kexec based hibernation -v5: kexec jump

Index: linux-2.6.23-rc8/arch/i386/kernel/machine_kexec.c
===================================================================
@@ -20,6 +20,7 @@
 #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;

@@ -83,10 +84,14 @@
  * reboot code buffer to allow us to avoid allocations
  * later.
  *
- * Currently nothing.
+ * Turn off NX bit for control page.
  */
 int machine_kexec_prepare(struct kimage *image)
 {
+	if (nx_enabled) {
+		change_page_attr(image->control_code_page, 1, PAGE_KERNEL_EXEC);
+		global_flush_tlb();
+	}
 	return 0;
 }
 

@@ -96,25 +101,50 @@
  */
 void machine_kexec_cleanup(struct kimage *image)
 {
+	if (nx_enabled) {
+		change_page_attr(image->control_code_page, 1, PAGE_KERNEL);
+		global_flush_tlb();
+	}
 }
 
 /*
  * 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 NORET_TYPE void
+		(*relocate_kernel_ptr)(unsigned long indirection_page,
+				       unsigned long control_page,
+				       unsigned long start_address,
+				       unsigned int has_pae) ATTRIB_NORET;
 
 	/* Interrupts aren't acceptable while we reboot */
 	local_irq_disable();
 
 	control_page = page_address(image->control_code_page);
-	memcpy(control_page, relocate_kernel, PAGE_SIZE);
+	memcpy(control_page, relocate_page, PAGE_SIZE/2);
 
+	if (image->jump_back) {
+		unsigned long pa_control_page;
+		pa_control_page = __pa(control_page);
+		memcpy(control_page + 1, &pa_control_page,
+		       sizeof(pa_control_page));
+		KJUMP_MAGIC(control_page) = KJUMP_MAGIC_NUMBER;
+		KJUMP_VERSION(control_page) = KJUMP_VERSION_NUMBER;
+
+		if (kexec_jump_save_cpu(control_page)) {
+			image->start = KJUMP_ENTRY(control_page);
+			return;
+		}
+	}
+
+	relocate_kernel_ptr = control_page +
+		((void *)relocate_kernel - (void *)relocate_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

@@ -127,6 +157,7 @@
 	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

@@ -145,8 +176,9 @@
 	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);
+	relocate_kernel_ptr((unsigned long)image->head,
+			    (unsigned long)page_list,
+			    image->start, cpu_has_pae);
 }
 
 void arch_crash_save_vmcoreinfo(void)

57 lines not on this page · raw message

Index: linux-2.6.23-rc8/include/linux/kexec.h
===================================================================
@@ -83,6 +83,7 @@
 
 	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 +99,21 @@
 	unsigned int type : 1;
 #define KEXEC_TYPE_DEFAULT 0
 #define KEXEC_TYPE_CRASH   1
+	unsigned int jump_back : 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 void kimage_free(struct kimage *image);
+extern int kexec_jump(struct kimage *image);
 #ifdef CONFIG_COMPAT
 extern asmlinkage long compat_sys_kexec_load(unsigned long entry,
 				unsigned long nr_segments,

@@ -153,6 +157,7 @@
 #endif
 
 #define KEXEC_ON_CRASH  0x00000001
+#define KEXEC_JUMP_BACK 0x00000002
 #define KEXEC_ARCH_MASK 0xffff0000
 
 /* These values match the ELF architecture values.

@@ -170,7 +175,8 @@
 #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_JUMP_BACK)
 
 #define VMCOREINFO_BYTES           (4096)
 #define VMCOREINFO_NOTE_NAME       "VMCOREINFO"

83 lines not on this page · raw message

Index: linux-2.6.23-rc8/kernel/sys.c
===================================================================
@@ -300,17 +300,25 @@
  *	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)
 {
 #ifdef CONFIG_KEXEC
 	struct kimage *image;
+	int ret;
 	image = xchg(&kexec_image, NULL);
 	if (!image)
-		return;
+		return -EINVAL;
+	if (image->jump_back) {
+		ret = kexec_jump(image);
+		image = xchg(&kexec_image, image);
+		kimage_free(image);
+		return ret;
+	}
 	kernel_restart_prepare(NULL);
 	printk(KERN_EMERG "Starting new kernel\n");
 	machine_shutdown();
 	machine_kexec(image);
+	return -EINVAL;
 #endif
 }
 

@@ -418,9 +426,12 @@
 		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:

Index: linux-2.6.23-rc8/arch/ppc/kernel/machine_kexec.c
===================================================================
@@ -66,7 +66,7 @@
  * 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);

Index: linux-2.6.23-rc8/arch/x86_64/kernel/machine_kexec.c
===================================================================
@@ -179,7 +179,7 @@
  * 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;

Index: linux-2.6.23-rc8/arch/sh/kernel/machine_kexec.c
===================================================================
@@ -70,7 +70,7 @@
  * 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;

Index: linux-2.6.23-rc8/arch/powerpc/kernel/machine_kexec.c
===================================================================
@@ -47,7 +47,7 @@
  * 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);