[PATCH] kexec: add kexec syscalls

This patch introduces the architecture independent implementation the
sys_kexec_load, the compat_sys_kexec_load system calls.

Kexec on panic support has been integrated into the core patch and is
relatively clean.

In addition the hopefully architecture independent option
crashkernel=size@location has been docuemented.  It's purpose is to reserve
space for the panic kernel to live, and where no DMA transfer will ever be
setup to access.

Signed-off-by: Eric Biederman <ebiederm@xmission.com>
Signed-off-by: Alexander Nyberg <alexn@telia.com>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Vivek Goyal <vgoyal@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

kernel/Makefile

@@ -17,6 +17,7 @@ obj-$(CONFIG_MODULES) += module.o
 obj-$(CONFIG_KALLSYMS) += kallsyms.o
 obj-$(CONFIG_PM) += power/
 obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o
+obj-$(CONFIG_KEXEC) += kexec.o
 obj-$(CONFIG_COMPAT) += compat.o
 obj-$(CONFIG_CPUSETS) += cpuset.o
 obj-$(CONFIG_IKCONFIG) += configs.o

kernel/panic.c

@@ -18,6 +18,7 @@
 #include <linux/sysrq.h>
 #include <linux/interrupt.h>
 #include <linux/nmi.h>
+#include <linux/kexec.h>
 
 int panic_timeout;
 int panic_on_oops;
@@ -63,6 +64,13 @@ NORET_TYPE void panic(const char * fmt, ...)
         unsigned long caller = (unsigned long) __builtin_return_address(0);
 #endif
 
+	/*
+	 * It's possible to come here directly from a panic-assertion and not
+	 * have preempt disabled. Some functions called from here want
+	 * preempt to be disabled. No point enabling it later though...
+	 */
+	preempt_disable();
+
 	bust_spinlocks(1);
 	va_start(args, fmt);
 	vsnprintf(buf, sizeof(buf), fmt, args);
@@ -70,7 +78,19 @@ NORET_TYPE void panic(const char * fmt, ...)
 	printk(KERN_EMERG "Kernel panic - not syncing: %s\n",buf);
 	bust_spinlocks(0);
 
+	/*
+	 * If we have crashed and we have a crash kernel loaded let it handle
+	 * everything else.
+	 * Do we want to call this before we try to display a message?
+	 */
+	crash_kexec();
+
 #ifdef CONFIG_SMP
+	/*
+	 * Note smp_send_stop is the usual smp shutdown function, which
+	 * unfortunately means it may not be hardened to work in a panic
+	 * situation.
+	 */
 	smp_send_stop();
 #endif
 
@@ -79,8 +99,7 @@ NORET_TYPE void panic(const char * fmt, ...)
 	if (!panic_blink)
 		panic_blink = no_blink;
 
-	if (panic_timeout > 0)
-	{
+	if (panic_timeout > 0) {
 		/*
 	 	 * Delay timeout seconds before rebooting the machine. 
 		 * We can't use the "normal" timers since we just panicked..

kernel/sys.c

@@ -16,6 +16,8 @@
 #include <linux/init.h>
 #include <linux/highuid.h>
 #include <linux/fs.h>
+#include <linux/kernel.h>
+#include <linux/kexec.h>
 #include <linux/workqueue.h>
 #include <linux/device.h>
 #include <linux/key.h>
@@ -439,6 +441,24 @@ asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user
 		machine_restart(buffer);
 		break;
 
+#ifdef CONFIG_KEXEC
+	case LINUX_REBOOT_CMD_KEXEC:
+	{
+		struct kimage *image;
+		image = xchg(&kexec_image, 0);
+		if (!image) {
+			unlock_kernel();
+			return -EINVAL;
+		}
+		notifier_call_chain(&reboot_notifier_list, SYS_RESTART, NULL);
+		system_state = SYSTEM_RESTART;
+		device_shutdown();
+		printk(KERN_EMERG "Starting new kernel\n");
+		machine_shutdown();
+		machine_kexec(image);
+		break;
+	}
+#endif
 #ifdef CONFIG_SOFTWARE_SUSPEND
 	case LINUX_REBOOT_CMD_SW_SUSPEND:
 		{

kernel/sys_ni.c

@@ -18,6 +18,8 @@ cond_syscall(sys_acct);
 cond_syscall(sys_lookup_dcookie);
 cond_syscall(sys_swapon);
 cond_syscall(sys_swapoff);
+cond_syscall(sys_kexec_load);
+cond_syscall(compat_sys_kexec_load);
 cond_syscall(sys_init_module);
 cond_syscall(sys_delete_module);
 cond_syscall(sys_socketpair);