kexec jump

This patch provides an enhancement to kexec/kdump.  It implements the
following features:

- Backup/restore memory used by the original kernel before/after
  kexec.

- Save/restore CPU state before/after kexec.

The features of this patch can be used as a general method to call program in
physical mode (paging turning off).  This can be used to call BIOS code under
Linux.

kexec-tools needs to be patched to support kexec jump. The patches and
the precompiled kexec can be download from the following URL:

       source: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec-tools-src_git_kh10.tar.bz2
       patches: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec-tools-patches_git_kh10.tar.bz2
       binary: http://khibernation.sourceforge.net/download/release_v10/kexec-tools/kexec_git_kh10

Usage example of calling some physical mode code and return:

1. Compile and install patched kernel with following options selected:

CONFIG_X86_32=y
CONFIG_KEXEC=y
CONFIG_PM=y
CONFIG_KEXEC_JUMP=y

2. Build patched kexec-tool or download the pre-built one.

3. Build some physical mode executable named such as "phy_mode"

4. Boot kernel compiled in step 1.

5. Load physical mode executable with /sbin/kexec. The shell command
   line can be as follow:

   /sbin/kexec --load-preserve-context --args-none phy_mode

6. Call physical mode executable with following shell command line:

   /sbin/kexec -e

Implementation point:

To support jumping without reserving memory.  One shadow backup page (source
page) is allocated for each page used by kexeced code image (destination
page).  When do kexec_load, the image of kexeced code is loaded into source
pages, and before executing, the destination pages and the source pages are
swapped, so the contents of destination pages are backupped.  Before jumping
to the kexeced code image and after jumping back to the original kernel, the
destination pages and the source pages are swapped too.

C ABI (calling convention) is used as communication protocol between
kernel and called code.

A flag named KEXEC_PRESERVE_CONTEXT for sys_kexec_load is added to
indicate that the loaded kernel image is used for jumping back.

Now, only the i386 architecture is supported.

Signed-off-by: Huang Ying <ying.huang@intel.com>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Nigel Cunningham <nigel@nigel.suspend2.net>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 23 insertions, 12 deletions

diff --git a/include/asm-x86/kexec.h b/include/asm-x86/kexec.h
index 8f855a15f64..c0e52a14fd4 100644
--- a/include/asm-x86/kexec.h
+++ b/include/asm-x86/kexec.h
@@ -10,14 +10,15 @@
 # define VA_PTE_0		5
 # define PA_PTE_1		6
 # define VA_PTE_1		7
+# define PA_SWAP_PAGE		8
 # ifdef CONFIG_X86_PAE
-#  define PA_PMD_0		8
-#  define VA_PMD_0		9
-#  define PA_PMD_1		10
-#  define VA_PMD_1		11
-#  define PAGES_NR		12
+#  define PA_PMD_0		9
+#  define VA_PMD_0		10
+#  define PA_PMD_1		11
+#  define VA_PMD_1		12
+#  define PAGES_NR		13
 # else
-#  define PAGES_NR		8
+#  define PAGES_NR		9
 # endif
 #else
 # define PA_CONTROL_PAGE	0
@@ -152,11 +153,12 @@ static inline void crash_setup_regs(struct pt_regs *newregs,
 }
 
 #ifdef CONFIG_X86_32
-asmlinkage NORET_TYPE void
+asmlinkage unsigned long
 relocate_kernel(unsigned long indirection_page,
 		unsigned long control_page,
 		unsigned long start_address,
-		unsigned int has_pae) ATTRIB_NORET;
+		unsigned int has_pae,
+		unsigned int preserve_context);
 #else
 NORET_TYPE void
 relocate_kernel(unsigned long indirection_page,
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 3265968cd2c..82f88a8a827 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -83,6 +83,7 @@ struct kimage {
 
 	unsigned long start;
 	struct page *control_code_page;
+	struct page *swap_page;
 
 	unsigned long nr_segments;
 	struct kexec_segment segment[KEXEC_SEGMENT_MAX];
@@ -98,18 +99,20 @@ struct kimage {
 	unsigned int type : 1;
 #define KEXEC_TYPE_DEFAULT 0
 #define KEXEC_TYPE_CRASH   1
+	unsigned int preserve_context : 1;
 };
 
 
 
 /* kexec interface functions */
-extern NORET_TYPE void machine_kexec(struct kimage *image) ATTRIB_NORET;
+extern void machine_kexec(struct kimage *image);
 extern int machine_kexec_prepare(struct kimage *image);
 extern void machine_kexec_cleanup(struct kimage *image);
 extern asmlinkage long sys_kexec_load(unsigned long entry,
 					unsigned long nr_segments,
 					struct kexec_segment __user *segments,
 					unsigned long flags);
+extern int kernel_kexec(void);
 #ifdef CONFIG_COMPAT
 extern asmlinkage long compat_sys_kexec_load(unsigned long entry,
 				unsigned long nr_segments,
@@ -156,8 +159,9 @@ extern struct kimage *kexec_crash_image;
 #define kexec_flush_icache_page(page)
 #endif
 
-#define KEXEC_ON_CRASH  0x00000001
-#define KEXEC_ARCH_MASK 0xffff0000
+#define KEXEC_ON_CRASH		0x00000001
+#define KEXEC_PRESERVE_CONTEXT	0x00000002
+#define KEXEC_ARCH_MASK		0xffff0000
 
 /* These values match the ELF architecture values.
  * Unless there is a good reason that should continue to be the case.
@@ -174,7 +178,12 @@ extern struct kimage *kexec_crash_image;
 #define KEXEC_ARCH_MIPS_LE (10 << 16)
 #define KEXEC_ARCH_MIPS    ( 8 << 16)
 
-#define KEXEC_FLAGS    (KEXEC_ON_CRASH)  /* List of defined/legal kexec flags */
+/* List of defined/legal kexec flags */
+#ifndef CONFIG_KEXEC_JUMP
+#define KEXEC_FLAGS    KEXEC_ON_CRASH
+#else
+#define KEXEC_FLAGS    (KEXEC_ON_CRASH | KEXEC_PRESERVE_CONTEXT)
+#endif
 
 #define VMCOREINFO_BYTES           (4096)
 #define VMCOREINFO_NOTE_NAME       "VMCOREINFO"