kexec: split kexec_load syscall from kexec core code

There are two kexec load syscalls, kexec_load another and kexec_file_load.
 kexec_file_load has been splited as kernel/kexec_file.c.  In this patch I
split kexec_load syscall code to kernel/kexec.c.

And add a new kconfig option KEXEC_CORE, so we can disable kexec_load and
use kexec_file_load only, or vice verse.

The original requirement is from Ted Ts'o, he want kexec kernel signature
being checked with CONFIG_KEXEC_VERIFY_SIG enabled.  But kexec-tools use
kexec_load syscall can bypass the checking.

Vivek Goyal proposed to create a common kconfig option so user can compile
in only one syscall for loading kexec kernel.  KEXEC/KEXEC_FILE selects
KEXEC_CORE so that old config files still work.

Because there's general code need CONFIG_KEXEC_CORE, so I updated all the
architecture Kconfig with a new option KEXEC_CORE, and let KEXEC selects
KEXEC_CORE in arch Kconfig.  Also updated general kernel code with to
kexec_load syscall.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: NDave Young <dyoung@redhat.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Petr Tesarik <ptesarik@suse.cz>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Josh Boyer <jwboyer@fedoraproject.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

arch/Kconfig

@@ -2,6 +2,9 @@
 # General architecture dependent options
 #
 
+config KEXEC_CORE
+	bool
+
 config OPROFILE
 	tristate "OProfile system profiling"
 	depends on PROFILING

arch/arm/Kconfig

@@ -2020,6 +2020,7 @@ config KEXEC
 	bool "Kexec system call (EXPERIMENTAL)"
 	depends on (!SMP || PM_SLEEP_SMP)
 	depends on !CPU_V7M
+	select KEXEC_CORE
 	help
 	  kexec is a system call that implements the ability to shutdown your
 	  current kernel, and to start another kernel.  It is like a reboot

arch/ia64/Kconfig

@@ -518,6 +518,7 @@ source "drivers/sn/Kconfig"
 config KEXEC
 	bool "kexec system call"
 	depends on !IA64_HP_SIM && (!SMP || HOTPLUG_CPU)
+	select KEXEC_CORE
 	help
 	  kexec is a system call that implements the ability to shutdown your
 	  current kernel, and to start another kernel.  It is like a reboot

arch/m68k/Kconfig

@@ -95,6 +95,7 @@ config MMU_SUN3
 config KEXEC
 	bool "kexec system call"
 	depends on M68KCLASSIC
+	select KEXEC_CORE
 	help
 	  kexec is a system call that implements the ability to shutdown your
 	  current kernel, and to start another kernel.  It is like a reboot

arch/mips/Kconfig

@@ -2597,6 +2597,7 @@ source "kernel/Kconfig.preempt"
 
 config KEXEC
 	bool "Kexec system call"
+	select KEXEC_CORE
 	help
 	  kexec is a system call that implements the ability to shutdown your
 	  current kernel, and to start another kernel.  It is like a reboot

arch/powerpc/Kconfig

@@ -420,6 +420,7 @@ config PPC64_SUPPORTS_MEMORY_FAILURE
 config KEXEC
 	bool "kexec system call"
 	depends on (PPC_BOOK3S || FSL_BOOKE || (44x && !SMP))
+	select KEXEC_CORE
 	help
 	  kexec is a system call that implements the ability to shutdown your
 	  current kernel, and to start another kernel.  It is like a reboot

arch/s390/Kconfig

@@ -48,6 +48,7 @@ config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 
 config KEXEC
 	def_bool y
+	select KEXEC_CORE
 
 config AUDIT_ARCH
 	def_bool y

arch/sh/Kconfig

@@ -602,6 +602,7 @@ source kernel/Kconfig.hz
 config KEXEC
 	bool "kexec system call (EXPERIMENTAL)"
 	depends on SUPERH32 && MMU
+	select KEXEC_CORE
 	help
 	  kexec is a system call that implements the ability to shutdown your
 	  current kernel, and to start another kernel.  It is like a reboot

arch/tile/Kconfig

@@ -205,6 +205,7 @@ source "kernel/Kconfig.hz"
 
 config KEXEC
 	bool "kexec system call"
+	select KEXEC_CORE
 	---help---
 	  kexec is a system call that implements the ability to shutdown your
 	  current kernel, and to start another kernel.  It is like a reboot

arch/x86/Kconfig

@@ -1754,6 +1754,7 @@ source kernel/Kconfig.hz
 
 config KEXEC
 	bool "kexec system call"
+	select KEXEC_CORE
 	---help---
 	  kexec is a system call that implements the ability to shutdown your
 	  current kernel, and to start another kernel.  It is like a reboot
@@ -1770,8 +1771,8 @@ config KEXEC
 
 config KEXEC_FILE
 	bool "kexec file based system call"
+	select KEXEC_CORE
 	select BUILD_BIN2C
-	depends on KEXEC
 	depends on X86_64
 	depends on CRYPTO=y
 	depends on CRYPTO_SHA256=y

arch/x86/boot/header.S

@@ -414,7 +414,7 @@ xloadflags:
 # define XLF23 0
 #endif
 
-#if defined(CONFIG_X86_64) && defined(CONFIG_EFI) && defined(CONFIG_KEXEC)
+#if defined(CONFIG_X86_64) && defined(CONFIG_EFI) && defined(CONFIG_KEXEC_CORE)
 # define XLF4 XLF_EFI_KEXEC
 #else
 # define XLF4 0

arch/x86/include/asm/kdebug.h

@@ -29,7 +29,7 @@ extern void show_trace(struct task_struct *t, struct pt_regs *regs,
 extern void __show_regs(struct pt_regs *regs, int all);
 extern unsigned long oops_begin(void);
 extern void oops_end(unsigned long, struct pt_regs *, int signr);
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 extern int in_crash_kexec;
 #else
 /* no crash dump is ever in progress if no crash kernel can be kexec'd */

arch/x86/kernel/Makefile

@@ -71,8 +71,8 @@ obj-$(CONFIG_LIVEPATCH)		+= livepatch.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
 obj-$(CONFIG_FTRACE_SYSCALLS)	+= ftrace.o
 obj-$(CONFIG_X86_TSC)		+= trace_clock.o
-obj-$(CONFIG_KEXEC)		+= machine_kexec_$(BITS).o
-obj-$(CONFIG_KEXEC)		+= relocate_kernel_$(BITS).o crash.o
+obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec_$(BITS).o
+obj-$(CONFIG_KEXEC_CORE)	+= relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_KEXEC_FILE)	+= kexec-bzimage64.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump_$(BITS).o
 obj-y				+= kprobes/

arch/x86/kernel/kvmclock.c

@@ -200,7 +200,7 @@ static void kvm_setup_secondary_clock(void)
  * kind of shutdown from our side, we unregister the clock by writting anything
  * that does not have the 'enable' bit set in the msr
  */
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 static void kvm_crash_shutdown(struct pt_regs *regs)
 {
 	native_write_msr(msr_kvm_system_time, 0, 0);
@@ -259,7 +259,7 @@ void __init kvmclock_init(void)
 	x86_platform.save_sched_clock_state = kvm_save_sched_clock_state;
 	x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state;
 	machine_ops.shutdown  = kvm_shutdown;
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	machine_ops.crash_shutdown  = kvm_crash_shutdown;
 #endif
 	kvm_get_preset_lpj();

arch/x86/kernel/reboot.c

@@ -673,7 +673,7 @@ struct machine_ops machine_ops = {
 	.emergency_restart = native_machine_emergency_restart,
 	.restart = native_machine_restart,
 	.halt = native_machine_halt,
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.crash_shutdown = native_machine_crash_shutdown,
 #endif
 };
@@ -703,7 +703,7 @@ void machine_halt(void)
 	machine_ops.halt();
 }
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 void machine_crash_shutdown(struct pt_regs *regs)
 {
 	machine_ops.crash_shutdown(regs);

arch/x86/kernel/setup.c

@@ -478,7 +478,7 @@ static void __init memblock_x86_reserve_range_setup_data(void)
  * --------- Crashkernel reservation ------------------------------
  */
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 
 /*
  * Keep the crash kernel below this limit.  On 32 bits earlier kernels

arch/x86/kernel/vmlinux.lds.S

@@ -364,7 +364,7 @@ INIT_PER_CPU(irq_stack_union);
 
 #endif /* CONFIG_X86_32 */
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 #include <asm/kexec.h>
 
 . = ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE,

arch/x86/kvm/vmx.c

@@ -1264,7 +1264,7 @@ static void vmcs_load(struct vmcs *vmcs)
 		       vmcs, phys_addr);
 }
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 /*
  * This bitmap is used to indicate whether the vmclear
  * operation is enabled on all cpus. All disabled by
@@ -1302,7 +1302,7 @@ static void crash_vmclear_local_loaded_vmcss(void)
 #else
 static inline void crash_enable_local_vmclear(int cpu) { }
 static inline void crash_disable_local_vmclear(int cpu) { }
-#endif /* CONFIG_KEXEC */
+#endif /* CONFIG_KEXEC_CORE */
 
 static void __loaded_vmcs_clear(void *arg)
 {
@@ -10411,7 +10411,7 @@ static int __init vmx_init(void)
 	if (r)
 		return r;
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	rcu_assign_pointer(crash_vmclear_loaded_vmcss,
 			   crash_vmclear_local_loaded_vmcss);
 #endif
@@ -10421,7 +10421,7 @@ static int __init vmx_init(void)
 
 static void __exit vmx_exit(void)
 {
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL);
 	synchronize_rcu();
 #endif

arch/x86/platform/efi/efi.c

@@ -650,7 +650,7 @@ static void __init get_systab_virt_addr(efi_memory_desc_t *md)
 
 static void __init save_runtime_map(void)
 {
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	efi_memory_desc_t *md;
 	void *tmp, *p, *q = NULL;
 	int count = 0;
@@ -748,7 +748,7 @@ static void * __init efi_map_regions(int *count, int *pg_shift)
 
 static void __init kexec_enter_virtual_mode(void)
 {
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	efi_memory_desc_t *md;
 	void *p;
 

arch/x86/platform/uv/uv_nmi.c

@@ -492,7 +492,7 @@ static void uv_nmi_touch_watchdogs(void)
 	touch_nmi_watchdog();
 }
 
-#if defined(CONFIG_KEXEC)
+#if defined(CONFIG_KEXEC_CORE)
 static atomic_t uv_nmi_kexec_failed;
 static void uv_nmi_kdump(int cpu, int master, struct pt_regs *regs)
 {
@@ -519,13 +519,13 @@ static void uv_nmi_kdump(int cpu, int master, struct pt_regs *regs)
 	uv_nmi_sync_exit(0);
 }
 
-#else /* !CONFIG_KEXEC */
+#else /* !CONFIG_KEXEC_CORE */
 static inline void uv_nmi_kdump(int cpu, int master, struct pt_regs *regs)
 {
 	if (master)
 		pr_err("UV: NMI kdump: KEXEC not supported in this kernel\n");
 }
-#endif /* !CONFIG_KEXEC */
+#endif /* !CONFIG_KEXEC_CORE */
 
 #ifdef CONFIG_KGDB
 #ifdef CONFIG_KGDB_KDB

drivers/firmware/efi/Kconfig

@@ -43,7 +43,7 @@ config EFI_VARS_PSTORE_DEFAULT_DISABLE
 
 config EFI_RUNTIME_MAP
 	bool "Export efi runtime maps to sysfs"
-	depends on X86 && EFI && KEXEC
+	depends on X86 && EFI && KEXEC_CORE
 	default y
 	help
 	  Export efi runtime memory maps to /sys/firmware/efi/runtime-map.

drivers/pci/pci-driver.c

@@ -467,7 +467,7 @@ static void pci_device_shutdown(struct device *dev)
 	pci_msi_shutdown(pci_dev);
 	pci_msix_shutdown(pci_dev);
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	/*
 	 * If this is a kexec reboot, turn off Bus Master bit on the
 	 * device to tell it to not continue to do DMA. Don't touch

include/linux/kexec.h

@@ -16,7 +16,7 @@
 
 #include <uapi/linux/kexec.h>
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 #include <linux/list.h>
 #include <linux/linkage.h>
 #include <linux/compat.h>
@@ -329,13 +329,13 @@ int __weak arch_kexec_apply_relocations_add(const Elf_Ehdr *ehdr,
 int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 					unsigned int relsec);
 
-#else /* !CONFIG_KEXEC */
+#else /* !CONFIG_KEXEC_CORE */
 struct pt_regs;
 struct task_struct;
 static inline void crash_kexec(struct pt_regs *regs) { }
 static inline int kexec_should_crash(struct task_struct *p) { return 0; }
 #define kexec_in_progress false
-#endif /* CONFIG_KEXEC */
+#endif /* CONFIG_KEXEC_CORE */
 
 #endif /* !defined(__ASSEBMLY__) */
 

init/initramfs.c

@@ -526,14 +526,14 @@ extern unsigned long __initramfs_size;
 
 static void __init free_initrd(void)
 {
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	unsigned long crashk_start = (unsigned long)__va(crashk_res.start);
 	unsigned long crashk_end   = (unsigned long)__va(crashk_res.end);
 #endif
 	if (do_retain_initrd)
 		goto skip;
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	/*
 	 * If the initrd region is overlapped with crashkernel reserved region,
 	 * free only memory that is not part of crashkernel region.

kernel/Makefile

@@ -49,6 +49,7 @@ obj-$(CONFIG_MODULES) += module.o
 obj-$(CONFIG_MODULE_SIG) += module_signing.o
 obj-$(CONFIG_KALLSYMS) += kallsyms.o
 obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o
+obj-$(CONFIG_KEXEC_CORE) += kexec_core.o
 obj-$(CONFIG_KEXEC) += kexec.o
 obj-$(CONFIG_KEXEC_FILE) += kexec_file.o
 obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o

kernel/events/core.c

@@ -9094,7 +9094,7 @@ static void perf_event_init_cpu(int cpu)
 	mutex_unlock(&swhash->hlist_mutex);
 }
 
-#if defined CONFIG_HOTPLUG_CPU || defined CONFIG_KEXEC
+#if defined CONFIG_HOTPLUG_CPU || defined CONFIG_KEXEC_CORE
 static void __perf_event_exit_context(void *__info)
 {
 	struct remove_event re = { .detach_group = true };

kernel/ksysfs.c

@@ -90,7 +90,7 @@ static ssize_t profiling_store(struct kobject *kobj,
 KERNEL_ATTR_RW(profiling);
 #endif
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 static ssize_t kexec_loaded_show(struct kobject *kobj,
 				 struct kobj_attribute *attr, char *buf)
 {
@@ -134,7 +134,7 @@ static ssize_t vmcoreinfo_show(struct kobject *kobj,
 }
 KERNEL_ATTR_RO(vmcoreinfo);
 
-#endif /* CONFIG_KEXEC */
+#endif /* CONFIG_KEXEC_CORE */
 
 /* whether file capabilities are enabled */
 static ssize_t fscaps_show(struct kobject *kobj,
@@ -196,7 +196,7 @@ static struct attribute * kernel_attrs[] = {
 #ifdef CONFIG_PROFILING
 	&profiling_attr.attr,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	&kexec_loaded_attr.attr,
 	&kexec_crash_loaded_attr.attr,
 	&kexec_crash_size_attr.attr,

kernel/printk/printk.c

@@ -835,7 +835,7 @@ const struct file_operations kmsg_fops = {
 	.release = devkmsg_release,
 };
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 /*
  * This appends the listed symbols to /proc/vmcore
  *

kernel/reboot.c

@@ -346,7 +346,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
 		kernel_restart(buffer);
 		break;
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	case LINUX_REBOOT_CMD_KEXEC:
 		ret = kernel_kexec();
 		break;

kernel/sysctl.c

@@ -621,7 +621,7 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	{
 		.procname	= "kexec_load_disabled",
 		.data		= &kexec_load_disabled,