kexec jump -v11: kexec jump

@@ -22,6 +22,7 @@
 #include <asm/cpufeature.h>
 #include <asm/desc.h>
 #include <asm/system.h>
+#include <asm/cacheflush.h>
 
 #define PAGE_ALIGNED __attribute__ ((__aligned__(PAGE_SIZE)))
 static u32 kexec_pgd[1024] PAGE_ALIGNED;

@@ -85,10 +86,12 @@ static void load_segments(void)
  * reboot code buffer to allow us to avoid allocations
  * later.
  *
- * Currently nothing.
+ * Make control page executable.
  */
 int machine_kexec_prepare(struct kimage *image)
 {
+	if (nx_enabled)
+		set_pages_x(image->control_code_page, 1);
 	return 0;
 }
 

@@ -98,16 +101,24 @@ int machine_kexec_prepare(struct kimage 
  */
 void machine_kexec_cleanup(struct kimage *image)
 {
+	if (nx_enabled)
+		set_pages_nx(image->control_code_page, 1);
 }
 
 /*
  * Do not allocate memory (or fail in any way) in machine_kexec().
  * We are past the point of no return, committed to rebooting now.
  */
-NORET_TYPE void machine_kexec(struct kimage *image)
+void machine_kexec(struct kimage *image)
 {
 	unsigned long page_list[PAGES_NR];
 	void *control_page;
+	asmlinkage unsigned long
+		(*relocate_kernel_ptr)(unsigned long indirection_page,
+				       unsigned long control_page,
+				       unsigned long start_address,
+				       unsigned int has_pae,
+				       unsigned int preserve_context);
 
 	tracer_disable();
 

@@ -115,10 +126,11 @@ NORET_TYPE void machine_kexec(struct kim
 	local_irq_disable();
 
 	control_page = page_address(image->control_code_page);
-	memcpy(control_page, relocate_kernel, PAGE_SIZE);
+	memcpy(control_page, relocate_kernel, PAGE_SIZE/2);
 
+	relocate_kernel_ptr = control_page;
 	page_list[PA_CONTROL_PAGE] = __pa(control_page);
-	page_list[VA_CONTROL_PAGE] = (unsigned long)relocate_kernel;
+	page_list[VA_CONTROL_PAGE] = (unsigned long)control_page;
 	page_list[PA_PGD] = __pa(kexec_pgd);
 	page_list[VA_PGD] = (unsigned long)kexec_pgd;
 #ifdef CONFIG_X86_PAE

@@ -131,6 +143,7 @@ NORET_TYPE void machine_kexec(struct kim
 	page_list[VA_PTE_0] = (unsigned long)kexec_pte0;
 	page_list[PA_PTE_1] = __pa(kexec_pte1);
 	page_list[VA_PTE_1] = (unsigned long)kexec_pte1;
+	page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page) << PAGE_SHIFT);
 
 	/* The segment registers are funny things, they have both a
 	 * visible and an invisible part.  Whenever the visible part is

@@ -149,8 +162,10 @@ NORET_TYPE void machine_kexec(struct kim
 	set_idt(phys_to_virt(0),0);
 
 	/* now call it */
-	relocate_kernel((unsigned long)image->head, (unsigned long)page_list,
-			image->start, cpu_has_pae);
+	image->start = relocate_kernel_ptr((unsigned long)image->head,
+					   (unsigned long)page_list,
+					   image->start, cpu_has_pae,
+					   image->preserve_context);
 }
 
 void arch_crash_save_vmcoreinfo(void)

@@ -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 kexec_jump(struct kimage *image);
 #ifdef CONFIG_COMPAT
 extern asmlinkage long compat_sys_kexec_load(unsigned long entry,
 				unsigned long nr_segments,

@@ -151,13 +154,15 @@ unsigned long paddr_vmcoreinfo_note(void
 
 extern struct kimage *kexec_image;
 extern struct kimage *kexec_crash_image;
+extern int kexec_lock;
 
 #ifndef kexec_flush_icache_page
 #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 +179,8 @@ 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 */
+#define KEXEC_FLAGS    (KEXEC_ON_CRASH | KEXEC_PRESERVE_CONTEXT)
 
 #define VMCOREINFO_BYTES           (4096)
 #define VMCOREINFO_NOTE_NAME       "VMCOREINFO"

@@ -24,6 +24,7 @@
 #include <linux/utsrelease.h>
 #include <linux/utsname.h>
 #include <linux/numa.h>
+#include <linux/suspend.h>
 
 #include <asm/page.h>
 #include <asm/uaccess.h>

@@ -242,6 +243,12 @@ static int kimage_normal_alloc(struct ki
 		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)

@@ -919,7 +926,7 @@ struct kimage *kexec_crash_image;
  * Nothing can wait so this mutex is safe to use
  * in interrupt context :)
  */
-static int kexec_lock;
+int kexec_lock;
 
 asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
 				struct kexec_segment __user *segments,

@@ -988,6 +995,8 @@ asmlinkage long sys_kexec_load(unsigned 
 		if (result)
 			goto out;
 
+		if (flags & KEXEC_PRESERVE_CONTEXT)
+			image->preserve_context = 1;
 		result = machine_kexec_prepare(image);
 		if (result)
 			goto out;

@@ -1415,3 +1424,19 @@ static int __init crash_save_vmcoreinfo_
 }
 
 module_init(crash_save_vmcoreinfo_init)
+
+int kexec_jump(struct kimage *image)
+{
+	if (image->preserve_context) {
+		local_irq_disable();
+		save_processor_state();
+	}
+
+	machine_kexec(image);
+
+	if (image->preserve_context) {
+		restore_processor_state();
+		local_irq_enable();
+	}
+	return 0;
+}

@@ -307,18 +307,26 @@ EXPORT_SYMBOL_GPL(kernel_restart);
  *	Move into place and start executing a preloaded standalone
  *	executable.  If nothing was preloaded return an error.
  */
-static void kernel_kexec(void)
+static int kernel_kexec(void)
 {
+	int ret = -ENOSYS;
 #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);
+	if (xchg(&kexec_lock, 1))
+		return -EBUSY;
+	if (!kexec_image) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+	if (!kexec_image->preserve_context) {
+		kernel_restart_prepare(NULL);
+		printk(KERN_EMERG "Starting new kernel\n");
+		machine_shutdown();
+	}
+	kexec_jump(kexec_image);
+unlock:
+	xchg(&kexec_lock, 0);
 #endif
+	return ret;
 }
 
 static void kernel_shutdown_prepare(enum system_states state)

@@ -426,9 +434,12 @@ asmlinkage long sys_reboot(int magic1, i
 		break;
 
 	case LINUX_REBOOT_CMD_KEXEC:
-		kernel_kexec();
-		unlock_kernel();
-		return -EINVAL;
+		{
+			int ret;
+			ret = kernel_kexec();
+			unlock_kernel();
+			return ret;
+		}
 
 #ifdef CONFIG_HIBERNATION
 	case LINUX_REBOOT_CMD_SW_SUSPEND:

@@ -66,7 +66,7 @@ void machine_kexec_cleanup(struct kimage
  * Do not allocate memory (or fail in any way) in machine_kexec().
  * We are past the point of no return, committed to rebooting now.
  */
-NORET_TYPE void machine_kexec(struct kimage *image)
+void machine_kexec(struct kimage *image)
 {
 	if (ppc_md.machine_kexec)
 		ppc_md.machine_kexec(image);

@@ -181,7 +181,7 @@ void machine_kexec_cleanup(struct kimage
  * Do not allocate memory (or fail in any way) in machine_kexec().
  * We are past the point of no return, committed to rebooting now.
  */
-NORET_TYPE void machine_kexec(struct kimage *image)
+void machine_kexec(struct kimage *image)
 {
 	unsigned long page_list[PAGES_NR];
 	void *control_page;

@@ -70,7 +70,7 @@ static void kexec_info(struct kimage *im
  * Do not allocate memory (or fail in any way) in machine_kexec().
  * We are past the point of no return, committed to rebooting now.
  */
-NORET_TYPE void machine_kexec(struct kimage *image)
+void machine_kexec(struct kimage *image)
 {
 
 	unsigned long page_list;

@@ -48,7 +48,7 @@ void machine_kexec_cleanup(struct kimage
  * Do not allocate memory (or fail in any way) in machine_kexec().
  * We are past the point of no return, committed to rebooting now.
  */
-NORET_TYPE void machine_kexec(struct kimage *image)
+void machine_kexec(struct kimage *image)
 {
 	if (ppc_md.machine_kexec)
 		ppc_md.machine_kexec(image);

@@ -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(stru
 }
 
 #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,