[PATCH V2 2/2 update] kexec: split kexec_load syscall from kexec core code

Dave Young dyoung at redhat.com
Tue Jul 21 19:19:00 PDT 2015


Now there's two kexec load syscall, one is kexec_load another is
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 Tedso, 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.

Signed-off-by: Dave Young <dyoung at redhat.com>
---

Update per comments from Vivek:
- Moved below functions which are used by kexec_load only to kexec.c
  copy_user_segment_list() and kimage_alloc_init() 
- add slab.h to kexec.c because kimage_alloc_init will call kfree
- drop unused declaration of kimage_alloc_init in kexec.h

 arch/Kconfig                  |    3 
 arch/arm/Kconfig              |    1 
 arch/ia64/Kconfig             |    1 
 arch/m68k/Kconfig             |    1 
 arch/mips/Kconfig             |    1 
 arch/powerpc/Kconfig          |    1 
 arch/s390/Kconfig             |    1 
 arch/sh/Kconfig               |    1 
 arch/tile/Kconfig             |    1 
 arch/x86/Kconfig              |    3 
 arch/x86/boot/header.S        |    2 
 arch/x86/include/asm/kdebug.h |    2 
 arch/x86/kernel/Makefile      |    4 
 arch/x86/kernel/kvmclock.c    |    4 
 arch/x86/kernel/reboot.c      |    4 
 arch/x86/kernel/setup.c       |    2 
 arch/x86/kernel/vmlinux.lds.S |    2 
 arch/x86/kvm/vmx.c            |    8 
 arch/x86/platform/efi/efi.c   |    4 
 arch/x86/platform/uv/uv_nmi.c |    6 
 drivers/firmware/efi/Kconfig  |    2 
 drivers/pci/pci-driver.c      |    2 
 include/linux/kexec.h         |    6 
 init/initramfs.c              |    4 
 kernel/Makefile               |    1 
 kernel/events/core.c          |    2 
 kernel/kexec.c                | 1496 -----------------------------------------
 kernel/kexec_core.c           | 1511 ++++++++++++++++++++++++++++++++++++++++++
 kernel/ksysfs.c               |    6 
 kernel/printk/printk.c        |    2 
 kernel/reboot.c               |    2 
 kernel/sysctl.c               |    2 
 32 files changed, 1560 insertions(+), 1528 deletions(-)
 create mode 100644 kernel/kexec_core.c

--- linux.orig/arch/Kconfig
+++ linux/arch/Kconfig
@@ -2,6 +2,9 @@
 # General architecture dependent options
 #
 
+config KEXEC_CORE
+	bool
+
 config OPROFILE
 	tristate "OProfile system profiling"
 	depends on PROFILING
--- linux.orig/arch/arm/Kconfig
+++ linux/arch/arm/Kconfig
@@ -2005,6 +2005,7 @@ 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
--- linux.orig/arch/ia64/Kconfig
+++ linux/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
--- linux.orig/arch/m68k/Kconfig
+++ linux/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
--- linux.orig/arch/mips/Kconfig
+++ linux/arch/mips/Kconfig
@@ -2592,6 +2592,7 @@ 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
--- linux.orig/arch/powerpc/Kconfig
+++ linux/arch/powerpc/Kconfig
@@ -415,6 +415,7 @@ 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
--- linux.orig/arch/s390/Kconfig
+++ linux/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
--- linux.orig/arch/sh/Kconfig
+++ linux/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
--- linux.orig/arch/tile/Kconfig
+++ linux/arch/tile/Kconfig
@@ -204,6 +204,7 @@ 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
--- linux.orig/arch/x86/Kconfig
+++ linux/arch/x86/Kconfig
@@ -1724,6 +1724,7 @@ 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
@@ -1740,8 +1741,8 @@ 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
--- linux.orig/arch/x86/boot/header.S
+++ linux/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
--- linux.orig/arch/x86/include/asm/kdebug.h
+++ linux/arch/x86/include/asm/kdebug.h
@@ -29,7 +29,7 @@ extern void show_trace(struct task_struc
 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 */
--- linux.orig/arch/x86/kernel/Makefile
+++ linux/arch/x86/kernel/Makefile
@@ -69,8 +69,8 @@ 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/
--- linux.orig/arch/x86/kernel/kvmclock.c
+++ linux/arch/x86/kernel/kvmclock.c
@@ -200,7 +200,7 @@ static void kvm_setup_secondary_clock(vo
  * 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();
--- linux.orig/arch/x86/kernel/reboot.c
+++ linux/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);
--- linux.orig/arch/x86/kernel/setup.c
+++ linux/arch/x86/kernel/setup.c
@@ -498,7 +498,7 @@ static void __init memblock_x86_reserve_
  * --------- Crashkernel reservation ------------------------------
  */
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 
 /*
  * Keep the crash kernel below this limit.  On 32 bits earlier kernels
--- linux.orig/arch/x86/kernel/vmlinux.lds.S
+++ linux/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,
--- linux.orig/arch/x86/kvm/vmx.c
+++ linux/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_v
 #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)
 {
@@ -10425,7 +10425,7 @@ 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
@@ -10435,7 +10435,7 @@ 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
--- linux.orig/arch/x86/platform/efi/efi.c
+++ linux/arch/x86/platform/efi/efi.c
@@ -650,7 +650,7 @@ static void __init get_systab_virt_addr(
 
 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
 
 static void __init kexec_enter_virtual_mode(void)
 {
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	efi_memory_desc_t *md;
 	void *p;
 
--- linux.orig/arch/x86/platform/uv/uv_nmi.c
+++ linux/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 ma
 	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
--- linux.orig/drivers/firmware/efi/Kconfig
+++ linux/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.
--- linux.orig/drivers/pci/pci-driver.c
+++ linux/drivers/pci/pci-driver.c
@@ -453,7 +453,7 @@ static void pci_device_shutdown(struct d
 	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
--- linux.orig/include/linux/kexec.h
+++ linux/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>
@@ -318,12 +318,12 @@ int crash_shrink_memory(unsigned long ne
 size_t crash_get_memory_size(void);
 void crash_free_reserved_phys_range(unsigned long begin, unsigned long end);
 
-#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; }
-#endif /* CONFIG_KEXEC */
+#endif /* CONFIG_KEXEC_CORE */
 
 #endif /* !defined(__ASSEBMLY__) */
 
--- linux.orig/init/initramfs.c
+++ linux/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.
--- linux.orig/kernel/Makefile
+++ linux/kernel/Makefile
@@ -50,6 +50,7 @@ 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
--- linux.orig/kernel/events/core.c
+++ linux/kernel/events/core.c
@@ -8872,7 +8872,7 @@ 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 };
--- linux.orig/kernel/kexec.c
+++ linux/kernel/kexec.c
@@ -1,147 +1,21 @@
 /*
- * kexec.c - kexec system call
+ * kexec.c - kexec_load system call
  * Copyright (C) 2002-2004 Eric Biederman  <ebiederm at xmission.com>
  *
  * This source code is licensed under the GNU General Public License,
  * Version 2.  See the file COPYING for more details.
  */
 
-#define pr_fmt(fmt)	"kexec: " fmt
-
 #include <linux/capability.h>
 #include <linux/mm.h>
 #include <linux/file.h>
-#include <linux/slab.h>
-#include <linux/fs.h>
 #include <linux/kexec.h>
 #include <linux/mutex.h>
 #include <linux/list.h>
-#include <linux/highmem.h>
 #include <linux/syscalls.h>
-#include <linux/reboot.h>
-#include <linux/ioport.h>
-#include <linux/hardirq.h>
-#include <linux/elf.h>
-#include <linux/elfcore.h>
-#include <linux/utsname.h>
-#include <linux/numa.h>
-#include <linux/suspend.h>
-#include <linux/device.h>
-#include <linux/freezer.h>
-#include <linux/pm.h>
-#include <linux/cpu.h>
-#include <linux/console.h>
-#include <linux/swap.h>
-#include <linux/syscore_ops.h>
-#include <linux/compiler.h>
-#include <linux/hugetlb.h>
-
-#include <asm/page.h>
-#include <asm/uaccess.h>
-#include <asm/io.h>
-#include <asm/sections.h>
-
-#include <crypto/hash.h>
-#include <crypto/sha.h>
+#include <linux/slab.h>
 #include "kexec_internal.h"
 
-DEFINE_MUTEX(kexec_mutex);
-
-/* Per cpu memory for storing cpu states in case of system crash. */
-note_buf_t __percpu *crash_notes;
-
-/* vmcoreinfo stuff */
-static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
-u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
-size_t vmcoreinfo_size;
-size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
-
-/* Flag to indicate we are going to kexec a new kernel */
-bool kexec_in_progress = false;
-
-
-/* Location of the reserved area for the crash kernel */
-struct resource crashk_res = {
-	.name  = "Crash kernel",
-	.start = 0,
-	.end   = 0,
-	.flags = IORESOURCE_BUSY | IORESOURCE_MEM
-};
-struct resource crashk_low_res = {
-	.name  = "Crash kernel",
-	.start = 0,
-	.end   = 0,
-	.flags = IORESOURCE_BUSY | IORESOURCE_MEM
-};
-
-int kexec_should_crash(struct task_struct *p)
-{
-	/*
-	 * If crash_kexec_post_notifiers is enabled, don't run
-	 * crash_kexec() here yet, which must be run after panic
-	 * notifiers in panic().
-	 */
-	if (crash_kexec_post_notifiers)
-		return 0;
-	/*
-	 * There are 4 panic() calls in do_exit() path, each of which
-	 * corresponds to each of these 4 conditions.
-	 */
-	if (in_interrupt() || !p->pid || is_global_init(p) || panic_on_oops)
-		return 1;
-	return 0;
-}
-
-/*
- * When kexec transitions to the new kernel there is a one-to-one
- * mapping between physical and virtual addresses.  On processors
- * where you can disable the MMU this is trivial, and easy.  For
- * others it is still a simple predictable page table to setup.
- *
- * In that environment kexec copies the new kernel to its final
- * resting place.  This means I can only support memory whose
- * physical address can fit in an unsigned long.  In particular
- * addresses where (pfn << PAGE_SHIFT) > ULONG_MAX cannot be handled.
- * If the assembly stub has more restrictive requirements
- * KEXEC_SOURCE_MEMORY_LIMIT and KEXEC_DEST_MEMORY_LIMIT can be
- * defined more restrictively in <asm/kexec.h>.
- *
- * The code for the transition from the current kernel to the
- * the new kernel is placed in the control_code_buffer, whose size
- * is given by KEXEC_CONTROL_PAGE_SIZE.  In the best case only a single
- * page of memory is necessary, but some architectures require more.
- * Because this memory must be identity mapped in the transition from
- * virtual to physical addresses it must live in the range
- * 0 - TASK_SIZE, as only the user space mappings are arbitrarily
- * modifiable.
- *
- * The assembly stub in the control code buffer is passed a linked list
- * of descriptor pages detailing the source pages of the new kernel,
- * and the destination addresses of those source pages.  As this data
- * structure is not used in the context of the current OS, it must
- * be self-contained.
- *
- * The code has been made to work with highmem pages and will use a
- * destination page in its final resting place (if it happens
- * to allocate it).  The end product of this is that most of the
- * physical address space, and most of RAM can be used.
- *
- * Future directions include:
- *  - allocating a page table with the control code buffer identity
- *    mapped, to simplify machine_kexec and make kexec_on_panic more
- *    reliable.
- */
-
-/*
- * KIMAGE_NO_DEST is an impossible destination address..., for
- * allocating pages whose destination address we do not care about.
- */
-#define KIMAGE_NO_DEST (-1UL)
-
-static struct page *kimage_alloc_page(struct kimage *image,
-				       gfp_t gfp_mask,
-				       unsigned long dest);
-
 static int copy_user_segment_list(struct kimage *image,
 				  unsigned long nr_segments,
 				  struct kexec_segment __user *segments)
@@ -159,123 +33,6 @@ static int copy_user_segment_list(struct
 	return ret;
 }
 
-int sanity_check_segment_list(struct kimage *image)
-{
-	int result, i;
-	unsigned long nr_segments = image->nr_segments;
-
-	/*
-	 * Verify we have good destination addresses.  The caller is
-	 * responsible for making certain we don't attempt to load
-	 * the new image into invalid or reserved areas of RAM.  This
-	 * just verifies it is an address we can use.
-	 *
-	 * Since the kernel does everything in page size chunks ensure
-	 * the destination addresses are page aligned.  Too many
-	 * special cases crop of when we don't do this.  The most
-	 * insidious is getting overlapping destination addresses
-	 * simply because addresses are changed to page size
-	 * granularity.
-	 */
-	result = -EADDRNOTAVAIL;
-	for (i = 0; i < nr_segments; i++) {
-		unsigned long mstart, mend;
-
-		mstart = image->segment[i].mem;
-		mend   = mstart + image->segment[i].memsz;
-		if ((mstart & ~PAGE_MASK) || (mend & ~PAGE_MASK))
-			return result;
-		if (mend >= KEXEC_DESTINATION_MEMORY_LIMIT)
-			return result;
-	}
-
-	/* Verify our destination addresses do not overlap.
-	 * If we alloed overlapping destination addresses
-	 * through very weird things can happen with no
-	 * easy explanation as one segment stops on another.
-	 */
-	result = -EINVAL;
-	for (i = 0; i < nr_segments; i++) {
-		unsigned long mstart, mend;
-		unsigned long j;
-
-		mstart = image->segment[i].mem;
-		mend   = mstart + image->segment[i].memsz;
-		for (j = 0; j < i; j++) {
-			unsigned long pstart, pend;
-			pstart = image->segment[j].mem;
-			pend   = pstart + image->segment[j].memsz;
-			/* Do the segments overlap ? */
-			if ((mend > pstart) && (mstart < pend))
-				return result;
-		}
-	}
-
-	/* Ensure our buffer sizes are strictly less than
-	 * our memory sizes.  This should always be the case,
-	 * and it is easier to check up front than to be surprised
-	 * later on.
-	 */
-	result = -EINVAL;
-	for (i = 0; i < nr_segments; i++) {
-		if (image->segment[i].bufsz > image->segment[i].memsz)
-			return result;
-	}
-
-	/*
-	 * Verify we have good destination addresses.  Normally
-	 * the caller is responsible for making certain we don't
-	 * attempt to load the new image into invalid or reserved
-	 * areas of RAM.  But crash kernels are preloaded into a
-	 * reserved area of ram.  We must ensure the addresses
-	 * are in the reserved area otherwise preloading the
-	 * kernel could corrupt things.
-	 */
-
-	if (image->type == KEXEC_TYPE_CRASH) {
-		result = -EADDRNOTAVAIL;
-		for (i = 0; i < nr_segments; i++) {
-			unsigned long mstart, mend;
-
-			mstart = image->segment[i].mem;
-			mend = mstart + image->segment[i].memsz - 1;
-			/* Ensure we are within the crash kernel limits */
-			if ((mstart < crashk_res.start) ||
-			    (mend > crashk_res.end))
-				return result;
-		}
-	}
-
-	return 0;
-}
-
-struct kimage *do_kimage_alloc_init(void)
-{
-	struct kimage *image;
-
-	/* Allocate a controlling structure */
-	image = kzalloc(sizeof(*image), GFP_KERNEL);
-	if (!image)
-		return NULL;
-
-	image->head = 0;
-	image->entry = &image->head;
-	image->last_entry = &image->head;
-	image->control_page = ~0; /* By default this does not apply */
-	image->type = KEXEC_TYPE_DEFAULT;
-
-	/* Initialize the list of control pages */
-	INIT_LIST_HEAD(&image->control_pages);
-
-	/* Initialize the list of destination pages */
-	INIT_LIST_HEAD(&image->dest_pages);
-
-	/* Initialize the list of unusable pages */
-	INIT_LIST_HEAD(&image->unusable_pages);
-
-	return image;
-}
-
 static int kimage_alloc_init(struct kimage **rimage, unsigned long entry,
 			     unsigned long nr_segments,
 			     struct kexec_segment __user *segments,
@@ -342,597 +99,6 @@ out_free_image:
 	return ret;
 }
 
-int kimage_is_destination_range(struct kimage *image,
-					unsigned long start,
-					unsigned long end)
-{
-	unsigned long i;
-
-	for (i = 0; i < image->nr_segments; i++) {
-		unsigned long mstart, mend;
-
-		mstart = image->segment[i].mem;
-		mend = mstart + image->segment[i].memsz;
-		if ((end > mstart) && (start < mend))
-			return 1;
-	}
-
-	return 0;
-}
-
-static struct page *kimage_alloc_pages(gfp_t gfp_mask, unsigned int order)
-{
-	struct page *pages;
-
-	pages = alloc_pages(gfp_mask, order);
-	if (pages) {
-		unsigned int count, i;
-		pages->mapping = NULL;
-		set_page_private(pages, order);
-		count = 1 << order;
-		for (i = 0; i < count; i++)
-			SetPageReserved(pages + i);
-	}
-
-	return pages;
-}
-
-static void kimage_free_pages(struct page *page)
-{
-	unsigned int order, count, i;
-
-	order = page_private(page);
-	count = 1 << order;
-	for (i = 0; i < count; i++)
-		ClearPageReserved(page + i);
-	__free_pages(page, order);
-}
-
-void kimage_free_page_list(struct list_head *list)
-{
-	struct list_head *pos, *next;
-
-	list_for_each_safe(pos, next, list) {
-		struct page *page;
-
-		page = list_entry(pos, struct page, lru);
-		list_del(&page->lru);
-		kimage_free_pages(page);
-	}
-}
-
-static struct page *kimage_alloc_normal_control_pages(struct kimage *image,
-							unsigned int order)
-{
-	/* Control pages are special, they are the intermediaries
-	 * that are needed while we copy the rest of the pages
-	 * to their final resting place.  As such they must
-	 * not conflict with either the destination addresses
-	 * or memory the kernel is already using.
-	 *
-	 * The only case where we really need more than one of
-	 * these are for architectures where we cannot disable
-	 * the MMU and must instead generate an identity mapped
-	 * page table for all of the memory.
-	 *
-	 * At worst this runs in O(N) of the image size.
-	 */
-	struct list_head extra_pages;
-	struct page *pages;
-	unsigned int count;
-
-	count = 1 << order;
-	INIT_LIST_HEAD(&extra_pages);
-
-	/* Loop while I can allocate a page and the page allocated
-	 * is a destination page.
-	 */
-	do {
-		unsigned long pfn, epfn, addr, eaddr;
-
-		pages = kimage_alloc_pages(KEXEC_CONTROL_MEMORY_GFP, order);
-		if (!pages)
-			break;
-		pfn   = page_to_pfn(pages);
-		epfn  = pfn + count;
-		addr  = pfn << PAGE_SHIFT;
-		eaddr = epfn << PAGE_SHIFT;
-		if ((epfn >= (KEXEC_CONTROL_MEMORY_LIMIT >> PAGE_SHIFT)) ||
-			      kimage_is_destination_range(image, addr, eaddr)) {
-			list_add(&pages->lru, &extra_pages);
-			pages = NULL;
-		}
-	} while (!pages);
-
-	if (pages) {
-		/* Remember the allocated page... */
-		list_add(&pages->lru, &image->control_pages);
-
-		/* Because the page is already in it's destination
-		 * location we will never allocate another page at
-		 * that address.  Therefore kimage_alloc_pages
-		 * will not return it (again) and we don't need
-		 * to give it an entry in image->segment[].
-		 */
-	}
-	/* Deal with the destination pages I have inadvertently allocated.
-	 *
-	 * Ideally I would convert multi-page allocations into single
-	 * page allocations, and add everything to image->dest_pages.
-	 *
-	 * For now it is simpler to just free the pages.
-	 */
-	kimage_free_page_list(&extra_pages);
-
-	return pages;
-}
-
-static struct page *kimage_alloc_crash_control_pages(struct kimage *image,
-						      unsigned int order)
-{
-	/* Control pages are special, they are the intermediaries
-	 * that are needed while we copy the rest of the pages
-	 * to their final resting place.  As such they must
-	 * not conflict with either the destination addresses
-	 * or memory the kernel is already using.
-	 *
-	 * Control pages are also the only pags we must allocate
-	 * when loading a crash kernel.  All of the other pages
-	 * are specified by the segments and we just memcpy
-	 * into them directly.
-	 *
-	 * The only case where we really need more than one of
-	 * these are for architectures where we cannot disable
-	 * the MMU and must instead generate an identity mapped
-	 * page table for all of the memory.
-	 *
-	 * Given the low demand this implements a very simple
-	 * allocator that finds the first hole of the appropriate
-	 * size in the reserved memory region, and allocates all
-	 * of the memory up to and including the hole.
-	 */
-	unsigned long hole_start, hole_end, size;
-	struct page *pages;
-
-	pages = NULL;
-	size = (1 << order) << PAGE_SHIFT;
-	hole_start = (image->control_page + (size - 1)) & ~(size - 1);
-	hole_end   = hole_start + size - 1;
-	while (hole_end <= crashk_res.end) {
-		unsigned long i;
-
-		if (hole_end > KEXEC_CRASH_CONTROL_MEMORY_LIMIT)
-			break;
-		/* See if I overlap any of the segments */
-		for (i = 0; i < image->nr_segments; i++) {
-			unsigned long mstart, mend;
-
-			mstart = image->segment[i].mem;
-			mend   = mstart + image->segment[i].memsz - 1;
-			if ((hole_end >= mstart) && (hole_start <= mend)) {
-				/* Advance the hole to the end of the segment */
-				hole_start = (mend + (size - 1)) & ~(size - 1);
-				hole_end   = hole_start + size - 1;
-				break;
-			}
-		}
-		/* If I don't overlap any segments I have found my hole! */
-		if (i == image->nr_segments) {
-			pages = pfn_to_page(hole_start >> PAGE_SHIFT);
-			break;
-		}
-	}
-	if (pages)
-		image->control_page = hole_end;
-
-	return pages;
-}
-
-
-struct page *kimage_alloc_control_pages(struct kimage *image,
-					 unsigned int order)
-{
-	struct page *pages = NULL;
-
-	switch (image->type) {
-	case KEXEC_TYPE_DEFAULT:
-		pages = kimage_alloc_normal_control_pages(image, order);
-		break;
-	case KEXEC_TYPE_CRASH:
-		pages = kimage_alloc_crash_control_pages(image, order);
-		break;
-	}
-
-	return pages;
-}
-
-static int kimage_add_entry(struct kimage *image, kimage_entry_t entry)
-{
-	if (*image->entry != 0)
-		image->entry++;
-
-	if (image->entry == image->last_entry) {
-		kimage_entry_t *ind_page;
-		struct page *page;
-
-		page = kimage_alloc_page(image, GFP_KERNEL, KIMAGE_NO_DEST);
-		if (!page)
-			return -ENOMEM;
-
-		ind_page = page_address(page);
-		*image->entry = virt_to_phys(ind_page) | IND_INDIRECTION;
-		image->entry = ind_page;
-		image->last_entry = ind_page +
-				      ((PAGE_SIZE/sizeof(kimage_entry_t)) - 1);
-	}
-	*image->entry = entry;
-	image->entry++;
-	*image->entry = 0;
-
-	return 0;
-}
-
-static int kimage_set_destination(struct kimage *image,
-				   unsigned long destination)
-{
-	int result;
-
-	destination &= PAGE_MASK;
-	result = kimage_add_entry(image, destination | IND_DESTINATION);
-
-	return result;
-}
-
-
-static int kimage_add_page(struct kimage *image, unsigned long page)
-{
-	int result;
-
-	page &= PAGE_MASK;
-	result = kimage_add_entry(image, page | IND_SOURCE);
-
-	return result;
-}
-
-
-static void kimage_free_extra_pages(struct kimage *image)
-{
-	/* Walk through and free any extra destination pages I may have */
-	kimage_free_page_list(&image->dest_pages);
-
-	/* Walk through and free any unusable pages I have cached */
-	kimage_free_page_list(&image->unusable_pages);
-
-}
-void kimage_terminate(struct kimage *image)
-{
-	if (*image->entry != 0)
-		image->entry++;
-
-	*image->entry = IND_DONE;
-}
-
-#define for_each_kimage_entry(image, ptr, entry) \
-	for (ptr = &image->head; (entry = *ptr) && !(entry & IND_DONE); \
-		ptr = (entry & IND_INDIRECTION) ? \
-			phys_to_virt((entry & PAGE_MASK)) : ptr + 1)
-
-static void kimage_free_entry(kimage_entry_t entry)
-{
-	struct page *page;
-
-	page = pfn_to_page(entry >> PAGE_SHIFT);
-	kimage_free_pages(page);
-}
-
-void kimage_free(struct kimage *image)
-{
-	kimage_entry_t *ptr, entry;
-	kimage_entry_t ind = 0;
-
-	if (!image)
-		return;
-
-	kimage_free_extra_pages(image);
-	for_each_kimage_entry(image, ptr, entry) {
-		if (entry & IND_INDIRECTION) {
-			/* Free the previous indirection page */
-			if (ind & IND_INDIRECTION)
-				kimage_free_entry(ind);
-			/* Save this indirection page until we are
-			 * done with it.
-			 */
-			ind = entry;
-		} else if (entry & IND_SOURCE)
-			kimage_free_entry(entry);
-	}
-	/* Free the final indirection page */
-	if (ind & IND_INDIRECTION)
-		kimage_free_entry(ind);
-
-	/* Handle any machine specific cleanup */
-	machine_kexec_cleanup(image);
-
-	/* Free the kexec control pages... */
-	kimage_free_page_list(&image->control_pages);
-
-	/*
-	 * Free up any temporary buffers allocated. This might hit if
-	 * error occurred much later after buffer allocation.
-	 */
-	if (image->file_mode)
-		kimage_file_post_load_cleanup(image);
-
-	kfree(image);
-}
-
-static kimage_entry_t *kimage_dst_used(struct kimage *image,
-					unsigned long page)
-{
-	kimage_entry_t *ptr, entry;
-	unsigned long destination = 0;
-
-	for_each_kimage_entry(image, ptr, entry) {
-		if (entry & IND_DESTINATION)
-			destination = entry & PAGE_MASK;
-		else if (entry & IND_SOURCE) {
-			if (page == destination)
-				return ptr;
-			destination += PAGE_SIZE;
-		}
-	}
-
-	return NULL;
-}
-
-static struct page *kimage_alloc_page(struct kimage *image,
-					gfp_t gfp_mask,
-					unsigned long destination)
-{
-	/*
-	 * Here we implement safeguards to ensure that a source page
-	 * is not copied to its destination page before the data on
-	 * the destination page is no longer useful.
-	 *
-	 * To do this we maintain the invariant that a source page is
-	 * either its own destination page, or it is not a
-	 * destination page at all.
-	 *
-	 * That is slightly stronger than required, but the proof
-	 * that no problems will not occur is trivial, and the
-	 * implementation is simply to verify.
-	 *
-	 * When allocating all pages normally this algorithm will run
-	 * in O(N) time, but in the worst case it will run in O(N^2)
-	 * time.   If the runtime is a problem the data structures can
-	 * be fixed.
-	 */
-	struct page *page;
-	unsigned long addr;
-
-	/*
-	 * Walk through the list of destination pages, and see if I
-	 * have a match.
-	 */
-	list_for_each_entry(page, &image->dest_pages, lru) {
-		addr = page_to_pfn(page) << PAGE_SHIFT;
-		if (addr == destination) {
-			list_del(&page->lru);
-			return page;
-		}
-	}
-	page = NULL;
-	while (1) {
-		kimage_entry_t *old;
-
-		/* Allocate a page, if we run out of memory give up */
-		page = kimage_alloc_pages(gfp_mask, 0);
-		if (!page)
-			return NULL;
-		/* If the page cannot be used file it away */
-		if (page_to_pfn(page) >
-				(KEXEC_SOURCE_MEMORY_LIMIT >> PAGE_SHIFT)) {
-			list_add(&page->lru, &image->unusable_pages);
-			continue;
-		}
-		addr = page_to_pfn(page) << PAGE_SHIFT;
-
-		/* If it is the destination page we want use it */
-		if (addr == destination)
-			break;
-
-		/* If the page is not a destination page use it */
-		if (!kimage_is_destination_range(image, addr,
-						  addr + PAGE_SIZE))
-			break;
-
-		/*
-		 * I know that the page is someones destination page.
-		 * See if there is already a source page for this
-		 * destination page.  And if so swap the source pages.
-		 */
-		old = kimage_dst_used(image, addr);
-		if (old) {
-			/* If so move it */
-			unsigned long old_addr;
-			struct page *old_page;
-
-			old_addr = *old & PAGE_MASK;
-			old_page = pfn_to_page(old_addr >> PAGE_SHIFT);
-			copy_highpage(page, old_page);
-			*old = addr | (*old & ~PAGE_MASK);
-
-			/* The old page I have found cannot be a
-			 * destination page, so return it if it's
-			 * gfp_flags honor the ones passed in.
-			 */
-			if (!(gfp_mask & __GFP_HIGHMEM) &&
-			    PageHighMem(old_page)) {
-				kimage_free_pages(old_page);
-				continue;
-			}
-			addr = old_addr;
-			page = old_page;
-			break;
-		} else {
-			/* Place the page on the destination list I
-			 * will use it later.
-			 */
-			list_add(&page->lru, &image->dest_pages);
-		}
-	}
-
-	return page;
-}
-
-static int kimage_load_normal_segment(struct kimage *image,
-					 struct kexec_segment *segment)
-{
-	unsigned long maddr;
-	size_t ubytes, mbytes;
-	int result;
-	unsigned char __user *buf = NULL;
-	unsigned char *kbuf = NULL;
-
-	result = 0;
-	if (image->file_mode)
-		kbuf = segment->kbuf;
-	else
-		buf = segment->buf;
-	ubytes = segment->bufsz;
-	mbytes = segment->memsz;
-	maddr = segment->mem;
-
-	result = kimage_set_destination(image, maddr);
-	if (result < 0)
-		goto out;
-
-	while (mbytes) {
-		struct page *page;
-		char *ptr;
-		size_t uchunk, mchunk;
-
-		page = kimage_alloc_page(image, GFP_HIGHUSER, maddr);
-		if (!page) {
-			result  = -ENOMEM;
-			goto out;
-		}
-		result = kimage_add_page(image, page_to_pfn(page)
-								<< PAGE_SHIFT);
-		if (result < 0)
-			goto out;
-
-		ptr = kmap(page);
-		/* Start with a clear page */
-		clear_page(ptr);
-		ptr += maddr & ~PAGE_MASK;
-		mchunk = min_t(size_t, mbytes,
-				PAGE_SIZE - (maddr & ~PAGE_MASK));
-		uchunk = min(ubytes, mchunk);
-
-		/* For file based kexec, source pages are in kernel memory */
-		if (image->file_mode)
-			memcpy(ptr, kbuf, uchunk);
-		else
-			result = copy_from_user(ptr, buf, uchunk);
-		kunmap(page);
-		if (result) {
-			result = -EFAULT;
-			goto out;
-		}
-		ubytes -= uchunk;
-		maddr  += mchunk;
-		if (image->file_mode)
-			kbuf += mchunk;
-		else
-			buf += mchunk;
-		mbytes -= mchunk;
-	}
-out:
-	return result;
-}
-
-static int kimage_load_crash_segment(struct kimage *image,
-					struct kexec_segment *segment)
-{
-	/* For crash dumps kernels we simply copy the data from
-	 * user space to it's destination.
-	 * We do things a page at a time for the sake of kmap.
-	 */
-	unsigned long maddr;
-	size_t ubytes, mbytes;
-	int result;
-	unsigned char __user *buf = NULL;
-	unsigned char *kbuf = NULL;
-
-	result = 0;
-	if (image->file_mode)
-		kbuf = segment->kbuf;
-	else
-		buf = segment->buf;
-	ubytes = segment->bufsz;
-	mbytes = segment->memsz;
-	maddr = segment->mem;
-	while (mbytes) {
-		struct page *page;
-		char *ptr;
-		size_t uchunk, mchunk;
-
-		page = pfn_to_page(maddr >> PAGE_SHIFT);
-		if (!page) {
-			result  = -ENOMEM;
-			goto out;
-		}
-		ptr = kmap(page);
-		ptr += maddr & ~PAGE_MASK;
-		mchunk = min_t(size_t, mbytes,
-				PAGE_SIZE - (maddr & ~PAGE_MASK));
-		uchunk = min(ubytes, mchunk);
-		if (mchunk > uchunk) {
-			/* Zero the trailing part of the page */
-			memset(ptr + uchunk, 0, mchunk - uchunk);
-		}
-
-		/* For file based kexec, source pages are in kernel memory */
-		if (image->file_mode)
-			memcpy(ptr, kbuf, uchunk);
-		else
-			result = copy_from_user(ptr, buf, uchunk);
-		kexec_flush_icache_page(page);
-		kunmap(page);
-		if (result) {
-			result = -EFAULT;
-			goto out;
-		}
-		ubytes -= uchunk;
-		maddr  += mchunk;
-		if (image->file_mode)
-			kbuf += mchunk;
-		else
-			buf += mchunk;
-		mbytes -= mchunk;
-	}
-out:
-	return result;
-}
-
-int kimage_load_segment(struct kimage *image,
-				struct kexec_segment *segment)
-{
-	int result = -ENOMEM;
-
-	switch (image->type) {
-	case KEXEC_TYPE_DEFAULT:
-		result = kimage_load_normal_segment(image, segment);
-		break;
-	case KEXEC_TYPE_CRASH:
-		result = kimage_load_crash_segment(image, segment);
-		break;
-	}
-
-	return result;
-}
-
 /*
  * Exec Kernel system call: for obvious reasons only root may call it.
  *
@@ -953,9 +119,6 @@ int kimage_load_segment(struct kimage *i
  * kexec does not sync, or unmount filesystems so if you need
  * that to happen you need to do that yourself.
  */
-struct kimage *kexec_image;
-struct kimage *kexec_crash_image;
-int kexec_load_disabled;
 
 SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments,
 		struct kexec_segment __user *, segments, unsigned long, flags)
@@ -1050,18 +213,6 @@ out:
 	return result;
 }
 
-/*
- * Add and remove page tables for crashkernel memory
- *
- * Provide an empty default implementation here -- architecture
- * code may override this
- */
-void __weak crash_map_reserved_pages(void)
-{}
-
-void __weak crash_unmap_reserved_pages(void)
-{}
-
 #ifdef CONFIG_COMPAT
 COMPAT_SYSCALL_DEFINE4(kexec_load, compat_ulong_t, entry,
 		       compat_ulong_t, nr_segments,
@@ -1100,646 +251,3 @@ COMPAT_SYSCALL_DEFINE4(kexec_load, compa
 	return sys_kexec_load(entry, nr_segments, ksegments, flags);
 }
 #endif
-
-void crash_kexec(struct pt_regs *regs)
-{
-	/* Take the kexec_mutex here to prevent sys_kexec_load
-	 * running on one cpu from replacing the crash kernel
-	 * we are using after a panic on a different cpu.
-	 *
-	 * If the crash kernel was not located in a fixed area
-	 * of memory the xchg(&kexec_crash_image) would be
-	 * sufficient.  But since I reuse the memory...
-	 */
-	if (mutex_trylock(&kexec_mutex)) {
-		if (kexec_crash_image) {
-			struct pt_regs fixed_regs;
-
-			crash_setup_regs(&fixed_regs, regs);
-			crash_save_vmcoreinfo();
-			machine_crash_shutdown(&fixed_regs);
-			machine_kexec(kexec_crash_image);
-		}
-		mutex_unlock(&kexec_mutex);
-	}
-}
-
-size_t crash_get_memory_size(void)
-{
-	size_t size = 0;
-	mutex_lock(&kexec_mutex);
-	if (crashk_res.end != crashk_res.start)
-		size = resource_size(&crashk_res);
-	mutex_unlock(&kexec_mutex);
-	return size;
-}
-
-void __weak crash_free_reserved_phys_range(unsigned long begin,
-					   unsigned long end)
-{
-	unsigned long addr;
-
-	for (addr = begin; addr < end; addr += PAGE_SIZE)
-		free_reserved_page(pfn_to_page(addr >> PAGE_SHIFT));
-}
-
-int crash_shrink_memory(unsigned long new_size)
-{
-	int ret = 0;
-	unsigned long start, end;
-	unsigned long old_size;
-	struct resource *ram_res;
-
-	mutex_lock(&kexec_mutex);
-
-	if (kexec_crash_image) {
-		ret = -ENOENT;
-		goto unlock;
-	}
-	start = crashk_res.start;
-	end = crashk_res.end;
-	old_size = (end == 0) ? 0 : end - start + 1;
-	if (new_size >= old_size) {
-		ret = (new_size == old_size) ? 0 : -EINVAL;
-		goto unlock;
-	}
-
-	ram_res = kzalloc(sizeof(*ram_res), GFP_KERNEL);
-	if (!ram_res) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
-
-	start = roundup(start, KEXEC_CRASH_MEM_ALIGN);
-	end = roundup(start + new_size, KEXEC_CRASH_MEM_ALIGN);
-
-	crash_map_reserved_pages();
-	crash_free_reserved_phys_range(end, crashk_res.end);
-
-	if ((start == end) && (crashk_res.parent != NULL))
-		release_resource(&crashk_res);
-
-	ram_res->start = end;
-	ram_res->end = crashk_res.end;
-	ram_res->flags = IORESOURCE_BUSY | IORESOURCE_MEM;
-	ram_res->name = "System RAM";
-
-	crashk_res.end = end - 1;
-
-	insert_resource(&iomem_resource, ram_res);
-	crash_unmap_reserved_pages();
-
-unlock:
-	mutex_unlock(&kexec_mutex);
-	return ret;
-}
-
-static u32 *append_elf_note(u32 *buf, char *name, unsigned type, void *data,
-			    size_t data_len)
-{
-	struct elf_note note;
-
-	note.n_namesz = strlen(name) + 1;
-	note.n_descsz = data_len;
-	note.n_type   = type;
-	memcpy(buf, &note, sizeof(note));
-	buf += (sizeof(note) + 3)/4;
-	memcpy(buf, name, note.n_namesz);
-	buf += (note.n_namesz + 3)/4;
-	memcpy(buf, data, note.n_descsz);
-	buf += (note.n_descsz + 3)/4;
-
-	return buf;
-}
-
-static void final_note(u32 *buf)
-{
-	struct elf_note note;
-
-	note.n_namesz = 0;
-	note.n_descsz = 0;
-	note.n_type   = 0;
-	memcpy(buf, &note, sizeof(note));
-}
-
-void crash_save_cpu(struct pt_regs *regs, int cpu)
-{
-	struct elf_prstatus prstatus;
-	u32 *buf;
-
-	if ((cpu < 0) || (cpu >= nr_cpu_ids))
-		return;
-
-	/* Using ELF notes here is opportunistic.
-	 * I need a well defined structure format
-	 * for the data I pass, and I need tags
-	 * on the data to indicate what information I have
-	 * squirrelled away.  ELF notes happen to provide
-	 * all of that, so there is no need to invent something new.
-	 */
-	buf = (u32 *)per_cpu_ptr(crash_notes, cpu);
-	if (!buf)
-		return;
-	memset(&prstatus, 0, sizeof(prstatus));
-	prstatus.pr_pid = current->pid;
-	elf_core_copy_kernel_regs(&prstatus.pr_reg, regs);
-	buf = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS,
-			      &prstatus, sizeof(prstatus));
-	final_note(buf);
-}
-
-static int __init crash_notes_memory_init(void)
-{
-	/* Allocate memory for saving cpu registers. */
-	crash_notes = alloc_percpu(note_buf_t);
-	if (!crash_notes) {
-		pr_warn("Kexec: Memory allocation for saving cpu register states failed\n");
-		return -ENOMEM;
-	}
-	return 0;
-}
-subsys_initcall(crash_notes_memory_init);
-
-
-/*
- * parsing the "crashkernel" commandline
- *
- * this code is intended to be called from architecture specific code
- */
-
-
-/*
- * This function parses command lines in the format
- *
- *   crashkernel=ramsize-range:size[,...][@offset]
- *
- * The function returns 0 on success and -EINVAL on failure.
- */
-static int __init parse_crashkernel_mem(char *cmdline,
-					unsigned long long system_ram,
-					unsigned long long *crash_size,
-					unsigned long long *crash_base)
-{
-	char *cur = cmdline, *tmp;
-
-	/* for each entry of the comma-separated list */
-	do {
-		unsigned long long start, end = ULLONG_MAX, size;
-
-		/* get the start of the range */
-		start = memparse(cur, &tmp);
-		if (cur == tmp) {
-			pr_warn("crashkernel: Memory value expected\n");
-			return -EINVAL;
-		}
-		cur = tmp;
-		if (*cur != '-') {
-			pr_warn("crashkernel: '-' expected\n");
-			return -EINVAL;
-		}
-		cur++;
-
-		/* if no ':' is here, than we read the end */
-		if (*cur != ':') {
-			end = memparse(cur, &tmp);
-			if (cur == tmp) {
-				pr_warn("crashkernel: Memory value expected\n");
-				return -EINVAL;
-			}
-			cur = tmp;
-			if (end <= start) {
-				pr_warn("crashkernel: end <= start\n");
-				return -EINVAL;
-			}
-		}
-
-		if (*cur != ':') {
-			pr_warn("crashkernel: ':' expected\n");
-			return -EINVAL;
-		}
-		cur++;
-
-		size = memparse(cur, &tmp);
-		if (cur == tmp) {
-			pr_warn("Memory value expected\n");
-			return -EINVAL;
-		}
-		cur = tmp;
-		if (size >= system_ram) {
-			pr_warn("crashkernel: invalid size\n");
-			return -EINVAL;
-		}
-
-		/* match ? */
-		if (system_ram >= start && system_ram < end) {
-			*crash_size = size;
-			break;
-		}
-	} while (*cur++ == ',');
-
-	if (*crash_size > 0) {
-		while (*cur && *cur != ' ' && *cur != '@')
-			cur++;
-		if (*cur == '@') {
-			cur++;
-			*crash_base = memparse(cur, &tmp);
-			if (cur == tmp) {
-				pr_warn("Memory value expected after '@'\n");
-				return -EINVAL;
-			}
-		}
-	}
-
-	return 0;
-}
-
-/*
- * That function parses "simple" (old) crashkernel command lines like
- *
- *	crashkernel=size[@offset]
- *
- * It returns 0 on success and -EINVAL on failure.
- */
-static int __init parse_crashkernel_simple(char *cmdline,
-					   unsigned long long *crash_size,
-					   unsigned long long *crash_base)
-{
-	char *cur = cmdline;
-
-	*crash_size = memparse(cmdline, &cur);
-	if (cmdline == cur) {
-		pr_warn("crashkernel: memory value expected\n");
-		return -EINVAL;
-	}
-
-	if (*cur == '@')
-		*crash_base = memparse(cur+1, &cur);
-	else if (*cur != ' ' && *cur != '\0') {
-		pr_warn("crashkernel: unrecognized char\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-#define SUFFIX_HIGH 0
-#define SUFFIX_LOW  1
-#define SUFFIX_NULL 2
-static __initdata char *suffix_tbl[] = {
-	[SUFFIX_HIGH] = ",high",
-	[SUFFIX_LOW]  = ",low",
-	[SUFFIX_NULL] = NULL,
-};
-
-/*
- * That function parses "suffix"  crashkernel command lines like
- *
- *	crashkernel=size,[high|low]
- *
- * It returns 0 on success and -EINVAL on failure.
- */
-static int __init parse_crashkernel_suffix(char *cmdline,
-					   unsigned long long	*crash_size,
-					   const char *suffix)
-{
-	char *cur = cmdline;
-
-	*crash_size = memparse(cmdline, &cur);
-	if (cmdline == cur) {
-		pr_warn("crashkernel: memory value expected\n");
-		return -EINVAL;
-	}
-
-	/* check with suffix */
-	if (strncmp(cur, suffix, strlen(suffix))) {
-		pr_warn("crashkernel: unrecognized char\n");
-		return -EINVAL;
-	}
-	cur += strlen(suffix);
-	if (*cur != ' ' && *cur != '\0') {
-		pr_warn("crashkernel: unrecognized char\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static __init char *get_last_crashkernel(char *cmdline,
-			     const char *name,
-			     const char *suffix)
-{
-	char *p = cmdline, *ck_cmdline = NULL;
-
-	/* find crashkernel and use the last one if there are more */
-	p = strstr(p, name);
-	while (p) {
-		char *end_p = strchr(p, ' ');
-		char *q;
-
-		if (!end_p)
-			end_p = p + strlen(p);
-
-		if (!suffix) {
-			int i;
-
-			/* skip the one with any known suffix */
-			for (i = 0; suffix_tbl[i]; i++) {
-				q = end_p - strlen(suffix_tbl[i]);
-				if (!strncmp(q, suffix_tbl[i],
-					     strlen(suffix_tbl[i])))
-					goto next;
-			}
-			ck_cmdline = p;
-		} else {
-			q = end_p - strlen(suffix);
-			if (!strncmp(q, suffix, strlen(suffix)))
-				ck_cmdline = p;
-		}
-next:
-		p = strstr(p+1, name);
-	}
-
-	if (!ck_cmdline)
-		return NULL;
-
-	return ck_cmdline;
-}
-
-static int __init __parse_crashkernel(char *cmdline,
-			     unsigned long long system_ram,
-			     unsigned long long *crash_size,
-			     unsigned long long *crash_base,
-			     const char *name,
-			     const char *suffix)
-{
-	char	*first_colon, *first_space;
-	char	*ck_cmdline;
-
-	BUG_ON(!crash_size || !crash_base);
-	*crash_size = 0;
-	*crash_base = 0;
-
-	ck_cmdline = get_last_crashkernel(cmdline, name, suffix);
-
-	if (!ck_cmdline)
-		return -EINVAL;
-
-	ck_cmdline += strlen(name);
-
-	if (suffix)
-		return parse_crashkernel_suffix(ck_cmdline, crash_size,
-				suffix);
-	/*
-	 * if the commandline contains a ':', then that's the extended
-	 * syntax -- if not, it must be the classic syntax
-	 */
-	first_colon = strchr(ck_cmdline, ':');
-	first_space = strchr(ck_cmdline, ' ');
-	if (first_colon && (!first_space || first_colon < first_space))
-		return parse_crashkernel_mem(ck_cmdline, system_ram,
-				crash_size, crash_base);
-
-	return parse_crashkernel_simple(ck_cmdline, crash_size, crash_base);
-}
-
-/*
- * That function is the entry point for command line parsing and should be
- * called from the arch-specific code.
- */
-int __init parse_crashkernel(char *cmdline,
-			     unsigned long long system_ram,
-			     unsigned long long *crash_size,
-			     unsigned long long *crash_base)
-{
-	return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
-					"crashkernel=", NULL);
-}
-
-int __init parse_crashkernel_high(char *cmdline,
-			     unsigned long long system_ram,
-			     unsigned long long *crash_size,
-			     unsigned long long *crash_base)
-{
-	return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
-				"crashkernel=", suffix_tbl[SUFFIX_HIGH]);
-}
-
-int __init parse_crashkernel_low(char *cmdline,
-			     unsigned long long system_ram,
-			     unsigned long long *crash_size,
-			     unsigned long long *crash_base)
-{
-	return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
-				"crashkernel=", suffix_tbl[SUFFIX_LOW]);
-}
-
-static void update_vmcoreinfo_note(void)
-{
-	u32 *buf = vmcoreinfo_note;
-
-	if (!vmcoreinfo_size)
-		return;
-	buf = append_elf_note(buf, VMCOREINFO_NOTE_NAME, 0, vmcoreinfo_data,
-			      vmcoreinfo_size);
-	final_note(buf);
-}
-
-void crash_save_vmcoreinfo(void)
-{
-	vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds());
-	update_vmcoreinfo_note();
-}
-
-void vmcoreinfo_append_str(const char *fmt, ...)
-{
-	va_list args;
-	char buf[0x50];
-	size_t r;
-
-	va_start(args, fmt);
-	r = vscnprintf(buf, sizeof(buf), fmt, args);
-	va_end(args);
-
-	r = min(r, vmcoreinfo_max_size - vmcoreinfo_size);
-
-	memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r);
-
-	vmcoreinfo_size += r;
-}
-
-/*
- * provide an empty default implementation here -- architecture
- * code may override this
- */
-void __weak arch_crash_save_vmcoreinfo(void)
-{}
-
-unsigned long __weak paddr_vmcoreinfo_note(void)
-{
-	return __pa((unsigned long)(char *)&vmcoreinfo_note);
-}
-
-static int __init crash_save_vmcoreinfo_init(void)
-{
-	VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
-	VMCOREINFO_PAGESIZE(PAGE_SIZE);
-
-	VMCOREINFO_SYMBOL(init_uts_ns);
-	VMCOREINFO_SYMBOL(node_online_map);
-#ifdef CONFIG_MMU
-	VMCOREINFO_SYMBOL(swapper_pg_dir);
-#endif
-	VMCOREINFO_SYMBOL(_stext);
-	VMCOREINFO_SYMBOL(vmap_area_list);
-
-#ifndef CONFIG_NEED_MULTIPLE_NODES
-	VMCOREINFO_SYMBOL(mem_map);
-	VMCOREINFO_SYMBOL(contig_page_data);
-#endif
-#ifdef CONFIG_SPARSEMEM
-	VMCOREINFO_SYMBOL(mem_section);
-	VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS);
-	VMCOREINFO_STRUCT_SIZE(mem_section);
-	VMCOREINFO_OFFSET(mem_section, section_mem_map);
-#endif
-	VMCOREINFO_STRUCT_SIZE(page);
-	VMCOREINFO_STRUCT_SIZE(pglist_data);
-	VMCOREINFO_STRUCT_SIZE(zone);
-	VMCOREINFO_STRUCT_SIZE(free_area);
-	VMCOREINFO_STRUCT_SIZE(list_head);
-	VMCOREINFO_SIZE(nodemask_t);
-	VMCOREINFO_OFFSET(page, flags);
-	VMCOREINFO_OFFSET(page, _count);
-	VMCOREINFO_OFFSET(page, mapping);
-	VMCOREINFO_OFFSET(page, lru);
-	VMCOREINFO_OFFSET(page, _mapcount);
-	VMCOREINFO_OFFSET(page, private);
-	VMCOREINFO_OFFSET(pglist_data, node_zones);
-	VMCOREINFO_OFFSET(pglist_data, nr_zones);
-#ifdef CONFIG_FLAT_NODE_MEM_MAP
-	VMCOREINFO_OFFSET(pglist_data, node_mem_map);
-#endif
-	VMCOREINFO_OFFSET(pglist_data, node_start_pfn);
-	VMCOREINFO_OFFSET(pglist_data, node_spanned_pages);
-	VMCOREINFO_OFFSET(pglist_data, node_id);
-	VMCOREINFO_OFFSET(zone, free_area);
-	VMCOREINFO_OFFSET(zone, vm_stat);
-	VMCOREINFO_OFFSET(zone, spanned_pages);
-	VMCOREINFO_OFFSET(free_area, free_list);
-	VMCOREINFO_OFFSET(list_head, next);
-	VMCOREINFO_OFFSET(list_head, prev);
-	VMCOREINFO_OFFSET(vmap_area, va_start);
-	VMCOREINFO_OFFSET(vmap_area, list);
-	VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER);
-	log_buf_kexec_setup();
-	VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
-	VMCOREINFO_NUMBER(NR_FREE_PAGES);
-	VMCOREINFO_NUMBER(PG_lru);
-	VMCOREINFO_NUMBER(PG_private);
-	VMCOREINFO_NUMBER(PG_swapcache);
-	VMCOREINFO_NUMBER(PG_slab);
-#ifdef CONFIG_MEMORY_FAILURE
-	VMCOREINFO_NUMBER(PG_hwpoison);
-#endif
-	VMCOREINFO_NUMBER(PG_head_mask);
-	VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE);
-#ifdef CONFIG_HUGETLBFS
-	VMCOREINFO_SYMBOL(free_huge_page);
-#endif
-
-	arch_crash_save_vmcoreinfo();
-	update_vmcoreinfo_note();
-
-	return 0;
-}
-
-subsys_initcall(crash_save_vmcoreinfo_init);
-
-/*
- * Move into place and start executing a preloaded standalone
- * executable.  If nothing was preloaded return an error.
- */
-int kernel_kexec(void)
-{
-	int error = 0;
-
-	if (!mutex_trylock(&kexec_mutex))
-		return -EBUSY;
-	if (!kexec_image) {
-		error = -EINVAL;
-		goto Unlock;
-	}
-
-#ifdef CONFIG_KEXEC_JUMP
-	if (kexec_image->preserve_context) {
-		lock_system_sleep();
-		pm_prepare_console();
-		error = freeze_processes();
-		if (error) {
-			error = -EBUSY;
-			goto Restore_console;
-		}
-		suspend_console();
-		error = dpm_suspend_start(PMSG_FREEZE);
-		if (error)
-			goto Resume_console;
-		/* At this point, dpm_suspend_start() has been called,
-		 * but *not* dpm_suspend_end(). We *must* call
-		 * dpm_suspend_end() now.  Otherwise, drivers for
-		 * some devices (e.g. interrupt controllers) become
-		 * desynchronized with the actual state of the
-		 * hardware at resume time, and evil weirdness ensues.
-		 */
-		error = dpm_suspend_end(PMSG_FREEZE);
-		if (error)
-			goto Resume_devices;
-		error = disable_nonboot_cpus();
-		if (error)
-			goto Enable_cpus;
-		local_irq_disable();
-		error = syscore_suspend();
-		if (error)
-			goto Enable_irqs;
-	} else
-#endif
-	{
-		kexec_in_progress = true;
-		kernel_restart_prepare(NULL);
-		migrate_to_reboot_cpu();
-
-		/*
-		 * migrate_to_reboot_cpu() disables CPU hotplug assuming that
-		 * no further code needs to use CPU hotplug (which is true in
-		 * the reboot case). However, the kexec path depends on using
-		 * CPU hotplug again; so re-enable it here.
-		 */
-		cpu_hotplug_enable();
-		pr_emerg("Starting new kernel\n");
-		machine_shutdown();
-	}
-
-	machine_kexec(kexec_image);
-
-#ifdef CONFIG_KEXEC_JUMP
-	if (kexec_image->preserve_context) {
-		syscore_resume();
- Enable_irqs:
-		local_irq_enable();
- Enable_cpus:
-		enable_nonboot_cpus();
-		dpm_resume_start(PMSG_RESTORE);
- Resume_devices:
-		dpm_resume_end(PMSG_RESTORE);
- Resume_console:
-		resume_console();
-		thaw_processes();
- Restore_console:
-		pm_restore_console();
-		unlock_system_sleep();
-	}
-#endif
-
- Unlock:
-	mutex_unlock(&kexec_mutex);
-	return error;
-}
--- /dev/null
+++ linux/kernel/kexec_core.c
@@ -0,0 +1,1511 @@
+/*
+ * kexec.c - kexec system call core code.
+ * Copyright (C) 2002-2004 Eric Biederman  <ebiederm at xmission.com>
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2.  See the file COPYING for more details.
+ */
+
+#define pr_fmt(fmt)	"kexec: " fmt
+
+#include <linux/capability.h>
+#include <linux/mm.h>
+#include <linux/file.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/kexec.h>
+#include <linux/mutex.h>
+#include <linux/list.h>
+#include <linux/highmem.h>
+#include <linux/syscalls.h>
+#include <linux/reboot.h>
+#include <linux/ioport.h>
+#include <linux/hardirq.h>
+#include <linux/elf.h>
+#include <linux/elfcore.h>
+#include <linux/utsname.h>
+#include <linux/numa.h>
+#include <linux/suspend.h>
+#include <linux/device.h>
+#include <linux/freezer.h>
+#include <linux/pm.h>
+#include <linux/cpu.h>
+#include <linux/console.h>
+#include <linux/vmalloc.h>
+#include <linux/swap.h>
+#include <linux/syscore_ops.h>
+#include <linux/compiler.h>
+#include <linux/hugetlb.h>
+
+#include <asm/page.h>
+#include <asm/uaccess.h>
+#include <asm/io.h>
+#include <asm/sections.h>
+
+#include <crypto/hash.h>
+#include <crypto/sha.h>
+#include "kexec_internal.h"
+
+DEFINE_MUTEX(kexec_mutex);
+
+/* Per cpu memory for storing cpu states in case of system crash. */
+note_buf_t __percpu *crash_notes;
+
+/* vmcoreinfo stuff */
+static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
+u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
+size_t vmcoreinfo_size;
+size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
+
+/* Flag to indicate we are going to kexec a new kernel */
+bool kexec_in_progress = false;
+
+
+/* Location of the reserved area for the crash kernel */
+struct resource crashk_res = {
+	.name  = "Crash kernel",
+	.start = 0,
+	.end   = 0,
+	.flags = IORESOURCE_BUSY | IORESOURCE_MEM
+};
+struct resource crashk_low_res = {
+	.name  = "Crash kernel",
+	.start = 0,
+	.end   = 0,
+	.flags = IORESOURCE_BUSY | IORESOURCE_MEM
+};
+
+int kexec_should_crash(struct task_struct *p)
+{
+	/*
+	 * If crash_kexec_post_notifiers is enabled, don't run
+	 * crash_kexec() here yet, which must be run after panic
+	 * notifiers in panic().
+	 */
+	if (crash_kexec_post_notifiers)
+		return 0;
+	/*
+	 * There are 4 panic() calls in do_exit() path, each of which
+	 * corresponds to each of these 4 conditions.
+	 */
+	if (in_interrupt() || !p->pid || is_global_init(p) || panic_on_oops)
+		return 1;
+	return 0;
+}
+
+/*
+ * When kexec transitions to the new kernel there is a one-to-one
+ * mapping between physical and virtual addresses.  On processors
+ * where you can disable the MMU this is trivial, and easy.  For
+ * others it is still a simple predictable page table to setup.
+ *
+ * In that environment kexec copies the new kernel to its final
+ * resting place.  This means I can only support memory whose
+ * physical address can fit in an unsigned long.  In particular
+ * addresses where (pfn << PAGE_SHIFT) > ULONG_MAX cannot be handled.
+ * If the assembly stub has more restrictive requirements
+ * KEXEC_SOURCE_MEMORY_LIMIT and KEXEC_DEST_MEMORY_LIMIT can be
+ * defined more restrictively in <asm/kexec.h>.
+ *
+ * The code for the transition from the current kernel to the
+ * the new kernel is placed in the control_code_buffer, whose size
+ * is given by KEXEC_CONTROL_PAGE_SIZE.  In the best case only a single
+ * page of memory is necessary, but some architectures require more.
+ * Because this memory must be identity mapped in the transition from
+ * virtual to physical addresses it must live in the range
+ * 0 - TASK_SIZE, as only the user space mappings are arbitrarily
+ * modifiable.
+ *
+ * The assembly stub in the control code buffer is passed a linked list
+ * of descriptor pages detailing the source pages of the new kernel,
+ * and the destination addresses of those source pages.  As this data
+ * structure is not used in the context of the current OS, it must
+ * be self-contained.
+ *
+ * The code has been made to work with highmem pages and will use a
+ * destination page in its final resting place (if it happens
+ * to allocate it).  The end product of this is that most of the
+ * physical address space, and most of RAM can be used.
+ *
+ * Future directions include:
+ *  - allocating a page table with the control code buffer identity
+ *    mapped, to simplify machine_kexec and make kexec_on_panic more
+ *    reliable.
+ */
+
+/*
+ * KIMAGE_NO_DEST is an impossible destination address..., for
+ * allocating pages whose destination address we do not care about.
+ */
+#define KIMAGE_NO_DEST (-1UL)
+
+static struct page *kimage_alloc_page(struct kimage *image,
+				       gfp_t gfp_mask,
+				       unsigned long dest);
+
+int sanity_check_segment_list(struct kimage *image)
+{
+	int result, i;
+	unsigned long nr_segments = image->nr_segments;
+
+	/*
+	 * Verify we have good destination addresses.  The caller is
+	 * responsible for making certain we don't attempt to load
+	 * the new image into invalid or reserved areas of RAM.  This
+	 * just verifies it is an address we can use.
+	 *
+	 * Since the kernel does everything in page size chunks ensure
+	 * the destination addresses are page aligned.  Too many
+	 * special cases crop of when we don't do this.  The most
+	 * insidious is getting overlapping destination addresses
+	 * simply because addresses are changed to page size
+	 * granularity.
+	 */
+	result = -EADDRNOTAVAIL;
+	for (i = 0; i < nr_segments; i++) {
+		unsigned long mstart, mend;
+
+		mstart = image->segment[i].mem;
+		mend   = mstart + image->segment[i].memsz;
+		if ((mstart & ~PAGE_MASK) || (mend & ~PAGE_MASK))
+			return result;
+		if (mend >= KEXEC_DESTINATION_MEMORY_LIMIT)
+			return result;
+	}
+
+	/* Verify our destination addresses do not overlap.
+	 * If we alloed overlapping destination addresses
+	 * through very weird things can happen with no
+	 * easy explanation as one segment stops on another.
+	 */
+	result = -EINVAL;
+	for (i = 0; i < nr_segments; i++) {
+		unsigned long mstart, mend;
+		unsigned long j;
+
+		mstart = image->segment[i].mem;
+		mend   = mstart + image->segment[i].memsz;
+		for (j = 0; j < i; j++) {
+			unsigned long pstart, pend;
+			pstart = image->segment[j].mem;
+			pend   = pstart + image->segment[j].memsz;
+			/* Do the segments overlap ? */
+			if ((mend > pstart) && (mstart < pend))
+				return result;
+		}
+	}
+
+	/* Ensure our buffer sizes are strictly less than
+	 * our memory sizes.  This should always be the case,
+	 * and it is easier to check up front than to be surprised
+	 * later on.
+	 */
+	result = -EINVAL;
+	for (i = 0; i < nr_segments; i++) {
+		if (image->segment[i].bufsz > image->segment[i].memsz)
+			return result;
+	}
+
+	/*
+	 * Verify we have good destination addresses.  Normally
+	 * the caller is responsible for making certain we don't
+	 * attempt to load the new image into invalid or reserved
+	 * areas of RAM.  But crash kernels are preloaded into a
+	 * reserved area of ram.  We must ensure the addresses
+	 * are in the reserved area otherwise preloading the
+	 * kernel could corrupt things.
+	 */
+
+	if (image->type == KEXEC_TYPE_CRASH) {
+		result = -EADDRNOTAVAIL;
+		for (i = 0; i < nr_segments; i++) {
+			unsigned long mstart, mend;
+
+			mstart = image->segment[i].mem;
+			mend = mstart + image->segment[i].memsz - 1;
+			/* Ensure we are within the crash kernel limits */
+			if ((mstart < crashk_res.start) ||
+			    (mend > crashk_res.end))
+				return result;
+		}
+	}
+
+	return 0;
+}
+
+struct kimage *do_kimage_alloc_init(void)
+{
+	struct kimage *image;
+
+	/* Allocate a controlling structure */
+	image = kzalloc(sizeof(*image), GFP_KERNEL);
+	if (!image)
+		return NULL;
+
+	image->head = 0;
+	image->entry = &image->head;
+	image->last_entry = &image->head;
+	image->control_page = ~0; /* By default this does not apply */
+	image->type = KEXEC_TYPE_DEFAULT;
+
+	/* Initialize the list of control pages */
+	INIT_LIST_HEAD(&image->control_pages);
+
+	/* Initialize the list of destination pages */
+	INIT_LIST_HEAD(&image->dest_pages);
+
+	/* Initialize the list of unusable pages */
+	INIT_LIST_HEAD(&image->unusable_pages);
+
+	return image;
+}
+
+int kimage_is_destination_range(struct kimage *image,
+					unsigned long start,
+					unsigned long end)
+{
+	unsigned long i;
+
+	for (i = 0; i < image->nr_segments; i++) {
+		unsigned long mstart, mend;
+
+		mstart = image->segment[i].mem;
+		mend = mstart + image->segment[i].memsz;
+		if ((end > mstart) && (start < mend))
+			return 1;
+	}
+
+	return 0;
+}
+
+static struct page *kimage_alloc_pages(gfp_t gfp_mask, unsigned int order)
+{
+	struct page *pages;
+
+	pages = alloc_pages(gfp_mask, order);
+	if (pages) {
+		unsigned int count, i;
+		pages->mapping = NULL;
+		set_page_private(pages, order);
+		count = 1 << order;
+		for (i = 0; i < count; i++)
+			SetPageReserved(pages + i);
+	}
+
+	return pages;
+}
+
+static void kimage_free_pages(struct page *page)
+{
+	unsigned int order, count, i;
+
+	order = page_private(page);
+	count = 1 << order;
+	for (i = 0; i < count; i++)
+		ClearPageReserved(page + i);
+	__free_pages(page, order);
+}
+
+void kimage_free_page_list(struct list_head *list)
+{
+	struct list_head *pos, *next;
+
+	list_for_each_safe(pos, next, list) {
+		struct page *page;
+
+		page = list_entry(pos, struct page, lru);
+		list_del(&page->lru);
+		kimage_free_pages(page);
+	}
+}
+
+static struct page *kimage_alloc_normal_control_pages(struct kimage *image,
+							unsigned int order)
+{
+	/* Control pages are special, they are the intermediaries
+	 * that are needed while we copy the rest of the pages
+	 * to their final resting place.  As such they must
+	 * not conflict with either the destination addresses
+	 * or memory the kernel is already using.
+	 *
+	 * The only case where we really need more than one of
+	 * these are for architectures where we cannot disable
+	 * the MMU and must instead generate an identity mapped
+	 * page table for all of the memory.
+	 *
+	 * At worst this runs in O(N) of the image size.
+	 */
+	struct list_head extra_pages;
+	struct page *pages;
+	unsigned int count;
+
+	count = 1 << order;
+	INIT_LIST_HEAD(&extra_pages);
+
+	/* Loop while I can allocate a page and the page allocated
+	 * is a destination page.
+	 */
+	do {
+		unsigned long pfn, epfn, addr, eaddr;
+
+		pages = kimage_alloc_pages(KEXEC_CONTROL_MEMORY_GFP, order);
+		if (!pages)
+			break;
+		pfn   = page_to_pfn(pages);
+		epfn  = pfn + count;
+		addr  = pfn << PAGE_SHIFT;
+		eaddr = epfn << PAGE_SHIFT;
+		if ((epfn >= (KEXEC_CONTROL_MEMORY_LIMIT >> PAGE_SHIFT)) ||
+			      kimage_is_destination_range(image, addr, eaddr)) {
+			list_add(&pages->lru, &extra_pages);
+			pages = NULL;
+		}
+	} while (!pages);
+
+	if (pages) {
+		/* Remember the allocated page... */
+		list_add(&pages->lru, &image->control_pages);
+
+		/* Because the page is already in it's destination
+		 * location we will never allocate another page at
+		 * that address.  Therefore kimage_alloc_pages
+		 * will not return it (again) and we don't need
+		 * to give it an entry in image->segment[].
+		 */
+	}
+	/* Deal with the destination pages I have inadvertently allocated.
+	 *
+	 * Ideally I would convert multi-page allocations into single
+	 * page allocations, and add everything to image->dest_pages.
+	 *
+	 * For now it is simpler to just free the pages.
+	 */
+	kimage_free_page_list(&extra_pages);
+
+	return pages;
+}
+
+static struct page *kimage_alloc_crash_control_pages(struct kimage *image,
+						      unsigned int order)
+{
+	/* Control pages are special, they are the intermediaries
+	 * that are needed while we copy the rest of the pages
+	 * to their final resting place.  As such they must
+	 * not conflict with either the destination addresses
+	 * or memory the kernel is already using.
+	 *
+	 * Control pages are also the only pags we must allocate
+	 * when loading a crash kernel.  All of the other pages
+	 * are specified by the segments and we just memcpy
+	 * into them directly.
+	 *
+	 * The only case where we really need more than one of
+	 * these are for architectures where we cannot disable
+	 * the MMU and must instead generate an identity mapped
+	 * page table for all of the memory.
+	 *
+	 * Given the low demand this implements a very simple
+	 * allocator that finds the first hole of the appropriate
+	 * size in the reserved memory region, and allocates all
+	 * of the memory up to and including the hole.
+	 */
+	unsigned long hole_start, hole_end, size;
+	struct page *pages;
+
+	pages = NULL;
+	size = (1 << order) << PAGE_SHIFT;
+	hole_start = (image->control_page + (size - 1)) & ~(size - 1);
+	hole_end   = hole_start + size - 1;
+	while (hole_end <= crashk_res.end) {
+		unsigned long i;
+
+		if (hole_end > KEXEC_CRASH_CONTROL_MEMORY_LIMIT)
+			break;
+		/* See if I overlap any of the segments */
+		for (i = 0; i < image->nr_segments; i++) {
+			unsigned long mstart, mend;
+
+			mstart = image->segment[i].mem;
+			mend   = mstart + image->segment[i].memsz - 1;
+			if ((hole_end >= mstart) && (hole_start <= mend)) {
+				/* Advance the hole to the end of the segment */
+				hole_start = (mend + (size - 1)) & ~(size - 1);
+				hole_end   = hole_start + size - 1;
+				break;
+			}
+		}
+		/* If I don't overlap any segments I have found my hole! */
+		if (i == image->nr_segments) {
+			pages = pfn_to_page(hole_start >> PAGE_SHIFT);
+			break;
+		}
+	}
+	if (pages)
+		image->control_page = hole_end;
+
+	return pages;
+}
+
+
+struct page *kimage_alloc_control_pages(struct kimage *image,
+					 unsigned int order)
+{
+	struct page *pages = NULL;
+
+	switch (image->type) {
+	case KEXEC_TYPE_DEFAULT:
+		pages = kimage_alloc_normal_control_pages(image, order);
+		break;
+	case KEXEC_TYPE_CRASH:
+		pages = kimage_alloc_crash_control_pages(image, order);
+		break;
+	}
+
+	return pages;
+}
+
+static int kimage_add_entry(struct kimage *image, kimage_entry_t entry)
+{
+	if (*image->entry != 0)
+		image->entry++;
+
+	if (image->entry == image->last_entry) {
+		kimage_entry_t *ind_page;
+		struct page *page;
+
+		page = kimage_alloc_page(image, GFP_KERNEL, KIMAGE_NO_DEST);
+		if (!page)
+			return -ENOMEM;
+
+		ind_page = page_address(page);
+		*image->entry = virt_to_phys(ind_page) | IND_INDIRECTION;
+		image->entry = ind_page;
+		image->last_entry = ind_page +
+				      ((PAGE_SIZE/sizeof(kimage_entry_t)) - 1);
+	}
+	*image->entry = entry;
+	image->entry++;
+	*image->entry = 0;
+
+	return 0;
+}
+
+static int kimage_set_destination(struct kimage *image,
+				   unsigned long destination)
+{
+	int result;
+
+	destination &= PAGE_MASK;
+	result = kimage_add_entry(image, destination | IND_DESTINATION);
+
+	return result;
+}
+
+
+static int kimage_add_page(struct kimage *image, unsigned long page)
+{
+	int result;
+
+	page &= PAGE_MASK;
+	result = kimage_add_entry(image, page | IND_SOURCE);
+
+	return result;
+}
+
+
+static void kimage_free_extra_pages(struct kimage *image)
+{
+	/* Walk through and free any extra destination pages I may have */
+	kimage_free_page_list(&image->dest_pages);
+
+	/* Walk through and free any unusable pages I have cached */
+	kimage_free_page_list(&image->unusable_pages);
+
+}
+void kimage_terminate(struct kimage *image)
+{
+	if (*image->entry != 0)
+		image->entry++;
+
+	*image->entry = IND_DONE;
+}
+
+#define for_each_kimage_entry(image, ptr, entry) \
+	for (ptr = &image->head; (entry = *ptr) && !(entry & IND_DONE); \
+		ptr = (entry & IND_INDIRECTION) ? \
+			phys_to_virt((entry & PAGE_MASK)) : ptr + 1)
+
+static void kimage_free_entry(kimage_entry_t entry)
+{
+	struct page *page;
+
+	page = pfn_to_page(entry >> PAGE_SHIFT);
+	kimage_free_pages(page);
+}
+
+void kimage_free(struct kimage *image)
+{
+	kimage_entry_t *ptr, entry;
+	kimage_entry_t ind = 0;
+
+	if (!image)
+		return;
+
+	kimage_free_extra_pages(image);
+	for_each_kimage_entry(image, ptr, entry) {
+		if (entry & IND_INDIRECTION) {
+			/* Free the previous indirection page */
+			if (ind & IND_INDIRECTION)
+				kimage_free_entry(ind);
+			/* Save this indirection page until we are
+			 * done with it.
+			 */
+			ind = entry;
+		} else if (entry & IND_SOURCE)
+			kimage_free_entry(entry);
+	}
+	/* Free the final indirection page */
+	if (ind & IND_INDIRECTION)
+		kimage_free_entry(ind);
+
+	/* Handle any machine specific cleanup */
+	machine_kexec_cleanup(image);
+
+	/* Free the kexec control pages... */
+	kimage_free_page_list(&image->control_pages);
+
+	/*
+	 * Free up any temporary buffers allocated. This might hit if
+	 * error occurred much later after buffer allocation.
+	 */
+	if (image->file_mode)
+		kimage_file_post_load_cleanup(image);
+
+	kfree(image);
+}
+
+static kimage_entry_t *kimage_dst_used(struct kimage *image,
+					unsigned long page)
+{
+	kimage_entry_t *ptr, entry;
+	unsigned long destination = 0;
+
+	for_each_kimage_entry(image, ptr, entry) {
+		if (entry & IND_DESTINATION)
+			destination = entry & PAGE_MASK;
+		else if (entry & IND_SOURCE) {
+			if (page == destination)
+				return ptr;
+			destination += PAGE_SIZE;
+		}
+	}
+
+	return NULL;
+}
+
+static struct page *kimage_alloc_page(struct kimage *image,
+					gfp_t gfp_mask,
+					unsigned long destination)
+{
+	/*
+	 * Here we implement safeguards to ensure that a source page
+	 * is not copied to its destination page before the data on
+	 * the destination page is no longer useful.
+	 *
+	 * To do this we maintain the invariant that a source page is
+	 * either its own destination page, or it is not a
+	 * destination page at all.
+	 *
+	 * That is slightly stronger than required, but the proof
+	 * that no problems will not occur is trivial, and the
+	 * implementation is simply to verify.
+	 *
+	 * When allocating all pages normally this algorithm will run
+	 * in O(N) time, but in the worst case it will run in O(N^2)
+	 * time.   If the runtime is a problem the data structures can
+	 * be fixed.
+	 */
+	struct page *page;
+	unsigned long addr;
+
+	/*
+	 * Walk through the list of destination pages, and see if I
+	 * have a match.
+	 */
+	list_for_each_entry(page, &image->dest_pages, lru) {
+		addr = page_to_pfn(page) << PAGE_SHIFT;
+		if (addr == destination) {
+			list_del(&page->lru);
+			return page;
+		}
+	}
+	page = NULL;
+	while (1) {
+		kimage_entry_t *old;
+
+		/* Allocate a page, if we run out of memory give up */
+		page = kimage_alloc_pages(gfp_mask, 0);
+		if (!page)
+			return NULL;
+		/* If the page cannot be used file it away */
+		if (page_to_pfn(page) >
+				(KEXEC_SOURCE_MEMORY_LIMIT >> PAGE_SHIFT)) {
+			list_add(&page->lru, &image->unusable_pages);
+			continue;
+		}
+		addr = page_to_pfn(page) << PAGE_SHIFT;
+
+		/* If it is the destination page we want use it */
+		if (addr == destination)
+			break;
+
+		/* If the page is not a destination page use it */
+		if (!kimage_is_destination_range(image, addr,
+						  addr + PAGE_SIZE))
+			break;
+
+		/*
+		 * I know that the page is someones destination page.
+		 * See if there is already a source page for this
+		 * destination page.  And if so swap the source pages.
+		 */
+		old = kimage_dst_used(image, addr);
+		if (old) {
+			/* If so move it */
+			unsigned long old_addr;
+			struct page *old_page;
+
+			old_addr = *old & PAGE_MASK;
+			old_page = pfn_to_page(old_addr >> PAGE_SHIFT);
+			copy_highpage(page, old_page);
+			*old = addr | (*old & ~PAGE_MASK);
+
+			/* The old page I have found cannot be a
+			 * destination page, so return it if it's
+			 * gfp_flags honor the ones passed in.
+			 */
+			if (!(gfp_mask & __GFP_HIGHMEM) &&
+			    PageHighMem(old_page)) {
+				kimage_free_pages(old_page);
+				continue;
+			}
+			addr = old_addr;
+			page = old_page;
+			break;
+		} else {
+			/* Place the page on the destination list I
+			 * will use it later.
+			 */
+			list_add(&page->lru, &image->dest_pages);
+		}
+	}
+
+	return page;
+}
+
+static int kimage_load_normal_segment(struct kimage *image,
+					 struct kexec_segment *segment)
+{
+	unsigned long maddr;
+	size_t ubytes, mbytes;
+	int result;
+	unsigned char __user *buf = NULL;
+	unsigned char *kbuf = NULL;
+
+	result = 0;
+	if (image->file_mode)
+		kbuf = segment->kbuf;
+	else
+		buf = segment->buf;
+	ubytes = segment->bufsz;
+	mbytes = segment->memsz;
+	maddr = segment->mem;
+
+	result = kimage_set_destination(image, maddr);
+	if (result < 0)
+		goto out;
+
+	while (mbytes) {
+		struct page *page;
+		char *ptr;
+		size_t uchunk, mchunk;
+
+		page = kimage_alloc_page(image, GFP_HIGHUSER, maddr);
+		if (!page) {
+			result  = -ENOMEM;
+			goto out;
+		}
+		result = kimage_add_page(image, page_to_pfn(page)
+								<< PAGE_SHIFT);
+		if (result < 0)
+			goto out;
+
+		ptr = kmap(page);
+		/* Start with a clear page */
+		clear_page(ptr);
+		ptr += maddr & ~PAGE_MASK;
+		mchunk = min_t(size_t, mbytes,
+				PAGE_SIZE - (maddr & ~PAGE_MASK));
+		uchunk = min(ubytes, mchunk);
+
+		/* For file based kexec, source pages are in kernel memory */
+		if (image->file_mode)
+			memcpy(ptr, kbuf, uchunk);
+		else
+			result = copy_from_user(ptr, buf, uchunk);
+		kunmap(page);
+		if (result) {
+			result = -EFAULT;
+			goto out;
+		}
+		ubytes -= uchunk;
+		maddr  += mchunk;
+		if (image->file_mode)
+			kbuf += mchunk;
+		else
+			buf += mchunk;
+		mbytes -= mchunk;
+	}
+out:
+	return result;
+}
+
+static int kimage_load_crash_segment(struct kimage *image,
+					struct kexec_segment *segment)
+{
+	/* For crash dumps kernels we simply copy the data from
+	 * user space to it's destination.
+	 * We do things a page at a time for the sake of kmap.
+	 */
+	unsigned long maddr;
+	size_t ubytes, mbytes;
+	int result;
+	unsigned char __user *buf = NULL;
+	unsigned char *kbuf = NULL;
+
+	result = 0;
+	if (image->file_mode)
+		kbuf = segment->kbuf;
+	else
+		buf = segment->buf;
+	ubytes = segment->bufsz;
+	mbytes = segment->memsz;
+	maddr = segment->mem;
+	while (mbytes) {
+		struct page *page;
+		char *ptr;
+		size_t uchunk, mchunk;
+
+		page = pfn_to_page(maddr >> PAGE_SHIFT);
+		if (!page) {
+			result  = -ENOMEM;
+			goto out;
+		}
+		ptr = kmap(page);
+		ptr += maddr & ~PAGE_MASK;
+		mchunk = min_t(size_t, mbytes,
+				PAGE_SIZE - (maddr & ~PAGE_MASK));
+		uchunk = min(ubytes, mchunk);
+		if (mchunk > uchunk) {
+			/* Zero the trailing part of the page */
+			memset(ptr + uchunk, 0, mchunk - uchunk);
+		}
+
+		/* For file based kexec, source pages are in kernel memory */
+		if (image->file_mode)
+			memcpy(ptr, kbuf, uchunk);
+		else
+			result = copy_from_user(ptr, buf, uchunk);
+		kexec_flush_icache_page(page);
+		kunmap(page);
+		if (result) {
+			result = -EFAULT;
+			goto out;
+		}
+		ubytes -= uchunk;
+		maddr  += mchunk;
+		if (image->file_mode)
+			kbuf += mchunk;
+		else
+			buf += mchunk;
+		mbytes -= mchunk;
+	}
+out:
+	return result;
+}
+
+int kimage_load_segment(struct kimage *image,
+				struct kexec_segment *segment)
+{
+	int result = -ENOMEM;
+
+	switch (image->type) {
+	case KEXEC_TYPE_DEFAULT:
+		result = kimage_load_normal_segment(image, segment);
+		break;
+	case KEXEC_TYPE_CRASH:
+		result = kimage_load_crash_segment(image, segment);
+		break;
+	}
+
+	return result;
+}
+
+struct kimage *kexec_image;
+struct kimage *kexec_crash_image;
+int kexec_load_disabled;
+
+void crash_kexec(struct pt_regs *regs)
+{
+	/* Take the kexec_mutex here to prevent sys_kexec_load
+	 * running on one cpu from replacing the crash kernel
+	 * we are using after a panic on a different cpu.
+	 *
+	 * If the crash kernel was not located in a fixed area
+	 * of memory the xchg(&kexec_crash_image) would be
+	 * sufficient.  But since I reuse the memory...
+	 */
+	if (mutex_trylock(&kexec_mutex)) {
+		if (kexec_crash_image) {
+			struct pt_regs fixed_regs;
+
+			crash_setup_regs(&fixed_regs, regs);
+			crash_save_vmcoreinfo();
+			machine_crash_shutdown(&fixed_regs);
+			machine_kexec(kexec_crash_image);
+		}
+		mutex_unlock(&kexec_mutex);
+	}
+}
+
+size_t crash_get_memory_size(void)
+{
+	size_t size = 0;
+	mutex_lock(&kexec_mutex);
+	if (crashk_res.end != crashk_res.start)
+		size = resource_size(&crashk_res);
+	mutex_unlock(&kexec_mutex);
+	return size;
+}
+
+void __weak crash_free_reserved_phys_range(unsigned long begin,
+					   unsigned long end)
+{
+	unsigned long addr;
+
+	for (addr = begin; addr < end; addr += PAGE_SIZE)
+		free_reserved_page(pfn_to_page(addr >> PAGE_SHIFT));
+}
+
+int crash_shrink_memory(unsigned long new_size)
+{
+	int ret = 0;
+	unsigned long start, end;
+	unsigned long old_size;
+	struct resource *ram_res;
+
+	mutex_lock(&kexec_mutex);
+
+	if (kexec_crash_image) {
+		ret = -ENOENT;
+		goto unlock;
+	}
+	start = crashk_res.start;
+	end = crashk_res.end;
+	old_size = (end == 0) ? 0 : end - start + 1;
+	if (new_size >= old_size) {
+		ret = (new_size == old_size) ? 0 : -EINVAL;
+		goto unlock;
+	}
+
+	ram_res = kzalloc(sizeof(*ram_res), GFP_KERNEL);
+	if (!ram_res) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	start = roundup(start, KEXEC_CRASH_MEM_ALIGN);
+	end = roundup(start + new_size, KEXEC_CRASH_MEM_ALIGN);
+
+	crash_map_reserved_pages();
+	crash_free_reserved_phys_range(end, crashk_res.end);
+
+	if ((start == end) && (crashk_res.parent != NULL))
+		release_resource(&crashk_res);
+
+	ram_res->start = end;
+	ram_res->end = crashk_res.end;
+	ram_res->flags = IORESOURCE_BUSY | IORESOURCE_MEM;
+	ram_res->name = "System RAM";
+
+	crashk_res.end = end - 1;
+
+	insert_resource(&iomem_resource, ram_res);
+	crash_unmap_reserved_pages();
+
+unlock:
+	mutex_unlock(&kexec_mutex);
+	return ret;
+}
+
+static u32 *append_elf_note(u32 *buf, char *name, unsigned type, void *data,
+			    size_t data_len)
+{
+	struct elf_note note;
+
+	note.n_namesz = strlen(name) + 1;
+	note.n_descsz = data_len;
+	note.n_type   = type;
+	memcpy(buf, &note, sizeof(note));
+	buf += (sizeof(note) + 3)/4;
+	memcpy(buf, name, note.n_namesz);
+	buf += (note.n_namesz + 3)/4;
+	memcpy(buf, data, note.n_descsz);
+	buf += (note.n_descsz + 3)/4;
+
+	return buf;
+}
+
+static void final_note(u32 *buf)
+{
+	struct elf_note note;
+
+	note.n_namesz = 0;
+	note.n_descsz = 0;
+	note.n_type   = 0;
+	memcpy(buf, &note, sizeof(note));
+}
+
+void crash_save_cpu(struct pt_regs *regs, int cpu)
+{
+	struct elf_prstatus prstatus;
+	u32 *buf;
+
+	if ((cpu < 0) || (cpu >= nr_cpu_ids))
+		return;
+
+	/* Using ELF notes here is opportunistic.
+	 * I need a well defined structure format
+	 * for the data I pass, and I need tags
+	 * on the data to indicate what information I have
+	 * squirrelled away.  ELF notes happen to provide
+	 * all of that, so there is no need to invent something new.
+	 */
+	buf = (u32 *)per_cpu_ptr(crash_notes, cpu);
+	if (!buf)
+		return;
+	memset(&prstatus, 0, sizeof(prstatus));
+	prstatus.pr_pid = current->pid;
+	elf_core_copy_kernel_regs(&prstatus.pr_reg, regs);
+	buf = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS,
+			      &prstatus, sizeof(prstatus));
+	final_note(buf);
+}
+
+static int __init crash_notes_memory_init(void)
+{
+	/* Allocate memory for saving cpu registers. */
+	crash_notes = alloc_percpu(note_buf_t);
+	if (!crash_notes) {
+		pr_warn("Kexec: Memory allocation for saving cpu register states failed\n");
+		return -ENOMEM;
+	}
+	return 0;
+}
+subsys_initcall(crash_notes_memory_init);
+
+
+/*
+ * parsing the "crashkernel" commandline
+ *
+ * this code is intended to be called from architecture specific code
+ */
+
+
+/*
+ * This function parses command lines in the format
+ *
+ *   crashkernel=ramsize-range:size[,...][@offset]
+ *
+ * The function returns 0 on success and -EINVAL on failure.
+ */
+static int __init parse_crashkernel_mem(char *cmdline,
+					unsigned long long system_ram,
+					unsigned long long *crash_size,
+					unsigned long long *crash_base)
+{
+	char *cur = cmdline, *tmp;
+
+	/* for each entry of the comma-separated list */
+	do {
+		unsigned long long start, end = ULLONG_MAX, size;
+
+		/* get the start of the range */
+		start = memparse(cur, &tmp);
+		if (cur == tmp) {
+			pr_warn("crashkernel: Memory value expected\n");
+			return -EINVAL;
+		}
+		cur = tmp;
+		if (*cur != '-') {
+			pr_warn("crashkernel: '-' expected\n");
+			return -EINVAL;
+		}
+		cur++;
+
+		/* if no ':' is here, than we read the end */
+		if (*cur != ':') {
+			end = memparse(cur, &tmp);
+			if (cur == tmp) {
+				pr_warn("crashkernel: Memory value expected\n");
+				return -EINVAL;
+			}
+			cur = tmp;
+			if (end <= start) {
+				pr_warn("crashkernel: end <= start\n");
+				return -EINVAL;
+			}
+		}
+
+		if (*cur != ':') {
+			pr_warn("crashkernel: ':' expected\n");
+			return -EINVAL;
+		}
+		cur++;
+
+		size = memparse(cur, &tmp);
+		if (cur == tmp) {
+			pr_warn("Memory value expected\n");
+			return -EINVAL;
+		}
+		cur = tmp;
+		if (size >= system_ram) {
+			pr_warn("crashkernel: invalid size\n");
+			return -EINVAL;
+		}
+
+		/* match ? */
+		if (system_ram >= start && system_ram < end) {
+			*crash_size = size;
+			break;
+		}
+	} while (*cur++ == ',');
+
+	if (*crash_size > 0) {
+		while (*cur && *cur != ' ' && *cur != '@')
+			cur++;
+		if (*cur == '@') {
+			cur++;
+			*crash_base = memparse(cur, &tmp);
+			if (cur == tmp) {
+				pr_warn("Memory value expected after '@'\n");
+				return -EINVAL;
+			}
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * That function parses "simple" (old) crashkernel command lines like
+ *
+ *	crashkernel=size[@offset]
+ *
+ * It returns 0 on success and -EINVAL on failure.
+ */
+static int __init parse_crashkernel_simple(char *cmdline,
+					   unsigned long long *crash_size,
+					   unsigned long long *crash_base)
+{
+	char *cur = cmdline;
+
+	*crash_size = memparse(cmdline, &cur);
+	if (cmdline == cur) {
+		pr_warn("crashkernel: memory value expected\n");
+		return -EINVAL;
+	}
+
+	if (*cur == '@')
+		*crash_base = memparse(cur+1, &cur);
+	else if (*cur != ' ' && *cur != '\0') {
+		pr_warn("crashkernel: unrecognized char\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+#define SUFFIX_HIGH 0
+#define SUFFIX_LOW  1
+#define SUFFIX_NULL 2
+static __initdata char *suffix_tbl[] = {
+	[SUFFIX_HIGH] = ",high",
+	[SUFFIX_LOW]  = ",low",
+	[SUFFIX_NULL] = NULL,
+};
+
+/*
+ * That function parses "suffix"  crashkernel command lines like
+ *
+ *	crashkernel=size,[high|low]
+ *
+ * It returns 0 on success and -EINVAL on failure.
+ */
+static int __init parse_crashkernel_suffix(char *cmdline,
+					   unsigned long long	*crash_size,
+					   const char *suffix)
+{
+	char *cur = cmdline;
+
+	*crash_size = memparse(cmdline, &cur);
+	if (cmdline == cur) {
+		pr_warn("crashkernel: memory value expected\n");
+		return -EINVAL;
+	}
+
+	/* check with suffix */
+	if (strncmp(cur, suffix, strlen(suffix))) {
+		pr_warn("crashkernel: unrecognized char\n");
+		return -EINVAL;
+	}
+	cur += strlen(suffix);
+	if (*cur != ' ' && *cur != '\0') {
+		pr_warn("crashkernel: unrecognized char\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static __init char *get_last_crashkernel(char *cmdline,
+			     const char *name,
+			     const char *suffix)
+{
+	char *p = cmdline, *ck_cmdline = NULL;
+
+	/* find crashkernel and use the last one if there are more */
+	p = strstr(p, name);
+	while (p) {
+		char *end_p = strchr(p, ' ');
+		char *q;
+
+		if (!end_p)
+			end_p = p + strlen(p);
+
+		if (!suffix) {
+			int i;
+
+			/* skip the one with any known suffix */
+			for (i = 0; suffix_tbl[i]; i++) {
+				q = end_p - strlen(suffix_tbl[i]);
+				if (!strncmp(q, suffix_tbl[i],
+					     strlen(suffix_tbl[i])))
+					goto next;
+			}
+			ck_cmdline = p;
+		} else {
+			q = end_p - strlen(suffix);
+			if (!strncmp(q, suffix, strlen(suffix)))
+				ck_cmdline = p;
+		}
+next:
+		p = strstr(p+1, name);
+	}
+
+	if (!ck_cmdline)
+		return NULL;
+
+	return ck_cmdline;
+}
+
+static int __init __parse_crashkernel(char *cmdline,
+			     unsigned long long system_ram,
+			     unsigned long long *crash_size,
+			     unsigned long long *crash_base,
+			     const char *name,
+			     const char *suffix)
+{
+	char	*first_colon, *first_space;
+	char	*ck_cmdline;
+
+	BUG_ON(!crash_size || !crash_base);
+	*crash_size = 0;
+	*crash_base = 0;
+
+	ck_cmdline = get_last_crashkernel(cmdline, name, suffix);
+
+	if (!ck_cmdline)
+		return -EINVAL;
+
+	ck_cmdline += strlen(name);
+
+	if (suffix)
+		return parse_crashkernel_suffix(ck_cmdline, crash_size,
+				suffix);
+	/*
+	 * if the commandline contains a ':', then that's the extended
+	 * syntax -- if not, it must be the classic syntax
+	 */
+	first_colon = strchr(ck_cmdline, ':');
+	first_space = strchr(ck_cmdline, ' ');
+	if (first_colon && (!first_space || first_colon < first_space))
+		return parse_crashkernel_mem(ck_cmdline, system_ram,
+				crash_size, crash_base);
+
+	return parse_crashkernel_simple(ck_cmdline, crash_size, crash_base);
+}
+
+/*
+ * That function is the entry point for command line parsing and should be
+ * called from the arch-specific code.
+ */
+int __init parse_crashkernel(char *cmdline,
+			     unsigned long long system_ram,
+			     unsigned long long *crash_size,
+			     unsigned long long *crash_base)
+{
+	return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
+					"crashkernel=", NULL);
+}
+
+int __init parse_crashkernel_high(char *cmdline,
+			     unsigned long long system_ram,
+			     unsigned long long *crash_size,
+			     unsigned long long *crash_base)
+{
+	return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
+				"crashkernel=", suffix_tbl[SUFFIX_HIGH]);
+}
+
+int __init parse_crashkernel_low(char *cmdline,
+			     unsigned long long system_ram,
+			     unsigned long long *crash_size,
+			     unsigned long long *crash_base)
+{
+	return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
+				"crashkernel=", suffix_tbl[SUFFIX_LOW]);
+}
+
+static void update_vmcoreinfo_note(void)
+{
+	u32 *buf = vmcoreinfo_note;
+
+	if (!vmcoreinfo_size)
+		return;
+	buf = append_elf_note(buf, VMCOREINFO_NOTE_NAME, 0, vmcoreinfo_data,
+			      vmcoreinfo_size);
+	final_note(buf);
+}
+
+void crash_save_vmcoreinfo(void)
+{
+	vmcoreinfo_append_str("CRASHTIME=%ld\n", get_seconds());
+	update_vmcoreinfo_note();
+}
+
+void vmcoreinfo_append_str(const char *fmt, ...)
+{
+	va_list args;
+	char buf[0x50];
+	size_t r;
+
+	va_start(args, fmt);
+	r = vscnprintf(buf, sizeof(buf), fmt, args);
+	va_end(args);
+
+	r = min(r, vmcoreinfo_max_size - vmcoreinfo_size);
+
+	memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r);
+
+	vmcoreinfo_size += r;
+}
+
+/*
+ * provide an empty default implementation here -- architecture
+ * code may override this
+ */
+void __weak arch_crash_save_vmcoreinfo(void)
+{}
+
+unsigned long __weak paddr_vmcoreinfo_note(void)
+{
+	return __pa((unsigned long)(char *)&vmcoreinfo_note);
+}
+
+static int __init crash_save_vmcoreinfo_init(void)
+{
+	VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
+	VMCOREINFO_PAGESIZE(PAGE_SIZE);
+
+	VMCOREINFO_SYMBOL(init_uts_ns);
+	VMCOREINFO_SYMBOL(node_online_map);
+#ifdef CONFIG_MMU
+	VMCOREINFO_SYMBOL(swapper_pg_dir);
+#endif
+	VMCOREINFO_SYMBOL(_stext);
+	VMCOREINFO_SYMBOL(vmap_area_list);
+
+#ifndef CONFIG_NEED_MULTIPLE_NODES
+	VMCOREINFO_SYMBOL(mem_map);
+	VMCOREINFO_SYMBOL(contig_page_data);
+#endif
+#ifdef CONFIG_SPARSEMEM
+	VMCOREINFO_SYMBOL(mem_section);
+	VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS);
+	VMCOREINFO_STRUCT_SIZE(mem_section);
+	VMCOREINFO_OFFSET(mem_section, section_mem_map);
+#endif
+	VMCOREINFO_STRUCT_SIZE(page);
+	VMCOREINFO_STRUCT_SIZE(pglist_data);
+	VMCOREINFO_STRUCT_SIZE(zone);
+	VMCOREINFO_STRUCT_SIZE(free_area);
+	VMCOREINFO_STRUCT_SIZE(list_head);
+	VMCOREINFO_SIZE(nodemask_t);
+	VMCOREINFO_OFFSET(page, flags);
+	VMCOREINFO_OFFSET(page, _count);
+	VMCOREINFO_OFFSET(page, mapping);
+	VMCOREINFO_OFFSET(page, lru);
+	VMCOREINFO_OFFSET(page, _mapcount);
+	VMCOREINFO_OFFSET(page, private);
+	VMCOREINFO_OFFSET(pglist_data, node_zones);
+	VMCOREINFO_OFFSET(pglist_data, nr_zones);
+#ifdef CONFIG_FLAT_NODE_MEM_MAP
+	VMCOREINFO_OFFSET(pglist_data, node_mem_map);
+#endif
+	VMCOREINFO_OFFSET(pglist_data, node_start_pfn);
+	VMCOREINFO_OFFSET(pglist_data, node_spanned_pages);
+	VMCOREINFO_OFFSET(pglist_data, node_id);
+	VMCOREINFO_OFFSET(zone, free_area);
+	VMCOREINFO_OFFSET(zone, vm_stat);
+	VMCOREINFO_OFFSET(zone, spanned_pages);
+	VMCOREINFO_OFFSET(free_area, free_list);
+	VMCOREINFO_OFFSET(list_head, next);
+	VMCOREINFO_OFFSET(list_head, prev);
+	VMCOREINFO_OFFSET(vmap_area, va_start);
+	VMCOREINFO_OFFSET(vmap_area, list);
+	VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER);
+	log_buf_kexec_setup();
+	VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
+	VMCOREINFO_NUMBER(NR_FREE_PAGES);
+	VMCOREINFO_NUMBER(PG_lru);
+	VMCOREINFO_NUMBER(PG_private);
+	VMCOREINFO_NUMBER(PG_swapcache);
+	VMCOREINFO_NUMBER(PG_slab);
+#ifdef CONFIG_MEMORY_FAILURE
+	VMCOREINFO_NUMBER(PG_hwpoison);
+#endif
+	VMCOREINFO_NUMBER(PG_head_mask);
+	VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE);
+#ifdef CONFIG_HUGETLBFS
+	VMCOREINFO_SYMBOL(free_huge_page);
+#endif
+
+	arch_crash_save_vmcoreinfo();
+	update_vmcoreinfo_note();
+
+	return 0;
+}
+
+subsys_initcall(crash_save_vmcoreinfo_init);
+
+/*
+ * Move into place and start executing a preloaded standalone
+ * executable.  If nothing was preloaded return an error.
+ */
+int kernel_kexec(void)
+{
+	int error = 0;
+
+	if (!mutex_trylock(&kexec_mutex))
+		return -EBUSY;
+	if (!kexec_image) {
+		error = -EINVAL;
+		goto Unlock;
+	}
+
+#ifdef CONFIG_KEXEC_JUMP
+	if (kexec_image->preserve_context) {
+		lock_system_sleep();
+		pm_prepare_console();
+		error = freeze_processes();
+		if (error) {
+			error = -EBUSY;
+			goto Restore_console;
+		}
+		suspend_console();
+		error = dpm_suspend_start(PMSG_FREEZE);
+		if (error)
+			goto Resume_console;
+		/* At this point, dpm_suspend_start() has been called,
+		 * but *not* dpm_suspend_end(). We *must* call
+		 * dpm_suspend_end() now.  Otherwise, drivers for
+		 * some devices (e.g. interrupt controllers) become
+		 * desynchronized with the actual state of the
+		 * hardware at resume time, and evil weirdness ensues.
+		 */
+		error = dpm_suspend_end(PMSG_FREEZE);
+		if (error)
+			goto Resume_devices;
+		error = disable_nonboot_cpus();
+		if (error)
+			goto Enable_cpus;
+		local_irq_disable();
+		error = syscore_suspend();
+		if (error)
+			goto Enable_irqs;
+	} else
+#endif
+	{
+		kexec_in_progress = true;
+		kernel_restart_prepare(NULL);
+		migrate_to_reboot_cpu();
+
+		/*
+		 * migrate_to_reboot_cpu() disables CPU hotplug assuming that
+		 * no further code needs to use CPU hotplug (which is true in
+		 * the reboot case). However, the kexec path depends on using
+		 * CPU hotplug again; so re-enable it here.
+		 */
+		cpu_hotplug_enable();
+		pr_emerg("Starting new kernel\n");
+		machine_shutdown();
+	}
+
+	machine_kexec(kexec_image);
+
+#ifdef CONFIG_KEXEC_JUMP
+	if (kexec_image->preserve_context) {
+		syscore_resume();
+ Enable_irqs:
+		local_irq_enable();
+ Enable_cpus:
+		enable_nonboot_cpus();
+		dpm_resume_start(PMSG_RESTORE);
+ Resume_devices:
+		dpm_resume_end(PMSG_RESTORE);
+ Resume_console:
+		resume_console();
+		thaw_processes();
+ Restore_console:
+		pm_restore_console();
+		unlock_system_sleep();
+	}
+#endif
+
+ Unlock:
+	mutex_unlock(&kexec_mutex);
+	return error;
+}
+
+/*
+ * Add and remove page tables for crashkernel memory
+ *
+ * Provide an empty default implementation here -- architecture
+ * code may override this
+ */
+void __weak crash_map_reserved_pages(void)
+{}
+
+void __weak crash_unmap_reserved_pages(void)
+{}
--- linux.orig/kernel/ksysfs.c
+++ linux/kernel/ksysfs.c
@@ -90,7 +90,7 @@ static ssize_t profiling_store(struct ko
 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 ko
 }
 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,
--- linux.orig/kernel/printk/printk.c
+++ linux/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
  *
--- linux.orig/kernel/reboot.c
+++ linux/kernel/reboot.c
@@ -346,7 +346,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int
 		kernel_restart(buffer);
 		break;
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	case LINUX_REBOOT_CMD_KEXEC:
 		ret = kernel_kexec();
 		break;
--- linux.orig/kernel/sysctl.c
+++ linux/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,



More information about the kexec mailing list