0.520 | -1.16 | 800 | 48.212 | 47.603 | -0.609 | -1.26 | -------------------------------------------------------------- * 8 CPUs Number of | without | with | diff | diff | processes | Marker [Sec] | Marker [Sec] | [Sec] | [%] | -------------------------------------------------------------- 50 | 2.094 | 2.072 | -0.022 | -1.07 | 100 | 4.162 | 4.273 | +0.111 | +2.66 | 150 | 6.485 | 6.540 | +0.055 | +0.84 | 200 | 8.556 | 8.478 | -0.078 | -0.91 | 250 | 10.458 | 10.258 | -0.200 | -1.91 | 300 | 12.425 | 12.750 | +0.325 | +2.62 | 350 | 14.807 | 14.839 | +0.032 | +0.22 | 400 | 16.801 | 16.959 | +0.158 | +0.94 | 450 | 19.478 | 19.009 | -0.470 | -2.41 | 500 | 21.296 | 21.504 | +0.208 | +0.98 | 550 | 23.842 | 23.979 | +0.137 | +0.57 | 600 | 26.309 | 26.111 | -0.198 | -0.75 | 650 | 28.705 | 28.446 | -0.259 | -0.9 | 700 | 31.233 | 31.394 | +0.161 | +0.52 | 750 | 34.064 | 33.720 | -0.344 | -1.01 | 800 | 36.320 | 36.114 | -0.206 | -0.57 | -------------------------------------------------------------- Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Acked-by: Masami Hiramatsu <mhiramat@redhat.com> Acked-by: 'Peter Zijlstra' <peterz@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-19 00:16:16 +08:00
#endif
srcu: Allocate per-CPU data for DEFINE_SRCU() in modules Adding DEFINE_SRCU() or DEFINE_STATIC_SRCU() to a loadable module requires that the size of the reserved region be increased, which is not something we want to be doing all that often. One approach would be to require that loadable modules define an srcu_struct and invoke init_srcu_struct() from their module_init function and cleanup_srcu_struct() from their module_exit function. However, this is more than a bit user unfriendly. This commit therefore creates an ___srcu_struct_ptrs linker section, and pointers to srcu_struct structures created by DEFINE_SRCU() and DEFINE_STATIC_SRCU() within a module are placed into that module's ___srcu_struct_ptrs section. The required init_srcu_struct() and cleanup_srcu_struct() functions are then automatically invoked as needed when that module is loaded and unloaded, thus allowing modules to continue to use DEFINE_SRCU() and DEFINE_STATIC_SRCU() while avoiding the need to increase the size of the reserved region. Many of the algorithms and some of the code was cheerfully cherry-picked from other code making use of linker sections, perhaps most notably from tracepoints. All bugs are nevertheless the sole property of the author. Suggested-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> [ paulmck: Use __section() and use "default" in srcu_module_notify()'s "switch" statement as suggested by Joel Fernandes. ] Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com> Tested-by: Joel Fernandes (Google) <joel@joelfernandes.org>
2019-04-06 07:15:00 +08:00
#ifdef CONFIG_TREE_SRCU
unsigned int num_srcu_structs;
struct srcu_struct **srcu_struct_ptrs;
#endif
#ifdef CONFIG_BPF_EVENTS
unsigned int num_bpf_raw_events;
struct bpf_raw_event_map *bpf_raw_events;
#endif
#ifdef CONFIG_JUMP_LABEL
struct jump_entry *jump_entries;
unsigned int num_jump_entries;
#endif
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk() Impact: faster and lighter tracing Now that we have trace_bprintk() which is faster and consume lesser memory than trace_printk() and has the same purpose, we can now drop the old implementation in favour of the binary one from trace_bprintk(), which means we move all the implementation of trace_bprintk() to trace_printk(), so the Api doesn't change except that we must now use trace_seq_bprintk() to print the TRACE_PRINT entries. Some changes result of this: - Previously, trace_bprintk depended of a single tracer and couldn't work without. This tracer has been dropped and the whole implementation of trace_printk() (like the module formats management) is now integrated in the tracing core (comes with CONFIG_TRACING), though we keep the file trace_printk (previously trace_bprintk.c) where we can find the module management. Thus we don't overflow trace.c - changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries. - change a bit trace_printk/trace_vprintk macros to support non-builtin formats constants, and fix 'const' qualifiers warnings. But this is all transparent for developers. - etc... V2: - Rebase against last changes - Fix mispell on the changelog V3: - Rebase against last changes (moving trace_printk() to kernel.h) Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1236356510-8381-5-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-07 00:21:49 +08:00
#ifdef CONFIG_TRACING
unsigned int num_trace_bprintk_fmt;
const char **trace_bprintk_fmt_start;
#endif
#ifdef CONFIG_EVENT_TRACING
struct trace_event_call **trace_events;
unsigned int num_trace_events;
struct trace_eval_map **trace_evals;
unsigned int num_trace_evals;
#endif
#ifdef CONFIG_FTRACE_MCOUNT_RECORD
unsigned int num_ftrace_callsites;
unsigned long *ftrace_callsites;
#endif
livepatch: Fix subtle race with coming and going modules There is a notifier that handles live patches for coming and going modules. It takes klp_mutex lock to avoid races with coming and going patches but it does not keep the lock all the time. Therefore the following races are possible: 1. The notifier is called sometime in STATE_MODULE_COMING. The module is visible by find_module() in this state all the time. It means that new patch can be registered and enabled even before the notifier is called. It might create wrong order of stacked patches, see below for an example. 2. New patch could still see the module in the GOING state even after the notifier has been called. It will try to initialize the related object structures but the module could disappear at any time. There will stay mess in the structures. It might even cause an invalid memory access. This patch solves the problem by adding a boolean variable into struct module. The value is true after the coming and before the going handler is called. New patches need to be applied when the value is true and they need to ignore the module when the value is false. Note that we need to know state of all modules on the system. The races are related to new patches. Therefore we do not know what modules will get patched. Also note that we could not simply ignore going modules. The code from the module could be called even in the GOING state until mod->exit() finishes. If we start supporting patches with semantic changes between function calls, we need to apply new patches to any still usable code. See below for an example. Finally note that the patch solves only the situation when a new patch is registered. There are no such problems when the patch is being removed. It does not matter who disable the patch first, whether the normal disable_patch() or the module notifier. There is nothing to do once the patch is disabled. Alternative solutions: ====================== + reject new patches when a patched module is coming or going; this is ugly + wait with adding new patch until the module leaves the COMING and GOING states; this might be dangerous and complicated; we would need to release kgr_lock in the middle of the patch registration to avoid a deadlock with the coming and going handlers; also we might need a waitqueue for each module which seems to be even bigger overhead than the boolean + stop modules from entering COMING and GOING states; wait until modules leave these states when they are already there; looks complicated; we would need to ignore the module that asked to stop the others to avoid a deadlock; also it is unclear what to do when two modules asked to stop others and both are in COMING state (situation when two new patches are applied) + always register/enable new patches and fix up the potential mess (registered patches order) in klp_module_init(); this is nasty and prone to regressions in the future development + add another MODULE_STATE where the kallsyms are visible but the module is not used yet; this looks too complex; the module states are checked on "many" locations Example of patch stacking breakage: =================================== The notifier could _not_ _simply_ ignore already initialized module objects. For example, let's have three patches (P1, P2, P3) for functions a() and b() where a() is from vmcore and b() is from a module M. Something like: a() b() P1 a1() b1() P2 a2() b2() P3 a3() b3(3) If you load the module M after all patches are registered and enabled. The ftrace ops for function a() and b() has listed the functions in this order: ops_a->func_stack -> list(a3,a2,a1) ops_b->func_stack -> list(b3,b2,b1) , so the pointer to b3() is the first and will be used. Then you might have the following scenario. Let's start with state when patches P1 and P2 are registered and enabled but the module M is not loaded. Then ftrace ops for b() does not exist. Then we get into the following race: CPU0 CPU1 load_module(M) complete_formation() mod->state = MODULE_STATE_COMING; mutex_unlock(&module_mutex); klp_register_patch(P3); klp_enable_patch(P3); # STATE 1 klp_module_notify(M) klp_module_notify_coming(P1); klp_module_notify_coming(P2); klp_module_notify_coming(P3); # STATE 2 The ftrace ops for a() and b() then looks: STATE1: ops_a->func_stack -> list(a3,a2,a1); ops_b->func_stack -> list(b3); STATE2: ops_a->func_stack -> list(a3,a2,a1); ops_b->func_stack -> list(b2,b1,b3); therefore, b2() is used for the module but a3() is used for vmcore because they were the last added. Example of the race with going modules: ======================================= CPU0 CPU1 delete_module() #SYSCALL try_stop_module() mod->state = MODULE_STATE_GOING; mutex_unlock(&module_mutex); klp_register_patch() klp_enable_patch() #save place to switch universe b() # from module that is going a() # from core (patched) mod->exit(); Note that the function b() can be called until we call mod->exit(). If we do not apply patch against b() because it is in MODULE_STATE_GOING, it will call patched a() with modified semantic and things might get wrong. [jpoimboe@redhat.com: use one boolean instead of two] Signed-off-by: Petr Mladek <pmladek@suse.cz> Acked-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Jiri Kosina <jkosina@suse.cz>
2015-03-12 19:55:13 +08:00
#ifdef CONFIG_LIVEPATCH
module: preserve Elf information for livepatch modules For livepatch modules, copy Elf section, symbol, and string information from the load_info struct in the module loader. Persist copies of the original symbol table and string table. Livepatch manages its own relocation sections in order to reuse module loader code to write relocations. Livepatch modules must preserve Elf information such as section indices in order to apply livepatch relocation sections using the module loader's apply_relocate_add() function. In order to apply livepatch relocation sections, livepatch modules must keep a complete copy of their original symbol table in memory. Normally, a stripped down copy of a module's symbol table (containing only "core" symbols) is made available through module->core_symtab. But for livepatch modules, the symbol table copied into memory on module load must be exactly the same as the symbol table produced when the patch module was compiled. This is because the relocations in each livepatch relocation section refer to their respective symbols with their symbol indices, and the original symbol indices (and thus the symtab ordering) must be preserved in order for apply_relocate_add() to find the right symbol. Signed-off-by: Jessica Yu <jeyu@redhat.com> Reviewed-by: Miroslav Benes <mbenes@suse.cz> Acked-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Rusty Russell <rusty@rustcorp.com.au> Reviewed-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Jiri Kosina <jkosina@suse.cz>
2016-03-23 08:03:16 +08:00
bool klp; /* Is this a livepatch module? */
livepatch: Fix subtle race with coming and going modules There is a notifier that handles live patches for coming and going modules. It takes klp_mutex lock to avoid races with coming and going patches but it does not keep the lock all the time. Therefore the following races are possible: 1. The notifier is called sometime in STATE_MODULE_COMING. The module is visible by find_module() in this state all the time. It means that new patch can be registered and enabled even before the notifier is called. It might create wrong order of stacked patches, see below for an example. 2. New patch could still see the module in the GOING state even after the notifier has been called. It will try to initialize the related object structures but the module could disappear at any time. There will stay mess in the structures. It might even cause an invalid memory access. This patch solves the problem by adding a boolean variable into struct module. The value is true after the coming and before the going handler is called. New patches need to be applied when the value is true and they need to ignore the module when the value is false. Note that we need to know state of all modules on the system. The races are related to new patches. Therefore we do not know what modules will get patched. Also note that we could not simply ignore going modules. The code from the module could be called even in the GOING state until mod->exit() finishes. If we start supporting patches with semantic changes between function calls, we need to apply new patches to any still usable code. See below for an example. Finally note that the patch solves only the situation when a new patch is registered. There are no such problems when the patch is being removed. It does not matter who disable the patch first, whether the normal disable_patch() or the module notifier. There is nothing to do once the patch is disabled. Alternative solutions: ====================== + reject new patches when a patched module is coming or going; this is ugly + wait with adding new patch until the module leaves the COMING and GOING states; this might be dangerous and complicated; we would need to release kgr_lock in the middle of the patch registration to avoid a deadlock with the coming and going handlers; also we might need a waitqueue for each module which seems to be even bigger overhead than the boolean + stop modules from entering COMING and GOING states; wait until modules leave these states when they are already there; looks complicated; we would need to ignore the module that asked to stop the others to avoid a deadlock; also it is unclear what to do when two modules asked to stop others and both are in COMING state (situation when two new patches are applied) + always register/enable new patches and fix up the potential mess (registered patches order) in klp_module_init(); this is nasty and prone to regressions in the future development + add another MODULE_STATE where the kallsyms are visible but the module is not used yet; this looks too complex; the module states are checked on "many" locations Example of patch stacking breakage: =================================== The notifier could _not_ _simply_ ignore already initialized module objects. For example, let's have three patches (P1, P2, P3) for functions a() and b() where a() is from vmcore and b() is from a module M. Something like: a() b() P1 a1() b1() P2 a2() b2() P3 a3() b3(3) If you load the module M after all patches are registered and enabled. The ftrace ops for function a() and b() has listed the functions in this order: ops_a->func_stack -> list(a3,a2,a1) ops_b->func_stack -> list(b3,b2,b1) , so the pointer to b3() is the first and will be used. Then you might have the following scenario. Let's start with state when patches P1 and P2 are registered and enabled but the module M is not loaded. Then ftrace ops for b() does not exist. Then we get into the following race: CPU0 CPU1 load_module(M) complete_formation() mod->state = MODULE_STATE_COMING; mutex_unlock(&module_mutex); klp_register_patch(P3); klp_enable_patch(P3); # STATE 1 klp_module_notify(M) klp_module_notify_coming(P1); klp_module_notify_coming(P2); klp_module_notify_coming(P3); # STATE 2 The ftrace ops for a() and b() then looks: STATE1: ops_a->func_stack -> list(a3,a2,a1); ops_b->func_stack -> list(b3); STATE2: ops_a->func_stack -> list(a3,a2,a1); ops_b->func_stack -> list(b2,b1,b3); therefore, b2() is used for the module but a3() is used for vmcore because they were the last added. Example of the race with going modules: ======================================= CPU0 CPU1 delete_module() #SYSCALL try_stop_module() mod->state = MODULE_STATE_GOING; mutex_unlock(&module_mutex); klp_register_patch() klp_enable_patch() #save place to switch universe b() # from module that is going a() # from core (patched) mod->exit(); Note that the function b() can be called until we call mod->exit(). If we do not apply patch against b() because it is in MODULE_STATE_GOING, it will call patched a() with modified semantic and things might get wrong. [jpoimboe@redhat.com: use one boolean instead of two] Signed-off-by: Petr Mladek <pmladek@suse.cz> Acked-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Jiri Kosina <jkosina@suse.cz>
2015-03-12 19:55:13 +08:00
bool klp_alive;
module: preserve Elf information for livepatch modules For livepatch modules, copy Elf section, symbol, and string information from the load_info struct in the module loader. Persist copies of the original symbol table and string table. Livepatch manages its own relocation sections in order to reuse module loader code to write relocations. Livepatch modules must preserve Elf information such as section indices in order to apply livepatch relocation sections using the module loader's apply_relocate_add() function. In order to apply livepatch relocation sections, livepatch modules must keep a complete copy of their original symbol table in memory. Normally, a stripped down copy of a module's symbol table (containing only "core" symbols) is made available through module->core_symtab. But for livepatch modules, the symbol table copied into memory on module load must be exactly the same as the symbol table produced when the patch module was compiled. This is because the relocations in each livepatch relocation section refer to their respective symbols with their symbol indices, and the original symbol indices (and thus the symtab ordering) must be preserved in order for apply_relocate_add() to find the right symbol. Signed-off-by: Jessica Yu <jeyu@redhat.com> Reviewed-by: Miroslav Benes <mbenes@suse.cz> Acked-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Rusty Russell <rusty@rustcorp.com.au> Reviewed-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Jiri Kosina <jkosina@suse.cz>
2016-03-23 08:03:16 +08:00
/* Elf information */
struct klp_modinfo *klp_info;
livepatch: Fix subtle race with coming and going modules There is a notifier that handles live patches for coming and going modules. It takes klp_mutex lock to avoid races with coming and going patches but it does not keep the lock all the time. Therefore the following races are possible: 1. The notifier is called sometime in STATE_MODULE_COMING. The module is visible by find_module() in this state all the time. It means that new patch can be registered and enabled even before the notifier is called. It might create wrong order of stacked patches, see below for an example. 2. New patch could still see the module in the GOING state even after the notifier has been called. It will try to initialize the related object structures but the module could disappear at any time. There will stay mess in the structures. It might even cause an invalid memory access. This patch solves the problem by adding a boolean variable into struct module. The value is true after the coming and before the going handler is called. New patches need to be applied when the value is true and they need to ignore the module when the value is false. Note that we need to know state of all modules on the system. The races are related to new patches. Therefore we do not know what modules will get patched. Also note that we could not simply ignore going modules. The code from the module could be called even in the GOING state until mod->exit() finishes. If we start supporting patches with semantic changes between function calls, we need to apply new patches to any still usable code. See below for an example. Finally note that the patch solves only the situation when a new patch is registered. There are no such problems when the patch is being removed. It does not matter who disable the patch first, whether the normal disable_patch() or the module notifier. There is nothing to do once the patch is disabled. Alternative solutions: ====================== + reject new patches when a patched module is coming or going; this is ugly + wait with adding new patch until the module leaves the COMING and GOING states; this might be dangerous and complicated; we would need to release kgr_lock in the middle of the patch registration to avoid a deadlock with the coming and going handlers; also we might need a waitqueue for each module which seems to be even bigger overhead than the boolean + stop modules from entering COMING and GOING states; wait until modules leave these states when they are already there; looks complicated; we would need to ignore the module that asked to stop the others to avoid a deadlock; also it is unclear what to do when two modules asked to stop others and both are in COMING state (situation when two new patches are applied) + always register/enable new patches and fix up the potential mess (registered patches order) in klp_module_init(); this is nasty and prone to regressions in the future development + add another MODULE_STATE where the kallsyms are visible but the module is not used yet; this looks too complex; the module states are checked on "many" locations Example of patch stacking breakage: =================================== The notifier could _not_ _simply_ ignore already initialized module objects. For example, let's have three patches (P1, P2, P3) for functions a() and b() where a() is from vmcore and b() is from a module M. Something like: a() b() P1 a1() b1() P2 a2() b2() P3 a3() b3(3) If you load the module M after all patches are registered and enabled. The ftrace ops for function a() and b() has listed the functions in this order: ops_a->func_stack -> list(a3,a2,a1) ops_b->func_stack -> list(b3,b2,b1) , so the pointer to b3() is the first and will be used. Then you might have the following scenario. Let's start with state when patches P1 and P2 are registered and enabled but the module M is not loaded. Then ftrace ops for b() does not exist. Then we get into the following race: CPU0 CPU1 load_module(M) complete_formation() mod->state = MODULE_STATE_COMING; mutex_unlock(&module_mutex); klp_register_patch(P3); klp_enable_patch(P3); # STATE 1 klp_module_notify(M) klp_module_notify_coming(P1); klp_module_notify_coming(P2); klp_module_notify_coming(P3); # STATE 2 The ftrace ops for a() and b() then looks: STATE1: ops_a->func_stack -> list(a3,a2,a1); ops_b->func_stack -> list(b3); STATE2: ops_a->func_stack -> list(a3,a2,a1); ops_b->func_stack -> list(b2,b1,b3); therefore, b2() is used for the module but a3() is used for vmcore because they were the last added. Example of the race with going modules: ======================================= CPU0 CPU1 delete_module() #SYSCALL try_stop_module() mod->state = MODULE_STATE_GOING; mutex_unlock(&module_mutex); klp_register_patch() klp_enable_patch() #save place to switch universe b() # from module that is going a() # from core (patched) mod->exit(); Note that the function b() can be called until we call mod->exit(). If we do not apply patch against b() because it is in MODULE_STATE_GOING, it will call patched a() with modified semantic and things might get wrong. [jpoimboe@redhat.com: use one boolean instead of two] Signed-off-by: Petr Mladek <pmladek@suse.cz> Acked-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Jiri Kosina <jkosina@suse.cz>
2015-03-12 19:55:13 +08:00
#endif
#ifdef CONFIG_MODULE_UNLOAD
/* What modules depend on me? */
struct list_head source_list;
/* What modules do I depend on? */
struct list_head target_list;
/* Destruction function. */
void (*exit)(void);
atomic_t refcnt;
#endif
#ifdef CONFIG_CONSTRUCTORS
/* Constructor functions. */
ctor_fn_t *ctors;
unsigned int num_ctors;
#endif
#ifdef CONFIG_FUNCTION_ERROR_INJECTION
struct error_injection_entry *ei_funcs;
unsigned int num_ei_funcs;
#endif
} ____cacheline_aligned __randomize_layout;
#ifndef MODULE_ARCH_INIT
#define MODULE_ARCH_INIT {}
#endif
ARM: module: Fix function kallsyms on Thumb-2 Thumb-2 functions have the lowest bit set in the symbol value in the symtab. When kallsyms are generated for the vmlinux, the kallsyms are generated from the output of nm, and nm clears the lowest bit. $ arm-linux-gnueabihf-readelf -a vmlinux | grep show_interrupts 95947: 8015dc89 686 FUNC GLOBAL DEFAULT 2 show_interrupts $ arm-linux-gnueabihf-nm vmlinux | grep show_interrupts 8015dc88 T show_interrupts $ cat /proc/kallsyms | grep show_interrupts 8015dc88 T show_interrupts However, for modules, the kallsyms uses the values in the symbol table without modification, so for functions in modules, the lowest bit is set in kallsyms. $ arm-linux-gnueabihf-readelf -a drivers/net/tun.ko | grep tun_get_socket 333: 00002d4d 36 FUNC GLOBAL DEFAULT 1 tun_get_socket $ arm-linux-gnueabihf-nm drivers/net/tun.ko | grep tun_get_socket 00002d4c T tun_get_socket $ cat /proc/kallsyms | grep tun_get_socket 7f802d4d t tun_get_socket [tun] Because of this, the symbol+offset of the crashing instruction shown in oopses is incorrect when the crash is in a module. For example, given a tun_get_socket which starts like this, 00002d4c <tun_get_socket>: 2d4c: 6943 ldr r3, [r0, #20] 2d4e: 4a07 ldr r2, [pc, #28] 2d50: 4293 cmp r3, r2 a crash when tun_get_socket is called with NULL results in: PC is at tun_xdp+0xa3/0xa4 [tun] pc : [<7f802d4c>] As can be seen, the "PC is at" line reports the wrong symbol name, and the symbol+offset will point to the wrong source line if it is passed to gdb. To solve this, add a way for archs to fixup the reading of these module kallsyms values, and use that to clear the lowest bit for function symbols on Thumb-2. After the fix: # cat /proc/kallsyms | grep tun_get_socket 7f802d4c t tun_get_socket [tun] PC is at tun_get_socket+0x0/0x24 [tun] pc : [<7f802d4c>] Signed-off-by: Vincent Whitchurch <vincent.whitchurch@axis.com> Signed-off-by: Jessica Yu <jeyu@kernel.org>
2018-12-15 00:05:55 +08:00
#ifndef HAVE_ARCH_KALLSYMS_SYMBOL_VALUE
static inline unsigned long kallsyms_symbol_value(const Elf_Sym *sym)
{
return sym->st_value;
}
#endif
extern struct mutex module_mutex;
/* FIXME: It'd be nice to isolate modules during init, too, so they
aren't used before they (may) fail. But presently too much code
(IDE & SCSI) require entry into the module during init.*/
static inline bool module_is_live(struct module *mod)
{
return mod->state != MODULE_STATE_GOING;
}
struct module *__module_text_address(unsigned long addr);
struct module *__module_address(unsigned long addr);
bool is_module_address(unsigned long addr);
locking/lockdep: Handle statically initialized PER_CPU locks properly If a PER_CPU struct which contains a spin_lock is statically initialized via: DEFINE_PER_CPU(struct foo, bla) = { .lock = __SPIN_LOCK_UNLOCKED(bla.lock) }; then lockdep assigns a seperate key to each lock because the logic for assigning a key to statically initialized locks is to use the address as the key. With per CPU locks the address is obvioulsy different on each CPU. That's wrong, because all locks should have the same key. To solve this the following modifications are required: 1) Extend the is_kernel/module_percpu_addr() functions to hand back the canonical address of the per CPU address, i.e. the per CPU address minus the per CPU offset. 2) Check the lock address with these functions and if the per CPU check matches use the returned canonical address as the lock key, so all per CPU locks have the same key. 3) Move the static_obj(key) check into look_up_lock_class() so this check can be avoided for statically initialized per CPU locks. That's required because the canonical address fails the static_obj(key) check for obvious reasons. Reported-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> [ Merged Dan's fixups for !MODULES and !SMP into this patch. ] Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Dan Murphy <dmurphy@ti.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20170227143736.pectaimkjkan5kow@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-02-27 22:37:36 +08:00
bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr);
bool is_module_percpu_address(unsigned long addr);
bool is_module_text_address(unsigned long addr);
static inline bool within_module_core(unsigned long addr,
const struct module *mod)
module: add within_module_core() and within_module_init() This series of patches allows kprobes to probe module's __init and __exit functions. This means, you can probe driver initialization and terminating. Currently, kprobes can't probe __init function because these functions are freed after module initialization. And it also can't probe module __exit functions because kprobe increments reference count of target module and user can't unload it. this means __exit functions never be called unless removing probes from the module. To solve both cases, this series of patches introduces GONE flag and sets it when the target code is freed(for this purpose, kprobes hooks MODULE_STATE_* events). This also removes refcount incrementing for allowing user to unload target module. Users can check which probes are GONE by debugfs interface. For taking timing of freeing module's .init text, these also include a patch which adds module's notifier of MODULE_STATE_LIVE event. This patch: Add within_module_core() and within_module_init() for checking whether an address is in the module .init.text section or .text section, and replace within() local inline functions in kernel/module.c with them. kprobes uses these functions to check where the kprobe is inserted. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> Acked-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 06:41:49 +08:00
{
return (unsigned long)mod->core_layout.base <= addr &&
addr < (unsigned long)mod->core_layout.base + mod->core_layout.size;
module: add within_module_core() and within_module_init() This series of patches allows kprobes to probe module's __init and __exit functions. This means, you can probe driver initialization and terminating. Currently, kprobes can't probe __init function because these functions are freed after module initialization. And it also can't probe module __exit functions because kprobe increments reference count of target module and user can't unload it. this means __exit functions never be called unless removing probes from the module. To solve both cases, this series of patches introduces GONE flag and sets it when the target code is freed(for this purpose, kprobes hooks MODULE_STATE_* events). This also removes refcount incrementing for allowing user to unload target module. Users can check which probes are GONE by debugfs interface. For taking timing of freeing module's .init text, these also include a patch which adds module's notifier of MODULE_STATE_LIVE event. This patch: Add within_module_core() and within_module_init() for checking whether an address is in the module .init.text section or .text section, and replace within() local inline functions in kernel/module.c with them. kprobes uses these functions to check where the kprobe is inserted. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> Acked-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 06:41:49 +08:00
}
static inline bool within_module_init(unsigned long addr,
const struct module *mod)
module: add within_module_core() and within_module_init() This series of patches allows kprobes to probe module's __init and __exit functions. This means, you can probe driver initialization and terminating. Currently, kprobes can't probe __init function because these functions are freed after module initialization. And it also can't probe module __exit functions because kprobe increments reference count of target module and user can't unload it. this means __exit functions never be called unless removing probes from the module. To solve both cases, this series of patches introduces GONE flag and sets it when the target code is freed(for this purpose, kprobes hooks MODULE_STATE_* events). This also removes refcount incrementing for allowing user to unload target module. Users can check which probes are GONE by debugfs interface. For taking timing of freeing module's .init text, these also include a patch which adds module's notifier of MODULE_STATE_LIVE event. This patch: Add within_module_core() and within_module_init() for checking whether an address is in the module .init.text section or .text section, and replace within() local inline functions in kernel/module.c with them. kprobes uses these functions to check where the kprobe is inserted. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> Acked-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 06:41:49 +08:00
{
return (unsigned long)mod->init_layout.base <= addr &&
addr < (unsigned long)mod->init_layout.base + mod->init_layout.size;
module: add within_module_core() and within_module_init() This series of patches allows kprobes to probe module's __init and __exit functions. This means, you can probe driver initialization and terminating. Currently, kprobes can't probe __init function because these functions are freed after module initialization. And it also can't probe module __exit functions because kprobe increments reference count of target module and user can't unload it. this means __exit functions never be called unless removing probes from the module. To solve both cases, this series of patches introduces GONE flag and sets it when the target code is freed(for this purpose, kprobes hooks MODULE_STATE_* events). This also removes refcount incrementing for allowing user to unload target module. Users can check which probes are GONE by debugfs interface. For taking timing of freeing module's .init text, these also include a patch which adds module's notifier of MODULE_STATE_LIVE event. This patch: Add within_module_core() and within_module_init() for checking whether an address is in the module .init.text section or .text section, and replace within() local inline functions in kernel/module.c with them. kprobes uses these functions to check where the kprobe is inserted. Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> Acked-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 06:41:49 +08:00
}
static inline bool within_module(unsigned long addr, const struct module *mod)
{
return within_module_init(addr, mod) || within_module_core(addr, mod);
}
/* Search for module by name: must hold module_mutex. */
struct module *find_module(const char *name);
struct symsearch {
const struct kernel_symbol *start, *stop;
modversions: treat symbol CRCs as 32 bit quantities The modversion symbol CRCs are emitted as ELF symbols, which allows us to easily populate the kcrctab sections by relying on the linker to associate each kcrctab slot with the correct value. This has a couple of downsides: - Given that the CRCs are treated as memory addresses, we waste 4 bytes for each CRC on 64 bit architectures, - On architectures that support runtime relocation, a R_<arch>_RELATIVE relocation entry is emitted for each CRC value, which identifies it as a quantity that requires fixing up based on the actual runtime load offset of the kernel. This results in corrupted CRCs unless we explicitly undo the fixup (and this is currently being handled in the core module code) - Such runtime relocation entries take up 24 bytes of __init space each, resulting in a x8 overhead in [uncompressed] kernel size for CRCs. Switching to explicit 32 bit values on 64 bit architectures fixes most of these issues, given that 32 bit values are not treated as quantities that require fixing up based on the actual runtime load offset. Note that on some ELF64 architectures [such as PPC64], these 32-bit values are still emitted as [absolute] runtime relocatable quantities, even if the value resolves to a build time constant. Since relative relocations are always resolved at build time, this patch enables MODULE_REL_CRCS on powerpc when CONFIG_RELOCATABLE=y, which turns the absolute CRC references into relative references into .rodata where the actual CRC value is stored. So redefine all CRC fields and variables as u32, and redefine the __CRC_SYMBOL() macro for 64 bit builds to emit the CRC reference using inline assembler (which is necessary since 64-bit C code cannot use 32-bit types to hold memory addresses, even if they are ultimately resolved using values that do not exceed 0xffffffff). To avoid potential problems with legacy 32-bit architectures using legacy toolchains, the equivalent C definition of the kcrctab entry is retained for 32-bit architectures. Note that this mostly reverts commit d4703aefdbc8 ("module: handle ppc64 relocating kcrctabs when CONFIG_RELOCATABLE=y") Acked-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-03 17:54:06 +08:00
const s32 *crcs;
enum {
NOT_GPL_ONLY,
GPL_ONLY,
WILL_BE_GPL_ONLY,
} licence;
bool unused;
};
/*
* Search for an exported symbol by name.
*
* Must be called with module_mutex held or preemption disabled.
*/
const struct kernel_symbol *find_symbol(const char *name,
struct module **owner,
modversions: treat symbol CRCs as 32 bit quantities The modversion symbol CRCs are emitted as ELF symbols, which allows us to easily populate the kcrctab sections by relying on the linker to associate each kcrctab slot with the correct value. This has a couple of downsides: - Given that the CRCs are treated as memory addresses, we waste 4 bytes for each CRC on 64 bit architectures, - On architectures that support runtime relocation, a R_<arch>_RELATIVE relocation entry is emitted for each CRC value, which identifies it as a quantity that requires fixing up based on the actual runtime load offset of the kernel. This results in corrupted CRCs unless we explicitly undo the fixup (and this is currently being handled in the core module code) - Such runtime relocation entries take up 24 bytes of __init space each, resulting in a x8 overhead in [uncompressed] kernel size for CRCs. Switching to explicit 32 bit values on 64 bit architectures fixes most of these issues, given that 32 bit values are not treated as quantities that require fixing up based on the actual runtime load offset. Note that on some ELF64 architectures [such as PPC64], these 32-bit values are still emitted as [absolute] runtime relocatable quantities, even if the value resolves to a build time constant. Since relative relocations are always resolved at build time, this patch enables MODULE_REL_CRCS on powerpc when CONFIG_RELOCATABLE=y, which turns the absolute CRC references into relative references into .rodata where the actual CRC value is stored. So redefine all CRC fields and variables as u32, and redefine the __CRC_SYMBOL() macro for 64 bit builds to emit the CRC reference using inline assembler (which is necessary since 64-bit C code cannot use 32-bit types to hold memory addresses, even if they are ultimately resolved using values that do not exceed 0xffffffff). To avoid potential problems with legacy 32-bit architectures using legacy toolchains, the equivalent C definition of the kcrctab entry is retained for 32-bit architectures. Note that this mostly reverts commit d4703aefdbc8 ("module: handle ppc64 relocating kcrctabs when CONFIG_RELOCATABLE=y") Acked-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-03 17:54:06 +08:00
const s32 **crc,
bool gplok,
bool warn);
/*
* Walk the exported symbol table
*
* Must be called with module_mutex held or preemption disabled.
*/
bool each_symbol_section(bool (*fn)(const struct symsearch *arr,
struct module *owner,
void *data), void *data);
/* Returns 0 and fills in value, defined and namebuf, or -ERANGE if
symnum out of range. */
int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
char *name, char *module_name, int *exported);
/* Look for this name: can be of form module:name. */
unsigned long module_kallsyms_lookup_name(const char *name);
int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
struct module *, unsigned long),
void *data);
extern void __noreturn __module_put_and_exit(struct module *mod,
long code);
#define module_put_and_exit(code) __module_put_and_exit(THIS_MODULE, code)
#ifdef CONFIG_MODULE_UNLOAD
int module_refcount(struct module *mod);
void __symbol_put(const char *symbol);
#define symbol_put(x) __symbol_put(__stringify(x))
void symbol_put_addr(void *addr);
/* Sometimes we know we already have a refcount, and it's easier not
to handle the error case (which only happens with rmmod --wait). */
extern void __module_get(struct module *module);
/* This is the Right Way to get a module: if it fails, it's being removed,
* so pretend it's not there. */
extern bool try_module_get(struct module *module);
extern void module_put(struct module *module);
#else /*!CONFIG_MODULE_UNLOAD*/
static inline bool try_module_get(struct module *module)
{
return !module || module_is_live(module);
}
static inline void module_put(struct module *module)
{
}
static inline void __module_get(struct module *module)
{
}
#define symbol_put(x) do { } while (0)
#define symbol_put_addr(p) do { } while (0)
#endif /* CONFIG_MODULE_UNLOAD */
int ref_module(struct module *a, struct module *b);
/* This is a #define so the string doesn't get put in every .o file */
#define module_name(mod) \
({ \
struct module *__mod = (mod); \
__mod ? __mod->name : "kernel"; \
})
sections: split dereference_function_descriptor() There are two format specifiers to print out a pointer in symbolic format: '%pS/%ps' and '%pF/%pf'. On most architectures, the two mean exactly the same thing, but some architectures (ia64, ppc64, parisc64) use an indirect pointer for C function pointers, where the function pointer points to a function descriptor (which in turn contains the actual pointer to the code). The '%pF/%pf, when used appropriately, automatically does the appropriate function descriptor dereference on such architectures. The "when used appropriately" part is tricky. Basically this is a subtle ABI detail, specific to some platforms, that made it to the API level and people can be unaware of it and miss the whole "we need to dereference the function" business out. [1] proves that point (note that it fixes only '%pF' and '%pS', there might be '%pf' and '%ps' cases as well). It appears that we can handle everything within the affected arches and make '%pS/%ps' smart enough to retire '%pF/%pf'. Function descriptors live in .opd elf section and all affected arches (ia64, ppc64, parisc64) handle it properly for kernel and modules. So we, technically, can decide if the dereference is needed by simply looking at the pointer: if it belongs to .opd section then we need to dereference it. The kernel and modules have their own .opd sections, obviously, that's why we need to split dereference_function_descriptor() and use separate kernel and module dereference arch callbacks. This patch does the first step, it a) adds dereference_kernel_function_descriptor() function. b) adds a weak alias to dereference_module_function_descriptor() function. So, for the time being, we will have: 1) dereference_function_descriptor() A generic function, that simply dereferences the pointer. There is bunch of places that call it: kgdbts, init/main.c, extable, etc. 2) dereference_kernel_function_descriptor() A function to call on kernel symbols that does kernel .opd section address range test. 3) dereference_module_function_descriptor() A function to call on modules' symbols that does modules' .opd section address range test. [1] https://marc.info/?l=linux-kernel&m=150472969730573 Link: http://lkml.kernel.org/r/20171109234830.5067-2-sergey.senozhatsky@gmail.com To: Fenghua Yu <fenghua.yu@intel.com> To: Benjamin Herrenschmidt <benh@kernel.crashing.org> To: Paul Mackerras <paulus@samba.org> To: Michael Ellerman <mpe@ellerman.id.au> To: James Bottomley <jejb@parisc-linux.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Jessica Yu <jeyu@kernel.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: linux-ia64@vger.kernel.org Cc: linux-parisc@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Tested-by: Tony Luck <tony.luck@intel.com> #ia64 Tested-by: Santosh Sivaraj <santosh@fossix.org> #powerpc Tested-by: Helge Deller <deller@gmx.de> #parisc64 Signed-off-by: Petr Mladek <pmladek@suse.com>
2017-11-10 07:48:25 +08:00
/* Dereference module function descriptor */
void *dereference_module_function_descriptor(struct module *mod, void *ptr);
/* For kallsyms to ask for address resolution. namebuf should be at
* least KSYM_NAME_LEN long: a pointer to namebuf is returned if
* found, otherwise NULL. */
const char *module_address_lookup(unsigned long addr,
unsigned long *symbolsize,
unsigned long *offset,
char **modname,
char *namebuf);
int lookup_module_symbol_name(unsigned long addr, char *symname);
int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name);
int register_module_notifier(struct notifier_block *nb);
int unregister_module_notifier(struct notifier_block *nb);
extern void print_modules(void);
static inline bool module_requested_async_probing(struct module *module)
{
return module && module->async_probe_requested;
}
module: preserve Elf information for livepatch modules For livepatch modules, copy Elf section, symbol, and string information from the load_info struct in the module loader. Persist copies of the original symbol table and string table. Livepatch manages its own relocation sections in order to reuse module loader code to write relocations. Livepatch modules must preserve Elf information such as section indices in order to apply livepatch relocation sections using the module loader's apply_relocate_add() function. In order to apply livepatch relocation sections, livepatch modules must keep a complete copy of their original symbol table in memory. Normally, a stripped down copy of a module's symbol table (containing only "core" symbols) is made available through module->core_symtab. But for livepatch modules, the symbol table copied into memory on module load must be exactly the same as the symbol table produced when the patch module was compiled. This is because the relocations in each livepatch relocation section refer to their respective symbols with their symbol indices, and the original symbol indices (and thus the symtab ordering) must be preserved in order for apply_relocate_add() to find the right symbol. Signed-off-by: Jessica Yu <jeyu@redhat.com> Reviewed-by: Miroslav Benes <mbenes@suse.cz> Acked-by: Josh Poimboeuf <jpoimboe@redhat.com> Acked-by: Rusty Russell <rusty@rustcorp.com.au> Reviewed-by: Rusty Russell <rusty@rustcorp.com.au> Signed-off-by: Jiri Kosina <jkosina@suse.cz>
2016-03-23 08:03:16 +08:00
#ifdef CONFIG_LIVEPATCH
static inline bool is_livepatch_module(struct module *mod)
{
return mod->klp;
}
#else /* !CONFIG_LIVEPATCH */
static inline bool is_livepatch_module(struct module *mod)
{
return false;
}
#endif /* CONFIG_LIVEPATCH */
bool is_module_sig_enforced(void);
void set_module_sig_enforced(void);
#else /* !CONFIG_MODULES... */
static inline struct module *__module_address(unsigned long addr)
{
return NULL;
}
static inline struct module *__module_text_address(unsigned long addr)
{
return NULL;
}
static inline bool is_module_address(unsigned long addr)
{
return false;
}
static inline bool is_module_percpu_address(unsigned long addr)
{
return false;
}
locking/lockdep: Handle statically initialized PER_CPU locks properly If a PER_CPU struct which contains a spin_lock is statically initialized via: DEFINE_PER_CPU(struct foo, bla) = { .lock = __SPIN_LOCK_UNLOCKED(bla.lock) }; then lockdep assigns a seperate key to each lock because the logic for assigning a key to statically initialized locks is to use the address as the key. With per CPU locks the address is obvioulsy different on each CPU. That's wrong, because all locks should have the same key. To solve this the following modifications are required: 1) Extend the is_kernel/module_percpu_addr() functions to hand back the canonical address of the per CPU address, i.e. the per CPU address minus the per CPU offset. 2) Check the lock address with these functions and if the per CPU check matches use the returned canonical address as the lock key, so all per CPU locks have the same key. 3) Move the static_obj(key) check into look_up_lock_class() so this check can be avoided for statically initialized per CPU locks. That's required because the canonical address fails the static_obj(key) check for obvious reasons. Reported-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> [ Merged Dan's fixups for !MODULES and !SMP into this patch. ] Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Dan Murphy <dmurphy@ti.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20170227143736.pectaimkjkan5kow@linutronix.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-02-27 22:37:36 +08:00
static inline bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr)
{
return false;
}
static inline bool is_module_text_address(unsigned long addr)
{
return false;
}
static inline bool within_module_core(unsigned long addr,
const struct module *mod)
{
return false;
}
static inline bool within_module_init(unsigned long addr,
const struct module *mod)
{
return false;
}
static inline bool within_module(unsigned long addr, const struct module *mod)
{
return false;
}
/* Get/put a kernel symbol (calls should be symmetric) */
#define symbol_get(x) ({ extern typeof(x) x __attribute__((weak)); &(x); })
#define symbol_put(x) do { } while (0)
#define symbol_put_addr(x) do { } while (0)
static inline void __module_get(struct module *module)
{
}
static inline bool try_module_get(struct module *module)
{
return true;
}
static inline void module_put(struct module *module)
{
}
#define module_name(mod) "kernel"
/* For kallsyms to ask for address resolution. NULL means not found. */
static inline const char *module_address_lookup(unsigned long addr,
unsigned long *symbolsize,
unsigned long *offset,
char **modname,
char *namebuf)
{
return NULL;
}
static inline int lookup_module_symbol_name(unsigned long addr, char *symname)
{
return -ERANGE;
}
static inline int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name)
{
return -ERANGE;
}
static inline int module_get_kallsym(unsigned int symnum, unsigned long *value,
char *type, char *name,
char *module_name, int *exported)
{
return -ERANGE;
}
static inline unsigned long module_kallsyms_lookup_name(const char *name)
{
return 0;
}
static inline int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
struct module *,
unsigned long),
void *data)
{
return 0;
}
static inline int register_module_notifier(struct notifier_block *nb)
{
/* no events will happen anyway, so this can always succeed */
return 0;
}
static inline int unregister_module_notifier(struct notifier_block *nb)
{
return 0;
}
#define module_put_and_exit(code) do_exit(code)
static inline void print_modules(void)
{
}
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)
{
}
sections: split dereference_function_descriptor() There are two format specifiers to print out a pointer in symbolic format: '%pS/%ps' and '%pF/%pf'. On most architectures, the two mean exactly the same thing, but some architectures (ia64, ppc64, parisc64) use an indirect pointer for C function pointers, where the function pointer points to a function descriptor (which in turn contains the actual pointer to the code). The '%pF/%pf, when used appropriately, automatically does the appropriate function descriptor dereference on such architectures. The "when used appropriately" part is tricky. Basically this is a subtle ABI detail, specific to some platforms, that made it to the API level and people can be unaware of it and miss the whole "we need to dereference the function" business out. [1] proves that point (note that it fixes only '%pF' and '%pS', there might be '%pf' and '%ps' cases as well). It appears that we can handle everything within the affected arches and make '%pS/%ps' smart enough to retire '%pF/%pf'. Function descriptors live in .opd elf section and all affected arches (ia64, ppc64, parisc64) handle it properly for kernel and modules. So we, technically, can decide if the dereference is needed by simply looking at the pointer: if it belongs to .opd section then we need to dereference it. The kernel and modules have their own .opd sections, obviously, that's why we need to split dereference_function_descriptor() and use separate kernel and module dereference arch callbacks. This patch does the first step, it a) adds dereference_kernel_function_descriptor() function. b) adds a weak alias to dereference_module_function_descriptor() function. So, for the time being, we will have: 1) dereference_function_descriptor() A generic function, that simply dereferences the pointer. There is bunch of places that call it: kgdbts, init/main.c, extable, etc. 2) dereference_kernel_function_descriptor() A function to call on kernel symbols that does kernel .opd section address range test. 3) dereference_module_function_descriptor() A function to call on modules' symbols that does modules' .opd section address range test. [1] https://marc.info/?l=linux-kernel&m=150472969730573 Link: http://lkml.kernel.org/r/20171109234830.5067-2-sergey.senozhatsky@gmail.com To: Fenghua Yu <fenghua.yu@intel.com> To: Benjamin Herrenschmidt <benh@kernel.crashing.org> To: Paul Mackerras <paulus@samba.org> To: Michael Ellerman <mpe@ellerman.id.au> To: James Bottomley <jejb@parisc-linux.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Jessica Yu <jeyu@kernel.org> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: linux-ia64@vger.kernel.org Cc: linux-parisc@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Tested-by: Tony Luck <tony.luck@intel.com> #ia64 Tested-by: Santosh Sivaraj <santosh@fossix.org> #powerpc Tested-by: Helge Deller <deller@gmx.de> #parisc64 Signed-off-by: Petr Mladek <pmladek@suse.com>
2017-11-10 07:48:25 +08:00
/* Dereference module function descriptor */
static inline
void *dereference_module_function_descriptor(struct module *mod, void *ptr)
{
return ptr;
}
#endif /* CONFIG_MODULES */
#ifdef CONFIG_SYSFS
extern struct kset *module_kset;
extern struct kobj_type module_ktype;
extern int module_sysfs_initialized;
#endif /* CONFIG_SYSFS */
#define symbol_request(x) try_then_request_module(symbol_get(x), "symbol:" #x)
/* BELOW HERE ALL THESE ARE OBSOLETE AND WILL VANISH */
#define __MODULE_STRING(x) __stringify(x)
#ifdef CONFIG_STRICT_MODULE_RWX
extern void module_enable_ro(const struct module *mod, bool after_init);
extern void module_disable_ro(const struct module *mod);
x86: Add RO/NX protection for loadable kernel modules This patch is a logical extension of the protection provided by CONFIG_DEBUG_RODATA to LKMs. The protection is provided by splitting module_core and module_init into three logical parts each and setting appropriate page access permissions for each individual section: 1. Code: RO+X 2. RO data: RO+NX 3. RW data: RW+NX In order to achieve proper protection, layout_sections() have been modified to align each of the three parts mentioned above onto page boundary. Next, the corresponding page access permissions are set right before successful exit from load_module(). Further, free_module() and sys_init_module have been modified to set module_core and module_init as RW+NX right before calling module_free(). By default, the original section layout and access flags are preserved. When compiled with CONFIG_DEBUG_SET_MODULE_RONX=y, the patch will page-align each group of sections to ensure that each page contains only one type of content and will enforce RO/NX for each group of pages. -v1: Initial proof-of-concept patch. -v2: The patch have been re-written to reduce the number of #ifdefs and to make it architecture-agnostic. Code formatting has also been corrected. -v3: Opportunistic RO/NX protection is now unconditional. Section page-alignment is enabled when CONFIG_DEBUG_RODATA=y. -v4: Removed most macros and improved coding style. -v5: Changed page-alignment and RO/NX section size calculation -v6: Fixed comments. Restricted RO/NX enforcement to x86 only -v7: Introduced CONFIG_DEBUG_SET_MODULE_RONX, added calls to set_all_modules_text_rw() and set_all_modules_text_ro() in ftrace -v8: updated for compatibility with linux 2.6.33-rc5 -v9: coding style fixes -v10: more coding style fixes -v11: minor adjustments for -tip -v12: minor adjustments for v2.6.35-rc2-tip -v13: minor adjustments for v2.6.37-rc1-tip Signed-off-by: Siarhei Liakh <sliakh.lkml@gmail.com> Signed-off-by: Xuxian Jiang <jiang@cs.ncsu.edu> Acked-by: Arjan van de Ven <arjan@linux.intel.com> Reviewed-by: James Morris <jmorris@namei.org> Signed-off-by: H. Peter Anvin <hpa@zytor.com> Cc: Andi Kleen <ak@muc.de> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Dave Jones <davej@redhat.com> Cc: Kees Cook <kees.cook@canonical.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> LKML-Reference: <4CE2F914.9070106@free.fr> [ minor cleanliness edits, -v14: build failure fix ] Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-11-17 05:35:16 +08:00
#else
static inline void module_enable_ro(const struct module *mod, bool after_init) { }
static inline void module_disable_ro(const struct module *mod) { }
x86: Add RO/NX protection for loadable kernel modules This patch is a logical extension of the protection provided by CONFIG_DEBUG_RODATA to LKMs. The protection is provided by splitting module_core and module_init into three logical parts each and setting appropriate page access permissions for each individual section: 1. Code: RO+X 2. RO data: RO+NX 3. RW data: RW+NX In order to achieve proper protection, layout_sections() have been modified to align each of the three parts mentioned above onto page boundary. Next, the corresponding page access permissions are set right before successful exit from load_module(). Further, free_module() and sys_init_module have been modified to set module_core and module_init as RW+NX right before calling module_free(). By default, the original section layout and access flags are preserved. When compiled with CONFIG_DEBUG_SET_MODULE_RONX=y, the patch will page-align each group of sections to ensure that each page contains only one type of content and will enforce RO/NX for each group of pages. -v1: Initial proof-of-concept patch. -v2: The patch have been re-written to reduce the number of #ifdefs and to make it architecture-agnostic. Code formatting has also been corrected. -v3: Opportunistic RO/NX protection is now unconditional. Section page-alignment is enabled when CONFIG_DEBUG_RODATA=y. -v4: Removed most macros and improved coding style. -v5: Changed page-alignment and RO/NX section size calculation -v6: Fixed comments. Restricted RO/NX enforcement to x86 only -v7: Introduced CONFIG_DEBUG_SET_MODULE_RONX, added calls to set_all_modules_text_rw() and set_all_modules_text_ro() in ftrace -v8: updated for compatibility with linux 2.6.33-rc5 -v9: coding style fixes -v10: more coding style fixes -v11: minor adjustments for -tip -v12: minor adjustments for v2.6.35-rc2-tip -v13: minor adjustments for v2.6.37-rc1-tip Signed-off-by: Siarhei Liakh <sliakh.lkml@gmail.com> Signed-off-by: Xuxian Jiang <jiang@cs.ncsu.edu> Acked-by: Arjan van de Ven <arjan@linux.intel.com> Reviewed-by: James Morris <jmorris@namei.org> Signed-off-by: H. Peter Anvin <hpa@zytor.com> Cc: Andi Kleen <ak@muc.de> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Dave Jones <davej@redhat.com> Cc: Kees Cook <kees.cook@canonical.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> LKML-Reference: <4CE2F914.9070106@free.fr> [ minor cleanliness edits, -v14: build failure fix ] Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-11-17 05:35:16 +08:00
#endif
#ifdef CONFIG_GENERIC_BUG
2010-10-06 02:29:27 +08:00
void module_bug_finalize(const Elf_Ehdr *, const Elf_Shdr *,
struct module *);
void module_bug_cleanup(struct module *);
#else /* !CONFIG_GENERIC_BUG */
2010-10-06 02:29:27 +08:00
static inline void module_bug_finalize(const Elf_Ehdr *hdr,
const Elf_Shdr *sechdrs,
struct module *mod)
{
}
static inline void module_bug_cleanup(struct module *mod) {}
#endif /* CONFIG_GENERIC_BUG */
x86, modpost: Replace last remnants of RETPOLINE with CONFIG_RETPOLINE Commit 4cd24de3a098 ("x86/retpoline: Make CONFIG_RETPOLINE depend on compiler support") replaced the RETPOLINE define with CONFIG_RETPOLINE checks. Remove the remaining pieces. [ bp: Massage commit message. ] Fixes: 4cd24de3a098 ("x86/retpoline: Make CONFIG_RETPOLINE depend on compiler support") Signed-off-by: WANG Chao <chao.wang@ucloud.cn> Signed-off-by: Borislav Petkov <bp@suse.de> Reviewed-by: Zhenzhong Duan <zhenzhong.duan@oracle.com> Reviewed-by: Masahiro Yamada <yamada.masahiro@socionext.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: David Woodhouse <dwmw@amazon.co.uk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Jessica Yu <jeyu@kernel.org> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Kees Cook <keescook@chromium.org> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Luc Van Oostenryck <luc.vanoostenryck@gmail.com> Cc: Michal Marek <michal.lkml@markovi.net> Cc: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: linux-kbuild@vger.kernel.org Cc: srinivas.eeda@oracle.com Cc: stable <stable@vger.kernel.org> Cc: x86-ml <x86@kernel.org> Link: https://lkml.kernel.org/r/20181210163725.95977-1-chao.wang@ucloud.cn
2018-12-11 00:37:25 +08:00
#ifdef CONFIG_RETPOLINE
extern bool retpoline_module_ok(bool has_retpoline);
#else
static inline bool retpoline_module_ok(bool has_retpoline)
{
return true;
}
#endif
#ifdef CONFIG_MODULE_SIG
static inline bool module_sig_ok(struct module *module)
{
return module->sig_ok;
}
#else /* !CONFIG_MODULE_SIG */
static inline bool module_sig_ok(struct module *module)
{
return true;
}
#endif /* CONFIG_MODULE_SIG */
#endif /* _LINUX_MODULE_H */