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, 65 insertions, 23 deletions

diff --git a/kernel/kexec.c b/kernel/kexec.c
index 6db42ff8d52..a0d920915b3 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -24,6 +24,8 @@
 #include <linux/utsrelease.h>
 #include <linux/utsname.h>
 #include <linux/numa.h>
+#include <linux/suspend.h>
+#include <linux/device.h>
 
 #include <asm/page.h>
 #include <asm/uaccess.h>
@@ -242,6 +244,12 @@ static int kimage_normal_alloc(struct kimage **rimage, unsigned long entry,
 		goto out;
 	}
 
+	image->swap_page = kimage_alloc_control_pages(image, 0);
+	if (!image->swap_page) {
+		printk(KERN_ERR "Could not allocate swap buffer\n");
+		goto out;
+	}
+
 	result = 0;
  out:
 	if (result == 0)
@@ -986,6 +994,8 @@ asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
 		if (result)
 			goto out;
 
+		if (flags & KEXEC_PRESERVE_CONTEXT)
+			image->preserve_context = 1;
 		result = machine_kexec_prepare(image);
 		if (result)
 			goto out;
@@ -1411,3 +1421,50 @@ static int __init crash_save_vmcoreinfo_init(void)
 }
 
 module_init(crash_save_vmcoreinfo_init)
+
+/**
+ *	kernel_kexec - reboot the system
+ *
+ *	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 (xchg(&kexec_lock, 1))
+		return -EBUSY;
+	if (!kexec_image) {
+		error = -EINVAL;
+		goto Unlock;
+	}
+
+	if (kexec_image->preserve_context) {
+#ifdef CONFIG_KEXEC_JUMP
+		local_irq_disable();
+		save_processor_state();
+#endif
+	} else {
+		blocking_notifier_call_chain(&reboot_notifier_list,
+					     SYS_RESTART, NULL);
+		system_state = SYSTEM_RESTART;
+		device_shutdown();
+		sysdev_shutdown();
+		printk(KERN_EMERG "Starting new kernel\n");
+		machine_shutdown();
+	}
+
+	machine_kexec(kexec_image);
+
+	if (kexec_image->preserve_context) {
+#ifdef CONFIG_KEXEC_JUMP
+		restore_processor_state();
+		local_irq_enable();
+#endif
+	}
+
+ Unlock:
+	xchg(&kexec_lock, 0);
+
+	return error;
+}
diff --git a/kernel/sys.c b/kernel/sys.c
index 0c9d3fa1f5f..c01858090a9 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -301,26 +301,6 @@ void kernel_restart(char *cmd)
 }
 EXPORT_SYMBOL_GPL(kernel_restart);
 
-/**
- *	kernel_kexec - reboot the system
- *
- *	Move into place and start executing a preloaded standalone
- *	executable.  If nothing was preloaded return an error.
- */
-static void kernel_kexec(void)
-{
-#ifdef CONFIG_KEXEC
-	struct kimage *image;
-	image = xchg(&kexec_image, NULL);
-	if (!image)
-		return;
-	kernel_restart_prepare(NULL);
-	printk(KERN_EMERG "Starting new kernel\n");
-	machine_shutdown();
-	machine_kexec(image);
-#endif
-}
-
 static void kernel_shutdown_prepare(enum system_states state)
 {
 	blocking_notifier_call_chain(&reboot_notifier_list,
@@ -425,10 +405,15 @@ asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user
 		kernel_restart(buffer);
 		break;
 
+#ifdef CONFIG_KEXEC
 	case LINUX_REBOOT_CMD_KEXEC:
-		kernel_kexec();
-		unlock_kernel();
-		return -EINVAL;
+		{
+			int ret;
+			ret = kernel_kexec();
+			unlock_kernel();
+			return ret;
+		}
+#endif
 
 #ifdef CONFIG_HIBERNATION
 	case LINUX_REBOOT_CMD_SW_SUSPEND: